STREAM numbers on nehalem

From: Tom Elken <tom.elken@qlogic.com>
Date: Mon May 11 2009 - 12:44:41 CDT

John,

I posted something similar to the following on the Beowulf list, but I had =
not gathered enough of the output for a posting to your STREAM site. I thi=
nk these are high numbers for Nehalem and 2-socket x86_64 systems in genera=
l.

System description:
Supermicro system and X8DTN Motherboard, workstation chassis:
2 sockets wach with:
model name : Intel(R) Xeon(R) CPU W5580 @ 3.20GHz
stepping : 4
cpu MHz : 3192.000

6 x 2GB DDR3-1333 dimms

Intel Compilers, Version 11.0 Build 20081105
$ icc -O3 -openmp -static stream.4.c

-------------------------------------------------------------
This system uses 8 bytes per DOUBLE PRECISION word.
-------------------------------------------------------------
Array size = 32000000, Offset = 0
Total memory required = 732.4 MB.
Each test is run 10 times, but only
the *best* time for each is used.
-------------------------------------------------------------
Number of Threads requested = 8
Number of Threads requested = 8
Number of Threads requested = 8
Number of Threads requested = 8
Number of Threads requested = 8
Number of Threads requested = 8
Number of Threads requested = 8
Number of Threads requested = 8
-------------------------------------------------------------
Your clock granularity/precision appears to be 1 microseconds.
Each test below will take on the order of 12519 microseconds.
   (= 12519 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) Avg time Min time Max time
Copy: 38435.7755 0.0136 0.0133 0.0139
Scale: 37358.5869 0.0138 0.0137 0.0140
Add: 36922.8751 0.0210 0.0208 0.0213
Triad: 37085.2576 0.0212 0.0207 0.0218
-------------------------------------------------------------
Solution Validates

Regards,
Tom



Received on Tue May 12 07:37:27 2009

This archive was generated by hypermail 2.1.8 : Thu Jan 17 2013 - 15:37:28 CST