From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 16961 invoked by alias); 3 Sep 2013 17:48:47 -0000 Mailing-List: contact libc-ports-help@sourceware.org; run by ezmlm Precedence: bulk List-Id: List-Subscribe: List-Post: List-Help: , Sender: libc-ports-owner@sourceware.org Received: (qmail 16947 invoked by uid 89); 3 Sep 2013 17:48:47 -0000 Received: from popelka.ms.mff.cuni.cz (HELO popelka.ms.mff.cuni.cz) (195.113.20.131) by sourceware.org (qpsmtpd/0.93/v0.84-503-g423c35a) with ESMTP; Tue, 03 Sep 2013 17:48:47 +0000 Authentication-Results: sourceware.org; auth=none X-Virus-Found: No X-Spam-SWARE-Status: No, score=-0.7 required=5.0 tests=AWL,BAYES_00,FREEMAIL_FROM,SPF_NEUTRAL autolearn=no version=3.3.2 X-Spam-User: qpsmtpd, 2 recipients X-HELO: popelka.ms.mff.cuni.cz Received: from domone.kolej.mff.cuni.cz (popelka.ms.mff.cuni.cz [195.113.20.131]) by popelka.ms.mff.cuni.cz (Postfix) with ESMTPS id B0B5069650; Tue, 3 Sep 2013 19:48:40 +0200 (CEST) Received: by domone.kolej.mff.cuni.cz (Postfix, from userid 1000) id 8A6055F822; Tue, 3 Sep 2013 19:48:40 +0200 (CEST) Date: Tue, 03 Sep 2013 17:48:00 -0000 From: =?utf-8?B?T25kxZllaiBCw61sa2E=?= To: Will Newton Cc: Siddhesh Poyarekar , Carlos O'Donell , "libc-ports@sourceware.org" , libc-alpha Subject: Re: benchmark improvements (Was: Re: [PATCH] sysdeps/arm/armv7/multiarch/memcpy_impl.S: Improve performance.) Message-ID: <20130903174840.GB2028@domone.kolej.mff.cuni.cz> References: <520894D5.7060207@linaro.org> <5220D30B.9080306@redhat.com> <5220F1F0.80501@redhat.com> <20130902142037.GH3273@spoyarek.pnq.redhat.com> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="IS0zKkzwUGydFO0o" Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.20 (2009-06-14) X-IsSubscribed: yes X-SW-Source: 2013-09/txt/msg00022.txt.bz2 --IS0zKkzwUGydFO0o Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-length: 1487 On Tue, Sep 03, 2013 at 02:46:13PM +0100, Will Newton wrote: > On 2 September 2013 15:20, Siddhesh Poyarekar wrote: > >> The glibc benchmarks also have some other weaknesses that should > >> really be addressed, hopefully I'll have some time to write patches > >> for some of this work. > > > > I know Ondrej had proposed a few improvements as well. I'd like to > > see those reposted so that we can look at it and if possible, have > > them merged in. > > I already have a patch to do multiple runs of benchmarks - some > things like physical page allocation that can impact a benchmark can > only be controlled for this way. As I mentioned above I'd also like to > get graphing capability in there too. Beyond that it would be nice to > have a look at the various sizes and alignments used and make sure > there is a reasonably complete set, and to make sure the tests are run > for a useful number of iterations (not too large or too small). > For alignments do you want existing implementation to take a) 0.031s b) 0.080s c) 0.036s If you want to get your implementation accepted pick a), if you do not like ACME implementation pick b), otherwise pick c). I got those numbers by 'benchmarking' memchr with alignment 15 and size 15 on ivy bridge. (benchmark attached.) Current memchr implementation has separate branches for loads that cross cache line and those that don't. For a) addresses are of form 64*x+15, for b) 64*x+63, and for c) 16*x+15. --IS0zKkzwUGydFO0o Content-Type: application/octet-stream Content-Disposition: attachment; filename="memchr.tar.bz2" Content-Transfer-Encoding: base64 Content-length: 8138 QlpoOTFBWSZTWTHdY0oAKBp/////////////////7//////vb/9W/vz3/f/9 fP/+/v//4Bs/HygDRoRQBKAbDKoqqiCCCCIkqQgCRCChESSAAAFACkpJAoKU FYz9VQABMTaTAAmEwA0AARgmBNoAE0wIwIwjGgE0YmRk0MBMNTTJ6RgAm0Jg RpiYhkwJoyZMAQAAaGgA0AAAABpoABoAAAAAAA0ANGgAANAAAAAMmRoAAAAA aGgBAABoaADQAAAAGmgAGgAAAAAADQA0aAAA0AAAAAyZGgAAAABoaAEAAGho ANAAAAAaaAAaAAAAAAANADRoAADQAAAADJkaAAAAAGhoAEUhAgAQACJtAVPy ekxEybQnomTGhD1Se1TyeqbTEzU8qeymJmowYpqb1T0bKTPSPUnmk1PU81TZ qjeqD1A9QPU/VPJN6o9TTJ6gPSaGNT0R6bUESSmiaaJ6mmTU2mh6lT/TKeqe VP0p+jJkmo9TeqeTTU/VD9U9Mnop6nintSeSH6p6J+1U9Q8o/U9UyH+qn6Se iekHtUGGppoyBoaekepoaPyp6mhofqmTaJtRoNNGQ0M1NhueM/PfQdlDKfln mP47ThQ2HPzHmPAfrmnltmwNmMBjGD5DGmA8eObBS8ARjBC8xgwQiEGDGMGD BwDBynPQ3TptaLRmNBpWNTrajfa2Br1mtmM2BueU1Vuva2sNpJ32Gu5wNTDD A3mG55TQKmGHfCxk5+u5f3XuP9b7vh5Tx3PbOu2etdq6btXou1c53LHLGOUu zOW8t03G2NU3A7mKjfawNZgTlOhrYa8zU53I4K2+MO2w6TjdlsZDfahk2smr K32saD1HbamBm3NzDJk5mTQecydxraNjDeeayZNbJwvIcLRyvM1GbjbEtZ8D JmzdDDJm1Os3DCJWwyQhhhhhWtrxtGt1XieD+Bm7T3dwda2vuXhPaOk9a8J1 nvmz0XaGjC4G+miGgT6esSdSjU2MDIGtgZPqodm6wo64Dsbo13YGJsaThw0G bVDSbXDzUK2sMFG2ynVW5MLha2+wFbD5L8Gies+D5PMrqfjy9nqvHgKsT/NJ SK3Tm6gHMqVmGV9rmH6r6LtPvfyNYYg2xljOD76wxAsLQEiXRIBcQxQdQFgx h0DmCYLicHkCaIaTAAjuOMeB5z0nrBqHrGE4trDy36rR/KakFCSvXMNja4Gd O6D2oeQ963KKJkbX4fK8513Q9i43wXCPpuXCAYGT8RzjRJo/uuR1WbDRfDdZ 17APZOlmZQdyx+c8je5mEBCRHZaKQAIgHIwCgch/H954WrrNYBhanK1Nbc9O x7tuZPnvsgm32nQYQ8JmG8/nMgoEO0y+sx7BoHps3ngQhyWOgwJ6D/K/3X7r 2D6T9t/+P8bc33mvlPzmn4rCmZjXYfBd1l6TrPGbGjY1sgLGEDwux5v4R+u/ rNYCHUYImJgKAYGII0wBETfsFFaYCsc1CkpCIEYMQi00MYhSDEIJ9A8k/CCz 6ti3BAS+wDGwNq2QkzYe9amYTCTYEw5wURJhCGhgaNTTGMYxCAN92QoFuCN8 IEjc00DTAB7SPtZdEAKaabzBQctgiZTBT84IqJZiKXmmlbmKgMgxigKSIc9i FMACRCMEJB37EKYsixgKdy01uaaQQjBO+YpTBAD1ma2bKxgglDhYNmmmDGmw GY+G0Al9ipmPwQp+vcDQmkxaYiBG5pjTGkI000NA4XC7ds3mMY3BnscxxNA5 Nx7TyTyZbi3w2EIgfovug5oeI80Kf1H3j47TfbnZbPv34DQfoNz9Jn9FseC1 s+kwBkbGF0AZwO6hiI0tOUTglGp/Rq7+prtD5MgNl44y3Xe3WobH2reZNHyQ 41gOw0Wh1mLrsCMQY+expwBB6wYBHAMlowElkyE/EYUNZ3nTfQfRZvGZg0eI yGsYZM2TUyZtHnOR3novVuADF+Q2vnu81AjVwmAZDjeS5OM4sTLku+1YW5hc TJQ3WB6jlfKfJGjvMNEIDjdkzZruhznoP4o0EgbOG2M39NDtm4e6GbbJ9uMu wH5CE2aHHYEOxb7J8wflhviXIUBDhtrDJ+E+uYeli8CHb/eqa3QHXPXsB6xv sBHrGG9WuzDN+nhJ7bQbmBJh0GSh4VGSN9gTaYC+EP2gh7V4zJ65o/Yf/D/z fivTfBf01tEEE4FRbizEuFYHJBHZGUIccoMDiBgcIJiZCcEkgANJkCgQVDiB EOO+W/0PzgvBy2IHygg8171oHjMfQCAm0CAD+KDHvwiAUhH4Ybpznqx9+7Z5 D8V7JwuYwHisYxp8tCldkPuWnx2DdG+NJ2D3DvXkvReg/FfpPxHI5gDrMfNC CD1rjZLDJkAnDetWQG06rtO0O0w7LU1MnvXVbWtsamxsahe9gN1gV798533v HsHs34LY9ywiSYBNq+3+B7O86z5j+yHG573DvIyMjIyKrgEROVC7ZC+aw5nM 6GTpOkzampm1NTJqaM2oQ94/iPotgcW7aBqAF9gwIIVB8WILUEPAb76DsjsI cVhhsbHtXivtixWpqBsYB+AwI/rhqYRwuF5L3j5bR/fYf1WwbGb5j9Azhhej pMgHXdZ5jD6i/caOhgag/O1AbULmHIwSYQsxDYYPxGdex0XOIHAyOU4W/umm w2GkJuoh4Ic0ZMDD2yJ6iyBubWHhDJuaISYeW2bDcN1NzQhFPUPbv1j57/u/ 4PoPmj0XgPbCarR7wOzaIezoww1PUcy5fjMB/TYRPTfpP13++/JZtyHuCIYm IB4vbPZuMcjzupnGVlQYGYXeVonRgkz5XTiXJqs8p8oJH5dX9b5h5kp7Vdt4 vEVVYflZQ/0v7X7HyPTTV/30dvpK6BqFaEzi21utI1aXigtAqgDbRAqXo3SS bi9+VdftgmDQp0YnVQLDZtImK8FVV4JJlkubm0uw4MWCkZfKlXpbDVBINoDV 5vecdlGeNyZD52BXWNV4Tw3hvRZs2Yye8YZs2pqd9k2bmu35BoTRUEZLG+/o OF9i/kvA0ZvHZtj2MIIdowhFjL2rJkLa2sDc3mY3MNGjR/gYei1tTU0axmza mGjYiF9wMlPACH3JA6bgbh6b8R6xrAUo0a3un67ncjjamtvto5WTJhytGphs 3nOfBzRXsQ2QgHTA9s+YG3Lg2HpB4gGEXtR9yH/DZ4LHtgoKbkKdhpg0EbKH eD6poLwx/BaQ+iwAbQQDkOQAeaPXD8xoaG+J+e5Boeg67TZgZYCGq08BjB3o PCCwAdcE9THLd4DwQ9sHwh7pvvUB6TX2z9k4w8Abwwwgfswiu12DnWaHGhsY H57A0fj67V79iBqZMIX3rd5taN9rZPmUZrEIEDNvN4aM3SDwHSZoWNzr/DaI bbjfzw/caPMeRjX/6GRwtdGQ+EzG8w0ampkzcT5DQP4fdByg8ACQWOd3whFd scFw1IXgO43HzxyNTIcjDA1lAZsNZb70Ch4IBynqT7Sd4GjA98EOXCowMP5I I3deRQgFCFm8lLcERjqlKF+1C3gIsE8+pQNARIjBgw/XNSB4AYQrwXvR8F+4 cPMV/kMFJnWEKQk7/RVm6kXwveplZ0SrSl5avhhAuLJfx6OI2nEDS4jDGL8H I0sqhKI7d9mrNvQURTan8J18J4NlioFdUhdKAQ8Pq/Dzt9qdW9jek9J44ch9 T3ZB4kWny4T1rt4V+rAxHPcD+66zsMOu3g+iwKf6A68P8gf+Q5bebm8w3n2h fcj0w02mEH7EcYCPkMRYKRgREX2b2eg3g70MA8RyBcw/AN/lrWoQLFRjVV6U PjfUOYHF9+8DiBiD5gcd4rm6ebfcQdw4wmk7zzY5/OLz4HPhCQU9eVR8Wxv7 yvchth3jLnvpBQM2fBkOU1OcMnowZzQRB+lvvVORh50ODuNbWg7uFGXLgKts KqwimLFaSKGiku80reWwm3J2tVJgCBTSYqqoYcUGAYaaxUFJBlQKhLsMPk3q z8GHS1GnGFgd66kD8ib5f7zleB/BuOs7DqtwB0nOrrAQwEAwEnE4nkBfPTSQ JJJBkCSRkkhCQSSYAvh7F4AvsBVXUL3bCEQh0LmSvfd51d9oAXguV1W80U5I QFMzzma6K5NWOLw20eudNvPHasCQN0kiSJgDCvLcmRTDVa6GYxTj/CJAdOzS 76UomDqz43986VGv41wZwDBygCVQxaoCQCExlEqGbT036sNo2yPdMfWj6Ldq 8keMHTzXRHLZDTGkH7PNn6vaNqOpeq9e0NWUG7Ahq7gC261AauTQTOia4Ze4 gf26TriEw1ukluNoBdpB1Ydsh9R+OHTedyWHumLuzDbAmkl5cwkRMyYVbVZh ZrAamYCxJcq8WYKpYGhw1dgqcSPEYS4jHqONdUnNtrHbkBLrtfcDAVYs4YRw q3BIhCQGkBJaOfasZpwtNN2jYbcry6M5dW5MIVw0yZMFAaEBeAm1Q1Ft8CZZ KcpTAka7+/XsJeakfcwhHatC4yFY5+GQTOHAw9e53r20wYYcpJDLRoNbDBAH U2HumjLsHcGYzfdjqrjCN14A7x8xoeW2OLGcoTvgh7cMe+8jb/E/C4t7YqwB 1tvT8QKvu97I72XsZqdZK5nCwaDXugzk09StfVcDec3uXmGWa5YvT1O25UJj a9y/KcQZDHk/n/09g/5vQeRshT3aHEdwhHr3nuBshc3mTD+VkbGjNoyYGpoz ZsmGTUzQoDNkwNes1Oy2NzA2tbDJsELVZITQoyZtf+JtbzRo2DUtzDRowNb8 IHsA0PcPfvtnr3xgfUdR1YOIe4DXDtX719q98+M98HTDCmk+kDYCB/WG5D/0 P5n5Ye0Dbvp3EHlh1Qd89sr0Rj5YX3tA/MD3Y8sdyrqvpHQe/aeAgWbPiAGK Id24UMgOqFn+14j5weQHvgygdl7t2GB0gxBpt99u9a5j7EPWBn/wMNQNjIeD sX8xm/2H7DJufNfiP8VNporJ6D69k7rAQ/bCTrhUyaD/1ZBJ9VufotHovZhI e5fnvguw3nI/WfvvxnyB9c/yOAbnTZvvHmtTqNTDD47ofvNTWwhidNyu6w/f CoPXuyMh2m+/MZsML7Jk/TeW9J2GjjCSFgVhD0GB+aw9i2Bzlee9r8DgaIUO 7DUOFPRd08kM0POfod08bkuw40PJbO0A9K74NF8cPsFbUIe9exRH9lyvlvZM g/aYvwww854juO+0U133DIwjVvenrPUPMdIHQtPbod677qu4DgwX3GGhyuV9 9qM2Yw/QCXdvTfaMIQ4mvbCp54cYcSHJC86bUXPmt9zMMOyGu9FDqDw2L9Qc d1HO987AaZrXnhOUHRBgaP1obIVmuT4AVoO0dmwQPF7AfXvSc0Nu871UDohe D2Go0HgOoib1g+I7gQ2p6/sehaWtrK9yZQOi7DiYNmwwY0hw32TrPFY7sYxj DJrVDsGBCQhjG598P5rIGH8xrd1h2PSdtm/EXVG1uGTc+G4VsbWsQmeQQxAF hC+OflqSXVJM1LhTG/qt9zNbNgcw5uBm7wf3gHfMGIRjGIcF65obAxWIQQgM EOI2HMG54dAQeK54nyR0uhKCESRhpgUEMpHrle3hk/LU8weSruA8V0y5rA2R JusF5aUU4TRL4GzM4qXxoq+V5oZL5qWuZ3gDaAuWOgmOIMRgpAgrFLMHeg6w voLI7hQgVEkKc8NYYruQcIWxieoDMYf1sZK1ga2IO5ddmzkxtMMA655D5Y1m wYTOSEdJAJcg6m4VzFMtobDpO6SdIbamTrqcTTdVrHIMpPwINoIIE4VOxexZ LtNcMhkphDYZuJxumobphdjMCl5yMMWjLGobzlSjfcTIbQTMzB1wyv+pumrt hSIhdW+dPYyLlELst4by7QgnOCtyV6gQ3MpGZqTC9BzLaBgQSsfpsSCvGKXx 0xvORUhIbkoAswkjAZGSm2tB1UPGdV798kPfuz4bD75gdlh338N8Rmh0WFaM PUYH773LWIfmtiFj7BqZIQ1tSHw2ELWjY2DNhrQow/IbHxn8Z8Z2ROK/o64+ yeZsMwZMIayG+9ccdkOm6JBDDkrQ8jmvWcshfQ69MzcOCEMgISEMDnYQxziC ta2ZNkyRWpLyHjvLUDz2EKZpvZv9BNI64OWnMUOseycbgee1CuEINkOBWvXW Bi2G1tLL2BCx0MIZdWJtbhcEPZOkr+ouVaeieObD2j7B1/PjYyI5GPusANjt 4ESD399zibXbD2w102hh4QHfvsDiPzXhPXmVekzo43eBwABxA31JKby4wOQX 7BO0MA4sx+G8IVStxBbJkHdw0mXCNzpIBiC+rA5bz877hzI2/H87qd25Q1s7 fcAb8qgiHQGN0LyRVNVNh2ELRTURNfagUrdYDukTZDC7FTNkjeVxBKStJBwK SBk4StkSuGxQhhidg1yQcZxlsG0bAqbUhtBsUk4RDkvbg5cQpEp6p342Fd8N PCNVTOIEZcMo0AX1zoURzg6jzQ4FbTMN9cy3KJRtGRo/kzK0LmAtNcU1LUGs ZgNee+TczsMUEMApGdhsbF1UMIxIJS7sAm2NH/iF+pAziYA3eoye+RdIYUQs ygY0kjyVMaZNxTeLGDOZmscwN+YzFbQIqYQ7R8Bu3Axjas2pkozGjig1oEMT qJIDWA5omBvhlvbAQM60SB0Ni5y8BhhC84kV3sQFBA6nCcTLZDCGm6Y4Ba2g cWTe0XnhvDDKya6OkIZQk/GGQN0WyTxWjvvw3AKV3noPQb2HE1JN4qGMbgcY wsLIZC6wBIDZCeuwqFAXKNBlrhactz9uKTfPJs2jCQZBkDqh9MrrbjDAw2OS 8DDDfUs1nOgvWPf4wbmobQTWdQ29t3gtUyPFOR1R60LFOI/ZA2F2hvOUPDDb D6IdW8Z5b+4OWQfKfv0sCbwYiaJynK3+R6wfCtp6DrRkjJQNQghIEqkaIKWT GFAhSAiEpIrZN3IeIvWCqchkNrqvKeOhMd9csHJXhOc/UmQQm2DP42PdvNeG 8N6271cexfTh5SHKdx7tTmB4wc5soWD74KRD/4PICgRMIp3TxW8/1w6Ir7Z9 s80eyHxn3LRmww0ZMMnAPymxraNrUwMMA+9d5+Y+8CgD57nD/9w2x4zqhfHt WMQuNvJH9A55fG+pAIhfDvGNmAWGO7esbClmMQ/WcAY3dOeFzfBfnwKCBAvO Rhxj61xhoaBpNGb1QWNjWw/LYd1kDRoNHuR3X3QSf1GxE47UyVhX+PgdJ1/2 95m/F86bruR3XB8jpXOh8QNWTaOmO89Uz6T/h0P2fn1u4N4bW8MmGTCERzO3 cQTfC0ncsaZnUcbgdRvBocTcNw8N54ej6rhan+Lh67gDM6brUf0nC+9rcwc4 O4f5v4X/+5XUFcwabAc8PTD+DgdDwO07T6TDeG8Ok4QBwv3RD1WA2EPREP3k Y713zqtnG8kNJEsPsgxBwA7Ae9dAwDWD9i4NV/HrX7L3D+e98+K9a32p/tPF fUbGxsbAamt85wM3C0YcIbDChvPCd4Zt5/AEM2Yfef0HfZjxWEKg3HpOyO/h amHjOJmPaPHfWVv5LV4o7wfJH6jRrQ5LJzvtHwQ9w0a3IyQ6181hoHJDgf3L gxvADUH3H3Rw2DI77+xsqrc6HE5h2zTQ0NNND812WnQf7HpjthDs36pwu/bg zQ1wxoSC/MPdsnqnI6GbedkZOR1wm7LU/jBfBzDhc74jcEnt3Vag0gtdlo7b Uj6D7d1QseWEDocPnXj4YaTc7djTTSHBY4GMdJpwOU3mmw9YwDY+61gwAwEA 6roZDmCxyPPbqlcjUwzeBm0agrDUbho3O22N5hhvN5mPGdx9c6T81k9e2tgb rChiee6rcUAvP+bdcjecj69zDa4H7WF7kKgPqWuJ/lZDqIVD57gZPuPtPqvV uRA3nxHxXO1PCCtK287r95+S/4H9F1217V7V+2/5xOEI1O0wMnmsAfpMB5Qw UxvVuUPbsbwN9inmMY/NZsn6bJo+0ZMn6zJrYQmNAhU8V4jje2eM/XXIFR2B +AROiWHOLuSKcKEgY7rGlA== --IS0zKkzwUGydFO0o--