Файли
rocm-systems/tests/workloads/Axes1/mi200/SQ_LEVEL_WAVES.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

48 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjGRBM_COUNTGRBM_GUI_ACTIVECPC_ME1_BUSY_FOR_PACKET_DECODESQ_CYCLESSQ_WAVESSQ_WAVE_CYCLESSQ_BUSY_CYCLESSQ_LEVEL_WAVESSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000200422200422335544322560043241600x00x7f294c004280381872381872867330549845242882399432402968704097603044417231436888452172307232308371723157979347217231579902522
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00220042220042232768256001224138880x00x7f294c023f8033766337662984927013651217637041701610706848817231585064932172315797934721723158519747317231585201818
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0052004222004224194304256001224143360x7f295a8823800x7f294c023fc016387716387713443131102465536794962431203897031971065217231585245607172315851974731723158557699317231585579388
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0082004222004224194304256001624150400x7f295a8822000x7f294c024000309221309221247952473776655362211123832370366088617726017231585625207172315855769931723158599331317231585995657
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00112004222004224194304256001624154880x7f295a8820800x7f294c024040307144307144240382457160655362189531502353946087754112417231586036396172315859933131723158641507317231586417365
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00142004222004224194304256001224159360x7f2958223f000x7f294c02408016512516512513541132100865536803310271217298032305065217231586459154172315864150731723158674291317231586744947
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00172004222004224194304256001224163840x7f2958223d800x7f294c0240c016443616443613859131549665536818096941211739032896892017231586785745172315867429131723158706387317231587066248
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00202004222004224194304256001224170880x7f2958223c000x7f294c024100162547162547146501300384655361076129501202849043217942017231587119646172315870638731723158739251417231587394499
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00232004222004224194304256001624177920x7f2958223a800x7f294c024140308062308062243412464504655362270322972356917090985695217231587434528172315873925141723158781555417231587817578
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00262004222004224194304256001624184960x7f29582239000x7f294c024180308317308317218472466544655362154082322361613086336193617231587857637172315878155541723158822499417231588227147
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00292004222004224194304256001624192000x7f29582237800x7f294c0241c016405816405814214131247265536974333281213034039145952017231588267185172315882249941723158854451417231588546578
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00322004222004224194304256001624199040x7f29582236000x7f294c02420016495416495415216131964065536980777231216678039403958417231588587457172315885445141723158886675417231588868799
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00352004222004224194304256001224206080x7f295a8824800x7f294c02424016508316508314806132067265536976929851212773039249976417231588920308172315888667541723158919923417231589201420
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00382004222004224194304256001624213120x7f295a8823000x7f294c024280309005309005233862472048655362250346212365908090186670417231589243559172315891992341723158960915417231589611309
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00412004222004224194304256001624220160x7f295a8821800x7f294c0242c0310724310724231582485800655362246538672376621090034263617231589653138172315896091541723159001907417231590021018
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00442004222004224194304256001624227200x7f295a8820000x7f294c024300164123164123148081312992655361017016501209561040853338817231590062177172315900190741723159038451417231590387098
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00472004222004224194304256001224234240x7f2958223e800x7f294c024340163637163637151741309104655361068391131207738042908005617231590427667172315903845141723159071443417231590716609
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00502004222004224194304256001224241280x7f2958223d000x7f294c02438016309916309914664130480065536913196891198689036699985617231590765488172315907144341723159101043517231591012051
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00532004222004224194304256001624248320x7f2958223b800x7f294c0243c0307817307817241462462544655362291293822360185091824527617231591057580172315910104351723159139699517231591398661
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00562004222004224194304256001624255360x7f2958223a000x7f294c024400305737305737217772445904655362174158722343908087139524417231591441640172315913969951723159177603517231591777621
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00592004222004224194304256001224262400x7f29582238800x7f294c024440163247163247152021305984655361098525151206631044113254817231591819060172315917760351723159207187517231592073333
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00622004222004224194304256001224269440x7f29582237000x7f294c024480162662162662152071301304655361028374291200475041307092017231592114142172315920718751723159236563517231592367205
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00652004222004224194304256001224276480x7f295a8825800x7f294c0244c0162145162145147061297168655361071493361200389043032978817231592415963172315923656351723159266595517231592667437
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00682004222004224194304256001624286080x7f295a8824000x7f294c024500308856308856236262470856655362285952922371593091611184817231592711085172315926659551723159304627517231593047786
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00712004222004224194304256001624293120x7f295a8822800x7f294c024540307216307216223412457736655362071968652342818083051560017231593089375172315930462751723159342595517231593427526
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00742004222004224194304256001224300160x7f295a8821000x7f294c024580162343162343153531298752655361033423211198061041510266417231593470395172315934259551723159371619517231593717608
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077200422200422419430425600824309760x7f2958223f800x7f294c0245c016286616286614483130293665536947865391201256038087472017231593759567172315937161951723159401059517231594012110
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00802004222004224194304256001224316800x7f2958223e000x7f294c024600162029162029151041296240655361055829301196527042405116017231594059839172315940105951723159431363517231594315072
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00832004222004224194304256001624326400x7f2958223c800x7f294c024640306910306910236092455288655362295530782355095091994242417231594356191172315943136351723159469715617231594698652
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00862004222004224194304256001224336000x7f2958223b000x7f294c024680305252305252226432442024655362130843912338703085406816817231594741760172315946971561723159507523617231595076681
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00892004222004224194304256001224345600x7f29582239800x7f294c0246c016289016289014183130312865536856983421200153034452346017231595118270172315950752361723159536659617231595367983
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092200422200422419430425600824355200x7f29582238000x7f294c02470016428816428814176131431265536912004531211620036652860817231595409292172315953665961723159566035617231595661895
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00952004222004224194304256001224362240x7f29582236800x7f294c024740162839162839146751302720655361025342851204287041185979617231595710134172315956603561723159594979617231595951618
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00982004222004224194304256001224371840x7f295a8825000x7f294c024780304190304190238002433528655362264215772329273090741737217231595996936172315959497961723159632963617231596331027
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001012004222004224194304256001224381440x7f295a8823800x7f294c0247c0302779302779199462422240655362057944362317590082490689617231596372246172315963296361723159670451617231596706087
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001042004222004224194304256001224391040x7f295a8822000x7f294c02480016225116225114774129801665536986606321195466039636610017231596747916172315967045161723159700371617231597005299
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107200422200422419430425600824403200x7f295a8820800x7f294c02484016263916263915081130112065536878388701198578035308010417231597047598172315970037161723159729715617231597298491
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001102004222004224194304256001224412800x7f2958223f000x7f294c02488016272716272714452130182465536923898061197277037128419217231597347480172315972971561723159758995617231597591533
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001132004222004224194304256001224422400x7f2958223d800x7f294c0248c0303688303688234622429512655362206876322330210088448014817231597636752172315975899561723159798899617231597990502
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001162004222004224194304256001224432000x7f2958223c000x7f294c024900304756304756223212438056655362219554292339543088955334017231598032641172315979889961723159837939717231598380842
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119200422200422419430425600824441600x7f2958223a800x7f294c02494016174416174414549129396065536987506281195926039672662417231598421111172315983793971723159867331717231598674804
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001222004222004224194304256001224453760x7f29582239000x7f294c02498016177716177715104129422465536934100861193329037536448417231598715953172315986733171723159897219717231598973686
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001252004222004224194304256001224463360x7f29582237800x7f294c0249c016112016112014500128896865536913736181189571036722349217231599022744172315989721971723159927187717231599273407
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001282004222004224194304256001224475520x7f29582236000x7f294c024a00305987305987235602447904655362203912442339617088329350817231599316616172315992718771723159965267717231599654177
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001312004222004224194304256001224485120x7f295a8824800x7f294c024a40301093301093206062408752655362108941642306493084530742017231599695966172315996526771723160003059717231600032097
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134200422200422419430425600824494720x7f295a8823000x7f294c024a8016120516120514431128964865536903902441189161036329244017231600073316172316000305971723160031987717231600321489
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001372004222004224194304256001224506880x7f295a8821800x7f294c024ac016229416229415781129836065536974453471193747039151846417231600362838172316003198771723160061075717231600612181
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001402004222004224194304256001224516480x7f295a8820000x7f294c024b0016108816108814473128871265536944757881190067037963306817231600661650172316006107571723160090419717231600905593
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001432004222004224194304256001224528640x7f2958223e800x7f294c024b40304126304126229672433016655362264826422329813090765894417231600948132172316009041971723160128387717231601285243
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001462004222004224194304256001224540800x7f2958223d000x7f294c024b80304104304104221472432840655362188723932331005087721882417231601325622172316012838771723160166515717231601666713
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149200422200422419430425600824552960x7f2958223b800x7f294c024bc016236416236414608129892065536956458011199488038431082817231601707732172316016651571723160195571817231601957175
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001522004222004224194304256001224567680x7f2958223a000x7f294c024c00163018163018160691304152655361002168491199878040260228017231601998094172316019557181723160225747817231602258967
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001552004222004224194304256001224577280x7f29582238800x7f294c024c4016339816339814437130719265536929745551200034037362438417231602307476172316022574781723160255683817231602558659
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001582004222004224194304256001224589440x7f29582237000x7f294c024c80301484301484229462411880655362182410432310822087469714417231602599168172316025568381723160293395817231602935359
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001612004222004224194304256001224601600x7f295a8825800x7f294c024cc0302080302080219922416648655362084573802310551083555657617231602977017172316029339581723160331219817231603313688
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164200422200422419430425600824613760x7f295a8824000x7f294c024d0016261616261614151130093665536970786841203996039003750417231603355847172316033121981723160360195817231603603221
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001672004222004224194304256001224628480x7f295a8822800x7f294c024d40168245168245162651345968655361062176531246019042660406017231603644549172316036019581723160390003817231603901552
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001702004222004224194304256001224638080x7f295a8821000x7f294c024d80162123162123146541296992655361017573161196478040875041617231603949961172316039000381723160418819817231604189745
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001732004222004224194304256001224650240x7f2958223f800x7f294c024dc0301055301055226562408448655362184387972306041087548853217231604234873172316041881981723160458163817231604583104
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001762004222004224194304256001224662400x7f2958223e000x7f294c024e00298868298868208012390952655362081582952286319083436738017231604624193172316045816381723160496483817231604966294
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179200422200422419430425600824674560x7f2958223c800x7f294c024e4016402916402914480131224065536927101141207982037256716417231605005893172316049648381723160525667817231605258176
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001822004222004224194304256001224689280x7f2958223b000x7f294c024e80176594176594162151412760655361081181991308234043420894417231605298755172316052566781723160555683917231605558298
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001852004222004224194304256001224701440x7f29582239800x7f294c024ec016057416057414856128460065536900264511183697036183797217231605606966172316055568391723160585715917231605858560
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001882004222004224194304256001224716160x7f29582238000x7f294c024f00303013303013233342424112655362219574682322322088956176017231605900158172316058571591723160623491917231606236539
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001912004222004224194304256001224728320x7f29582236800x7f294c024f40300754300754216792406040655362190229882305582087782101217231606278738172316062349191723160661731917231606618759
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194200422200422419430425600824740480x7f295a8825000x7f294c024f8016081916081914584128656065536897715261187721036082175617231606659708172316066173191723160690691917231606908431
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001972004222004224194304256001224757760x7f295a8823800x7f294c024fc0181071181071168591448576655361128694361345061045322008417231606949150172316069069191723160721091917231607212403
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002002004222004224194304256001224769920x7f295a8822000x7f294c025000160683160683146471285472655361007958571187139040490965217231607272191172316072109191723160750291917231607504525
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002032004222004224194304256001224784640x7f295a8820800x7f294c025040301757301757233512414064655362178917822311532087329876417231607552224172316075029191723160788707917231607888715
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002062004222004224194304256001224799360x7f2958223f000x7f294c025080300565300565220212404528655362134865912298636085567562417231607929804172316078870791723160827091917231608272454
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209200422200422419430425600824814080x7f2958223d800x7f294c0250c016281516281515202130252865536948752611202603038122524817231608313853172316082709191723160856403917231608565586
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002122004222004224194304256001224831360x7f2958223c000x7f294c025100190365190365174651522928655361276408211424804051230684417231608606595172316085640391723160887635917231608877858
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002152004222004224194304256001224843520x7f2958223a800x7f294c02514016117616117614444128941665536935670461190218037599829217231608926297172316088763591723160917252017231609173970
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002182004222004224194304256001224858240x7f29582239000x7f294c025180303654303654240972429240655362222356122325778089067923217231609218419172316091725201723160956404017231609565659
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002212004222004224194304256001224872960x7f29582237800x7f294c0251c0299116299116224012392936655362111635362293811084638272817231609607558172316095640401723160994164017231609943099
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002242004222004224194304256001224887680x7f29582236000x7f294c02520016330916330915891130648065536963349041199470038706628017231609983598172316099416401723161024452017231610246011
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002272004222004224194304256001224907520x7f295a8824800x7f294c025240200492200492180591603944655361298002261500390052094368417231610287420172316102445201723161056964017231610571252
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002302004222004224194304256001224919680x7f295a8823000x7f294c02528016224416224415514129796065536935383611192686037587723217231610619871172316105696401723161086852017231610869844
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002332004222004224194304256001224934400x7f295a8821800x7f294c0252c0301762301762230442414104655362169265422303429086943846017231610915023172316108685201723161125396017231611255464
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002362004222004224194304256001224949120x7f295a8820000x7f294c025300299453299453200782395632655362035935272292485081610898017231611297982172316112539601723161163076017231611632223
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002392004222004224194304256001224963840x7f2958223e800x7f294c02534016189116189115198129513665536979684611196395039360432817231611673732172316116307601723161192788017231611929345
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002422004222004224194304256001224983680x7f2958223d000x7f294c025380211095211095188171688768655361244303951573317049946766417231611969644172316119278801723161225668017231612258076
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002452004222004224194304256001224995840x7f2958223b800x7f294c0253c016102316102314706128819265536898590981190262036117134417231612306345172316122566801723161255364017231612555048
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024820042220042241943042560012241013120x7f2958223a000x7f294c025400299799299799230682398400655362179786252298970087364894017231612595717172316125536401723161293588117231612937458
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025120042220042241943042560012241027840x7f29582238800x7f294c025440297931297931205932383456655362087331862276747083666573217231612977937172316129358811723161331252117231613314078
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025420042220042241943042560012241042560x7f29582237000x7f294c02548016208516208516597129668865536992375391186965039868130817231613354017172316133125211723161360564117231613607050
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025720042220042241943042560012241062400x7f295a8825800x7f294c0254c0219424219424195921755400655361380815621643017055407711217231613648159172316136056411723161394708117231613948560
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026020042220042241943042560012241077120x7f295a8824000x7f294c02550016099316099314458128795265536909298041188426036546064017231613996809172316139470811723161424724117231614248812
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026320042220042241943042560016241094400x7f295a8822800x7f294c025540297705297705216062381648655362083103282276299083497355217231614294091172316142472411723161462772117231614629302
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026620042220042241943042560016241111680x7f295a8821000x7f294c025580298417298417203122387344655362070520092283088082993827617231614670921172316146277211723161500532117231615006822
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002692004222004224194304256008241128960x7f2958223f800x7f294c0255c0162670162670153691301368655361022402181200080041069999617231615048431172316150053211723161530260117231615304094
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027220042220042241943042560012241151360x7f2958223e000x7f294c025600229540229540198571836328655361473060501721496059096719217231615344683172316153026011723161563860117231615639985
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027520042220042241943042560012241166080x7f2958223c800x7f294c02564016210216210215943129682465536953729291190358038322480017231615687453172316156386011723161593140117231615932817
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027820042220042241943042560016241183360x7f2958223b000x7f294c025680299345299345224722394768655362118918662292097084929919617231615978446172316159314011723161631508217231616316836
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028120042220042241943042560016241200640x7f29582239800x7f294c0256c0298015298015202392384128655362067709212273589082881586417231616357715172316163150821723161669236217231616693966
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028420042220042241943042560012241217920x7f29582238000x7f294c025700163980163980160651311848655361021376581207572041028161617231616735305172316166923621723161698964217231616991188
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028720042220042241943042560012241240320x7f29582236800x7f294c025740239995239995199041919968655361487359961809358059669126417231617031657172316169896421723161733556217231617337189
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029020042220042241943042560012241255040x7f295a8825000x7f294c025780162264162264156041298120655361014786021191938040764110817231617385988172316173355621723161763508217231617636491
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029320042220042241943042560012241274880x7f295a8823800x7f294c0257c0296689296689201832373520655362078518292269995083314029217231617681250172316176350821723161802324217231618024760
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029620042220042241943042560012241292160x7f295a8822000x7f294c025800297534297534200712380280655362102917102275068084289888417231618067049172316180232421723161840996217231618411480
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029920042220042241943042560012241309440x7f295a8820800x7f294c025840169609169609159481356880655361039933111254775041772156817231618454409172316184099621723161870804217231618709582
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030220042220042241943042560012241334400x7f2958223f000x7f294c025880258710258710213292069688655361813368551955134072709436017231618753921172316187080421723161906580217231619067322
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030520042220042241943042560012241349120x7f2958223d800x7f294c0258c016194916194917038129560065536991623291183969039837927217231619117481172316190658021723161936036217231619362094
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030820042220042241943042560012241368960x7f2958223c000x7f294c025900296914296914207622375320655362072732882273821083083451217231619403113172316193603621723161974340217231619744954
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031120042220042241943042560012241388800x7f2958223a800x7f294c025940297449297449209562379600655362140076202271210085776252817231619786493172316197434021723162012292317231620124414
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031420042220042241943042560012241408640x7f29582239000x7f294c025980177732177732165861421864655361119524321320538044955043217231620164802172316201229231723162042612317231620427605
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031720042220042241943042560012241436160x7f29582237800x7f294c0259c0279200279200221682233608655362001799562126518080246190817231620468884172316204261231723162079332317231620794805
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032020042220042241943042560012241453440x7f29582236000x7f294c025a0016217016217015687129736865536996699191194945040041400417231620843374172316207933231723162109140317231621092897
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032320042220042241943042560012241475840x7f295a8824800x7f294c025a40293819293819203192350560655362052994122251239082293250017231621137226172316210914031723162147396317231621475397
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032620042220042241943042560012241495680x7f295a8823000x7f294c025a80295370295370205252362968655362098787422257967084125094817231621518336172316214739631723162185444317231621855877
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032920042220042241943042560012241515520x7f295a8821800x7f294c025ac0186634186634176611493080655361093407911382012043911195617231621896716172316218544431723162216788317231622169448
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033220042220042241943042560012241543040x7f295a8820000x7f294c025b00299341299341229842394736655362007690012287059080483074017231622210747172316221678831723162255092317231622552358
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033520042220042241943042560012241562880x7f2958223e800x7f294c025b40171560171560165621372488655361037368011268941041669994017231622600427172316225509231723162285124317231622852750
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033820042220042241943042560012241587840x7f2958223d000x7f294c025b80296654296654196212373240655361858430272263227074511808417231622893479172316228512431723162323124317231623232619
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034120042220042241943042560012241610240x7f2958223b800x7f294c025bc0296141296141200192369136655362009001582261354080535602817231623273688172316232312431723162361140417231623612949
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034420042220042241943042560012241632640x7f2958223a000x7f294c025c00205397205397180781643184655361281448571530767051432496417231623652688172316236114041723162393204417231623933490
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034720042220042241943042560012241665280x7f29582238800x7f294c025c40339666339666250042717336655362404924712608449096372414017231623973549172316239320441723162433732417231624380198
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035020042220042241943042560012241685120x7f29582237000x7f294c025c80183456183456167861467656655361042086801361092041858221617231624398528172316243373241723162467268417231624674130
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035320042220042241943042560012241712640x7f295a8825800x7f294c025cc0295239295239186972361920655361644663832237031065962748417231624715079172316246726841723162505444417231625055970
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035620042220042241943042560012241737600x7f295a8824000x7f294c025d00295772295772207622366184655361968699492258497078922650017231625097169172316250544441723162543540417231625436859
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035920042220042241943042560012241762560x7f295a8822800x7f294c025d40225282225282194801802264655361455424281695158058392224417231625477358172316254354041723162577012417231625771560
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036220042220042241943042560012241797760x7f295a8821000x7f294c025d803796563796562692230372566553628020983629296530112258978017231625812829172316257701241723162619988417231626223518
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036520042220042241943042560012241822720x7f2958223f800x7f294c025dc0210469210469185711683760655361336857921577480053649454417231626250577172316261998841723162653892417231626540340
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036820042220042241943042560012241855360x7f2958223e000x7f294c025e00303172303172221122425384655361918236652305203076905281617231626580688172316265389241723162693316417231626935539
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037120042220042241943042560012241885440x7f2958223c800x7f294c025e40307442307442224852459544655361769539682332701070957750817231626974578172316269331641723162733140517231627333718
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037420042220042241943042560012241915520x7f2958223b000x7f294c025e80266294266294219262130360655361800653752018223072202381617231627372797172316273314051723162769284517231627694478
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037720042220042241943042560012241958400x7f29582239800x7f294c025ec04606364606363132136850966553634684610635774280138914404817231627734717172316276928451723162817780517231628195495
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038020042220042241943042560012241985920x7f29582238000x7f294c025f00244610244610202631956888655361510094131844672060579855617231628227354172316281778051723162852612517231628527686
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038320042220042241943042560012242023680x7f29582236800x7f294c025f40334198334198226282673592655362134975312558930085576590817231628568385172316285261251723162893284517231628947655
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038620042220042241943042560012242058880x7f295a8825000x7f294c025f80330180330180227612641448655362100716692521111084205698817231628975584172316289328451723162934676517231629361293
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038920042220042241943042560012242094080x7f295a8823800x7f294c025fc0305389305389231762443120655362185138072340306087581111217231629387873172316293467651723162973796517231629739543
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039220042220042241943042560012242144640x7f295a8822000x7f294c0260005419665419663527043357366553641253717742242560165191202417231629779832172316297379651723163027332517231630287808
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039520042220042241943042560012242177280x7f295a8820800x7f294c026040273069273069213272184560655361713201822075622068703923617231630323797172316302733251723163064356517231630645059
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039820042220042241943042560012242220160x7f2958223f000x7f294c026080363323363323286532906592655362479556992796665099360352817231630686228172316306435651723163107156617231631113446
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040120042220042241943042560012242260480x7f2958223d800x7f294c0260c03654503654502768629236086553625675307228172390102878360417231631122856172316310715661723163152164617231631563344
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040420042220042241943042560012242300800x7f2958223c000x7f294c026100347119347119252412776960655362480172572666784099383509217231631573494172316315216461723163195300617231631994052
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040720042220042241943042560012242359040x7f2958223a800x7f294c0261406247226247224066049977846553647381057848755110189700230817231632004202172316319530061723163255924617231632600426
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041020042220042241943042560012242394240x7f29582239000x7f294c026180302147302147226212417184655362115678132315765084803474817231632618725172316325592461723163297172617231632973296
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041320042220042241943042560012242442240x7f29582237800x7f294c0261c03975763975762787231806166553627385292030681980109719436417231633014045172316329717261723163341924617231633460683
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041620042220042241943042560012242487680x7f29582236000x7f294c0262003898773898772719131190246553629449622730212030117975608817231633470072172316334192461723163388468617231633902211
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041920042220042241943042560012242533120x7f295a8824800x7f294c0262403872043872042752030976406553629044958129906390116359166417231633926980172316338846861723163432292617231634369898
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004222004222004224194304256008242555520x7f295a8823000x7f294c0262807169807169804386257358486553655092970256304130220545846817231634380888172316343229261723163500404717231635047210
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042520042220042241943042560012242598400x7f295a8821800x7f294c0262c03643803643802616629150486553625730539328041730103098581217231635066309172316350040471723163544868717231635491298
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042820042220042241943042560012242656640x7f295a8820000x7f294c0263004692134692133116437537126553635353887236464340141594271217231635501767172316354486871723163597172717231636012804
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043120042220042241943042560012242712320x7f2958223e800x7f294c0263404727824727823220837822646553635069276536749880140455400817231636023083172316359717271723163649428717231636535000
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004342004222004224194304256008242732160x7f2958223d000x7f294c0263804834104834103316538672886553635674134337556580142870570417231636545169172316364942871723163701012717231637050746
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004372004222004224194304256008242757120x7f2958223b800x7f294c0263c08792088792085278370336726553668375077269239190273674426017231637061125172316370101271723163778692717231637828775
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044020042220042241943042560012242807680x7f2958223a000x7f294c0264004257454257452914434059686553631949545733012800127975075217231637847614172316377869271723163827284817231638317091
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044320042220042241943042560012242876160x7f29582238800x7f294c0264405482895482893521843863206553641475848542860260166082075217231638328781172316382728481723163884788817231638891636
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044620042220042241943042560012242942080x7f29582237000x7f294c0264805509835509833571844078726553640615885842985250162641940017231638901696172316388478881723163941844817231639459870
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004492004222004224194304256008242969600x7f295a8825800x7f294c0264c05620225620223628244961846553642476320743875860170079572017231639469750172316394184481723163998452817231640025425
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004522004222004224194304256008242999680x7f295a8824000x7f294c026500104221510422156127083377286553681700344282208060326975593617231640035765172316399845281723164086740817231640911091
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004552004222004224194304256008243027200x7f295a8822800x7f294c0265407226417226414455157811366553654539479156564910218332201217231640929850172316408674081723164153652817231641577063
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045820042220042241943042560012243054720x7f295a8821000x7f294c0265807230957230954444857847686553655245506456738530221156119217231641587173172316415365281723164222196917231642266534
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046120042220042241943042560012243082240x7f2958223f800x7f294c0265c07212597212594398757700806553654876003756613500219678006417231642277424172316422218161723164290725617231642958655
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004642004222004224194304256008243109760x7f2958223e000x7f294c0266007266307266304464458130486553655556114056972710222398599617231642969215172316429072561723164358821417231643631587
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004672004222004224194304256008243132160x7f2958223c800x7f294c026640136730413673047750110938440655361067749919108224140427274117617231643642027172316435882141723164468005417231644723038
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004702004222004224194304256008243159680x7f2958223b000x7f294c026680137122813712287737510969832655361082524152108499560433183872017231644744147172316446800541723164578053417231645844557
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047320042220042241943042560012243187200x7f29582239800x7f294c0266c0137231513723157716610978528655361074250970108621440429874448017231645855407172316457805341723164692053417231646986267
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047620042220042241943042560012243214720x7f29582238000x7f294c026700137146513714657702910971728655361079868798108495050432121618417231646996746172316469205341723164806117417231648127126
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004792004222004224194304256008243242240x7f29582236800x7f294c026740137741213774127786211019304655361067129407108915980427025998017231648136856172316480611741723164919141417231649257825
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004822004222004224194304256008243264640x7f295a8825000x7f294c0267802664265266426514206321314128655362119458099211831220847957407617231649267665172316491914141723165115061417231651226242
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004852004222004224194304256008243292160x7f295a8823800x7f294c0267c02669748266974814352121357992655362133181962212319140853446899217231651245222172316511506141723165308965417231653156420
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048820042220042241943042560012243319680x7f295a8822000x7f294c0268002671224267122414296721369800655362131474553212390230852763889217231653167080172316530896541723165507861417231655150156
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049120042220042241943042560012243347200x7f295a8820800x7f294c0268402668850266885014294821350808655362125485042212347790850368017617231655160816172316550786141723165707061417231657135542
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004942004222004224194304256008243374720x7f2958223f000x7f294c0268802674558267455814258321396472655362127696938212626530851253004017231657146272172316570706141723165900325417231659074779
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049720042220042241943042560082400x7f2958223d800x7f294c0268c052569825256982274055420558646553642326678334193101701693241271217231659085669172316590032541723166263109417231662703371