Dear Mr. McCalpin:
Here are some results for your STREAM benchmark for the following
configuration:
Acer Vi15G motherboard
Cyrix 486DX-50 CPU
SiS 471 chipset
256 KB L2-cache, SRAM 15ns
8 MB DRAM, 60ns
I used an executable generated from the C version (see below) with the WATCOM
C compiler v. 10.0 at highest optimization, which has been provided as a ready
to run executable on the Internet. Unfortuntely, the execution times are too
small according to the calibration output. However, I do not have the WATCOM C
compiler here, so I unfortunately can not recompile the code. Hope this is
interesting anyhow. Find below the output from four runs of your benchmark.
-- Norbert Juffa (norbert@iit.com)
/*
* Program: Stream
* Programmer: John D. McCalpin
* Revision: 2.0, September 30,1991
*
* This program measures memory transfer rates in MB/s for simple
* computational kernels coded in Fortran. These numbers reveal the
* quality of code generation for simple uncacheable kernels as well
* as showing the cost of floating-point operations relative to memory
* accesses.
*
* INSTRUCTIONS:
* 1) (fortran-specific, omitted.)
* 2) Stream requires a good bit of memory to run.
* Adjust the Parameter 'N' in the second line of the main
* program to give a 'timing calibration' of at least 20 clicks.
* This will provide rate estimates that should be good to
* about 5% precision.
* 3) Compile the code with full optimization. Many compilers
* generate unreasonably bad code before the optimizer tightens
* things up. If the results are unreasonable good, on the
* other hand, the optimizer might be too smart for me!
* 4) Mail the results to mccalpin@perelandra.cms.udel.edu
* Be sure to include:
* a) computer hardware model number and software revision
* b) the compiler flags
* c) all of the output from the test case.
*
* Thanks!
*
* This version was ported from the fortran by Mark Hahn, hahn+@pitt.edu.
* The code is also available for anon ftp from
* neurocog.lrdc.pitt.edu:pub/cstream.c
*/
Timing calibration ; time = 160.00 usec.
Increase the size of the arrays if this is < 300
and your clock precision is =< 1/100 second.
---------------------------------------------------
Function Rate (MB/s) RMS time Min time Max time
Assignment: 38.130 124.338 110.000 170.000
Scaling : 26.214 214.756 160.000 220.000
Summing : 28.598 239.583 220.000 280.000
SAXPYing : 23.302 301.496 270.000 330.000
Timing calibration ; time = 170.00 usec.
Increase the size of the arrays if this is < 300
and your clock precision is =< 1/100 second.
---------------------------------------------------
Function Rate (MB/s) RMS time Min time Max time
Assignment: 38.130 123.004 110.000 170.000
Scaling : 26.214 210.167 160.000 220.000
Summing : 28.598 249.600 220.000 280.000
SAXPYing : 23.302 296.395 270.000 330.000
Timing calibration ; time = 160.00 usec.
Increase the size of the arrays if this is < 300
and your clock precision is =< 1/100 second.
---------------------------------------------------
Function Rate (MB/s) RMS time Min time Max time
Assignment: 38.130 129.653 110.000 170.000
Scaling : 26.214 210.167 160.000 220.000
Summing : 29.959 246.516 210.000 280.000
SAXPYing : 23.302 294.024 270.000 330.000
Timing calibration ; time = 160.00 usec.
Increase the size of the arrays if this is < 300
and your clock precision is =< 1/100 second.
---------------------------------------------------
Function Rate (MB/s) RMS time Min time Max time
Assignment: 38.130 123.004 110.000 170.000
Scaling : 26.214 210.167 160.000 220.000
Summing : 28.598 248.495 220.000 280.000
SAXPYing : 23.302 298.245 270.000 330.000
This archive was generated by hypermail 2b29 : Tue Apr 18 2000 - 05:23:04 CDT