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

71 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_CYCLESSQ_BUSY_CYCLESSQ_BUSY_CU_CYCLESSQ_WAVESSQ_WAVE_CYCLESGRBM_COUNTGRBM_GUI_ACTIVETA_TA_BUSY_sumTA_SH_FIFO_BUSY_sumTA_BUFFER_COALESCED_READ_CYCLES_sumTA_BUFFER_COALESCED_WRITE_CYCLES_sumTA_ADDR_STALLED_BY_TC_CYCLES_sumTA_TOTAL_WAVEFRONTS_sumTA_ADDR_STALLED_BY_TD_CYCLES_sumTA_DATA_STALLED_BY_TC_CYCLES_sumTA_FLAT_WAVEFRONTS_sumTA_FLAT_READ_WAVEFRONTS_sumTA_FLAT_WRITE_WAVEFRONTS_sumTA_FLAT_ATOMIC_WAVEFRONTS_sumTA_FLAT_COALESCEABLE_WAVEFRONTS_sumTA_SH_FIFO_CMD_BUSY_sumTA_SH_FIFO_ADDR_BUSY_sumTA_SH_FIFO_DATA_BUSY_sumTA_SH_FIFO_DATA_SFIFO_BUSY_sumTA_SH_FIFO_DATA_TFIFO_BUSY_sumTA_SQ_TA_CMD_CYCLES_sumTA_SP_TA_ADDR_CYCLES_sumTA_SP_TA_DATA_CYCLES_sumTA_SH_FIFO_ADDR_STARVED_WHILE_BUSY_CYCLES_sumTA_SH_FIFO_CMD_STARVED_WHILE_BUSY_CYCLES_sumTA_SH_FIFO_DATA_STARVED_WHILE_BUSY_CYCLES_sumTA_TA_SH_FIFO_STARVED_sumTA_BUFFER_WAVEFRONTS_sumTA_BUFFER_READ_WAVEFRONTS_sumTA_BUFFER_WRITE_WAVEFRONTS_sumTA_BUFFER_ATOMIC_WAVEFRONTS_sumTA_BUFFER_TOTAL_CYCLES_sumTA_BUFFER_COALESCABLE_WAVEFRONTS_sumDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000857583857588335544322560083264640x00x7fbf7a204180401684838082485692249552428837271180950210550210554315858542201140017584769104857603747566610485760104857601048576522670015202189753959648536326995415765041943044194304419430400036563500000104857612075005624787169120750227629775681207502276330492512075005872218276
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00285758385758832768256002424124800x00x7fbf7a23510022412077149107936851211502042801428014131904113142006058840960040964096004096688906584500016384163840000229600000409612075005887090134120750227790460221207502277905258212075005887527727
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0048575838575884194304256002424129280x7fc085d839000x7fbf7a2351401746856158296223486854655361366536332183562183562202332121895572002100384752428800524288524288005242882245542722452384000209715220971520000163850000052428812075005887702171120750227791309811207502277926170012075005888204024
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0068575838575884194304256003624136320x7fc085d838000x7fbf7a23518031581282994388445946796553623442879039476539476543483285433561990035077190524288005242885242880004398145843980032000209715220971520000501300000012075005888446564120750227793370601207502277958009712075005889056388
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0088575838575884194304256002824140800x7fc085d837000x7fbf7a2351c0321892830382774529414765536295165771402365402365439954174382991900358806695242880052428852428800040989097409155280002097152209715200006094200000012075005889210845120750227797239361207502277997145412075005889827551
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00108575838575884194304256002424145280x7fc085d836000x7fbf7a2352001766360160359723728642655361269604552207942207942173204021555880002100665352428800524288524288005242882204712322041949000209715220971520000102770000052428812075005889992628120750227801199331207502278024569112075005890419561
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00128575838575884194304256002424149760x7fc085d835000x7fbf7a235240178796816244202403697365536122660029223495223495219833332175853900201567935242880052428852428800524288234624092345758400020971522097152000084180000052428812075005890651241120750227802957711207502278042041012075005891077644
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00148575838575884194304256002424154240x7fc085d834000x7fbf7a2352801722800155192323088228655361503655392153492153492180820521714816002006275352428800524288524288005242882174372421732385000209715220971520000215260000052428812075005891324903120750227804946491207502278061880812075005891738793
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00168575838575884194304256002824161280x7fc085d833000x7fbf7a2352c0368510430965994604794065536254539243460637460637432967524288572100348687285242880052428852428800043188143431831040002097152209715200005987400000012075005891962188120750227806685681207502278091400512075005892621613
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00188575838575884194304256002824168320x7fc085d83a000x7fbf7a23530032762883090418460693546553624998047540953540953543521220431158960036717248524288005242885242880004402023144013426000209715220971520000344000000012075005892777383120750227810588041207502278130808212075005893394289
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00208575838575884194304256002424175360x7fc085d839000x7fbf7a2353401742360158016623380542655361457064092177942177942235267922249134001979454252428800524288524288005242882126826521248456000209715220971520000296520000052428812075005893549828120750227814511211207502278157623912075005893964188
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00228575838575884194304256002424182400x7fc085d838000x7fbf7a2353801764136160330123712760655361367391942205162205162247347922371150002045184152428800524288524288005242882221688122210935000209715220971520000146290000052428812075005894191971120750227816267991207502278175287812075005894606732
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00248575838575884194304256002424189440x7fc085d837000x7fbf7a2353c01696944153270622721932655361613389032121172121172189763621842613002010363952428800524288524288005242882220300122199142000209715220971520000177800000052428812075005894840577120750227818128771207502278193735612075005895257592
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00268575838575884194304256002824199040x7fc085d836000x7fbf7a235400322844030727904586777965536339593910403554403554447408774466045000353907375242880052428852428800043450492434457190002097152209715200002461200000012075005895480957120750227819922361207502278224247312075005896083096
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00288575838575884194304256002824206080x7fc085d835000x7fbf7a23544032019603018183450068196553632678829440024440024444389128443584570036337166524288005242885242880004340447843399303000209715220971520000429300000012075005896250818120750227823851921207502278263159012075005896852806
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00308575838575884194304256002424213120x7fc085d834000x7fbf7a2354801715632154514122942894655361580242642144532144532216504322083595002090554152428800524288524288005242882213159322118648000209715220971520000366720000052428812075005897024686120750227827437491207502278286806812075005897433405
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00328575838575884194304256002424220160x7fc085d833000x7fbf7a2354c0170110415370602275539665536160928564212637212637219550942190943400211502425242880052428852428800524288214807792146661300020971522097152000055620000052428812075005897659295120750227829192671207502278304406612075005898067103
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00348575838575884194304256002424227200x7fc085d83a000x7fbf7a2355001681088151454522450138655361564431712101352101352168585321637967001974891052428800524288524288005242882208012022067550000209715220971520000323470000052428812075005898302931120750227831064661207502278323078512075005898712122
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00368575838575884194304256002824236800x7fc085d839000x7fbf7a23554032490083080288458207856553627113983340612540612543979519437393940035705123524288005242885242880004237545242345758000209715220971520000485800000012075005898928964120750227832842241207502278353478212075005899549778
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00388575838575884194304256002824243840x7fc085d838000x7fbf7a23558032262403068101456634356553630635574940327940327944665932445910970035111495524288005242885242880004016438740071820000209715220971520000809600000012075005899699496120750227836466211207502278389205912075005900302497
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00408575838575884194304256002424250880x7fc085d837000x7fbf7a2355c01670848150859922354347655361633340142088552088552157525521512241001939177952428800524288524288005242882209916822083609000209715220971520000334950000052428812075005900458767120750227840382971207502278416245612075005900866475
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00428575838575884194304256002424257920x7fc085d836000x7fbf7a2356001807808164334224329487655361349506832259752259752225235622031684002051304152428800524288524288005242882195918521950564000209715220971520000167780000052428812075005901084620120750227842170161207502278434213512075005901514089
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00448575838575884194304256002424264960x7fc085d835000x7fbf7a2356401678360151224722412343655361528306692097942097942151943421429103001950303052428800524288524288005242882280222722791163000209715220971520000234280000052428812075005901752121120750227844064541207502278453077312075005902173474
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00468575838575884194304256002824277120x7fc085d834000x7fbf7a235680324861630834874589248365536301483634406076406076450019124494092100360393595242880052428852428800042695940426480510002097152209715200003301000000012075005902397190120750227845917321207502278483957012075005903008536
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00488575838575884194304256002824284160x7fc085d833000x7fbf7a2356c0328951231035584619990965536288286975411188411188451467124504385600365915865242880052428852428800042088082420321300002097152209715200003081800000012075005903171098120750227849530091207502278519652712075005903787503
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00508575838575884194304256002424291200x7fc085d83a000x7fbf7a2357001720792155967023112545655361482787122150982150982182165121666397001954397252428800524288524288005242882207522022066608000209715220971520000249940000052428812075005903950627120750227853366861207502278546132512075005904365978
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00528575838575884194304256002424300800x7fc085d839000x7fbf7a2357401785128162247224004213655361411608692231402231402257698122394112001982299552428800524288524288005242882211635622093170000209715220971520000448040000052428812075005904595886120750227855094841207502278563460312075005905009274
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00548575838575884194304256002424307840x7fc085d838000x7fbf7a2357801695128153619622766250655361578404772118902118902181760821740949001940142752428800524288524288005242882197636921962900000209715220971520000188620000052428812075005905243359120750227856920421207502278581636112075005905648492
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00568575838575884194304256002824320000x7fc085d837000x7fbf7a2357c032421363074869457038776553627639476540526640526644297891441401820034338927524288005242885242880004337334743368539000209715220971520000745500000012075005905851379120750227858651611207502278611299912075005906470069
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00588575838575884194304256002824329600x7fc085d836000x7fbf7a23580032432483077592459208606553634119604540540540540545063030450205880036061411524288005242885242880004175845141712188000209715220971520000352500000012075005906625808120750227862528371207502278649907512075005907229570
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00608575838575884194304256002424339200x7fc085d835000x7fbf7a2358401721576156158023110202655361578626512151962151962230690922222602001972345752428800524288524288005242882129869721285666000209715220971520000299080000052428812075005907386802120750227866369941207502278676163312075005907805551
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00628575838575884194304256002424348800x7fc085d834000x7fbf7a2358801731176156602723130674655361432898792163962163962124153420959029001914758952428800524288524288005242882238359822369879000209715220971520000294690000052428812075005908036299120750227868173121207502278694355112075005908454446
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00648575838575884194304256002424358400x7fc085d833000x7fbf7a2358c01652392149018622110317655361579236172065482065482102898020925648001979560552428800524288524288005242882239839022378820000209715220971520000187160000052428812075005908686127120750227870048311207502278712963012075005909086621
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00668575838575884194304256002824373120x7fc085d83a000x7fbf7a235900319189630325264516476665536305563317398986398986439885724391781300362949395242880052428852428800043266571432601740002097152209715200007180700000012075005909311710120750227871816291207502278742802712075005909910382
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00688575838575884194304256002824382720x7fc085d839000x7fbf7a23594032196323060598455828756553632709591740245340245344973536449557870036297803524288005242885242880004229568142239500000209715220971520000386500000012075005910078224120750227875317061207502278777746412075005910684300
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00708575838575884194304256002424392320x7fc085d838000x7fbf7a2359801755688159464823648477655361390120132194602194602250717522350901001988432752428800524288524288005242882226390222243256000209715220971520000415650000052428812075005910850660120750227878742631207502278799922212075005911269688
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00728575838575884194304256002424401920x7fc085d837000x7fbf7a2359c01753072158371523424269655361527525922191332191332173179121450726002004184352428800524288524288005242882136589221345256000209715220971520000479340000052428812075005911500307120750227880504211207502278817698012075005911911791
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00748575838575884194304256002424411520x7fc085d836000x7fbf7a235a001708848154759622906443655361476715692136052136052163879821484961002024096752428800524288524288005242882195863421942702000209715220971520000362200000052428812075005912152379120750227882377801207502278836257812075005912560477
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00768575838575884194304256002824426240x7fc085d835000x7fbf7a235a40322752030639694567888565536322042300403439403439444032804432186000335268405242880052428852428800044143339441379910002097152209715200001560900000012075005912777590120750227884137781207502278866225612075005913391121
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00788575838575884194304256002824435840x7fc085d834000x7fbf7a235a8031358082975105443912106553635571833239197539197543694472436772190035672507524288005242885242880004232085742264361000209715220971520000411300000012075005913541771120750227887316951207502278897521312075005914135263
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00808575838575884194304256002424445440x7fc085d833000x7fbf7a235ac01725504156296923120434655361559805142156872156872240597222326692001957438452428800524288524288005242882184152821830717000209715220971520000151890000052428812075005914290312120750227890536121207502278917985112075005914702287
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00828575838575884194304256002424457600x7fc085d83a000x7fbf7a235b0018383121665952245514836553614944500722978822978822176771217132970019339611524288005242885242880052428820693077206556730002097152209715200001054510000052428812075005914927065120750227892284911207502278935521012075005915350662
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00848575838575884194304256002424467200x7fc085d839000x7fbf7a235b401720936153545222730844655361649616152151162151162192957721865090001965451852428800524288524288005242882219724422179072000209715220971520000329670000052428812075005915586180120750227894148891207502278953968812075005915990782
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00868575838575884194304256002824484480x7fc085d838000x7fbf7a235b803287592311638846453920655363324904054109484109484538243645257198003667707552428800524288524288000448697224485063200020971522097152000010522400000012075005916216201120750227895886471207502278984272512075005916819582
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00888575838575884194304256002824494080x7fc085d837000x7fbf7a235bc0323232030617864559713565536307576783404039404039446025124449502200344949175242880052428852428800044121367441153670002097152209715200001335800000012075005916953060120750227899102451207502279015360212075005917566350
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00908575838575884194304256002424503680x7fc085d836000x7fbf7a235c001728112155754923098003655361439087652160132160132172154021524599001967784652428800524288524288005242882194294621926328000209715220971520000145770000052428812075005917715697120750227902228821207502279034736112075005918132802
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00928575838575884194304256002424515840x7fc085d835000x7fbf7a235c401831360166217524444186655361586313002289192289192232631021704583001810232652428800524288524288005242882135101921300718000209715220971520000443070000052428812075005918351980120750227903985601207502279052495912075005918779985
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00948575838575884194304256002424525440x7fc085d834000x7fbf7a235c801669464150592422320163655361551970662086822086822103189320896387001947149452428800524288524288005242882132006921305926000209715220971520000169430000052428812075005919027305120750227905851191207502279071039712075005919435503
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00968575838575884194304256002824542720x7fc085d833000x7fbf7a235cc0330519231411114672403165536350053896413148413148451695554496242200352725935242880052428852428800043684189436284160002097152209715200007723500000012075005919664178120750227907603171207502279101663512075005920281906
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00988575838575884194304256002824554880x7fc085d83a000x7fbf7a235d00320452830444844538556065536272565155400565400565428091414243350400358984155242880052428852428800044254528442501270002097152209715200002388400000012075005920437776120750227910859141207502279133311212075005921041458
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001008575838575884194304256002424567040x7fc085d839000x7fbf7a235d401767400160615023733963655361394436432209242209242184381421561803001906748252428800524288524288005242882152409821509674000209715220971520000133340000052428812075005921201215120750227914001511207502279152495012075005921612689
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001028575838575884194304256002424581760x7fc085d838000x7fbf7a235d8018472081668905246388086553615281004623090023090020508263194758200017657094524288005242885242880052428818637054184749630002097152209715200001898790000052428812075005921842096120750227915745501207502279170350812075005922279368
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001048575838575884194304256002424593920x7fc085d837000x7fbf7a235dc01724784156585823148737655361555916902155972155972230223322195159001968189652428800524288524288005242882241135722391271000209715220971520000205650000052428812075005922490761120750227917633481207502279188894712075005922905482
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001068575838575884194304256002824613760x7fc085d836000x7fbf7a235e003317608315435246905740655363574470144147004147004549381045321224003662632352428800524288524288000405836054038477000020971522097152000010896700000012075005923137112120750227919393461207502279219614412075005923752536
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001088575838575884194304256002824625920x7fc085d835000x7fbf7a235e4031699203002021446840456553628497306539623939623943695799435921240036236002524288005242885242880004160884041539927000209715220971520000378800000012075005923913285120750227922663831207502279251358112075005924513320
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001108575838575884194304256002424638080x7fc085d834000x7fbf7a235e801714840154154822878330655361541724162143542143542183906821686763002028830352428800524288524288005242882173686121724586000209715220971520000205090000052428812075005924678797120750227925876611207502279271325912075005925084311
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001128575838575884194304256002424652800x7fc085d833000x7fbf7a235ec017960561609465238010106553616618083622450622450617170033155497020015774460524288005242885242880052428817060128168184840002097152209715200003037780000052428812075005925313236120750227927622191207502279289149812075005925727997
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001148575838575884194304256002424664960x7fc085d83a000x7fbf7a235f001692184151899422484277655361596280972115222115222109625720953627001918772652428800524288524288005242882159130121577898000209715220971520000342970000052428812075005925965488120750227929518171207502279307677612075005926386511
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001168575838575884194304256002824684800x7fc085d839000x7fbf7a235f40319723230356654510911565536352114199399653399653440026364390018900317765435242880052428852428800039724689395597870002097152209715200004597200000012075005926609114120750227931257361207502279338061312075005927210051
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001188575838575884194304256002824696960x7fc085d838000x7fbf7a235f80360185630191824507916765536326893953450231450231442665354422046000367100025242880052428852428800043452678434479170002097152209715200003590800000012075005927370860120750227934495731207502279373165012075005928023793
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001208575838575884194304256002424709120x7fc085d837000x7fbf7a235fc01718184153750622746906655361600488652147722147722170153421569595002059428852428800524288524288005242882176473521733418000209715220971520000331740000052428812075005928177659120750227937954901207502279392172912075005928583854
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001228575838575884194304256002424723840x7fc085d836000x7fbf7a2360001767792160688923787614655361717906222209732209731162843096944340085447495242880052428852428800524288956938389814810002097152209715200004484480000052428812075005928790578120750227939710081207502279410796712075005929221489
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001248575838575884194304256002424736000x7fc085d835000x7fbf7a2360401709056154283822811538655361441461432136312136312132816621096286001896069152428800524288524288005242882206645122042419000209715220971520000199020000052428812075005929456816120750227941714861207502279429596512075005929863272
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001268575838575884194304256002824758400x7fc085d834000x7fbf7a236080335507231797504727588265536338436837419383419383448276934444931500361292235242880052428852428800039410574392068230002097152209715200006413600000012075005930089873120750227943470051207502279460556212075005930710506
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001288575838575884194304256002824770560x7fc085d833000x7fbf7a2360c0317707230101774496484165536351318563397133397133442963414427116700352231885242880052428852428800043281823432590040002097152209715200003878600000012075005930871275120750227946774021207502279492891912075005931475318
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001308575838575884194304256002424782720x7fc085d83a000x7fbf7a2361001726320155267523103046655361567699192157892157892161505921403208001963852852428800524288524288005242882126438421238350000209715220971520000252150000052428812075005931635545120750227950001191207502279512475812075005932041710
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001328575838575884194304256002424800000x7fc085d839000x7fbf7a2361401842712167467324814186655361954113352303382303381048235886632470080259035242880052428852428800524288946330888564430002097152209715200006473210000052428812075005932270966120750227951749971207502279531723612075005932688242
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001348575838575884194304256002424812160x7fc085d838000x7fbf7a2361801697024153667322717993655361492154682121272121272102132820723555002033495352428800524288524288005242882156221521536372000209715220971520000303780000052428812075005932926014120750227953767551207502279550283412075005933337268
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001368575838575884194304256002824834560x7fc085d837000x7fbf7a2361c03316736313843246638235655363488066794145914145914401278243635234003439443352428800524288524288000386303883843293900020971522097152000020080700000012075005933566604120750227955532341207502279581147212075005934175045
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001388575838575884194304256002824849280x7fc085d836000x7fbf7a236200318756030061254480292965536329550303398444398444440952524407326500358456055242880052428852428800041525893414661760002097152209715200006658600000012075005934335092120750227958794711207502279612698912075005934907366
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001408575838575884194304256002424864000x7fc085d835000x7fbf7a2362401831080164511624306896655361434958422288842288842166896521228297002073950652428800524288524288005242882190907221877277000209715220971520000261920000052428812075005935075027120750227961991481207502279632490712075005935486732
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001428575838575884194304256002424881280x7fc085d834000x7fbf7a236280190978417512622598696865536208442249238722238722848615268128680049495115242880052428852428800524288733117566275810002097152209715200007228340000052428812075005935714506120750227963733861207502279652282512075005936146408
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001448575838575884194304256002424896000x7fc085d833000x7fbf7a2362c01687216151364622344148655361633162592109012109012151774621418175001960094452428800524288524288005242882169857621672447000209715220971520000388310000052428812075005936405149120750227966005841207502279672586312075005936821883
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001468575838575884194304256002824920960x7fc085d83a000x7fbf7a2363003334144315170146900156655363124528114167674167673964630538429265003493012452428800524288524288000402819184010896600020971522097152000015465700000012075005937053604120750227967751431207502279703946112075005937672825
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001488575838575884194304256002824935680x7fc085d839000x7fbf7a23634032170003051698454208506553624281383040212440212442915672424954830035575740524288005242885242880004178736541736460000209715220971520000994600000012075005937832962120750227971127401207502279739433712075005938442445
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001508575838575884194304256002424950400x7fc085d838000x7fbf7a2363801791656162605624000402655361514693642239562239562261768022335267001950644052428800524288524288005242882236898522338690000209715220971520000425830000052428812075005938603484120750227974604171207502279758617612075005939025919
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001528575838575884194304256002424967680x7fc085d837000x7fbf7a2363c0201195218513722750303165536219872977251493251493794929263259990032000615242880052428852428800524288562747148766670002097152209715200007789400000052428812075005939248623120750227976367351207502279779385412075005939684543
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001548575838575884194304256002424982400x7fc085d836000x7fbf7a2364001743832158591123379680655361546662302179782179782171651221440991001893355752428800524288524288005242882198845821965996000209715220971520000419500000052428812075005939917606120750227978551331207502279798025212075005940343859
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015685758385758841943042560028241007360x7fc085d835000x7fbf7a2364403314304311963446345970655363081502154142874142873884650237457263002564210652428800524288524288000309003063039741100020971522097152000039403400000012075005940546205120750227980356121207502279830200912075005941164373
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015885758385758841943042560028241022080x7fc085d834000x7fbf7a236480320751230442134534250165536340505625400938400938446206674458943300350435955242880052428852428800043300614432791180002097152209715200001105500000012075005941318269120750227983808881207502279862680612075005941919096
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016085758385758841943042560024241036800x7fc085d833000x7fbf7a2364c01766680160085823657160655361480012922208342208342162349021217199001911763652428800524288524288005242882110384421084015000209715220971520000481360000052428812075005942085225120750227986994461207502279882520412075005942500376
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016285758385758841943042560024241056640x7fc085d83a000x7fbf7a236500209572819435552889109565536233063384261965261965713201155728290028290095242880052428852428800524288590179851493890002097152209715200007783340000052428812075005942729272120750227988730441207502279903800312075005943167265
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016485758385758841943042560024241071360x7fc085d839000x7fbf7a2365401779368158862123518706655361552167062224202224202173617221461621001924501652428800524288524288005242882193587921922257000209715220971520000463190000052428812075005943406290120750227990988021207502279922440112075005943827763
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016685758385758841943042560028241098880x7fc085d838000x7fbf7a2365803238400304686345314409655363188596224047994047993332888931267997002454025452428800524288524288000304478752995304300020971522097152000055852200000012075005944054013120750227992733601207502279953735812075005944667934
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016885758385758841943042560028241113600x7fc085d837000x7fbf7a2365c0322012030405594530976465536274449308402514402514429299334256750800357449595242880052428852428800043458872434541450002097152209715200001898800000012075005944830276120750227996026371207502279984887512075005945440450
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017085758385758841943042560024241128320x7fc085d836000x7fbf7a2366001799232164297024193193655361533796802249032249032266312422291835001901394352428800524288524288005242882194215621913501000209715220971520000797070000052428812075005945595388120750227999136751207502280003959412075005946022061
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017285758385758841943042560024241148160x7fc085d835000x7fbf7a236640220898420411123032815765536242341776276122276122682393153150600024724775242880052428852428800524288532753945479930002097152209715200008028700000052428812075005946241098120750228000925531207502280026551212075005946700291
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017485758385758841943042560024241162880x7fc085d834000x7fbf7a2366801668224150907722301440655361558970232085272085272107421220880168001904194852428800524288524288005242882173406521700187000209715220971520000490010000052428812075005946910482120750228003258311207502280045143012075005947321796
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017685758385758841943042560028241190400x7fc085d833000x7fbf7a2366c03345216313758346602701655363370431214181514181513138600729080169001525929752428800524288524288000228660112210492900020971522097152000085450700000012075005947547265120750228005018291207502280075334712075005948161186
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017885758385758841943042560028241207680x7fc085d83a000x7fbf7a23670032602723096189460453276553629470624840753340753345181075451204310035826654524288005242885242880003985764439763160000209715220971520000405900000012075005948314952120750228008199071207502280106582412075005948928031
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018085758385758841943042560024241224960x7fc085d839000x7fbf7a2367401850344165532524438423655361521878592312922312922233014821912975001947804952428800524288524288005242882245350322418668000209715220971520000656570000052428812075005949092877120750228011381441207502280126470312075005949513830
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018285758385758841943042560024241247360x7fc085d838000x7fbf7a236780229917621445613183554365536258177450287396287396667897552190960022771825242880052428852428800524288491145541437930002097152209715200007533280000052428812075005949743627120750228013131821207502280149606012075005950214372
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018485758385758841943042560024241264640x7fc085d837000x7fbf7a2367c01815784165061124334542655361539802892269722269722215279221716372002041159852428800524288524288005242882223298622191224000209715220971520000363490000052428812075005950450350120750228015571801207502280168373912075005950872895
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018685758385758841943042560020241279360x7fc085d836000x7fbf7a23680032728163117654463775236553637847604640910140910122266984149609470026863665242880052428852428800096890016239194000209715220971520000359300900000012075005951097913120750228017354181207502280199797612075005951703840
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018885758385758841943042560028241296640x7fc085d835000x7fbf7a23684032562403063148454845786553625761092540702940702943197739429073870034689473524288005242885242880004232780042287911000209715220971520000395200000012075005951863436120750228020683751207502280232021312075005952481465
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019085758385758841943042560024241313920x7fc085d834000x7fbf7a2368801783168161972023938233655361615630972228952228952245274822083305001843494752428800524288524288005242882198413221944399000209715220971520000480290000052428812075005952641422120750228023843721207502280250997112075005953053788
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019285758385758841943042560024241336320x7fc085d833000x7fbf7a2368c0241220822512933345241765536270721802301525301525657244551384660022389685242880052428852428800524288511336243401080002097152209715200008263040000052428812075005953285559120750228025581311207502280274884912075005953819511
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019485758385758841943042560024241353600x7fc085d83a000x7fbf7a2369001755432159959423581065655361561471482194282194282174062421284493001979257652428800524288524288005242882164930921593269000209715220971520000679540000052428812075005953989137120750228028082091207502280293476812075005954418815
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019685758385758841943042560020241368320x7fc085d839000x7fbf7a23694034898803322479494920976553640214340043623443623422751916147909630018315955242880052428852428800093810165792331000209715220971520000372024900000012075005954641479120750228029840471207502280326612512075005955275407
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019885758385758841943042560028241385600x7fc085d838000x7fbf7a236980322065630396784522472865536321270484402581402581439574384389429900360781525242880052428852428800041577660415153050002097152209715200001683000000012075005955430916120750228033386041207502280358724212075005956035289
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020085758385758841943042560024241402880x7fc085d837000x7fbf7a2369c01818944164564724295799655361567566472273672273672257314822073949001940173152428800524288524288005242882140694721359720000209715220971520000413910000052428812075005956198953120750228036605211207502280378660012075005956622540
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020285758385758841943042560024241427840x7fc085d836000x7fbf7a236a00264979224881703695600165536299773052331223331223693101453934460024053065242880052428852428800524288518366743659740002097152209715200008193890000052428812075005956849683120750228038365191207502280404611812075005957411176
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020485758385758841943042560024241447680x7fc085d835000x7fbf7a236a4018167521641991241663246553615361156122709322709321870611211761820018688741524288005242885242880052428821791921217354300002097152209715200001103550000052428812075005957582424120750228041241971207502280425299612075005958011201
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020685758385758841943042560020241457280x7fc085d834000x7fbf7a236a8037620883606954537397746553644025743947026047026023402589149757740017326555242880052428852428800088854655201016000209715220971520000379332300000012075005958227964120750228043032351207502280460947212075005958879204
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020885758385758841943042560028241477120x7fc085d833000x7fbf7a236ac0325015230694904563340265536312423124406268406268446516154459621400359435505242880052428852428800039709759396099640002097152209715200001408700000012075005959025917120750228046771521207502280492531012075005959640599
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021085758385758841943042560024241496960x7fc085d83a000x7fbf7a236b0017588321592699234377266553615296786221985321985320498400197719750019086859524288005242885242880052428821344337213094800002097152209715200001083310000052428812075005959794335120750228049917091207502280511874812075005960213243
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021285758385758841943042560024241521920x7fc085d839000x7fbf7a236b40284977626861383991747165536325494963356221356221684915152807030023946295242880052428852428800524288510395243127300002097152209715200008103760000052428812075005960437029120750228051701071207502280539714512075005961023419
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021485758385758841943042560024241541760x7fc085d838000x7fbf7a236b8017902721626863239079716553615837933922378322378320574267197096070017843752524288005242885242880052428821317868212488170002097152209715200001375960000052428812075005961188225120750228054809851207502280560706412075005961609258
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021685758385758841943042560020241556480x7fc085d837000x7fbf7a236bc040505363867092576255126553647121919650631650631623306076147878400016282215242880052428852428800091408585453242000209715220971520000380451400000012075005961837612120750228056574631207502280601506012075005962517896
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021885758385758841943042560028241576320x7fc085d836000x7fbf7a236c00330135230903834597478965536275123306412668412668428107914234966600361763285242880052428852428800039643260395258510002097152209715200003595400000012075005962680969120750228060868991207502280633713712075005963297816
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022085758385758841943042560024241596160x7fc085d835000x7fbf7a236c4018144881638677242414076553615782841622681022681020443727194979410017788717524288005242885242880052428820152930200525920002097152209715200001420020000052428812075005963453625120750228064059361207502280653377512075005963868616
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022285758385758841943042560024241623680x7fc085d834000x7fbf7a236c80305267228964834303315765536351129440381583381583683915752313460024346425242880052428852428800524288510487343111140002097152209715200007994120000052428812075005964098884120750228065828951207502280682577312075005964689903
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022485758385758841943042560024241646080x7fc085d833000x7fbf7a236cc017854961604820237115316553616076484122318622318618853431174905280016391219524288005242885242880052428819911546197689510002097152209715200001912350000052428812075005964855831120750228069016121207502280703009112075005965278857
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022685758385758841943042560020241663360x7fc085d83a000x7fbf7a236d0048796644424893659303576553654089320860995760995723940392149902670012885475242880052428852428800089910155223564000209715220971520000387704500000012075005965496632120750228070843301207502280745952712075005966238290
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022885758385758841943042560028241685760x7fc085d839000x7fbf7a236d403282968308395245792943655363211619144103704103704369746143438119003091679852428800524288524288000392250153908659900020971522097152000013406200000012075005966392647120750228075411261207502280780304412075005967019872
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023085758385758841943042560024241708160x7fc085d838000x7fbf7a236d8017617281595225234661396553616458702322021522021517903796163875700015284959524288005242885242880052428819270666190979820002097152209715200002080630000052428812075005967174780120750228078752031207502280800464212075005967587858
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023285758385758841943042560024241740800x7fc085d837000x7fbf7a236dc0349386433053974917473065536400489590436732436732669169151827320022872785242880052428852428800524288502603142474040002097152209715200008243070000052428812075005967817274120750228080635211207502280834159912075005968448187
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023485758385758841943042560024241765760x7fc085d836000x7fbf7a236e0017752161596792236426196553617489264622190122190114294808123488520011904536524288005242885242880052428813908517134906420002097152209715200005335120000052428812075005968615197120750228084211181207502280855647712075005969030709
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023685758385758841943042560020241777920x7fc085d835000x7fbf7a236e4051440884981360743222666553661161843164301064301024001286147933590015205475242880052428852428800090867555301826000209715220971520000388123600000012075005969255076120750228086052771207502280902815312075005970031379
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023885758385758841943042560028241802880x7fc085d834000x7fbf7a236e803252352306816345438484655363228225564065434065433472249833643189002311193952428800524288524288000327704283253386600020971522097152000036266600000012075005970191366120750228091171121207502280937743012075005970800949
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024085758385758841943042560024241827840x7fc085d833000x7fbf7a236ec018186881633396241733566553616007069222733522733512417682101011970010201189524288005242885242880052428813635056132060600002097152209715200004537290000052428812075005970961568120750228094491091207502280958430812075005971393630
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024285758385758841943042560024241863040x7fc085d83a000x7fbf7a236f00388344037276945555483765536452200366485429485429660335051315520023844355242880052428852428800524288503413042392690002097152209715200008389560000052428812075005971622526120750228096310271207502280994478512075005972282352
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024485758385758841943042560024241893120x7fc085d839000x7fbf7a236f40194044017784712643991565536214164578242554242554758803652446460015621335242880052428852428800524288518377443429260002097152209715200008329480000052428812075005972449042120750228100286241207502281018158212075005972885212
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024685758385758841943042560020241907840x7fc085d838000x7fbf7a236f8062657686109244911326426553675059600678322078322024656150148546430014769465242880052428852428800089357755076021000209715220971520000393906800000012075005973110822120750228102339021207502281074925712075005973975929
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024885758385758841943042560028241937920x7fc085d837000x7fbf7a236fc03654976346802651259454655363803389404568714568712597429824510900001692707852428800524288524288000235640732311792200020971522097152000045776000000012075005974139614120750228108313371207502281112925412075005974790393
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025085758385758841943042560024241968000x7fc085d836000x7fbf7a237000196792018146932696285365536218963289245989245989759250852775220017980085242880052428852428800524288475256639187260002097152209715200008752170000052428812075005974939500120750228112137331207502281136877212075005975382263
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025285758385758841943042560024242010880x7fc085d835000x7fbf7a237040474304045784746826874865536560426029592879592879684167953640580023403735242880052428852428800524288504152142881440002097152209715200009427210000052428812075005975612280120750228114158111207502281179996812075005976342076
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025485758385758841943042560024242046080x7fc085d834000x7fbf7a237080221495220576023061693465536249380136276868276868715268349117850018830495242880052428852428800524288495700341152510002097152209715200008598200000052428812075005976513846120750228118850871207502281206172612075005976965675
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025685758385758841943042560020242060800x7fc085d833000x7fbf7a2370c073967367232040107923760655368896599659245919245912494693215146669009493755242880052428852428800089358665094082000209715220971520000390422900000012075005977195593120750228121138851207502281272140012075005978149175
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025885758385758841943042560028242096000x7fc085d83a000x7fbf7a237100400012838480755721835665536460770582500015500015180851201622309700581321552428800524288524288000128555331218723900020971522097152000066384800000012075005978309763120750228127937191207502281311995612075005978986922
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026085758385758841943042560024242131200x7fc085d839000x7fbf7a237140226952821053733130583965536254684458283690283690761996353403950015562365242880052428852428800524288508254542371130002097152209715200008112490000052428812075005979152810120750228131964351207502281337467412075005979610530
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026285758385758841943042560024242181760x7fc085d838000x7fbf7a237180583116854212078086890465536665189854728895728895692460054569050023135985242880052428852428800524288519394344163740002097152209715200009528910000052428812075005979837863120750228134236331207502281387898912075005980661944
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026485758385758841943042560024242222080x7fc085d837000x7fbf7a2371c0251912823431893484933665536284804950314890314890732969550211600016155075242880052428852428800524288489799440570050002097152209715200008524880000052428812075005980833263120750228139597881207502281415882712075005981383726
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026685758385758841943042560020242239360x7fc085d836000x7fbf7a237200850526483538511246750596553610283166731063157106315725009267149255090015591935242880052428852428800090099825119375000209715220971520000396754700000012075005981545376120750228142305061207502281494042012075005982597972
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026885758385758841943042560028242279680x7fc085d835000x7fbf7a237240454584043734856514648465536516693374568229568229155197071368359700428388552428800524288524288000120916281138280200020971522097152000068484500000012075005982759262120750228150192991207502281539177612075005983491813
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027085758385758841943042560024242320000x7fc085d834000x7fbf7a237280252900823728393528799765536286350536316125316125722789049758220016087105242880052428852428800524288503561042450890002097152209715200008473280000052428812075005983647463120750228154688951207502281567081312075005984197084
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027285758385758841943042560024242378240x7fc085d833000x7fbf7a2372c0663255262642519351893865536768003430829068829068698666855130010023520805242880052428852428800524288522567044513690002097152209715200009673870000052428812075005984353475120750228157405721207502281626568812075005985243268
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027485758385758841943042560024242423680x7fc085d83a000x7fbf7a237300280885626322753907054865536315494889351106351106715663449120520015246745242880052428852428800524288472605539349950002097152209715200008535510000052428812075005985418854120750228163512871207502281657448512075005985985407
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027685758385758841943042560020242435840x7fc085d839000x7fbf7a237340965790494849001416335476553611694927291207237120723725764684155200810013833555242880052428852428800084971334585577000209715220971520000396601900000012075005986147589120750228166458441207502281744279712075005987295582
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027885758385758841943042560028242481280x7fc085d838000x7fbf7a237380512267249515417381622465536593278714640333640333156593501386266100393963852428800524288524288000121572491144075200020971522097152000066469800000012075005987459867120750228175165571207502281793351312075005988229918
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028085758385758841943042560024242526720x7fc085d837000x7fbf7a2373c0281768826609723960932465536323561989352210352210726164249497450015037695242880052428852428800524288482987239751360002097152209715200008449930000052428812075005988397470120750228180072721207502281823207012075005988971677
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028285758385758841943042560024242592640x7fc085d836000x7fbf7a2374007268416711113010618079765536874994100908551908551745399158635970022970265242880052428852428800524288554945347704730002097152209715200008956990000052428812075005989137154120750228183077491207502281890406412075005990075999
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028485758385758841943042560024242648320x7fc085d835000x7fbf7a2374403341032318135847310216655363872672644176284176287550584542111100209610452428800524288524288005242885181200428080700020971522097152000010074470000052428812075005990250864120750228189835831207502281925222112075005990859615
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028685758385758841943042560020242663040x7fc085d834000x7fbf7a23748011916136117342611752082796553614456137261489516148951625248089148964660011593105242880052428852428800084822004567285000209715220971520000397647900000012075005991031725120750228193301401207502282031381112075005992372928
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028885758385758841943042560028242718720x7fc085d833000x7fbf7a2374c0620623260485599023468565536738006319775778775778154710271342913700334460152428800524288524288000119320671121469900020971522097152000065466200000012075005992534668120750228203910911207502282092148612075005993397482
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029085758385758841943042560024242774400x7fc085d83a000x7fbf7a2375003372464321064847749667655363905890744215574215577702724548458700206880352428800524288524288005242885248098438127900020971522097152000010443900000052428812075005993544224120750228209973251207502282126948312075005994159167
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029285758385758841943042560012242799360x7fc085d839000x7fbf7a23754090060648842732132051232655361089959540112575711257571892505888207260077042352428800524288524288005242888146760437762200020971522097152000037665160000052428812075005994323973120750228213421221207502282207923612075005995404331
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029485758385758841943042560024242865280x7fc085d838000x7fbf7a237580390758437453955575751465536456120811488447488447758267354185750019865965242880052428852428800524288513281242831050002097152209715200009826370000052428812075005995578795120750228221635551207502282247811212075005996244923
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029685758385758841943042560020242880000x7fc085d837000x7fbf7a2375c014146392139827922087686706553617241034511768298176829826136461151415680014035185242880052428852428800090338675076821000209715220971520000402497400000012075005996400031120750228225491511207502282371906112075005997925677
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029885758385758841943042560032242945920x7fc085d836000x7fbf7a2376007336808717537210713672865536813806095917100917100146174961289925100393418252428800524288524288000118666031110999400020971522097152000065904300000012075005998085003120750228237909001207502282440321512075005999032964
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030085758385758841943042560024243011840x7fc085d835000x7fbf7a2376403951656376829056125326655364597550314939564939567406586535432300210054152428800524288524288005242885216109434530500020971522097152000010194210000052428812075005999194635120750228244776141207502282479521112075005999863077
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030285758385758841943042560012243049600x7fc085d834000x7fbf7a2376801069164810529032157228147655361297295641133645513364551836049885314850055184052428800524288524288005242887806368416225000020971522097152000037071640000052428812075006000037712120750228248670501207502282574352312075006001264822
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030485758385758841943042560024243136000x7fc085d833000x7fbf7a2376c05059688488806472776046655365976361596324606324607267830528311300201261352428800524288524288005242885053711421685500020971522097152000010062790000052428812075006001437844120750228258328001207502282624063712075006002199469
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030685758385758841943042560020243148160x7fc085d83a000x7fbf7a23770018641256184911852762451806553622844892162330156233015625482668149871340013277315242880052428852428800090045105045691000209715220971520000401253300000012075006002363313120750228263249551207502282787182312075006004252124
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030885758385758841943042560020243175680x7fc085d839000x7fbf7a237740964701694371991408789416553611622788611205876120587625290652149401610015453705242880052428852428800087763124870023000209715220971520000396070200000012075006004418072120750228279876621207502282877837612075006005559543
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031085758385758841943042560012243203200x7fc085d838000x7fbf7a2377805116776495520673919005655366079991346395966395961861518688272520069877552428800524288524288005242887995100425835700020971522097152000038530360000052428812075006005721164120750228288948551207502282930797212075006006476357
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031285758385758841943042560012243240960x7fc085d837000x7fbf7a2377c01405220813893517207519166655361713605869175652517565251910139787203590071957752428800524288524288005242887836927418261700020971522097152000036969280000052428812075006006638849120750228294246111207502283058220212075006008121564
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031485758385758841943042560012243288960x7fc085d836000x7fbf7a23780095768729419004140682739655361161828410119710811971081827622985635620068668652428800524288524288005242887879704422983500020971522097152000037243120000052428812075006008294897120750228307113211207502283149563512075006009426980
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031685758385758841943042560020243301120x7fc085d835000x7fbf7a23784036666600365056275455163666553645155849654583324458332426732671156806230011892225242880052428852428800089213444955847000209715220971520000401647800000012075006009592919120750228316129141207502283466089012075006012991695
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031885758385758841943042560020243328640x7fc085d834000x7fbf7a2378801857790418420076275191475655362274978871232223723222372599609815352813008785925242880052428852428800084519264542556000209715220971520000398324000000012075006013153536120750228347794491207502283632039712075006015036325
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032085758385758841943042560012243356160x7fc085d833000x7fbf7a2378c096064649453392141193708655361165874168120080712008071865887286143540055876952428800524288524288005242888068651427830200020971522097152000038285240000052428812075006015203525120750228364389561207502283722775012075006016344155
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032285758385758841943042560012243393920x7fc085d83a000x7fbf7a2379002753555227380203409119298655363385564351344194334419431758637680697720072412952428800524288524288005242887503100404372800020971522097152000034185400000052428812075006016506988120750228373453491207502283962597112075006019136574
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032485758385758841943042560012243441920x7fc085d839000x7fbf7a2379401857309618415648275105620655362274095117232163623216361921484887296400090758952428800524288524288005242887918932420628400020971522097152000037827240000052428812075006019308915120750228397518901207502284128707812075006021187385
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032685758385758841943042560020243454080x7fc085d838000x7fbf7a23798072680984725260221083989120655368976801495908512290851222661522815629447008719465242880052428852428800090200885069353000209715220971520000400860100000012075006021356800120750228414057971207502284745775012075006027749420
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032885758385758841943042560020243481600x7fc085d837000x7fbf7a2379c03656688836410988544129327655364502382453457086045708602398767114344527007981065242880052428852428800087413464986700000209715220971520000388315500000012075006027962326120750228475735891207502285061468512075006031373635
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033085758385758841943042560012243509120x7fc085d836000x7fbf7a237a001862355218463206275765883655362280343217232794323279431930272088332150081498452428800524288524288005242888036122423454300020971522097152000038332880000052428812075006031529034120750228507313241207502285227035212075006033407555
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332857583857588419430425600122400x7fc085d835000x7fbf7a237a405448834454333224812017734655366724078728681104268110421751183580539620075094252428800524288524288005242887618790417776100020971522097152000035886520000052428812075006033565048120750228523847511207502285690983612075006038439386