Stream result for AMD 2GHz "Barcelona" 2P system

From: Waldecker, Brian <brian.waldecker@amd.com>
Date: Sun Nov 04 2007 - 08:29:14 CST

Hello,

Included below, please find the Stream result for a two cpu (2.0GHz)
Barcelona system with description. Note, the "Warthog" is actually
a four socket board but in this case, only 2 out of 4 sockets were
populated.

thank you,
Brian Waldecker
Advanced Micro Devices


System Description
------------------
Internal AMD "Warthog" unified-power-plane motherboard
Two AMD Opteron 2350 ("Barcelona") cpus (2.0 GHz)
8 x 2GB DDR2-667 CL5 memory ECC, REG, 2Rx4 (Micron)
default bios settings loaded

SUSE Linux Enterprise Server 10 (x86_64)
VERSION = 10
PATCHLEVEL = 1

QLogic PathScale(TM) Compiler Suite: Version 3.0
GNU gcc version 4.0.2 (PathScale 3.0 driver)

Compiler invocation:
  pathcc -gnu3 -mp -Ofast -static -static-libgcc
-CG:load_exe=2:use_prefetchnta=ON \
         -LNO:blocking=0 -o stream_psc3_omp_c_Ofast stream.c



-------------------------------------------------------------
STREAM version $Revision: 5.6 $
-------------------------------------------------------------
This system uses 8 bytes per DOUBLE PRECISION word.
-------------------------------------------------------------
Array size = 2000000, Offset = 384
Total memory required = 45.8 MB.
Each test is run 10 times, but only
the *best* time for each is used.
-------------------------------------------------------------
Number of Threads requested = 8
-------------------------------------------------------------
Printing one line per active thread....
Printing one line per active thread....
Printing one line per active thread....
Printing one line per active thread....
Printing one line per active thread....
Printing one line per active thread....
Printing one line per active thread....
Printing one line per active thread....
-------------------------------------------------------------
Your clock granularity/precision appears to be 2 microseconds.
Each test below will take on the order of 1757 microseconds.
   (= 878 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: 15633.9811 0.0021 0.0020 0.0021
Scale: 15525.4746 0.0021 0.0021 0.0021
Add: 15518.8925 0.0031 0.0031 0.0031
Triad: 15508.1337 0.0031 0.0031 0.0031
-------------------------------------------------------------
Solution Validates
-------------------------------------------------------------


Received on Sun Nov 04 09:34:49 2007

This archive was generated by hypermail 2.1.8 : Tue Nov 06 2007 - 14:44:38 CST