Files
rocm-systems/tests/workloads/mixbench2/mi100/SQ_IFETCH_LEVEL.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

46 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjGRBM_COUNTGRBM_GUI_ACTIVESQ_WAVESSQ_IFETCHSQ_IFETCH_LEVELSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000763517763522335544322560083264640x00x7f1e10e04180505857505857524288629145679269510140339212073442306812763120734425526232151207344255294881312073442553060085
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00276351776352232768256002424124800x00x7f1e10e35100285392853951281929217117356812073442567379506120734425676810101207344256768757012073442567692658
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0047635177635224194304256002424129280x7f1f1ca969000x7f1e10e35140214259214259655369175041422401819276412073442567759682120734425679867681207344256811748812073442568121335
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0067635177635224194304256003624136320x7f1f1ca968000x7f1e10e351803930653930656553612451841864782404512812073442568191485120734425683704461207344256862196512073442568692055
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0087635177635224194304256002824140800x7f1f1ca967000x7f1e10e351c0401499401499655369830401369001749950012073442568722141120734425689165231207344256917252212073442569242528
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00107635177635224194304256002424145280x7f1f1ca966000x7f1e10e352002130812130816553610485761607242056461612073442569267755120734425694603601207344256959107912073442569594713
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00127635177635224194304256002424149760x7f1f1ca965000x7f1e10e35240227035227035655369830401487381903742412073442569641490120734425698251581207344256996419712073442569967836
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00147635177635224194304256002424154240x7f1f1ca964000x7f1e10e352802228732228736553610485761465121874190412073442570053776120734425702360361207344257037379512073442570377387
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00167635177635224194304256002824161280x7f1f1ca963000x7f1e10e352c04014274014276553615728642304842942854012073442570422100120734425706099541207344257086435212073442570907833
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00187635177635224194304256002824168320x7f1f1ca96a000x7f1e10e353004006654006656553611796481586962029361612073442570932338120734425711371511207344257139410912073442571435854
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00207635177635224194304256002424175360x7f1f1ca969000x7f1e10e353402096352096356553611141121574012012011212073442571473424120734425716465881207344257177458712073442571778290
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00227635177635224194304256002424182400x7f1f1ca968000x7f1e10e353802182892182896553611141121588852032676012073442571830367120734425720070661207344257213986512073442572143519
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00247635177635224194304256002424189440x7f1f1ca967000x7f1e10e353c02116432116436553611796481636122097782812073442572211586120734425723835441207344257251314312073442572516633
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00267635177635224194304256002824199040x7f1f1ca966000x7f1e10e354003910253910256553618350082597213330105612073442572568198120734425727481821207344257299922012073442573049282
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00287635177635224194304256002824206080x7f1f1ca965000x7f1e10e354403974993974996553613107201766432269083212073442573075060120734425732694591207344257352321712073442573569629
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00307635177635224194304256002424213120x7f1f1ca964000x7f1e10e354802121372121376553612451841772532265980012073442573594476120734425737830561207344257391345512073442573917075
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00327635177635224194304256002424220160x7f1f1ca963000x7f1e10e354c02259072259076553613107201992092544202412073442573963602120734425741524941207344257429089312073442574294577
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00347635177635224194304256002424227200x7f1f1ca96a000x7f1e10e355002078012078016553613107201816022318856012073442574359828120734425745289721207344257465681112073442574660477
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00367635177635224194304256002824236800x7f1f1ca969000x7f1e10e355403935953935956553620971522931963757739612073442574705751120734425748904101207344257514192812073442575184310
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00387635177635224194304256002824243840x7f1f1ca968000x7f1e10e355803919213919216553614417921960092507380412073442575218724120734425753988871207344257564992612073442575691673
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00407635177635224194304256002424250880x7f1f1ca967000x7f1e10e355c02150672150676553613762561870922394481212073442575723623120734425759012841207344257603296312073442576036684
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00427635177635224194304256002424257920x7f1f1ca966000x7f1e10e356002150972150976553615073282112742702924812073442576090454120734425762696021207344257640224112073442576406031
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00447635177635224194304256002424264960x7f1f1ca965000x7f1e10e356402213312213316553614417922037302601683612073442576470440120734425766422401207344257677775912073442576781539
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00467635177635224194304256002824277120x7f1f1ca964000x7f1e10e356804006894006896553623592963225814142608012073442576827153120734425770065581207344257726335712073442577333975
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00487635177635224194304256002824284160x7f1f1ca963000x7f1e10e356c03976993976996553615728642108362696790412073442577359623120734425775486351207344257780255412073442577870763
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00507635177635224194304256002424291200x7f1f1ca96a000x7f1e10e357002107692107696553615073282124152718458812073442577899957120734425780980721207344257822783112073442578231774
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00527635177635224194304256002424300800x7f1f1ca969000x7f1e10e357402088352088356553617039362339602994543612073442578284111120734425784628701207344257859070912073442578594418
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00547635177635224194304256002424307840x7f1f1ca968000x7f1e10e357802206092206096553615728642151612754804012073442578658086120734425788215881207344257895790712073442578961710
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00567635177635224194304256002824320000x7f1f1ca967000x7f1e10e357c03989073989076553626214403596644602915612073442579020008120734425792033461207344257945886412073442579480344
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00587635177635224194304256002824329600x7f1f1ca966000x7f1e10e358003979933979936553617039362279912916423612073442579534515120734425797031831207344257995806212073442580013865
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00607635177635224194304256002424339200x7f1f1ca965000x7f1e10e358402211792211796553616384002304832947221612073442580038691120734425802283001207344258036413912073442580367933
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00627635177635224194304256002424348800x7f1f1ca964000x7f1e10e358802134332134336553619005442916793728440012073442580420681120734425805940581207344258072605712073442580729666
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00647635177635224194304256002424358400x7f1f1ca963000x7f1e10e358c02093952093956553617039362365913023308012073442580794817120734425809606161207344258108861512073442581092630
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00667635177635224194304256002824373120x7f1f1ca96a000x7f1e10e359004675294675296553628835843930795032174012073442581143655120734425813268541207344258162925212073442581676665
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00687635177635224194304256002824382720x7f1f1ca969000x7f1e10e359404000834000836553618350082432043131633612073442581699808120734425818890911207344258214444912073442582191592
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00707635177635224194304256002424392320x7f1f1ca968000x7f1e10e359802163212163216553617694722513543225587212073442582217440120734425824052481207344258253868712073442582542495
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00727635177635224194304256002424401920x7f1f1ca967000x7f1e10e359c02172592172596553620971522972373815422812073442582594601120734425827732461207344258290652512073442582910358
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00747635177635224194304256002424411520x7f1f1ca966000x7f1e10e35a002095692095696553618350082498443189891212073442582972995120734425831460441207344258327532312073442583279274
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00767635177635224194304256002824426240x7f1f1ca965000x7f1e10e35a404089874089876553631457284338715542567212073442583331321120734425835066821207344258376892012073442583836770
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00787635177635224194304256002824435840x7f1f1ca964000x7f1e10e35a803864813864816553619660802641393368990812073442583863399120734425840521191207344258430059712073442584370472
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00807635177635224194304256002424445440x7f1f1ca963000x7f1e10e35ac02148592148596553619005442998813837592812073442584394516120734425845892361207344258472123512073442584724910
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00827635177635224194304256002424457600x7f1f1ca96a000x7f1e10e35b002170572170576553622937603061963936028012073442584778189120734425849513141207344258508603312073442585090019
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00847635177635224194304256002424467200x7f1f1ca969000x7f1e10e35b402124672124676553619660802719433472974012073442585156302120734425853260321207344258545627112073442585459986
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00867635177635224194304256002824484480x7f1f1ca968000x7f1e10e35b804044414044416553634078724574625846570412073442585510751120734425856852301207344258594602812073442586024636
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00887635177635224194304256002824494080x7f1f1ca967000x7f1e10e35bc04632594632596553620971522770353533681612073442586049873120734425862364271207344258653434512073442586602510
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00907635177635224194304256002424503680x7f1f1ca966000x7f1e10e35c002098732098736553620316162753133524134412073442586626735120734425868097031207344258693802312073442586941810
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00927635177635224194304256002424515840x7f1f1ca965000x7f1e10e35c402233872233876553624903683475074473815212073442586993446120734425871751411207344258731386112073442587317969
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00947635177635224194304256002424525440x7f1f1ca964000x7f1e10e35c802131052131056553620971522986753832044012073442587381818120734425875450591207344258767593912073442587679872
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00967635177635224194304256002824542720x7f1f1ca963000x7f1e10e35cc04009314009316553636700164980966356599212073442587731588120734425879077771207344258816649612073442588214996
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00987635177635224194304256002824554880x7f1f1ca96a000x7f1e10e35d003970573970576553622282242975273806300012073442588239512120734425884271341207344258868233312073442588728741
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001007635177635224194304256002424567040x7f1f1ca969000x7f1e10e35d402183872183876553621626883434424402348412073442588755711120734425889344921207344258906937112073442589073452
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001027635177635224194304256002424581760x7f1f1ca968000x7f1e10e35d802277852277856553626869764118945282738412073442589125679120734425893093691207344258945096912073442589454770
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001047635177635224194304256002424593920x7f1f1ca967000x7f1e10e35dc02148832148836553622282243397024342773612073442589517577120734425896836071207344258981416712073442589818406
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001067635177635224194304256002824613760x7f1f1ca966000x7f1e10e35e004118814118816553639321605261456719112012073442589872116120734425900535251207344259031912412073442590366034
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001087635177635224194304256002824625920x7f1f1ca965000x7f1e10e35e403890433890436553623592963110323981607212073442590390820120734425905748021207344259082536112073442590871543
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001107635177635224194304256002424638080x7f1f1ca964000x7f1e10e35e802206252206256553622937603328724253442412073442590894446120734425910869601207344259122087912073442591224890
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001127635177635224194304256002424652800x7f1f1ca963000x7f1e10e35ec02263552263556553628835843855514934386012073442591276636120734425914602371207344259160151712073442591605357
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001147635177635224194304256002424664960x7f1f1ca96a000x7f1e10e35f002084652084656553623592963248104156777212073442591670718120734425918331951207344259196167512073442591965356
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001167635177635224194304256002824684800x7f1f1ca969000x7f1e10e35f404123794123796553641943045524397051287212073442592013786120734425921987931207344259246519212073442592514587
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001187635177635224194304256002824696960x7f1f1ca968000x7f1e10e35f803952813952816553624903683360914297554412073442592538110120734425927223101207344259297654912073442593024404
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001207635177635224194304256002424709120x7f1f1ca967000x7f1e10e35fc02829392829396553624248323647324673843212073442593047928120734425932352681207344259341318712073442593417024
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001227635177635224194304256002424723840x7f1f1ca966000x7f1e10e360002298492298496553630801924863136228288412073442593468279120734425936450251207344259378694412073442593790908
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001247635177635224194304256002424736000x7f1f1ca965000x7f1e10e360402162192162196553624903683405144360402412073442593854447120734425940235831207344259415702212073442594161076
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001267635177635224194304256002824758400x7f1f1ca964000x7f1e10e360804115854115856553644564485937937584487612073442594212432120734425943911011207344259465670012073442594703364
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001287635177635224194304256002824770560x7f1f1ca963000x7f1e10e360c04016754016756553626214403439584382703212073442594728230120734425949203781207344259517909712073442595202562
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001307635177635224194304256002424782720x7f1f1ca96a000x7f1e10e361002197132197136553625559044144245302872812073442595250411120734425954179751207344259555333512073442595557261
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001327635177635224194304256002424800000x7f1f1ca969000x7f1e10e361402318352318356553632768005119476563274012073442595601042120734425957814931207344259592645312073442595930124
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001347635177635224194304256002424812160x7f1f1ca968000x7f1e10e361802084732084736553626214403738794784452012073442595993091120734425961662911207344259629445012073442596298438
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001367635177635224194304256002824834560x7f1f1ca967000x7f1e10e361c04087714087716553647185926261898028392012073442596349704120734425965240491207344259678852812073442596836869
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001387635177635224194304256002824849280x7f1f1ca966000x7f1e10e362003869533869536553627525123914825016309212073442596861495120734425970515661207344259730068512073442597351405
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001407635177635224194304256002424864000x7f1f1ca965000x7f1e10e362402111472111476553626869763803304868819612073442597376321120734425975626031207344259769284312073442597696847
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001427635177635224194304256002424881280x7f1f1ca964000x7f1e10e362802409852409856553634734085232456729752412073442597748423120734425979222811207344259807316112073442598077454
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001447635177635224194304256002424896000x7f1f1ca963000x7f1e10e362c02199952199956553627525123928505025922012073442598161561120734425983297991207344259846611812073442598470034
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001467635177635224194304256002824920960x7f1f1ca96a000x7f1e10e363004096254096256553649807366511638333604412073442598522051120734425986984371207344259896355612073442598984009
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001487635177635224194304256002824935680x7f1f1ca969000x7f1e10e363403937473937476553628835843816544901397212073442599042327120734425992073941207344259946115312073442599506480
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001507635177635224194304256002424950400x7f1f1ca968000x7f1e10e363802197532197536553628180483924015023578812073442599529954120734425997145911207344259984979112073442599853485
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001527635177635224194304256002424967680x7f1f1ca967000x7f1e10e363c02522752522756553636700165518387082295612073442599906924120734426000830691207344260024162812073442600245614
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001547635177635224194304256002424982400x7f1f1ca966000x7f1e10e364002197932197936553628835844548365824392412073442600310064120734426004811471207344260061682612073442600620721
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015676351776352241943042560028241007360x7f1f1ca965000x7f1e10e364403975073975076553651773446833558756647612073442600671946120734426008477051207344260110530412073442601154112
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015876351776352241943042560028241022080x7f1f1ca964000x7f1e10e364803948173948176553630146564319165538588012073442601179139120734426013667421207344260162146112073442601668688
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016076351776352241943042560024241036800x7f1f1ca963000x7f1e10e364c02208832208836553629491205031106435827212073442601698684120734426018886591207344260202577912073442602029900
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016276351776352241943042560024241056640x7f1f1ca96a000x7f1e10e365002636572636576553638666245776107376338812073442602082517120734426022630571207344260242913612073442602432758
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016476351776352241943042560024241071360x7f1f1ca969000x7f1e10e365402131712131716553630146564120325284790012073442602495214120734426026603351207344260279233412073442602796274
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016676351776352241943042560028241098880x7f1f1ca968000x7f1e10e365804009534009536553654394887251969296636412073442602839895120734426030296131207344260328929112073442603315629
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016876351776352241943042560028241113600x7f1f1ca967000x7f1e10e365c03917473917476553631457284278455483180412073442603358829120734426035235301207344260377696912073442603798617
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017076351776352241943042560024241128320x7f1f1ca966000x7f1e10e366002147612147616553630801924452845702460012073442603846205120734426040070471207344260413968712073442604143598
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017276351776352241943042560024241148160x7f1f1ca965000x7f1e10e366402751552751556553640632325784877400941612073442604186668120734426043700851207344260454416412073442604548069
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017476351776352241943042560024241162880x7f1f1ca964000x7f1e10e366802162252162256553631457284546685818032812073442604613741120734426047790431207344260491264212073442604916574
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017676351776352241943042560028241190400x7f1f1ca963000x7f1e10e366c04000594000596553657016327554949644937612073442604966888120734426051542411207344260541408012073442605440618
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017876351776352241943042560028241207680x7f1f1ca96a000x7f1e10e367003935933935936553632768004343815578247212073442605484449120734426056486381207344260590303712073442605924838
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018076351776352241943042560024241224960x7f1f1ca969000x7f1e10e367402169152169156553632112644451625693152412073442605967327120734426061380761207344260627263512073442606276441
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018276351776352241943042560024241247360x7f1f1ca968000x7f1e10e367802889132889136553642598405746217400633212073442606326504120734426065025541207344260668543312073442606689339
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018476351776352241943042560024241264640x7f1f1ca967000x7f1e10e367c02241472241476553632768005051536460510412073442606753418120734426069191911207344260705679012073442607060689
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018676351776352241943042560020241279360x7f1f1ca966000x7f1e10e3680041139341139365536773324898178412538629612073442607115100120734426072980691207344260756574812073442607589321
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018876351776352241943042560028241296640x7f1f1ca965000x7f1e10e368403943393943396553634078724768936099982812073442607633583120734426077961461207344260805198512073442608076757
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019076351776352241943042560024241313920x7f1f1ca964000x7f1e10e368802234812234816553633423364705066022560812073442608124746120734426082927841207344260842974312073442608433620
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019276351776352241943042560024241336320x7f1f1ca963000x7f1e10e368c03019633019636553644564486224927987450412073442608486078120734426086590221207344260885118012073442608873979
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019476351776352241943042560024241353600x7f1f1ca96a000x7f1e10e369002233772233776553635389445809767438939212073442608932367120734426091106991207344260924909812073442609252873
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019676351776352241943042560020241368320x7f1f1ca969000x7f1e10e36940437779437779655368978432112959214435999612073442609303878120734426094788571207344260976445512073442609789720
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019876351776352241943042560028241385600x7f1f1ca968000x7f1e10e369803894733894736553636700165305676814414012073442609830676120734426099924541207344261024429312073442610273249
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020076351776352241943042560024241402880x7f1f1ca967000x7f1e10e369c02188912188916553636044805028356432768412073442610315698120734426104807711207344261061629112073442610620444
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020276351776352241943042560024241427840x7f1f1ca966000x7f1e10e36a003303693303696553648496647138349073107612073442610662973120734426108446091207344261105468812073442611081220
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020476351776352241943042560024241447680x7f1f1ca965000x7f1e10e36a402226912226916553638010885878627523850412073442611138948120734426113057271207344261144428612073442611448323
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020676351776352241943042560020241457280x7f1f1ca964000x7f1e10e36a804715694715696553614548992182759623405364812073442611500319120734426116772451207344261198508312073442612014304
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020876351776352241943042560028241477120x7f1f1ca963000x7f1e10e36ac03921793921796553639321605548647111586012073442612056894120734426122222021207344261247660012073442612502712
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021076351776352241943042560024241496960x7f1f1ca96a000x7f1e10e36b002185932185936553638666245358396858839612073442612544229120734426127063591207344261284187812073442612845800
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021276351776352241943042560024241521920x7f1f1ca969000x7f1e10e36b4035704335704365536524288078455610059990812073442612895392120734426130796371207344261330827612073442613334788
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021476351776352241943042560024241541760x7f1f1ca968000x7f1e10e36b802216572216576553640632326392628178819612073442613390592120734426135605941207344261369787312073442613702071
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021676351776352241943042560020241556480x7f1f1ca967000x7f1e10e36bc05095395095396553610027008125790516138513212073442613747345120734426139269921207344261426075012073442614286828
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021876351776352241943042560028241576320x7f1f1ca966000x7f1e10e36c003919613919616553641943045581517176968012073442614330589120734426144975491207344261475114812073442614773171
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022076351776352241943042560024241596160x7f1f1ca965000x7f1e10e36c402238752238756553641287685951887615511212073442614819738120734426149831461207344261512266612073442615126979
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022276351776352241943042560024241623680x7f1f1ca964000x7f1e10e36c803843533843536553656360967741949845594812073442615177423120734426153624631207344261560918212073442615635073
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022476351776352241943042560024241646080x7f1f1ca963000x7f1e10e36cc02213072213076553645875206856438767762012073442615689214120734426158560591207344261599333912073442615996735
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022676351776352241943042560020241663360x7f1f1ca96a000x7f1e10e36d005755215755216553611075584139395417824285612073442616048772120734426162278981207344261660645612073442616632256
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022876351776352241943042560028241685760x7f1f1ca969000x7f1e10e36d404062354062356553647185926239287993882012073442616673172120734426168360551207344261709989412073442617128108
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023076351776352241943042560024241708160x7f1f1ca968000x7f1e10e36d802267532267536553646530567256819289383612073442617173622120734426173382931207344261747941212073442617482547
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023276351776352241943042560024241740800x7f1f1ca967000x7f1e10e36dc043365143365165536642252890561211586666012073442617527600120734426177058111207344261798597012073442618024093
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023476351776352241943042560024241765760x7f1f1ca966000x7f1e10e36e002185692185696553651118087682159820288412073442618074467120734426182451681207344261838068812073442618384212
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023676351776352241943042560020241777920x7f1f1ca965000x7f1e10e36e406792116792116553615007744188040224081060812073442618434957120734426186107671207344261905924512073442619084303
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023876351776352241943042560028241802880x7f1f1ca964000x7f1e10e36e803988813988816553652428807046119005206012073442619131531120734426193011641207344261955924212073442619582619
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024076351776352241943042560024241827840x7f1f1ca963000x7f1e10e36ec02208432208436553651773447748169911114812073442619629046120734426197930011207344261993092112073442619934283
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024276351776352241943042560024241863040x7f1f1ca96a000x7f1e10e36f00488281488281655367208960104791013376382412073442619977513120734426201693201207344262048595812073442620510724
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024476351776352241943042560024241893120x7f1f1ca969000x7f1e10e36f4024323524323565536616038490925611633818412073442620570736120734426207381171207344262089123612073442620894878
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024676351776352241943042560020241907840x7f1f1ca968000x7f1e10e36f807879297879296553617104896214451027446380012073442620938509120734426211278751207344262164851312073442621673936
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024876351776352241943042560028241937920x7f1f1ca967000x7f1e10e36fc045694745694765536629145692395811771447612073442621718078120734426218825921207344262218115012073442622204592
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025076351776352241943042560024241968000x7f1f1ca966000x7f1e10e3700024868924868965536622592094507412085320012073442622249916120734426224150691207344262257090812073442622574159
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025276351776352241943042560024242010880x7f1f1ca965000x7f1e10e37040594155594155655368781824126959016259202012073442622625955120734426228048271207344262319218612073442623214619
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025476351776352241943042560024242046080x7f1f1ca964000x7f1e10e37080280897280897655367208960109298413973681612073442623272426120734426234419441207344262362034412073442623623990
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025676351776352241943042560020242060800x7f1f1ca963000x7f1e10e370c09267079267076553619202048240798830801335212073442623672770120734426238486631207344262446194012073442624488095
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025876351776352241943042560028242096000x7f1f1ca96a000x7f1e10e3710049879349879365536734003297913012567850412073442624521588120734426246995391207344262502689712073442625048507
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026076351776352241943042560024242131200x7f1f1ca969000x7f1e10e37140282491282491655367274496106186813604038812073442625093691120734426252590561207344262543889512073442625442309
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026276351776352241943042560024242181760x7f1f1ca968000x7f1e10e371806976256976256553610354688147676819044037212073442625493314120734426256758541207344262613217212073442626156206
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026476351776352241943042560024242222080x7f1f1ca967000x7f1e10e371c0313507313507655368257536123636515840827612073442626218081120734426263849711207344262658641012073442626609829
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026676351776352241943042560020242239360x7f1f1ca966000x7f1e10e37200106423310642336553621299200266974634169798412073442626661495120734426268281691207344262753312612073442627562008
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026876351776352241943042560028242279680x7f1f1ca965000x7f1e10e37240567347567347655368388608112800914391553612073442627601431120734426277780841207344262815264312073442628177312
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027076351776352241943042560024242320000x7f1f1ca964000x7f1e10e37280317273317273655368323072125128716016974012073442628224068120734426283892821207344262859216112073442628616408
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027276351776352241943042560024242378240x7f1f1ca963000x7f1e10e372c08046518046516553611927552168458321500182412073442628662483120734426288270401207344262935327712073442629383924
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027476351776352241943042560024242423680x7f1f1ca96a000x7f1e10e37300350305350305655369306112144357318479146012073442629436842120734426296057561207344262983135512073442629852835
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027676351776352241943042560020242435840x7f1f1ca969000x7f1e10e37340120688312068836553629163520365138746741329612073442629898450120734426300657541207344263086703012073442630890604
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027876351776352241943042560028242481280x7f1f1ca968000x7f1e10e37380639081639081655369437184126891916331722812073442630935998120734426311123091207344263153326712073442631558515
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028076351776352241943042560024242526720x7f1f1ca967000x7f1e10e373c0353803353803655369371648141765818149099212073442631603919120734426317673461207344263199518512073442632018500
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028276351776352241943042560024242592640x7f1f1ca966000x7f1e10e374009096739096736553613500416191709824644943212073442632070116120734426322377441207344263283678112073442632881514
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028476351776352241943042560024242648320x7f1f1ca965000x7f1e10e374404181634181636553611403264175088922414833612073442632916459120734426331247801207344263339581812073442633443548
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028676351776352241943042560020242663040x7f1f1ca964000x7f1e10e37480148720114872016553633357824417447353451279212073442633468194120734426336516571207344263463917312073442634687650
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028876351776352241943042560028242718720x7f1f1ca963000x7f1e10e374c07794277794276553611534336157163420235080812073442634712036120734426349044511207344263542156912073442635473180
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029076351776352241943042560024242774400x7f1f1ca96a000x7f1e10e375004237134237136553611534336175035422398722812073442635495692120734426356868481207344263596108712073442636016169
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029276351776352241943042560012242799360x7f1f1ca969000x7f1e10e37540112566711256676553619267584242207031014053212073442636045944120734426362250851207344263696508212073442637033219
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029476351776352241943042560024242865280x7f1f1ca968000x7f1e10e375805318735318736553613500416207364126545745212073442637072111120734426372415611207344263758747912073442637655145
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029676351776352241943042560020242880000x7f1f1ca967000x7f1e10e375c0176960317696036553637552128470625660162902012073442637673068120734426378669981207344263904123212073442639114186
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029876351776352241943042560032242945920x7f1f1ca966000x7f1e10e376009171379171376553613631488186672123908907612073442639144022120734426393269911207344263993786812073442639984093
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030076351776352241943042560024243011840x7f1f1ca965000x7f1e10e376404935474935476553613631488207889126603453212073442640008058120734426402068271207344264052698612073442640575632
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030276351776352241943042560012243049600x7f1f1ca964000x7f1e10e37680133552913355296553621692416273993835095428012073442640600008120734426407844241207344264166298012073442641711714
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030476351776352241943042560024243136000x7f1f1ca963000x7f1e10e376c06304436304436553617694720271589934776666812073442641747310120734426419157791207344264232745712073442642395264
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030676351776352241943042560020243148160x7f1f1ca96a000x7f1e10e37700233180123318016553657475072719147792087243212073442642420330120734426426076161207344264415864912073442644227729
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030876351776352241943042560020243175680x7f1f1ca969000x7f1e10e37740120060312006036553619660800248175631745958012073442644251313120734426444463271207344264524440412073442645314148
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031076351776352241943042560012243203200x7f1f1ca968000x7f1e10e377806393136393136553620381696257897133005688412073442645345637120734426455290421207344264594504012073442645992238
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031276351776352241943042560012243240960x7f1f1ca967000x7f1e10e377c0175759517575956553628704768361496446249854412073442646024749120734426462157591207344264737543412073442647446731
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031476351776352241943042560012243288960x7f1f1ca966000x7f1e10e37800119748911974896553636634624464634159486246012073442647490533120734426476591131207344264844534912073442648515508
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031676351776352241943042560020243301120x7f1f1ca965000x7f1e10e37840458529145852916553610584064013234943169473950812073442648543009120734426487351081207344265178741412073442651857709
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031876351776352241943042560020243328640x7f1f1ca964000x7f1e10e37880232583323258336553638535168482940761834265612073442651886492120734426520894921207344265363364512073442653704821
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032076351776352241943042560012243356160x7f1f1ca963000x7f1e10e378c0120253912025396553639124992491365462903633212073442653734216120734426539240441207344265471316012073442654783646
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032276351776352241943042560012243393920x7f1f1ca96a000x7f1e10e37900344310534431056553655771136700859789723685212073442654817750120734426550001991207344265728338812073442657353011
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032476351776352241943042560012243441920x7f1f1ca969000x7f1e10e379402323339232333965536725483529111881116624612412073442657397834120734426575694671207344265910530012073442659174316
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032676351776352241943042560020243454080x7f1f1ca968000x7f1e10e37980908786590878656553621069824026338872337266033612073442659197419120734426593891381207344266544655012073442665515139
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032876351776352241943042560020243481600x7f1f1ca967000x7f1e10e379c04573131457313165536762839049537857122204669212073442665545496120734426657302291207344266877565512073442668845268
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033076351776352241943042560012243509120x7f1f1ca966000x7f1e10e37a002328265232826565536773980169705065124221431612073442668874292120734426690746941207344267061468712073442670684546
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332763517763522419430425600122400x7f1f1ca965000x7f1e10e37a40681361168136116553611082137613882173177729482812073442670714332120734426709033251207344267543162412073442675501969