Announcement

Collapse
No announcement yet.

Keeping The Ryzen Threadripper Busy With An Array Of Compiler Benchmarks

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

  • Keeping The Ryzen Threadripper Busy With An Array Of Compiler Benchmarks

    Phoronix: Keeping The Ryzen Threadripper Busy With An Array Of Compiler Benchmarks

    While there are an array of interesting AMD Ryzen Threadripper 1950X Linux benchmarks in this morning's review, after hitting a 36 second Linux kernel compilation time with this 16 core / 32 thread processor, I spent this afternoon seeing what I was getting for some other compile times of popular programs...

    http://www.phoronix.com/scan.php?pag...-Compile-Times

  • #2
    When I saw Michael compiling everything in sight it somehow reminded me of this scene:

    https://www.youtube.com/watch?v=B02dsLGLw4E

    Comment


    • #3
      thanks Michael for the benchmarks - right in my area of interest

      Comment


      • #4
        You really ought to write a timed Chromium compilation script :P

        Comment


        • #5
          Originally posted by carewolf View Post
          You really ought to write a timed Chromium compilation script :P
          Patches always welcome too.
          Michael Larabel
          http://www.michaellarabel.com/

          Comment


          • #6
            Could you test Eclipse/IntelliJ huge compiling?

            Comment


            • #7
              Originally posted by amossoma View Post
              Could you test Eclipse/IntelliJ huge compiling?
              If someone provides a PTS test profile for it or at least a complete bash script doing so.
              Michael Larabel
              http://www.michaellarabel.com/

              Comment


              • #8
                Sorry, my fault. I joined two things together. First was just simple cusriosity about using Eclispse/IntelliJ in such powerfull PC (it's no testable by script ). And second was java huge compiling. It's testable . In example you can build hibernate(https://github.com/hibernate/hibernate-orm) or any other big project.

                Comment


                • #9
                  "I did also try some runs when the tests were installed to tmpfs/zram, but that showed the Corsair MP500 NVMe SSD wasn't actually the bottleneck that the build times weren't getting reduced in any meaningful way."

                  Hmm that's stange. I've noticed significant speedups when compiling kernel in /tmp tmpfs versus NVMe SSD. Especially all disk operations which involve traversing directories and checking individual small files are faster. OTOH disk blocks are cached if you repeat the test so maybe that explains it.

                  Comment


                  • #10
                    Originally posted by bridgman View Post
                    When I saw Michael compiling everything in sight it somehow reminded me of this scene:

                    https://www.youtube.com/watch?v=B02dsLGLw4E
                    O_O

                    Prediction! AMD will repeat history and underperform like the FX-series in crucial tasks.
                    Last edited by AdamOne; 08-29-2017, 10:08 AM.

                    Comment

                    Working...
                    X