Announcement

Collapse
No announcement yet.

CPUs From 2004 Against AMD's New 64-Core Threadripper 3990X + Tests Against FX-9590

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

  • CPUs From 2004 Against AMD's New 64-Core Threadripper 3990X + Tests Against FX-9590

    Phoronix: CPUs From 2004 Against AMD's New 64-Core Threadripper 3990X + Tests Against FX-9590

    With having the initial AMD Ryzen Threadripper 3990X Linux benchmarks out of the way, I did some fun Friday night benchmarking with this 64-core HEDT CPU... Seeing how the 3990X performance compares to some CPUs used when starting out Phoronix back in 2004 as well as also for fun seeing how the Threadripper 3990X compares to the notorious AMD FX-9590...

    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
    vs Raspberry PI ?

    It is actually not that impressive that it is only 4x faster with compiling the kernel and only 2x faster encoding an mp3 than the AMD FX-9590 with its 64/128 against 8/8...

    For me lots of cores only looks good in benchmarks designed for that purpose.
    In the "real world" you still get bad diminishing returns ...

    Yesterday I ran a program that calculates prime numbers and I was not impressed that my 2012 model i7-3770 (3.4GHz/3.9GHZ) did it in 4s versus my "shinny new" ryzen7-3700x (3.6Ghz/4.4GHz) which only managed 8s....

    Running bloatware is where the ryzens shine with all their cache, but pure calculations intel seems to still be far ahead...
    Last edited by Raka555; 08 February 2020, 09:53 AM.

    Comment


    • #3
      Wow, great, thank you Michael! When I read AMD Ryzen Threadripper 3990X Offers Incredible Linux Performance I was like “too bad you didn't include the FX-59590”, because that's the CPU I still use and I'm interested about how is the difference between this one and the beasty TR 3990X.

      So, if q3map2 lightmapper behaves like C-Ray, a noFast map compilation that takes 2 days would last 2 hours instead… And if q3map2 does not behave like this and is less efficient, I can still expect unit time going from day to hour.

      Comment


      • #4
        Gains in single threaded performance for the past 10 years have still been minuscule in comparison to what we had from 1981 to the end of the 00's where performance increased 100 fold or maybe more.

        It would be great if someone managed to compare the following CPUs:
        • Intel 386
        • Intel 486
        • Pentium Pro
        • Pentium 2
        • Pentium III
        • Pentium 4
        • Core 2 Duo
        • Sandy Bridge
        • Sky Lake
        • Ice Lake
        Intel 8086 and 286 are out of the question since they lack 32bit support.
        Last edited by birdie; 08 February 2020, 10:46 AM.

        Comment


        • #5
          Originally posted by birdie View Post
          Gains in single threaded performance for the past 10 years have still been minuscule in comparison to what we had from 1981 to the end of the 00's where performance increased 100 fold or maybe more.

          It would be great if someone managed to compare the following CPUs:
          • Intel 386
          • Intel 486
          • Pentium Pro
          • Pentium 2
          • Pentium III
          • Pentium 4
          • Core 2 Duo
          • Sandy Bridge
          • Sky Lake
          • Ice Lake
          Intel 8086 and 286 are out of the question since they lack 32bit support.
          I wonder of Michael has some old DOS benchmarks

          Comment


          • #6
            Originally posted by Raka555 View Post

            I wonder of Michael has some old DOS benchmarks
            That's not really necessary as you can install Windows 98 on even Intel 386, and there are quite a lot of 32bit benchmarks which support this OS including 7-Zip.

            Comment


            • #7
              Just last week, I reached my 6 core Phenom II x6 1055t file server with a spare Ryzen 1700.

              I did it mostly for the idle power consumption improvements, but it's good to see that the performance is likely to be a night and day difference as well.

              Time to load up on VMs/Containers

              Comment


              • #8
                Ouch.
                My FX-8350 now seems quite a slow CPU... :|

                Comment


                • #9
                  Originally posted by Raka555 View Post
                  vs Raspberry PI ?

                  It is actually not that impressive that it is only 4x faster with compiling the kernel and only 2x faster encoding an mp3 than the AMD FX-9590 with its 64/128 against 8/8...

                  For me lots of cores only looks good in benchmarks designed for that purpose.
                  In the "real world" you still get bad diminishing returns ...

                  Yesterday I ran a program that calculates prime numbers and I was not impressed that my 2012 model i7-3770 (3.4GHz/3.9GHZ) did it in 4s versus my "shinny new" ryzen7-3700x (3.6Ghz/4.4GHz) which only managed 8s....

                  Running bloatware is where the ryzens shine with all their cache, but pure calculations intel seems to still be far ahead...
                  such small calculations are at a certain point dominated by providing all data for all cores ...do some primenumber crunching with bigger numbers and you will see the difference.



                  Last edited by CochainComplex; 08 February 2020, 11:51 AM.

                  Comment


                  • #10
                    Too bad the Ryzen loses all the price/performance metrics since I can get a p4 (or even Sandy Bridge) for free these days.

                    Comment

                    Working...
                    X