Announcement

Collapse
No announcement yet.

13-Way IBM POWER9 Talos II vs. Intel Xeon vs. AMD Linux Benchmarks On Debian

Collapse
X
  • Filter
  • Time
  • Show
Clear All
new posts

  • 13-Way IBM POWER9 Talos II vs. Intel Xeon vs. AMD Linux Benchmarks On Debian

    Phoronix: 13-Way IBM POWER9 Talos II vs. Intel Xeon vs. AMD Linux Benchmarks On Debian Linux

    Back in April we were able to run some IBM POWER9 benchmarks with remote access to the open-source friendly Talos II systems by Raptor Computer Systems. We were recently allowed remote access again to a few different configurations of this libre hardware with three different POWER9 processor combinations. Here are those latest benchmarks compared to Intel Xeon and AMD EPYC server processors.

    http://www.phoronix.com/vr.php?view=26482

  • #2
    In other words: Promising hardware, needs more software optimizations in some cases.

    Comment


    • #3
      Typo:

      Originally posted by phoronix View Post
      The PWOER9 performance
      Also, the LAME benchmark is missing.

      Comment


      • #4
        This was pretty interesting. Not too often do you see 3 different brands trading so many blows with each other.

        Comment


        • #5
          Highly inconsistent on various ways at compiler level, libraries, SIMD instructions support, not always scaling very well per core.

          Comment


          • #6
            Your price/performance charts are a little weird, then I read this: "Following the raw performance results are also performance-per-dollar metrics based upon current CPU retail prices."

            So you are only looking at the (usually wrong) CPU sticker price as the metric here. Furthermore, I have no idea where you get the prices for those Power9 chips from. So take the price/performance table with a mountain of salt.

            Comment


            • #7
              Originally posted by chuckula View Post
              Your price/performance charts are a little weird, then I read this: "Following the raw performance results are also performance-per-dollar metrics based upon current CPU retail prices."

              So you are only looking at the (usually wrong) CPU sticker price as the metric here. Furthermore, I have no idea where you get the prices for those Power9 chips from. So take the price/performance table with a mountain of salt.
              The pricing source is mentioned in the article.
              Michael Larabel
              http://www.michaellarabel.com/

              Comment


              • #8
                POWER9 seems to have about the same performance as EPYC except on benchmarks which use SIMD optimizations like video and audio encoding or encryption.

                Comment


                • #9
                  Several of the benchmarks where the POWER9 falls behind are where the program in quesiton relies a lot on inline assembly--which isn't available for most non-x86 arch's. So, they fall back to the generic C version. That makes the processor look bad when it's really a benchmarking problem. Comparing hand made assembly vs C compiler generated code isn't very interesting especially when you throw in a change in processor architecture. Notable for this probem is x264.

                  Single threaded tests? Really?

                  As has been pointed out, the LAME graph is missing--the FLAC chart is duplicated in its place.

                  There is also to keep in mind motherboard cost differences and other factors in evaluating the total cost of ownership.
                  Which you didn't do nor did you report the values necessary to do so.

                  Given that you compared the costs of just the CPUs in the performance/$ charts, you're really leaving out any meaningful way to compare these systems. Considering you compared *systems*, but reported results for just *processors*, that whole page can be pretty much ignored. Actually, *must be* ignored lest one be mislead.

                  For a quick runthrough of the systems, this article does a good job, but you continue to rely on your readers being very knowledgable about the limitations of specific benchmarks. Said another way, you make it very easy for your readers to be mislead unless they posess a great deal of knowledge about the benchmarks you run.

                  Comment


                  • #10
                    Spectacular, love the per dollar numbers, it puts the cost of these Talos systems into perspective.

                    Comment

                    Working...
                    X