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

46 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjGRBM_COUNTGRBM_GUI_ACTIVESQ_WAVESSQ_IFETCHSQ_IFETCH_LEVELSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000851446851451335544322560083264640x00x7f57d7204180502017502017524288629145679169110139669612074888626877398120748888760008321207488887632339012074888876416213
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00285144685145132768256002424124800x00x7f57d7235100278062780651281929394119883612074888891216898120748888915483931207488889155511312074888891564213
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0048514468514514194304256002424129280x7f59075059000x7f57d7235140216862216862655369175041398781790160012074888891674198120748888918594321207488889199159112074888891995104
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0068514468514514194304256003624136320x7f59075058000x7f57d72351804005824005826553612451841838632346002412074888892097605120748888922896701207488889254486812074888892593396
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0088514468514514194304256002824140800x7f59075057000x7f57d72351c0400438400438655369830401372941750744812074888892669447120748888928501471207488889310470612074888893151513
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00108514468514514194304256002424145280x7f59075056000x7f57d72352002167422167426553610485761577282020289212074888893233876120748888934168641207488889354966312074888893552588
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00128514468514514194304256002424149760x7f59075055000x7f57d7235240226558226558655369830401480401889918812074888893635202120748888938151021207488889395366112074888893956599
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00148514468514514194304256002424154240x7f59075054000x7f57d72352802201422201426553610485761465511877702012074888894070230120748888942469401207488889438021912074888894383182
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00168514468514514194304256002824161280x7f59075053000x7f57d72352c04013024013026553615728642266012888105212074888894456689120748888946334981207488889488885712074888894933945
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00188514468514514194304256002824168320x7f5907505a000x7f57d72353004034704034706553611796481587932033979612074888894968399120748888951715751207488889542853412074888895473989
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00208514468514514194304256002424175360x7f59075059000x7f57d72353402134302134306553611141121793242294852812074888895512611120748888956928531207488889582261212074888895825592
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00228514468514514194304256002424182400x7f59075058000x7f57d72353802266942266946553611141121574952017763212074888895899630120748888960749311207488889621413012074888896217260
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00248514468514514194304256002424189440x7f59075057000x7f57d72353c02157182157186553611796481717492188700812074888896303400120748888964824491207488889661412812074888896617083
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00268514468514514194304256002824199040x7f59075056000x7f57d72354004568144568146553618350082664493415618412074888896691021120748888968648471207488889715844512074888897203623
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00288514468514514194304256002824206080x7f59075055000x7f57d72354403988703988706553613107201780232273509612074888897242756120748888974405241207488889769364312074888897738427
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00308514468514514194304256002424213120x7f59075054000x7f57d72354802123102123106553612451841768292267807612074888897773613120748888979584411207488889808820112074888898091493
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00328514468514514194304256002424220160x7f59075053000x7f57d72354c02148062148066553613107201868002388554012074888898165932120748888983417991207488889847267912074888898475687
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00348514468514514194304256002424227200x7f5907505a000x7f57d72355002181902181906553613107201802722300981612074888898564001120748888987390781207488889887267712074888898875651
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00368514468514514194304256002824236800x7f59075059000x7f57d72355404043744043746553620971522866503666150012074888898948245120748888991283561207488889938659412074888899432095
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00388514468514514194304256002824243840x7f59075058000x7f57d72355803936943936946553614417921956752512058012074888899469775120748888996461131207488889989747212074888899941962
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00408514468514514194304256002424250880x7f59075057000x7f57d72355c02166862166866553613762561964252515094812074888899977118120748889001696301207488890030179012074888900305057
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00428514468514514194304256002424257920x7f59075056000x7f57d72356002166782166786553615073282114422701984812074888900376179120748889005541081207488890068690812074888900689962
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00448514468514514194304256002424264960x7f59075055000x7f57d72356402146862146866553614417921993342548000012074888900777936120748889009497871207488890108050612074888901083794
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00468514468514514194304256002824277120x7f59075054000x7f57d72356804004624004626553623592963228984126292012074888901154626120748889013305851207488890158722312074888901631221
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00488514468514514194304256002824284160x7f59075053000x7f57d72356c04054864054866553615728642129512717439212074888901668270120748889018526621207488890211122112074888902156938
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00508514468514514194304256002424291200x7f5907505a000x7f57d72357002177022177026553615073282041562617057612074888902191212120748889023840191207488890251745912074888902520514
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00528514468514514194304256002424300800x7f59075059000x7f57d72357402210622210626553617039362324872984855212074888902593199120748889027641771207488890289969712074888902902754
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00548514468514514194304256002424307840x7f59075058000x7f57d72357802135502135506553615728642252942881985612074888902987121120748889031664151207488890329729512074888903300283
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00568514468514514194304256002824320000x7f59075057000x7f57d72357c04001184001186553626214403554394541878812074888903376164120748889035491341207488890380513212074888903849975
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00588514468514514194304256002824329600x7f59075056000x7f57d72358003945263945266553617039362330402981428812074888903885681120748889040684911207488890432065012074888904366675
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00608514468514514194304256002424339200x7f59075055000x7f57d72358402145902145906553616384002271512904959212074888904401109120748889045891281207488890472000812074888904722987
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00628514468514514194304256002424348800x7f59075054000x7f57d72358802219662219666553619005442678383423179212074888904797285120748889049707271207488890510752612074888905110798
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00648514468514514194304256002424358400x7f59075053000x7f57d72358c02195182195186553617039362306972958210812074888905200234120748889053756851207488890550848412074888905511512
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00668514468514514194304256002824373120x7f5907505a000x7f57d72359004043824043826553628835843935595039811612074888905584378120748889057566431207488890601632112074888906061545
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00688514468514514194304256002824382720x7f59075059000x7f57d72359404019984019986553618350082442953133242812074888906100357120748889062913601207488890654831912074888906591920
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00708514468514514194304256002424392320x7f59075058000x7f57d72359802187342187346553617694722765853542627612074888906628598120748889068065571207488890694095712074888906944105
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00728514468514514194304256002424401920x7f59075057000x7f57d72359c02187422187426553620971523083743932390012074888907020286120748889071932751207488890732767512074888907330673
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00748514468514514194304256002424411520x7f59075056000x7f57d7235a002177342177346553618350082482023177332412074888907419168120748889075910341207488890772463312074888907727541
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00768514468514514194304256002824426240x7f59075055000x7f57d7235a404019664019666553631457284167035348012412074888907798753120748889079711921207488890822879012074888908276160
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00788514468514514194304256002824435840x7f59075054000x7f57d7235a803960943960946553619660802631043357518012074888908310935120748889084969491207488890875102812074888908794063
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00808514468514514194304256002424445440x7f59075053000x7f57d7235ac02126062126066553619005442824323617356012074888908833656120748889090127861207488890914286612074888909146217
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00828514468514514194304256002424457600x7f5907505a000x7f57d7235b002233902233906553622937603096013983746812074888909219613120748889093937451207488890953214412074888909535430
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00848514468514514194304256002424467200x7f59075059000x7f57d7235b402186062186066553619660803022853877777212074888909621440120748889097939031207488890992766212074888909930855
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00868514468514514194304256002824484480x7f59075058000x7f57d7235b804152704152706553634078724561355847254012074888910007678120748889101811011207488891044829912074888910494012
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00888514468514514194304256002824494080x7f59075057000x7f57d7235bc03971663971666553620971522782363562321212074888910529638120748889107105381207488891096445712074888911019027
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00908514468514514194304256002424503680x7f59075056000x7f57d7235c002189182189186553620316162867183670142812074888911054894120748889112450951207488891137949512074888911382874
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00928514468514514194304256002424515840x7f59075055000x7f57d7235c402222782222786553624903683450374415069612074888911457432120748889116302131207488891176717312074888911770304
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00948514468514514194304256002424525440x7f59075054000x7f57d7235c802246542246546553620971523266274179669612074888911858558120748889120330911207488891217149112074888912174986
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00968514468514514194304256002824542720x7f59075053000x7f57d7235cc04237664237666553636700165013146421532012074888912253391120748889124268491207488891269916812074888912744414
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00988514468514514194304256002824554880x7f5907505a000x7f57d7235d003912063912066553622282243116303978464012074888912782775120748889129556471207488891320668612074888913252147
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001008514468514514194304256002424567040x7f59075059000x7f57d7235d402187342187346553621626883105443978424012074888913288745120748889134742041207488891360828412074888913611335
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001028514468514514194304256002424581760x7f59075058000x7f57d7235d802318062318066553626869763834754896306412074888913680814120748889138527621207488891399676212074888913999847
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001048514468514514194304256002424593920x7f59075057000x7f57d7235dc02256382256386553622282243131404001336412074888914088742120748889142612401207488891439980012074888914402866
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001068514468514514194304256002824613760x7f59075056000x7f57d7235e004102464102466553639321605205546667600812074888914477014120748889146469981207488891491163712074888914956445
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001088514468514514194304256002824625920x7f59075055000x7f57d7235e403957583957586553623592963103903978952412074888914990869120748889151852361207488891543851412074888915482412
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001108514468514514194304256002424638080x7f59075054000x7f57d7235e802805182805186553622937603221264127143212074888915519852120748889157007531207488891587659212074888915879580
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001128514468514514194304256002424652800x7f59075053000x7f57d7235ec02246302246306553628835844028435122366012074888915954209120748889161348311207488891627323012074888916276618
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001148514468514514194304256002424664960x7f5907505a000x7f57d7235f002164062164066553623592963164554043878012074888916361556120748889165317891207488891666490812074888916668015
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001168514468514514194304256002824684800x7f59075059000x7f57d7235f404157664157666553641943045820487464789612074888916741261120748889169138671207488891718042612074888917226413
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001188514468514514194304256002824696960x7f59075058000x7f57d7235f803992943992946553624903683267184186258012074888917263592120748889174469851207488891770314312074888917747682
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001208514468514514194304256002424709120x7f59075057000x7f57d7235fc02176702176706553624248323404484360505612074888917781515120748889179641021207488891809738112074888918100818
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001228514468514514194304256002424723840x7f59075056000x7f57d72360002249982249986553630801925054436477009212074888918174084120748889183469801207488891848681912074888918489931
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001248514468514514194304256002424736000x7f59075055000x7f57d72360402259182259186553624903684000915122987212074888918575710120748889187463381207488891888473712074888918887800
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001268514468514514194304256002824758400x7f59075054000x7f57d72360804226304226306553644564486013277682690412074888918958832120748889191367361207488891940937512074888919453782
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001288514468514514194304256002824770560x7f59075053000x7f57d72360c04020704020706553626214403510174501263212074888919490460120748889196775331207488891993545212074888919979289
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001308514468514514194304256002424782720x7f5907505a000x7f57d72361002162542162546553625559043703404746444012074888920018331120748889202061711207488892033929012074888920342694
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001328514468514514194304256002424800000x7f59075059000x7f57d72361402348382348386553632768004842046163711212074888920416832120748889205876091207488892073304812074888920736065
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001348514468514514194304256002424812160x7f59075058000x7f57d72361802147182147186553626214403766394826482812074888920821674120748889209914471207488892112376612074888921127382
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001368514468514514194304256002824834560x7f59075057000x7f57d72361c04142304142306553647185926412048202374412074888921200679120748889213724051207488892163960412074888921684478
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001388514468514514194304256002824849280x7f59075056000x7f57d72362003945743945746553627525123731504796437612074888921717639120748889219012021207488892215512112074888922201218
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001408514468514514194304256002424864000x7f59075055000x7f57d72362402189182189186553626869763751614812133612074888922236554120748889224237601207488892255783912074888922561077
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001428514468514514194304256002424881280x7f59075054000x7f57d72362802431102431106553634734085185136635192812074888922633361120748889228042381207488892295591712074888922958926
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001448514468514514194304256002424896000x7f59075053000x7f57d72362c02168302168306553627525123944015043089212074888923074501120748889232491961207488892338231512074888923385449
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001468514468514514194304256002824920960x7f5907505a000x7f57d72363004164704164706553649807366656268513107612074888923455739120748889236264741207488892389639212074888923941262
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001488514468514514194304256002824935680x7f59075059000x7f57d72363403999503999506553628835843957635041086812074888923977008120748889241650311207488892442247012074888924469243
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001508514468514514194304256002424950400x7f59075058000x7f57d72363802231662231666553628180484355505582648012074888924503496120748889246907881207488892482854812074888924831766
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001528514468514514194304256002424967680x7f59075057000x7f57d72363c02531422531426553636700165527957061593612074888924904602120748889250859871207488892524406612074888925247188
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001548514468514514194304256002424982400x7f59075056000x7f57d72364002228222228226553628835844612225916634012074888925331816120748889255045441207488892564214412074888925645308
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015685144685145141943042560028241007360x7f59075055000x7f57d72364404123984123986553651773446802648677167612074888925717623120748889258885431207488892615526112074888926200791
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015885144685145141943042560028241022080x7f59075054000x7f57d72364803971583971586553630146564031965159570012074888926235816120748889264203801207488892667685912074888926720737
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016085144685145141943042560024241036800x7f59075053000x7f57d72364c02175182175186553629491204056805189558412074888926752496120748889269408571207488892707445712074888927077670
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016285144685145141943042560024241056640x7f5907505a000x7f57d72365002646542646546553638666245736867392834412074888927156236120748889273282151207488892749445512074888927497651
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016485144685145141943042560024241071360x7f59075059000x7f57d72365402190542190546553630146564043155175178412074888927578421120748889277507731207488892788533312074888927888507
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016685144685145141943042560028241098880x7f59075058000x7f57d72365804197104197106553654394887399159409715612074888927960511120748889281406911207488892841317012074888928440292
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016885144685145141943042560028241113600x7f59075057000x7f57d72365c04013024013026553631457284335835561334012074888928492069120748889286611691207488892891956712074888928943327
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017085144685145141943042560024241128320x7f59075056000x7f57d72366002241662241666553630801924608555904970012074888928997277120748889291771661207488892931604512074888929319566
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017285144685145141943042560024241148160x7f59075055000x7f57d72366402773422773426553640632325691427293296412074888929392492120748889295739641207488892974820312074888929751659
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017485144685145141943042560024241162880x7f59075054000x7f57d72366802170862170866553631457284239885442357612074888929831007120748889300040421207488893013748112074888930141824
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017685144685145141943042560028241190400x7f59075053000x7f57d72366c04060224060226553657016327721259873424412074888930212626120748889303912401207488893065379912074888930681317
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017885144685145141943042560028241207680x7f5907505a000x7f57d72367004079584079586553632768004342305563176412074888930740237120748889309189181207488893118275612074888931210440
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018085144685145141943042560024241224960x7f59075059000x7f57d72367402273262273266553632112644807626154766812074888931265553120748889314381151207488893157811412074888931581229
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018285144685145141943042560024241247360x7f59075058000x7f57d72367802884462884466553642598405867447508740412074888931650849120748889318233931207488893200659212074888932009666
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018485144685145141943042560024241264640x7f59075057000x7f57d72367c02287742287746553632768005137336578444412074888932095495120748889322696311207488893241091012074888932414578
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018685144685145141943042560020241279360x7f59075056000x7f57d723680046034246034265536773324898900512640148812074888932483917120748889326566691207488893295650712074888932982333
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018885144685145141943042560028241296640x7f59075055000x7f57d72368403964623964626553634078724518525794974412074888933044479120748889332192261207488893347426512074888933501468
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019085144685145141943042560024241313920x7f59075054000x7f57d72368802161342161346553633423365009286412236412074888933552583120748889337206641207488893385282312074888933856047
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019285144685145141943042560024241336320x7f59075053000x7f57d72368c03031423031426553644564486799858724741212074888933929904120748889341173021207488893430962112074888934335077
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019485144685145141943042560024241353600x7f5907505a000x7f57d72369002253982253986553635389445304886788187612074888934403554120748889345753791207488893471489912074888934718139
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019685144685145141943042560020241368320x7f59075059000x7f57d7236940435494435494655368978432112863814451568412074888934786196120748889349569771207488893524081612074888935269063
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019885144685145141943042560028241385600x7f59075058000x7f57d72369804070224070226553636700165460407000627612074888935322172120748889355046551207488893576769312074888935791704
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020085144685145141943042560024241402880x7f59075057000x7f57d72369c02186462186466553636044804984506376786012074888935849181120748889360318521207488893616641112074888936170268
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020285144685145141943042560024241427840x7f59075056000x7f57d7236a003299343299346553648496647173269187292012074888936243614120748889364174501207488893662768912074888936652744
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020485144685145141943042560024241447680x7f59075055000x7f57d7236a402231822231826553638010885935697588869612074888936722003120748889368940881207488893703152712074888937034894
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020685144685145141943042560020241457280x7f59075054000x7f57d7236a804734544734546553614548992182661223381544412074888937103612120748889372761661207488893758560412074888937609973
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020885144685145141943042560028241477120x7f59075053000x7f57d7236ac04040864040866553639321605181906627548812074888937666298120748889378350431207488893809584212074888938121534
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021085144685145141943042560024241496960x7f5907505a000x7f57d7236b002279182279186553638666245627637207373212074888938175614120748889383484811207488893849024012074888938493505
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021285144685145141943042560024241521920x7f59075059000x7f57d7236b4035809435809465536524288078577410055361212074888938560880120748889387312631207488893895926212074888938987423
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021485144685145141943042560024241541760x7f59075058000x7f57d7236b802313582313586553640632326343308115528412074888939058876120748889392322191207488893937621912074888939378900
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021685144685145141943042560020241556480x7f59075057000x7f57d7236bc05048545048546553610027008126004116140689212074888939449231120748889396240581207488893995349712074888939975820
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021885144685145141943042560028241576320x7f59075056000x7f57d7236c004020224020226553641943045887817523345612074888940037645120748889402122151207488894047253412074888940497379
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022085144685145141943042560024241596160x7f59075055000x7f57d7236c402228862228866553641287686117257824907212074888940549957120748889407186131207488894085637312074888940858961
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022285144685145141943042560024241623680x7f59075054000x7f57d7236c803805983805986553656360967719389840330412074888940926647120748889411093321207488894135397112074888941378807
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022485144685145141943042560024241646080x7f59075053000x7f57d7236cc02247262247266553645875206731028616992412074888941447124120748889416210101207488894175972912074888941762220
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022685144685145141943042560020241663360x7f5907505a000x7f57d7236d005751025751026553611075584139296417831457212074888941832270120748889420037281207488894238068712074888942405044
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022885144685145141943042560028241685760x7f59075059000x7f57d7236d404149744149746553647185926297758082105212074888942459856120748889426306061207488894289924412074888942921604
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023085144685145141943042560024241708160x7f59075058000x7f57d7236d802271502271506553646530566842628759745612074888942974653120748889431522031207488894329348312074888943296230
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023285144685145141943042560024241740800x7f59075057000x7f57d7236dc043479043479065536642252890877011656998412074888943363636120748889435355621207488894381556112074888943838348
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023485144685145141943042560024241765760x7f59075056000x7f57d7236e0022279022279065536511180880392810293153212074888943905933120748889440907601207488894422931912074888944232250
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023685144685145141943042560020241777920x7f59075055000x7f57d7236e406443746443746553615007744188729124144886812074888944302340120748889444776381207488894490083612074888944924877
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023885144685145141943042560028241802880x7f59075054000x7f57d7236e8040563840563865536524288078942810112101612074888944981252120748889451624351207488894542595412074888945451496
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024085144685145141943042560024241827840x7f59075053000x7f57d7236ec022675022675065536517734485362510936474012074888945503502120748889456715531207488894581203312074888945814650
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024285144685145141943042560024241863040x7f5907505a000x7f57d7236f00488758488758655367208960104740413491498412074888945882997120748889460573121207488894637315012074888946398866
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024485144685145141943042560024241893120x7f59075059000x7f57d7236f4024379824379865536616038492608211854865612074888946465821120748889466411491207488894679378812074888946796595
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024685144685145141943042560020241907840x7f59075058000x7f57d7236f807847267847266553617104896214717627470051612074888946865093120748889470408271207488894755890512074888947583728
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024885144685145141943042560028241937920x7f59075057000x7f57d7236fc046294246294265536629145692131111786196412074888947637278120748889478073841207488894810930312074888948135934
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025085144685145141943042560024241968000x7f59075056000x7f57d723700024670224670265536622592090264111551726812074888948186087120748889483561821207488894851122112074888948514087
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025285144685145141943042560024242010880x7f59075055000x7f57d7237040594726594726655368781824125465516110330412074888948587584120748889487611401207488894914769912074888949173603
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025485144685145141943042560024242046080x7f59075054000x7f57d7237080280110280110655367208960112960214464047212074888949246468120748889494252981207488894960305712074888949605686
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025685144685145141943042560020242060800x7f59075053000x7f57d72370c09433909433906553619202048240688430818620012074888949674193120748889498464161207488895046865312074888950495629
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025885144685145141943042560028242096000x7f5907505a000x7f57d7237100500950500950655367340032103044313185034812074888950547105120748889507180921207488895104561112074888951070939
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026085144685145141943042560024242131200x7f59075059000x7f57d7237140283014283014655367274496102849513158729612074888951130509120748889513024101207488895148208912074888951484768
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026285144685145141943042560024242181760x7f59075058000x7f57d72371806982626982626553610354688147431618880676012074888951554978120748889517252881207488895218128612074888952208192
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026485144685145141943042560024242222080x7f59075057000x7f57d72371c0314134314134655368257536125655716081521212074888952279695120748889524526451207488895265360412074888952677234
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026685144685145141943042560020242239360x7f59075056000x7f57d7237200107619010761906553621299200267671234260491212074888952738978120748889529137631207488895362432012074888953650342
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026885144685145141943042560028242279680x7f59075055000x7f57d7237240567686567686655368388608113350614543916012074888953708440120748889538844791207488895425679812074888954283859
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027085144685145141943042560024242320000x7f59075054000x7f57d7237280317862317862655368323072125443316051885612074888954334924120748889545059171207488895470959612074888954733485
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027285144685145141943042560024242378240x7f59075053000x7f57d72372c08033588033586553611927552164154221036701212074888954790461120748889549628751207488895548927312074888955514496
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027485144685145141943042560024242423680x7f5907505a000x7f57d7237300349966349966655369306112143168218328525612074888955583985120748889557599921207488895598479112074888956017611
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027685144685145141943042560020242435840x7f59075059000x7f57d7237340120681412068146553629163520365241546744271612074888956076050120748889562487901207488895704798612074888957094482
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027885144685145141943042560028242481280x7f59075058000x7f57d7237380636030636030655369437184128448916485141212074888957131040120748889573172651207488895773694412074888957779976
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028085144685145141943042560024242526720x7f59075057000x7f57d72373c0352582352582655369371648135348717333913212074888957812938120748889579974231207488895822318212074888958269246
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028285144685145141943042560024242592640x7f59075056000x7f57d72374009097909097906553613500416190946124555106012074888958305172120748889584891011207488895908717812074888959133682
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028485144685145141943042560024242648320x7f59075055000x7f57d72374404172944172946553611403264170533821836045612074888959178175120748889593553371207488895962477612074888959668426
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028685144685145141943042560020242663040x7f59075054000x7f57d7237480148693414869346553633357824417774053465206812074888959702459120748889598958151207488896088205112074888960928207
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028885144685145141943042560028242718720x7f59075053000x7f57d72374c07794547794546553611534336159137220342696412074888960965797120748889611530901207488896166876712074888961713086
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029085144685145141943042560024242774400x7f5907505a000x7f57d72375004239424239426553611534336181991523298202412074888961750485120748889619287661207488896220284512074888962248250
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029285144685145141943042560012242799360x7f59075059000x7f57d7237540112677411267746553619267584242066131028597212074888962287844120748889624654041207488896320428112074888963249982
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029485144685145141943042560024242865280x7f59075058000x7f57d72375804896144896146553613500416213964227389289212074888963301978120748889634777201207488896379499912074888963839908
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029685144685145141943042560020242880000x7f59075057000x7f57d72375c0176952617695266553637552128470854860273177612074888963873711120748889640650781207488896523835312074888965284212
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029885144685145141943042560032242945920x7f59075056000x7f57d72376009215749215746553613631488191161124421440012074888965324146120748889655004321207488896611306912074888966158948
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030085144685145141943042560024243011840x7f59075055000x7f57d72376404928464928466553613631488208601126707584412074888966198541120748889663924281207488896671210712074888966755957
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030285144685145141943042560012243049600x7f59075054000x7f57d7237680133691013369106553621692416274081135086126412074888966792976120748889669733861207488896785290212074888967899071
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030485144685145141943042560024243136000x7f59075053000x7f57d72376c06319986319986553617694720274919935195155612074888967952160120748889681333811207488896854569912074888968591328
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030685144685145141943042560020243148160x7f5907505a000x7f57d7237700233234223323426553657475072719797392076984412074888968625682120748889688175381207488897036697212074888970411711
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030885144685145141943042560020243175680x7f59075059000x7f57d7237740120043012004306553619660800247987531708696812074888970450934120748889706306511207488897142744712074888971472522
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031085144685145141943042560012243203200x7f59075058000x7f57d72377806406146406146553620381696257779332985376812074888971512386120748889716888861207488897210472512074888972149510
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031285144685145141943042560012243240960x7f59075057000x7f57d72377c0175980617598066553628704768361175246259408012074888972193873120748889723679241207488897352871912074888973574288
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031485144685145141943042560012243288960x7f59075056000x7f57d7237800119807011980706553636634624465320059573355212074888973626054120748889737997581207488897458583512074888974633156
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031685144685145141943042560020243301120x7f59075055000x7f57d7237840458479045847906553610584064013245300169493652412074888974672880120748889748664731207488897791894112074888977965619
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031885144685145141943042560020243328640x7f59075054000x7f57d7237880232483823248386553638535168484179861935046412074888978077557120748889782576591207488897980101312074888979848147
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032085144685145141943042560012243356160x7f59075053000x7f57d72378c0120331012033106553639124992491882162956524412074888979938806120748889801226121207488898091220912074888980958641
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032285144685145141943042560012243393920x7f5907505a000x7f57d7237900344288634428866553655771136700566589632240412074888981046614120748889812213271207488898350339812074888983553854
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032485144685145141943042560012243441920x7f59075059000x7f57d72379402325446232544665536725483529114234116660819212074888983636998120748889838125171207488898534867012074888985396097
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032685144685145141943042560020243454080x7f59075058000x7f57d7237980908712690871266553621069824026347058337264733612074888985482338120748889856659491207488899172000412074888991766927
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032885144685145141943042560020243481600x7f59075057000x7f57d72379c04572350457235065536762839049557129122245327212074888991845613120748889920284831207488899507055112074888995119968
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033085144685145141943042560012243509120x7f59075056000x7f57d7237a002328798232879865536773980169706889124259312012074888995198614120748889953737491207488899691422312074888996960258
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332851446851451419430425600122400x7f59075055000x7f57d7237a40681322268132226553611082137613879283177683212412074888997047430120748889972254391207488900175309912074889001804089