Files
rocm-systems/tests/workloads/L2/mi100/SQ_INST_LEVEL_VMEM.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

43 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_VMEMSQ_INST_LEVEL_VMEMSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000880581880586335544322560083264640x00x7fe7ed804180104857611078382141797149612075537965584008120755382084044861207553820873136512075538208839027
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00288058188058632768256002424124800x00x7fe7ed83510040961171811499390812075538223157086120755382234632291207553822346978912075538223481179
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0048805818805864194304256002424129280x7fe8f94cc9000x7fe7ed83514052428810299796131842499612075538223533306120755382237496281207553822388962712075538223893285
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0068805818805864194304256003624136320x7fe8f94cc8000x7fe7ed83518052428813515734172999473612075538223964246120755382241406661207553822438994512075538224460459
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0088805818805864194304256002824140800x7fe8f94cc7000x7fe7ed8351c052428813539810173303646812075538224486357120755382246734641207553822492850312075538224995824
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00108805818805864194304256002424145280x7fe8f94cc6000x7fe7ed83520052428812128656155241206812075538225026921120755382252117021207553822534418212075538225347898
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00128805818805864194304256002424149760x7fe8f94cc5000x7fe7ed8352405242889985762127817886812075538225391098120755382255733011207553822571554012075538225718937
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00148805818805864194304256002424154240x7fe8f94cc4000x7fe7ed83528052428812792480163743223212075538225797784120755382259660991207553822609697912075538226100466
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00168805818805864194304256002824161280x7fe8f94cc3000x7fe7ed8352c052428813498189172776131212075538226150479120755382263324981207553822659249712075538226634118
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00188805818805864194304256002824168320x7fe8f94cca000x7fe7ed83530052428814083761180274324012075538226661048120755382268425761207553822709521512075538227136221
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00208805818805864194304256002424175360x7fe8f94cc9000x7fe7ed83534052428811635924148933217212075538227160266120755382273523341207553822748641412075538227489959
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00228805818805864194304256002424182400x7fe8f94cc8000x7fe7ed83538052428811995112153530572412075538227539541120755382277113731207553822784417212075538227847573
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00248805818805864194304256002424189440x7fe8f94cc7000x7fe7ed8353c052428812015895153809157212075538227910180120755382280809711207553822821377112075538228217441
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00268805818805864194304256002824199040x7fe8f94cc6000x7fe7ed83540052428814002035179231312812075538228267895120755382284408101207553822869808912075538228764748
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00288805818805864194304256002824206080x7fe8f94cc5000x7fe7ed83544052428813521213173068671612075538228791608120755382289724881207553822922960712075538229295865
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00308805818805864194304256002424213120x7fe8f94cc4000x7fe7ed83548052428812233259156595367612075538229321473120755382295121661207553822964384612075538229647318
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00328805818805864194304256002424220160x7fe8f94cc3000x7fe7ed8354c052428812416727158933452812075538229695568120755382298657651207553822999712412075538230004622
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00348805818805864194304256002424227200x7fe8f94cca000x7fe7ed83550052428811839102151542728012075538230063271120755382302320031207553823036512312075538230368699
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00368805818805864194304256002824236800x7fe8f94cc9000x7fe7ed83554052428813344902170816614812075538230419112120755382305833621207553823084144112075538230907961
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00388805818805864194304256002824243840x7fe8f94cc8000x7fe7ed83558052428814069899180093597612075538230932837120755382311251201207553823137231912075538231439158
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00408805818805864194304256002424250880x7fe8f94cc7000x7fe7ed8355c052428812674288162242710412075538231463704120755382316470381207553823177679812075538231780222
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00428805818805864194304256002424257920x7fe8f94cc6000x7fe7ed83560052428811064786141637496412075538231830606120755382319971171207553823213519612075538232138818
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00448805818805864194304256002424264960x7fe8f94cc5000x7fe7ed83564052428811800008151045904412075538232200433120755382323665551207553823250031512075538232504017
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00468805818805864194304256002824277120x7fe8f94cc4000x7fe7ed83568052428813482638172573119612075538232552257120755382327227141207553823298015312075538233046946
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00488805818805864194304256002824284160x7fe8f94cc3000x7fe7ed8356c052428814347090183638580012075538233073816120755382332542321207553823351135112075538233577893
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00508805818805864194304256002424291200x7fe8f94cca000x7fe7ed83570052428813278725169967783612075538233600805120755382337791901207553823390703012075538233910441
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00528805818805864194304256002424300800x7fe8f94cc9000x7fe7ed83574052428811793425150947639612075538233959492120755382341318291207553823426558812075538234269148
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00548805818805864194304256002424307840x7fe8f94cc8000x7fe7ed83578052428811609859148604946412075538234329951120755382344945471207553823462814712075538234631922
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00568805818805864194304256002824320000x7fe8f94cc7000x7fe7ed8357c052428813418552171762391612075538234679871120755382348574261207553823512398512075538235191091
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00588805818805864194304256002824329600x7fe8f94cc6000x7fe7ed83580052428813893440177832401612075538235217901120755382354027041207553823566142312075538235727798
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00608805818805864194304256002424339200x7fe8f94cc5000x7fe7ed83584052428813150677168335402812075538235754378120755382359315021207553823606014212075538236063442
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00628805818805864194304256002424348800x7fe8f94cc4000x7fe7ed83588052428811094429142005170412075538236114167120755382362796611207553823641758012075538236421087
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00648805818805864194304256002424358400x7fe8f94cc3000x7fe7ed8358c052428811713009149926552812075538236482291120755382366462191207553823678077912075538236784122
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00668805818805864194304256002824373120x7fe8f94cca000x7fe7ed83590052428813700817175368960412075538236832832120755382370020581207553823726413712075538237330878
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00688805818805864194304256002824382720x7fe8f94cc9000x7fe7ed83594052428813526094173135606012075538237355393120755382375364561207553823779645512075538237865642
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00708805818805864194304256002424392320x7fe8f94cc8000x7fe7ed83598052428811563245148002545612075538237888724120755382380951741207553823822893312075538238232533
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00728805818805864194304256002424401920x7fe8f94cc7000x7fe7ed8359c052428813240486169473317612075538238282236120755382384649331207553823859309212075538238596650
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00748805818805864194304256002424411520x7fe8f94cc6000x7fe7ed835a0052428811290351144517570012075538238657914120755382388190111207553823895485112075538238958222
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00768805818805864194304256002824426240x7fe8f94cc5000x7fe7ed835a4052428813622054174356479212075538239010770120755382391959701207553823945740912075538239523803
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00788805818805864194304256002824435840x7fe8f94cc4000x7fe7ed835a8052428813556919173528648012075538239549912120755382397289281207553823998412712075538240026578
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00808805818805864194304256002424445440x7fe8f94cc3000x7fe7ed835ac052428811832430151456673612075538240048999120755382402302061207553824036412512075538240367501
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00828805818805864194304256002424457600x7fe8f94cca000x7fe7ed835b0052428810496991134353900012075538240416622120755382405849251207553824072348412075538240726989
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00848805818805864194304256002424467200x7fe8f94cc9000x7fe7ed835b4052428813097079167637815612075538240787161120755382409481231207553824107756312075538241080947
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00868805818805864194304256002824484480x7fe8f94cc8000x7fe7ed835b8052428813517986173026500412075538241129347120755382413054021207553824157516112075538241642901
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00888805818805864194304256002824494080x7fe8f94cc7000x7fe7ed835bc052428813255976169679863212075538241665904120755382418463601207553824210139912075538242168749
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00908805818805864194304256002424503680x7fe8f94cc6000x7fe7ed835c0052428812125376155197462412075538242194186120755382423783581207553824251051712075538242514221
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00928805818805864194304256002424515840x7fe8f94cc5000x7fe7ed835c4052428810217239130777038812075538242563983120755382427330771207553824287355612075538242877005
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00948805818805864194304256002424525440x7fe8f94cc4000x7fe7ed835c8052428812568696160883868812075538242937738120755382431143551207553824324571512075538243249337
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00968805818805864194304256002824542720x7fe8f94cc3000x7fe7ed835cc052428813534572173242870812075538243298849120755382434689141207553824373451312075538243777338
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00988805818805864194304256002824554880x7fe8f94cca000x7fe7ed835d0052428812879972164865310412075538243804519120755382439813921207553824424091112075538244309297
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001008805818805864194304256002424567040x7fe8f94cc9000x7fe7ed835d4052428812109424155002142012075538244335425120755382445186701207553824465066912075538244654088
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001028805818805864194304256002424581760x7fe8f94cc8000x7fe7ed835d805242889106859116564227212075538244702728120755382448730681207553824501866812075538245022282
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001048805818805864194304256002424593920x7fe8f94cc7000x7fe7ed835dc052428812629362161655352812075538245083726120755382452500271207553824538090712075538245384475
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001068805818805864194304256002824613760x7fe8f94cc6000x7fe7ed835e0052428813896745177872123612075538245433767120755382456013861207553824586202512075538245927374
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001088805818805864194304256002824625920x7fe8f94cc5000x7fe7ed835e4052428813948159178534303212075538245951358120755382461468241207553824640442312075538246471515
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001108805818805864194304256002424638080x7fe8f94cc4000x7fe7ed835e8052428812242388156699080812075538246495369120755382466749821207553824680730112075538246810806
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001128805818805864194304256002424652800x7fe8f94cc3000x7fe7ed835ec05242888572301109723533612075538246857843120755382470332201207553824717178012075538247175744
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001148805818805864194304256002424664960x7fe8f94cca000x7fe7ed835f0052428811571011148102643212075538247236717120755382474004191207553824753561912075538247539269
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001168805818805864194304256002824684800x7fe8f94cc9000x7fe7ed835f4052428812957802165851004812075538247587649120755382477588181207553824802793712075538248094992
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001188805818805864194304256002824696960x7fe8f94cc8000x7fe7ed835f8052428813777803176353017612075538248119047120755382483018561207553824856121512075538248628183
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001208805818805864194304256002424709120x7fe8f94cc7000x7fe7ed835fc052428811942537152874196812075538248655815120755382488384941207553824897129312075538248974777
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001228805818805864194304256002424723840x7fe8f94cc6000x7fe7ed836000524288675573686470033612075538249028888120755382492029721207553824934121212075538249344775
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001248805818805864194304256002424736000x7fe8f94cc5000x7fe7ed83604052428812578793161011766412075538249404887120755382495668111207553824969689012075538249700516
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001268805818805864194304256002824758400x7fe8f94cc4000x7fe7ed83608052428813526393173137925612075538249748866120755382499240901207553825019384912075538250243044
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001288805818805864194304256002824770560x7fe8f94cc3000x7fe7ed8360c052428814060144179965710812075538250267330120755382504488881207553825069832712075538250747201
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001308805818805864194304256002424782720x7fe8f94cca000x7fe7ed83610052428811510644147342666412075538250770425120755382509493661207553825108488512075538251088546
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001328805818805864194304256002424800000x7fe8f94cc9000x7fe7ed836140524288694873788938460812075538251136515120755382513080841207553825145288412075538251456249
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001348805818805864194304256002424812160x7fe8f94cc8000x7fe7ed83618052428811630910148878057212075538251517773120755382516781631207553825181208312075538251815417
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001368805818805864194304256002824834560x7fe8f94cc7000x7fe7ed8361c052428813080371167433223612075538251863696120755382520389621207553825230616112075538252356131
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001388805818805864194304256002824849280x7fe8f94cc6000x7fe7ed83620052428813246453169557224412075538252380557120755382525612001207553825281863912075538252865789
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001408805818805864194304256002424864000x7fe8f94cc5000x7fe7ed83624052428810838034138726469212075538252892178120755382530736781207553825321191712075538253215649
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001428805818805864194304256002424881280x7fe8f94cc4000x7fe7ed836280524288605457177498187612075538253268537120755382534357561207553825358663612075538253589974
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001448805818805864194304256002424896000x7fe8f94cc3000x7fe7ed8362c052428811577572148201844412075538253669162120755382538307951207553825396439412075538253967977
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001468805818805864194304256002824920960x7fe8f94cca000x7fe7ed83630052428812333488157863559612075538254016567120755382541957541207553825445735312075538254505626
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001488805818805864194304256002824935680x7fe8f94cc9000x7fe7ed83634052428813717317175581284812075538254529591120755382547074321207553825496807112075538255017588
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001508805818805864194304256002424950400x7fe8f94cc8000x7fe7ed83638052428812969537166005017212075538255045770120755382552250301207553825535510912075538255358451
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001528805818805864194304256002424967680x7fe8f94cc7000x7fe7ed8363c0524288495205963393622412075538255406120120755382555746281207553825573270812075538255736053
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001548805818805864194304256002424982400x7fe8f94cc6000x7fe7ed83640052428811531501147593021612075538255797457120755382559634271207553825609910612075538256102975
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015688058188058641943042560028241007360x7fe8f94cc5000x7fe7ed83644052428812754109163250436012075538256151405120755382563259861207553825659862512075538256646635
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015888058188058641943042560028241022080x7fe8f94cc4000x7fe7ed83648052428813766111176199541212075538256669317120755382568491841207553825710902312075538257160049
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016088058188058641943042560024241036800x7fe8f94cc3000x7fe7ed8364c052428810793443138152872812075538257184745120755382573658221207553825750390112075538257507525
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016288058188058641943042560024241056640x7fe8f94cca000x7fe7ed836500524288417010753371042012075538257558009120755382577290201207553825789622012075538257899764
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016488058188058641943042560024241071360x7fe8f94cc9000x7fe7ed83654052428812288568157293646012075538257960477120755382581264591207553825825925812075538258263209
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016688058188058641943042560028241098880x7fe8f94cc8000x7fe7ed8365805242889450603120961373612075538258314084120755382585010171207553825876949612075538258816097
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016888058188058641943042560028241113600x7fe8f94cc7000x7fe7ed8365c052428813599670174072758012075538258841955120755382590235751207553825928405512075538259333368
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017088058188058641943042560024241128320x7fe8f94cc6000x7fe7ed8366005242889689906124023473212075538259357623120755382595410141207553825968453312075538259688158
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017288058188058641943042560024241148160x7fe8f94cc5000x7fe7ed836640524288368674247206444812075538259735766120755382599046921207553826007941212075538260083112
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017488058188058641943042560024241162880x7fe8f94cc4000x7fe7ed83668052428812946752165717359612075538260143434120755382603067711207553826043685012075538260440356
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017688058188058641943042560028241190400x7fe8f94cc3000x7fe7ed8366c05242888024530102719792812075538260490258120755382606598891207553826092404812075538260971433
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017888058188058641943042560028241207680x7fe8f94cca000x7fe7ed83670052428813433917171955523612075538260993153120755382611867671207553826144724612075538261496819
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018088058188058641943042560024241224960x7fe8f94cc9000x7fe7ed83674052428810615056135870131212075538261526083120755382617093251207553826185060512075538261854323
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018288058188058641943042560024241247360x7fe8f94cc8000x7fe7ed836780524288323629841427911212075538261902463120755382620773241207553826226020312075538262263905
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018488058188058641943042560024241264640x7fe8f94cc7000x7fe7ed8367c052428810341404132362322812075538262325689120755382624893231207553826263076212075538262634553
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018688058188058641943042560020241279360x7fe8f94cc6000x7fe7ed836800524288417031853371571612075538262683034120755382628496411207553826311652012075538263164268
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018888058188058641943042560028241296640x7fe8f94cc5000x7fe7ed83684052428813329490170618072412075538263188533120755382633689991207553826363043812075538263652976
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019088058188058641943042560024241313920x7fe8f94cc4000x7fe7ed83688052428811674332149436585612075538263695064120755382638534771207553826398739712075538263991044
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019288058188058641943042560024241336320x7fe8f94cc3000x7fe7ed8368c0524288364930346704486812075538264039214120755382642096361207553826440147512075538264448725
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019488058188058641943042560024241353600x7fe8f94cca000x7fe7ed83690052428811043812141363288412075538264487036120755382646507541207553826478707412075538264790450
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019688058188058641943042560020241368320x7fe8f94cc9000x7fe7ed836940524288285158536493377212075538264840082120755382650232331207553826533971212075538265390285
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019888058188058641943042560028241385600x7fe8f94cc8000x7fe7ed83698052428813543167173345654412075538265413829120755382655985911207553826586115012075538265907897
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020088058188058641943042560024241402880x7fe8f94cc7000x7fe7ed8369c052428810611757135826156812075538265933394120755382661147491207553826625234812075538266256244
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020288058188058641943042560024241427840x7fe8f94cc6000x7fe7ed836a00524288348635744627080812075538266307239120755382664736281207553826668402712075538266730656
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020488058188058641943042560024241447680x7fe8f94cc5000x7fe7ed836a4052428810919982139777742812075538266768356120755382669310661207553826706946512075538267073102
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020688058188058641943042560020241457280x7fe8f94cc4000x7fe7ed836a80524288258221433057000812075538267120971120755382672950641207553826760242312075538267623866
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020888058188058641943042560028241477120x7fe8f94cc3000x7fe7ed836ac052428812550142160639980012075538267665363120755382678245031207553826808914212075538268137551
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021088058188058641943042560024241496960x7fe8f94cca000x7fe7ed836b005242889872914126362368412075538268164691120755382683419411207553826848466012075538268488152
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021288058188058641943042560024241521920x7fe8f94cc9000x7fe7ed836b40524288345002644156400012075538268535851120755382687048191207553826893313812075538268979545
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021488058188058641943042560024241541760x7fe8f94cc8000x7fe7ed836b8052428810405505133188793212075538269020501120755382691950571207553826933665712075538269340516
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021688058188058641943042560020241556480x7fe8f94cc7000x7fe7ed836bc0524288247907031729344812075538269388295120755382695601761207553826989073512075538269937546
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021888058188058641943042560028241576320x7fe8f94cc6000x7fe7ed836c0052428812556680160725590812075538269960929120755382701465741207553827041105312075538270457813
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022088058188058641943042560024241596160x7fe8f94cc5000x7fe7ed836c405242889450258120966226412075538270481617120755382706620921207553827080737112075538270810748
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022288058188058641943042560024241623680x7fe8f94cc4000x7fe7ed836c80524288334342042781830012075538270858397120755382710302511207553827127489012075538271323511
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022488058188058641943042560024241646080x7fe8f94cc3000x7fe7ed836cc05242888853184113324540412075538271363005120755382715277201207553827167108012075538271678211
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022688058188058641943042560020241663360x7fe8f94cca000x7fe7ed836d00524288238887530574614012075538271723244120755382718931581207553827227011712075538272320514
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022888058188058641943042560028241685760x7fe8f94cc9000x7fe7ed836d4052428812274089157109577212075538272345060120755382725265961207553827279315512075538272839940
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023088058188058641943042560024241708160x7fe8f94cc8000x7fe7ed836d8052428810270306131447620012075538272865718120755382730477141207553827322499312075538273228312
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023288058188058641943042560024241740800x7fe8f94cc7000x7fe7ed836dc0524288323088841359837212075538273278134120755382734536331207553827373299212075538273780107
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023488058188058641943042560024241765760x7fe8f94cc6000x7fe7ed836e005242888071992103332010812075538273816595120755382739781111207553827411651012075538274120249
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023688058188058641943042560020241777920x7fe8f94cc5000x7fe7ed836e40524288234930130072413212075538274168449120755382743384301207553827476290812075538274809320
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023888058188058641943042560028241802880x7fe8f94cc4000x7fe7ed836e8052428811425784146243788812075538274833244120755382750217871207553827529170712075538275338954
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024088058188058641943042560024241827840x7fe8f94cc3000x7fe7ed836ec0524288752565396325054012075538275364922120755382755457861207553827568690512075538275690287
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024288058188058641943042560024241863040x7fe8f94cca000x7fe7ed836f00524288342060343788117212075538275738577120755382759080251207553827622450312075538276245769
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024488058188058641943042560024241893120x7fe8f94cc9000x7fe7ed836f40524288374713447957923612075538276300912120755382764662631207553827661922212075538276622910
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024688058188058641943042560020241907840x7fe8f94cc8000x7fe7ed836f80524288230269029475710812075538276671651120755382768505811207553827736850012075538277418990
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024888058188058641943042560028241937920x7fe8f94cc7000x7fe7ed836fc0524288732363493738833212075538277446962120755382776286591207553827792769812075538277974262
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025088058188058641943042560024241968000x7fe8f94cc6000x7fe7ed837000524288321305141124572412075538277996202120755382781948971207553827834945612075538278352865
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025288058188058641943042560024242010880x7fe8f94cc5000x7fe7ed837040524288329843342213468412075538278403529120755382785680161207553827895425412075538279008544
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025488058188058641943042560024242046080x7fe8f94cc4000x7fe7ed837080524288328800642076932812075538279045723120755382792100941207553827938609312075538279389752
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025688058188058641943042560020242060800x7fe8f94cc3000x7fe7ed8370c0524288229839429407456012075538279437461120755382796089721207553828021937012075538280266682
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025888058188058641943042560028242096000x7fe8f94cca000x7fe7ed837100524288478160561203098012075538280290336120755382804804891207553828081072812075538280857700
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026088058188058641943042560024242131200x7fe8f94cc9000x7fe7ed837140524288328275342022042412075538280882707120755382810668871207553828124656712075538281250110
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026288058188058641943042560024242181760x7fe8f94cc8000x7fe7ed837180524288327620741941405212075538281299942120755382814700861207553828194928512075538281970058
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026488058188058641943042560024242222080x7fe8f94cc7000x7fe7ed8371c0524288327223241877458412075538282032323120755382821988841207553828243744312075538282485195
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026688058188058641943042560020242239360x7fe8f94cc6000x7fe7ed837200524288230045529436111212075538282515401120755382826958421207553828340032012075538283449407
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026888058188058641943042560028242279680x7fe8f94cc5000x7fe7ed837240524288326126241734625612075538283482799120755382836678391207553828404095812075538284089276
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027088058188058641943042560024242320000x7fe8f94cc4000x7fe7ed837280524288300699938480997612075538284124582120755382842905571207553828449439612075538284545334
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027288058188058641943042560024242378240x7fe8f94cc3000x7fe7ed8372c0524288421704553977727612075538284573947120755382847483151207553828527503412075538285323470
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027488058188058641943042560024242423680x7fe8f94cca000x7fe7ed837300524288311737339899883212075538285362512120755382855271931207553828575103212075538285798763
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027688058188058641943042560020242435840x7fe8f94cc9000x7fe7ed837340524288229576029380703212075538285821966120755382860017511207553828680126912075538286850768
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027888058188058641943042560028242481280x7fe8f94cc8000x7fe7ed837380524288356196745587750012075538286874142120755382870745481207553828749470612075538287543426
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028088058188058641943042560024242526720x7fe8f94cc7000x7fe7ed8373c0524288314999340327854812075538287569875120755382877489451207553828797550512075538288022676
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028288058188058641943042560024242592640x7fe8f94cc6000x7fe7ed837400524288454101658127999212075538288048184120755382882271841207553828882478212075538288872646
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028488058188058641943042560024242648320x7fe8f94cc5000x7fe7ed837440524288332132142513834012075538288908753120755382890860611207553828935582012075538289404915
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028688058188058641943042560020242663040x7fe8f94cc4000x7fe7ed837480524288231498229635623212075538289428098120755382896071791207553829059181612075538290658324
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028888058188058641943042560028242718720x7fe8f94cc3000x7fe7ed8374c0524288328344042029524012075538290682189120755382908697351207553829140189312075538291471185
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029088058188058641943042560024242774400x7fe8f94cca000x7fe7ed837500524288331912442481824812075538291495340120755382916820521207553829195565212075538292022850
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029288058188058641943042560012242799360x7fe8f94cc9000x7fe7ed837540524288219536328103082412075538292046604120755382922271711207553829296572812075538293032677
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029488058188058641943042560024242865280x7fe8f94cc8000x7fe7ed837580524288335409742940673212075538293071259120755382932351671207553829355308612075538293619818
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029688058188058641943042560020242880000x7fe8f94cc7000x7fe7ed8375c0524288230254029466830012075538293644244120755382938210851207553829499196112075538295062299
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029888058188058641943042560032242945920x7fe8f94cc6000x7fe7ed837600524288332337142532580812075538295093196120755382952711611207553829588203912075538295949147
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030088058188058641943042560024243011840x7fe8f94cc5000x7fe7ed837640524288330781342336778412075538295976829120755382961593181207553829647899712075538296547649
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030288058188058641943042560012243049600x7fe8f94cc4000x7fe7ed837680524288220828428269943612075538296572245120755382967609161207553829763979312075538297707775
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030488058188058641943042560024243136000x7fe8f94cc3000x7fe7ed8376c0524288322770241319570812075538297750735120755382979157921207553829833019012075538298399180
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030688058188058641943042560020243148160x7fe8f94cca000x7fe7ed837700524288230350429474897212075538298431230120755382986089101207553830015898412075538300227548
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030888058188058641943042560020243175680x7fe8f94cc9000x7fe7ed837740524288228987129314580812075538300258766120755383004383431207553830123530112075538301303608
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031088058188058641943042560012243203200x7fe8f94cc8000x7fe7ed837780524288218349427944820012075538301332772120755383015159401207553830195449812075538302022975
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031288058188058641943042560012243240960x7fe8f94cc7000x7fe7ed8377c0524288224608928741605612075538302052550120755383022349781207553830339337412075538303460978
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031488058188058641943042560012243288960x7fe8f94cc6000x7fe7ed837800524288217666827844314412075538303501884120755383036650531207553830445097012075538304518603
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031688058188058641943042560020243301120x7fe8f94cc5000x7fe7ed837840524288264022833802101212075538304548909120755383047292091207553830778183912075538307850656
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031888058188058641943042560020243328640x7fe8f94cc4000x7fe7ed837880524288233240129862046012075538307882104120755383080751181207553830961799312075538309687389
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032088058188058641943042560012243356160x7fe8f94cc3000x7fe7ed8378c0524288220591828228983612075538309710001120755383099083921207553831069895012075538310768398
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032288058188058641943042560012243393920x7fe8f94cca000x7fe7ed837900524288250685932083312812075538310798885120755383109840691207553831326662112075538313335759
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032488058188058641943042560012243441920x7fe8f94cc9000x7fe7ed837940524288247618831696097612075538313378389120755383135485401207553831508469512075538315152115
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032688058188058641943042560020243454080x7fe8f94cc8000x7fe7ed837980524288291449437303097212075538315183433120755383153661341207553832142163412075538321490264
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032888058188058641943042560020243481600x7fe8f94cc7000x7fe7ed8379c0524288337535743195926812075538321519348120755383217021131207553832474610312075538324817207
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033088058188058641943042560012243509120x7fe8f94cc6000x7fe7ed837a00524288231564929643563612075538324844087120755383250368221207553832657713712075538326647749
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332880581880586419430425600122400x7fe8f94cc5000x7fe7ed837a40524288254869532623409212075538326677284120755383268596961207553833138704112075538331456095