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

50 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjGRBM_COUNTGRBM_GUI_ACTIVECPC_ME1_BUSY_FOR_PACKET_DECODESQ_CYCLESSQ_WAVESSQ_WAVE_CYCLESSQ_BUSY_CYCLESSQ_LEVEL_WAVESSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000891508891513335544322560083264640x00x7f301960418049935049935016307399480852428836618713137978070147954607612075754251090885120757544955679391207575449588953712075754496009475
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00289150889151332768256002424124800x00x7f30196351002799827998209582239925121150884773520461754412075754510868550120757545112112591207575451121797912075754511227137
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0048915088915134194304256002424129280x7f31253609000x7f3019635140215716215716223581725736655361441486431567089057841004412075754511296295120757545115405371207575451167253712075754511676271
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0068915088915134194304256003624136320x7f31253608000x7f3019635180397044397044268233176360655362301557083006315092243847212075754511754887120757545119498151207575451220309412075754512275956
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0088915088915134194304256002824140800x7f31253607000x7f30196351c03958443958442593631667606553630359662430017700121620011612075754512313626120757545125288521207575451278117112075754512850784
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00108915088915134194304256002424145280x7f31253606000x7f3019635200217980217980228901743848655361488692851578184059728648812075754512877003120757545130965301207575451322996912075754513233536
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00128915088915134194304256002424149760x7f31253605000x7f3019635240217077217077214951736624655361461855231577524058655398012075754513294359120757545134963681207575451362980712075754513632998
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00148915088915134194304256002424154240x7f31253604000x7f3019635280212069212069177711696560655361604662151510719064368397612075754513718737120757545139043661207575451403220512075754514035666
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00168915088915134194304256002824161280x7f31253603000x7f30196352c03955653955653707931645286553632160809129848750128824921212075754514098152120757545143059641207575451455700212075754514601558
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00188915088915134194304256002824168320x7f3125360a000x7f30196353003934443934443130131475606553632400115129756600129782167212075754514638046120757545148435611207575451509396012075754515164875
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00208915088915134194304256002424175360x7f31253609000x7f3019635340211173211173219961689392655361591052441531422063823929612075754515191504120757545154059581207575451553507712075754515538179
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00228915088915134194304256002424182400x7f31253608000x7f3019635380210869210869206041686960655361495261141524310059992326812075754515598671120757545157992361207575451592787512075754515931009
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00248915088915134194304256002424189440x7f31253607000x7f30196353c0218941218941252131751536655361544932561572671061978672412075754516011769120757545161931541207575451632579312075754516328828
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00268915088915134194304256002824199040x7f31253606000x7f30196354003956453956453353231651686553631718555529987010127055724412075754516383590120757545165870721207575451683971112075754516909217
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00288915088915134194304256002824206080x7f31253605000x7f30196354403871323871323053130970646553632817593929331820131452204812075754516935926120757545171632291207575451741058812075754517479907
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00308915088915134194304256002424213120x7f31253604000x7f3019635480215692215692236521725544655361500935301561198060219422812075754517506406120757545177136261207575451784546612075754517848853
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00328915088915134194304256002424220160x7f31253603000x7f30196354c0215668215668228971725352655361543971771565185061940058012075754517908394120757545181227441207575451825522412075754518258314
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00348915088915134194304256002424227200x7f3125360a000x7f3019635500211749211749233681694000655361612126911533308064667073612075754518334546120757545185208221207575451865074212075754518653939
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00368915088915134194304256002824236800x7f31253609000x7f30196355403981083981082839531848726553631068376530090330124455261612075754518715313120757545189048201207575451915937912075754519232063
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00388915088915134194304256002824243840x7f31253608000x7f30196355803923403923402926531387286553629039695429720750116340378012075754519259464120757545194673781207575451971809612075754519787255
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00408915088915134194304256002424250880x7f31253607000x7f30196355c0218581218581214281748656655361540378821586664061796152412075754519812482120757545200254551207575452016001412075754520163605
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00428915088915134194304256002424257920x7f31253606000x7f3019635600218197218197249821745584655361616749161578111064851182412075754520224308120757545204248131207575452055841212075754520561745
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00448915088915134194304256002424264960x7f31253605000x7f3019635640213068213068223341704552655361599432571543226064159072412075754520637055120757545208160111207575452094673012075754520950046
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00468915088915134194304256002824277120x7f31253604000x7f30196356803931333931333298831450726553629982269129869630120110744412075754521007212120757545212105691207575452146256812075754521532328
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00488915088915134194304256002824284160x7f31253603000x7f30196356c03891563891562968331132566553633175616629516320132884227212075754521558207120757545217628861207575452201216512075754522081719
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00508915088915134194304256002424291200x7f3125360a000x7f3019635700219061219061253941752496655361645687681593759066008769612075754522110383120757545223187231207575452245344312075754522456676
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00528915088915134194304256002424300800x7f31253609000x7f3019635740211740211740258781693928655361693866791534346067936643612075754522516017120757545227067211207575452283712112075754522840279
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00548915088915134194304256002424307840x7f31253608000x7f3019635780207668207668203631661352655361663107081501465066706203212075754522911331120757545230985591207575452322591912075754523229503
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00568915088915134194304256002824320000x7f31253607000x7f30196357c04500444500441599136003606553632021847729626850128269148012075754523283543120757545234884771207575452377855612075754523822585
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00588915088915134194304256002824329600x7f31253606000x7f30196358003869493869493221930956006553633178699029225200132896502412075754523858872120757545240559951207575452430335312075754524374280
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00608915088915134194304256002424339200x7f31253605000x7f3019635840211100211100253321688808655361665189551509118066790235612075754524400028120757545246027121207575452473055112075754524733828
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00628915088915134194304256002424348800x7f31253604000x7f3019635880211292211292208631690344655361605747021515031064413717212075754524798889120757545249908701207575452512094912075754525124314
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00648915088915134194304256002424358400x7f31253603000x7f30196358c0211157211157219811689264655361626917841534735065258588412075754525195126120757545253785481207575452550862712075754525511634
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00668915088915134194304256002824373120x7f3125360a000x7f30196359003936533936533058731492326553633601260729844240134586856812075754525571736120757545257663861207575452601966512075754526090259
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00688915088915134194304256002824382720x7f31253609000x7f30196359403923653923653283231389286553635591939429746490142549399612075754526117460120757545263265431207575452657758212075754526646793
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00708915088915134194304256002424392320x7f31253608000x7f3019635980218252218252261731746024655361611977311563291064662208412075754526671479120757545268827001207575452701502012075754527018584
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00728915088915134194304256002424401920x7f31253607000x7f30196359c0222100222100261391776808655361668396661615753066920697212075754527082313120757545272847781207575452742237812075754527425962
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00748915088915134194304256002424411520x7f31253606000x7f3019635a00210621210621252951684976655361602269021522721064272624412075754527496893120757545276758161207575452780525612075754527808392
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00768915088915134194304256002824426240x7f31253605000x7f3019635a404002774002773044032022246553631406786330364410125809160812075754527868484120757545280729341207575452833037312075754528402637
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00788915088915134194304256002824435840x7f31253604000x7f3019635a803995653995652543031965286553626761851930251550107229245212075754528429086120757545286348521207575452889133012075754528960544
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00808915088915134194304256002424445440x7f31253603000x7f3019635ac0212757212757206181702064655361706265851539715068433362012075754528986392120757545292028491207575452933356812075754529337414
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00828915088915134194304256002424457600x7f3125360a000x7f3019635b00216164216164266271729320655361596885351567761064057546812075754529397736120757545295916471207575452972556612075754529728781
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00848915088915134194304256002424467200x7f31253609000x7f3019635b40208492208492205321667944655361636444661504993065640685612075754529802358120757545299796451207575453010796412075754530111162
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00868915088915134194304256002824484480x7f31253608000x7f3019635b804063334063332897632506726553628819869130804840115460880412075754530171484120757545303670031207575453062908212075754530696700
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00888915088915134194304256002824494080x7f31253607000x7f3019635bc03906853906853447531254886553632600093929560350130581968412075754530722227120757545309266801207575453117723912075754531248496
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00908915088915134194304256002424503680x7f31253606000x7f3019635c00206485206485232321651888655361645741491493609066013779612075754531274233120757545314789971207575453160619712075754531609296
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00928915088915134194304256002424515840x7f31253605000x7f3019635c40221341221341262271770736655361693632501604422067927353612075754531670019120757545318599551207575453199723512075754532005132
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00948915088915134194304256002424525440x7f31253604000x7f3019635c80209269209269238561674160655361614296391509720064754500812075754532074831120757545322569131207575453238523312075754532388985
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00968915088915134194304256002824542720x7f31253603000x7f3019635cc04031654031653179432253286553631580934330511060126505632412075754532447794120757545326428311207575453290251012075754532971518
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00988915088915134194304256002824554880x7f3125360a000x7f3019635d003967803967802522731742486553630261414629905250121227072012075754532996805120757545332132291207575453346810712075754533537610
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001008915088915134194304256002424567040x7f31253609000x7f3019635d40208861208861215721670896655361687481181510263067685508812075754533568477120757545337649061207575453389338512075754533896687
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001028915088915134194304256002424581760x7f31253608000x7f3019635d80225333225333264481802672655361792533111640362071886668012075754533957219120757545341585041207575453429866312075754534302281
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001048915088915134194304256002424593920x7f31253607000x7f3019635dc0210341210341193981682736655361686604401520638067650140012075754534374836120757545345553021207575453468490112075754534688158
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001068915088915134194304256002824613760x7f31253606000x7f3019635e004068604068603206632548886553626314158230466740105438594012075754534747608120757545349383401207575453519913912075754535269579
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001088915088915134194304256002824625920x7f31253605000x7f3019635e403999573999572980531996646553630146217630277140120766622812075754535295427120757545354996171207575453575689612075754535826453
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001108915088915134194304256002424638080x7f31253604000x7f3019635e80212613212613198061700912655361618513591544093064923594012075754535851600120757545360749741207575453620617312075754536209956
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001128915088915134194304256002424652800x7f31253603000x7f3019635ec0223277223277278311786224655361863327891622574074717170012075754536271480120757545364640921207575453660297112075754536606243
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001148915088915134194304256002424664960x7f3125360a000x7f3019635f00213797213797238381710384655361707220901552687068473254412075754536678988120757545368573701207575453698921012075754536992480
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001168915088915134194304256002824684800x7f31253609000x7f3019635f404008054008053305732064486553632848902230358960131577584412075754537052422120757545372466481207575453750520712075754537575053
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001188915088915134194304256002824696960x7f31253608000x7f3019635f803947963947963358931583766553635597080029920500142570064412075754537602324120757545378029651207575453805720412075754538127841
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001208915088915134194304256002424709120x7f31253607000x7f3019635fc0211517211517250081692144655361635244551528089065593364412075754538153588120757545383564031207575453848664212075754538489963
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001228915088915134194304256002424723840x7f31253606000x7f3019636000221885221885253301775088655361886686581612524075654621612075754538550646120757545387434411207575453888184012075754538885098
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001248915088915134194304256002424736000x7f31253605000x7f3019636040209452209452206321675624655361662452281507691066681074012075754538957552120757545391455191207575453927431812075754539278078
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001268915088915134194304256002824758400x7f31253604000x7f30196360804120934120933509732967526553630787432331228660123331334812075754539330836120757545395299971207575453979591512075754539866331
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001288915088915134194304256002824770560x7f31253603000x7f30196360c03906123906122965731249046553634293515729560310137355740812075754539893091120757545401007141207575454035239312075754540423176
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001308915088915134194304256002424782720x7f3125360a000x7f3019636100213572213572232141708584655361629397241552161065359362812075754540448323120757545406493511207575454078135012075754540784478
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001328915088915134194304256002424800000x7f31253609000x7f3019636140232588232588273731860712655361985452251691777079605033612075754540844129120757545410403891207575454118614812075754541189661
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001348915088915134194304256002424812160x7f31253608000x7f3019636180214660214660251451717288655361639890351558245065778826812075754541262256120757545414410271207575454157366712075754541576840
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001368915088915134194304256002824834560x7f31253607000x7f30196361c04094854094853398232758886553630995923430870300124165481612075754541636772120757545418287051207575454209430412075754542163831
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001388915088915134194304256002824849280x7f31253606000x7f3019636200393524393524241003148200655362233977942967661089540947612075754542190421120757545423981421207575454265222112075754542720536
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001408915088915134194304256002424864000x7f31253605000x7f3019636240217533217533218591740272655361709445721580733068566836412075754542746674120757545429479001207575454308277912075754543086396
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001428915088915134194304256002424881280x7f31253604000x7f3019636280240972240972280991927784655362056057481760557082428132012075754543148080120757545433437381207575454349477712075754543498281
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001448915088915134194304256002424896000x7f31253603000x7f30196362c0215229215229215371721840655361704149961562682068352156812075754543591925120757545437728551207575454390613512075754543909295
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001468915088915134194304256002824920960x7f3125360a000x7f30196363004121964121963214732975766553630506553530884410122207853212075754543967613120757545441688531207575454443589212075754544506515
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001488915088915134194304256002824935680x7f31253609000x7f30196363403849333849333033030794726553631422325029122680125871102012075754544536901120757545447330111207575454498180912075754545051568
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001508915088915134194304256002424950400x7f31253608000x7f3019636380220861220861272661766896655361694598201604255067969733212075754545076795120757545452848481207575454542164712075754545424912
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001528915088915134194304256002424967680x7f31253607000x7f30196363c0251093251093277352008752655362227007541850982089266094012075754545483451120757545456746061207575454583236512075754545835605
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001548915088915134194304256002424982400x7f31253606000x7f3019636400210629210629223581685040655361621707321520160065053992012075754545907188120757545460893241207575454621908312075754546222374
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015689150889151341943042560028241007360x7f31253605000x7f30196364404020444020443460532163606553629816259230326720119447570012075754546281995120757545464738021207575454673444112075754546804596
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015889150889151341943042560028241022080x7f31253604000x7f30196364803951403951402965231611286553630931654429913100123910809612075754546829452120757545470374791207575454729251812075754547363695
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016089150889151341943042560024241036800x7f31253603000x7f30196364c0212333212333245231698672655361641852601531396065859464012075754547388671120757545475939561207575454772499612075754547728313
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016289150889151341943042560024241056640x7f3125360a000x7f3019636500264181264181283192113456655362354197431957122094354490012075754547793063120757545479864341207575454815283312075754548156679
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016489150889151341943042560024241071360x7f31253609000x7f3019636540214372214372270961714984655361681933351547913067463504012075754548229544120757545484085121207575454854099212075754548544279
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016689150889151341943042560028241098880x7f31253608000x7f30196365804068124068123957732545046553632880973830525830131705699612075754548603529120757545487960301207575454905842912075754549128304
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016889150889151341943042560028241113600x7f31253607000x7f30196365c03932523932522567131460246553633196748529506390132972932012075754549155415120757545493565071207575454961090612075754549679338
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017089150889151341943042560024241128320x7f31253606000x7f3019636600214821214821256061718576655361708921581553993068542542812075754549704986120757545499048251207575455003778412075754550041451
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017289150889151341943042560024241148160x7f31253605000x7f3019636640275829275829297012206640655362466684992046421098853027212075754550100922120757545502936231207575455046802212075754550471210
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017489150889151341943042560024241162880x7f31253604000x7f3019636680221372221372228681770984655361674944361604729067182795212075754550543535120757545507235411207575455086066012075754550863920
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017689150889151341943042560028241190400x7f31253603000x7f30196366c03990523990523558331924246553635038637830289370140336723612075754550922900120757545511257791207575455138481712075754551456772
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017889150889151341943042560028241207680x7f3125360a000x7f30196367003934693934693031531477606553630417191529634930121852102412075754551485225120757545516854561207575455193985412075754552016392
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018089150889151341943042560024241224960x7f31253609000x7f3019636740221108221108261221768872655361607418831598553064480029212075754552041719120757545522462531207575455238305212075754552386369
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018289150889151341943042560024241247360x7f31253608000x7f30196367802889972889973047823119846553625678899821516220102899761612075754552446040120757545526355311207575455281857012075754552821819
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018489150889151341943042560024241264640x7f31253607000x7f30196367c0219740219740253651757928655361710450121598359068604929612075754552913479120757545531038491207575455324032812075754553243933
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018689150889151341943042560020241279360x7f31253606000x7f30196368004116534116533564332932326553638115992931310490152646112812075754553303364120757545535001671207575455376784512075754553838177
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018889150889151341943042560028241296640x7f31253605000x7f30196368403901963901963178431215766553632596177929445430130566582012075754553863164120757545540689641207575455432176212075754554391165
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019089150889151341943042560024241313920x7f31253604000x7f3019636880217612217612257631740904655361725324451572649069200299612075754554416693120757545546211211207575455475600012075754554759279
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019289150889151341943042560024241336320x7f31253603000x7f30196368c03018213018213166524145766553627159653922567930108823106412075754554821535120757545550094391207575455520143812075754555274597
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019489150889151341943042560024241353600x7f3125360a000x7f3019636900219764219764264091758120655361726859061594924069263631612075754555311215120757545555051171207575455564159612075754555644845
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019689150889151341943042560020241368320x7f31253609000x7f30196369404374774374773948934998246553640290535933368880161344259612075754555703744120757545558927951207575455617823312075754556248677
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019889150889151341943042560028241385600x7f31253608000x7f30196369803913803913803172431310486553630696845829537630122969417212075754556274094120757545564748721207575455672863012075754556798128
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020089150889151341943042560024241402880x7f31253607000x7f30196369c0216988216988209761735912655361713214281571712068716875612075754556824257120757545570332691207575455716798812075754557171673
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020289150889151341943042560024241427840x7f31253606000x7f3019636a003300603300603315226404886553630114998724807050120645680012075754557232115120757545574315071207575455764190612075754557685267
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020489150889151341943042560024241447680x7f31253605000x7f3019636a40217373217373244411738992655361683479821575123067527943612075754557735911120757545579190241207575455805406412075754558057910
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020689150889151341943042560020241457280x7f31253604000x7f3019636a804703164703164075037625366553643875153236032270175682618412075754558120476120757545583142151207575455862189412075754558695414
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020889150889151341943042560028241477120x7f31253603000x7f3019636ac04032764032763200032262166553629051079130406240116387187612075754558721403120757545589305321207575455919181012075754559262829
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021089150889151341943042560024241496960x7f3125360a000x7f3019636b00221493221493256821771952655361740233991611053069795717612075754559288917120757545594930891207575455963068912075754559633217
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021289150889151341943042560024241521920x7f31253609000x7f3019636b403552933552933402528423526553632161356126879680128831275212075754559696194120757545598839681207575456011244712075754560183420
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021489150889151341943042560024241541760x7f31253608000x7f3019636b80215540215540271851724328655361676845481553692067263063612075754560222282120757545604175661207575456055116512075754560553728
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021689150889151341943042560020241556480x7f31253607000x7f3019636bc05477325477321502043818646553647404666038933830189800686012075754560612998120757545608084441207575456116796312075754561238801
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021889150889151341943042560028241576320x7f31253606000x7f3019636c003989883989883448331919126553634389174430127330137739942812075754561264419120757545614678011207575456172588012075754561794394
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022089150889151341943042560024241596160x7f31253605000x7f3019636c40217053217053260031736432655361692515691577444067888120012075754561820442120757545620295591207575456216475812075754562167617
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022289150889151341943042560024241623680x7f31253604000x7f3019636c803829483829483711730635926553635177483829073600140895713212075754562231065120757545624258771207575456267179612075754562739951
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022489150889151341943042560024241646080x7f31253603000x7f3019636cc0228356228356291841826856655361836777801652658073660711212075754562775908120757545629673151207575456310971512075754563112744
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022689150889151341943042560020241663360x7f3125360a000x7f3019636d005799645799645223146397206553654369646744518960217660577612075754563171623120757545633735541207575456375243212075754563821742
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022889150889151341943042560028241685760x7f31253609000x7f3019636d404014204014203496032113686553633483595130083650134116385612075754563846938120757545640580311207575456431627012075754564387222
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023089150889151341943042560024241708160x7f31253608000x7f3019636d80226820226820286481814568655361804411131636708072365074812075754564409694120757545646153091207575456475610812075754564758863
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023289150889151341943042560024241740800x7f31253607000x7f3019636dc04368854368854247234950886553640234597633127910161123556012075754564819536120757545650074671207575456528778612075754565358928
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023489150889151341943042560024241765760x7f31253606000x7f3019636e00224909224909294011799280655361847676841625020074096050812075754565396698120757545655877851207575456572874412075754565731370
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023689150889151341943042560020241777920x7f31253605000x7f3019636e406435326435325093251482646553661044723149848350244360848012075754565791051120757545659812231207575456640554112075754566474982
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023889150889151341943042560028241802880x7f31253604000x7f3019636e804011484011483703632091926553630153379930225520120796641612075754566506070120757545667033001207575456696361912075754567014575
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024089150889151341943042560024241827840x7f31253603000x7f3019636ec0218597218597251711748784655361840333251588121073803528412075754567043960120757545672442581207575456738025712075754567382990
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024289150889151341943042560024241863040x7f3125360a000x7f3019636f004886844886844324939094806553645784323437487920183323117212075754567443933120757545676367361207575456795353512075754568025434
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024489150889151341943042560024241893120x7f31253609000x7f3019636f40242364242364273631938920655362149954851779921086186860812075754568063735120757545682538541207575456840601312075754568408656
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024689150889151341943042560020241907840x7f31253608000x7f3019636f807867567867566132362940566553674963753661222190300036997212075754568467816120757545686591321207575456917881012075754569248747
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024889150889151341943042560028241937920x7f31253607000x7f3019636fc04582534582534155036660326553638610738734827640154628082812075754569275196120757545694767291207575456977688812075754569845326
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025089150889151341943042560024241968000x7f31253606000x7f3019637000247741247741281461981936655362190003571820072087788335212075754569871946120757545700850461207575457024088612075754570244217
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025289150889151341943042560024242010880x7f31253605000x7f30196370405956935956934993247655526553656282899045951640225317031212075754570306363120757545704964051207575457088392312075754570927217
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025489150889151341943042560024242046080x7f31253604000x7f30196370802795242795242952722362006553625136534220755130100735434012075754570977119120757545711676021207575457134520112075754571348149
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025689150889151341943042560020242060800x7f31253603000x7f30196370c09283899283896799374271206553689013062772414000356234390812075754571409192120757545716055201207575457221815812075754572287374
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025889150889151341943042560028242096000x7f3125360a000x7f30196371004989654989654371239917286553646086839638217200184531617212075754572312802120757545725218371207575457284887512075754572916724
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026089150889151341943042560024242131200x7f31253609000x7f30196371402806052806052936822448486553625365978920895800101651978012075754572943544120757545731544741207575457333303312075754573336093
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026289150889151341943042560024242181760x7f31253608000x7f30196371807015247015245827256122006553666576489254265730266491041212075754573396596120757545735968721207575457405399012075754574123667
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026489150889151341943042560024242222080x7f31253607000x7f30196371c03152533152533179725220326553628570258723620920114470721212075754574163802120757545743480691207575457455030812075754574618507
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026689150889151341943042560020242239360x7f31253606000x7f30196372001074892107489215034859914465536102908432083605740411815857212075754574644705120757545748421471207575457555366412075754575625518
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026889150889151341943042560028242279680x7f31253605000x7f30196372405680685680684845245445526553653119024343702210212661179612075754575654843120757545758626231207575457623606212075754576305933
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027089150889151341943042560024242320000x7f31253604000x7f30196372803181323181323163125450646553629049087623919970116386596412075754576331340120757545765370201207575457674102012075754576809298
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027289150889151341943042560024242378240x7f31253603000x7f30196372c08057498057496363464460006553676751446262608110307190492012075754576838452120757545770435781207575457757045612075754577639782
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027489150889151341943042560024242423680x7f3125360a000x7f30196373003497083497083387227976726553631943624326367940127963517612075754577677362120757545778686951207575457809397412075754578163275
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027689150889151341943042560020242435840x7f31253609000x7f30196373401208764120876485127967012065536117139241295034010468739063212075754578190255120757545783925331207575457919349012075754579262908
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027889150889151341943042560028242481280x7f31253608000x7f30196373806378446378445253451027606553660227371749365600241093719612075754579296400120757545795003681207575457992180712075754579990560
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028089150889151341943042560024242526720x7f31253607000x7f30196373c03566683566683707728533526553632434081526709100129926603212075754580024974120757545802312461207575458045876512075754580529412
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028289150889151341943042560024242592640x7f31253606000x7f30196374009095659095656683472765286553687479113171137170350101234812075754580557374120757545807635631207575458136164112075754581431629
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028489150889151341943042560024242648320x7f31253605000x7f30196374404202854202853915833622886553638577479131732640154499771612075754581469259120757545816669201207575458193667912075754582011937
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028689150889151341943042560020242663040x7f31253604000x7f3019637480148761214876123030211900904655361448364550117404010579527783612075754582045099120757545822465971207575458323299312075754583302696
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028889150889151341943042560028242718720x7f31253603000x7f30196374c07784937784936055662279526553674203602560573280297000271612075754583336439120757545835381121207575458405219012075754584120265
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029089150889151341943042560024242774400x7f3125360a000x7f30196375004227254227253880333818086553639143391232211590156762818012075754584148047120757545843576291207575458463138812075754584699963
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029289150889151341943042560012242799360x7f31253609000x7f30196375401125973112597379240900779265536109017360288468010436251700812075754584724939120757545849315471207575458567106412075754585742109
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029489150889151341943042560024242865280x7f31253608000x7f30196375804912854912854523339302886553645792404237595370183359308012075754585779820120757545859715421207575458629026112075754586359607
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029689150889151341943042560020242880000x7f31253607000x7f30196375c01768892176889211751014151144655361724480471139893770689974224812075754586386237120757545865917001207575458776401512075754587833156
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029889150889151341943042560032242945920x7f31253606000x7f30196376009175899175896464873407206553681706507271781980327010598012075754587862360120757545880689741207575458867937112075754588749599
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030089150889151341943042560024243011840x7f31253605000x7f30196376404939804939804469939518486553646101835237846890184597399612075754588775677120757545889828901207575458930288912075754589373939
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030289150889151341943042560012243049600x7f31253604000x7f3019637680133614113361412058410689136655361299542372105356230519999990412075754589399977120757545896027281207575459048208412075754590551077
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030489150889151341943042560024243136000x7f31253603000x7f30196376c06346136346135518650769126553659797522048987640239380294012075754590592424120757545907745631207575459118864112075754591258081
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030689150889151341943042560020243148160x7f3125360a000x7f3019637700233162923316297865118653040655362285089271184962110914217791212075754591290912120757545914921601207575459304191412075754593111896
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030889150889151341943042560020243175680x7f31253609000x7f30196377401201749120174984261961400065536116422378894454510465871818412075754593143835120757545933491131207575459414542912075754594214565
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031089150889151341943042560012243203200x7f31253608000x7f30196377806395896395895057251167206553660874890549642100243682092012075754594240253120757545944508681207575459486654612075754594935144
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031289150889151341943042560012243240960x7f31253607000x7f30196377c0175661317566134514114052912655361715784544138995580686496508812075754594965461120757545951764651207575459633614012075754596406849
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031489150889151341943042560012243288960x7f31253606000x7f30196378001199037119903783022959230465536116298910794284330465378491212075754596445431120757545966369391207575459742333612075754597493058
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031689150889151341943042560020243301120x7f31253605000x7f301963784045834844583484280720366678806553645148508923651003901806122506412075754597526480120757545977260551207575460077900312075754600848314
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031889150889151341943042560020243328640x7f31253604000x7f3019637880232440423244047983118595240655362275540691184355760910398424012075754600880974120757546010911611207575460263563512075754602707519
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032089150889151341943042560012243356160x7f31253603000x7f30196378c01207477120747717661965982465536116654971394637570466802229212075754602734379120757546029445941207575460373611112075754603806261
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032289150889151341943042560012243393920x7f3125360a000x7f301963790034438133443813215423275505126553633856745772738626801354452506012075754603833161120757546040524291207575460633546012075754606406734
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032489150889151341943042560012243441920x7f31253609000x7f30196379402323060232306014882418584488655362277076633184309840911013424412075754606456196120757546066396191207575460817673312075754608246333
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032689150889151341943042560020243454080x7f31253608000x7f301963798090868859086885543240726950886553689779018977253485003591342791212075754608280185120757546084794511207575461453654712075754614609949
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032889150889151341943042560020243481600x7f31253607000x7f30196379c045740284574028283010365922326553645038709573642686701801730790412075754614638682120757546148408661207575461789045312075754617966096
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033089150889151341943042560012243509120x7f31253606000x7f3019637a002327900232790014883018623208655362281926568184651780912953248012075754617994349120757546182099721207575461975012612075754619819972
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332891508891513419430425600122400x7f31253605000x7f3019637a4068120536812053411443544964326553667248089855434029902690106288412075754619854035120757546200602611207575462458952512075754624664906