**Previous message:**Joe Glenski: "Streams results for the CRAY SV1"**Messages sorted by:**[ date ] [ thread ] [ subject ] [ author ]

This is a custom-built system with an Athlon 800 in an ASUS K7V motherboard,

768 MB PC133 (7.5 ns) SDRAM. The memory bus was set to asynchronous mode,

with a 4:3 multiplier of the CPU FSB, and memory timing at 3-2-2.

It turns out that it is currently hard to get truly fast SDRAM in 256 MB DIMMs.

I took the source code and recompiled it with Lahey F90 4.5, to take advantage

of the advanced timer. I hope that's OK. Your wstream executable gave somewhat

odd results on this win98 system.

================================

---------------------------------------------

Double precision appears to have 16 digits of accuracy

Assuming 8 bytes per DOUBLE PRECISION word

---------------------------------------------

Array size = 2000000

Offset = 0

The total memory requirement is 45 MB

You are running each test 10 times

The *best* time for each test is used

----------------------------------------------------

Your clock granularity/precision appears to be 4 microseconds

The tests below will each take a time on the order

of 95864 microseconds

(= 23966 clock ticks)

Increase the size of the arrays if this shows that

you are not getting at least 20 clock ticks per test.

----------------------------------------------------

WARNING -- The above is only a rough guideline.

For best results, please be sure you know the

precision of your system timer.

----------------------------------------------------

Function Rate (MB/s) RMS time Min time Max time

Copy: 376.0116 0.0866 0.0851 0.0926

Scale: 427.8838 0.0757 0.0748 0.0821

Add: 473.2809 0.1044 0.1014 0.1256

Triad: 571.6290 0.0986 0.0840 0.1823

Sum of a is = 0.230660156259187D+019

Sum of b is = 0.461320312485644D+018

Sum of c is = 0.615093750014126D+018

**Next message:**Frank de Lange: "stream results"**Previous message:**Joe Glenski: "Streams results for the CRAY SV1"**Messages sorted by:**[ date ] [ thread ] [ subject ] [ author ]

*
This archive was generated by hypermail 2b29
: Sat Jun 03 2000 - 02:58:55 CDT
*