\noindent
{\bf
CONVEX C-120/130 and C-210/220/230/240
}
\vspace{.1in}
\noindent
{\bf
Vector Register, Parallel Processor, Bus-Based Architecture
}
\vspace{.1in}
\noindent
{\bf Architecture:}
The C-2, which was available from January 1988, is a multiple-processor
bus-connected, shared-memory computer. Each CPU is similar to
(but a new design) the single CPUs of the C-1 computers.
\vspace{.1in}
\noindent
The CPUs consist of a scalar and address unit (based on ECL 7K and
10K density chips) and a vector processor (using CMOS VLSI 20K
gates/chip). The vector architecture is register-to-register with three
asynchronous pipelined functions (load, store, and edit; add, subtract;
multiply, add, divide, and square root). Each CPU has 8
vector registers, each with 128 elements (64-bit elements).
VL and VS registers are also present.
The scalar unit performs integer
arithmetic and floating-point multiplies, adds, divisions, and square
roots in hardware. There is a 64 Kbyte cache for the scalar unit with
cache bypass for the vector unit. The cycle time is 40 nsec for the C-2
(100 nsec for the C-1).
Scalar and vector units (fixed and float) can operate concurrently.
\vspace{.1in}
\noindent
The C-2 has new microcode instructions for vector square root,
mask operations, type conversions, intrinsic functions, and random
memory access.
\vspace{.1in}
\noindent
Real memory is up to 4 Gbytes (1 Gbyte for the C-1) of DRAM.
The early C-1 memories were in 256 Kbit DRAMs, but the later memories
and those of the C-2 use 1 Mbit DRAM.
Virtual address space is 4
Gbytes (page size 4 Kbytes) with 2 Gbytes available per user. Memory is
64-way interleaved (32 bit) or 32 way (64 bit).
\vspace{.1in}
\noindent
Transfer rates between memory and CPU on the C-1 are
rated at 80 Mbytes/sec.
There is a single memory pipe between
memory and registers.
\vspace{.1in}
\noindent
On the C-2, the access between
each CPU and the memory is via a non-contentious, non-blocking 5-bus
crossbar using ECL chips, with each bus rated at 200 Mbytes/sec.
\vspace{.1in}
\noindent
The arithmetic is in
floating-point IEEE standard format.
Byte-addressable with integer*1, integer*2, integer*4,
integer*8,
complex*8, and complex*16 supported.
\vspace{.1in}
\noindent
There is a
1/2 Mbyte IOP buffer. The IOP is 68000
based with event-driven monitor
and I/O transfer rates of 80 Mbytes/sec on custom application boards,
or standard Multibus at 8 Mbytes/sec, or VME bus at
16 Mbytes/sec.
\vspace{.1in}
\noindent
{\bf Configuration:}
All machines are stand-alone, multi-user, interactive
machines. They can be
interfaced to most standard communication channels including Ethernet
(TCP/IP), DECnet, and Hyperchannel.
Pink book and color books over LAN and NFS are
also available. X25 color book will be available shortly. Batch job
submission from VAX to C-2 possible with output files and results
returned to VAX.
\vspace{.1in}
\noindent
{\bf Software:}
UNIX 4.2 BSD and COVUE shell offer emulation of most common VMS
commands.
\vspace{.1in}
\noindent
{\bf Languages available:}
Parallel Fortran, C, vectorized Ada, common Lisp, Prolog
\vspace{.1in}
\noindent
{\bf Fortran characteristics:}
Fortran 77 with VAX extensions and
excellent Fortran vectorizing compiler.
C compiler (VC) automatically vectorizes scalar code.
HCR/PASCAL and HCR/UX-BASIC are available as third party compilers.
\vspace{.1in}
\noindent
{\bf Applications:}
There is a very extensive range of application software. General-purpose
packages include NAG, IMSL, ABAQUS, MSC, NASTRAN, ANSYS, DI-3000, DISPLA,
GKSGral, UNIRAS, TELEGRAF, Q-Calc, Sir, and Oracle.
\vspace{.1in}
\noindent
{\bf Performance:}
Peak performance for the C-120 is 20 Mflops in double precision
(64-bit arithmetic) and 40 Mflops in single precision (32-bit
arithmetic). LINPACK timings are 3.7 Mflops (100 x 100 matrix with
unmodified code).
\vspace{.1in}
\noindent
Peak scalar performance of C-210 is 22 Whetstone mips
at 32 bit and 14 Whetstone mips at 64 bit
(with in-line
subroutine expansion).
Peak vector performance is 50 Mflops.
LINPACK benchmark runs at 10.0 Mflops (again for unmodified code on 100
x 100 case).
\vspace{.1in}
\noindent
The following two tables compare the C-210 performance in Mflops
of a single processor with the
C-120. The first table compares the performances for
the algorithm $a_{i} = b_{i} * k $
\vspace{.1in}
\begin{center}
\begin{tabular}{l r r}
& 64 bit & 32 bit \\ \hline
C-120 & 6.6 & 13.3 \\
C-210 & 16.3 & 25.0
\end{tabular}
\end{center}
\vspace{.1in}
\vspace{.1in}
\noindent
The second table shows a comparison for
an indirect vector addressing algorithm of the form
$ a_{x_{i}} =a_{x_{i}} * b_{x_{i}} * k $
\vspace{.1in}
\begin{center}
\begin{tabular}{l r r}
& 64 bit & 32 bit \\
\hline
C-120 & 3.6 & 3.5 \\
C-210 & 12.5 & 16.7
\end{tabular}
\end{center}
\vspace{.1in}
\vspace{.1in}
\noindent
The C-210, used in these benchmarks,
is the single processor version of the C-2 computer. The
multiple processor C-220, C-230, and C-240 versions are available and
are all field upgradable from the C-210.
\vspace{.1in}
\noindent
Basic C-120 system: two 19-in. racks and 32 Mbytes memory, 1 I/O
processor, service processor, 434 Mbyte Winchester, 6250 bpi tape
drive.
\vspace{.1in}
\noindent
Size: 25 x 62 x 40 inches for each cabinet. Base
system requires two cabinets, each about 500 lb. Forced air
cooling. Power consumption 3200-4500 Watts
\vspace{.1in}
\noindent
A 2 CPU C-220 system consumes 12 KW.
\vspace{.1in}
\noindent
{\bf Status:}
C-120 base system lists at about \$250K
but generous academic discounts available. The C-210 will be
about twice as much as a C-120 but trade-in possible. Trade-in value
calculated by
CPU * (1 - M/36) where CPU is initial
cost of C-120 processor and M is its age in months. The F77
compiler costs \$25K, as does the C compiler with
GPROFF, PROF, and BPROF run-time profilers.
A source level debugger and a range of editors, including VAX EDT
emulation, are available.
\vspace{.1in}
\noindent
CONVEX has sold 380 systems (280 C-1, 100 C-2) worldwide since 1985.
\vspace{.1in}
\noindent
Contact:
\begin{flushleft}
CONVEX Computer Corporation\\
701 N. Plano Road\\
Richardson, Texas 75081\\
214-952-0200\\
FAX 214-952-0550
uucp convex!wallach
\vspace {.1in}
Technical: Steve Wallach\\
Sales: Adrian Wise\\
\vspace {.1in}
A.S. Nutt\\
CONVEX Computer Limited\\
Hays Wharf\\
Millmead\\
Guildford GU2 5BE\\
England\\
0483-69000 Telex 858136 Fax 0483-36775
\end{flushleft}