BTIO Although parallel file systems support similar interfaces, the lack of a standard makes developing a truly portable program impossible. Working together, IBM T.J. Watson Research Center and the Parallel Systems Group at the NAS facility (NASA Ames Research Center) have drafted MPI-IO, a proposal to address the portable parallel I/O problem. BTIO is the NAS Application benchmark for MPI-IO.
Cachebench This is version 1.1 of a program to empirically determine some parameters about an architectures memory subsystem. Portions of it may be used an upcoming benchmark suite like ParkBench.
Dhrystone Benchmarks Short synthetic benchmark program intended to be representative for system (integer) programming.
EXPAR Experimental Parallel Algorithmics at UMIACS
Fhourstone Benchmarks Small integer-only program that solves positions in the game of connect-4 using exhaustive search with a very large transposition table.
Flops Benchmarks Estimates MFLOPS rating for specific FADD, FSUB, FMUL, and FDIV instruction mixes.
The FIRE Benchmarks FIRE is a general purpose software package developed specifically for computing compressible , incompressible turbulent
(laminar) or (non-) reacting fluid flows in complex 3D geometries with highly transient boundary conditions.
GAMESS The General Atomic and Molecular Electronic Structure System (GAMESS) is a general ab initio quantum chemistry package.
The Genesis Benchmarking SuiteThe GENESIS distributed-memory benchmark suite was assembled to fulfill a need forevaluating the performance of distributed memory MIMD systems on scientific and engineering applications.
The Micro Benchmark Small benchmarks which measures a particular aspect of shared memory machines under controlled conditions
MPBench This is version 3 of a program to measure the performance of some critical PVM and now MPI functions. By critical we mean that the behavior of these functions can dominate the run time of a distributed application. This program generates data points to be fed to a graphing tool like GNUplot. In version 2, the graphs for broadcast and reduce were 3D surface plots, while the rest are 2D.
NAS Parallel Benchmarks The NAS Parallel Benchmarks (NPB) are a set of 8 programs designed to help evaluate the performance of parallel supercomputers. The benchmarks, which are derived from computational fluid dynamics (CFD) applications, consist of five kernels and three pseudo-applications.
Parallel Community Climate Model for Scalable Message Passing Systems (PCCM2)PCCM2.1 is a parallel version of the NCAR Community Climate Model, CCM2, implemented for MIMD massively parallel computers using a message-passing programming paradigm. Click here for the User's Guide for PCCM2(in Postscript)
Performance Evaluation and Benchmarking Projects at CSRD Perfect Benchmarks: A suite of scientific and engineering programs that are representative of applications run on high-performance computers has been collected in a joint effort of several US research and development orgainizations.
Phil's Parkbench Bits This site contains some experimental software related to the ParkBench suite of
benchmarks for parallel computers.
PSTSWM PSTSWM Version 4.0 is a message-passing benchmark code and parallel algorithm testbed that solves the nonlinear shallow water equations on a rotating sphere using the spectral transform method. Click here for the log form to download the User's Guide for PSTSWM 4.0 (in Postscript)
The Scalable I/O Initiative The Scalable I/O Initiative, a project of the Concurrent Supercomputing Consortium, systematically investigates a primary obstacle to effective use of current gigaFLOPS-scale and future teraFLOPS-scale computing systems: getting data into, around, and out of the system.
Sim Benchmarks An integer program that compares DNA segments for similarity.
SKaMPI Benchmark Measures many MPI operations. Useful for tuning and predicting performance of MPI programs.
SPEC (Standard Performance Evaluation Corporation) SPEC was formed in 1988 to establish, maintain, and endorse a standardized set of relevant benchmarks and metrics for performance evaluation of modern computer systems. SPEC95 Benchmarks are posted here.
SPEC (Standard Performance Evaluation Corporation) at PDS SPEC was formed in 1988 to establish, maintain, and endorse a standardized set of relevantbenchmarks and metrics for performance evaluation of modern computer systems. CINT92,CFP92,SFS1,SDM1 Benchmarks are posted here.
Sphinx Parallel microbenchmark suite that measures performance of MPI and Pthreads
implementations.
STREAM Measuring Sustainable Memory Bandwidth in High Performance Computers
TFFTdp Benchmarks This program performs FFT's using the Duhamel-Hollman method for FFT's from 32 to 262,144 points in size.
Top 500 Supercomputer Sites at Manheim University and Netlib To provide a better basis for statistics on high-performance computers, Netlib lists the sites that have the 500 most powerful computer systems installed. The best Linpack benchmark performance
achieved is used as a performance measure in ranking the computers.
