AMD's dual core Opteron & Athlon 64 X2 - Server/Desktop Performance Preview
by Anand Lal Shimpi, Jason Clark & Ross Whitehead on April 21, 2005 9:25 AM EST- Posted in
- CPUs
Data Warehouse Test
We are always looking to improve the quality of our reviews and as a result, we have added a new Stress Test to our suite.This "Data Warehouse" test is focused on large record sets with plenty of aggregation. This test is based on a system that we developed to track and manage Request statistics for www.AnandTech.com and Forums.AnandTech.com. It tracks statistics like Requests/Hour, Requests/Hour/IP Address, Unique IP Addresses/Hour, Unique Users/Hour, Daily Browser stats, etc. These stats are further summarized by site, i.e. www or Forums.
As with the other Stress Tests, each test was repeated three times and the average between the three tests was used. For this Data Warehouse Stress Test, we defined a quantity of work to complete and measured how long each platform required to process the workload.
So, to ensure that IO was not the bottleneck, each test was started with a database, including tempdb, which had already been expanded so that autogrow activity did not occur during the test. During the execution of the tests, there were no applications running on the server or monitoring software. Task Manager, Profiler, and Performance Monitor were used when establishing the baseline for the test, but never during execution of the tests.
At the beginning of each platform, the server was rebooted to ensure a clean and consistent environment. The database was always copied to the 8 disk RAID 0 array with no other files present to ensure that file placement and fragmentation were consistent between runs. In between each of the three tests, the database was deleted, the original database was copied again to the array, and SQL Server was restarted.
There is no "client" required for this test. The workload is initiated by a stored procedure call from Query Analyzer.
Facebook
Twitter
RSS
144 Comments
View All Comments
Zebo - Friday, April 22, 2005 - link
It's all good Jep. I was mainly hoping you'd link me to a real live X2 over at xtreme which is why I persisted;)Minotar - Friday, April 22, 2005 - link
All I can say is WOW!!! AMD keeps kicking more and more ass!!!!!!Jep4444 - Friday, April 22, 2005 - link
why would i make this up? im just saying what i was told, for all i know that person made it upPS if anyone tries to comment and i dont respond within the next 3 days, its cause i wont be on, not cause im backing out of what i said
Zebo - Friday, April 22, 2005 - link
Frankey Jep I'm not buying it. It would cost AMD signifigantly more to make these dual 1MB L2 cores different at the core level. 8XX, 2XX, 1XX, and X2 are identical except for tracing in the pakageing and pins to make them function differently. Check out Tomshardware's recent CPU article about AMD manufacturing and you'll see what I'm talking.Jep4444 - Friday, April 22, 2005 - link
im not trying to start a rumour, im very much pro AMD(and if you knew me, i generally dislike attention)all im saying is dont decided it'll be so fast until we see the real thing
Son of a N00b - Friday, April 22, 2005 - link
#107......rumor.....looking for attentin....engineering sample...of course rushed....BIOS........shhhh jep...........period:-P
Filibuster - Friday, April 22, 2005 - link
If you've actually read through this entire thing, congratulations!Jep4444 - Friday, April 22, 2005 - link
#98 what i heard is from word of mouth, not from the site itselfwhile it is true they don't OC very well, apparently the Athlon X2 was rushed and so its functionality wasn't as good as the Opteron 875
from what i hear they don't multi-task nearly aswell as the Opteron does but single threaded performance should still be up to par
the Athlon 64 has had changes made to the ALU amongst other places which would differentiate it from the Opteron aswell
keep in mind i have no actual proof of this and i would love to be wrong but the guys at XS generally know what they're talking about
UzairH - Friday, April 22, 2005 - link
AT should run the doom 3 tests again, this time not using the timedemo but actual gameplay run-throughs. If Doom3 uses a seperate thread for physics then dual-core should definitely benefit.fitten - Friday, April 22, 2005 - link
#102 ++