Announcement

Collapse
No announcement yet.

Azure Provides Excellent HPC Cloud Performance With HBv4 Series Powered By AMD EPYC Genoa-X

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

  • Azure Provides Excellent HPC Cloud Performance With HBv4 Series Powered By AMD EPYC Genoa-X

    Phoronix: Azure Provides Excellent HPC Cloud Performance With HBv4 Series Powered By AMD EPYC Genoa-X

    The past several weeks at Phoronix has been very exciting with benchmarking AMD EPYC Genoa-X processors (along with Bergamo) and the incredible uplift delivered by these latest AMD server processors. But for those not yet having the opportunity to test the new EPYC Genoa-X processors locally, those wishing to evaluate the Genoa-X capabilities in the public cloud prior to making an investment in these high-end server processors with 3D V-Cache, or those simply preferring the ease of cloud infrastructure, Azure's new HBv4 series provide an excellent route for leveraging AMD Genoa-X compute capabilities in the cloud. Here are benchmarks of the new Azure HBv4 powered by EPYC Genoa-X compared to prior Azure HPC VMs. The Azure HBv4 performance is outstanding with incredible generational uplift and leading value among Microsoft's HPC-focused VMs.

    Phoronix, Linux Hardware Reviews, Linux hardware benchmarks, Linux server benchmarks, Linux benchmarking, Desktop Linux, Linux performance, Open Source graphics, Linux How To, Ubuntu benchmarks, Ubuntu hardware, Phoronix Test Suite

  • #2
    Typo:

    Originally posted by phoronix View Post
    HC - The original 44 vCPus with the Xeon Platinum 8168 Skylake processors.​

    Comment


    • #3
      I always appreciate your work Michael, but I find hard to swallow an HPC benchmark without internode scaling results. With a 400Gbps RDMA interconnect Azure is probably the only one offering that among mainstream CSP.

      Comment


      • #4
        Originally posted by sabian2008 View Post
        I always appreciate your work Michael, but I find hard to swallow an HPC benchmark without internode scaling results. With a 400Gbps RDMA interconnect Azure is probably the only one offering that among mainstream CSP.
        Because this testing is focused just on the CPU/VM generational performance to which 1 VM conveys that just fine... Not focused on inter-node scaling though the 400Gbps RDMA is mentioned in the article. And it's not like it's some very lucrative topic or highly sought after. Hence the little forum commentary and from traffic it's rare that my cloud tests justify all the time I spend working on said tests, mostly a matter of satisfying my own curiosity and such.
        Michael Larabel
        https://www.michaellarabel.com/

        Comment


        • #5
          The way it's written makes the article sound like a puff piece for Azure. Are you sure you're not getting paid by AMD and/or Microsoft for this? If so it should be disclosed somewhere in the article.

          Comment


          • #6
            Originally posted by blae View Post
            The way it's written makes the article sound like a puff piece for Azure. Are you sure you're not getting paid by AMD and/or Microsoft for this? If so it should be disclosed somewhere in the article.
            As mentioned in the article, the only form of compensation was getting free access to the Azure VM instances for benchmarking.
            Michael Larabel
            https://www.michaellarabel.com/

            Comment


            • #7
              Originally posted by blae View Post
              The way it's written makes the article sound like a puff piece for Azure.
              You mean this is an overly positive report which is downplaying or neglecting to mention negative aspects?

              What kind of problem do you propose that Michael encountered when using Azure but did not describe faithfully?

              Comment


              • #8
                Originally posted by chithanh View Post
                You mean this is an overly positive report which is downplaying or neglecting to mention negative aspects?

                What kind of problem do you propose that Michael encountered when using Azure but did not describe faithfully?
                To me, this article looks a lot like an ad for Microsoft for several reasons:
                1) It compares the benchmarks of several paid Microsoft products with each other and nothing else. To me, it sounds like: "Take a look which paid Microsoft product is best for you!" and that is hardly an impartial review.

                2) The style. The first word of the title is "Azure". And the title is: "[Paid product] provides excellent cloud performance with [such and such hardware]". That is how commercial ads are written, not reviews.

                3) Some example sentences:
                -"The Azure HBv4 performance is outstanding with incredible generational uplift and leading value among Microsoft's HPC-focused VMs."
                -"Last year Microsoft upgraded the Azure HBv3 series with Milan-X and since that first generation 3D V-Cache server processor deployment, these cloud VMs have offered industry-leading performance. zz0.6kp9yhjzyxszz"
                -"Performance-per-dollar benchmarks are also available based on the Azure pay-as-you-go pricing, per hour for each of these instances."

                Again, this is praise for Microsoft's paid product. There's no attempt to compare it to anything else, free or paid. And it even provides a convenient price estimate for would-be Microsoft customers - again with no comparison to anything else.

                IMHO this is an advertisement, not journalism.

                Comment

                Working...
                X