{"id":16,"date":"2006-07-03T04:24:06","date_gmt":"2006-06-15T21:55:10","guid":{"rendered":""},"modified":"2016-11-26T07:49:56","modified_gmt":"2016-11-26T07:49:56","slug":"benchmarking_the_power5_1","status":"publish","type":"post","link":"https:\/\/blogs.gentoo.org\/solar\/2006\/07\/03\/benchmarking_the_power5_1\/","title":{"rendered":"Benchmarking the power5"},"content":{"rendered":"<p>Yesterday I got fwded along a forum posting over at <a href=\"http:\/\/penguinppc.org\">penguinppc.org<\/a> from our good friend over at the OSL [cshields@osuosl] <a href=\"http:\/\/www.power.org\/phpbb\/viewtopic.php?t=262\">powerpc-cpu optimizations<\/a> <\/p>\n<p>Gentoo PPC64 has glibc-2.3.4.20041102-r2 marked stable so first I started patching it up. While talking to another developer [vapier@gentoo] I found out that the powerpc-cpu optimizations had already been integrated in our glibc-2.4-r3 by him, so I stopped with the patching up of 2.3.x<br \/>\nTime for a few benchmarks. First nbench was not keyworded for PPC64 so I passed that info along to our PPC64 team and [ranger@gentoo] keyworded it for future use.<\/p>\n<p>Here are the results.<\/p>\n<p><em>Base PPC64 stable.<\/em><br \/>\n<strong>gcc-3.4.4 glibc-2.3.4.20041102-r2<\/strong><\/p>\n<pre>\r\nBYTEmark* Native Mode Benchmark ver. 2 (10\/95)\r\nIndex-split by Andrew D. Balsa (11\/97)\r\nLinux\/Unix* port by Uwe F. Mayer (12\/96,11\/97)\r\n\r\nTEST                : Iterations\/sec.  : Old Index   : New Index\r\n                    :                  : Pentium 90* : AMD K6\/233*\r\n--------------------:------------------:-------------:------------\r\nNUMERIC SORT        :          581.52  :      14.91  :       4.90\r\nSTRING SORT         :            96.4  :      43.07  :       6.67\r\nBITFIELD            :      1.2933e+08  :      22.19  :       4.63\r\nFP EMULATION        :          36.512  :      17.52  :       4.04\r\nFOURIER             :          8689.8  :       9.88  :       5.55\r\nASSIGNMENT          :          7.3297  :      27.89  :       7.23\r\nIDEA                :          1503.4  :      22.99  :       6.83\r\nHUFFMAN             :          589.62  :      16.35  :       5.22\r\nNEURAL NET          :          14.411  :      23.15  :       9.74\r\nLU DECOMPOSITION    :           556.8  :      28.85  :      20.83\r\n==========================ORIGINAL BYTEMARK RESULTS==========================\r\nINTEGER INDEX       : 22.153\r\nFLOATING-POINT INDEX: 18.757\r\nBaseline (MSDOS*)   : Pentium* 90, 256 KB L2-cache, Watcom* compiler 10.0\r\n==============================LINUX DATA BELOW===============================\r\nCPU                 : 8 CPU\r\nL2 Cache            : \r\nOS                  : Linux 2.6.5-7.97-pseries64\r\nC compiler          : 3.4.4\r\nlibc                : \r\nMEMORY INDEX        : 6.069\r\nINTEGER INDEX       : 5.154\r\nFLOATING-POINT INDEX: 10.403\r\nBaseline (LINUX)    : AMD K6\/233*, 512 KB L2-cache, gcc 2.7.2.3, libc-5.4.38\r\n* Trademarks are property of their respective holder.\r\n<\/pre>\n<p><em>glibc-2.4.x requires gcc-4 so I compiled that, then recompiled nbench so we could establish any differences it makes alone.<\/em><br \/>\n<strong>gcc-4.1.1 with 2.3.4.20041102-r2<\/strong><\/p>\n<pre>\r\nBYTEmark* Native Mode Benchmark ver. 2 (10\/95)\r\nIndex-split by Andrew D. Balsa (11\/97)\r\nLinux\/Unix* port by Uwe F. Mayer (12\/96,11\/97)\r\n\r\nTEST                : Iterations\/sec.  : Old Index   : New Index\r\n                    :                  : Pentium 90* : AMD K6\/233*\r\n--------------------:------------------:-------------:------------\r\nNUMERIC SORT        :          586.56  :      15.04  :       4.94\r\nSTRING SORT         :          102.48  :      45.79  :       7.09\r\nBITFIELD            :      1.3137e+08  :      22.54  :       4.71\r\nFP EMULATION        :          39.625  :      19.01  :       4.39\r\nFOURIER             :            8742  :       9.94  :       5.58\r\nASSIGNMENT          :          10.188  :      38.77  :      10.06\r\nIDEA                :          1750.9  :      26.78  :       7.95\r\nHUFFMAN             :          775.66  :      21.51  :       6.87\r\nNEURAL NET          :          16.845  :      27.06  :      11.38\r\nLU DECOMPOSITION    :          605.04  :      31.34  :      22.63\r\n==========================ORIGINAL BYTEMARK RESULTS==========================\r\nINTEGER INDEX       : 25.276\r\nFLOATING-POINT INDEX: 20.354\r\nBaseline (MSDOS*)   : Pentium* 90, 256 KB L2-cache, Watcom* compiler 10.0\r\n==============================LINUX DATA BELOW===============================\r\nCPU                 : 8 CPU\r\nL2 Cache            : \r\nOS                  : Linux 2.6.5-7.97-pseries64\r\nC compiler          : 4.1.1\r\nlibc                : \r\nMEMORY INDEX        : 6.948\r\nINTEGER INDEX       : 5.866\r\nFLOATING-POINT INDEX: 11.289\r\nBaseline (LINUX)    : AMD K6\/233*, 512 KB L2-cache, gcc 2.7.2.3, libc-5.4.38\r\n* Trademarks are property of their respective holder.\r\n<\/pre>\n<p>Sadly the kernel version that&#8217;s running on the OSL box is a SuSe one without the support needed. I kept getting FATAL: kernel too old while building glibc. Guess I&#8217;ll have to save the powerpc-cpu optimizations testing for another day..<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Yesterday I got fwded along a forum posting over at penguinppc.org from our good friend over at the OSL [cshields@osuosl] powerpc-cpu optimizations Gentoo PPC64 has glibc-2.3.4.20041102-r2 marked stable so first I started patching it up. While talking to another developer [vapier@gentoo] I found out that the powerpc-cpu optimizations had already been integrated in our glibc-2.4-r3 &hellip; <a href=\"https:\/\/blogs.gentoo.org\/solar\/2006\/07\/03\/benchmarking_the_power5_1\/\" class=\"more-link\">Continue reading <span class=\"screen-reader-text\">Benchmarking the power5<\/span><\/a><\/p>\n","protected":false},"author":36,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[3,4],"tags":[],"jetpack_featured_media_url":"","_links":{"self":[{"href":"https:\/\/blogs.gentoo.org\/solar\/wp-json\/wp\/v2\/posts\/16"}],"collection":[{"href":"https:\/\/blogs.gentoo.org\/solar\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blogs.gentoo.org\/solar\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blogs.gentoo.org\/solar\/wp-json\/wp\/v2\/users\/36"}],"replies":[{"embeddable":true,"href":"https:\/\/blogs.gentoo.org\/solar\/wp-json\/wp\/v2\/comments?post=16"}],"version-history":[{"count":1,"href":"https:\/\/blogs.gentoo.org\/solar\/wp-json\/wp\/v2\/posts\/16\/revisions"}],"predecessor-version":[{"id":23,"href":"https:\/\/blogs.gentoo.org\/solar\/wp-json\/wp\/v2\/posts\/16\/revisions\/23"}],"wp:attachment":[{"href":"https:\/\/blogs.gentoo.org\/solar\/wp-json\/wp\/v2\/media?parent=16"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blogs.gentoo.org\/solar\/wp-json\/wp\/v2\/categories?post=16"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blogs.gentoo.org\/solar\/wp-json\/wp\/v2\/tags?post=16"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}