@Preamble{"\input bibnames.sty" #
"\def \TM {${}^{\sc TM}$}"
}
@String{ack-nhfb = "Nelson H. F. Beebe,
University of Utah,
Department of Mathematics, 110 LCB,
155 S 1400 E RM 233,
Salt Lake City, UT 84112-0090, USA,
Tel: +1 801 581 5254,
FAX: +1 801 581 4148,
e-mail: \path|beebe@math.utah.edu|,
\path|beebe@acm.org|,
\path|beebe@computer.org| (Internet),
URL: \path|https://www.math.utah.edu/~beebe/|"}
@String{j-TOPC = "ACM Transactions on Parallel Computing
(TOPC)"}
@Article{Gibbons:2014:ATP,
author = "Phillip B. Gibbons",
title = "{ACM Transactions on Parallel Computing}: an
introduction",
journal = j-TOPC,
volume = "1",
number = "1",
pages = "1:1--1:??",
month = sep,
year = "2014",
CODEN = "????",
DOI = "https://doi.org/10.1145/2661651",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Oct 17 12:28:03 MDT 2014",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Techniques",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "1",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Lilja:2014:I,
author = "David J. Lilja",
title = "Introduction",
journal = j-TOPC,
volume = "1",
number = "1",
pages = "2:1--2:??",
month = sep,
year = "2014",
CODEN = "????",
DOI = "https://doi.org/10.1145/2609798",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Oct 17 12:28:03 MDT 2014",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "2",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Rane:2014:EPO,
author = "Ashay Rane and James Browne",
title = "Enhancing Performance Optimization of Multicore\slash
Multichip Nodes with Data Structure Metrics",
journal = j-TOPC,
volume = "1",
number = "1",
pages = "3:1--3:??",
month = sep,
year = "2014",
CODEN = "????",
DOI = "https://doi.org/10.1145/2588788",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Oct 17 12:28:03 MDT 2014",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Program performance optimization is usually based
solely on measurements of execution behavior of code
segments using hardware performance counters. However,
memory access patterns are critical performance
limiting factors for today's multicore chips where
performance is highly memory bound. Therefore diagnoses
and selection of optimizations based only on
measurements of the execution behavior of code segments
are incomplete because they do not incorporate
knowledge of memory access patterns and behaviors. This
article presents a low-overhead tool (MACPO) that
captures memory traces and computes metrics for the
memory access behavior of source-level (C, C++,
Fortran) data structures. MACPO explicitly targets the
measurement and metrics important to performance
optimization for multicore chips. The article also
presents a complete process for integrating measurement
and analyses of code execution with measurements and
analyses of memory access patterns and behaviors for
performance optimization, specifically targeting
multicore chips and multichip nodes of clusters. MACPO
uses more realistic cache models for computation of
latency metrics than those used by previous tools.
Evaluation of the effectiveness of adding memory access
behavior characteristics of data structures to
performance optimization was done on subsets of the
ASCI, NAS and Rodinia parallel benchmarks and two
versions of one application program from a domain not
represented in these benchmarks. Adding characteristics
of the behavior of data structures enabled easier
diagnoses of bottlenecks and more accurate selection of
appropriate optimizations than with only code centric
behavior measurements. The performance gains ranged
from a few percent to 38 percent.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "3",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Jimenez:2014:APP,
author = "V{\'\i}ctor Jim{\'e}nez and Francisco J. Cazorla and
Roberto Gioiosa and Alper Buyuktosunoglu and Pradip
Bose and Francis P. O'Connell and Bruce G. Mealey",
title = "Adaptive Prefetching on {POWER7}: Improving
Performance and Power Consumption",
journal = j-TOPC,
volume = "1",
number = "1",
pages = "4:1--4:??",
month = sep,
year = "2014",
CODEN = "????",
DOI = "https://doi.org/10.1145/2588889",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Oct 17 12:28:03 MDT 2014",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Hardware data prefetch engines are integral parts of
many general purpose server-class microprocessors in
the field today. Some prefetch engines allow users to
change some of their parameters. But, the prefetcher is
usually enabled in a default configuration during
system bring-up, and dynamic reconfiguration of the
prefetch engine is not an autonomic feature of current
machines. Conceptually, however, it is easy to infer
that commonly used prefetch algorithms---when applied
in a fixed mode---will not help performance in many
cases. In fact, they may actually degrade performance
due to useless bus bandwidth consumption and cache
pollution, which in turn, will also waste power. We
present an adaptive prefetch scheme that dynamically
modifies the prefetch settings in order to adapt to
workloads' requirements. We use a commercial processor,
namely the IBM POWER7 as a vehicle for our study. First
we characterize---in terms of performance and power
consumption---the prefetcher in that processor using
microbenchmarks and SPEC CPU2006. We then present our
adaptive prefetch mechanism showing performance
improvements with respect to the default prefetch
setting up to 2.7X and 1.3X for single-threaded and
multiprogrammed workloads, respectively. Adaptive
prefetching is also able to reduce power consumption in
some cases. Finally, we also evaluate our mechanism
with SPECjbb2005, improving both performance and power
consumption.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "4",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Heil:2014:APH,
author = "Timothy Heil and Anil Krishna and Nicholas Lindberg
and Farnaz Toussi and Steven Vanderwiel",
title = "Architecture and Performance of the Hardware
Accelerators in {IBM}'s {PowerEN} Processor",
journal = j-TOPC,
volume = "1",
number = "1",
pages = "5:1--5:??",
month = sep,
year = "2014",
CODEN = "????",
DOI = "https://doi.org/10.1145/2588888",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Oct 17 12:28:03 MDT 2014",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Computation at the edge of a datacenter has unique
characteristics. It deals with streaming data from
multiple sources, going to multiple destinations, often
requiring repeated application of one or more of
several standard algorithmic kernels. These kernels,
related to encryption, compression, XML Parsing and
regular expression searching on the data, demand a high
data processing rate and power efficiency. This
suggests the use of hardware acceleration for key
functions. However, robust general purpose processing
support is necessary to orchestrate the flow of data
between accelerators, as well as perform tasks that are
not suited to acceleration. Further, these accelerators
must be tightly integrated with the general purpose
computation in order to keep invocation overhead and
latency low. The accelerators must be easy for software
to use, and the system must be flexible enough to
support evolving networking standards. In this article,
we describe and evaluate the architecture of IBM's
PowerEN processor, with a focus on PowerEN's
architectural enhancements and its on-chip hardware
accelerators. PowerEN unites the throughput of
application-specific accelerators with the
programmability of general purpose cores on a single
coherent memory architecture. Hardware acceleration
improves throughput by orders of magnitude in some
cases compared to equivalent computation on the general
purpose cores. By offloading work to the accelerators,
general purpose cores are freed to simultaneously work
on computation less suited to acceleration.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "5",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Wu:2014:MAG,
author = "Xing Wu and Frank Mueller and Scott Pakin",
title = "A methodology for automatic generation of executable
communication specifications from parallel {MPI}
applications",
journal = j-TOPC,
volume = "1",
number = "1",
pages = "6:1--6:??",
month = sep,
year = "2014",
CODEN = "????",
DOI = "https://doi.org/10.1145/2660249",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Oct 17 12:28:03 MDT 2014",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Portable parallel benchmarks are widely used for
performance evaluation of HPC systems. However, because
these are manually produced, they generally represent a
greatly simplified view of application behavior,
missing the subtle but important-to-performance nuances
that may exist in a complete application. This work
contributes novel methods to automatically generate
highly portable and customizable communication
benchmarks from HPC applications. We utilize
ScalaTrace, a lossless yet scalable
parallel-application tracing framework to collect
selected aspects of the run-time behavior of HPC
applications, including communication operations and
computation time, while abstracting away the details of
the computation proper. We subsequently generate
benchmarks with nearly identical run-time behavior to
the original applications. Results demonstrate that the
generated benchmarks are in fact able to preserve the
run-time behavior (including both the communication
pattern and the execution time) of the original
applications. Such automated benchmark generation is
without precedent and particularly valuable for
proprietary, export-controlled, or classified
application codes.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "6",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Ravishankar:2014:APC,
author = "Mahesh Ravishankar and John Eisenlohr and
Louis-No{\"e}l Pouchet and J. Ramanujam and Atanas
Rountev and P. Sadayappan",
title = "Automatic parallelization of a class of irregular
loops for distributed memory systems",
journal = j-TOPC,
volume = "1",
number = "1",
pages = "7:1--7:??",
month = sep,
year = "2014",
CODEN = "????",
DOI = "https://doi.org/10.1145/2660251",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Oct 17 12:28:03 MDT 2014",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Many scientific applications spend significant time
within loops that are parallel, except for dependences
from associative reduction operations. However these
loops often contain data-dependent control-flow and
array-access patterns. Traditional optimizations that
rely on purely static analysis fail to generate
parallel code in such cases. This article proposes an
approach for automatic parallelization for distributed
memory environments, using both static and runtime
analysis. We formalize the computations that are
targeted by this approach and develop algorithms to
detect such computations. We also describe algorithms
to generate a parallel inspector that performs a
runtime analysis of control-flow and array-access
patterns, and a parallel executor to take advantage of
this information. The effectiveness of the approach is
demonstrated on several benchmarks that were
automatically transformed using a prototype compiler.
For these, the inspector overheads and performance of
the executor code were measured. The benefit on
real-world applications was also demonstrated through
similar manual transformations of an atmospheric
modeling software.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "7",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Shun:2014:SPC,
author = "Julian Shun and Guy E. Blelloch",
title = "A simple parallel {Cartesian} tree algorithm and its
application to parallel suffix tree construction",
journal = j-TOPC,
volume = "1",
number = "1",
pages = "8:1--8:??",
month = sep,
year = "2014",
CODEN = "????",
DOI = "https://doi.org/10.1145/2661653",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Oct 17 12:28:03 MDT 2014",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "We present a simple linear work and space, and
polylogarithmic time parallel algorithm for generating
multiway Cartesian trees. We show that bottom-up
traversals of the multiway Cartesian tree on the
interleaved suffix array and longest common prefix
array of a string can be used to answer certain string
queries. By adding downward pointers in the tree (e.g.
using a hash table), we can also generate suffix trees
from suffix arrays on arbitrary alphabets in the same
bounds. In conjunction with parallel suffix array
algorithms, such as the skew algorithm, this gives a
rather simple linear work parallel, $ O(n \epsilon) $
time $ (0 < \epsilon < 1) $, algorithm for generating
suffix trees over an integer alphabet $ \Sigma \{ 1,
\ldots {}, n \} $, where $n$ is the length of the input
string. It also gives a linear work parallel algorithm
requiring $ O(\log_2 n) $ time with high probability
for constant-sized alphabets. More generally, given a
sorted sequence of strings and the longest common
prefix lengths between adjacent elements, the algorithm
will generate a patricia tree (compacted trie) over the
strings. Of independent interest, we describe a
work-efficient parallel algorithm for solving the all
nearest smaller values problem using Cartesian trees,
which is much simpler than the work-efficient parallel
algorithm described in previous work. We also present
experimental results comparing the performance of the
algorithm to existing sequential implementations and a
second parallel algorithm that we implement. We present
comparisons for the Cartesian tree algorithm on its own
and for constructing a suffix tree. The results show
that on a variety of strings our algorithm is
competitive with the sequential version on a single
processor and achieves good speedup on multiple
processors. We present experiments for three
applications that require only the Cartesian tree, and
also for searching using the suffix tree.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "8",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Pingali:2015:ISI,
author = "Keshav Pingali and J. Ramanujam and P. Sadayappan",
title = "Introduction to the Special Issue on {PPoPP'12}",
journal = j-TOPC,
volume = "1",
number = "2",
pages = "9:1--9:??",
month = jan,
year = "2015",
CODEN = "????",
DOI = "https://doi.org/10.1145/2716343",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Feb 18 16:46:00 MST 2015",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "9",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Bouteiller:2015:ABF,
author = "Aurelien Bouteiller and Thomas Herault and George
Bosilca and Peng Du and Jack Dongarra",
title = "Algorithm-Based Fault Tolerance for Dense Matrix
Factorizations, Multiple Failures and Accuracy",
journal = j-TOPC,
volume = "1",
number = "2",
pages = "10:1--10:??",
month = jan,
year = "2015",
CODEN = "????",
DOI = "https://doi.org/10.1145/2686892",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Feb 18 16:46:00 MST 2015",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/bibnet/authors/d/dongarra-jack-j.bib;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Dense matrix factorizations, such as LU, Cholesky and
QR, are widely used for scientific applications that
require solving systems of linear equations,
eigenvalues and linear least squares problems. Such
computations are normally carried out on
supercomputers, whose ever-growing scale induces a fast
decline of the Mean Time To Failure (MTTF). This
article proposes a new hybrid approach, based on
Algorithm-Based Fault Tolerance (ABFT), to help matrix
factorizations algorithms survive fail-stop failures.
We consider extreme conditions, such as the absence of
any reliable node and the possibility of losing both
data and checksum from a single failure. We will
present a generic solution for protecting the right
factor, where the updates are applied, of all above
mentioned factorizations. For the left factor, where
the panel has been applied, we propose a scalable
checkpointing algorithm. This algorithm features high
degree of checkpointing parallelism and cooperatively
utilizes the checksum storage leftover from the right
factor protection. The fault-tolerant algorithms
derived from this hybrid solution is applicable to a
wide range of dense matrix factorizations, with minor
modifications. Theoretical analysis shows that the
fault tolerance overhead decreases inversely to the
scaling in the number of computing units and the
problem size. Experimental results of LU and QR
factorization on the Kraken (Cray XT5) supercomputer
validate the theoretical evaluation and confirm
negligible overhead, with- and without-errors.
Applicability to tolerate multiple failures and
accuracy after multiple recovery is also considered.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "10",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Ballard:2015:ACS,
author = "Grey Ballard and James Demmel and Nicholas Knight",
title = "Avoiding Communication in Successive Band Reduction",
journal = j-TOPC,
volume = "1",
number = "2",
pages = "11:1--11:??",
month = jan,
year = "2015",
CODEN = "????",
DOI = "https://doi.org/10.1145/2686877",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Feb 18 16:46:00 MST 2015",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "The running time of an algorithm depends on both
arithmetic and communication (i.e., data movement)
costs, and the relative costs of communication are
growing over time. In this work, we present sequential
and distributed-memory parallel algorithms for
tridiagonalizing full symmetric and symmetric band
matrices that asymptotically reduce communication
compared to previous approaches. The tridiagonalization
of a symmetric band matrix is a key kernel in solving
the symmetric eigenvalue problem for both full and band
matrices. In order to preserve structure,
tridiagonalization routines use annihilate-and-chase
procedures that previously have suffered from poor data
locality and high parallel latency cost. We improve
both by reorganizing the computation and obtain
asymptotic improvements. We also propose new algorithms
for reducing a full symmetric matrix to band form in a
communication-efficient manner. In this article, we
consider the cases of computing eigenvalues only and of
computing eigenvalues and all eigenvectors.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "11",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Sack:2015:CAM,
author = "Paul Sack and William Gropp",
title = "Collective Algorithms for Multiported Torus Networks",
journal = j-TOPC,
volume = "1",
number = "2",
pages = "12:1--12:??",
month = jan,
year = "2015",
CODEN = "????",
DOI = "https://doi.org/10.1145/2686882",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Feb 18 16:46:00 MST 2015",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Modern supercomputers with torus networks allow each
node to simultaneously pass messages on all of its
links. However, most collective algorithms are designed
to only use one link at a time. In this work, we
present novel multiported algorithms for the scatter,
gather, all-gather, and reduce-scatter operations. Our
algorithms can be combined to create multiported
reduce, all-reduce, and broadcast algorithms. Several
of these algorithms involve a new technique where we
relax the MPI message-ordering constraints to achieve
high performance and restore the correct ordering using
an additional stage of redundant communication.
According to our models, on an $n$-dimensional torus,
our algorithms should allow for nearly a $ 2 n$-fold
improvement in communication performance compared to
known, single-ported torus algorithms. In practice, we
have achieved nearly $ 6 \times $ better performance on
a 32k-node 3-dimensional torus.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "12",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Dice:2015:LCG,
author = "David Dice and Virendra J. Marathe and Nir Shavit",
title = "Lock Cohorting: a General Technique for Designing
{NUMA} Locks",
journal = j-TOPC,
volume = "1",
number = "2",
pages = "13:1--13:??",
month = jan,
year = "2015",
CODEN = "????",
DOI = "https://doi.org/10.1145/2686884",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Feb 18 16:46:00 MST 2015",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Multicore machines are quickly shifting to NUMA and
CC-NUMA architectures, making scalable NUMA-aware
locking algorithms, ones that take into account the
machine's nonuniform memory and caching hierarchy, ever
more important. This article presents lock cohorting, a
general new technique for designing NUMA-aware locks
that is as simple as it is powerful. Lock cohorting
allows one to transform any spin-lock algorithm, with
minimal nonintrusive changes,into a scalable NUMA-aware
spin-lock. Our new cohorting technique allows us to
easily create NUMA-aware versions of the TATAS-Backoff,
CLH, MCS, and ticket locks, to name a few. Moreover, it
allows us to derive a CLH-based cohort abortable lock,
the first NUMA-aware queue lock to support
abortability. We empirically compared the performance
of cohort locks with prior NUMA-aware and classic
NUMA-oblivious locks on a synthetic micro-benchmark, a
real world key-value store application memcached, as
well as the libc memory allocator. Our results
demonstrate that cohort locks perform as well or better
than known locks when the load is low and significantly
out-perform them as the load increases.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "13",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Merrill:2015:HPS,
author = "Duane Merrill and Michael Garland and Andrew
Grimshaw",
title = "High-Performance and Scalable {GPU} Graph Traversal",
journal = j-TOPC,
volume = "1",
number = "2",
pages = "14:1--14:??",
month = jan,
year = "2015",
CODEN = "????",
DOI = "https://doi.org/10.1145/2717511",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Feb 18 16:46:00 MST 2015",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Breadth-First Search (BFS) is a core primitive for
graph traversal and a basis for many higher-level graph
analysis algorithms. It is also representative of a
class of parallel computations whose memory accesses
and work distribution are both irregular and data
dependent. Recent work has demonstrated the
plausibility of GPU sparse graph traversal, but has
tended to focus on asymptotically inefficient
algorithms that perform poorly on graphs with
nontrivial diameter. We present a BFS parallelization
focused on fine-grained task management constructed
from efficient prefix sum computations that achieves an
asymptotically optimal O(|V| + |E|) gd work complexity.
Our implementation delivers excellent performance on
diverse graphs, achieving traversal rates in excess of
3.3 billion and 8.3 billion traversed edges per second
using single- and quad-GPU configurations,
respectively. This level of performance is several
times faster than state-of-the-art implementations on
both CPU and GPU platforms.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "14",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Kramer:2015:SET,
author = "Stephan C. Kramer and Johannes Hagemann",
title = "{SciPAL}: Expression Templates and Composition Closure
Objects for High Performance Computational Physics with
{CUDA} and {OpenMP}",
journal = j-TOPC,
volume = "1",
number = "2",
pages = "15:1--15:??",
month = jan,
year = "2015",
CODEN = "????",
DOI = "https://doi.org/10.1145/2686886",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Feb 18 16:46:00 MST 2015",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "We present SciPAL (scientific parallel algorithms
library), a C ++-based, hardware-independent
open-source library. Its core is a domain-specific
embedded language for numerical linear algebra. The
main fields of application are finite element
simulations, coherent optics and the solution of
inverse problems. Using SciPAL algorithms can be stated
in a mathematically intuitive way in terms of matrix
and vector operations. Existing algorithms can easily
be adapted to GPU-based computing by proper template
specialization. Our library is compatible with the
finite element library deal.II and provides a port of
deal.II's most frequently used linear algebra classes
to CUDA (NVidia's extension of the programming
languages C and C ++ for programming their GPUs).
SciPAL 's operator-based API for BLAS operations
particularly aims at simplifying the usage of NVidia's
CUBLAS. For non-BLAS array arithmetic SciPAL 's
expression templates are able to generate CUDA kernels
at compile time. We demonstrate the benefits of SciPAL
using the iterative principal component analysis as
example which is the core algorithm for the
spike-sorting problem in neuroscience.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "15",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Totoni:2015:PME,
author = "Ehsan Totoni and Nikhil Jain and Laxmikant V. Kale",
title = "Power Management of Extreme-Scale Networks with
On\slash Off Links in Runtime Systems",
journal = j-TOPC,
volume = "1",
number = "2",
pages = "16:1--16:??",
month = jan,
year = "2015",
CODEN = "????",
DOI = "https://doi.org/10.1145/2687001",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Feb 18 16:46:00 MST 2015",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Networks are among major power consumers in
large-scale parallel systems. During execution of
common parallel applications, a sizeable fraction of
the links in the high-radix interconnects are either
never used or are underutilized. We propose a runtime
system based adaptive approach to turn off unused
links, which has various advantages over the previously
proposed hardware and compiler based approaches. We
discuss why the runtime system is the best system
component to accomplish this task, and test the
effectiveness of our approach using real applications
(including NAMD, MILC), and application benchmarks
(including NAS Parallel Benchmarks, Stencil). These
codes are simulated on representative topologies such
as 6-D Torus and multilevel directly connected network
(similar to IBM PERCS in Power 775 and Dragonfly in
Cray Aries). For common applications with near-neighbor
communication pattern, our approach can save up to 20\%
of total machine's power and energy, without any
performance penalty.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "16",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Herlihy:2015:GEI,
author = "Maurice Herlihy",
title = "{Guest Editor} Introduction",
journal = j-TOPC,
volume = "2",
number = "1",
pages = "1:1--1:??",
month = may,
year = "2015",
CODEN = "????",
DOI = "https://doi.org/10.1145/2716306",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Thu May 21 16:27:00 MDT 2015",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "1",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Degener:2015:LCS,
author = "Bastian Degener and Barbara Kempkes and Peter Kling
and Friedhelm {Meyer Auf Der Heide}",
title = "Linear and Competitive Strategies for Continuous Robot
Formation Problems",
journal = j-TOPC,
volume = "2",
number = "1",
pages = "2:1--2:??",
month = may,
year = "2015",
CODEN = "????",
DOI = "https://doi.org/10.1145/2742341",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Thu May 21 16:27:00 MDT 2015",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "We study a scenario in which n mobile robots with a
limited viewing range are distributed in the Euclidean
plane and have to solve a formation problem. The
formation problems we consider are the Gathering
problem and the Chain-Formation problem. In the
Gathering problem, the robots have to gather in one
(not predefined) point, while in the Chain-Formation
problem they have to form a connected communication
chain of minimal length between two stationary base
stations. Each robot may base its decisions where to
move only on the current relative positions of
neighboring robots (that are within its viewing range);
that is, besides having a limited viewing range, the
robots are oblivious (they do not use information from
the past), have none or only very limited identities,
and they do not have a common sense of direction.
Variants of these problems (especially for the
Gathering problem) have been studied extensively in
different discrete time models. In contrast, our work
focuses on a continuous time model; that is, the robots
continuously sense the positions of other robots within
their viewing range and continuously adapt their speed
and direction according to some simple, local rules.
Hereby, we assume that the robots have a maximum
movement speed of one. We show that this idealized idea
of continuous sensing allows us to solve the mentioned
formation problems in linear time $ O(n) $ (which,
given the maximum speed of one, immediately yields a
maximum traveled distance of $ O(n)$). Note that in the
more classical discrete time models, the best known
strategies need at least $ \Theta (n^2)$ or even $
\Theta (n^2 \log n)$ timesteps to solve these problems.
For the Gathering problem, our analysis solves a
problem left open by Gordon et al. [2004], where the
authors could prove that gathering in a continuous
model is possible in finite time, but were not able to
give runtime bounds. Apart from these linear bounds, we
also provide runtime bounds for both formation problems
that relate the runtime of our strategies to the
runtime of an optimal, global algorithm. Specifically,
we show that our strategy for the Gathering problem is
log OPT-competitive and the strategy for the
Chain-Formation problem is $ \log n$ competitive. Here,
by $c$-competitive, we mean that our (local) strategy
is asymptotically by at most a factor of $c$ slower
than an optimal, global strategy.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "2",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Jain:2015:NOS,
author = "Navendu Jain and Ishai Menache and Joseph (Seffi) Naor
and Jonathan Yaniv",
title = "Near-Optimal Scheduling Mechanisms for
Deadline-Sensitive Jobs in Large Computing Clusters",
journal = j-TOPC,
volume = "2",
number = "1",
pages = "3:1--3:??",
month = may,
year = "2015",
CODEN = "????",
DOI = "https://doi.org/10.1145/2742343",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Thu May 21 16:27:00 MDT 2015",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "We consider a market-based resource allocation model
for batch jobs in cloud computing clusters. In our
model, we incorporate the importance of the due date of
a job rather than the number of servers allocated to it
at any given time. Each batch job is characterized by
the work volume of total computing units (e.g., CPU
hours) along with a bound on maximum degree of
parallelism. Users specify, along with these job
characteristics, their desired due date and a value for
finishing the job by its deadline. Given this
specification, the primary goal is to determine the
scheduling of cloud computing instances under capacity
constraints in order to maximize the social welfare
(i.e., sum of values gained by allocated users). Our
main result is a new (CC-kcss-1)-approximation
algorithm for this objective, where $C$ denotes cloud
capacity, $k$ is the maximal bound on parallelized
execution (in practical settings, $ k < C$) and $s$ is
the slackness on the job completion time, that is, the
minimal ratio between a specified deadline and the
earliest finish time of a job. Our algorithm is based
on utilizing dual fitting arguments over a strengthened
linear program to the problem. Based on the new
approximation algorithm, we construct truthful
allocation and pricing mechanisms, in which reporting
the true value and other properties of the job
(deadline, work volume, and the parallelism bound) is a
dominant strategy for all users. To that end, we extend
known results for single-value settings to provide a
general framework for transforming allocation
algorithms into truthful mechanisms in domains of
single-value and multi-properties. We then show that
the basic mechanism can be extended under proper
Bayesian assumptions to the objective of maximizing
revenues, which is important for public clouds. We
empirically evaluate the benefits of our approach
through simulations on data-center job traces, and show
that the revenues obtained under our mechanism are
comparable with an ideal fixed-price mechanism, which
sets an on-demand price using oracle knowledge of
users' valuations. Finally, we discuss how our model
can be extended to accommodate uncertainties in job
work volumes, which is a practical challenge in cloud
settings.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "3",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Feldman:2015:HCG,
author = "Moran Feldman and Liane Lewin-Eytan and Joseph (Seffi)
Naor",
title = "Hedonic Clustering Games",
journal = j-TOPC,
volume = "2",
number = "1",
pages = "4:1--4:??",
month = may,
year = "2015",
CODEN = "????",
DOI = "https://doi.org/10.1145/2742345",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Thu May 21 16:27:00 MDT 2015",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Clustering, the partitioning of objects with respect
to a similarity measure, has been extensively studied
as a global optimization problem. We investigate
clustering from a game-theoretic approach, and consider
the class of hedonic clustering games. Here, a
self-organized clustering is obtained via decisions
made by independent players, corresponding to the
elements clustered. Being a hedonic setting, the
utility of each player is determined by the identity of
the other members of her cluster. This class of games
seems to be quite robust, as it fits with rather
different, yet commonly used, clustering criteria.
Specifically, we investigate hedonic clustering games
in two different models: fixed clustering, which
subdivides into $k$-median and $k$-center, and
correlation clustering. We provide a thorough analysis
of these games, characterizing Nash equilibria, and
proving upper and lower bounds on the price of anarchy
and price of stability. For fixed clustering we focus
on the existence of a Nash equilibrium, as it is a
rather nontrivial issue in this setting. We study it
both for general metrics and special cases, such as
line and tree metrics. In the correlation clustering
model, we study both minimization and maximization
variants, and provide almost tight bounds on both the
price of anarchy and price of stability.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "4",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Jahn:2015:RRA,
author = "Janmartin Jahn and Santiago Pagani and Sebastian Kobbe
and Jian-Jia Chen and J{\"o}rg Henkel",
title = "Runtime Resource Allocation for Software Pipelines",
journal = j-TOPC,
volume = "2",
number = "1",
pages = "5:1--5:??",
month = may,
year = "2015",
CODEN = "????",
DOI = "https://doi.org/10.1145/2742347",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Thu May 21 16:27:00 MDT 2015",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Efficiently allocating the computational resources of
many-core systems is one of the most prominent
challenges, especially when resource requirements may
vary unpredictably at runtime. This is even more
challenging when facing unreliable cores --- a scenario
that becomes common as the number of cores increases
and integration sizes shrink. To address this
challenge, this article presents an optimal method for
the allocation of the resources to software-pipelined
applications. Here we show how runtime observations of
the resource requirements of tasks can be used to adapt
resource allocations. Furthermore, we show how the
optimum can be traded for a high degree of scalability
by clustering applications in a distributed,
hierarchical manner. To diminish the negative effects
of unreliable cores, this article shows how
self-organization can effectively restore the integrity
of such a hierarchy when it is corrupted by a failing
core. Experiments on Intel's 48-core Single-Chip Cloud
Computer and in a many-core simulator show that a
significant improvement in system throughput can be
achieved over the current state of the art.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "5",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Xu:2015:SVC,
author = "Yi Xu and Bo Zhao and Youtao Zhang and Jun Yang",
title = "Simple Virtual Channel Allocation for High-Throughput
and High-Frequency On-Chip Routers",
journal = j-TOPC,
volume = "2",
number = "1",
pages = "6:1--6:??",
month = may,
year = "2015",
CODEN = "????",
DOI = "https://doi.org/10.1145/2742349",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Thu May 21 16:27:00 MDT 2015",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Packet-switched network-on-chip (NoC) has provided a
scalable solution to the communications for tiled
multicore processors. However, the virtual channel (VC)
buffers in the NoC consume significant dynamic and
leakage power. To improve the energy efficiency of the
router design, it is advantageous to use small buffer
sizes while still maintaining throughput of the
network. This article proposes two new virtual channel
allocation (VA) mechanisms, termed fixed VC assignment
with dynamic VC allocation (FVADA) and adjustable VC
assignment with dynamic VC allocation (AVADA). VCs are
designated to output ports and allocated to packets
according to such assignment. This can help to reduce
the head-of-line blocking. Such VC-output port
assignment can also be adjusted dynamically to
accommodate traffic changes. Simulation results show
that both mechanisms can improve network throughput by
41\% on average. Real traffic evaluation shows a
network latency reduction of up to 66\%. In addition,
AVADA can outperform the baseline in throughput with
only half of the buffer size. Finally, we are able to
achieve comparable or better throughput than a previous
dynamic VC allocator while reducing its critical path
delay by 57\%. Hence, the proposed VA mechanisms are
suitable for low-power, high-throughput, and
high-frequency NoC designs.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "6",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Hammouda:2015:NTE,
author = "Adam Hammouda and Andrew R. Siegel and Stephen F.
Siegel",
title = "Noise-Tolerant Explicit Stencil Computations for
Nonuniform Process Execution Rates",
journal = j-TOPC,
volume = "2",
number = "1",
pages = "7:1--7:??",
month = may,
year = "2015",
CODEN = "????",
DOI = "https://doi.org/10.1145/2742351",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Thu May 21 16:27:00 MDT 2015",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Next-generation HPC computing platforms are likely to
be characterized by significant, unpredictable
nonuniformities in execution time among compute nodes
and cores. The resulting load imbalances from this
nonuniformity are expected to arise from a variety of
sources-manufacturing discrepancies, dynamic power
management, runtime component failure, OS jitter,
software-mediated resiliency, and TLB/- cache
performance variations, for example. It is well
understood that existing algorithms with frequent
points of bulk synchronization will perform relatively
poorly in the presence of these sources of process
nonuniformity. Thus, recasting classic bulk synchronous
algorithms into more asynchronous, coarse-grained
parallelism is a critical area of research for
next-generation computing. We propose a class of
parallel algorithms for explicit stencil computations
that can tolerate these nonuniformities by decoupling
per process communication and computation in order for
each process to progress asynchronously while
maintaining solution correctness. These algorithms are
benchmarked with a $1$D domain decomposed (``slabbed'')
implementation of the $2$D heat equation as a model
problem, and are tested in the presence of simulated
nonuniform process execution rates. The resulting
performance is compared to a classic bulk synchronous
implementation of the model problem. Results show that
the runtime of this article's algorithm on a machine
with simulated process nonuniformities is 5--99\%
slower than the runtime of its classic counterpart on a
machine free of nonuniformities. However, when both
algorithms are run on a machine with comparable
synthetic process nonuniformities, this article's
algorithm is 1--37 times faster than its classic
counterpart.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "7",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{McCreesh:2015:SST,
author = "Ciaran McCreesh and Patrick Prosser",
title = "The Shape of the Search Tree for the Maximum Clique
Problem and the Implications for Parallel Branch and
Bound",
journal = j-TOPC,
volume = "2",
number = "1",
pages = "8:1--8:??",
month = may,
year = "2015",
CODEN = "????",
DOI = "https://doi.org/10.1145/2742359",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Thu May 21 16:27:00 MDT 2015",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Finding a maximum clique in a given graph is one of
the fundamental NP-hard problems. We compare two
multicore thread-parallel adaptations of a
state-of-the-art branch-and-bound algorithm for the
maximum clique problem and provide a novel explanation
as to why they are successful. We show that load
balance is sometimes a problem but that the interaction
of parallel search order and the most likely location
of solutions within the search space is often the
dominating consideration. We use this explanation to
propose a new low-overhead, scalable work-splitting
mechanism. Our approach uses explicit early diversity
to avoid strong commitment to the weakest heuristic
advice and late resplitting for balance. More
generally, we argue that, for branch-and-bound,
parallel algorithm design should not be performed
independently of the underlying sequential algorithm.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "8",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Hoefler:2015:RMA,
author = "Torsten Hoefler and James Dinan and Rajeev Thakur and
Brian Barrett and Pavan Balaji and William Gropp and
Keith Underwood",
title = "Remote Memory Access Programming in {MPI-3}",
journal = j-TOPC,
volume = "2",
number = "2",
pages = "9:1--9:??",
month = jul,
year = "2015",
CODEN = "????",
DOI = "https://doi.org/10.1145/2780584",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Aug 7 10:22:35 MDT 2015",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/pvm.bib;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "The Message Passing Interface (MPI) 3.0 standard,
introduced in September 2012, includes a significant
update to the one-sided communication interface, also
known as remote memory access (RMA). In particular, the
interface has been extended to better support popular
one-sided and global-address-space parallel programming
models to provide better access to hardware performance
features and enable new data-access modes. We present
the new RMA interface and specify formal axiomatic
models for data consistency and access semantics. Such
models can help users reason about details of the
semantics that are hard to extract from the English
prose in the standard. It also fosters the development
of tools and compilers, enabling them to automatically
analyze, optimize, and debug RMA programs.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "9",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Maldonado:2015:STB,
author = "Walther Maldonado and Patrick Marlier and Pascal
Felber and Julia Lawall and Gilles Muller and Etienne
Rivi{\`e}re",
title = "Supporting Time-Based {QoS} Requirements in Software
Transactional Memory",
journal = j-TOPC,
volume = "2",
number = "2",
pages = "10:1--10:??",
month = jul,
year = "2015",
CODEN = "????",
DOI = "https://doi.org/10.1145/2779621",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Aug 7 10:22:35 MDT 2015",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Software transactional memory (STM) is an optimistic
concurrency control mechanism that simplifies parallel
programming. However, there has been little interest in
its applicability to reactive applications in which
there is a required response time for certain
operations. We propose supporting such applications by
allowing programmers to associate time with atomic
blocks in the form of deadlines and quality-of-service
(QoS) requirements. Based on statistics of past
executions, we adjust the execution mode of
transactions by decreasing the level of optimism as the
deadline approaches. In the presence of concurrent
deadlines, we propose different conflict resolution
policies. Execution mode switching mechanisms allow the
meeting of multiple deadlines in a consistent manner,
with potential QoS degradations being split fairly
among several threads as contention increases, and
avoiding starvation. Our implementation consists of
extensions to an STM runtime that allow gathering
statistics and switching execution modes. We also
propose novel contention managers adapted to
transactional workloads subject to deadlines. The
experimental evaluation shows that our approaches
significantly improve the likelihood of a transaction
meeting its deadline and QoS requirement, even in cases
where progress is hampered by conflicts and other
concurrent transactions with deadlines.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "10",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Kestor:2015:TPD,
author = "Gokcen Kestor and Osman S. Unsal and Adrian Cristal
and Serdar Tasiran",
title = "{TRADE}: Precise Dynamic Race Detection for Scalable
Transactional Memory Systems",
journal = j-TOPC,
volume = "2",
number = "2",
pages = "11:1--11:??",
month = jul,
year = "2015",
CODEN = "????",
DOI = "https://doi.org/10.1145/2786021",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Aug 7 10:22:35 MDT 2015",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/multithreading.bib;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "As other multithreaded programs, transactional memory
(TM) programs are prone to race conditions. Previous
work focuses on extending existing definitions of data
race for lock-based applications to TM applications,
which requires all transactions to be totally ordered
``as if'' serialized by a global lock. This approach
poses implementation constraints on the STM that
severely limits TM applications' performance. This
article shows that forcing total ordering among all
running transactions, while sufficient, is not
necessary. We introduce an alternative data race
definition, relaxed transactional data race, that
requires ordering of only conflicting transactions. The
advantages of our relaxed definition are twofold:
First, unlike the previous definition, this definition
can be applied to a wide range of TMs, including those
that do not enforce transaction total ordering. Second,
within a single execution, it exposes a higher number
of data races, which considerably reduces debugging
time. Based on this definition, we propose a novel and
precise race detection tool for C/C++ TM applications
(TRADE), which detects data races by tracking
happens-before edges among conflicting transactions.
Our experiments reveal that TRADE precisely detects
data races for STAMP applications running on modern
STMs with overhead comparable to state-of-the-art race
detectors for lock-based applications. Our experiments
also show that in a single run, TRADE identifies
several races not discovered by 10 separate runs of a
race detection tool based on the previous data race
definition.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "11",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Diegues:2015:TWE,
author = "Nuno Diegues and Paolo Romano",
title = "{Time-Warp}: Efficient Abort Reduction in
Transactional Memory",
journal = j-TOPC,
volume = "2",
number = "2",
pages = "12:1--12:??",
month = jul,
year = "2015",
CODEN = "????",
DOI = "https://doi.org/10.1145/2775435",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Aug 7 10:22:35 MDT 2015",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "The multicore revolution that took place one decade
ago has turned parallel programming into a major
concern for the mainstream software development
industry. In this context, Transactional Memory (TM)
has emerged as a simpler and attractive alternative to
that of lock-based synchronization, whose complexity
and error-proneness are widely recognized. The notion
of permissiveness in TM translates to only aborting a
transaction when it cannot be accepted in any history
that guarantees a target correctness criterion. This
theoretically powerful property is often neglected by
state-of-the-art TMs because it imposes considerable
algorithmic costs. Instead, these TMs opt to maximize
their implementation's efficiency by aborting
transactions under overly conservative conditions. As a
result, they risk rejecting a significant number of
safe executions. In this article, we seek to identify a
sweet spot between permissiveness and efficiency by
introducing the Time-Warp Multiversion (TWM) algorithm.
TWM is based on the key idea of allowing an update
transaction that has performed stale reads (i.e.,
missed the writes of concurrently committed
transactions) to be serialized by ``committing it in
the past,'' which we call a time-warp commit. At its
core, TWM uses a novel, lightweight validation
mechanism with little computational overhead. TWM also
guarantees that read-only transactions can never be
aborted. Further, TWM guarantees Virtual World
Consistency, a safety property that is deemed as
particularly relevant in the context of TM. We
demonstrate the practicality of this approach through
an extensive experimental study: we compare TWM with
five other TMs, representative of typical alternative
design choices, and on a wide variety of benchmarks.
This study shows an average performance improvement
across all considered workloads and TMs of 65\% in high
concurrency scenarios, with gains extending up to $ 9
\times $ with the most favorable benchmarks. These
results are a consequence of TWM's ability to achieve
drastic reduction of aborts in scenarios of nonminimal
contention, while introducing little overhead
(approximately 10\%) in worst-case, synthetically
designed scenarios (i.e., no contention or contention
patterns that cannot be optimized using TWM).",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "12",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Eyraud-Dubois:2015:PST,
author = "Lionel Eyraud-Dubois and Loris Marchal and Oliver
Sinnen and Fr{\'e}d{\'e}ric Vivien",
title = "Parallel Scheduling of Task Trees with Limited
Memory",
journal = j-TOPC,
volume = "2",
number = "2",
pages = "13:1--13:??",
month = jul,
year = "2015",
CODEN = "????",
DOI = "https://doi.org/10.1145/2779052",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Aug 7 10:22:35 MDT 2015",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "This article investigates the execution of tree-shaped
task graphs using multiple processors. Each edge of
such a tree represents some large data. A task can only
be executed if all input and output data fit into
memory, and a data can only be removed from memory
after the completion of the task that uses it as an
input data. Such trees arise in the multifrontal method
of sparse matrix factorization. The peak memory needed
for the processing of the entire tree depends on the
execution order of the tasks. With one processor, the
objective of the tree traversal is to minimize the
required memory. This problem was well studied, and
optimal polynomial algorithms were proposed. Here, we
extend the problem by considering multiple processors,
which is of obvious interest in the application area of
matrix factorization. With multiple processors comes
the additional objective to minimize the time needed to
traverse the tree-that is, to minimize the makespan.
Not surprisingly, this problem proves to be much harder
than the sequential one. We study the computational
complexity of this problem and provide
inapproximability results even for unit weight trees.
We design a series of practical heuristics achieving
different trade-offs between the minimization of peak
memory usage and makespan. Some of these heuristics are
able to process a tree while keeping the memory usage
under a given memory limit. The different heuristics
are evaluated in an extensive experimental evaluation
using realistic trees.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "13",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Dinitz:2015:ISI,
author = "Michael Dinitz and Torsten Hoefler",
title = "Introduction to the Special Issue on {SPAA 2013}",
journal = j-TOPC,
volume = "2",
number = "3",
pages = "14:1--14:??",
month = oct,
year = "2015",
CODEN = "????",
DOI = "https://doi.org/10.1145/2809923",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Nov 3 07:30:42 MST 2015",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "14e",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Kumar:2015:FGA,
author = "Ravi Kumar and Benjamin Moseley and Sergei
Vassilvitskii and Andrea Vattani",
title = "Fast Greedy Algorithms in {MapReduce} and Streaming",
journal = j-TOPC,
volume = "2",
number = "3",
pages = "14:1--14:??",
month = oct,
year = "2015",
CODEN = "????",
DOI = "https://doi.org/10.1145/2809814",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Nov 3 07:30:42 MST 2015",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Greedy algorithms are practitioners' best
friends---they are intuitive, are simple to implement,
and often lead to very good solutions. However,
implementing greedy algorithms in a distributed setting
is challenging since the greedy choice is inherently
sequential, and it is not clear how to take advantage
of the extra processing power. Our main result is a
powerful sampling technique that aids in
parallelization of sequential algorithms. Armed with
this primitive, we then adapt a broad class of greedy
algorithms to the MapReduce paradigm; this class
includes maximum cover and submodular maximization
subject to p -system constraint problems. Our method
yields efficient algorithms that run in a logarithmic
number of rounds while obtaining solutions that are
arbitrarily close to those produced by the standard
sequential greedy algorithm. We begin with algorithms
for modular maximization subject to a matroid
constraint and then extend this approach to obtain
approximation algorithms for submodular maximization
subject to knapsack or p -system constraints.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "14",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Sanders:2015:WEM,
author = "Peter Sanders and Jochen Speck and Raoul Steffen",
title = "Work-Efficient Matrix Inversion in Polylogarithmic
Time",
journal = j-TOPC,
volume = "2",
number = "3",
pages = "15:1--15:??",
month = oct,
year = "2015",
CODEN = "????",
DOI = "https://doi.org/10.1145/2809812",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Nov 3 07:30:42 MST 2015",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "We present an algorithm for inversion of symmetric
positive definite matrices that combines the practical
requirement of an optimal number of arithmetic
operations and the theoretical goal of a
polylogarithmic critical path length. The algorithm
reduces inversion to matrix multiplication. It uses
Strassen's recursion scheme, but on the critical path
it breaks the recursion early, switching to an
asymptotically inefficient yet fast use of Newton's
method. We also show that the algorithm is numerically
stable. Overall, we get a candidate for a massively
parallel algorithm that scales to exascale systems even
on relatively small inputs.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "15",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Gilbert:2015:SBO,
author = "Seth Gilbert and Chaodong Zheng",
title = "{SybilCast}: Broadcast on the Open Airwaves",
journal = j-TOPC,
volume = "2",
number = "3",
pages = "16:1--16:??",
month = oct,
year = "2015",
CODEN = "????",
DOI = "https://doi.org/10.1145/2809810",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Nov 3 07:30:42 MST 2015",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Consider a scenario where many wireless users are
attempting to download data from a single base station.
While most of the users are honest, some users may be
malicious and attempt to obtain more than their fair
share of the bandwidth. One possible strategy for
attacking the system is to simulate multiple fake
identities, each of which is given its own equal share
of the bandwidth. Such an attack is often referred to
as a sybil attack. To counter such behavior, we propose
SybilCast, a protocol for multichannel wireless
networks that limits the number of fake identities and,
in doing so, ensures that each honest user gets at
least a constant fraction of his or her fair share of
the bandwidth. As a result, each honest user can
complete his or her data download in asymptotically
optimal time. A key aspect of this protocol is
balancing the rate at which new identities are admitted
and the maximum number of fake identities that can
coexist while keeping the overhead low. Besides sybil
attacks, our protocol can also tolerate spoofing and
jamming.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "16",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Lee:2015:FPP,
author = "I-Ting Angelina Lee and Charles E. Leiserson and Tao
B. Schardl and Zhunping Zhang and Jim Sukha",
title = "On-the-Fly Pipeline Parallelism",
journal = j-TOPC,
volume = "2",
number = "3",
pages = "17:1--17:??",
month = oct,
year = "2015",
CODEN = "????",
DOI = "https://doi.org/10.1145/2809808",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Nov 3 07:30:42 MST 2015",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Pipeline parallelism organizes a parallel program as a
linear sequence of stages. Each stage processes
elements of a data stream, passing each processed data
element to the next stage, and then taking on a new
element before the subsequent stages have necessarily
completed their processing. Pipeline parallelism is
used especially in streaming applications that perform
video, audio, and digital signal processing. Three out
of 13 benchmarks in PARSEC, a popular software
benchmark suite designed for shared-memory
multiprocessors, can be expressed as pipeline
parallelism. Whereas most concurrency platforms that
support pipeline parallelism use a
``construct-and-run'' approach, this article
investigates ``on-the-fly'' pipeline parallelism, where
the structure of the pipeline emerges as the program
executes rather than being specified a priori.
On-the-fly pipeline parallelism allows the number of
stages to vary from iteration to iteration and
dependencies to be data dependent. We propose simple
linguistics for specifying on-the-fly pipeline
parallelism and describe a provably efficient
scheduling algorithm, the P iper algorithm, which
integrates pipeline parallelism into a work-stealing
scheduler, allowing pipeline and fork-join parallelism
to be arbitrarily nested. The Piper algorithm
automatically throttles the parallelism, precluding
``runaway'' pipelines. Given a pipeline computation
with $ T_1 $ work and $ T_\infty $ span (critical-path
length), Piper executes the computation on $P$
processors in $ T_P \leq T_1 / P + O(T \infty + \lg P)$
expected time. Piper also limits stack space, ensuring
that it does not grow unboundedly with running time. We
have incorporated on-the-fly pipeline parallelism into
a Cilk-based work-stealing runtime system. Our
prototype Cilk-P implementation exploits optimizations
such as ``lazy enabling'' and ``dependency folding.''
We have ported the three PARSEC benchmarks that exhibit
pipeline parallelism to run on Cilk-P. One of these,
x264, cannot readily be executed by systems that
support only construct-and-run pipeline parallelism.
Benchmark results indicate that Cilk-P has low serial
overhead and good scalability. On x264, for example,
Cilk-P exhibits a speedup of 13.87 over its respective
serial counterpart when running on 16 processors.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "17",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Eikel:2015:IRI,
author = "Martina Eikel and Christian Scheideler",
title = "{IRIS}: a Robust Information System Against Insider
{DoS} Attacks",
journal = j-TOPC,
volume = "2",
number = "3",
pages = "18:1--18:??",
month = oct,
year = "2015",
CODEN = "????",
DOI = "https://doi.org/10.1145/2809806",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Nov 3 07:30:42 MST 2015",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "In this work, we present the first scalable
distributed information system, that is, a system with
low storage overhead, that is provably robust against
denial-of-service (DoS) attacks by a current insider.
We allow a current insider to have complete knowledge
about the information system and to have the power to
block any \varepsilon-fraction of its servers by a DoS
attack, where \varepsilon can be chosen up to a
constant. The task of the system is to serve any
collection of lookup requests with at most one per
nonblocked server in an efficient way despite this
attack. Previously, scalable solutions were only known
for DoS attacks of past insiders, where a past insider
only has complete knowledge about some past time point
$ t_0 $ of the information system. Scheideler et al.
[Awerbuch and Scheideler 2007; Baumgart et al. 2009]
showed that in this case, it is possible to design an
information system so that any information that was
inserted or last updated after $ t_0 $ is safe against
a DoS attack. But their constructions would not work at
all for a current insider. The key idea behind our IRIS
system is to make extensive use of coding. More
precisely, we present two alternative distributed
coding strategies with an at most logarithmic storage
overhead that can handle up to a constant fraction of
blocked servers.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "18",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Kling:2015:PSM,
author = "Peter Kling and Peter Pietrzyk",
title = "Profitable Scheduling on Multiple Speed-Scalable
Processors",
journal = j-TOPC,
volume = "2",
number = "3",
pages = "19:1--19:??",
month = oct,
year = "2015",
CODEN = "????",
DOI = "https://doi.org/10.1145/2809872",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Nov 3 07:30:42 MST 2015",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "We present a new online algorithm for profit-oriented
scheduling on multiple speed-scalable processors and
provide a tight analysis of the algorithm's
competitiveness. Our results generalize and improve
upon work by Chan et al. [2010], which considers a
single speed-scalable processor. Using significantly
different techniques, we can not only extend their
model to multiprocessors but also prove an enhanced and
tight competitive ratio for our algorithm. In our
scheduling problem, jobs arrive over time and are
preemptable. They have different workloads, values, and
deadlines. The scheduler may decide not to finish a job
but instead to suffer a loss equaling the job's value.
However, to process a job's workload until its deadline
the scheduler must invest a certain amount of energy.
The cost of a schedule is the sum of lost values and
invested energy. In order to finish a job, the
scheduler has to determine which processors to use and
set their speeds accordingly. A processor's energy
consumption is power $ P_\alpha (s) $ integrated over
time, where $ P_\alpha (s) = s^\alpha $ is the power
consumption when running at speed $s$. Since we
consider the online variant of the problem, the
scheduler has no knowledge about future jobs. This
problem was introduced by Chan et al. [2010] for the
case of a single processor. They presented an online
algorithm that is $ \alpha^\alpha + 2 e \alpha
$-competitive. We provide an online algorithm for the
case of multiple processors with an improved
competitive ratio of $ \alpha^\alpha $.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "19",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Dutta:2015:CBR,
author = "Chinmoy Dutta and Gopal Pandurangan and Rajmohan
Rajaraman and Scott Roche",
title = "Coalescing-Branching Random Walks on Graphs",
journal = j-TOPC,
volume = "2",
number = "3",
pages = "20:1--20:??",
month = oct,
year = "2015",
CODEN = "????",
DOI = "https://doi.org/10.1145/2817830",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Nov 3 07:30:42 MST 2015",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "We study a distributed randomized information
propagation mechanism in networks we call the
coalescing-branching random walk (cobra walk, for
short). A cobra walk is a generalization of the
well-studied ``standard'' random walk, and is useful in
modeling and understanding the Susceptible-Infected-
Susceptible (SIS)-type of epidemic processes in
networks. It can also be helpful in performing
light-weight information dissemination in
resource-constrained networks. A cobra walk is
parameterized by a branching factor $k$. The process
starts from an arbitrary vertex, which is labeled
active for step 1. In each step of a cobra walk, each
active vertex chooses $k$ random neighbors to become
active for the next step (``branching''). A vertex is
active for step $ t + 1$ only if it is chosen by an
active vertex in step $t$ (``coalescing''). This
results in a stochastic process in the underlying
network with properties that are quite different from
both the standard random walk (which is equivalent to
the cobra walk with branching factor 1) as well as
other gossip-based rumor spreading mechanisms. We focus
on the cover time of the cobra walk, which is the
number of steps for the walk to reach all the vertices,
and derive almost-tight bounds for various graph
classes. We show an $ O(\log^2 n)$ high probability
bound for the cover time of cobra walks on expanders,
if either the expansion factor or the branching factor
is sufficiently large; we also obtain an $ O(\log n)$
high probability bound for the partial cover time,
which is the number of steps needed for the walk to
reach at least a constant fraction of the vertices. We
also show that the cover time of the cobra walk is,
with high probability, $ O(n \log n)$ on any $n$-vertex
tree for $ k \geq 2$, $ {\~ O}(n^{1 / d})$ on a
$d$-dimensional grid for $ k \geq 2$, and $ O(\log n)$
on the complete graph.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "20",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Larus:2016:ISI,
author = "James Larus and Sandhya Dwarkadas and Jos{\'e} Moreira
and Andrew Lumsdaine",
title = "Introduction to the Special Issue on {PPoPP'14}",
journal = j-TOPC,
volume = "2",
number = "4",
pages = "21:1--21:??",
month = mar,
year = "2016",
CODEN = "????",
DOI = "https://doi.org/10.1145/2856513",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Sat Mar 19 08:11:13 MDT 2016",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "21",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
remark = "Special Issue on PPoPP'14 conference.",
}
@Article{Herlihy:2016:WSF,
author = "Maurice Herlihy and Zhiyu Liu",
title = "Well-Structured Futures and Cache Locality",
journal = j-TOPC,
volume = "2",
number = "4",
pages = "22:1--22:??",
month = mar,
year = "2016",
CODEN = "????",
DOI = "https://doi.org/10.1145/2858650",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Sat Mar 19 08:11:13 MDT 2016",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "In fork-join parallelism, a sequential program is
split into a directed acyclic graph of tasks linked by
directed dependency edges, and the tasks are executed,
possibly in parallel, in an order consistent with their
dependencies. A popular and effective way to extend
fork-join parallelism is to allow threads to create
futures. A thread creates a future to hold the results
of a computation, which may or may not be executed in
parallel. That result is returned when some thread
touches that future, blocking if necessary until the
result is ready. Recent research has shown that
although futures can, of course, enhance parallelism in
a structured way, they can have a deleterious effect on
cache locality. In the worst case, futures can incur $
\Omega (P T_\infty + t T_\infty) $ deviations, which
implies $ \Omega (C P T_\infty + C t T_\infty) $
additional cache misses, where $C$ is the number of
cache lines, $P$ is the number of processors, $t$ is
the number of touches, and $ T_\infty $ is the
computation span. Since cache locality has a large
impact on software performance on modern multicores,
this result is troubling. In this article, we show that
if futures are used in a simple, disciplined way, then
the situation is much better: if each future is touched
only once, either by the thread that created it or by a
later descendant of the thread that created it, then
parallel executions with work stealing can incur at
most $ O(C P T^2_\infty)$ additional cache misses-a
substantial improvement. This structured use of futures
is characteristic of many (but not all) parallel
applications.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "22",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
remark = "Special Issue on PPoPP'14 conference.",
}
@Article{Thomson:2016:CTU,
author = "Paul Thomson and Alastair F. Donaldson and Adam
Betts",
title = "Concurrency Testing Using Controlled Schedulers: an
Empirical Study",
journal = j-TOPC,
volume = "2",
number = "4",
pages = "23:1--23:??",
month = mar,
year = "2016",
CODEN = "????",
DOI = "https://doi.org/10.1145/2858651",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Sat Mar 19 08:11:13 MDT 2016",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "We present an independent empirical study on
concurrency testing using controlled schedulers. We
have gathered 49 buggy concurrent software benchmarks,
drawn from public code bases, which we call SCTBench.
We applied a modified version of an existing
concurrency testing tool to SCTBench, testing five
controlled scheduling techniques: depth-first search,
preemption bounding, delay bounding, a controlled
random scheduler, and probabilistic concurrency testing
(PCT). We attempt to answer several research questions:
Which technique performs the best, in terms of bug
finding ability? How effective are the two main
schedule bounding techniques-preemption bounding and
delay bounding-at finding bugs? What challenges are
associated with applying concurrency testing techniques
to existing code? Can we classify certain benchmarks as
trivial or nontrivial? Overall, we found that PCT (with
parameter d = 3) was the most effective technique in
terms of bug finding; it found all bugs found by the
other techniques, plus an additional three, and it
missed only one bug. Surprisingly, we found that the
naive controlled random scheduler, which randomly
chooses one thread to execute at each scheduling point,
performs well, finding more bugs than preemption
bounding and just two fewer bugs than delay bounding.
Our findings confirm that delay bounding is superior to
preemption bounding and that schedule bounding is
superior to an unbounded depth-first search. The
majority of bugs in SCTBench can be exposed using a
small schedule bound (1--2), supporting previous
claims, although one benchmark requires five
preemptions. We found that the need to remove
nondeterminism and control all synchronization (as is
required for systematic concurrency testing) can be
nontrivial. There were eight distinct programs that
could not easily be included in out study, such as
those that perform network and interprocess
communication. We report various properties about the
benchmarks tested, such as the fact that the bugs in 18
benchmarks were exposed 50\% of the time when using
random scheduling. We note that future work should not
use the benchmarks that we classify as trivial when
presenting new techniques, other than as a minimum
baseline. We have made SCTBench and our tools publicly
available for reproducibility and use in future work.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "23",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
remark = "Special Issue on PPoPP'14 conference.",
}
@Article{Petrovic:2016:LHM,
author = "Darko Petrovi{\'c} and Thomas Ropars and Andr{\'e}
Schiper",
title = "Leveraging Hardware Message Passing for Efficient
Thread Synchronization",
journal = j-TOPC,
volume = "2",
number = "4",
pages = "24:1--24:??",
month = mar,
year = "2016",
CODEN = "????",
DOI = "https://doi.org/10.1145/2858652",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Sat Mar 19 08:11:13 MDT 2016",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "As the level of parallelism in manycore processors
keeps increasing, providing efficient mechanisms for
thread synchronization in concurrent programs is
becoming a major concern. On cache-coherent
shared-memory processors, synchronization efficiency is
ultimately limited by the performance of the underlying
cache coherence protocol. This article studies how
hardware support for message passing can improve
synchronization performance. Considering the ubiquitous
problem of mutual exclusion, we devise novel algorithms
for (i) classic locking, where application threads
obtain exclusive access to a shared resource prior to
executing their critical sections (CSes), and (ii)
delegation, where CSes are executed by special threads.
For classic locking, our HybLock algorithm uses a mix
of shared memory and hardware message passing, which
introduces the idea of hybrid synchronization
algorithms. For delegation, we propose mp-server and
HybComb: the former is a straightforward adaptation of
the server approach to hardware message passing,
whereas the latter is a novel hybrid combining
algorithm. Evaluation on Tilera's TILE-Gx processor
shows that HybLock outperforms the best known classic
locks. Furthermore, mp-server can execute contended
CSes with unprecedented throughput, as stalls related
to cache coherence are removed from the critical path.
HybComb can achieve comparable performance while
avoiding the need to dedicate server cores.
Consequently, our queue and stack implementations,
based on the new synchronization algorithms, largely
outperform their most efficient shared-memory-only
counterparts.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "24",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
remark = "Special Issue on PPoPP'14 conference.",
}
@Article{Tardieu:2016:XAP,
author = "Olivier Tardieu and Benjamin Herta and David
Cunningham and David Grove and Prabhanjan Kambadur and
Vijay Saraswat and Avraham Shinnar and Mikio Takeuchi
and Mandana Vaziri and Wei Zhang",
title = "{X10} and {APGAS} at Petascale",
journal = j-TOPC,
volume = "2",
number = "4",
pages = "25:1--25:??",
month = mar,
year = "2016",
CODEN = "????",
DOI = "https://doi.org/10.1145/2894746",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Sat Mar 19 08:11:13 MDT 2016",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "X10 is a high-performance, high-productivity
programming language aimed at large-scale distributed
and shared-memory parallel applications. It is based on
the Asynchronous Partitioned Global Address Space
(APGAS) programming model, supporting the same
fine-grained concurrency mechanisms within and across
shared-memory nodes. We demonstrate that X10 delivers
solid performance at petascale by running (weak
scaling) eight application kernels on an IBM Power--775
supercomputer utilizing up to 55,680 Power7 cores (for
1.7Pflop/s of theoretical peak performance). For the
four HPC Class 2 Challenge benchmarks, X10 achieves
41\% to 87\% of the system's potential at scale (as
measured by IBM's HPCC Class 1 optimized runs). We also
implement K-Means, Smith-Waterman, Betweenness
Centrality, and Unbalanced Tree Search (UTS) for
geometric trees. Our UTS implementation is the first to
scale to petaflop systems. We describe the advances in
distributed termination detection, distributed load
balancing, and use of high-performance interconnects
that enable X10 to scale out to tens of thousands of
cores. We discuss how this work is driving the
evolution of the X10 language, core class libraries,
and runtime systems.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "25",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
remark = "Special Issue on PPoPP'14 conference.",
}
@Article{Maleki:2016:LRM,
author = "Saeed Maleki and Madanlal Musuvathi and Todd
Mytkowicz",
title = "Low-Rank Methods for Parallelizing Dynamic Programming
Algorithms",
journal = j-TOPC,
volume = "2",
number = "4",
pages = "26:1--26:??",
month = mar,
year = "2016",
CODEN = "????",
DOI = "https://doi.org/10.1145/2884065",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Sat Mar 19 08:11:13 MDT 2016",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "This article proposes efficient parallel methods for
an important class of dynamic programming problems that
includes Viterbi, Needleman--Wunsch, Smith--Waterman,
and Longest Common Subsequence. In dynamic programming,
the subproblems that do not depend on each other, and
thus can be computed in parallel, form stages or
wavefronts. The methods presented in this article
provide additional parallelism allowing multiple stages
to be computed in parallel despite dependencies among
them. The correctness and the performance of the
algorithm relies on rank convergence properties of
matrix multiplication in the tropical semiring, formed
with plus as the multiplicative operation and max as
the additive operation. This article demonstrates the
efficiency of the parallel algorithm by showing
significant speedups on a variety of important dynamic
programming problems. In particular, the parallel
Viterbi decoder is up to $ 24 \times $ faster (with 64
processors) than a highly optimized commercial
baseline.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "26",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
remark = "Special Issue on PPoPP'14 conference.",
}
@Article{Yuan:2016:FCN,
author = "Xin Yuan and Wickus Nienaber and Santosh Mahapatra",
title = "On Folded-{Clos} Networks with Deterministic
Single-Path Routing",
journal = j-TOPC,
volume = "2",
number = "4",
pages = "27:1--27:??",
month = mar,
year = "2016",
CODEN = "????",
DOI = "https://doi.org/10.1145/2858654",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Sat Mar 19 08:11:13 MDT 2016",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Folded-Clos networks, also known as fat-trees, have
been widely used as interconnects in large-scale
high-performance computing clusters. Although users
often treat such interconnects as replacements of
nonblocking crossbar switches that can carry out any
permutation communication without contention, the
networking capability of such interconnects without a
centralized controller in computer communication
environments is not well understood. In this article,
we investigate nonblocking two-level folded-Clos
networks with deterministic single-path routing, but no
centralized controller, and establish the nonblocking
condition. The results indicate that nonblocking
two-level folded-Clos networks without a centralized
controller are much more expensive to construct than
the traditional nonblocking networks in the
telecommunication environment. Practical two-level
folded-Clos based interconnects are blocking. For such
interconnects, we establish the lower bound for
worst-case contention for permutations with any
deterministic single-path routing scheme, show that
existing routing schemes perform poorly in terms of
worst-case contention for permutations, present a
routing scheme that achieves the theoretical optimal,
and empirically compare the performance of existing
schemes with the optimal routing scheme. The techniques
developed for two-level folded-Clos networks are
further extended for the general fat-trees of any
heights.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "27",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
remark = "Special Issue on PPoPP'14 conference.",
}
@Article{Sandes:2016:MMA,
author = "Edans F. De O. Sandes and Guillermo Miranda and Xavier
Martorell and Eduard Ayguade and George Teodoro and
Alba C. M. A. {De Melo}",
title = "{MASA}: a Multiplatform Architecture for Sequence
Aligners with Block Pruning",
journal = j-TOPC,
volume = "2",
number = "4",
pages = "28:1--28:??",
month = mar,
year = "2016",
CODEN = "????",
DOI = "https://doi.org/10.1145/2858656",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Sat Mar 19 08:11:13 MDT 2016",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Biological sequence alignment is a very popular
application in Bioinformatics, used routinely
worldwide. Many implementations of biological sequence
alignment algorithms have been proposed for multicores,
GPUs, FPGAs and CellBEs. These implementations are
platform-specific; porting them to other systems
requires considerable programming effort. This article
proposes and evaluates MASA, a flexible and
customizable software architecture that enables the
execution of biological sequence alignment applications
with three variants (local, global, and semiglobal) in
multiple hardware/software platforms with block
pruning, which is able to reduce significantly the
amount of data processed. To attain our flexibility
goals, we also propose a generic version of block
pruning and developed multiple parallelization
strategies as building blocks, including a new
asynchronous dataflow-based parallelization, which may
be combined to implement efficient aligners in
different platforms. We provide four MASA aligner
implementations for multicores (OmpSs and OpenMP), GPU
(CUDA), and Intel Phi (OpenMP), showing that MASA is
very flexible. The evaluation of our generic block
pruning strategy shows that it significantly
outperforms the previously proposed block pruning,
being able to prune up to 66.5\% of the cells when
using the new dataflow-based parallelization
strategy.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "28",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
remark = "Special Issue on PPoPP'14 conference.",
}
@Article{MeyeraufderHeide:2016:ISI,
author = "Friedhelm {Meyer auf der Heide} and Peter Sanders and
Nodari Sitchinava",
title = "Introduction to the Special Issue on {SPAA 2014}",
journal = j-TOPC,
volume = "3",
number = "1",
pages = "1:1--1:??",
month = aug,
year = "2016",
CODEN = "????",
DOI = "https://doi.org/10.1145/2936716",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Sep 23 15:24:51 MDT 2016",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "1",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Kaler:2016:EDD,
author = "Tim Kaler and William Hasenplaugh and Tao B. Schardl
and Charles E. Leiserson",
title = "Executing Dynamic Data-Graph Computations
Deterministically Using Chromatic Scheduling",
journal = j-TOPC,
volume = "3",
number = "1",
pages = "2:1--2:??",
month = aug,
year = "2016",
CODEN = "????",
DOI = "https://doi.org/10.1145/2896850",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Sep 23 15:24:51 MDT 2016",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "A data-graph computation-popularized by such
programming systems as Galois, Pregel, GraphLab,
PowerGraph, and GraphChi-is an algorithm that performs
local updates on the vertices of a graph. During each
round of a data-graph computation, an update function
atomically modifies the data associated with a vertex
as a function of the vertex's prior data and that of
adjacent vertices. A dynamic data-graph computation
updates only an active subset of the vertices during a
round, and those updates determine the set of active
vertices for the next round. This article introduces
Prism, a chromatic-scheduling algorithm for executing
dynamic data-graph computations. Prism uses a vertex
coloring of the graph to coordinate updates performed
in a round, precluding the need for mutual-exclusion
locks or other nondeterministic data synchronization. A
multibag data structure is used by Prism to maintain a
dynamic set of active vertices as an unordered set
partitioned by color. We analyze Prism using work-span
analysis. Let $ G = (V, E) $ be a degree-$ \Delta $
graph colored with \chi colors, and suppose that $ Q
\subseteq V $ is the set of active vertices in a round.
Define $ {\rm size} (Q) = | Q | + \Sigma_{v \in Q} {\rm
deg}(v) $, which is proportional to the space required
to store the vertices of $Q$ using a sparse-graph
layout. We show that a $P$-processor execution of Prism
performs updates in $Q$ using $ O(\chi (l g (Q / \chi)
+ l g \Delta)) + l g P$ span and $ \Theta (s i z e (Q)
+ P)$ work. These theoretical guarantees are matched by
good empirical performance. To isolate the effect of
the scheduling algorithm on performance, we modified
GraphLab to incorporate Prism and studied seven
application benchmarks on a 12-core multicore machine.
Prism executes the benchmarks 1.2 to 2.1 times faster
than GraphLab's nondeterministic lock-based scheduler
while providing deterministic behavior. This article
also presents Prism-R, a variation of Prism that
executes dynamic data-graph computations
deterministically even when updates modify global
variables with associative operations. Prism-R
satisfies the same theoretical bounds as Prism, but its
implementation is more involved, incorporating a
multivector data structure to maintain a
deterministically ordered set of vertices partitioned
by color. Despite its additional complexity, Prism-R is
only marginally slower than Prism. On the seven
application benchmarks studied, Prism-R incurs a 7\%
geometric mean overhead relative to Prism.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "2",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Im:2016:CST,
author = "Sungjin Im and Benjamin Moseley and Kirk Pruhs and
Eric Torng",
title = "Competitively Scheduling Tasks with Intermediate
Parallelizability",
journal = j-TOPC,
volume = "3",
number = "1",
pages = "4:1--4:??",
month = aug,
year = "2016",
CODEN = "????",
DOI = "https://doi.org/10.1145/2938378",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Sep 23 15:24:51 MDT 2016",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "We introduce a scheduling algorithm Intermediate-SRPT,
and show that it is $ O (\log P)$-competitive with
respect to average flow time when scheduling jobs whose
parallelizability is intermediate between being fully
parallelizable and sequential. Here, the parameter P
denotes the ratio between the maximum job size to the
minimum. We also show a general matching lower bound on
the competitive ratio. Our analysis builds on an
interesting combination of potential function and local
competitiveness arguments.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "4",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Bercea:2016:CMI,
author = "Ioana O. Bercea and Navin Goyal and David G. Harris
and Aravind Srinivasan",
title = "On Computing Maximal Independent Sets of Hypergraphs
in Parallel",
journal = j-TOPC,
volume = "3",
number = "1",
pages = "5:1--5:??",
month = aug,
year = "2016",
CODEN = "????",
DOI = "https://doi.org/10.1145/2938436",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Sep 23 15:24:51 MDT 2016",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Whether or not the problem of finding maximal
independent sets (MIS) in hypergraphs is in (R)NC is
one of the fundamental problems in the theory of
parallel computing. Essentially, the challenge is to
design (randomized) algorithms in which the number of
processors used is polynomial and the (expected)
runtime is polylogarithmic in the size of the input.
Unlike the well-understood case of MIS in graphs, for
the hypergraph problem, our knowledge is quite limited
despite considerable work. It is known that the problem
is in RNC when the edges of the hypergraph have
constant size. For general hypergraphs with n vertices
and m edges, the fastest previously known algorithm
works in time $ O(\sqrt n) $ with $ \poly (m, n) $
processors. In this article, we give an EREW PRAM
randomized algorithm that works in time $ n^{o (1)} $
with $ O(n + m \log n) $ processors on general
hypergraphs satisfying $ m \leq n^{o (1) \log \log n /
\log \log \log n} $. We also give an EREW PRAM
deterministic algorithm that runs in time $ n^\epsilon
$ on a graph with $ m \leq n^{1 / \delta } $ edges, for
any constants $ \delta $, $ \epsilon $; the number of
processors is polynomial in $m$, $n$ for a fixed choice
of $ \delta $, $ \epsilon $. Our algorithms are based
on a sampling idea that reduces the dimension of the
hypergraph and employs the algorithm for constant
dimension hypergraphs as a subroutine.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "5",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Bilo:2016:LBN,
author = "Davide Bil{\`o} and Luciano Gual{\`a} and Stefano
Leucci and Guido Proietti",
title = "Locality-Based Network Creation Games",
journal = j-TOPC,
volume = "3",
number = "1",
pages = "6:1--6:??",
month = aug,
year = "2016",
CODEN = "????",
DOI = "https://doi.org/10.1145/2938426",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Sep 23 15:24:51 MDT 2016",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Network creation games have been extensively studied,
both by economists and computer scientists, due to
their versatility in modeling individual-based
community formation processes. These processes, in
turn, are the theoretical counterpart of several
economics, social, and computational applications on
the Internet. In their several variants, these games
model the tension of a player between the player's two
antagonistic goals: to be as close as possible to the
other players and to activate a cheapest possible set
of links. However, the generally adopted assumption is
that players have a common and complete information
about the ongoing network, which is quite unrealistic
in practice. In this article, we consider a more
compelling scenario in which players have only limited
information about the network in which they are
embedded. More precisely, we explore the game-theoretic
and computational implications of assuming that players
have a complete knowledge of the network structure only
up to a given radius k, which is one of the most
qualified local-knowledge models used in distributed
computing. In this respect, we define a suitable
equilibrium concept, and we provide a comprehensive set
of upper and lower bounds to the price of anarchy for
the entire range of values of k and for the two classic
variants of the game, namely, those in which a player's
cost-besides the activation cost of the owned
links-depends on the maximum/sum of all distances to
the other nodes in the network, respectively. These
bounds are assessed through an extensive set of
experiments.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "6",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Jiang:2016:PPA,
author = "Jiayang Jiang and Michael Mitzenmacher and Justin
Thaler",
title = "Parallel Peeling Algorithms",
journal = j-TOPC,
volume = "3",
number = "1",
pages = "7:1--7:??",
month = aug,
year = "2016",
CODEN = "????",
DOI = "https://doi.org/10.1145/2938412",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Sep 23 15:24:51 MDT 2016",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "The analysis of several algorithms and data structures
can be framed as a peeling process on a random
hypergraph: vertices with degree less than k are
removed until there are no vertices of degree less than
k left. The remaining hypergraph is known as the k
core. In this article, we analyze parallel peeling
processes, in which in each round, all vertices of
degree less than k are removed. It is known that, below
a specific edge-density threshold, the k -core is empty
with high probability. We show that, with high
probability, below this threshold, only $ 1 / \log ((k
- 1) (r - 1)) \log \log n + O (1) $ rounds of peeling
are needed to obtain the empty $k$-core for $ 4 b
r$-uniform hypergraphs. This bound is tight up to an
additive constant. Interestingly, we show that, above
this threshold, $ \Omega (\log n)$ rounds of peeling
are required to find the nonempty $k$-core. Since most
algorithms and data structures aim to peel to an empty
$k$-core, this asymmetry appears fortunate. We verify
the theoretical results both with simulation and with a
parallel implementation using graphics processing units
(GPUs). Our implementation provides insights into how
to structure parallel peeling algorithms for efficiency
in practice.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "7",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Simhadri:2016:EAS,
author = "Harsha Vardhan Simhadri and Guy E. Blelloch and Jeremy
T. Fineman and Phillip B. Gibbons and Aapo Kyrola",
title = "Experimental Analysis of Space-Bounded Schedulers",
journal = j-TOPC,
volume = "3",
number = "1",
pages = "8:1--8:??",
month = aug,
year = "2016",
CODEN = "????",
DOI = "https://doi.org/10.1145/2938389",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Sep 23 15:24:51 MDT 2016",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "The running time of nested parallel programs on
shared-memory machines depends in significant part on
how well the scheduler mapping the program to the
machine is optimized for the organization of caches and
processor cores on the machine. Recent work proposed
``space-bounded schedulers'' for scheduling such
programs on the multilevel cache hierarchies of current
machines. The main benefit of this class of schedulers
is that they provably preserve locality of the program
at every level in the hierarchy, which can result in
fewer cache misses and better use of bandwidth than the
popular work-stealing scheduler. On the other hand,
compared to work stealing, space-bounded schedulers are
inferior at load balancing and may have greater
scheduling overheads, raising the question as to the
relative effectiveness of the two schedulers in
practice. In this article, we provide the first
experimental study aimed at addressing this question.
To facilitate this study, we built a flexible
experimental framework with separate interfaces for
programs and schedulers. This enables a head-to-head
comparison of the relative strengths of schedulers in
terms of running times and cache miss counts across a
range of benchmarks. (The framework is validated by
comparisons with the Intel{\reg} CilkTM Plus
work-stealing scheduler.) We present experimental
results on a 32-core Xeon{\reg} 7560 comparing work
stealing, hierarchy-minded work stealing, and two
variants of space-bounded schedulers on both
divide-and-conquer microbenchmarks and some popular
algorithmic kernels. Our results indicate that
space-bounded schedulers reduce the number of L3 cache
misses compared to work-stealing schedulers by 25\% to
65\% for most of the benchmarks, but incur up to 27\%
additional scheduler and load-imbalance overhead. Only
for memory-intensive benchmarks can the reduction in
cache misses overcome the added overhead, resulting in
up to a 25\% improvement in running time for synthetic
benchmarks and about 20\% improvement for algorithmic
kernels. We also quantify runtime improvements varying
the available bandwidth per core (the ``bandwidth
gap'') and show up to 50\% improvements in the running
times of kernels as this gap increases fourfold. As
part of our study, we generalize prior definitions of
space-bounded schedulers to allow for more practical
variants (while still preserving their guarantees) and
explore implementation tradeoffs.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "8",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Sheikh:2016:SHJ,
author = "Hafiz Fahad Sheikh and Ishfaq Ahmad",
title = "Sixteen Heuristics for Joint Optimization of
Performance, Energy, and Temperature in Allocating
Tasks to Multi-Cores",
journal = j-TOPC,
volume = "3",
number = "2",
pages = "9:1--9:??",
month = aug,
year = "2016",
CODEN = "????",
DOI = "https://doi.org/10.1145/2948973",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Sep 23 15:24:52 MDT 2016",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Three-way joint optimization of performance ( P ),
energy ( E ), and temperature ( T ) in scheduling
parallel tasks to multiple cores poses a challenge that
is staggering in its computational complexity. The goal
of the PET optimized scheduling ( PETOS ) problem is to
minimize three quantities: the completion time of a
task graph, the total energy consumption, and the peak
temperature of the system. Algorithms based on
conventional multi-objective optimization techniques
can be designed for solving the PETOS problem. But
their execution times are exceedingly high and hence
their applicability is restricted merely to problems of
modest size. Exacerbating the problem is the solution
space that is typically a Pareto front since no single
solution can be strictly best along all three
objectives. Thus, not only is the absolute quality of
the solutions important but ``the spread of the
solutions'' along each objective and the distribution
of solutions within the generated tradeoff front are
also desired. A natural alternative is to design
efficient heuristic algorithms that can generate good
solutions as well as good spreads --- note that most of
the prior work in energy-efficient task allocation is
predominantly single- or dual-objective oriented. Given
a directed acyclic graph (DAG) representing a parallel
program, a heuristic encompasses policies as to what
tasks should go to what cores and at what frequency
should that core operate. Various policies, such as
greedy, iterative, and probabilistic, can be employed.
However, the choice and usage of these policies can
influence a heuristic towards a particular objective
and can also profoundly impact its performance. This
article proposes 16 heuristics that utilize various
methods for task-to-core allocation and frequency
selection. This article also presents a methodical
classification scheme which not only categorizes the
proposed heuristics but can also accommodate additional
heuristics. Extensive simulation experiments compare
these algorithms while shedding light on their
strengths and tradeoffs.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "9",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Blanchard:2016:SMO,
author = "Jeffrey D. Blanchard and Erik Opavsky and Emircan
Uysaler",
title = "Selecting Multiple Order Statistics with a Graphics
Processing Unit",
journal = j-TOPC,
volume = "3",
number = "2",
pages = "10:1--10:??",
month = aug,
year = "2016",
CODEN = "????",
DOI = "https://doi.org/10.1145/2948974",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Sep 23 15:24:52 MDT 2016",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Extracting a set of multiple order statistics from a
huge data set provides important information about the
distribution of the values in the full set of data.
This article introduces an algorithm,
bucketMultiSelect, for simultaneously selecting
multiple order statistics with a graphics processing
unit (GPU). Typically, when a large set of order
statistics is desired, the vector is sorted. When the
sorted version of the vector is not needed,
bucketMultiSelect significantly reduces computation
time by eliminating a large portion of the unnecessary
operations involved in sorting. For large vectors,
bucketMultiSelect returns thousands of order statistics
in less time than sorting the vector while typically
using less memory. For vectors containing $ 2^{28} $
values of type double, bucketMultiSelect selects the
101 percentile order statistics in less than 95ms and
is more than $ 8 \times $ faster than sorting the
vector with a GPU optimized merge sort.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "10",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Bohme:2016:IRC,
author = "David B{\"o}hme and Markus Geimer and Lukas Arnold and
Felix Voigtlaender and Felix Wolf",
title = "Identifying the Root Causes of Wait States in
Large-Scale Parallel Applications",
journal = j-TOPC,
volume = "3",
number = "2",
pages = "11:1--11:??",
month = aug,
year = "2016",
CODEN = "????",
DOI = "https://doi.org/10.1145/2934661",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Sep 23 15:24:52 MDT 2016",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Driven by growing application requirements and
accelerated by current trends in microprocessor design,
the number of processor cores on modern supercomputers
is increasing from generation to generation. However,
load or communication imbalance prevents many codes
from taking advantage of the available parallelism, as
delays of single processes may spread wait states
across the entire machine. Moreover, when employing
complex point-to-point communication patterns, wait
states may propagate along far-reaching cause-effect
chains that are hard to track manually and that
complicate an assessment of the actual costs of an
imbalance. Building on earlier work by Meira, Jr., et
al., we present a scalable approach that identifies
program wait states and attributes their costs in terms
of resource waste to their original cause. By replaying
event traces in parallel both forward and backward, we
can identify the processes and call paths responsible
for the most severe imbalances, even for runs with
hundreds of thousands of processes.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "11",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Dathathri:2016:CAL,
author = "Roshan Dathathri and Ravi Teja Mullapudi and Uday
Bondhugula",
title = "Compiling Affine Loop Nests for a Dynamic Scheduling
Runtime on Shared and Distributed Memory",
journal = j-TOPC,
volume = "3",
number = "2",
pages = "12:1--12:??",
month = aug,
year = "2016",
CODEN = "????",
DOI = "https://doi.org/10.1145/2948975",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Sep 23 15:24:52 MDT 2016",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Current de-facto parallel programming models like
OpenMP and MPI make it difficult to extract task-level
dataflow parallelism as opposed to bulk-synchronous
parallelism. Task parallel approaches that use
point-to-point synchronization between dependent tasks
in conjunction with dynamic scheduling dataflow
runtimes are thus becoming attractive. Although good
performance can be extracted for both shared and
distributed memory using these approaches, there is
little compiler support for them. In this article, we
describe the design of compiler--runtime interaction to
automatically extract coarse-grained dataflow
parallelism in affine loop nests for both shared and
distributed-memory architectures. We use techniques
from the polyhedral compiler framework to extract tasks
and generate components of the runtime that are used to
dynamically schedule the generated tasks. The runtime
includes a distributed decentralized scheduler that
dynamically schedules tasks on a node. The schedulers
on different nodes cooperate with each other through
asynchronous point-to-point communication, and all of
this is achieved by code automatically generated by the
compiler. On a set of six representative affine loop
nest benchmarks, while running on 32 nodes with 8
threads each, our compiler-assisted runtime yields a
geometric mean speedup of $ 143.6 \times $ ($ 70.3
\times $ to $ 474.7 \times $) over the sequential
version and a geometric mean speedup of $ 1.64 \times $
($ 1.04 \times $ to $ 2.42 \times $) over the
state-of-the-art automatic parallelization approach
that uses bulk synchronization. We also compare our
system with past work that addresses some of these
challenges on shared memory, and an emerging runtime
(Intel Concurrent Collections) that demands higher
programmer input and effort in parallelizing. To the
best of our knowledge, ours is also the first automatic
scheme that allows for dynamic scheduling of affine
loop nests on a cluster of multicores.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "12",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Benoit:2016:AGP,
author = "Anne Benoit and Aur{\'e}lien Cavelan and Yves Robert
and Hongyang Sun",
title = "Assessing General-Purpose Algorithms to Cope with
Fail-Stop and Silent Errors",
journal = j-TOPC,
volume = "3",
number = "2",
pages = "13:1--13:??",
month = aug,
year = "2016",
CODEN = "????",
DOI = "https://doi.org/10.1145/2897189",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Sep 23 15:24:52 MDT 2016",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "In this article, we combine the traditional
checkpointing and rollback recovery strategies with
verification mechanisms to cope with both fail-stop and
silent errors. The objective is to minimize makespan
and/or energy consumption. For divisible load
applications, we use first-order approximations to find
the optimal checkpointing period to minimize execution
time, with an additional verification mechanism to
detect silent errors before each checkpoint, hence
extending the classical formula by Young and Daly for
fail-stop errors only. We further extend the approach
to include intermediate verifications, and to consider
a bicriteria problem involving both time and energy
(linear combination of execution time and energy
consumption). Then, we focus on application workflows
whose dependence graph is a linear chain of tasks.
Here, we determine the optimal checkpointing and
verification locations, with or without intermediate
verifications, for the bicriteria problem. Rather than
using a single speed during the whole execution, we
further introduce a new execution scenario, which
allows for changing the execution speed via Dynamic
Voltage and Frequency Scaling (DVFS). In this latter
scenario, we determine the optimal checkpointing and
verification locations, as well as the optimal speed
pairs for each task segment between any two consecutive
checkpoints. Finally, we conduct an extensive set of
simulations to support the theoretical study, and to
assess the performance of each algorithm, showing that
the best overall performance is achieved under the most
flexible scenario using intermediate verifications and
different speeds.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "13",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Koutis:2016:SPD,
author = "Ioannis Koutis and Shen Chen Xu",
title = "Simple Parallel and Distributed Algorithms for
Spectral Graph Sparsification",
journal = j-TOPC,
volume = "3",
number = "2",
pages = "14:1--14:??",
month = aug,
year = "2016",
CODEN = "????",
DOI = "https://doi.org/10.1145/2948062",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Sep 23 15:24:52 MDT 2016",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "We describe simple algorithms for spectral graph
sparsification, based on iterative computations of
weighted spanners and sampling. Leveraging the
algorithms of Baswana and Sen for computing spanners,
we obtain the first distributed spectral sparsification
algorithm in the CONGEST model. We also obtain a
parallel algorithm with improved work and time
guarantees, as well as other natural distributed
implementations. Combining this algorithm with the
parallel framework of Peng and Spielman for solving
symmetric diagonally dominant linear systems, we get a
parallel solver that is significantly more efficient in
terms of the total work.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "14",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Dorier:2016:DAP,
author = "Matthieu Dorier and Gabriel Antoniu and Franck
Cappello and Marc Snir and Robert Sisneros and Orcun
Yildiz and Shadi Ibrahim and Tom Peterka and Leigh
Orf",
title = "{Damaris}: Addressing Performance Variability in Data
Management for Post-Petascale Simulations",
journal = j-TOPC,
volume = "3",
number = "3",
pages = "15:1--15:??",
month = dec,
year = "2016",
CODEN = "????",
DOI = "https://doi.org/10.1145/2987371",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Mon Dec 26 17:40:41 MST 2016",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "With exascale computing on the horizon, reducing
performance variability in data management tasks
(storage, visualization, analysis, etc.) is becoming a
key challenge in sustaining high performance. This
variability significantly impacts the overall
application performance at scale and its predictability
over time. In this article, we present Damaris, a
system that leverages dedicated cores in multicore
nodes to offload data management tasks, including I/O,
data compression, scheduling of data movements, in situ
analysis, and visualization. We evaluate Damaris with
the CM1 atmospheric simulation and the Nek5000
computational fluid dynamic simulation on four
platforms, including NICS's Kraken and NCSA's Blue
Waters. Our results show that (1) Damaris fully hides
the I/O variability as well as all I/O-related costs,
thus making simulation performance predictable; (2) it
increases the sustained write throughput by a factor of
up to 15 compared with standard I/O approaches; (3) it
allows almost perfect scalability of the simulation up
to over 9,000 cores, as opposed to state-of-the-art
approaches that fail to scale; and (4) it enables a
seamless connection to the VisIt visualization software
to perform in situ analysis and visualization in a way
that impacts neither the performance of the simulation
nor its variability. In addition, we extended our
implementation of Damaris to also support the use of
dedicated nodes and conducted a thorough comparison of
the two approaches-dedicated cores and dedicated
nodes-for I/O tasks with the aforementioned
applications.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "15",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Gao:2016:AOM,
author = "Jiaquan Gao and Yu Wang and Jun Wang and Ronghua
Liang",
title = "Adaptive Optimization Modeling of Preconditioned
Conjugate Gradient on Multi-{GPUs}",
journal = j-TOPC,
volume = "3",
number = "3",
pages = "16:1--16:??",
month = dec,
year = "2016",
CODEN = "????",
DOI = "https://doi.org/10.1145/2990849",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Mon Dec 26 17:40:41 MST 2016",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "The preconditioned conjugate gradient (PCG) algorithm
is a well-known iterative method for solving sparse
linear systems in scientific computations.
GPU-accelerated PCG algorithms for large-sized problems
have attracted considerable attention recently.
However, on a specific multi-GPU platform, producing a
highly parallel PCG implementation for any large-sized
problem requires significant time because several
manual steps are involved in adjusting the related
parameters and selecting an appropriate storage format
for the matrix block that is assigned to each GPU. This
motivates us to propose adaptive optimization modeling
of PCG on multi-GPUs, which mainly involves the
following parts: (1) an optimization multi-GPU parallel
framework of PCG and (2) the profile-based optimization
modeling for each one of the main components of the PCG
algorithm, including vector operation, inner product,
and sparse matrix-vector multiplication (SpMV). Our
model does not construct a new storage format or kernel
but automatically and rapidly generates an optimal
parallel PCG algorithm for any problem on a specific
multi-GPU platform by integrating existing storage
formats and kernels. We take a vector operation kernel,
an inner-product kernel, and five popular SpMV kernels
for an example to present the idea of constructing the
model. Given that our model is general, independent of
the problems, and dependent on the resources of
devices, this model is constructed only once for each
type of GPU. The experiments validate the high
efficiency of our proposed model.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "16",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Creech:2016:TSS,
author = "Timothy Creech and Rajeev Barua",
title = "Transparently Space Sharing a Multicore Among Multiple
Processes",
journal = j-TOPC,
volume = "3",
number = "3",
pages = "17:1--17:??",
month = dec,
year = "2016",
CODEN = "????",
DOI = "https://doi.org/10.1145/3001910",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Mon Dec 26 17:40:41 MST 2016",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "As hardware becomes increasingly parallel and the
availability of scalable parallel software improves,
the problem of managing multiple multithreaded
applications (processes) becomes important. Malleable
processes, which can vary the number of threads used as
they run, enable sophisticated and flexible resource
management. Although many existing applications
parallelized for SMPs with parallel runtimes are in
fact already malleable, deployed runtime environments
provide no interface nor any strategy for intelligently
allocating hardware threads or even preventing
oversubscription. Prior research methods either depend
on profiling applications ahead of time to make good
decisions about allocations or do not account for
process efficiency at all, leading to poor performance.
None of these prior methods have been adapted widely in
practice. This article presents the Scheduling and
Allocation with Feedback (SCAF) system: a drop-in
runtime solution that supports existing malleable
applications in making intelligent allocation decisions
based on observed efficiency without any changes to
semantics, program modification, offline profiling, or
even recompilation. Our existing implementation can
control most unmodified OpenMP applications. Other
malleable threading libraries can also easily be
supported with small modifications without requiring
application modification or recompilation. In this
work, we present the SCAF daemon and a SCAF-aware port
of the GNU OpenMP runtime. We present a new technique
for estimating process efficiency purely at runtime
using available hardware counters and demonstrate its
effectiveness in aiding allocation decisions. We
evaluated SCAF using NAS NPB parallel benchmarks on
five commodity parallel platforms, enumerating
architectural features and their effects on our scheme.
We measured the benefit of SCAF in terms of sum of
speedups improvement (a common metric for
multiprogrammed environments) when running all
benchmark pairs concurrently compared to
equipartitioning-the best existing competing scheme in
the literature. We found that SCAF improves on
equipartitioning on four out of five machines, showing
a mean improvement factor in sum of speedups of 1.04 to
1.11x for benchmark pairs, depending on the machine,
and 1.09x on average. Since we are not aware of any
widely available tool for equipartitioning, we also
compare SCAF against multiprogramming using unmodified
OpenMP, which is the only environment available to end
users today. SCAF improves on the unmodified OpenMP
runtimes for all five machines, with a mean improvement
of 1.08 to 2.07x, depending on the machine, and 1.59x
on average.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "17",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Ballard:2016:HPS,
author = "Grey Ballard and Alex Druinsky and Nicholas Knight and
Oded Schwartz",
title = "Hypergraph Partitioning for Sparse Matrix--Matrix
Multiplication",
journal = j-TOPC,
volume = "3",
number = "3",
pages = "18:1--18:??",
month = dec,
year = "2016",
CODEN = "????",
DOI = "https://doi.org/10.1145/3015144",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Mon Dec 26 17:40:41 MST 2016",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "We propose a fine-grained hypergraph model for sparse
matrix-matrix multiplication (SpGEMM), a key
computational kernel in scientific computing and data
analysis whose performance is often communication
bound. This model correctly describes both the
interprocessor communication volume along a critical
path in a parallel computation and also the volume of
data moving through the memory hierarchy in a
sequential computation. We show that identifying a
communication-optimal algorithm for particular input
matrices is equivalent to solving a hypergraph
partitioning problem. Our approach is nonzero structure
dependent, meaning that we seek the best algorithm for
the given input matrices. In addition to our
three-dimensional fine-grained model, we also propose
coarse-grained one-dimensional and two-dimensional
models that correspond to simpler SpGEMM algorithms. We
explore the relations between our models theoretically,
and we study their performance experimentally in the
context of three applications that use SpGEMM as a key
computation. For each application, we find that at
least one coarse-grained model is as communication
efficient as the fine-grained model. We also observe
that different applications have affinities for
different algorithms. Our results demonstrate that
hypergraphs are an accurate model for reasoning about
the communication costs of SpGEMM as well as a
practical tool for exploring the SpGEMM algorithm
design space.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "18",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Grove:2017:ISS,
author = "David Grove",
title = "Introduction to the Special Section on {PPoPP'15}",
journal = j-TOPC,
volume = "3",
number = "4",
pages = "19:1--19:??",
month = mar,
year = "2017",
CODEN = "????",
DOI = "https://doi.org/10.1145/3040224",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Sat Mar 25 07:55:06 MDT 2017",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "19",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Majo:2017:LPC,
author = "Zoltan Majo and Thomas R. Gross",
title = "A Library for Portable and Composable Data Locality
Optimizations for {NUMA} Systems",
journal = j-TOPC,
volume = "3",
number = "4",
pages = "20:1--20:??",
month = mar,
year = "2017",
CODEN = "????",
DOI = "https://doi.org/10.1145/3040222",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Sat Mar 25 07:55:06 MDT 2017",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Many recent multiprocessor systems are realized with a
nonuniform memory architecture (NUMA) and accesses to
remote memory locations take more time than local
memory accesses. Optimizing NUMA memory system
performance is difficult and costly for three principal
reasons: (1) Today's programming languages/libraries
have no explicit support for NUMA systems, (2) NUMA
optimizations are not portable, and (3) optimizations
are not composable (i.e., they can become ineffective
or worsen performance in environments that support
composable parallel software). This article presents
TBB-NUMA, a parallel programming library based on Intel
Threading Building Blocks (TBB) that supports portable
and composable NUMA-aware programming. TBB-NUMA
provides a model of task affinity that captures a
programmer's insights on mapping tasks to resources.
NUMA-awareness affects all layers of the library (i.e.,
resource management, task scheduling, and high-level
parallel algorithm templates) and requires close
coupling between all these layers. Optimizations
implemented with TBB-NUMA (for a set of standard
benchmark programs) result in up to 44\% performance
improvement over standard TBB. But more important,
optimized programs are portable across different NUMA
architectures and preserve data locality also when
composed with other parallel computations sharing the
same resource management layer.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "20",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Golan-Gueta:2017:ASA,
author = "Guy Golan-Gueta and G. Ramalingam and Mooly Sagiv and
Eran Yahav",
title = "Automatic Scalable Atomicity via Semantic Locking",
journal = j-TOPC,
volume = "3",
number = "4",
pages = "21:1--21:??",
month = mar,
year = "2017",
CODEN = "????",
DOI = "https://doi.org/10.1145/3040223",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Sat Mar 25 07:55:06 MDT 2017",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "In this article, we consider concurrent programs in
which the shared state consists of instances of
linearizable abstract data types (ADTs). We present an
automated approach to concurrency control that
addresses a common need: the need to atomically execute
a code fragment, which may contain multiple ADT
operations on multiple ADT instances. We present a
synthesis algorithm that automatically enforces
atomicity of given code fragments (in a client program)
by inserting pessimistic synchronization that
guarantees atomicity and deadlock-freedom (without
using any rollback mechanism). Our algorithm takes a
commutativity specification as an extra input. This
specification indicates for every pair of ADT
operations the conditions under which the operations
commute. Our algorithm enables greater parallelism by
permitting commuting operations to execute
concurrently. We have implemented the synthesis
algorithm in a Java compiler and applied it to several
Java programs. Our results show that our approach
produces efficient and scalable synchronization.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "21",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Izraelevitz:2017:GSN,
author = "Joseph Izraelevitz and Michael L. Scott",
title = "Generality and Speed in Nonblocking Dual Containers",
journal = j-TOPC,
volume = "3",
number = "4",
pages = "22:1--22:??",
month = mar,
year = "2017",
CODEN = "????",
DOI = "https://doi.org/10.1145/3040220",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Sat Mar 25 07:55:06 MDT 2017",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Nonblocking dual data structures extend traditional
notions of nonblocking progress to accommodate partial
methods, both by bounding the number of steps that a
thread can execute after its preconditions have been
satisfied and by ensuring that a waiting thread
performs no remote memory accesses that could interfere
with the execution of other threads. A nonblocking dual
container, in particular, is designed to hold either
data or requests. An insert operation either adds data
to the container or removes and satisfies a request; a
remove operation either takes data out of the container
or inserts a request. We present the first
general-purpose construction for nonblocking dual
containers, allowing any nonblocking container for data
to be paired with almost any nonblocking container for
requests. We also present new custom algorithms, based
on the LCRQ of Morrison and Afek, that outperform the
fastest previously known dual containers by factors of
four to six.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "22",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Cole:2017:ROS,
author = "Richard Cole and Vijaya Ramachandran",
title = "Resource Oblivious Sorting on Multicores",
journal = j-TOPC,
volume = "3",
number = "4",
pages = "23:1--23:??",
month = mar,
year = "2017",
CODEN = "????",
DOI = "https://doi.org/10.1145/3040221",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Sat Mar 25 07:55:06 MDT 2017",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "We present a deterministic sorting algorithm, Sample,
Partition, and Merge Sort (SPMS), that interleaves the
partitioning of a sample sort with merging.
Sequentially, it sorts $n$ elements in $ O(n \log n)$
time cache-obliviously with an optimal number of cache
misses. The parallel complexity (or critical path
length) of the algorithm is $ O(\log n \log \log n)$,
which improves on previous bounds for deterministic
sample sort. The algorithm also has low false sharing
costs. When scheduled by a work-stealing scheduler in a
multicore computing environment with a global shared
memory and p cores, each having a cache of size $M$
organized in blocks of size $B$, the costs of the
additional cache misses and false sharing misses due to
this parallel execution are bounded by the cost of $
O(S \cdot M / B)$ and $ O(S \cdot B)$ cache misses,
respectively, where $S$ is the number of steals
performed during the execution. Finally, SPMS is
resource oblivious in that the dependence on machine
parameters appear only in the analysis of its
performance and not within the algorithm itself.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "23",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Ballard:2017:GEIa,
author = "Grey Ballard and Mary Hall and Tim Harris and Brandon
Lucia",
title = "{Guest Editor} Introduction {PPoPP 2016}, Special
Issue 2 of 2",
journal = j-TOPC,
volume = "4",
number = "1",
pages = "1:1--1:??",
month = oct,
year = "2017",
CODEN = "????",
DOI = "https://doi.org/10.1145/3108141",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Oct 10 17:42:07 MDT 2017",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "1",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Ashkiani:2017:GME,
author = "Saman Ashkiani and Andrew Davidson and Ulrich Meyer
and John D. Owens",
title = "{GPU Multisplit}: an Extended Study of a Parallel
Algorithm",
journal = j-TOPC,
volume = "4",
number = "1",
pages = "2:1--2:??",
month = oct,
year = "2017",
CODEN = "????",
DOI = "https://doi.org/10.1145/3108139",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Oct 10 17:42:07 MDT 2017",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Multisplit is a broadly useful parallel primitive that
permutes its input data into contiguous buckets or
bins, where the function that categorizes an element
into a bucket is provided by the programmer. Due to the
lack of an efficient multisplit on Graphics Processing
Units (GPUs), programmers often choose to implement
multisplit with a sort. One way is to first generate an
auxiliary array of bucket IDs and then sort input data
based on it. In case smaller indexed buckets possess
smaller valued keys, another way for multisplit is to
directly sort input data. Both methods are inefficient
and require more work than necessary: The former
requires more expensive data movements while the latter
spends unnecessary effort in sorting elements within
each bucket. In this work, we provide a parallel model
and multiple implementations for the multisplit
problem. Our principal focus is multisplit for a small
(up to 256) number of buckets. We use warp-synchronous
programming models and emphasize warpwide
communications to avoid branch divergence and reduce
memory usage. We also hierarchically reorder input
elements to achieve better coalescing of global memory
accesses. On a GeForce GTX 1080 GPU, we can reach a
peak throughput of 18.93Gkeys/s (or 11.68Gpairs/s) for
a key-only (or key-value) multisplit. Finally, we
demonstrate how multisplit can be used as a building
block for radix sort. In our multisplit-based sort
implementation, we achieve comparable performance to
the fastest GPU sort routines, sorting 32-bit keys (and
key-value pairs) with a throughput of 3.0Gkeys/s (and
2.1Gpair/s).",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "2",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Wang:2017:GGG,
author = "Yangzihao Wang and Yuechao Pan and Andrew Davidson and
Yuduo Wu and Carl Yang and Leyuan Wang and Muhammad
Osama and Chenshan Yuan and Weitang Liu and Andy T.
Riffel and John D. Owens",
title = "{Gunrock}: {GPU} Graph Analytics",
journal = j-TOPC,
volume = "4",
number = "1",
pages = "3:1--3:??",
month = oct,
year = "2017",
CODEN = "????",
DOI = "https://doi.org/10.1145/3108140",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Oct 10 17:42:07 MDT 2017",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "For large-scale graph analytics on the GPU, the
irregularity of data access and control flow, and the
complexity of programming GPUs, have presented two
significant challenges to developing a programmable
high-performance graph library. ``Gunrock,'' our
graph-processing system designed specifically for the
GPU, uses a high-level, bulk-synchronous, data-centric
abstraction focused on operations on a vertex or edge
frontier. Gunrock achieves a balance between
performance and expressiveness by coupling
high-performance GPU computing primitives and
optimization strategies with a high-level programming
model that allows programmers to quickly develop new
graph primitives with small code size and minimal GPU
programming knowledge. We characterize the performance
of various optimization strategies and evaluate
Gunrock's overall performance on different GPU
architectures on a wide range of graph primitives that
span from traversal-based algorithms and ranking
algorithms, to triangle counting and
bipartite-graph-based algorithms. The results show that
on a single GPU, Gunrock has on average at least an
order of magnitude speedup over Boost and PowerGraph,
comparable performance to the fastest GPU hardwired
primitives and CPU shared-memory graph libraries, such
as Ligra and Galois, and better performance than any
other GPU high-level graph library.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "3",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Chowdhury:2017:AAD,
author = "Rezaul Chowdhury and Pramod Ganapathi and Stephen
Tschudi and Jesmin Jahan Tithi and Charles Bachmeier
and Charles E. Leiserson and Armando Solar-Lezama and
Bradley C. Kuszmaul and Yuan Tang",
title = "{Autogen}: Automatic Discovery of Efficient Recursive
Divide-\&-Conquer Algorithms for Solving Dynamic
Programming Problems",
journal = j-TOPC,
volume = "4",
number = "1",
pages = "4:1--4:??",
month = oct,
year = "2017",
CODEN = "????",
DOI = "https://doi.org/10.1145/3125632",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Oct 10 17:42:07 MDT 2017",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "We present Autogen --- an algorithm that for a wide
class of dynamic programming (DP) problems
automatically discovers highly efficient
cache-oblivious parallel recursive divide-and-conquer
algorithms from inefficient iterative descriptions of
DP recurrences. Autogen analyzes the set of DP table
locations accessed by the iterative algorithm when run
on a DP table of small size and automatically
identifies a recursive access pattern and a
corresponding provably correct recursive algorithm for
solving the DP recurrence. We use Autogen to
autodiscover efficient algorithms for several
well-known problems. Our experimental results show that
several autodiscovered algorithms significantly
outperform parallel looping and tiled loop-based
algorithms. Also, these algorithms are less sensitive
to fluctuations of memory and bandwidth compared with
their looping counterparts, and their running times and
energy profiles remain relatively more stable. To the
best of our knowledge, Autogen is the first algorithm
that can automatically discover new nontrivial
divide-and-conquer algorithms.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "4",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Steele:2017:AAC,
author = "Guy L. {Steele Jr.} and Jean-Baptiste Tristan",
title = "Adding Approximate Counters",
journal = j-TOPC,
volume = "4",
number = "1",
pages = "5:1--5:??",
month = oct,
year = "2017",
CODEN = "????",
DOI = "https://doi.org/10.1145/3132167",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Oct 10 17:42:07 MDT 2017",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "We describe a general framework for adding the values
of two approximate counters to produce a new
approximate counter value whose expected estimated
value is equal to the sum of the expected estimated
values of the given approximate counters. (To the best
of our knowledge, this is the first published
description of any algorithm for adding two approximate
counters.) We then work out implementation details for
five different kinds of approximate counter and provide
optimized pseudocode. For three of them, we present
proofs that the variance of a counter value produced by
adding two counter values in this way is bounded, and
in fact is no worse, or not much worse, than the
variance of the value of a single counter to which the
same total number of increment operations have been
applied. Addition of approximate counters is useful in
massively parallel divide-and-conquer algorithms that
use a distributed representation for large arrays of
counters. We describe two machine-learning algorithms
for topic modeling that use millions of integer
counters and confirm that replacing the integer
counters with approximate counters is effective,
speeding up a GPU-based implementation by over 65\% and
a CPU-based implementation by nearly 50\%, as well as
reducing memory requirements, without degrading their
statistical effectiveness.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "5",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Ballard:2017:GEIb,
author = "Grey Ballard and Mary Hall and Tim Harris and Brandon
Lucia",
title = "{Guest Editor} Introduction {PPoPP 2016}, Special
Issue 2 of 2",
journal = j-TOPC,
volume = "4",
number = "2",
pages = "6:1--6:??",
month = oct,
year = "2017",
CODEN = "????",
DOI = "https://doi.org/10.1145/3108142",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Oct 10 17:42:07 MDT 2017",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "6",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Kalikar:2017:DNM,
author = "Saurabh Kalikar and Rupesh Nasre",
title = "{DomLock}: a New Multi-Granularity Locking Technique
for Hierarchies",
journal = j-TOPC,
volume = "4",
number = "2",
pages = "7:1--7:??",
month = oct,
year = "2017",
CODEN = "????",
DOI = "https://doi.org/10.1145/3127584",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Oct 10 17:42:07 MDT 2017",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "We present efficient locking mechanisms for
hierarchical data structures. Several applications work
on an abstract hierarchy of objects, and a parallel
execution on this hierarchy necessitates
synchronization across workers operating on different
parts of the hierarchy. Existing synchronization
mechanisms are too coarse, too inefficient, or too ad
hoc, resulting in reduced or unpredictable amount of
concurrency. We propose a new locking approach based on
the structural properties of the underlying hierarchy.
We show that the developed techniques are efficient
even when the hierarchy is an arbitrary graph.
Theoretically, we present our approach as a
locking-cost-minimizing instance of a generic algebraic
model of synchronization for hierarchies. Using
STMBench7, we illustrate considerable reduction in the
locking cost, resulting in an average throughput
improvement of 42\%.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "7",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Haider:2017:LRA,
author = "Syed Kamran Haider and William Hasenplaugh and Dan
Alistarh",
title = "{Lease\slash Release}: Architectural Support for
Scaling Contended Data Structures",
journal = j-TOPC,
volume = "4",
number = "2",
pages = "8:1--8:??",
month = oct,
year = "2017",
CODEN = "????",
DOI = "https://doi.org/10.1145/3132168",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Oct 10 17:42:07 MDT 2017",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "High memory contention is generally agreed to be a
worst-case scenario for concurrent data structures.
There has been a significant amount of research effort
spent investigating designs that minimize contention,
and several programming techniques have been proposed
to mitigate its effects. However, there are currently
few architectural mechanisms to allow scaling contended
data structures at high thread counts. In this article,
we investigate hardware support for scalable contended
data structures. We propose Lease/Release, a simple
addition to standard directory-based MESI cache
coherence protocols, allowing participants to lease
memory, at the granularity of cache lines, by delaying
coherence messages for a short, bounded period of time.
Our analysis shows that Lease/Release can significantly
reduce the overheads of contention for both
non-blocking (lock-free) and lock-based data structure
implementations while ensuring that no deadlocks are
introduced. We validate Lease/Release empirically on
the Graphite multiprocessor simulator on a range of
data structures, including queue, stack, and priority
queue implementations, as well as on transactional
applications. Results show that Lease/Release
consistently improves both throughput and energy usage,
by up to 5x, both for lock-free and lock-based data
structure designs.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "8",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Cao:2017:HRD,
author = "Man Cao and Minjia Zhang and Aritra Sengupta and
Swarnendu Biswas and Michael D. Bond",
title = "Hybridizing and Relaxing Dependence Tracking for
Efficient Parallel Runtime Support",
journal = j-TOPC,
volume = "4",
number = "2",
pages = "9:1--9:??",
month = oct,
year = "2017",
CODEN = "????",
DOI = "https://doi.org/10.1145/3108138",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Oct 10 17:42:07 MDT 2017",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "It is notoriously challenging to develop parallel
software systems that are both scalable and correct.
Runtime support for parallelism-such as multithreaded
record and replay, data race detectors, transactional
memory, and enforcement of stronger memory models-helps
achieve these goals, but existing commodity solutions
slow programs substantially to track (i.e., detect or
control) an execution's cross-thread dependencies
accurately. Prior work tracks cross-thread dependencies
either ``pessimistically,'' slowing every program
access, or ``optimistically,'' allowing for lightweight
instrumentation of most accesses but dramatically
slowing accesses that are conflicting (i.e., involved
in cross-thread dependencies). This article presents
two novel approaches that seek to improve the
performance of dependence tracking. Hybrid tracking
(HT) hybridizes pessimistic and optimistic tracking by
overcoming a fundamental mismatch between these two
kinds of tracking. HT uses an adaptive, profile-based
policy to make runtime decisions about switching
between pessimistic and optimistic tracking. Relaxed
tracking (RT) attempts to reduce optimistic tracking's
overhead on conflicting accesses by tracking
dependencies in a ``relaxed'' way-meaning that not all
dependencies are tracked accurately-while still
preserving both program semantics and runtime support's
correctness. To demonstrate the usefulness and
potential of HT and RT, we build runtime support based
on the two approaches. Our evaluation shows that both
approaches offer performance advantages over existing
approaches, but there exist challenges and
opportunities for further improvement. HT and RT are
distinct solutions to the same problem. It is easier to
build runtime support based on HT than on RT, although
RT does not incur the overhead of online profiling.
This article presents the two approaches together to
inform and inspire future designs for efficient
parallel runtime support.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "9",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Chatzopoulos:2017:EES,
author = "Georgios Chatzopoulos and Aleksandar Dragojevi{\'c}
and Rachid Guerraoui",
title = "{ESTIMA}: Extrapolating {ScalabiliTy} of In-Memory
Applications",
journal = j-TOPC,
volume = "4",
number = "2",
pages = "10:1--10:??",
month = oct,
year = "2017",
CODEN = "????",
DOI = "https://doi.org/10.1145/3108137",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Oct 10 17:42:07 MDT 2017",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "This article presents estima, an easy-to-use tool for
extrapolating the scalability of in-memory
applications. estima is designed to perform a simple
yet important task: Given the performance of an
application on a small machine with a handful of cores,
estima extrapolates its scalability to a larger machine
with more cores, while requiring minimum input from the
user. The key idea underlying estima is the use of
stalled cycles (e.g., cycles that the processor spends
waiting for missed cache line fetches or busy locks).
estima measures stalled cycles on a few cores and
extrapolates them to more cores, estimating the amount
of waiting in the system. estima can be effectively
used to predict the scalability of in-memory
applications for bigger execution machines. For
instance, using measurements of memcached and SQLite on
a desktop machine, we obtain accurate predictions of
their scalability on a server. Our extensive evaluation
shows the effectiveness of estima on a large number of
in-memory benchmarks.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "10",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Gulisano:2017:EDS,
author = "Vincenzo Gulisano and Yiannis Nikolakopoulos and
Daniel Cederman and Marina Papatriantafilou and
Philippas Tsigas",
title = "Efficient Data Streaming Multiway Aggregation through
Concurrent Algorithmic Designs and New Abstract Data
Types",
journal = j-TOPC,
volume = "4",
number = "2",
pages = "11:1--11:??",
month = oct,
year = "2017",
CODEN = "????",
DOI = "https://doi.org/10.1145/3131272",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Oct 10 17:42:07 MDT 2017",
bibsource = "http://topc.acm.org/;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Data streaming relies on continuous queries to process
unbounded streams of data in a real-time fashion. It is
commonly demanding in computation capacity, given that
the relevant applications involve very large volumes of
data. Data structures act as articulation points and
maintain the state of data streaming operators,
potentially supporting high parallelism and balancing
the work among them. Prompted by this fact, in this
work we study and analyze parallelization needs of
these articulation points, focusing on the problem of
streaming multiway aggregation, where large data
volumes are received from multiple input streams. The
analysis of the parallelization needs, as well as of
the use and limitations of existing aggregate designs
and their data structures, leads us to identify needs
for appropriate shared objects that can achieve
low-latency and high-throughput multiway aggregation.
We present the requirements of such objects as abstract
data types and we provide efficient lock-free
linearizable algorithmic implementations of them, along
with new multiway aggregate algorithmic designs that
leverage them, supporting both deterministic
order-sensitive and order-insensitive aggregate
functions. Furthermore, we point out future directions
that open through these contributions. The article
includes an extensive experimental study, based on a
variety of continuous aggregation queries on two large
datasets extracted from SoundCloud, a music social
network, and from a Smart Grid network. In all the
experiments, the proposed data structures and the
enhanced aggregate operators improved the processing
performance significantly, up to one order of
magnitude, in terms of both throughput and latency,
over the commonly used techniques based on queues.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "11",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Malas:2018:MIP,
author = "Tareq M. Malas and Georg Hager and Hatem Ltaief and
David E. Keyes",
title = "Multidimensional Intratile Parallelization for
Memory-Starved Stencil Computations",
journal = j-TOPC,
volume = "4",
number = "3",
pages = "12:1--12:??",
month = apr,
year = "2018",
CODEN = "????",
DOI = "https://doi.org/10.1145/3155290",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Jan 23 16:12:25 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Optimizing the performance of stencil algorithms has
been the subject of intense research over the last two
decades. Since many stencil schemes have low arithmetic
intensity, most optimizations focus on increasing the
temporal data access locality, thus reducing the data
traffic through the main memory interface with the
ultimate goal of decoupling from this bottleneck. There
are, however, only a few approaches that explicitly
leverage the shared cache feature of modern multicore
chips. If every thread works on its private, separate
cache block, the available cache space can become too
small, and sufficient temporal locality may not be
achieved. We propose a flexible multidimensional
intratile parallelization method for stencil algorithms
on multicore CPUs with a shared outer-level cache. This
method leads to a significant reduction in the required
cache space without adverse effects from hardware
prefetching or TLB shortage. Our Girih framework
includes an autotuner to select optimal parameter
configurations on the target hardware. We conduct
performance experiments on two contemporary Intel
processors and compare with the state-of-the-art
stencil frameworks Pluto and Pochoir, using four
corner-case stencil schemes and a wide range of problem
sizes. Girih shows substantial performance advantages
and best arithmetic intensity at almost all problem
sizes, especially on low-intensity stencils with
variable coefficients. We study in detail the
performance behavior at varying grid sizes using
phenomenological performance modeling. Our analysis of
energy consumption reveals that our method can save
energy through reduced DRAM bandwidth usage even at a
marginal performance gain. It is thus well suited for
future architectures that will be strongly challenged
by the cost of data movement, be it in terms of
performance or energy consumption.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "12",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Akbudak:2018:PMS,
author = "Kadir Akbudak and Oguz Selvitopi and Cevdet Aykanat",
title = "Partitioning Models for Scaling Parallel Sparse
Matrix--Matrix Multiplication",
journal = j-TOPC,
volume = "4",
number = "3",
pages = "13:1--13:??",
month = apr,
year = "2018",
CODEN = "????",
DOI = "https://doi.org/10.1145/3155292",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Jan 23 16:12:25 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "We investigate outer-product--parallel,
inner-product--parallel, and
row-by-row-product--parallel formulations of sparse
matrix-matrix multiplication (SpGEMM) on distributed
memory architectures. For each of these three
formulations, we propose a hypergraph model and a
bipartite graph model for distributing SpGEMM
computations based on one-dimensional (1D) partitioning
of input matrices. We also propose a communication
hypergraph model for each formulation for distributing
communication operations. The computational graph and
hypergraph models adopted in the first phase aim at
minimizing the total message volume and balancing the
computational loads of processors, whereas the
communication hypergraph models adopted in the second
phase aim at minimizing the total message count and
balancing the message volume loads of processors. That
is, the computational partitioning models reduce the
bandwidth cost and the communication hypergraph models
reduce the latency cost. Our extensive parallel
experiments on up to 2048 processors for a wide range
of realistic SpGEMM instances show that although the
outer-product--parallel formulation scales better, the
row-by-row-product--parallel formulation is more viable
due to its significantly lower partitioning overhead
and competitive scalability. For computational
partitioning models, our experimental findings indicate
that the proposed bipartite graph models are attractive
alternatives to their hypergraph counterparts because
of their lower partitioning overhead. Finally, we show
that by reducing the latency cost besides the bandwidth
cost through using the communication hypergraph models,
the parallel SpGEMM time can be further improved up to
32\%.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "13",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Bilardi:2018:LBT,
author = "Gianfranco Bilardi and Michele Scquizzato and
Francesco Silvestri",
title = "A Lower Bound Technique for Communication in {BSP}",
journal = j-TOPC,
volume = "4",
number = "3",
pages = "14:1--14:??",
month = apr,
year = "2018",
CODEN = "????",
DOI = "https://doi.org/10.1145/3181776",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Jan 23 16:12:25 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Communication is a major factor determining the
performance of algorithms on current computing systems;
it is therefore valuable to provide tight lower bounds
on the communication complexity of computations. This
article presents a lower bound technique for the
communication complexity in the bulk-synchronous
parallel (BSP) model of a given class of DAG
computations. The derived bound is expressed in terms
of the switching potential of a DAG, that is, the
number of permutations that the DAG can realize when
viewed as a switching network. The proposed technique
yields tight lower bounds for the fast Fourier
transform (FFT), and for any sorting and permutation
network. A stronger bound is also derived for the
periodic balanced sorting network, by applying this
technique to suitable subnetworks. Finally, we
demonstrate that the switching potential captures
communication requirements even in computational models
different from BSP, such as the I/O model and the
LPRAM.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "14",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Sahin:2018:CSC,
author = "Semih Sahin and Bugra Gedik",
title = "{C-Stream}: a Co-routine-Based Elastic Stream
Processing Engine",
journal = j-TOPC,
volume = "4",
number = "3",
pages = "15:1--15:??",
month = apr,
year = "2018",
CODEN = "????",
DOI = "https://doi.org/10.1145/3184120",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Jan 23 16:12:25 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/multithreading.bib;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Stream processing is a computational paradigm for
on-the-fly processing of live data. This paradigm lends
itself to implementations that can provide high
throughput and low latency by taking advantage of
various forms of parallelism that are naturally
captured by the stream processing model of computation,
such as pipeline, task, and data parallelism. In this
article, we describe the design and implementation of
C-Stream, which is an elastic stream processing engine.
C-Stream encompasses three unique properties. First, in
contrast to the widely adopted event-based interface
for developing streaming operators, C-Stream provides
an interface wherein each operator has its own driver
loop and relies on data availability application
programming interfaces (APIs) to decide when to perform
its computations. This self-control-based model
significantly simplifies the development of operators
that require multiport synchronization. Second,
C-Stream contains a dynamic scheduler that manages the
multithreaded execution of the operators. The
scheduler, which is customizable via plug-ins, enables
the execution of the operators as co-routines, using
any number of threads. The base scheduler implements
back-pressure, provides data availability APIs, and
manages preemption and termination handling. Last,
C-Stream varies the degree of parallelism to resolve
bottlenecks by both dynamically changing the number of
threads used to execute an application and adjusting
the number of replicas of data-parallel operators. We
provide an experimental evaluation of C-Stream. The
results show that C-Stream is scalable, highly
customizable, and can resolve bottlenecks by
dynamically adjusting the level of data parallelism
used.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "15",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Agrawal:2018:ISI,
author = "Kunal Agrawal and I-Ting Angelina Lee and Michael
Spear",
title = "Introduction to Special Issue on {SPAA'15}",
journal = j-TOPC,
volume = "4",
number = "4",
pages = "16:1--16:??",
month = sep,
year = "2018",
CODEN = "????",
DOI = "https://doi.org/10.1145/3226041",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Jan 23 16:12:25 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "16",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Ahn:2018:ADN,
author = "Kook Jin Ahn and Sudipto Guha",
title = "Access to Data and Number of Iterations: Dual Primal
Algorithms for Maximum Matching under Resource
Constraints",
journal = j-TOPC,
volume = "4",
number = "4",
pages = "17:1--17:??",
month = sep,
year = "2018",
CODEN = "????",
DOI = "https://doi.org/10.1145/3154855",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Jan 23 16:12:25 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "In this article, we consider graph algorithms in
models of computation where the space usage (random
accessible storage, in addition to the read-only input)
is sublinear in the number of edges $m$ and the access
to input is constrained. These questions arise in many
natural settings, and in particular in the analysis of
streaming algorithms, MapReduce or similar algorithms,
or message passing distributed computing that model
constrained parallelism with sublinear central
processing. We focus on weighted nonbipartite maximum
matching in this article. For any constant $ p > 1$, we
provide an iterative sampling-based algorithm for
computing a $ (1 - \epsilon)$-approximation of the
weighted nonbipartite maximum matching that uses $ O(p
/ \epsilon)$ rounds of sampling, and $ O(n^{1 + 1 /
p})$ space. The results extend to $b$-Matching with
small changes. This article combines adaptive sketching
literature and fast primal-dual algorithms based on
relaxed Dantzig--Wolfe decision procedures. Each round
of sampling is implemented through linear sketches and
can be executed in a single round of streaming or two
rounds of MapReduce. The article also proves that
nonstandard linear relaxations of a problem, in
particular penalty-based formulations, are helpful in
reducing the adaptive dependence of the iterations.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "17",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Alistarh:2018:TAS,
author = "Dan Alistarh and William Leiserson and Alexander
Matveev and Nir Shavit",
title = "{ThreadScan}: Automatic and Scalable Memory
Reclamation",
journal = j-TOPC,
volume = "4",
number = "4",
pages = "18:1--18:??",
month = sep,
year = "2018",
CODEN = "????",
DOI = "https://doi.org/10.1145/3201897",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Jan 23 16:12:25 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "The concurrent memory reclamation problem is that of
devising a way for a deallocating thread to verify that
no other concurrent threads hold references to a memory
block being deallocated. To date, in the absence of
automatic garbage collection, there is no satisfactory
solution to this problem; existing tracking methods
like hazard pointers, reference counters, or
epoch-based techniques like RCU are either
prohibitively expensive or require significant
programming expertise to the extent that implementing
them efficiently can be worthy of a publication. None
of the existing techniques are automatic or even
semi-automated. In this article, we take a new approach
to concurrent memory reclamation. Instead of manually
tracking access to memory locations as done in
techniques like hazard pointers, or restricting shared
accesses to specific epoch boundaries as in RCU, our
algorithm, called ThreadScan, leverages operating
system signaling to automatically detect which memory
locations are being accessed by concurrent threads.
Initial empirical evidence shows that ThreadScan scales
surprisingly well and requires negligible programming
effort beyond the standard use of Malloc and Free.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "18",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Dimitrov:2018:RDT,
author = "Dimitar Dimitrov and Martin Vechev and Vivek Sarkar",
title = "Race Detection in Two Dimensions",
journal = j-TOPC,
volume = "4",
number = "4",
pages = "19:1--19:??",
month = sep,
year = "2018",
CODEN = "????",
DOI = "https://doi.org/10.1145/3264618",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Jan 23 16:12:25 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Dynamic race detection is a program analysis technique
for detecting errors caused by undesired interleavings
of concurrent tasks. A primary challenge when designing
efficient race detection algorithms is to achieve
manageable space requirements. State-of-the-art
algorithms for unstructured parallelism require $
\Theta (n) $ space per monitored memory location, where
n is the total number of tasks. This is a serious
drawback when analyzing programs with many tasks. In
contrast, algorithms for programs with a
series-parallel (SP) structure require only $ \Theta
(1) $ space. Unfortunately, it is currently not well
understood if there are classes of parallelism beyond
SP that can also benefit from and be analyzed with $
\Theta (1) $ space complexity. In this work, we show
that structures richer than SP graphs, namely, that of
two-dimensional (2D) lattices, can also be analyzed in
$ \Theta (1) $ space. Toward that (a) we extend
Tarjan's algorithm for finding lowest common ancestors
to handle 2D lattices; (b) from that extension we
derive a serial algorithm for race detection that can
analyze arbitrary task graphs with a 2D lattice
structure; (c) we present a restriction to fork-join
that admits precisely the 2D lattices as task graphs
(e.g., it can express pipeline parallelism). Our work
generalizes prior work on structured race detection and
aims to provide a deeper understanding of the interplay
between structured parallelism and program analysis
efficiency.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "19",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Lee:2018:ERD,
author = "I-Ting Angelina Lee and Tao B. Schardl",
title = "Efficient Race Detection for Reducer Hyperobjects",
journal = j-TOPC,
volume = "4",
number = "4",
pages = "20:1--20:??",
month = sep,
year = "2018",
CODEN = "????",
DOI = "https://doi.org/10.1145/3205914",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Jan 23 16:12:25 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/multithreading.bib;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "A multithreaded Cilk program that is ostensibly
deterministic may nevertheless behave
nondeterministically due to programming errors in the
code. For a Cilk program that uses reducers-a general
reduction mechanism supported in various Cilk
dialects-such programming errors are especially
challenging to debug, because the errors can expose the
nondeterminism in how the Cilk runtime system manages
reducers. We identify two unique types of races that
arise from incorrect use of reducers in a Cilk program,
and we present two algorithms to catch these races. The
first algorithm, called the Peer-Set algorithm, detects
view-read races, which occur when the program attempts
to retrieve a value out of a reducer when the read may
result in a nondeterministic value, such as before all
previously spawned subcomputations that might update
the reducer have necessarily returned. The second
algorithm, called the SP+ algorithm, detects
determinacy races-instances where a write to a memory
location occurs logically in parallel with another
access to that location-even when the raced-on memory
locations relate to reducers. Both algorithms are
provably correct, asymptotically efficient, and can be
implemented efficiently in practice. We have
implemented both algorithms in our prototype race
detector, Rader. When running Peer-Set, Rader incurs a
geometric-mean multiplicative overhead of 2.56 over
running the benchmark without instrumentation. When
running SP+, Rader incurs a geometric-mean
multiplicative overhead of 16.94.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "20",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Gilbert:2018:ISI,
author = "Seth Gilbert",
title = "Introduction to the Special Issue for {SPAA 2016}",
journal = j-TOPC,
volume = "5",
number = "1",
pages = "1:1--1:??",
month = sep,
year = "2018",
CODEN = "????",
DOI = "https://doi.org/10.1145/3230677",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Jan 23 16:12:26 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "1",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Mitzenmacher:2018:BBC,
author = "Michael Mitzenmacher and Rajmohan Rajaraman and Scott
Roche",
title = "Better Bounds for Coalescing-Branching Random Walks",
journal = j-TOPC,
volume = "5",
number = "1",
pages = "2:1--2:??",
month = sep,
year = "2018",
CODEN = "????",
DOI = "https://doi.org/10.1145/3209688",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Jan 23 16:12:26 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Coalescing-branching random walks, or cobra walks for
short, are a natural variant of random walks on graphs
that can model the spread of disease through contacts
or the spread of information in networks. In a k -cobra
walk, at each timestep, a subset of the vertices are
active; each active vertex chooses k random neighbors
(sampled independently and uniformly with replacement)
that become active at the next step, and these are the
only active vertices at the next step. A natural
quantity to study for cobra walks is the cover time,
which corresponds to the expected time when all nodes
have become infected or received the disseminated
information. In this article, we extend previous
results for cobra walks in multiple ways. We show that
the cover time for the 2-cobra walk on $ [0, n]^d $ is
$ O(n) $ (where the order notation hides constant
factors that depend on $d$); previous work had shown
the cover time was $ O(n \cdot \polylog (n))$. We show
that the cover time for a 2-cobra walk on an $n$-vertex
$d$ regular graph with conductance $ \phi_G$ is $ O(d^4
\phis^{-2}_G \log^2 n)$, significantly generalizing a
previous result that held only for expander graphs with
sufficiently high expansion. And, finally, we show that
the cover time for a 2-cobra walk on a graph with n
vertices and m edges is always $ O(m n^{3 / 4} \log
n)$; this is the first result showing that the bound of
$ \Theta (n^3)$ for the worst-case cover time for
random walks can be beaten using 2-cobra walks.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "2",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Liu:2018:RAN,
author = "Mingmou Liu and Xiaoyin Pan and Yitong Yin",
title = "Randomized Approximate Nearest Neighbor Search with
Limited Adaptivity",
journal = j-TOPC,
volume = "5",
number = "1",
pages = "3:1--3:??",
month = sep,
year = "2018",
CODEN = "????",
DOI = "https://doi.org/10.1145/3209884",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Jan 23 16:12:26 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "We study the complexity of parallel data structures
for approximate nearest neighbor search in
$d$-dimensional Hamming space $ \{ 0, 1 \}^d$. A
classic model for static data structures is the
cell-probe model [27]. We consider a cell-probe model
with limited adaptivity, where given a $ k \geq 1$, a
query is resolved by making at most $k$ rounds of
parallel memory accesses to the data structure. We give
two randomized algorithms that solve the approximate
nearest neighbor search using $k$ rounds of parallel
memory accesses: --- a simple algorithm with $ O(k
(\log d)^{1 / k})$ total number of memory accesses for
all $ k \geq 1$ --- an algorithm with $ O(k + (1 / k
\log d)^{O(1 / k)})$ total number of memory accesses
for all sufficiently large $k$. Both algorithms use
data structures of polynomial size. We prove an $
\Omega (1 / k (\log d)^{1 / k})$ lower bound for the
total number of memory accesses for any randomized
algorithm solving the approximate nearest neighbor
search within $ k \leq \log \log d / 2 \log \log \log
d$ rounds of parallel memory accesses on any data
structures of polynomial size. This lower bound shows
that our first algorithm is asymptotically optimal when
$ k = O(1)$. And our second algorithm achieves the
asymptotically optimal tradeoff between number of
rounds and total number of memory accesses. In the
extremal case, when $ k = O(\log \log d / \log \log
\log d)$ is big enough, our second algorithm matches
the $ \Theta (\log \log d / \log \log \log d)$ tight
bound for fully adaptive algorithms for approximate
nearest neighbor search in [11].",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "3",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Pandurangan:2018:FDA,
author = "Gopal Pandurangan and Peter Robinson and Michele
Scquizzato",
title = "Fast Distributed Algorithms for Connectivity and {MST}
in Large Graphs",
journal = j-TOPC,
volume = "5",
number = "1",
pages = "4:1--4:??",
month = sep,
year = "2018",
CODEN = "????",
DOI = "https://doi.org/10.1145/3209689",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Jan 23 16:12:26 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Motivated by the increasing need to understand the
algorithmic foundations of distributed large-scale
graph computations, we study a number of fundamental
graph problems in a message-passing model for
distributed computing where $ k \geq 2 $ machines
jointly perform computations on graphs with $n$ nodes
(typically, $ n \gg k$). The input graph is assumed to
be initially randomly partitioned among the $k$
machines, a common implementation in many real-world
systems. Communication is point-to-point, and the goal
is to minimize the number of communication rounds of
the computation. Our main result is an (almost) optimal
distributed randomized algorithm for graph
connectivity. Our algorithm runs in $ {\tilde O}(n /
k^2)$ rounds ($ {\tilde O}$ notation hides a $ \polylog
(n)$ factor and an additive $ \polylog (n)$ term). This
improves over the best previously known bound of $
{\tilde O}(n / k)$ [Klauck et al., SODA 2015] and is
optimal (up to a polylogarithmic factor) in light of an
existing lower bound of $ \tilde \Omega (n / k^2)$. Our
improved algorithm uses a bunch of techniques,
including linear graph sketching, that prove useful in
the design of efficient distributed graph algorithms.
Using the connectivity algorithm as a building block,
we then present fast randomized algorithms for
computing minimum spanning trees, (approximate)
min-cuts, and for many graph verification problems. All
these algorithms take $ {\tilde O}(n / k^2)$ rounds and
are optimal up to polylogarithmic factors. We also show
an almost matching lower bound of $ \tilde \Omega (n /
k^2)$ rounds for many graph verification problems by
leveraging lower bounds in random-partition
communication complexity.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "4",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Korupolu:2018:RPF,
author = "Madhukar Korupolu and Rajmohan Rajaraman",
title = "Robust and Probabilistic Failure-Aware Placement",
journal = j-TOPC,
volume = "5",
number = "1",
pages = "5:1--5:??",
month = sep,
year = "2018",
CODEN = "????",
DOI = "https://doi.org/10.1145/3210367",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Jan 23 16:12:26 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Motivated by the growing complexity and heterogeneity
of modern data centers, and the prevalence of commodity
component failures, this article studies the
failure-aware placement problem of placing tasks of a
parallel job on machines in the data center with the
goal of increasing availability. We consider two models
of failures: adversarial and probabilistic. In the
adversarial model, each node has a weight (higher
weight implying higher reliability) and the adversary
can remove any subset of nodes of total weight at most
a given bound W and our goal is to find a placement
that incurs the least disruption against such an
adversary. In the probabilistic model, each node has a
probability of failure and we need to find a placement
that maximizes the probability that at least K out of N
tasks survive at any time. For adversarial failures, we
first show that (i) the problems are in $ \Sigma_2 $,
the second level of the polynomial hierarchy; (ii) a
variant of the problem that we call RobustFap (for
Robust Failure-Aware Placement) is co-NP-hard; and
(iii) an all-or-nothing version of RobustFap is $
\Sigma_2$-complete. We then give a polynomial-time
approximation scheme (PTAS) for RobustFap, a key
ingredient of which is a solution that we design for a
fractional version of RobustFap. We then study
HierRobustFap, which is the fractional RobustFap
problem over a hierarchical network, in which failures
can occur at any subset of nodes in the hierarchy, and
a failure at a node can adversely impact all of its
descendants in the hierarchy. To solve HierRobustFap,
we introduce a notion of hierarchical max-min fairness
and a novel Generalized Spreading algorithm, which is
simultaneously optimal for every upper bound W on the
total weight of nodes that an adversary can fail. These
generalize the classical notion of max-min fairness to
work with nodes of differing capacities, differing
reliability weights, and hierarchical structures. Using
randomized rounding, we extend this to give an
algorithm for integral HierRobustFap. For the
probabilistic version, we first give an algorithm that
achieves an additive $ \epsilon $ approximation in the
failure probability for the single level version,
called ProbFap, while giving up a $ (1 + \epsilon)$
multiplicative factor in the number of failures. We
then extend the result to the hierarchical version,
HierProbFap, achieving an \epsilon additive
approximation in failure probability while giving up an
$ (L + \epsilon)$ multiplicative factor in the number
of failures, where $L$ is the number of levels in the
hierarchy.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "5",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Zhang:2018:LFT,
author = "Deli Zhang and Pierre Laborde and Lance Lebanoff and
Damian Dechev",
title = "Lock-Free Transactional Transformation for Linked Data
Structures",
journal = j-TOPC,
volume = "5",
number = "1",
pages = "6:1--6:??",
month = sep,
year = "2018",
CODEN = "????",
DOI = "https://doi.org/10.1145/3209690",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Jan 23 16:12:26 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/hash.bib;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Nonblocking data structures allow scalable and
thread-safe access to shared data. They provide
individual operations that appear to execute
atomically. However, it is often desirable to execute
multiple operations atomically in a transactional
manner. Previous solutions, such as Software
Transactional Memory (STM) and transactional boosting,
manage transaction synchronization separately from the
underlying data structure's thread synchronization.
Although this reduces programming effort, it leads to
overhead associated with additional synchronization and
the need to rollback aborted transactions. In this
work, we present a new methodology for transforming
high-performance lock-free linked data structures into
high-performance lock-free transactional linked data
structures without revamping the data structures'
original synchronization design. Our approach leverages
the semantic knowledge of the data structure to
eliminate the overhead of false conflicts and
rollbacks. We encapsulate all operations, operands, and
transaction status in a transaction descriptor, which
is shared among the nodes accessed by the same
transaction. We coordinate threads to help finish the
remaining operations of delayed transactions based on
their transaction descriptors. When a transaction
fails, we recover the correct abstract state by
reversely interpreting the logical status of a node. We
also present an obstruction-free version of our
algorithm that can be applied to dynamic execution
scenarios and an example of our approach applied to a
hash map. In our experimental evaluation using
transactions with randomly generated operations, our
lock-free transactional data structures outperform the
transactional boosted ones by 70\% on average. They
also outperform the alternative STM-based approaches by
a factor of 2 to 13 across all scenarios. More
importantly, we achieve 4,700 to 915,000 times fewer
spurious aborts than the alternatives.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "6",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Muller:2018:NHP,
author = "Michel M{\"u}ller and Takayuki Aoki",
title = "New High Performance {GPGPU} Code Transformation
Framework Applied to Large Production Weather
Prediction Code",
journal = j-TOPC,
volume = "5",
number = "2",
pages = "7:1--7:??",
month = jan,
year = "2018",
CODEN = "????",
DOI = "https://doi.org/10.1145/3291523",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Jan 23 16:12:26 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/fortran3.bib;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "We introduce ``Hybrid Fortran,'' a new approach that
allows a high-performance GPGPU port for structured
grid Fortran codes. This technique only requires
minimal changes for a CPU targeted codebase, which is a
significant advancement in terms of productivity. It
has been successfully applied to both dynamical core
and physical processes of ASUCA, a Japanese mesoscale
weather prediction model with more than 150k lines of
code. By means of a minimal weather application that
resembles ASUCA's code structure, Hybrid Fortran is
compared to both a performance model as well as today's
commonly used method, OpenACC. As a result, the Hybrid
Fortran implementation is shown to deliver the same or
better performance than OpenACC, and its performance
agrees with the model both on CPU and GPU. In a
full-scale production run, using an ASUCA grid with
1581 $ \times $ 1301 $ \times $ 58 cells and real-world
weather data in 2km resolution, 24 NVIDIA Tesla P100
running the Hybrid Fortran-based GPU port are shown to
replace more than fifty 18-core Intel Xeon Broadwell
E5-2695 v4 running the reference implementation-an
achievement comparable to more invasive GPGPU rewrites
of other weather models.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "7",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Burtscher:2018:HQF,
author = "Martin Burtscher and Sindhu Devale and Sahar Azimi and
Jayadharini Jaiganesh and Evan Powers",
title = "A High-Quality and Fast Maximal Independent Set
Implementation for {GPUs}",
journal = j-TOPC,
volume = "5",
number = "2",
pages = "8:1--8:??",
month = jan,
year = "2018",
CODEN = "????",
DOI = "https://doi.org/10.1145/3291525",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Jan 23 16:12:26 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Computing a maximal independent set is an important
step in many parallel graph algorithms. This article
introduces ECL-MIS, a maximal independent set
implementation that works well on GPUs. It includes key
optimizations to speed up computation, reduce the
memory footprint, and increase the set size. Its CUDA
implementation requires fewer than 30 kernel
statements, runs asynchronously, and produces a
deterministic result. It outperforms the maximal
independent set implementations of Pannotia, CUSP, and
IrGL on each of the 16 tested graphs of various types
and sizes. On a Titan X GPU, ECL-MIS is between 3.9 and
100 times faster (11.5 times, on average). ECL-MIS
running on the GPU is also faster than the parallel CPU
codes Ligra, Ligra+, and PBBS running on 20 Xeon cores,
which it outperforms by 4.1 times, on average. At the
same time, ECL-MIS produces maximal independent sets
that are up to 52\% larger (over 10\%, on average)
compared to these preexisting CPU and GPU
implementations. Whereas these codes produce maximal
independent sets that are, on average, about 15\%
smaller than the largest possible such sets, ECL-MIS
sets are less than 6\% smaller than the maximum
independent sets.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "8",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Liu:2018:APR,
author = "Junhong Liu and Guangming Tan and Yulong Luo and
Jiajia Li and Zeyao Mo and Ninghui Sun",
title = "An Autotuning Protocol to Rapidly Build Autotuners",
journal = j-TOPC,
volume = "5",
number = "2",
pages = "9:1--9:??",
month = jan,
year = "2018",
CODEN = "????",
DOI = "https://doi.org/10.1145/3291527",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Jan 23 16:12:26 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Automatic performance tuning (Autotuning) is an
increasingly critical tuning technique for the high
portable performance of Exascale applications. However,
constructing an autotuner from scratch remains a
challenge, even for domain experts. In this work, we
propose a performance tuning and knowledge management
suite (PAK) to help rapidly build autotuners. In order
to accommodate existing autotuning techniques, we
present an autotuning protocol that is composed of an
extractor, producer, optimizer, evaluator, and learner.
To achieve modularity and reusability, we also define
programming interfaces for each protocol component as
the fundamental infrastructure, which provides a
customizable mechanism to deploy knowledge mining in
the performance database. PAK's usability is
demonstrated by studying two important computational
kernels: stencil computation and sparse matrix-vector
multiplication (SpMV). Our proposed autotuner based on
PAK shows comparable performance and higher
productivity than traditional autotuners by writing
just a few tens of code using our autotuning
protocol.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "9",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Anta:2018:SDP,
author = "Antonio Fern{\'a}ndez Anta and Dariusz R. Kowalski and
Miguel A. Mosteiro and Prudence W. H. Wong",
title = "Scheduling Dynamic Parallel Workload of Mobile Devices
with Access Guarantees",
journal = j-TOPC,
volume = "5",
number = "2",
pages = "10:1--10:??",
month = jan,
year = "2018",
CODEN = "????",
DOI = "https://doi.org/10.1145/3291529",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Jan 23 16:12:26 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "We study a dynamic resource-allocation problem that
arises in various parallel computing scenarios, such as
mobile cloud computing, cloud computing systems,
Internet of Things systems, and others. Generically, we
model the architecture as client mobile devices and
static base stations. Each client ``arrives'' to the
system to upload data to base stations by radio
transmissions and then ``leaves.'' The problem, called
Station Assignment, is to assign clients to stations so
that every client uploads their data under some
restrictions, including a target subset of stations, a
maximum delay between transmissions, a volume of data
to upload, and a maximum bandwidth for each station. We
study the solvability of Station Assignment under an
adversary that controls the arrival and departure of
clients, limited to maximum rate and burstiness of such
arrivals. We show upper and lower bounds on the rate
and burstiness for various client arrival schedules and
protocol classes. To the best of our knowledge, this is
the first time that Station Assignment is studied under
adversarial arrivals and departures.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "10",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Mirhosseini:2018:BBA,
author = "Amirhossein Mirhosseini and Mohammad Sadrosadati and
Fatemeh Aghamohammadi and Mehdi Modarressi and Hamid
Sarbazi-Azad",
title = "{BARAN}: Bimodal Adaptive Reconfigurable-Allocator
Network-on-Chip",
journal = j-TOPC,
volume = "5",
number = "3",
pages = "11:1--11:??",
month = jan,
year = "2018",
CODEN = "????",
DOI = "https://doi.org/10.1145/3294049",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Jan 23 16:12:26 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Virtual channels are employed to improve the
throughput under high traffic loads in
Networks-on-Chips (NoCs). However, they can impose
non-negligible overheads on performance by prolonging
clock cycle time, especially under low traffic loads
where the impact of virtual channels on performance is
trivial. In this article, we propose a novel
architecture, called BARAN, that can either improve
on-chip network performance or reduce its power
consumption (depending on the specific implementation
chosen), not both at the same time, when virtual
channels are underutilized; that is, the average number
of virtual channel allocation requests per cycle is
lower than the number of total virtual channels. We
also introduce a reconfigurable arbitration logic
within the BARAN architecture that can be configured to
have multiple latencies and, hence, multiple slack
times. The increased slack times are then used to
reduce the supply voltage of the routers or increase
their clock frequency in order to reduce power
consumption or improve the performance of the whole NoC
system. The power-centric design of BARAN reduces NoC
power consumption by 43.4\% and 40.6\% under CMP and
GPU workloads, on average, respectively, compared to a
baseline architecture while imposing negligible area
and performance overheads. The performance-centric
design of BARAN reduces the average packet latency by
45.4\% and 42.1\%, on average, under CMP and GPU
workloads, respectively, compared to the baseline
architecture while increasing power consumption by
39.7\% and 43.7\%, on average. Moreover, the
performance-centric BARAN postpones the network
saturation rate by 11.5\% under uniform random traffic
compared to the baseline architecture.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "11",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Amer:2018:LCM,
author = "Abdelhalim Amer and Huiwei Lu and Pavan Balaji and
Milind Chabbi and Yanjie Wei and Jeff Hammond and
Satoshi Matsuoka",
title = "Lock Contention Management in Multithreaded {MPI}",
journal = j-TOPC,
volume = "5",
number = "3",
pages = "12:1--12:??",
month = jan,
year = "2018",
CODEN = "????",
DOI = "https://doi.org/10.1145/3275443",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Jan 23 16:12:26 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/multithreading.bib;
https://www.math.utah.edu/pub/tex/bib/pvm.bib;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3275443",
abstract = "In this article, we investigate contention management
in lock-based thread-safe MPI libraries. Specifically,
we make two assumptions: (1) locks are the only form of
synchronization when protecting communication paths;
and (2) contention occurs, and thus serialization is
unavoidable. Our work distinguishes between lock
acquisitions with respect to work being performed
inside a critical section; productive vs. unproductive.
Waiting for message reception without doing anything
else inside a critical section is an example of
unproductive lock acquisition. We show that the
high-throughput nature of modern scalable locking
protocols translates into better communication progress
for throughput-intensive MPI communication but
negatively impacts latency-sensitive communication
because of overzealous unproductive lock acquisition.
To reduce unproductive lock acquisitions, we devised a
method that promotes threads with productive work using
a generic two-level priority locking protocol. Our
results show that using a high-throughput protocol for
productive work and a fair protocol for less productive
code paths ensures the best tradeoff for fine-grained
communication, whereas a fair protocol is sufficient
for more coarse-grained communication. Although these
efforts have been rewarding, scalability degradation
remains significant. We discuss techniques that diverge
from the pure locking model and offer the potential to
further improve scalability.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "12",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Chen:2018:PDG,
author = "Rong Chen and Jiaxin Shi and Yanzhe Chen and Binyu
Zang and Haibing Guan and Haibo Chen",
title = "{PowerLyra}: Differentiated Graph Computation and
Partitioning on Skewed Graphs",
journal = j-TOPC,
volume = "5",
number = "3",
pages = "13:1--13:??",
month = jan,
year = "2018",
CODEN = "????",
DOI = "https://doi.org/10.1145/3298989",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Jan 23 16:12:26 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Natural graphs with skewed distributions raise unique
challenges to distributed graph computation and
partitioning. Existing graph-parallel systems usually
use a ``one-size-fits-all'' design that uniformly
processes all vertices, which either suffer from
notable load imbalance and high contention for
high-degree vertices (e.g., Pregel and GraphLab) or
incur high communication cost and memory consumption
even for low-degree vertices (e.g., PowerGraph and
GraphX). In this article, we argue that skewed
distributions in natural graphs also necessitate
differentiated processing on high-degree and low-degree
vertices. We then introduce PowerLyra, a new
distributed graph processing system that embraces the
best of both worlds of existing graph-parallel systems.
Specifically, PowerLyra uses centralized computation
for low-degree vertices to avoid frequent
communications and distributes the computation for
high-degree vertices to balance workloads. PowerLyra
further provides an efficient hybrid graph partitioning
algorithm (i.e., hybrid-cut) that combines edge-cut
(for low-degree vertices) and vertex-cut (for
high-degree vertices) with heuristics. To improve cache
locality of inter-node graph accesses, PowerLyra
further provides a locality-conscious data layout
optimization. PowerLyra is implemented based on the
latest GraphLab and can seamlessly support various
graph algorithms running in both synchronous and
asynchronous execution modes. A detailed evaluation on
three clusters using various graph-analytics and MLDM
(Machine Learning and Data Mining) applications shows
that PowerLyra outperforms PowerGraph by up to 5.53X
(from 1.24X) and 3.26X (from 1.49X) for real-world and
synthetic graphs, respectively, and is much faster than
other systems like GraphX and Giraph, yet with much
less memory consumption. A porting of hybrid-cut to
GraphX further confirms the efficiency and generality
of PowerLyra.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "13",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Aravind:2019:GME,
author = "Alex Aravind and Wim H. Hesselink",
title = "Group Mutual Exclusion by Fetch-and-increment",
journal = j-TOPC,
volume = "5",
number = "4",
pages = "14:1--14:??",
month = mar,
year = "2019",
CODEN = "????",
DOI = "https://doi.org/10.1145/3309202",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Mon Mar 11 18:54:51 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3309202",
abstract = "The group mutual exclusion (GME) problem (also called
the room synchronization problem) arises in various
practical applications that require concurrent data
sharing. Group mutual exclusion aims to achieve
exclusive access to a shared resource (a shared room)
while facilitating concurrency among non-conflicting
requests. The problem is that threads with distinct
interests are not allowed to access the shared resource
concurrently, but multiple threads with same interest
can. In Blelloch et al. (2003), the authors presented a
simple solution to the room synchronization problem
using fetch8add (F8A) and test-and-set (T8S) atomic
operations. This algorithm has $ O(m) $ remote memory
references (RMRs) in the cache coherent (CC) model,
where $m$ is the number of forums. In Bhatt and Huang
(2010), an open problem was posed: `` Is it possible to
design a GME algorithm with constant RMR for the CC
model using fetch8add instructions? '' This question is
partially answered in this article by presenting a
group mutual exclusion algorithm using
fetch-and-increment instructions. The algorithm is
simple and scalable.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "14",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Behzad:2019:OPH,
author = "Babak Behzad and Surendra Byna and Prabhat and Marc
Snir",
title = "Optimizing {I/O} Performance of {HPC} Applications
with Autotuning",
journal = j-TOPC,
volume = "5",
number = "4",
pages = "15:1--15:??",
month = mar,
year = "2019",
CODEN = "????",
DOI = "https://doi.org/10.1145/3309205",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Mon Mar 11 18:54:51 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3309205",
abstract = "Parallel Input output is an essential component of
modern high-performance computing (HPC). Obtaining good
I/O performance for a broad range of applications on
diverse HPC platforms is a major challenge, in part,
because of complex inter dependencies between I/O
middleware and hardware. The parallel file system and
I/O middleware layers all offer optimization parameters
that can, in theory, result in better I/O performance.
Unfortunately, the right combination of parameters is
highly dependent on the application, HPC platform,
problem size, and concurrency. Scientific application
developers do not have the time or expertise to take on
the substantial burden of identifying good parameters
for each problem configuration. They resort to using
system defaults, a choice that frequently results in
poor I/O performance. We expect this problem to be
compounded on exascale-class machines, which will
likely have a deeper software stack with hierarchically
arranged hardware resources. We present as a solution
to this problem an autotuning system for optimizing I/O
performance, I/O performance modeling, I/O tuning, and
I/O patterns. We demonstrate the value of this
framework across several HPC platforms and applications
at scale.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "15",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Maier:2019:CHT,
author = "Tobias Maier and Peter Sanders and Roman Dementiev",
title = "Concurrent Hash Tables: Fast and General(?)!",
journal = j-TOPC,
volume = "5",
number = "4",
pages = "16:1--16:??",
month = mar,
year = "2019",
CODEN = "????",
DOI = "https://doi.org/10.1145/3309206",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Mon Mar 11 18:54:51 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/hash.bib;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3309206",
abstract = "Concurrent hash tables are one of the most important
concurrent data structures, which are used in numerous
applications. For some applications, it is common that
hash table accesses dominate the execution time. To
efficiently solve these problems in parallel, we need
implementations that achieve speedups in highly
concurrent scenarios. Unfortunately, currently
available concurrent hashing libraries are far away
from this requirement, in particular, when adaptively
sized tables are necessary or contention on some
elements occurs. Our starting point for better
performing data structures is a fast and simple
lock-free concurrent hash table based on linear probing
that is, however, limited to word-sized key-value types
and does not support dynamic size adaptation. We
explain how to lift these limitations in a provably
scalable way and demonstrate that dynamic growing has a
performance overhead comparable to the same
generalization in sequential hash tables. We perform
extensive experiments comparing the performance of our
implementations with six of the most widely used
concurrent hash tables. Ours are considerably faster
than the best algorithms with similar restrictions and
an order of magnitude faster than the best more general
tables. In some extreme cases, the difference even
approaches four orders of magnitude. All our
implementations discussed in this publication can be
found on github [17].",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "16",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Cruz:2019:ETM,
author = "Eduardo H. M. Cruz and Matthias Diener and La{\'e}rcio
L. Pilla and Philippe O. A. Navaux",
title = "{EagerMap}: a Task Mapping Algorithm to Improve
Communication and Load Balancing in Clusters of
Multicore Systems",
journal = j-TOPC,
volume = "5",
number = "4",
pages = "17:1--17:??",
month = mar,
year = "2019",
CODEN = "????",
DOI = "https://doi.org/10.1145/3309711",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Mon Mar 11 18:54:51 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3309711",
abstract = "Communication between tasks and load imbalance have
been identified as a major challenge for the
performance and energy efficiency of parallel
applications. A common way to improve communication is
to increase its locality, that is, to reduce the
distances of data transfers, prioritizing the usage of
faster and more efficient local interconnections over
remote ones. Regarding load imbalance, cores should
execute a similar amount of work. An important problem
to be solved in this context is how to determine an
optimized mapping of tasks to cluster nodes and cores
that increases the overall locality and load balancing.
In this article, we propose the EagerMap algorithm to
determine task mappings, which is based on a greedy
heuristic to match application communication patterns
to hardware hierarchies and which can also consider the
task load. Compared to previous algorithms, EagerMap is
faster, scales better, and supports more types of
computer systems, while maintaining the same or better
quality of the determined task mapping. EagerMap is
therefore an interesting choice for task mapping on a
variety of modern parallel architectures.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "17",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Bader:2019:EEC,
author = "David A. Bader",
title = "Editorial from the {Editor-in-Chief}",
journal = j-TOPC,
volume = "6",
number = "1",
pages = "1:1--1:??",
month = jun,
year = "2019",
CODEN = "????",
DOI = "https://doi.org/10.1145/3325883",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Nov 20 07:59:58 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3325883",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "1",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Kronbichler:2019:MMF,
author = "Martin Kronbichler and Karl Ljungkvist",
title = "Multigrid for Matrix-Free High-Order Finite Element
Computations on Graphics Processors",
journal = j-TOPC,
volume = "6",
number = "1",
pages = "2:1--2:??",
month = jun,
year = "2019",
CODEN = "????",
DOI = "https://doi.org/10.1145/3322813",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Nov 20 07:59:58 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3322813",
abstract = "This article presents matrix-free finite-element
techniques for efficiently solving partial differential
equations on modern many-core processors, such as
graphics cards. We develop a GPU parallelization of a
matrix-free geometric multigrid iterative solver
targeting moderate and high polynomial degrees, with
support for general curved and adaptively refined
hexahedral meshes with hanging nodes. The central
algorithmic component is the matrix-free operator
evaluation with sum factorization. We compare the
node-level performance of our implementation running on
an Nvidia Pascal P100 GPU to a highly optimized
multicore implementation running on comparable Intel
Broadwell CPUs and an Intel Xeon Phi. Our experiments
show that the GPU implementation is approximately 1.5
to 2 times faster across four different scenarios of
the Poisson equation and a variety of element degrees
in 2D and 3D. The lowest time to solution per degree of
freedom is recorded for moderate polynomial degrees
between 3 and 5. A detailed performance analysis
highlights the capabilities of the GPU architecture and
the chosen execution model with threading within the
element, particularly with respect to the evaluation of
the matrix-vector product. Atomic intrinsics are shown
to provide a fast way for avoiding the possible race
conditions in summing the elemental residuals into the
global vector associated to shared vertices, edges, and
surfaces. In addition, the solver infrastructure allows
for using mixed-precision arithmetic that performs the
multigrid V-cycle in single precision with an outer
correction in double precision, increasing throughput
by up to 83",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "2",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Bonifaci:2019:GPT,
author = "Vincenzo Bonifaci and Andreas Wiese and Sanjoy K.
Baruah and Alberto Marchetti-Spaccamela and Sebastian
Stiller and Leen Stougie",
title = "A Generalized Parallel Task Model for Recurrent
Real-Time Processes",
journal = j-TOPC,
volume = "6",
number = "1",
pages = "3:1--3:??",
month = jun,
year = "2019",
CODEN = "????",
DOI = "https://doi.org/10.1145/3322809",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Nov 20 07:59:58 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3322809",
abstract = "A model is considered for representing recurrent
precedence-constrained tasks that are to execute on
multiprocessor platforms. A recurrent task is specified
as a directed acyclic graph (DAG), a period, and a
relative deadline. Each vertex of the DAG represents a
sequential job, while the edges of the DAG represent
precedence constraints between these jobs. All the jobs
of the DAG are released simultaneously and need to
complete execution within the specified relative
deadline of their release. Each task may release jobs
in this manner an unbounded number of times, with
successive releases occurring at least the specified
period apart. Conditional control structures are also
allowed. The scheduling problem is to determine whether
a set of such recurrent tasks can be scheduled to
always meet all deadlines upon a specified number of
identical processors. This problem is shown to be
computationally intractable, but amenable to efficient
approximate solutions. Earliest Deadline First (EDF)
and Deadline Monotonic (DM) are shown to be good
approximate global scheduling algorithms. Polynomial
and pseudo-polynomial time schedulability tests, of
differing effectiveness, are presented for determining
whether a given task set can be scheduled by EDF or DM
to always meet deadlines on a specified number of
processors.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "3",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Ltaief:2019:MPP,
author = "Hatem Ltaief and Dalal Sukkari and Aniello Esposito
and Yuji Nakatsukasa and David Keyes",
title = "Massively Parallel Polar Decomposition on
Distributed-memory Systems",
journal = j-TOPC,
volume = "6",
number = "1",
pages = "4:1--4:??",
month = jun,
year = "2019",
CODEN = "????",
DOI = "https://doi.org/10.1145/3328723",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Nov 20 07:59:58 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3328723",
abstract = "We present a high-performance implementation of the
Polar Decomposition (PD) on distributed-memory systems.
Building upon on the QR-based Dynamically Weighted
Halley (QDWH) algorithm, the key idea lies in finding
the best rational approximation for the scalar sign
function, which also corresponds to the polar factor
for symmetric matrices, to further accelerate the QDWH
convergence. Based on the Zolotarev rational
functions-introduced by Zolotarev (ZOLO) in 1877-this
new PD algorithm ZOLO-PD converges within two
iterations even for ill-conditioned matrices, instead
of the original six iterations needed for QDWH. ZOLO-PD
uses the property of Zolotarev functions that
optimality is maintained when two functions are
composed in an appropriate manner. The resulting
ZOLO-PD has a convergence rate up to 17, in contrast to
the cubic convergence rate for QDWH. This comes at the
price of higher arithmetic costs and memory footprint.
These extra floating-point operations can, however, be
processed in an embarrassingly parallel fashion. We
demonstrate performance using up to 102,400 cores on
two supercomputers. We demonstrate that, in the
presence of a large number of processing units, ZOLO-PD
is able to outperform QDWH by up to 2.3$ \times $
speedup, especially in situations where QDWH runs out
of work, for instance, in the strong scaling mode of
operation.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "4",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Saha:2019:OSA,
author = "Dibakar Saha and Koushik Sinha",
title = "Optimal Schedule for All-to-All Personalized
Communication in Multiprocessor Systems",
journal = j-TOPC,
volume = "6",
number = "1",
pages = "5:1--5:??",
month = jun,
year = "2019",
CODEN = "????",
DOI = "https://doi.org/10.1145/3329867",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Nov 20 07:59:58 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3329867",
abstract = "In this article, we address the problem of finding an
optimal schedule for all-to-all personalized message
communication among the processors in a multiprocessor
system where every processor has a unique message for
every other processor. When there are n processors and
\lfloor n /2 \rfloor parallel databus or channels for
message communications, there exist algorithms that
require O ( n$^2$ ) time for assigning the
databus/channels to the processor-pairs to obtain a
schedule with minimum number of time slots. However, in
recent massively parallel processing systems with a
huge number of processors, the number k of available
databus/channels is usually much smaller than \lfloor n
/2",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "5",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Pumma:2019:SDL,
author = "Sarunya Pumma and Min Si and Wu-Chun Feng and Pavan
Balaji",
title = "Scalable Deep Learning via {I/O} Analysis and
Optimization",
journal = j-TOPC,
volume = "6",
number = "2",
pages = "6:1--6:??",
month = sep,
year = "2019",
CODEN = "????",
DOI = "https://doi.org/10.1145/3331526",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Nov 20 07:59:59 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3331526",
abstract = "Scalable deep neural network training has been gaining
prominence because of the increasing importance of deep
learning in a multitude of scientific and commercial
domains. Consequently, a number of researchers have
investigated techniques to optimize deep learning
systems. Much of the prior work has focused on runtime
and algorithmic enhancements to optimize the
computation and communication. Despite these
enhancements, however, deep learning systems still
suffer from scalability limitations, particularly with
respect to data I/O. This situation is especially true
for training models where the computation can be
effectively parallelized, leaving I/O as the major
bottleneck. In fact, our analysis shows that I/O can
take up to 90",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "6",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Aupy:2019:SSP,
author = "Guilllaume Aupy and Ana Gainaru and Valentin {Le
F{\`e}vre}",
title = "{I/O} Scheduling Strategy for Periodic Applications",
journal = j-TOPC,
volume = "6",
number = "2",
pages = "7:1--7:??",
month = sep,
year = "2019",
CODEN = "????",
DOI = "https://doi.org/10.1145/3338510",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Nov 20 07:59:59 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3338510",
abstract = "With the ever-growing need of data in HPC
applications, the congestion at the I/O level becomes
critical in supercomputers. Architectural enhancement
such as burst buffers and pre-fetching are added to
machines but are not sufficient to prevent congestion.
Recent online I/O scheduling strategies have been put
in place, but they add an additional congestion point
and overheads in the computation of applications. In
this work, we show how to take advantage of the
periodic nature of HPC applications to develop
efficient periodic scheduling strategies for their I/O
transfers. Our strategy computes once during the job
scheduling phase a pattern that defines the I/O
behavior for each application, after which the
applications run independently, performing their I/O at
the specified times. Our strategy limits the amount of
congestion at the I/O node level and can be easily
integrated into current job schedulers. We validate
this model through extensive simulations and
experiments on an HPC cluster by comparing it to
state-of-the-art online solutions, showing that not
only does our scheduler have the advantage of being
de-centralized and thus overcoming the overhead of
online schedulers, but also that it performs better
than the other solutions, improving the application
dilation up to 16",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "7",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Kagaris:2019:SME,
author = "Dimitri Kagaris and Sourav Dutta",
title = "Scheduling Mutual Exclusion Accesses in Equal-Length
Jobs",
journal = j-TOPC,
volume = "6",
number = "2",
pages = "8:1--8:??",
month = sep,
year = "2019",
CODEN = "????",
DOI = "https://doi.org/10.1145/3342562",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Nov 20 07:59:59 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3342562",
abstract = "A fundamental problem in parallel and distributed
processing is the partial serialization that is imposed
due to the need for mutually exclusive access to common
resources. In this article, we investigate the problem
of optimally scheduling (in terms of makespan) a set of
jobs, where each job consists of the same number L of
unit-duration tasks, and each task either accesses
exclusively one resource from a given set of resources
or accesses a fully shareable resource. We develop and
establish the optimality of a fast polynomial-time
algorithm to find a schedule with the shortest makespan
for any number of jobs and for any number of resources
for the case of L = 2. In the notation commonly used
for job-shop scheduling problems, this result means
that the problem J | d$_{ij}$ =1, n$_j$ =2| C$_{max}$
is polynomially solvable, adding to the polynomial
solutions known for the problems J 2 | n$_j$ {$<$}= 2 |
C$_{max}$ and J 2 | d$_{ij}$ = 1 | C$_{max}$ (whereas
other closely related versions such as J 2 | n$_j$ \leq
3 | C$_{max}$, J 2 | d$_{ij}$ ) \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "8",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Mollah:2019:MUG,
author = "Md Atiqul Mollah and Wenqi Wang and Peyman Faizian and
MD Shafayat Rahman and Xin Yuan and Scott Pakin and
Michael Lang",
title = "Modeling Universal Globally Adaptive Load-Balanced
Routing",
journal = j-TOPC,
volume = "6",
number = "2",
pages = "9:1--9:??",
month = sep,
year = "2019",
CODEN = "????",
DOI = "https://doi.org/10.1145/3349620",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Nov 20 07:59:59 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3349620",
abstract = "Universal globally adaptive load-balanced (UGAL)
routing has been proposed for various interconnection
networks and has been deployed in a number of
current-generation supercomputers. Although UGAL-based
schemes have been extensively studied, most existing
results are based on either simulation or measurement.
Without a theoretical understanding of UGAL, multiple
questions remain: For which traffic patterns is UGAL
most suited? In addition, what determines the
performance of the UGAL-based scheme on a particular
network configuration? In this work, we develop a set
of throughput models for UGALbased on linear
programming. We show that the throughput models are
valid across the torus, Dragonfly, and Slim Fly network
topologies. Finally, we identify a robust model that
can accurately and efficiently predict UGAL throughput
for a set of representative traffic patterns across
different topologies. Our models not only provide a
mechanism to predict UGAL performance on large-scale
interconnection networks but also reveal the inner
working of UGAL and further our understanding of this
type of routing.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "9",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Bateni:2019:ISI,
author = "Mohammed Hossein Bateni and Mohammad T. Hajiaghayi and
Silvio Lattanzi",
title = "Introduction to the Special Issue for {SPAA'17}",
journal = j-TOPC,
volume = "6",
number = "3",
pages = "10:1--10:??",
month = oct,
year = "2019",
CODEN = "????",
DOI = "https://doi.org/10.1145/3363417",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Nov 20 07:59:59 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3363417",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "10",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Guha:2019:DPC,
author = "Sudipto Guha and Yi Li and Qin Zhang",
title = "Distributed Partial Clustering",
journal = j-TOPC,
volume = "6",
number = "3",
pages = "11:1--11:??",
month = oct,
year = "2019",
CODEN = "????",
DOI = "https://doi.org/10.1145/3322808",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Nov 20 07:59:59 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3322808",
abstract = "Recent years have witnessed an increasing popularity
of algorithm design for distributed data, largely due
to the fact that massive datasets are often collected
and stored in different locations. In the distributed
setting, communication typically dominates the query
processing time. Thus, it becomes crucial to design
communication-efficient algorithms for queries on
distributed data. Simultaneously, it has been widely
recognized that partial optimizations, where we are
allowed to disregard a small part of the data, provide
us significantly better solutions. The motivation for
disregarded points often arises from noise and other
phenomena that are pervasive in large data scenarios.
In this article, we focus on partial clustering
problems, k -center, k -median, and k -means objectives
in the distributed model, and provide algorithms with
communication sublinear of the input size. As a
consequence, we develop the first algorithms for the
partial k -median and means objectives that run in
subquadratic running time. We also initiate the study
of distributed algorithms for clustering uncertain
data, where each data point can possibly fall into
multiple locations under certain probability
distribution.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "11",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Fraigniaud:2019:DDC,
author = "Pierre Fraigniaud and Dennis Olivetti",
title = "Distributed Detection of Cycles",
journal = j-TOPC,
volume = "6",
number = "3",
pages = "12:1--12:??",
month = oct,
year = "2019",
CODEN = "????",
DOI = "https://doi.org/10.1145/3322811",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Nov 20 07:59:59 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3322811",
abstract = "Distributed property testing in networks has been
introduced by Brakerski and Patt-Shamir [6], with the
objective of detecting the presence of large dense
sub-networks in a distributed manner. Recently,
Censor-Hillel et al. [7] have revisited this notion and
formalized it in a broader context. In particular, they
have shown how to detect 3-cycles in a constant number
of rounds by a distributed algorithm. In a follow-up
work, Fraigniaud et al. [21] have shown how to detect
4-cycles in a constant number of rounds as well.
However, the techniques in these latter works were
shown not to generalize to larger cycles C$_k$ with k
{$>$}= 5. In this article, we completely settle the
problem of cycle detection by establishing the
following result: For every k {$>$}= 3, there exists a
distributed property testing algorithm for C$_k$
-freeness, performing in a constant number of rounds.
All these results hold in the classical congest model
for distributed network computing. Our algorithm is
1-sided error. Its round-complexity is O (1 \epsilon )
where \epsilon \in (0,1) is the property-testing
parameter measuring the gap between legal and illegal
instances.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "12",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Albers:2019:ECD,
author = "Susanne Albers",
title = "On Energy Conservation in Data Centers",
journal = j-TOPC,
volume = "6",
number = "3",
pages = "13:1--13:??",
month = oct,
year = "2019",
CODEN = "????",
DOI = "https://doi.org/10.1145/3364210",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Nov 20 07:59:59 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3364210",
abstract = "We formulate and study an optimization problem that
arises in the energy management of data centers and,
more generally, multiprocessor environments. Data
centers host a large number of heterogeneous servers.
Each server has an active state and several
standby/sleep states with individual power consumption
rates. The demand for computing capacity varies over
time. Idle servers may be transitioned to low-power
modes so as to rightsize the pool of active servers.
The goal is to find a state transition schedule for the
servers that minimizes the total energy consumed. On a
small scale, the same problem arises in multicore
architectures with heterogeneous processors on a chip.
One has to determine active and idle periods for the
cores so as to guarantee a certain service and minimize
the consumed energy. For this power/capacity management
problem, we develop two main results. We use the
terminology of the data center setting. First, we
investigate the scenario that each server has two
states: an active state and a sleep state. We show that
an optimal solution, minimizing energy consumption, can
be computed in polynomial time by a combinatorial
algorithm. The algorithm resorts to a single-commodity
minimum-cost flow computation. Second, we study the
general scenario that each server has an active state
and multiple standby/sleep states. We devise a",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "13",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Feldkord:2019:MSP,
author = "Bj{\"o}rn Feldkord and Friedhelm Meyer Auf Der Heide",
title = "The Mobile Server Problem",
journal = j-TOPC,
volume = "6",
number = "3",
pages = "14:1--14:??",
month = oct,
year = "2019",
CODEN = "????",
DOI = "https://doi.org/10.1145/3364204",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Nov 20 07:59:59 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3364204",
abstract = "We introduce the Mobile Server problem, inspired by
current trends to move computational tasks from cloud
structures to multiple devices close to the end user.
An example of this is embedded systems in autonomous
cars that communicate to coordinate their actions. Our
model is a variant of the classical Page Migration
problem. More formally, we consider a mobile server
holding a data page. The server can move in the
Euclidean space (of arbitrary dimension). In every
round, requests for data items from the page pop up at
arbitrary points in the space. The requests are served,
each at a cost of the distance from the requesting
point and the server, and the mobile server may move,
at a cost D times the distance traveled for some
constant D. We assume a maximum distance m that the
server is allowed to move per round. We show that no
online algorithm can achieve a competitive ratio
independent of the length of the input sequence in this
setting. Hence, we augment the maximum movement
distance of the online algorithms to \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "14",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Azar:2019:TBC,
author = "Yossi Azar and Danny Vainstein",
title = "Tight Bounds for Clairvoyant Dynamic Bin Packing",
journal = j-TOPC,
volume = "6",
number = "3",
pages = "15:1--15:??",
month = oct,
year = "2019",
CODEN = "????",
DOI = "https://doi.org/10.1145/3364214",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Nov 20 07:59:59 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3364214",
abstract = "In this article, we focus on the Clairvoyant Dynamic
Bin Packing (DBP) problem, which extends the Classical
Online Bin Packing problem in that items arrive and
depart over time and the departure time of an item is
known upon its arrival. The problem naturally arises
when handling cloud-based networks. We focus
specifically on the MinUsageTime objective function,
which aims to minimize the overall usage time of all
bins that are opened during the packing process.
Earlier work has shown a O (log \mu / log log \mu)
upper bound on the algorithm's competitiveness, where
\mu is defined as the ratio between the maximal and
minimal durations of all items. We improve the upper
bound by giving a \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "15",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Cooper:2019:NCT,
author = "Colin Cooper and Tomasz Radzik and Nicolas Rivera",
title = "New Cover Time Bounds for the Coalescing-Branching
Random Walk on Graphs",
journal = j-TOPC,
volume = "6",
number = "3",
pages = "16:1--16:??",
month = oct,
year = "2019",
CODEN = "????",
DOI = "https://doi.org/10.1145/3364206",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Nov 20 07:59:59 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3364206",
abstract = "We present new bounds on the cover time of the
coalescing-branching random walk process COBRA. The
COBRA process, introduced in Dutta et al. [9], can be
viewed as spreading a single item of information
throughout an undirected graph in synchronised rounds.
In each round, each vertex that has received the
information in the previous round (possibly
simultaneously from more than one neighbour and
possibly not for the first time), ``pushes'' the
information to k randomly selected neighbours. The
COBRA process is typically studied for integer
branching rates k {$>$}= 2 (with the case k =1
corresponding to a random walk). The aim of the process
is to propagate the information quickly, but with a
limited number of transmissions per vertex per round.
The COBRA cover time is the expected number of rounds
until all vertices have received the information at
least once. Our main results are bounds of O ( m + (
d$_{max}$ )$^2$ log n ) and O ( m log n ) on the COBRA
cover time for arbitrary connected graphs with n
vertices, m edges and maximum graph degree d$_{max}$,
and bounds of \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "16",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Sun:2019:DGC,
author = "He Sun and Luca Zanetti",
title = "Distributed Graph Clustering and Sparsification",
journal = j-TOPC,
volume = "6",
number = "3",
pages = "17:1--17:??",
month = oct,
year = "2019",
CODEN = "????",
DOI = "https://doi.org/10.1145/3364208",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Nov 20 07:59:59 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3364208",
abstract = "Graph clustering is a fundamental computational
problem with a number of applications in algorithm
design, machine learning, data mining, and analysis of
social networks. Over the past decades, researchers
have proposed a number of algorithmic design methods
for graph clustering. Most of these methods, however,
are based on complicated spectral techniques or convex
optimisation and cannot be directly applied for
clustering many networks that occur in practice, whose
information is often collected on different sites.
Designing a simple and distributed clustering algorithm
is of great interest and has comprehensive applications
for processing big datasets. In this article, we
present a simple and distributed algorithm for graph
clustering: For a wide class of graphs that are
characterised by a strong cluster-structure, our
algorithm finishes in a poly-logarithmic number of
rounds and recovers a partition of the graph close to
optimal. One of the main procedures behind our
algorithm is a sampling scheme that, given a dense
graph as input, produces a sparse subgraph that
provably preserves the cluster-structure of the input.
Compared with previous sparsification algorithms that
require Laplacian solvers or involve combinatorial
constructions, this procedure is easy to implement in a
distributed setting and runs fast in practice.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "17",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Khan:2019:NOP,
author = "Shahbaz Khan",
title = "Near Optimal Parallel Algorithms for Dynamic {DFS} in
Undirected Graphs",
journal = j-TOPC,
volume = "6",
number = "3",
pages = "18:1--18:??",
month = oct,
year = "2019",
CODEN = "????",
DOI = "https://doi.org/10.1145/3364212",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Nov 20 07:59:59 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3364212",
abstract = "Depth first search (DFS) tree is a fundamental data
structure for solving various graph problems. The
classical algorithm [54] for building a DFS tree
requires O ( m + n ) time for a given undirected graph
G having n vertices and m edges. Recently, Baswana et
al. [5] presented a simple algorithm for updating the
DFS tree of an undirected graph after an edge/vertex
update in {\tilde O}( n )$^1$ time. However, their
algorithm is strictly sequential. \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "18",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Rauchwerger:2019:ISI,
author = "Lawrence Rauchwerger and Jaejin Lee and Armando
Solar-Lezama and Guy Steele",
title = "Introduction to the Special Issue on {PPoPP} 2017
(Part 1)",
journal = j-TOPC,
volume = "6",
number = "4",
pages = "19:1--19:??",
month = dec,
year = "2019",
CODEN = "????",
DOI = "https://doi.org/10.1145/3373151",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Dec 27 16:13:12 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "19e",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Schardl:2019:TER,
author = "Tao B. Schardl and William S. Moses and Charles E.
Leiserson",
title = "{Tapir}: Embedding Recursive Fork-join Parallelism
into {LLVM}'s Intermediate Representation",
journal = j-TOPC,
volume = "6",
number = "4",
pages = "19:1--19:??",
month = dec,
year = "2019",
CODEN = "????",
DOI = "https://doi.org/10.1145/3365655",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Dec 27 16:13:12 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/pvm.bib;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3365655",
abstract = "Tapir (pronounced TAY-per) is a compiler intermediate
representation (IR) that embeds recursive fork-join
parallelism, as supported by task-parallel programming
platforms such as Cilk and OpenMP, into a mainstream
compiler's IR. Mainstream compilers typically treat
parallel linguistic constructs as syntactic sugar for
function calls into a parallel runtime. These calls
prevent the compiler from performing optimizations on
and across parallel control constructs. Remedying this
situation has generally been thought to require an
extensive reworking of compiler analyses and code
transformations to handle parallel semantics. Tapir
leverages the ``serial-projection property,'' which is
commonly satisfied by task-parallel programs, to handle
the semantics of these programs without an extensive
rework of the compiler. For recursive fork-join
programs that satisfy the serial-projection property,
Tapir enables effective compiler optimization of
parallel programs with only minor changes to existing
compiler analyses and code transformations. Tapir uses
the serial-projection property to order logically
parallel fine-grained tasks in the program's
control-flow graph. This ordered representation of
parallel tasks allows the compiler to optimize parallel
codes effectively with only minor modifications. For
example, to implement Tapir/LLVM, a prototype of Tapir
in the LLVM compiler, we added or modified less than
3,000 lines of LLVM's half-million-line core middle-end
functionality. These changes sufficed to enable LLVM's
existing compiler optimizations for serial
code-including loop-invariant-code motion,
common-subexpression elimination, and tail-recursion
elimination-to work with parallel control constructs
such as parallel loops and Cilk's Cilk\_Spawn keyword.
Tapir also supports parallel optimizations, such as
loop scheduling, which restructure the parallel control
flow of the program. By making use of existing LLVM
optimizations and new parallel optimizations,
Tapir/LLVM can optimize recursive fork-join programs
more effectively than traditional compilation methods.
On a suite of 35 Cilk application benchmarks,
Tapir/LLVM produces more efficient executables for 30
benchmarks, with faster 18-core running times for 26 of
them, compared to a nearly identical compiler that
compiles parallel linguistic constructs the traditional
way.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "19",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Utterback:2019:POR,
author = "Robert Utterback and Kunal Agrawal and I-Ting Angelina
Lee and Milind Kulkarni",
title = "Processor-Oblivious Record and Replay",
journal = j-TOPC,
volume = "6",
number = "4",
pages = "20:1--20:??",
month = dec,
year = "2019",
CODEN = "????",
DOI = "https://doi.org/10.1145/3365659",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Dec 27 16:13:12 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/multithreading.bib;
https://www.math.utah.edu/pub/tex/bib/pvm.bib;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3365659",
abstract = "Record-and-replay systems are useful tools for
debugging non-deterministic parallel programs by first
recording an execution and then replaying that
execution to produce the same access pattern. Existing
record-and-replay systems generally target thread-based
execution models, and record the behaviors and
interleavings of individual threads. Dynamic
multithreaded languages and libraries, such as the Cilk
family, OpenMP, TBB, and the like, do not have a notion
of threads. Instead, these languages provide a
processor-oblivious model of programming, where
programs expose task parallelism using high-level
constructs such as spawn/sync without regard to the
number of threads/cores available to run the program.
Thread-based record-and-replay would violate the
processor-oblivious nature of these programs, as they
incorporate the number of threads into the recorded
information, constraining the replayed execution to the
same number of threads. In this article, we present a
processor-oblivious record-and-replay scheme for
dynamic multithreaded languages where record and replay
can use different number of processors and both are
scheduled using work stealing. We provide theoretical
guarantees for our record and replay scheme-namely that
record is optimal for programs with one lock and replay
is near-optimal for all cases. In addition, we
implemented this scheme in the Cilk Plus runtime system
and our evaluation indicates that
processor-obliviousness does not cause substantial
overheads.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "20",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Yeh:2019:PGR,
author = "Tsung Tai Yeh and Amit Sabne and Putt Sakdhnagool and
Rudolf Eigenmann and Timothy G. Rogers",
title = "{Pagoda}: a {GPU} Runtime System for Narrow Tasks",
journal = j-TOPC,
volume = "6",
number = "4",
pages = "21:1--21:??",
month = nov,
year = "2019",
CODEN = "????",
DOI = "https://doi.org/10.1145/3365657",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Nov 20 07:59:59 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/multithreading.bib;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "Massively multithreaded GPUs achieve high throughput
by running thousands of threads in parallel. To fully
utilize the their hardware, contemporary workloads
spawn work to the GPU in bulk by launching large tasks,
where each task is a kernel that contains thousands of
threads that occupy the entire GPU. GPUs face severe
underutilization and their performance benefits vanish
if the tasks are narrow, i.e., they contain less than
512 threads. Latency-sensitive applications in network,
signal, and image processing that generate a large
number of tasks with relatively small inputs are
examples of such limited parallelism. This article
presents Pagoda, a runtime system that virtualizes GPU
resources, using an OS-like daemon kernel called
MasterKernel. Tasks are spawned from the CPU onto
Pagoda as they become available, and are scheduled by
the MasterKernel at the warp granularity. This level of
control enables the GPU to keep scheduling and
executing tasks as long as free warps are found,
dramatically reducing underutilization. Experimental
results on real hardware demonstrate that Pagoda
achieves a geometric mean speedup of 5.52X over
PThreads running on a 20-core CPU, 1.76X over
CUDA-HyperQ, and 1.44X over GeMTC, the state-of-the-art
runtime GPU task scheduling system.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "21",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Steele:2019:UBP,
author = "Guy L. {Steele Jr.} and Jean-Baptiste Tristan",
title = "Using Butterfly-patterned Partial Sums to Draw from
Discrete Distributions",
journal = j-TOPC,
volume = "6",
number = "4",
pages = "22:1--22:??",
month = nov,
year = "2019",
CODEN = "????",
DOI = "https://doi.org/10.1145/3365662",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Nov 20 07:59:59 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/prng.bib;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "We describe a SIMD technique for drawing values from
multiple discrete distributions, such as sampling from
the random variables of a mixture model, that avoids
computing a complete table of partial sums of the
relative probabilities. A table of alternate
(``butterfly-patterned'') form is faster to compute,
making better use of coalesced memory accesses; from
this table, complete partial sums are computed on the
fly during a binary search. Measurements using Cuda 7.5
on an NVIDIA Titan Black GPU show that this technique
makes an entire machine-learning application that uses
a Latent Dirichlet Allocation topic model with 1,024
topics about 13\% faster (when using single-precision
floating-point data) or about 35\% faster (when using
double-precision floating-point data) than doing a
straightforward matrix transposition after using
coalesced accesses.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "22",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Vandierendonck:2019:HDI,
author = "Hans Vandierendonck and Dimitrios S. Nikolopoulos",
title = "Hyperqueues: Design and Implementation of
Deterministic Concurrent Queues",
journal = j-TOPC,
volume = "6",
number = "4",
pages = "23:1--23:??",
month = nov,
year = "2019",
CODEN = "????",
DOI = "https://doi.org/10.1145/3365660",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Nov 20 07:59:59 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "The hyperqueue is a programming abstraction for queues
that results in deterministic and scale-free parallel
programs. Hyperqueues extend the concept of Cilk++
hyperobjects to provide thread-local views on a shared
data structure. While hyperobjects are organized around
private local views, hyperqueues provide a shared view
on a queue data structure. Hereby, hyperqueues
guarantee determinism for programs using concurrent
queues. We define the programming API and semantics of
two instances of the hyperqueue concept. These
hyperqueues differ in their API and the degree of
concurrency that is extracted. We describe the
implementation of the hyperqueues in a work-stealing
scheduler and demonstrate scalable performance on
pipeline-parallel benchmarks from PARSEC and
StreamIt.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "23",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Ren:2019:ESP,
author = "Bin Ren and Shruthi Balakrishna and Youngjoon Jo and
Sriram Krishnamoorthy and Kunal Agrawal and Milind
Kulkarni",
title = "Extracting {SIMD} Parallelism from Recursive
Task-Parallel Programs",
journal = j-TOPC,
volume = "6",
number = "4",
pages = "24:1--24:??",
month = dec,
year = "2019",
CODEN = "????",
DOI = "https://doi.org/10.1145/3365663",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Dec 27 16:13:12 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
abstract = "The pursuit of computational efficiency has led to the
proliferation of throughput-oriented hardware, from
GPUs to increasingly wide vector units on commodity
processors and accelerators. This hardware is designed
to execute data-parallel computations in a vectorized
manner efficiently. However, many algorithms are more
naturally expressed as divide-and-conquer, recursive,
task-parallel computations. In the absence of data
parallelism, it seems that such algorithms are not well
suited to throughput-oriented architectures. This
article presents a set of novel code transformations
that expose the data parallelism latent in recursive,
task-parallel programs. These transformations
facilitate straightforward vectorization of
task-parallel programs on commodity hardware. We also
present scheduling policies that maintain high
utilization of vector resources while limiting space
usage. Across several task-parallel benchmarks, we
demonstrate both efficient vector resource utilization
and substantial speedup on chips using Intel's SSE4.2
vector units, as well as accelerators using Intel's
AVX512 units. We then show through rigorous sampling
that, in practice, our vectorization techniques are
effective for a much larger class of programs.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "24",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Tumeo:2020:ITSa,
author = "Antonino Tumeo and Fabrizio Petrini and John Feo and
Mahantesh Halappanavar",
title = "Introduction to the {TOPC} Special Issue on
Innovations in Systems for Irregular Applications,
{Part 1}",
journal = j-TOPC,
volume = "7",
number = "1",
pages = "1:1--1:2",
month = apr,
year = "2020",
CODEN = "????",
DOI = "https://doi.org/10.1145/3383318",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Mon Apr 6 08:56:55 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3383318",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "1",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Anzt:2020:LBS,
author = "Hartwig Anzt and Terry Cojean and Chen Yen-Chen and
Jack Dongarra and Goran Flegar and Pratik Nayak and
Stanimire Tomov and Yuhsiang M. Tsai and Weichung
Wang",
title = "Load-balancing Sparse Matrix Vector Product Kernels on
{GPUs}",
journal = j-TOPC,
volume = "7",
number = "1",
pages = "2:1--2:26",
month = apr,
year = "2020",
CODEN = "????",
DOI = "https://doi.org/10.1145/3380930",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Mon Apr 6 08:56:55 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3380930",
abstract = "Efficient processing of Irregular Matrices on Single
Instruction, Multiple Data (SIMD)-type architectures is
a persistent challenge. Resolving it requires
innovations in the development of data formats,
computational techniques, and implementations that
strike a balance between thread divergence, which is
inherent for Irregular Matrices, and padding, which
alleviates the performance-detrimental thread
divergence but introduces artificial overheads. To this
end, in this article, we address the challenge of
designing high performance sparse matrix-vector product
(SpMV) kernels designed for Nvidia Graphics Processing
Units (GPUs). We present a compressed sparse row (CSR)
format suitable for unbalanced matrices. We also
provide a load-balancing kernel for the coordinate
(COO) matrix format and extend it to a hybrid algorithm
that stores part of the matrix in SIMD-friendly Ellpack
format (ELL) format. The ratio between the ELL- and the
COO-part is determined using a theoretical analysis of
the nonzeros-per-row distribution. For the over 2,800
test matrices available in the Suite Sparse matrix
collection, we compare the performance against SpMV
kernels provided by NVIDIA's cuSPARSE library and a
heavily-tuned sliced ELL (SELL-P) kernel that prevents
unnecessary padding by considering the irregular
matrices as a combination of matrix blocks stored in
ELL format.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "2",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Hadade:2020:SPU,
author = "Ioan Hadade and Timothy M. Jones and Feng Wang and
Luca di Mare",
title = "Software Prefetching for Unstructured Mesh
Applications",
journal = j-TOPC,
volume = "7",
number = "1",
pages = "3:1--3:23",
month = apr,
year = "2020",
CODEN = "????",
DOI = "https://doi.org/10.1145/3380932",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Mon Apr 6 08:56:55 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3380932",
abstract = "This article demonstrates the utility and
implementation of software prefetching in an
unstructured finite volume computational fluid dynamics
code of representative size and complexity to an
industrial application and across a number of modern
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "3",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Grutzmacher:2020:APC,
author = "Thomas Gr{\"u}tzmacher and Terry Cojean and Goran
Flegar and Hartwig Anzt and Enrique S.
Quintana-Ort{\'\i}",
title = "Acceleration of {PageRank} with Customized Precision
Based on Mantissa Segmentation",
journal = j-TOPC,
volume = "7",
number = "1",
pages = "4:1--4:19",
month = apr,
year = "2020",
CODEN = "????",
DOI = "https://doi.org/10.1145/3380934",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Mon Apr 6 08:56:55 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/fparith.bib;
https://www.math.utah.edu/pub/tex/bib/pagerank.bib;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3380934",
abstract = "We describe the application of a
communication-reduction technique for the PageRank
algorithm that dynamically adapts the precision of the
data access to the numerical requirements of the
algorithm as the iteration converges. Our
variable-precision strategy, using a customized
precision format based on mantissa segmentation (CPMS),
abandons the IEEE 754 single- and double-precision
number representation formats employed in the standard
implementation of PageRank, and instead handles the
data in memory using a customized floating-point
format. The customized format enables fast data access
in different accuracy, prevents overflow/underflow by
preserving the IEEE 754 double-precision exponent, and
efficiently avoids data duplication, since all bits of
the original IEEE 754 double-precision mantissa are
preserved in memory, but re-organized for efficient
reduced precision access. With this approach, the
truncated values (omitting significand bits), as well
as the original IEEE double-precision values, can be
retrieved without duplicating the data in different
formats.\par
Our numerical experiments on an NVIDIA V100 GPU (Volta
architecture) and a server equipped with two Intel Xeon
Platinum 8168 CPUs (48 cores in total) expose that,
compared with a standard IEEE double-precision
implementation, the CPMS-based PageRank completes about
10\% faster if high-accuracy output is needed, and
about 30\% faster if reduced output accuracy is
acceptable.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "4",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Das:2020:SMP,
author = "Apurba Das and Seyed-Vahid Sanei-Mehri and Srikanta
Tirthapura",
title = "Shared-memory Parallel Maximal Clique Enumeration from
Static and Dynamic Graphs",
journal = j-TOPC,
volume = "7",
number = "1",
pages = "5:1--5:28",
month = apr,
year = "2020",
CODEN = "????",
DOI = "https://doi.org/10.1145/3380936",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Mon Apr 6 08:56:55 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3380936",
abstract = "Maximal Clique Enumeration (MCE) is a fundamental
graph mining problem and is useful as a primitive in
identifying dense structures in a graph. Due to the
high computational cost of MCE, parallel methods are
imperative for dealing with large graphs. We \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "5",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Hamilton:2020:ASC,
author = "Kathleen E. Hamilton and Catherine D. Schuman and
Steven R. Young and Ryan S. Bennink and Neena Imam and
Travis S. Humble",
title = "Accelerating Scientific Computing in the
Post-{Moore}'s Era",
journal = j-TOPC,
volume = "7",
number = "1",
pages = "6:1--6:31",
month = apr,
year = "2020",
CODEN = "????",
DOI = "https://doi.org/10.1145/3380940",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Mon Apr 6 08:56:55 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3380940",
abstract = "Novel uses of graphical processing units for
accelerated computation revolutionized the field of
high-performance scientific computing by providing
specialized workflows tailored to algorithmic
requirements. As the era of Moore's law draws to a
close, \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "6",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Lakhotia:2020:GSC,
author = "Kartik Lakhotia and Rajgopal Kannan and Sourav Pati
and Viktor Prasanna",
title = "{GPOP}: a Scalable Cache- and Memory-efficient
Framework for Graph Processing over Parts",
journal = j-TOPC,
volume = "7",
number = "1",
pages = "7:1--7:24",
month = apr,
year = "2020",
CODEN = "????",
DOI = "https://doi.org/10.1145/3380942",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Mon Apr 6 08:56:55 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3380942",
abstract = "The past decade has seen the development of many
shared-memory graph processing frameworks intended to
reduce the effort of developing high-performance
parallel applications. However, many of these
frameworks, based on Vertex-centric or Edge-centric
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "7",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Anderson:2020:RRO,
author = "Jeff Anderson and Engin Kayraklioglu and Shuai Sun and
Joseph Crandall and Yousra Alkabani and Vikram Narayana
and Volker Sorger and Tarek El-Ghazawi",
title = "{ROC}: a Reconfigurable Optical Computer for
Simulating Physical Processes",
journal = j-TOPC,
volume = "7",
number = "1",
pages = "8:1--8:29",
month = apr,
year = "2020",
CODEN = "????",
DOI = "https://doi.org/10.1145/3380944",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Mon Apr 6 08:56:55 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3380944",
abstract = "Due to the end of Moore's law and Dennard scaling, we
are entering a new era of processors. Computing systems
are increasingly facing power and performance
challenges due to both device- and circuit-related
challenges with resistive and capacitive \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "8",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Monemi:2020:EDW,
author = "Alireza Monemi and Farshad Khunjush and Maurizio
Palesi and Hamid Sarbazi-Azad",
title = "An Enhanced Dynamic Weighted Incremental Technique for
{QoS} Support in {NoC}",
journal = j-TOPC,
volume = "7",
number = "2",
pages = "9:1--9:31",
month = may,
year = "2020",
CODEN = "????",
DOI = "https://doi.org/10.1145/3391442",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Mon Jun 1 09:19:25 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3391442",
abstract = "Providing Quality-of-Service (QoS) in many-core
network-on-chip (NoC) platforms is critical due to the
high level of resource sharing in such systems. This
article presents a hard-built Equality-of-Service (EoS)
and Differential-Service (DS) as subsets \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "9",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Natarajan:2020:FLL,
author = "Aravind Natarajan and Arunmoezhi Ramachandran and
Neeraj Mittal",
title = "{FEAST}: a Lightweight Lock-free Concurrent Binary
Search Tree",
journal = j-TOPC,
volume = "7",
number = "2",
pages = "10:1--10:64",
month = may,
year = "2020",
CODEN = "????",
DOI = "https://doi.org/10.1145/3391438",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Mon Jun 1 09:19:25 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3391438",
abstract = "We present a lock-free algorithm for concurrent
manipulation of a binary search tree (BST) in an
asynchronous shared memory system that supports search,
insert, and delete operations. In addition to read and
write instructions, our algorithm uses \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "10",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Salah:2020:TSE,
author = "Ahmad Salah and Kenli Li and Qing Liao and Mervat
Hashem and Zhiyong Li and Anthony T. Chronopoulos and
Albert Y. Zomaya",
title = "A Time-space Efficient Algorithm for Parallel $k$-way
In-place Merging based on Sequence Partitioning and
Perfect Shuffle",
journal = j-TOPC,
volume = "7",
number = "2",
pages = "11:1--11:23",
month = may,
year = "2020",
CODEN = "????",
DOI = "https://doi.org/10.1145/3391443",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Mon Jun 1 09:19:25 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3391443",
abstract = "The huge data volumes, big data, and the emergence of
new parallel architectures lead to revisiting classic
computer science topics. The motivation of the proposed
work for revisiting the parallel k -way in-place
merging is primarily related to the \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "11",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Duan:2020:CSR,
author = "Shaohua Duan and Pradeep Subedi and Philip Davis and
Keita Teranishi and Hemanth Kolla and Marc Gamell and
Manish Parashar",
title = "{CoREC}: Scalable and Resilient In-memory Data Staging
for In-situ Workflows",
journal = j-TOPC,
volume = "7",
number = "2",
pages = "12:1--12:29",
month = may,
year = "2020",
CODEN = "????",
DOI = "https://doi.org/10.1145/3391448",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Mon Jun 1 09:19:25 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3391448",
abstract = "The dramatic increase in the scale of current and
planned high-end HPC systems is leading new challenges,
such as the growing costs of data movement and IO, and
the reduced mean time between failures (MTBF) of system
components. In-situ workflows, i.e., \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "12",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Alam:2020:GMS,
author = "Maksudul Alam and Maleq Khan and Kalyan S. Perumalla
and Madhav Marathe",
title = "Generating Massive Scale-free Networks: Novel Parallel
Algorithms using the Preferential Attachment Model",
journal = j-TOPC,
volume = "7",
number = "2",
pages = "13:1--13:35",
month = may,
year = "2020",
CODEN = "????",
DOI = "https://doi.org/10.1145/3391446",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Mon Jun 1 09:19:25 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3391446",
abstract = "Recently, there has been substantial interest in the
study of various random networks as mathematical models
of complex systems. As real-life complex systems grow
larger, the ability to generate progressively large
random networks becomes all the more \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "13",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Lee:2020:ISI,
author = "Jaejin Lee and Lawrence Rauchwerger and Armando
Solar-Lezama and Guy Steele",
title = "Introduction to the Special Issue on {PPoPP 2017}
(Part 2)",
journal = j-TOPC,
volume = "7",
number = "3",
pages = "14:1--14:2",
month = aug,
year = "2020",
CODEN = "????",
DOI = "https://doi.org/10.1145/3407185",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Thu Aug 6 08:56:07 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3407185",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "14",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Jiang:2020:CSM,
author = "Peng Jiang and Yang Xia and Gagan Agrawal",
title = "Combining {SIMD} and Many\slash Multi-core Parallelism
for Finite-state Machines with Enumerative
Speculation",
journal = j-TOPC,
volume = "7",
number = "3",
pages = "15:1--15:26",
month = aug,
year = "2020",
CODEN = "????",
DOI = "https://doi.org/10.1145/3399714",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Thu Aug 6 08:56:07 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3399714",
abstract = "Finite-state Machine (FSM) is the key kernel behind
many popular applications, including regular expression
matching, text tokenization, and Huffman decoding.
Parallelizing FSMs is extremely difficult because of
the strong dependencies and unpredictable \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "15",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Basin:2020:KKV,
author = "Dmitry Basin and Edward Bortnikov and Anastasia
Braginsky and Guy Golan-Gueta and Eshcar Hillel and
Idit Keidar and Moshe Sulamy",
title = "{KiWi}: a Key--value Map for Scalable Real-time
Analytics",
journal = j-TOPC,
volume = "7",
number = "3",
pages = "16:1--16:28",
month = aug,
year = "2020",
CODEN = "????",
DOI = "https://doi.org/10.1145/3399718",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Thu Aug 6 08:56:07 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/java2020.bib;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3399718",
abstract = "We present KiWi, the first atomic KV-map to
efficiently support simultaneous large scans and
real-time access. The key to achieving this is treating
scans as first class citizens and organizing the data
structure around them. KiWi provides wait-free scans,
whereas its put operations are lightweight and
lock-free. It optimizes memory management jointly with
data structure access. We implement KiWi and compare it
to state-of-the-art solutions. Compared to other
KV-maps providing atomic scans, KiWi performs either
long scans or concurrent puts an order of magnitude
faster. Its scans are twice as fast as non-atomic ones
implemented via iterators in the Java skiplist.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "16",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Chabbi:2020:EAL,
author = "Milind Chabbi and Abdelhalim Amer and Xu Liu",
title = "Efficient Abortable-locking Protocol for Multi-level
{NUMA} Systems: Design and Correctness",
journal = j-TOPC,
volume = "7",
number = "3",
pages = "17:1--17:32",
month = aug,
year = "2020",
CODEN = "????",
DOI = "https://doi.org/10.1145/3399728",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Thu Aug 6 08:56:07 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3399728",
abstract = "The popularity of Non-Uniform Memory Access (NUMA)
architectures has led to numerous locality-preserving
hierarchical lock designs, such as HCLH, HMCS, and
cohort locks. Locality-preserving locks trade fairness
for higher throughput. Hence, some \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "17",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Ben-Nun:2020:GAM,
author = "Tal Ben-Nun and Michael Sutton and Sreepathi Pai and
Keshav Pingali",
title = "{Groute}: Asynchronous Multi-{GPU} Programming Model
with Applications to Large-scale Graph Processing",
journal = j-TOPC,
volume = "7",
number = "3",
pages = "18:1--18:27",
month = aug,
year = "2020",
CODEN = "????",
DOI = "https://doi.org/10.1145/3399730",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Thu Aug 6 08:56:07 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3399730",
abstract = "Nodes with multiple GPUs are becoming the platform of
choice for high-performance computing. However, most
applications are written using bulk-synchronous
programming models, which may not be optimal for
irregular algorithms that benefit from low-. \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "18",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Alappat:2020:RAC,
author = "Christie Alappat and Achim Basermann and Alan R.
Bishop and Holger Fehske and Georg Hager and Olaf
Schenk and Jonas Thies and Gerhard Wellein",
title = "A Recursive Algebraic Coloring Technique for
Hardware-efficient Symmetric Sparse Matrix--vector
Multiplication",
journal = j-TOPC,
volume = "7",
number = "3",
pages = "19:1--19:37",
month = aug,
year = "2020",
CODEN = "????",
DOI = "https://doi.org/10.1145/3399732",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Thu Aug 6 08:56:07 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3399732",
abstract = "The symmetric sparse matrix-vector multiplication
(SymmSpMV) is an important building block for many
numerical linear algebra kernel operations or graph
traversal applications. Parallelizing SymmSpMV on
today's multicore platforms with up to 100 cores is
difficult due to the need to manage conflicting updates
on the result vector. Coloring approaches can be used
to solve this problem without data duplication, but
existing coloring algorithms do not take load balancing
and deep memory hierarchies into account, hampering
scalability and full-chip performance. In this work, we
propose the recursive algebraic coloring engine (RACE),
a novel coloring algorithm and open-source library
implementation that eliminates the shortcomings of
previous coloring methods in terms of hardware
efficiency and parallelization overhead. We describe
the level construction, distance-$k$ coloring, and load
balancing steps in RACE, use it to parallelize
SymmSpMV, and compare its performance on 31 sparse
matrices with other state-of-the-art coloring
techniques and Intel MKL on two modern multicore
processors. RACE outperforms all other approaches
substantially. By means of a parameterized roofline
model, we analyze the SymmSpMV performance in detail
and discuss outliers. While we focus on SymmSpMV in
this article, our algorithm and software are applicable
to any sparse matrix operation with data dependencies
that can be resolved by distance-$k$ coloring.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "19",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Davydov:2020:ADS,
author = "Denis Davydov and Martin Kronbichler",
title = "Algorithms and Data Structures for Matrix-Free Finite
Element Operators with {MPI}-Parallel Sparse
Multi-Vectors",
journal = j-TOPC,
volume = "7",
number = "3",
pages = "20:1--20:30",
month = aug,
year = "2020",
CODEN = "????",
DOI = "https://doi.org/10.1145/3399736",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Thu Aug 6 08:56:07 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/pvm.bib;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3399736",
abstract = "Traditional solution approaches for problems in
quantum mechanics scale as $ O(M^3) $, where $M$ is the
number of electrons. Various methods have been proposed
to address this issue and obtain a linear scaling $
O(M)$. One promising formulation is the direct
minimization of energy. Such methods take advantage of
physical localization of the solution, allowing users
to seek it in terms of non-orthogonal orbitals with
local support.\par
This work proposes a numerically efficient
implementation of sparse parallel vectors within the
open-source finite element library deal.II. The main
algorithmic ingredient is the matrix-free evaluation of
the Hamiltonian operator by cell-wise quadrature. Based
on an a-priori chosen support for each vector, we
develop algorithms and data structures to perform (i)
matrix-free sparse matrix multivector products (SpMM),
(ii) the projection of an operator onto a sparse
sub-space (inner products), and (iii)
post-multiplication of a sparse multivector with a
square matrix. The node-level performance is analyzed
using a roofline model. Our matrix-free implementation
of finite element operators with sparse multivectors
achieves a performance of 157 GFlop/s on an Intel
Cascade Lake processor with 20 cores. Strong and weak
scaling results are reported for a representative
benchmark problem using quadratic and quartic finite
element bases.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "20",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Sengupta:2020:HAP,
author = "Tapan K. Sengupta and Prasannabalaji Sundaram and
Vajjala K. Suman and Swagata Bhaumik",
title = "A High Accuracy Preserving Parallel Algorithm for
Compact Schemes for {DNS}",
journal = j-TOPC,
volume = "7",
number = "4",
pages = "21:1--21:32",
month = dec,
year = "2020",
CODEN = "????",
DOI = "https://doi.org/10.1145/3418073",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Sun Mar 28 08:05:40 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3418073",
abstract = "A new accuracy-preserving parallel algorithm employing
compact schemes is presented for direct numerical
simulation of the Navier--Stokes equations. Here the
connotation of accuracy preservation is having the same
level of accuracy obtained by the \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "21",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Aggarwal:2020:OLF,
author = "Karan Aggarwal and Uday Bondhugula",
title = "Optimizing the Linear Fascicle Evaluation Algorithm
for Multi-core and Many-core Systems",
journal = j-TOPC,
volume = "7",
number = "4",
pages = "22:1--22:45",
month = dec,
year = "2020",
CODEN = "????",
DOI = "https://doi.org/10.1145/3418075",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Sun Mar 28 08:05:40 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3418075",
abstract = "Sparse matrix-vector multiplication ( SpMV )
operations are commonly used in various scientific and
engineering applications. The performance of the SpMV
operation often depends on exploiting regularity
patterns in the matrix. Various representations and
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "22",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Tumeo:2020:ITSb,
author = "Antonino Tumeo and Fabrizio Petrini and John Feo and
Mahantesh Halappanavar",
title = "Introduction to the {TOPC} Special Issue on
Innovations in Systems for Irregular Applications,
{Part 2}",
journal = j-TOPC,
volume = "7",
number = "4",
pages = "23:1--23:2",
month = dec,
year = "2020",
CODEN = "????",
DOI = "https://doi.org/10.1145/3419771",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Sun Mar 28 08:05:40 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3419771",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "23",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Namashivayam:2020:MFI,
author = "Naveen Namashivayam and Bill Long and Deepak
Eachempati and Bob Cernohous and Mark Pagel",
title = "A Modern {Fortran} Interface in {OpenSHMEM} Need for
Interoperability with {Parallel Fortran} Using
Coarrays",
journal = j-TOPC,
volume = "7",
number = "4",
pages = "24:1--24:25",
month = dec,
year = "2020",
CODEN = "????",
DOI = "https://doi.org/10.1145/3418084",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Sun Mar 28 08:05:40 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/fortran3.bib;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3418084",
abstract = "Languages and libraries based on Partitioned Global
Address Space (PGAS) programming models are convenient
for exploiting scalable parallelism on large
applications across different domains with irregular
memory access patterns. OpenSHMEM is a PGAS-.
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "24",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Hein:2020:PSI,
author = "Eric R. Hein and Srinivas Eswar and Abdurrahman Yasar
and Jiajia Li and Jeffrey S. Young and Thomas M. Conte
and {\"U}mit V. {\c{C}}ataly{\"u}rek and Richard Vuduc
and Jason Riedy and Bora U{\c{c}}ar",
title = "Programming Strategies for Irregular Algorithms on the
{Emu Chick}",
journal = j-TOPC,
volume = "7",
number = "4",
pages = "25:1--25:25",
month = dec,
year = "2020",
CODEN = "????",
DOI = "https://doi.org/10.1145/3418077",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Sun Mar 28 08:05:40 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3418077",
abstract = "The Emu Chick prototype implements migratory
memory-side processing in a novel hardware system.
Rather than transferring large amounts of data across
the system interconnect, the Emu Chick moves
lightweight thread contexts to near-memory cores before
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "25",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Leidel:2020:TME,
author = "John D. Leidel and Xi Wang and Brody Williams and Yong
Chen",
title = "Toward a Microarchitecture for Efficient Execution of
Irregular Applications",
journal = j-TOPC,
volume = "7",
number = "4",
pages = "26:1--26:24",
month = dec,
year = "2020",
CODEN = "????",
DOI = "https://doi.org/10.1145/3418082",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Sun Mar 28 08:05:40 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3418082",
abstract = "Given the increasing importance of efficient
data-intensive computing, we find that modern processor
designs are not well suited to the irregular memory
access patterns often found in these algorithms.
Applications and algorithms that do not exhibit
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "26",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Fezzardi:2020:ABD,
author = "Pietro Fezzardi and Fabrizio Ferrandi",
title = "Automated Bug Detection for High-level Synthesis of
Multi-threaded Irregular Applications",
journal = j-TOPC,
volume = "7",
number = "4",
pages = "27:1--27:26",
month = dec,
year = "2020",
CODEN = "????",
DOI = "https://doi.org/10.1145/3418086",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Sun Mar 28 08:05:40 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3418086",
abstract = "Field Programmable Gate Arrays (FPGAs) are becoming an
appealing technology in datacenters and High
Performance Computing. High-Level Synthesis (HLS) of
multi-threaded parallel programs is increasingly used
to extract parallelism. Despite great leaps \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "27",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Savoie:2021:MIJ,
author = "Lee Savoie and David K. Lowenthal and Bronis R. {De
Supinski} and Kathryn Mohror and Nikhil Jain",
title = "Mitigating Inter-Job Interference via Process-Level
Quality-of-Service",
journal = j-TOPC,
volume = "8",
number = "1",
pages = "1:1--1:26",
month = apr,
year = "2021",
CODEN = "????",
DOI = "https://doi.org/10.1145/3434397",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Apr 23 17:58:56 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3434397",
abstract = "Jobs on most high-performance computing (HPC) systems
share the network with other concurrently executing
jobs. Network sharing leads to contention that can
severely degrade performance. This article investigates
the use of Quality of Service (QoS) \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "1",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Reza:2021:SPM,
author = "Tahsin Reza and Hassan Halawa and Matei Ripeanu and
Geoffrey Sanders and Roger A. Pearce",
title = "Scalable Pattern Matching in Metadata Graphs via
Constraint Checking",
journal = j-TOPC,
volume = "8",
number = "1",
pages = "2:1--2:45",
month = apr,
year = "2021",
CODEN = "????",
DOI = "https://doi.org/10.1145/3434391",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Apr 23 17:58:56 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3434391",
abstract = "Pattern matching is a fundamental tool for answering
complex graph queries. Unfortunately, existing
solutions have limited capabilities: They do not scale
to process large graphs and/or support only a
restricted set of search templates or usage \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "2",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Fineman:2021:ISIa,
author = "Jeremy Fineman and Aydin Buluc and Seth Gilbert",
title = "Introduction to the Special Issue for {SPAA 2018}:
{Part 1}",
journal = j-TOPC,
volume = "8",
number = "1",
pages = "3e:1--3e:1",
month = apr,
year = "2021",
CODEN = "????",
DOI = "https://doi.org/10.1145/3456774",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Apr 23 17:58:56 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3456774",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "3e",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Alon:2021:PBP,
author = "Noga Alon and Yossi Azar and Mark Berlin",
title = "The Price of Bounded Preemption",
journal = j-TOPC,
volume = "8",
number = "1",
pages = "3:1--3:21",
month = apr,
year = "2021",
CODEN = "????",
DOI = "https://doi.org/10.1145/3434377",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Apr 23 17:58:56 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3434377",
abstract = "In this article we provide a tight bound for the price
of preemption for scheduling jobs on a single machine
(or multiple machines). The input consists of a set of
jobs to be scheduled and of an integer parameter k
{$>$}= 1. Each job has a release time, \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "3",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Dhulipala:2021:TEP,
author = "Laxman Dhulipala and Guy E. Blelloch and Julian Shun",
title = "Theoretically Efficient Parallel Graph Algorithms Can
Be Fast and Scalable",
journal = j-TOPC,
volume = "8",
number = "1",
pages = "4:1--4:70",
month = apr,
year = "2021",
CODEN = "????",
DOI = "https://doi.org/10.1145/3434393",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Apr 23 17:58:56 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3434393",
abstract = "There has been significant recent interest in parallel
graph processing due to the need to quickly analyze the
large graphs available today. Many graph codes have
been designed for distributed memory or external
memory. However, today even the largest \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "4",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Kaplan:2021:DRS,
author = "Haim Kaplan and Shay Solomon",
title = "Dynamic Representations of Sparse Distributed
Networks: a Locality-sensitive Approach",
journal = j-TOPC,
volume = "8",
number = "1",
pages = "5:1--5:26",
month = apr,
year = "2021",
CODEN = "????",
DOI = "https://doi.org/10.1145/3434395",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Apr 23 17:58:56 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3434395",
abstract = "In 1999, Brodal and Fagerberg (BF) gave an algorithm
for maintaining a low outdegree orientation of a
dynamic uniformly sparse graph. Specifically, for a
dynamic graph on $n$-vertices, with arboricity bounded
by $ \alpha $ at all times, the BF algorithm supports
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "5",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Fineman:2021:ISIb,
author = "Jeremy Fineman and Aydin Buluc and Seth Gilbert",
title = "Introduction to the Special Issue for {SPAA 2018} ---
{Part 2}",
journal = j-TOPC,
volume = "8",
number = "2",
pages = "6:1--6:1",
month = jun,
year = "2021",
CODEN = "????",
DOI = "https://doi.org/10.1145/3463366",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Aug 24 07:42:49 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3463366",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "6",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Pandurangan:2021:DCL,
author = "Gopal Pandurangan and Peter Robinson and Michele
Scquizzato",
title = "On the Distributed Complexity of Large-Scale Graph
Computations",
journal = j-TOPC,
volume = "8",
number = "2",
pages = "7:1--7:28",
month = jun,
year = "2021",
CODEN = "????",
DOI = "https://doi.org/10.1145/3460900",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Aug 24 07:42:49 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3460900",
abstract = "Motivated by the increasing need to understand the
distributed algorithmic foundations of large-scale
graph computations, we study some fundamental graph
problems in a message-passing model for distributed
computing where $ k \geq 2 $ machines jointly perform
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "7",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Geissmann:2021:PMC,
author = "Barbara Geissmann and Lukas Gianinazzi",
title = "Parallel Minimum Cuts in Near-linear Work and Low
Depth",
journal = j-TOPC,
volume = "8",
number = "2",
pages = "8:1--8:20",
month = jun,
year = "2021",
CODEN = "????",
DOI = "https://doi.org/10.1145/3460890",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Aug 24 07:42:49 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3460890",
abstract = "We present the first near-linear work and
poly-logarithmic depth algorithm for computing a
minimum cut in an undirected graph. Previous parallel
algorithms with poly-logarithmic depth required at
least quadratic work in the number of vertices. In a
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "8",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Lucarelli:2021:ONP,
author = "Giorgio Lucarelli and Benjamin Moseley and Nguyen Kim
Thang and Abhinav Srivastav and Denis Trystram",
title = "Online Non-preemptive Scheduling on Unrelated Machines
with Rejections",
journal = j-TOPC,
volume = "8",
number = "2",
pages = "9:1--9:22",
month = jun,
year = "2021",
CODEN = "????",
DOI = "https://doi.org/10.1145/3460880",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Aug 24 07:42:49 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3460880",
abstract = "When a computer system schedules jobs there is
typically a significant cost associated with preempting
a job during execution. This cost can be incurred from
the expensive task of saving the memory's state or from
loading data into and out of memory. \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "9",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Winblad:2021:LFC,
author = "Kjell Winblad and Konstantinos Sagonas and Bengt
Jonsson",
title = "Lock-free Contention Adapting Search Trees",
journal = j-TOPC,
volume = "8",
number = "2",
pages = "10:1--10:38",
month = jun,
year = "2021",
CODEN = "????",
DOI = "https://doi.org/10.1145/3460874",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Aug 24 07:42:49 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3460874",
abstract = "Concurrent key-value stores with range query support
are crucial for the scalability and performance of many
applications. Existing lock-free data structures of
this kind use a fixed synchronization granularity.
Using a fixed synchronization granularity \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "10",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Green:2021:HSH,
author = "Oded Green",
title = "{HashGraph} --- Scalable Hash Tables Using a Sparse
Graph Data Structure",
journal = j-TOPC,
volume = "8",
number = "2",
pages = "11:1--11:17",
month = jun,
year = "2021",
CODEN = "????",
DOI = "https://doi.org/10.1145/3460872",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Aug 24 07:42:49 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/hash.bib;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3460872",
abstract = "In this article, we introduce HashGraph, a new
scalable approach for building hash tables that uses
concepts taken from sparse graph representations ---
hence, the name HashGraph. HashGraph introduces a new
way to deal with hash-collisions that does not use
``open-addressing'' or ``separate-chaining,'' yet it
has the benefits of both these approaches. HashGraph
currently works for static inputs. Recent progress with
dynamic graph data structures suggests that HashGraph
might be extendable to dynamic inputs as well. We show
that HashGraph can deal with a large number of hash
values per entry without loss of performance. Last, we
show a new querying algorithm for value lookups. We
experimentally compare HashGraph to several
state-of-the-art implementations and find that it
outperforms them on average $ 2 \times $ when the
inputs are unique and by as much as $ 40 \times $ when
the input contains duplicates. The implementation of
HashGraph in this article is for NVIDIA GPUs. HashGraph
can build a hash table at a rate of 2.5 billion keys
per second on a NVIDIA GV100 GPU and can query at
nearly the same rate.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "11",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Berenbrink:2021:ISI,
author = "Petra Berenbrink",
title = "Introduction to the Special Issue for {SPAA 2019}",
journal = j-TOPC,
volume = "8",
number = "3",
pages = "12:1--12:1",
month = sep,
year = "2021",
CODEN = "????",
DOI = "https://doi.org/10.1145/3477610",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Sep 21 07:18:25 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3477610",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "12",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Behnezhad:2021:MPC,
author = "Soheil Behnezhad and Laxman Dhulipala and Hossein
Esfandiari and Jakub Lacki and Vahab Mirrokni and
Warren Schudy",
title = "Massively Parallel Computation via Remote Memory
Access",
journal = j-TOPC,
volume = "8",
number = "3",
pages = "13:1--13:25",
month = sep,
year = "2021",
CODEN = "????",
DOI = "https://doi.org/10.1145/3470631",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Sep 21 07:18:25 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3470631",
abstract = "We introduce the Adaptive Massively Parallel
Computation (AMPC) model, which is an extension of the
Massively Parallel Computation (MPC) model. At a high
level, the AMPC model strengthens the MPC model by
storing all messages sent within a round in a
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "13",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Ellen:2021:CLL,
author = "Faith Ellen and Barun Gorain and Avery Miller and
Andrzej Pelc",
title = "Constant-Length Labeling Schemes for Deterministic
Radio Broadcast",
journal = j-TOPC,
volume = "8",
number = "3",
pages = "14:1--14:17",
month = sep,
year = "2021",
CODEN = "????",
DOI = "https://doi.org/10.1145/3470633",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Sep 21 07:18:25 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3470633",
abstract = "Broadcast is one of the fundamental network
communication primitives. One node of a network, called
the source, has a message that has to be learned by all
other nodes. We consider broadcast in radio networks,
modeled as simple undirected connected graphs
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "14",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Bender:2021:EMD,
author = "Michael A. Bender and Alex Conway and Mart{\'\i}n
Farach-Colton and William Jannen and Yizheng Jiao and
Rob Johnson and Eric Knorr and Sara Mcallister and
Nirjhar Mukherjee and Prashant Pandey and Donald E.
Porter and Jun Yuan and Yang Zhan",
title = "External-memory Dictionaries in the Affine and {PDAM}
Models",
journal = j-TOPC,
volume = "8",
number = "3",
pages = "15:1--15:20",
month = sep,
year = "2021",
CODEN = "????",
DOI = "https://doi.org/10.1145/3470635",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Sep 21 07:18:25 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3470635",
abstract = "Storage devices have complex performance profiles,
including costs to initiate IOs (e.g., seek times in
hard drives), parallelism and bank conflicts (in SSDs),
costs to transfer data, and firmware-internal
operations. The Disk-access Machine (DAM) model
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "15",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Maier:2021:EPC,
author = "Matthias Maier and Martin Kronbichler",
title = "Efficient Parallel {$3$D} Computation of the
Compressible {Euler} Equations with an Invariant-domain
Preserving Second-order Finite-element Scheme",
journal = j-TOPC,
volume = "8",
number = "3",
pages = "16:1--16:30",
month = sep,
year = "2021",
CODEN = "????",
DOI = "https://doi.org/10.1145/3470637",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Sep 21 07:18:25 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3470637",
abstract = "We discuss the efficient implementation of a
high-performance second-order collocation-type
finite-element scheme for solving the compressible
Euler equations of gas dynamics on unstructured meshes.
The solver is based on the convex-limiting technique
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "16",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Edwards:2021:SFG,
author = "James Edwards and Uzi Vishkin",
title = "Study of Fine-grained Nested Parallelism in {CDCL SAT}
Solvers",
journal = j-TOPC,
volume = "8",
number = "3",
pages = "17:1--17:18",
month = sep,
year = "2021",
CODEN = "????",
DOI = "https://doi.org/10.1145/3470639",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Sep 21 07:18:25 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3470639",
abstract = "Boolean satisfiability (SAT) is an important
performance-hungry problem with applications in many
problem domains. However, most work on parallelizing
SAT solvers has focused on coarse-grained, mostly
embarrassing, parallelism. Here, we study fine-grained
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "17",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Feuilloley:2021:RLN,
author = "Laurent Feuilloley and Pierre Fraigniaud",
title = "Randomized Local Network Computing: Derandomization
Beyond Locally Checkable Labelings",
journal = j-TOPC,
volume = "8",
number = "4",
pages = "18:1--18:25",
month = dec,
year = "2021",
CODEN = "????",
DOI = "https://doi.org/10.1145/3470640",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Dec 10 10:52:35 MST 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3470640",
abstract = "We carry on investigating the line of research
questioning the power of randomization for the design
of distributed algorithms. In their seminal paper, Naor
and Stockmeyer [STOC 1993] established that, in the
context of network computing in which all \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "18",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Monfared:2021:HTP,
author = "Saleh Khalaj Monfared and Omid Hajihassani and Vahid
Mohsseni and Dara Rahmati and Saeid Gorgin",
title = "A High-throughput Parallel {Viterbi} Algorithm via
Bitslicing",
journal = j-TOPC,
volume = "8",
number = "4",
pages = "19:1--19:25",
month = dec,
year = "2021",
CODEN = "????",
DOI = "https://doi.org/10.1145/3470642",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Dec 10 10:52:35 MST 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3470642",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "19",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Wang:2021:PBD,
author = "Shao-Chung Wang and Lin-Ya Yu and Li-An Her and
Yuan-Shin Hwang and Jenq-Kuen Lee",
title = "Pointer-Based Divergence Analysis for {OpenCL 2.0}
Programs",
journal = j-TOPC,
volume = "8",
number = "4",
pages = "20:1--20:23",
month = dec,
year = "2021",
CODEN = "????",
DOI = "https://doi.org/10.1145/3470644",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Dec 10 10:52:35 MST 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3470644",
abstract = "A modern GPU is designed with many large thread groups
to achieve a high throughput and performance. Within
these groups, the threads are grouped into fixed-size
SIMD batches in which the same instruction is applied
to vectors of data in a lockstep. This \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "20",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Kang:2021:AEC,
author = "Xuejiao Kang and David F. Gleich and Ahmed Sameh and
Ananth Grama",
title = "Adaptive Erasure Coded Fault Tolerant Linear System
Solver",
journal = j-TOPC,
volume = "8",
number = "4",
pages = "21:1--21:19",
month = dec,
year = "2021",
CODEN = "????",
DOI = "https://doi.org/10.1145/3490557",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Dec 10 10:52:35 MST 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3490557",
abstract = "As parallel and distributed systems scale, fault
tolerance is an increasingly important
problem-particularly on systems with limited I/O
capacity and bandwidth. Erasure coded computations
address this problem by augmenting a given problem
instance with \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "21",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Jayanti:2021:DCA,
author = "Prasad Jayanti and Siddhartha Jayanti",
title = "Deterministic Constant-Amortized-{RMR} Abortable Mutex
for {CC} and {DSM}",
journal = j-TOPC,
volume = "8",
number = "4",
pages = "22:1--22:26",
month = dec,
year = "2021",
CODEN = "????",
DOI = "https://doi.org/10.1145/3490559",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Dec 10 10:52:35 MST 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3490559",
abstract = "The abortable mutual exclusion problem, proposed by
Scott and Scherer in response to the needs in real-time
systems and databases, is a variant of mutual exclusion
that allows processes to abort from their attempt to
acquire the lock. Worst-case constant \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "22",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Leinhauser:2022:MDI,
author = "Matthew Leinhauser and Ren{\'e} Widera and Sergei
Bastrakov and Alexander Debus and Michael Bussmann and
Sunita Chandrasekaran",
title = "Metrics and Design of an Instruction Roofline Model
for {AMD GPUs}",
journal = j-TOPC,
volume = "9",
number = "1",
pages = "1:1--1:14",
month = mar,
year = "2022",
CODEN = "????",
DOI = "https://doi.org/10.1145/3505285",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Thu Mar 24 08:01:07 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3505285",
abstract = "Due to the recent announcement of the Frontier
supercomputer, many scientific application developers
are working to make their applications compatible with
AMD (CPU-GPU) architectures, which means moving away
from the traditional CPU and NVIDIA-GPU \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "1",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Axtmann:2022:EPS,
author = "Michael Axtmann and Sascha Witt and Daniel Ferizovic
and Peter Sanders",
title = "Engineering In-place (Shared-memory) Sorting
Algorithms",
journal = j-TOPC,
volume = "9",
number = "1",
pages = "2:1--2:62",
month = mar,
year = "2022",
CODEN = "????",
DOI = "https://doi.org/10.1145/3505286",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Thu Mar 24 08:01:07 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3505286",
abstract = "We present new sequential and parallel sorting
algorithms that now represent the fastest known
techniques for a wide range of input sizes, input
distributions, data types, and machines. Somewhat
surprisingly, part of the speed advantage is due to the
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "2",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Mitchell:2022:BOR,
author = "Rory Mitchell and Daniel Stokes and Eibe Frank and
Geoffrey Holmes",
title = "Bandwidth-Optimal Random Shuffling for {GPUs}",
journal = j-TOPC,
volume = "9",
number = "1",
pages = "3:1--3:20",
month = mar,
year = "2022",
CODEN = "????",
DOI = "https://doi.org/10.1145/3505287",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Thu Mar 24 08:01:07 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3505287",
abstract = "Linear-time algorithms that are traditionally used to
shuffle data on CPUs, such as the method of
Fisher-Yates, are not well suited to implementation on
GPUs due to inherent sequential dependencies, and
existing parallel shuffling algorithms are \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "3",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Alomairy:2022:HPU,
author = "Rabab Alomairy and Wael Bader and Hatem Ltaief and
Youssef Mesri and David Keyes",
title = "High-performance {$3$D} Unstructured Mesh Deformation
Using Rank Structured Matrix Computations",
journal = j-TOPC,
volume = "9",
number = "1",
pages = "4:1--4:23",
month = mar,
year = "2022",
CODEN = "????",
DOI = "https://doi.org/10.1145/3512756",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Thu Mar 24 08:01:07 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3512756",
abstract = "The Radial Basis Function (RBF) technique is an
interpolation method that produces high-quality
unstructured adaptive meshes. However, the RBF-based
boundary problem necessitates solving a large dense
linear system with cubic arithmetic complexity that is
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "4",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Milman-Sela:2022:BLF,
author = "Gal Milman-Sela and Alex Kogan and Yossi Lev and
Victor Luchangco and Erez Petrank",
title = "{BQ}: a Lock-Free Queue with Batching",
journal = j-TOPC,
volume = "9",
number = "1",
pages = "5:1--5:49",
month = mar,
year = "2022",
CODEN = "????",
DOI = "https://doi.org/10.1145/3512757",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Thu Mar 24 08:01:07 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3512757",
abstract = "Concurrent data structures provide fundamental
building blocks for concurrent programming. Standard
concurrent data structures may be extended by allowing
a sequence of operations to be submitted as a batch for
later execution. A sequence of such \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "5",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Rinberg:2022:FCD,
author = "Arik Rinberg and Alexander Spiegelman and Edward
Bortnikov and Eshcar Hillel and Idit Keidar and Lee
Rhodes and Hadar Serviansky",
title = "Fast Concurrent Data Sketches",
journal = j-TOPC,
volume = "9",
number = "2",
pages = "6:1--6:35",
month = jun,
year = "2022",
CODEN = "????",
DOI = "https://doi.org/10.1145/3512758",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Sep 2 10:15:52 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3512758",
abstract = "Data sketches are approximate succinct summaries of
long data streams. They are widely used for processing
massive amounts of data and answering statistical
queries about it. Existing libraries producing sketches
are very fast, but do not allow \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "6",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Blelloch:2022:JPB,
author = "Guy Blelloch and Daniel Ferizovic and Yihan Sun",
title = "Joinable Parallel Balanced Binary Trees",
journal = j-TOPC,
volume = "9",
number = "2",
pages = "7:1--7:41",
month = jun,
year = "2022",
CODEN = "????",
DOI = "https://doi.org/10.1145/3512769",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Sep 2 10:15:52 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3512769",
abstract = "In this article, we show how a single function, join,
can be used to implement parallel balanced binary
search trees (BSTs) simply and efficiently. Based on
join, our approach applies to multiple balanced tree
data structures, and a variety of functions \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "7",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Chen:2022:FFG,
author = "Yuedan Chen and Guoqing Xiao and Kenli Li and
Francesco Piccialli and Albert Y. Zomaya",
title = "{fgSpMSpV}: a Fine-grained Parallel {SpMSpV} Framework
on {HPC} Platforms",
journal = j-TOPC,
volume = "9",
number = "2",
pages = "8:1--8:29",
month = jun,
year = "2022",
CODEN = "????",
DOI = "https://doi.org/10.1145/3512770",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Sep 2 10:15:52 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3512770",
abstract = "Sparse matrix--sparse vector (SpMSpV) multiplication
is one of the fundamental and important operations in
many high-performance scientific and engineering
applications. The inherent irregularity and poor data
locality lead to two main challenges to to scaling
SpMSpV over high-performance computing (HPC) systems:
(i) a large amount of redundant data limits the
utilization of bandwidth and parallel resources; (ii)
the irregular access pattern limits the exploitation of
computing resources. This paper proposes a fine-grained
parallel SpMSpV (fgSpMSpV) framework on Sunway
TaihuLight supercomputer to alleviate the challenges
for large-scale real-world applications. First,
fgSpMSpV adopts an MPI+OpenMP+X parallelization model
to exploit the multi-stage and hybrid parallelism of
heterogeneous HPC architectures and accelerate both
pre-/post-processing and main SpMSpV computation.
Second, fgSpMSpV utilizes an adaptive parallel
execution to reduce the pre-processing, adapt to the
parallelism and memory hierarchy of the Sunway system,
while still tame redundant and random memory accesses
in SpMSpV, including a set of techniques like the
fine-grained partitioner, re-collection method, and
Compressed Sparse Column Vector (CSCV) matrix format.
Third, fgSpMSpV uses several optimization techniques to
further utilize the computing resources. fgSpMSpV on
the Sunway TaihuLight gains a noticeable performance
improvement from the key optimization techniques with
various sparsity of the input. Additionally, fgSpMSpV
is implemented on an NVIDIA Tesal P100 GPU and applied
to the breath-first-search (BFS) application. fgSpMSpV
on a P100 GPU obtains the speedup of up to 134.38 $
\times $ over the state-of-the-art SpMSpV algorithms,
and the BFS application using fgSpMSpV achieves the
speedup of up to 21.68 $ \times $ over the
state-of-the-arts.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "8",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Liu:2022:SCC,
author = "Sixue Cliff Liu and Robert Endre Tarjan",
title = "Simple Concurrent Connected Components Algorithms",
journal = j-TOPC,
volume = "9",
number = "2",
pages = "9:1--9:26",
month = jun,
year = "2022",
CODEN = "????",
DOI = "https://doi.org/10.1145/3543546",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Sep 2 10:15:52 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3543546",
abstract = "We study a class of simple algorithms for concurrently
computing the connected components of an n-vertex,
m-edge graph. Our algorithms are easy to implement in
either the COMBINING CRCW PRAM or the MPC computing
model. For two related algorithms in this \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "9",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Alabandi:2022:ISQ,
author = "Ghadeer Alabandi and Martin Burtscher",
title = "Improving the Speed and Quality of Parallel Graph
Coloring",
journal = j-TOPC,
volume = "9",
number = "3",
pages = "10:1--10:35",
month = sep,
year = "2022",
CODEN = "????",
DOI = "https://doi.org/10.1145/3543545",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Sep 20 09:34:53 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3543545",
abstract = "Graph coloring assigns a color to each vertex of a
graph such that no two adjacent vertices get the same
color. It is a key building block in many applications.
In practice, solutions that require fewer distinct
colors and that can be computed faster are \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "10",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Nguyen:2022:DIC,
author = "Hung K. Nguyen and Xuan-Tu Tran",
title = "Design and Implementation of a Coarse-grained
Dynamically Reconfigurable Multimedia Accelerator",
journal = j-TOPC,
volume = "9",
number = "3",
pages = "11:1--11:23",
month = sep,
year = "2022",
CODEN = "????",
DOI = "https://doi.org/10.1145/3543544",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Sep 20 09:34:53 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3543544",
abstract = "This article proposes and implements a Coarse-grained
dynamically Reconfigurable Architecture, named
Reconfigurable Multimedia Accelerator (REMAC). REMAC
architecture is driven by the pipelined
multi-instruction-multi-data execution model for
exploiting \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "11",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Anju:2022:MID,
author = "M. A. Anju and Rupesh Nasre",
title = "Multi-Interval {DomLock}: Toward Improving Concurrency
in Hierarchies",
journal = j-TOPC,
volume = "9",
number = "3",
pages = "12:1--12:27",
month = sep,
year = "2022",
CODEN = "????",
DOI = "https://doi.org/10.1145/3543543",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Sep 20 09:34:53 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3543543",
abstract = "Locking has been a predominant technique depended upon
for achieving thread synchronization and ensuring
correctness in multi-threaded applications. It has been
established that the concurrent applications working
with hierarchical data witness \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "12",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Ji:2022:IPI,
author = "Yuede Ji and Hang Liu and Yang Hu and H. Howie Huang",
title = "{iSpan}: Parallel Identification of Strongly Connected
Components with Spanning Trees",
journal = j-TOPC,
volume = "9",
number = "3",
pages = "13:1--13:27",
month = sep,
year = "2022",
CODEN = "????",
DOI = "https://doi.org/10.1145/3543542",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Tue Sep 20 09:34:53 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3543542",
abstract = "Detecting strongly connected components (SCCs) in a
directed graph is crucial for understanding the
structure of graphs. Most real-world graphs have one
large SCC that contains the majority of the vertices as
well as many small SCCs whose sizes are \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "13",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Benoit:2022:CWY,
author = "Anne Benoit and Luca Perotin and Yves Robert and
Hongyang Sun",
title = "Checkpointing Workflows {\`a} la {Young\slash Daly} Is
Not Good Enough",
journal = j-TOPC,
volume = "9",
number = "4",
pages = "14:1--14:??",
month = dec,
year = "2022",
CODEN = "????",
DOI = "https://doi.org/10.1145/3548607",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Apr 5 10:44:10 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3548607",
abstract = "This article revisits checkpointing strategies when
workflows composed of multiple tasks execute on a
parallel platform. The objective is to minimize the
expectation of the total execution time. For a single
task, the Young\slash Daly formula provides the
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "14",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Albers:2022:OAR,
author = "Susanne Albers and Jens Quedenfeld",
title = "Optimal Algorithms for Right-sizing Data Centers",
journal = j-TOPC,
volume = "9",
number = "4",
pages = "15:1--15:??",
month = dec,
year = "2022",
CODEN = "????",
DOI = "https://doi.org/10.1145/3565513",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Apr 5 10:44:10 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3565513",
abstract = "Electricity cost is a dominant and rapidly growing
expense in data centers. Unfortunately, much of the
consumed energy is wasted, because servers are idle for
extended periods of time. We study a capacity
management problem that dynamically right-sizes a
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "15",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Kappes:2022:FRC,
author = "Giorgos Kappes and Stergios V. Anastasiadis",
title = "A Family of Relaxed Concurrent Queues for Low-Latency
Operations and Item Transfers",
journal = j-TOPC,
volume = "9",
number = "4",
pages = "16:1--16:??",
month = dec,
year = "2022",
CODEN = "????",
DOI = "https://doi.org/10.1145/3565514",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Apr 5 10:44:10 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3565514",
abstract = "The producer-consumer communication over shared memory
is a critical function of current scalable systems.
Queues that provide low latency and high throughput on
highly utilized systems can improve the overall
performance perceived by the end users. In \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "16",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Sundaram:2023:NOH,
author = "Prasannabalaji Sundaram and Aditi Sengupta and Vajjala
K. Suman and Tapan K. Sengupta",
title = "Non-overlapping High-accuracy Parallel Closure for
Compact Schemes: Application in Multiphysics and
Complex Geometry",
journal = j-TOPC,
volume = "10",
number = "1",
pages = "1:1--1:??",
month = mar,
year = "2023",
CODEN = "????",
DOI = "https://doi.org/10.1145/3580005",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Apr 5 10:44:11 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3580005",
abstract = "Compact schemes are often preferred in performing
scientific computing for their superior spectral
resolution. Error-free parallelization of a compact
scheme is a challenging task due to the requirement of
additional closures at the inter-processor \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "1",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Lockhart:2023:PAO,
author = "Shelby Lockhart and Amanda Bienz and William Gropp and
Luke Olson",
title = "Performance Analysis and Optimal Node-aware
Communication for Enlarged Conjugate Gradient Methods",
journal = j-TOPC,
volume = "10",
number = "1",
pages = "2:1--2:??",
month = mar,
year = "2023",
CODEN = "????",
DOI = "https://doi.org/10.1145/3580003",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Apr 5 10:44:11 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3580003",
abstract = "Krylov methods are a key way of solving large sparse
linear systems of equations but suffer from poor strong
scalability on distributed memory machines. This is due
to high synchronization costs from large numbers of
collective communication calls \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "2",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Munch:2023:EDM,
author = "Peter Munch and Timo Heister and Laura Prieto Saavedra
and Martin Kronbichler",
title = "Efficient Distributed Matrix-free Multigrid Methods on
Locally Refined Meshes for {FEM} Computations",
journal = j-TOPC,
volume = "10",
number = "1",
pages = "3:1--3:??",
month = mar,
year = "2023",
CODEN = "????",
DOI = "https://doi.org/10.1145/3580314",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Apr 5 10:44:11 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3580314",
abstract = "This work studies three multigrid variants for
matrix-free finite-element computations on locally
refined meshes: geometric local smoothing, geometric
global coarsening (both h -multigrid), and polynomial
global coarsening (a variant of p -multigrid). We
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "3",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Klein:2023:TGL,
author = "Christoph Klein and Robert Strzodka",
title = "{Tridigpu}: a {GPU} Library for Block Tridiagonal and
Banded Linear Equation Systems",
journal = j-TOPC,
volume = "10",
number = "1",
pages = "4:1--4:??",
month = mar,
year = "2023",
CODEN = "????",
DOI = "https://doi.org/10.1145/3580373",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Apr 5 10:44:11 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/pvm.bib;
https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3580373",
abstract = "In this article, we present a CUDA library with a C
API for solving block cyclic tridiagonal and banded
systems on one GPU. The library can process block
tridiagonal systems with block sizes from $ 1 \times 1
$ (scalar) to $ 4 \times 4 $ and banded systems with up
to four sub- and superdiagonals. For the
compute-intensive block size cases and cases with many
right-hand sides, we write out an explicit
factorization to memory; however, for the scalar case,
the fastest approach is to only output the coarse
system and recompute the factorization. Prominent
features of the library are (scaled) partial pivoting
for improved numeric stability; highest-performance
kernels, which completely utilize GPU memory bandwidth;
and support for multiple sparse or dense right-hand
side and solution vectors. The additional memory
consumption is only 5\% of the original tridiagonal
system, which enables the solution of systems up to GPU
memory size. The performance of the state-of-the-art
scalar tridiagonal solver of cuSPARSE is outperformed
by factor 5 for large problem sizes of $ 2^{25} $
unknowns, on a GeForce RTX 2080 Ti.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "4",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Lakhotia:2023:PPB,
author = "Kartik Lakhotia and Rajgopal Kannan and Viktor
Prasanna",
title = "Parallel Peeling of Bipartite Networks for
Hierarchical Dense Subgraph Discovery",
journal = j-TOPC,
volume = "10",
number = "2",
pages = "5:1--5:??",
month = jun,
year = "2023",
CODEN = "????",
DOI = "https://doi.org/10.1145/3583084",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Sep 29 08:18:36 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3583084",
abstract = "Wing and Tip decomposition are motif-based analytics
for bipartite graphs that construct a hierarchy of
butterfly (2,2-biclique) dense edge and vertex induced
subgraphs, respectively. They have applications in
several domains, including e-commerce, \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "5",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Zheng:2023:DGD,
author = "Weijian Zheng and Dali Wang and Fengguang Song",
title = "A Distributed-{GPU} Deep Reinforcement Learning System
for Solving Large Graph Optimization Problems",
journal = j-TOPC,
volume = "10",
number = "2",
pages = "6:1--6:??",
month = jun,
year = "2023",
CODEN = "????",
DOI = "https://doi.org/10.1145/3589188",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Sep 29 08:18:36 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3589188",
abstract = "Graph optimization problems (such as minimum vertex
cover, maximum cut, traveling salesman problems) appear
in many fields including social sciences, power
systems, chemistry, and bioinformatics. Recently, deep
reinforcement learning (DRL) has shown \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "6",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Brown:2023:PED,
author = "Andrew D. Brown and Jonathan R. Beaumont and David B.
Thomas and Julian C. Shillcock and Matthew F. Naylor
and Graeme M. Bragg and Mark L. Vousden and Simon W.
Moore and Shane T. Fleming",
title = "{POETS}: an Event-driven Approach to Dissipative
Particle Dynamics: Implementing a Massively
Compute-intensive Problem on a Novel Hard\slash
Software Architecture.",
journal = j-TOPC,
volume = "10",
number = "2",
pages = "7:1--7:??",
month = jun,
year = "2023",
CODEN = "????",
DOI = "https://doi.org/10.1145/3580372",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Sep 29 08:18:36 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3580372",
abstract = "HPC clusters have become ever more expensive, both in
terms of capital cost and energy consumption; some
estimates suggest that competitive installations at the
end of the next decade will require their own power
station. One way around this looming \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "7",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Aleeva:2023:IIP,
author = "Valentina Aleeva and Rifkhat Aleev",
title = "Investigation and Implementation of Parallelism
Resources of Numerical Algorithms",
journal = j-TOPC,
volume = "10",
number = "2",
pages = "8:1--8:??",
month = jun,
year = "2023",
CODEN = "????",
DOI = "https://doi.org/10.1145/3583755",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Sep 29 08:18:36 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3583755",
abstract = "This article is devoted to an approach to solving a
problem of the efficiency of parallel computing. The
theoretical basis of this approach is the concept of a
Q -determinant. Any numerical algorithm has a Q
-determinant. The Q -determinant of the algorithm
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "8",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Wang:2023:HPC,
author = "Haotian Wang and Wangdong Yang and Renqiu Ouyang and
Rong Hu and Kenli Li and Keqin Li",
title = "A Heterogeneous Parallel Computing Approach Optimizing
{SpTTM} on {CPU-GPU} via {GCN}",
journal = j-TOPC,
volume = "10",
number = "2",
pages = "9:1--9:??",
month = jun,
year = "2023",
CODEN = "????",
DOI = "https://doi.org/10.1145/3584373",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Sep 29 08:18:36 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3584373",
abstract = "Sparse Tensor-Times-Matrix (SpTTM) is the core
calculation in tensor analysis. The sparse
distributions of different tensors vary greatly, which
poses a big challenge to designing efficient and
general SpTTM. In this paper, we describe SpTTM on
CPU-GPU \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "9",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Miao:2023:PIT,
author = "Zheng Miao and Jon C. Calhoun and Rong Ge and Jiajia
Li",
title = "Performance Implication of Tensor Irregularity and
Optimization for Distributed Tensor Decomposition",
journal = j-TOPC,
volume = "10",
number = "2",
pages = "10:1--10:??",
month = jun,
year = "2023",
CODEN = "????",
DOI = "https://doi.org/10.1145/3580315",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Sep 29 08:18:36 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3580315",
abstract = "Tensors are used by a wide variety of applications to
represent multi-dimensional data; tensor decompositions
are a class of methods for latent data analytics, data
compression, and so on. Many of these applications
generate large tensors with irregular \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "10",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Hesselink:2023:MLS,
author = "Wim H. Hesselink and Peter A. Buhr",
title = "{MCSH}, a Lock with the Standard Interface",
journal = j-TOPC,
volume = "10",
number = "2",
pages = "11:1--11:??",
month = jun,
year = "2023",
CODEN = "????",
DOI = "https://doi.org/10.1145/3584696",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Sep 29 08:18:36 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3584696",
abstract = "The MCS lock of Mellor-Crummey and Scott (1991), 23
pages. is a very efficient first-come first-served
mutual-exclusion algorithm that uses the atomic
hardware primitives fetch-and-store and
compare-and-swap. However, it has the disadvantage that
the \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "11",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Zamani:2023:GEE,
author = "Hadi Zamani and Laxmi Bhuyan and Jieyang Chen and
Zizhong Chen",
title = "{GreenMD}: Energy-efficient Matrix Decomposition on
Heterogeneous Multi-{GPU} Systems",
journal = j-TOPC,
volume = "10",
number = "2",
pages = "12:1--12:??",
month = jun,
year = "2023",
CODEN = "????",
DOI = "https://doi.org/10.1145/3583590",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Sep 29 08:18:36 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3583590",
abstract = "The current trend of performance growth in HPC systems
is accompanied by a massive increase in energy
consumption. In this article, we introduce GreenMD, an
energy-efficient framework for heterogeneous systems
for LU factorization utilizing multi-GPUs. LU
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "12",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Kamenev:2023:FSA,
author = "Aleksandar Kamenev and Dariusz R. Kowalski and Miguel
A. Mosteiro",
title = "Faster Supervised Average Consensus in Adversarial and
Stochastic Anonymous Dynamic Networks",
journal = j-TOPC,
volume = "10",
number = "2",
pages = "13:1--13:??",
month = jun,
year = "2023",
CODEN = "????",
DOI = "https://doi.org/10.1145/3593426",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Sep 29 08:18:36 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3593426",
abstract = "How do we reach consensus on an average value in a
dynamic crowd without revealing identity? In this work,
we study the problem of average network consensus in
Anonymous Dynamic Networks (ADN). Network dynamicity is
specified by the sequence of topology-. \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "13",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Baruah:2023:CCF,
author = "Sanjoy Baruah and Alberto Marchetti-Spaccamela",
title = "The Computational Complexity of Feasibility Analysis
for Conditional {DAG} Tasks",
journal = j-TOPC,
volume = "10",
number = "3",
pages = "14:1--14:??",
month = sep,
year = "2023",
CODEN = "????",
DOI = "https://doi.org/10.1145/3606342",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Sep 29 08:18:37 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3606342",
abstract = "The Conditional DAG (CDAG) task model is used for
modeling multiprocessor real-time systems containing
conditional expressions for which outcomes are not
known prior to their evaluation. Feasibility analysis
for CDAG tasks upon multiprocessor platforms is
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "14",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Blanusa:2023:FPA,
author = "Jovan Blanusa and Kubilay Atasu and Paolo Ienne",
title = "Fast Parallel Algorithms for Enumeration of Simple,
Temporal, and Hop-constrained Cycles",
journal = j-TOPC,
volume = "10",
number = "3",
pages = "15:1--15:??",
month = sep,
year = "2023",
CODEN = "????",
DOI = "https://doi.org/10.1145/3611642",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Sep 29 08:18:37 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3611642",
abstract = "Cycles are one of the fundamental subgraph patterns
and being able to enumerate them in graphs enables
important applications in a wide variety of fields,
including finance, biology, chemistry, and network
science. However, to enable cycle enumeration in
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "15",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Alvermann:2023:OLP,
author = "Andreas Alvermann and Georg Hager and Holger Fehske",
title = "Orthogonal Layers of Parallelism in Large-Scale
Eigenvalue Computations",
journal = j-TOPC,
volume = "10",
number = "3",
pages = "16:1--16:??",
month = sep,
year = "2023",
CODEN = "????",
DOI = "https://doi.org/10.1145/3614444",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Sep 29 08:18:37 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3614444",
abstract = "We address the communication overhead of distributed
sparse matrix-(multiple)-vector multiplication in the
context of large-scale eigensolvers, using filter
diagonalization as an example. The basis of our study
is a performance model, which includes a communication
metric that is computed directly from the matrix
sparsity pattern without running any code. The
performance model quantifies to which extent
scalability and parallel efficiency are lost due to
communication overhead.\par
To restore scalability, we identify two orthogonal
layers of parallelism in the filter diagonalization
technique. In the horizontal layer the rows of the
sparse matrix are distributed across individual
processes. In the vertical layer bundles of multiple
vectors are distributed across separate process groups.
An analysis in terms of the communication metric
predicts that scalability can be restored if, and only
if, one implements the two orthogonal layers of
parallelism via different distributed vector
layouts.\par
Our theoretical analysis is corroborated by benchmarks
for application matrices from quantum and solid state
physics, road networks, and nonlinear programming. We
finally demonstrate the benefits of using orthogonal
layers of parallelism with two exemplary application
cases --- an exciton and a strongly correlated electron
system --- which incur either small or large
communication overhead.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "16",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Azar:2023:ISI,
author = "Yossi Azar and Julian Shun",
title = "Introduction to the Special Issue for {SPAA'21}",
journal = j-TOPC,
volume = "10",
number = "4",
pages = "17:1--17:??",
month = dec,
year = "2023",
CODEN = "????",
DOI = "https://doi.org/10.1145/3630608",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Thu Dec 21 10:57:17 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3630608",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "17",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Anderson:2023:PMC,
author = "Daniel Anderson and Guy E. Blelloch",
title = "Parallel Minimum Cuts in {$ O(m \log_2 n) $} Work and
Low Depth",
journal = j-TOPC,
volume = "10",
number = "4",
pages = "18:1--18:??",
month = dec,
year = "2023",
CODEN = "????",
DOI = "https://doi.org/10.1145/3565557",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Thu Dec 21 10:57:17 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3565557",
abstract = "We present a randomized $ O(m \log^2 n) $ work, $
O(\polylog n) $ depth parallel algorithm for minimum
cut. This algorithm matches the work bounds of a recent
sequential algorithm by Gawrychowski, Mozes, and
Weimann [ICALP'20], and improves on the previously best
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "18",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Im:2023:NCS,
author = "Sungjin Im and Ravi Kumar and Mahshid Montazer Qaem
and Manish Purohit",
title = "Non-clairvoyant Scheduling with Predictions",
journal = j-TOPC,
volume = "10",
number = "4",
pages = "19:1--19:??",
month = dec,
year = "2023",
CODEN = "????",
DOI = "https://doi.org/10.1145/3593969",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Thu Dec 21 10:57:17 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3593969",
abstract = "In the single-machine non-clairvoyant scheduling
problem, the goal is to minimize the total completion
time of jobs whose processing times are unknown a
priori. We revisit this well-studied problem and
consider the question of how to effectively use (.
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "19",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Albers:2023:ARS,
author = "Susanne Albers and Jens Quedenfeld",
title = "Algorithms for Right-sizing Heterogeneous Data
Centers",
journal = j-TOPC,
volume = "10",
number = "4",
pages = "20:1--20:??",
month = dec,
year = "2023",
CODEN = "????",
DOI = "https://doi.org/10.1145/3595286",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Thu Dec 21 10:57:17 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3595286",
abstract = "Power consumption is a dominant and still growing cost
factor in data centers. In time periods with low load,
the energy consumption can be reduced by powering down
unused servers. We resort to a model introduced by Lin,
Wierman, Andrew, and Thereska [23, \ldots{}]",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "20",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Maus:2023:DGC,
author = "Yannic Maus",
title = "Distributed Graph Coloring Made Easy",
journal = j-TOPC,
volume = "10",
number = "4",
pages = "21:1--21:??",
month = dec,
year = "2023",
CODEN = "????",
DOI = "https://doi.org/10.1145/3605896",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Thu Dec 21 10:57:17 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3605896",
abstract = "In this article, we present a deterministic $ \mathsf
{CONGEST} $ algorithm to compute an $ O(k
\Delta)$-vertex coloring in $ O(\Delta / k) + \log^* n$
rounds, where $ \Delta $ is the maximum degree of the
network graph and $ k \geq 1$ can be freely chosen. The
algorithm is extremely simple: \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "21",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Ahmad:2023:FAA,
author = "Zafar Ahmad and Rezaul Chowdhury and Rathish Das and
Pramod Ganapathi and Aaron Gregory and Yimin Zhu",
title = "A Fast Algorithm for Aperiodic Linear Stencil
Computation using {Fast Fourier Transforms}",
journal = j-TOPC,
volume = "10",
number = "4",
pages = "22:1--22:??",
month = dec,
year = "2023",
CODEN = "????",
DOI = "https://doi.org/10.1145/3606338",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Thu Dec 21 10:57:17 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3606338",
abstract = "Stencil computations are widely used to simulate the
change of state of physical systems across a
multidimensional grid over multiple timesteps. The
state-of-the-art techniques in this area fall into
three groups: cache-aware tiled looping algorithms,
cache-oblivious divide-and-conquer trapezoidal
algorithms, and Krylov subspace methods.
In this article, we present two efficient parallel
algorithms for performing linear stencil computations.
Current direct solvers in this domain are
computationally inefficient, and Krylov methods require
manual labor and mathematical training. We solve these
problems for linear stencils by using discrete Fourier
transforms preconditioning on a Krylov method to
achieve a direct solver that is both fast and general.
Indeed, while all currently available algorithms for
solving general linear stencils perform (NT) work,
where N is the size of the spatial grid and T is the
number of timesteps, our algorithms perform o(NT)
work.
To the best of our knowledge, we give the first
algorithms that use fast Fourier transforms to compute
final grid data by evolving the initial data for many
timesteps at once. Our algorithms handle both periodic
and aperiodic boundary conditions and achieve
polynomially better performance bounds (i.e.,
computational complexity and parallel runtime) than all
other existing solutions. Initial experimental results
show that implementations of our algorithms that evolve
grids of roughly 107 cells for around 105 timesteps run
orders of magnitude faster than state-of-the-art
implementations for periodic stencil problems, and $
1.3 \times $ to $ 8.5 \times $ faster for aperiodic
stencil problems.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "22",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Benoit:2024:CST,
author = "Anne Benoit and Lucas Perotin and Yves Robert and
Fr{\'e}d{\'e}ric Vivien",
title = "Checkpointing Strategies to Tolerate Non-Memoryless
Failures on {HPC} Platforms",
journal = j-TOPC,
volume = "11",
number = "1",
pages = "1:1--1:??",
month = mar,
year = "2024",
CODEN = "????",
DOI = "https://doi.org/10.1145/3624560",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Mar 13 07:22:23 MDT 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3624560",
abstract = "This article studies checkpointing strategies for
parallel applications subject to failures. The optimal
strategy to minimize total execution time, or makespan,
is well known when failure IATs obey an Exponential
distribution, but it is unknown for non-. \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "1",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Perotin:2024:IOS,
author = "Lucas Perotin and Hongyang Sun",
title = "Improved Online Scheduling of Moldable Task Graphs
under Common Speedup Models",
journal = j-TOPC,
volume = "11",
number = "1",
pages = "2:1--2:??",
month = mar,
year = "2024",
CODEN = "????",
DOI = "https://doi.org/10.1145/3630052",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Mar 13 07:22:23 MDT 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3630052",
abstract = "We consider the online scheduling problem of moldable
task graphs on multiprocessor systems for minimizing
the overall completion time (or makespan). Moldable job
scheduling has been widely studied in the literature,
in particular when tasks have \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "2",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Lin:2024:HCH,
author = "Shengle Lin and Wangdong Yang and Yikun Hu and Qinyun
Cai and Minlu Dai and Haotian Wang and Kenli Li",
title = "{HPS Cholesky}: Hierarchical Parallelized Supernodal
{Cholesky} with Adaptive Parameters",
journal = j-TOPC,
volume = "11",
number = "1",
pages = "3:1--3:??",
month = mar,
year = "2024",
CODEN = "????",
DOI = "https://doi.org/10.1145/3630051",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Mar 13 07:22:23 MDT 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3630051",
abstract = "Sparse supernodal Cholesky on multi-NUMAs is
challenging due to the supernode relaxation and load
balancing. In this work, we propose a novel approach to
improve the performance of sparse Cholesky by combining
deep learning with a relaxation parameter and
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "3",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Marotta:2024:CRL,
author = "Romolo Marotta and Mauro Ianni and Alessandro
Pellegrini and Francesco Quaglia",
title = "A Conflict-Resilient Lock-Free Linearizable Calendar
Queue",
journal = j-TOPC,
volume = "11",
number = "1",
pages = "4:1--4:??",
month = mar,
year = "2024",
CODEN = "????",
DOI = "https://doi.org/10.1145/3635163",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Mar 13 07:22:23 MDT 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3635163",
abstract = "In the last two decades, great attention has been
devoted to the design of non-blocking and linearizable
data structures, which enable exploiting the scaled-up
degree of parallelism in off-the-shelf shared-memory
multi-core machines. In this context, \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "4",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Muller:2024:MAE,
author = "Stefan K. Muller and Jan Hoffmann",
title = "Modeling and Analyzing Evaluation Cost of {CUDA}
Kernels",
journal = j-TOPC,
volume = "11",
number = "1",
pages = "5:1--5:??",
month = mar,
year = "2024",
CODEN = "????",
DOI = "https://doi.org/10.1145/3639403",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Mar 13 07:22:23 MDT 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3639403",
abstract = "Motivated by the increasing importance of
general-purpose Graphic Processing Units (GPGPU)
programming, exemplified by NVIDIA's CUDA framework, as
well as the difficulty, especially for novice
programmers, of reasoning about performance in GPGPU
kernels, \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "5",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Cai:2024:AAB,
author = "Qinyun Cai and Guoqing Xiao and Shengle Lin and
Wangdong Yang and Keqin Li and Kenli Li",
title = "{ABSS}: an Adaptive Batch-Stream Scheduling Module for
Dynamic Task Parallelism on Chiplet-based Multi-Chip
Systems",
journal = j-TOPC,
volume = "11",
number = "1",
pages = "6:1--6:??",
month = mar,
year = "2024",
CODEN = "????",
DOI = "https://doi.org/10.1145/3643597",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Wed Mar 13 07:22:23 MDT 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3643597",
abstract = "Thanks to the recognition and promotion of
chiplet-based High-Performance Computing (HPC) system
design technology by semiconductor industry/market
leaders, chiplet-based multi-chip systems have
gradually become the mainstream. Unfortunately,
programming \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "6",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Fu:2024:TLT,
author = "Qiang Fu and Yuede Ji and Thomas Rolinger and H. Howie
Huang",
title = "{TLPGNN}: a Lightweight Two-level Parallelism Paradigm
for Graph Neural Network Computation on Single and
Multiple {GPUs}",
journal = j-TOPC,
volume = "11",
number = "2",
pages = "7:1--7:??",
month = jun,
year = "2024",
CODEN = "????",
DOI = "https://doi.org/10.1145/3644712",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Thu Jun 13 07:45:59 MDT 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3644712",
abstract = "Graph Neural Networks (GNNs) are an emerging class of
deep learning models specifically designed for
graph-structured data. They have been effectively
employed in a variety of real-world applications,
including recommendation systems, drug development,
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "7",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Li:2024:CSO,
author = "Zixuan Li and Yunchuan Qin and Qi Xiao and Wangdong
Yang and Kenli Li",
title = "{cuFasterTucker}: a Stochastic Optimization Strategy
for Parallel Sparse {FastTucker} Decomposition on {GPU}
Platform",
journal = j-TOPC,
volume = "11",
number = "2",
pages = "8:1--8:??",
month = jun,
year = "2024",
CODEN = "????",
DOI = "https://doi.org/10.1145/3648094",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Thu Jun 13 07:45:59 MDT 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3648094",
abstract = "The amount of scientific data is currently growing at
an unprecedented pace, with tensors being a common form
of data that display high-order, high-dimensional, and
sparse features. While tensor-based analysis methods
are effective, the vast increase in \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "8",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Darche:2024:LOT,
author = "S{\'e}bastien Darche and Michel R. Dagenais",
title = "Low-Overhead Trace Collection and Profiling on {GPU}
Compute Kernels",
journal = j-TOPC,
volume = "11",
number = "2",
pages = "9:1--9:??",
month = jun,
year = "2024",
CODEN = "????",
DOI = "https://doi.org/10.1145/3649510",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Thu Jun 13 07:45:59 MDT 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3649510",
abstract = "While GPUs can bring substantial speedup to
compute-intensive tasks, their programming is
notoriously hard. From their programming model, to
microarchitectural particularities, the programmer may
encounter many pitfalls which may hinder performance in
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "9",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Li:2024:DSD,
author = "Ziyang Li and Dongsheng Li and Yingwen Chen and Kai
Chen and Yiming Zhang",
title = "Decentralized Scheduling for Data-Parallel Tasks in
the Cloud",
journal = j-TOPC,
volume = "11",
number = "2",
pages = "10:1--10:??",
month = jun,
year = "2024",
CODEN = "????",
DOI = "https://doi.org/10.1145/3651858",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Thu Jun 13 07:45:59 MDT 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3651858",
abstract = "For latency-sensitive data processing applications in
the cloud, concurrent data-parallel tasks need to be
scheduled and processed quickly. A data-parallel task
usually consists of a set of sub-tasks, generating a
set of flows that are collectively \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "10",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Xiao:2024:MLB,
author = "Guoqing Xiao and Tao Zhou and Yuedan Chen and Yikun Hu
and Kenli Li",
title = "Machine Learning-Based Kernel Selector for {SpMV}
Optimization in Graph Analysis",
journal = j-TOPC,
volume = "11",
number = "2",
pages = "11:1--11:??",
month = jun,
year = "2024",
CODEN = "????",
DOI = "https://doi.org/10.1145/3652579",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Thu Jun 13 07:45:59 MDT 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3652579",
abstract = "Sparse Matrix and Vector multiplication (SpMV) is one
of the core algorithms in various large-scale
scientific computing and real-world applications. With
the rapid development of AI and big data, the input
vector in SpMV becomes sparse in many \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "11",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Li:2024:CNS,
author = "Zixuan Li and Yikun Hu and Mengquan Li and Wangdong
Yang and Kenli Li",
title = "{cuFastTucker}: a Novel Sparse {FastTucker}
Decomposition For {HHLST} on Multi-{GPUs}",
journal = j-TOPC,
volume = "11",
number = "2",
pages = "12:1--12:??",
month = jun,
year = "2024",
CODEN = "????",
DOI = "https://doi.org/10.1145/3661450",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Thu Jun 13 07:45:59 MDT 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3661450",
abstract = "High-order, high-dimension, and large-scale sparse
tensors (HHLST) have found their origin in various real
industrial applications, such as social networks,
recommender systems, bioinformatics, and traffic
information. To handle these complex tensors,
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "12",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Liu:2024:IPG,
author = "Yiqian Liu and Noushin Azami and Avery Vanausdal and
Martin Burtscher",
title = "{Indigo3}: a Parallel Graph Analytics Benchmark Suite
for Exploring Implementation Styles and Common Bugs",
journal = j-TOPC,
volume = "11",
number = "3",
pages = "13:1--13:??",
month = sep,
year = "2024",
CODEN = "????",
DOI = "https://doi.org/10.1145/3665251",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Sep 13 13:52:04 MDT 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3665251",
abstract = "Graph analytics codes are widely used and tend to
exhibit input-dependent behavior, making them
particularly interesting for software verification and
validation. This article presents Indigo3, a labeled
benchmark suite based on 7 graph algorithms that
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "13",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Bontes:2024:RSC,
author = "Johan Bontes and James Gain",
title = "Redzone stream compaction: removing $k$ items from a
list in parallel {$ O(k) $} time",
journal = j-TOPC,
volume = "11",
number = "3",
pages = "14:1--14:??",
month = sep,
year = "2024",
CODEN = "????",
DOI = "https://doi.org/10.1145/3675782",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Fri Sep 13 13:52:04 MDT 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3675782",
abstract = "Stream compaction, the parallel removal of selected
items from a list, is a fundamental building block in
parallel algorithms. It is extensively used, both in
computer graphics, for shading, collision detection,
and ray tracing, as well as in general \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "14",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Cui:2024:ATP,
author = "Cu Cui",
title = "Acceleration of Tensor-Product Operations with Tensor
Cores",
journal = j-TOPC,
volume = "11",
number = "4",
pages = "15:1--15:??",
month = dec,
year = "2024",
CODEN = "????",
DOI = "https://doi.org/10.1145/3695466",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Mon Nov 18 14:38:19 MST 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3695466",
abstract = "In this article, we explore the acceleration of tensor
product operations in finite element methods,
leveraging the computational power of the NVIDIA A100
GPU Tensor Cores. We provide an accessible overview of
the necessary mathematical background and discuss our
implementation strategies. Our study focuses on two
common programming approaches for NVIDIA Tensor Cores:
the C++ Warp Matrix Functions in nvcuda::wmma and the
inline Parallel Thread Execution (PTX) instructions
mma.sync.aligned. A significant focus is placed on the
adoption of the versatile inline PTX instructions
combined with a conflict-free shared memory access
pattern, a key to unlocking superior performance. When
benchmarked against traditional CUDA Cores, our
approach yields a remarkable 2.3-fold increase in
double-precision performance, achieving 8 TFLOPS/s ---
45% of the theoretical maximum. Furthermore, in
half-precision computations, numerical experiments
demonstrate a fourfold enhancement in solving the
Poisson equation using the flexible GMRES (FGMRES)
method, preconditioned by a multigrid method in 3D.
This is achieved while maintaining the same
discretization error as observed in double-precision
computations. These results highlight the considerable
benefits of using Tensor Cores for finite element
operators with tensor products, achieving an optimal
balance between computational speed and precision.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "15",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Hesselink:2024:FCF,
author = "Wim A. Hesselink and Peter A. Buhr and Colby A.
Parsons",
title = "First-Come-First-Served as a Separate Principle",
journal = j-TOPC,
volume = "11",
number = "4",
pages = "16:1--16:??",
month = dec,
year = "2024",
CODEN = "????",
DOI = "https://doi.org/10.1145/3669989",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Mon Nov 18 14:38:19 MST 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3669989",
abstract = "A lock is a mechanism to guarantee mutual exclusion
with eventual progress, i.e., some degree of fairness.
First-come-first-served (FCFS) progress is perfectly
fair. FCFS progress can be offered by a locking
algorithm or added by wrapping a non-FCFS lock
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "16",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Pahlke:2024:PDM,
author = "Johannes Pahlke and Ivo F. Sbalzarini",
title = "Proven Distributed Memory Parallelization of Particle
Methods",
journal = j-TOPC,
volume = "11",
number = "4",
pages = "17:1--17:??",
month = dec,
year = "2024",
CODEN = "????",
DOI = "https://doi.org/10.1145/3696189",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Mon Nov 18 14:38:19 MST 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3696189",
abstract = "We provide a mathematically proven parallelization
scheme for particle methods on distributed-memory
computer systems. Particle methods are a versatile and
widely used class of algorithms for computer
simulations and numerical predictions in various
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "17",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
@Article{Tepiele:2024:DPB,
author = "Hermann Bogning Tepiele and Vianney Kengne Tchendji
and Mathias Akong Onabid and Jean Fr{\'e}d{\'e}ric
Myoupo and Armel Nkonjoh Ngomade",
title = "Dominant Point-Based Sequential and Parallel
Algorithms for the Multiple Sequential Substring
Constrained-{LCS} Problem",
journal = j-TOPC,
volume = "11",
number = "4",
pages = "18:1--18:??",
month = dec,
year = "2024",
CODEN = "????",
DOI = "https://doi.org/10.1145/3696657",
ISSN = "2329-4949 (print), 2329-4957 (electronic)",
ISSN-L = "2329-4949",
bibdate = "Mon Nov 18 14:38:19 MST 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/topc.bib",
URL = "https://dl.acm.org/doi/10.1145/3696657",
abstract = "The Longest Common Subsequence (LCS) problem is a
well-known and studied problem in computer science and
bioinformatics. It consists in finding the longest
subsequence that is common to two or more given
sequences. In this article, we address the problem
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Parallel Comput.",
articleno = "18",
fjournal = "ACM Transactions on Parallel Computing",
journal-URL = "https://dl.acm.org/loi/topc",
}
