Order Entry Results

Our Vendor test has received quite a bit of interest from certain processor vendors; rightfully so, as the workload is quite difficult to recreate.

As you can see from the results below, there are some interesting conclusions that you can draw:
  • The Dual Opteron 875 took the lead by 18% over the fastest Quad Intel. This should come as no surprise as we have seen in the past that the memory bandwidth limitation of the Intel FSB architecture does not allow the quads to really stretch their legs. On the other hand, the Integrated Memory Controller of the Opterons allow them to pull ahead.
  • The additional L3 cache of the Quad Xeon 3.3GHz allows it to outperform the Quad Xeon 3.6GHz by 16%.
  • The Quad Xeon 3.6GHz with the 667MHz FSB is only able to outperform the Dual Xeon 3.6GHz 800MHz FSB by 5%.
  • The dual Xeons are able to outpace the dual 252's by 2%, and the single 875 by 5%. The Xeons success here can be attributed to the additional L2 cache.
  • The Dual Opteron 875 demonstrated nice scalability by servicing 52% more requests in the same period as the single Opteron 875.

Vendor Heavy Workload Test (Reads)

Vendor Heavy Workload Test (Writes)

To give you an idea of the scale of this benchmark, we have graphs of stored procedures calls per second. We decided to focus on Stored Procedures / Second rather than Transactions / Second, as the definition of a Transaction can have a business context or a technical context.

Vendor Heavy Workload Stored Procedures


"Order Entry" Stress Test: Measuring Enterprise Class Performance Data Warehouse Results
Comments Locked

144 Comments

View All Comments

  • morcegovermelho - Thursday, April 21, 2005 - link

    page 3 "For example, the Opteron 252 and Opteron 852 both run at 2.6GHz, but the 252 is for use in up to 2-way configurations, while the 852 is certified for use in 4- and 8-way configurations. The two chips are identical; it's just that one has been run through additional validation and costs a lot more. "
    I thought that they had different number of HyperTransport (HT) links:
    152 - 1 HT
    252 - 2 HT
    852 - 3 HT
    I thought that was the reason why it was impossible to use two 152s in a two-way motherboard.
    Maybe i'm wrong.
  • faboloso112 - Thursday, April 21, 2005 - link

    great article
  • fungmak - Thursday, April 21, 2005 - link

    #50
    Dual 875s have 4 cores
  • stmok - Thursday, April 21, 2005 - link

    I have waited SOOOOO long! Finally, a reason to dump my dual PIII setups. Next stop, Athlon64 X2!
  • jediknight - Thursday, April 21, 2005 - link

    Can someone explain the huge performance difference between the dual Operaon 252s (2.6GHz) and the dual Opteron 875 (2.2GHz)?

    Since:
    "The two chips are identical; it's just that one has been run through additional validation and costs a lot more"

    I would expect the 252s, running at 400MHz more, would outperform the 875s. Can someone explain this (large) discrepency?
  • snedzad - Thursday, April 21, 2005 - link

    Yes. That's gonna be a four proc-machine. Terrific.

    I am really astonished about whole AMD K8 architecture. And K9 should be 4-core processor architecture.

    Can't wait.

    But, I still won't get a rid of my AX2600 machine.
  • Griswold - Thursday, April 21, 2005 - link

    Ah the brilliant KillerBob.

    Anand used plenty of real world apps for the multitask benchmarks.

    How much more real world testing would you want to go with your (pointless) whining?

  • GoatHerderEd - Thursday, April 21, 2005 - link

    Why is their stock price at a 6 month low? I hope this pulls it up a bit. It would be a shame if they don’t start making a profit.
  • suryad - Thursday, April 21, 2005 - link

    I just am astounded at the performance these first versions of dual core processing that is being presented to us...WOW...couple that with a well written 64 bit OS and it will be even more smoking!! I think AMD did a job extremely well done and I am glad that they are being aggressive in keeping their pockets full with the prices of their chips. I personally dont think that would stop me from buying their processors. I would wait for the FX to become dual core though. A 3 ghz dual core FX would rock so bad!!!

    Also one more thing...so the Tyan mobo holds 2 procs correct? So if we stuck a dual core in 1 socket and another in the other sock...that makes it a 4 proc machine then right?!!
  • bldckstark - Thursday, April 21, 2005 - link

    Thanks for the double post KillerBob. Your statements are as intelligent as your ability to use a keyboard.

Log in

Don't have an account? Sign up now