Announcement

Collapse
No announcement yet.

More AMD FX-4100, FX-8150 Bulldozer Linux Details

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

  • More AMD FX-4100, FX-8150 Bulldozer Linux Details

    Phoronix: More AMD FX-4100, FX-8150 Bulldozer Linux Details

    On Friday some benchmarks of the AMD FX-8150 Bulldozer on Linux were shared, thanks to an early adopter running some benchmarks under Gentoo and uploading them to OpenBenchmarking.org. But there's more to come...

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

  • #2
    How about trying some LLVM benches on it? I know Cray was looking to add some special BD support to it earlier this year. Not sure if they have been introduced into the main branch yet however.

    EDIT: looks like patches for LLVM were submitted back in August.
    Last edited by deanjo; 10-16-2011, 10:59 AM.

    Comment


    • #3
      Oh, that's how you compare test results on openbenchmarking. For some reason I never saw this.

      Compared to the 1090T the 8150 is hardly faster, except in few massive parallel benchmarks. That's not very good. But what happened to the "messina" 2600k? In comparison with that it looks terribly awful.
      (By the way: This seems to be buggy: http://openbenchmarking.org/opc/1110159-LI-1110131LI24 as the "messina" fails to appear in many of those graphs).

      I still think we really need a test with optimized binaries and a patched and optimized kernel to see whether not something goes terribly wrong in software or the problems I have read about are really that severe...

      Comment


      • #4
        The link to the test-suite (third paragraph) links to 'http://www.phoroni-test-suite.com/' which should be 'http://www.phoronix-test-suite.com/'

        messina is really sick

        Comment


        • #5
          For those looking to facilitate a comparison of these results from the web-interface, simply click on the results via the "Compare Test Results" from the left-hand menu. Here's an OpenBenchmarking.org example that's comparing the AMD FX-8150 to some of the other user-supplied data.
          Clicking the link yields
          Code:
          XML parsing failed: syntax error (Line: 46, Character: 585)
          
          Error:
          unexpected end-of-file
          
           43: <div id="oborg_main_area">
           44: 	<p style="text-align: center; margin: 0 0 15px;"><object data="/ads/idg_728x90.html" type="text/html" width="728" height="100"></object></p>
           45: 	<div id="oborg_main">
           46: 		<h1><img src="css/icons/openbenchmark-small.png" /> bulldozer</h1><p><strong>1110165-LI-1110131LI64:</strong> AMD FX -8150 Eight-Core testing with a ASUS SABERTOOTH 990FX and NVIDIA GeForce 8800 GT 512MB on Gentoo Base release 2.1 via the Phoronix Test Suite.</p><p><strong>A comparison of:</strong> 1110165-LI-1110131LI64, 1110165-AGY-1110158L96, 1110164-GR-1110131LI17, 1110158-LI-1110131LI42, 1110152-LI-1110131LI59, 1110150-GR-1110131LI69, 1110147-GR-1110131LI32, 1110159-LI-1110131LI24, 1110158-IV-1110131LI29.</p><a name="system_table" /><h2>System Hardware &amp; Software</h2>
          in Opera 11.51

          Comment


          • #6
            Originally posted by PsynoKhi0 View Post
            Clicking the link yields
            Code:
            XML parsing failed: syntax error (Line: 46, Character: 585)
            
            Error:
            unexpected end-of-file
            
             43: <div id="oborg_main_area">
             44:     <p style="text-align: center; margin: 0 0 15px;"><object data="/ads/idg_728x90.html" type="text/html" width="728" height="100"></object></p>
             45:     <div id="oborg_main">
             46:         <h1><img src="css/icons/openbenchmark-small.png" /> bulldozer</h1><p><strong>1110165-LI-1110131LI64:</strong> AMD FX -8150 Eight-Core testing with a ASUS SABERTOOTH 990FX and NVIDIA GeForce 8800 GT 512MB on Gentoo Base release 2.1 via the Phoronix Test Suite.</p><p><strong>A comparison of:</strong> 1110165-LI-1110131LI64, 1110165-AGY-1110158L96, 1110164-GR-1110131LI17, 1110158-LI-1110131LI42, 1110152-LI-1110131LI59, 1110150-GR-1110131LI69, 1110147-GR-1110131LI32, 1110159-LI-1110131LI24, 1110158-IV-1110131LI29.</p><a name="system_table" /><h2>System Hardware &amp; Software</h2>
            in Opera 11.51
            Try now should work.
            Michael Larabel
            http://www.michaellarabel.com/

            Comment


            • #7
              https://twitter.com/#!/michaellarabe...74658283528192
              Michael Larabel
              http://www.michaellarabel.com/

              Comment


              • #8
                congrats to your new Bulldozer CPU

                Comment


                • #9
                  Are you still planning to publish the results of the SSH system, or will you wait to do the local testing?

                  Comment


                  • #10
                    Tried to edit my previous post, but too late... Could one get another button besides "Cancel changes" so as to be able to copy/paste changes instead of just losing them?

                    Anyway, I tried to compare an FX-4100 to a Phenom II x4 965 since it's the closest similarly priced AMD CPU, and I used some comma-separated copy/paste: http://openbenchmarking.org/result/1...AR-BULLDOZER08
                    How comes some tests end up with entries on different lines for each system? E.g. the GraphicsMagick and John the Ripper tests. Do the tests need to be performed in the exact same fashion/order on both system for a easy-to-read comparison?

                    Comment


                    • #11
                      Originally posted by Michael View Post
                      Try now should work.
                      Code:
                      XML parsing failed: syntax error (Line: 46, Character: 581)
                      Hey at least something happened :P

                      And grats on the Dozer, which model?
                      Hope you don't get an Asus Crosshair V as a board...

                      Comment


                      • #12
                        Originally posted by PsynoKhi0 View Post
                        Code:
                        XML parsing failed: syntax error (Line: 46, Character: 581)
                        Hey at least something happened :P

                        And grats on the Dozer, which model?
                        Hope you don't get an Asus Crosshair V as a board...
                        Can you paste that line / character?

                        No idea about the CPU or board.

                        Not sure why some of your tests aren't merging, order shouldn't matter at all, will look into it.

                        Will still publish the remote results soon.
                        Michael Larabel
                        http://www.michaellarabel.com/

                        Comment


                        • #13
                          Originally posted by Michael View Post
                          Can you paste that line / character?
                          Code:
                          <h1><img src="css/icons/openbenchmark-small.png" /> bulldozer</h1><p><strong>1110165-LI-1110131LI64:</strong> AMD FX -8150 Eight-Core testing with a ASUS SABERTOOTH 990FX and NVIDIA GeForce 8800 GT 512MB on Gentoo Base release 2.1 via the Phoronix Test Suite.</p><p><strong>A comparison of:</strong> 1110165-LI-1110131LI64, 1110165-AGY-1110158L96, 1110164-GR-1110131LI17, 1110158-LI-1110131LI42, 1110152-LI-1110131LI59, 1110150-GR-1110131LI69, 1110147-GR-1110131LI32, 1110159-LI-1110131LI24, 1110158-IV-1110131LI29.</p><a name="system_table" /><h2>System Hardware / Software</h2>
                          Missing </a>?

                          Originally posted by Michael View Post
                          No idea about the CPU or board.
                          Oh well... Now is not the time to be nitpicking I suppose heh. Will you include the BD patch?

                          Originally posted by Michael View Post
                          Not sure why some of your tests aren't merging, order shouldn't matter at all, will look into it.
                          Cool. But they aren't my tests

                          Comment


                          • #14
                            Originally posted by ChrisXY View Post
                            Oh, that's how you compare test results on openbenchmarking. For some reason I never saw this.

                            Compared to the 1090T the 8150 is hardly faster, except in few massive parallel benchmarks. That's not very good. But what happened to the "messina" 2600k? In comparison with that it looks terribly awful.
                            (By the way: This seems to be buggy: http://openbenchmarking.org/opc/1110159-LI-1110131LI24 as the "messina" fails to appear in many of those graphs).

                            I still think we really need a test with optimized binaries and a patched and optimized kernel to see whether not something goes terribly wrong in software or the problems I have read about are really that severe...
                            My initial thoughts when reading about Bulldozer (pre release) was: "Wait, we get eight "three-quarter" cores? I want at last six full cores to replace my 1090! Will there be a 12150?"
                            ATM its seems that one bulldozer Module is 55% faster then one? thuban core: (AMD was promising 80% per CMT core)
                            So four Modules == 6.2 cores. (... lets ignore the new instructions for a bit ;P)

                            Imho .. 8150 is a quad core with 50% more power for everything but single threaded apps. The cache trashing due to missing patches/CMT scheduler finish him off.

                            AgY

                            Comment


                            • #15
                              Seems someone submitted something "more" optimized (compiler?):
                              http://openbenchmarking.org/result/1...GR-BULLDOZER88

                              and with 2600K:
                              http://openbenchmarking.org/result/1...LI-1110131LI24

                              but its not a 990FX board ;(
                              MT performance seems to suffer .. a bit.

                              Finally!

                              Comment

                              Working...
                              X