Files
rocm-systems/tests/workloads/Axes3/mi100/SQ_INST_LEVEL_SMEM.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

43 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_SMEMSQ_INST_LEVEL_SMEMSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000910940910945335544322560083264640x00x7fbb292041804194304307232639342278412076131878204691120761321216766981207613212200037712076132122110910
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00291094091094532768256002424124800x00x7fbb2923510051221876279738412076132136823112120761321371215871207613213712766712076132137132998
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0049109409109454194304256002424129280x7fbc34dd99000x7fbb29235140655361807802311063212076132137192027120761321374079861207613213754622512076132137550373
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0069109409109454194304256003624136320x7fbc34dd98000x7fbb29235180655361383841782332812076132137616045120761321377907041207613213804190312076132138110684
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0089109409109454194304256002824140800x7fbc34dd97000x7fbb292351c0655361535841958272012076132138143586120761321383313421207613213858974112076132138656970
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00109109409109454194304256002424145280x7fbc34dd96000x7fbb29235200655361523181947308012076132138683890120761321388615791207613213900221912076132139006309
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00129109409109454194304256002424149760x7fbc34dd95000x7fbb29235240655361729942217000012076132139057133120761321392294181207613213937005712076132139374393
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00149109409109454194304256002424154240x7fbc34dd94000x7fbb292352801310722339102993983212076132139451496120761321396186961207613213975197512076132139755872
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00169109409109454194304256002824161280x7fbc34dd93000x7fbb292352c01310722002922557532012076132139803631120761321399780541207613214023149312076132140274606
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00189109409109454194304256002824168320x7fbc34dd9a000x7fbb29235300655361515921935515212076132140301215120761321404820521207613214074013112076132140782059
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00209109409109454194304256002424175360x7fbc34dd99000x7fbb292353401310722558183297932812076132140805242120761321409972501207613214112988912076132141133873
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00229109409109454194304256002424182400x7fbc34dd98000x7fbb292353801310722302102943720012076132141180049120761321413593281207613214149932712076132141503450
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00249109409109454194304256002424189440x7fbc34dd97000x7fbb292353c01310722229442855196012076132141565756120761321417262061207613214185628612076132141860043
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00269109409109454194304256002824199040x7fbc34dd96000x7fbb292354001310721856062384987212076132141911709120761321420780451207613214233916412076132142383085
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00289109409109454194304256002824206080x7fbc34dd95000x7fbb29235440655361802202298511212076132142412189120761321425942021207613214284988112076132142890798
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00309109409109454194304256002424213120x7fbc34dd94000x7fbb292354801310722284362904976012076132142917267120761321431044401207613214323531912076132143239216
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00329109409109454194304256002424220160x7fbc34dd93000x7fbb292354c01310722218002823717612076132143290942120761321434557981207613214359355812076132143597411
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00349109409109454194304256002424227200x7fbc34dd9a000x7fbb292355001310722289722937480012076132143657974120761321438217171207613214395035612076132143954054
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00369109409109454194304256002824236800x7fbc34dd99000x7fbb292355401310721820162338432012076132144016240120761321441794751207613214444043412076132144506641
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00389109409109454194304256002824243840x7fbc34dd98000x7fbb29235580655361512921931340812076132144530626120761321447146731207613214497131212076132145038479
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00409109409109454194304256002424250880x7fbc34dd97000x7fbb292355c01310722173182768295212076132145064959120761321452463501207613214537643012076132145380165
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00429109409109454194304256002424257920x7fbc34dd96000x7fbb292356001310722355063024140012076132145428715120761321455951491207613214573562812076132145739232
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00449109409109454194304256002424264960x7fbc34dd95000x7fbb292356401310722616283342451212076132145798462120761321459575471207613214609018612076132146094182
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00469109409109454194304256002824277120x7fbc34dd94000x7fbb292356801310721811142318452812076132146145347120761321463071451207613214656922412076132146612334
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00489109409109454194304256002824284160x7fbc34dd93000x7fbb292356c0655361497901914895212076132146637942120761321468127431207613214710650212076132147173457
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00509109409109454194304256002424291200x7fbc34dd9a000x7fbb292357001310722366703028056812076132147199375120761321473762611207613214750506012076132147508690
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00529109409109454194304256002424300800x7fbc34dd99000x7fbb292357401310722242042871076812076132147560146120761321477253791207613214786553812076132147869300
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00549109409109454194304256002424307840x7fbc34dd98000x7fbb292357801310722237342857134412076132147927909120761321480940171207613214822601712076132148229720
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00569109409109454194304256002824320000x7fbc34dd97000x7fbb292357c01310721848562379153612076132148278070120761321484560961207613214871065512076132148778190
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00589109409109454194304256002824329600x7fbc34dd96000x7fbb29235800655361778982285250412076132148802775120761321489812131207613214923993212076132149307974
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00609109409109454194304256002424339200x7fbc34dd95000x7fbb292358401310722315782959504812076132149331909120761321495114511207613214964073012076132149644379
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00629109409109454194304256002424348800x7fbc34dd94000x7fbb292358801310722264642891158412076132149692879120761321498543291207613214998424912076132149988178
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00649109409109454194304256002424358400x7fbc34dd93000x7fbb292358c01310722322122971721612076132150049061120761321502111281207613215034424712076132150348388
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00669109409109454194304256002824373120x7fbc34dd9a000x7fbb292359001310722119502719487212076132150399403120761321505624861207613215082248512076132150865278
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00689109409109454194304256002824382720x7fbc34dd99000x7fbb29235940655361535001961981612076132150891046120761321510732041207613215132840312076132151395834
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00709109409109454194304256002424392320x7fbc34dd98000x7fbb292359801310722558023275488012076132151422013120761321516028011207613215173704112076132151740886
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00729109409109454194304256002424401920x7fbc34dd97000x7fbb292359c01310722308262952261612076132151788454120761321519551201207613215209175912076132152096126
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00749109409109454194304256002424411520x7fbc34dd96000x7fbb29235a001310722203942829196012076132152158321120761321523207181207613215245287812076132152456716
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00769109409109454194304256002824426240x7fbc34dd95000x7fbb29235a401310721756662249792812076132152504214120761321526706371207613215292935512076132152996369
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00789109409109454194304256002824435840x7fbc34dd94000x7fbb29235a80655361433161838428812076132153018740120761321532096741207613215346439312076132153532856
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00809109409109454194304256002424445440x7fbc34dd93000x7fbb29235ac01310722312582970399212076132153559095120761321537336721207613215386119112076132153864983
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00829109409109454194304256002424457600x7fbc34dd9a000x7fbb29235b001310722523463240752012076132153913022120761321540813501207613215426134912076132154265457
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00849109409109454194304256002424467200x7fbc34dd99000x7fbb29235b401310722589223294526412076132154369872120761321546016681207613215473046712076132154734639
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00869109409109454194304256002824484480x7fbc34dd98000x7fbb29235b801310721862702373788812076132154777309120761321549771861207613215524758512076132155317092
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00889109409109454194304256002824494080x7fbc34dd97000x7fbb29235bc0655361485301904057612076132155378366120761321555970231207613215585462212076132155922357
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00909109409109454194304256002424503680x7fbc34dd96000x7fbb29235c001310722291322923785612076132155982769120761321562067801207613215634342012076132156347497
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00929109409109454194304256002424515840x7fbc34dd95000x7fbb29235c401310722335002996716812076132156407078120761321565781391207613215675829812076132156762127
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00949109409109454194304256002424525440x7fbc34dd94000x7fbb29235c801310722184042797248012076132156827238120761321569928571207613215712181612076132157126274
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00969109409109454194304256002824542720x7fbc34dd93000x7fbb29235cc01310721849882361628812076132157180765120761321573435751207613215761077412076132157678681
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00989109409109454194304256002824554880x7fbc34dd9a000x7fbb29235d00655361785902275723212076132157733523120761321579485331207613215820677112076132158277003
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001009109409109454194304256002424567040x7fbc34dd99000x7fbb29235d401310722254762899716812076132158339158120761321585563701207613215869252912076132158696492
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001029109409109454194304256002424581760x7fbc34dd98000x7fbb29235d801310722663223404259212076132158754620120761321589229281207613215906628712076132159070688
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001049109409109454194304256002424593920x7fbc34dd97000x7fbb29235dc01310722314582954030412076132159134637120761321593000461207613215943812612076132159442048
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001069109409109454194304256002824613760x7fbc34dd96000x7fbb29235e001310722260162901524012076132159500867120761321596630851207613215991924412076132159986229
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001089109409109454194304256002824625920x7fbc34dd95000x7fbb29235e40655361511761932536012076132160019231120761321602008421207613216045924112076132160527555
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001109109409109454194304256002424638080x7fbc34dd94000x7fbb29235e801310722261742885136812076132160558974120761321607394001207613216087539912076132160879349
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001129109409109454194304256002424652800x7fbc34dd93000x7fbb29235ec01310722266082893296812076132160929502120761321611051581207613216124771812076132161251811
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001149109409109454194304256002424664960x7fbc34dd9a000x7fbb29235f001310722258462896381612076132161312314120761321614731571207613216160579612076132161609676
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001169109409109454194304256002824684800x7fbc34dd99000x7fbb29235f401310722264302893673612076132161658768120761321618219551207613216208307412076132162152365
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001189109409109454194304256002824696960x7fbc34dd98000x7fbb29235f80655361824202326530412076132162179575120761321623557131207613216261427112076132162682751
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001209109409109454194304256002424709120x7fbc34dd97000x7fbb29235fc01310722328022967288812076132162707517120761321628827501207613216301491012076132163018915
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001229109409109454194304256002424723840x7fbc34dd96000x7fbb292360001310722241402883876012076132163067626120761321632363491207613216337490812076132163378744
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001249109409109454194304256002424736000x7fbc34dd95000x7fbb292360401310722314642948388012076132163441871120761321635987471207613216373154612076132163735567
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001269109409109454194304256002824758400x7fbc34dd94000x7fbb292360801310722105902704212012076132163783136120761321639549051207613216422418412076132164291811
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001289109409109454194304256002824770560x7fbc34dd93000x7fbb292360c0655361434261829164812076132164313020120761321644771431207613216473218212076132164800045
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001309109409109454194304256002424782720x7fbc34dd9a000x7fbb292361001310722580483294388812076132164820554120761321649784211207613216511890012076132165123216
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001329109409109454194304256002424800000x7fbc34dd99000x7fbb292361401310721828202340992812076132165169131120761321653168191207613216546129812076132165465402
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001349109409109454194304256002424812160x7fbc34dd98000x7fbb292361801310722257082904744012076132165525213120761321656587381207613216578865712076132165792610
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001369109409109454194304256002824834560x7fbc34dd97000x7fbb292361c01310721842022357992012076132165837904120761321659814561207613216625313512076132166305253
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001389109409109454194304256002824849280x7fbc34dd96000x7fbb29236200655361700042164460812076132166326823120761321664884941207613216675409312076132166803038
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001409109409109454194304256002424864000x7fbc34dd95000x7fbb292362401310722242562858952012076132166825880120761321669811311207613216711553112076132167120057
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001429109409109454194304256002424881280x7fbc34dd94000x7fbb292362801310721808042324804812076132167168527120761321673160101207613216746544912076132167469376
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001449109409109454194304256002424896000x7fbc34dd93000x7fbb292362c01310722271182908279212076132167542132120761321676795281207613216781280812076132167816712
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001469109409109454194304256002824920960x7fbc34dd9a000x7fbb292363001310721837262345137612076132167862357120761321680115271207613216828048612076132168329705
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001489109409109454194304256002824935680x7fbc34dd99000x7fbb29236340655361513241933243212076132168351386120761321685099251207613216876848312076132168819245
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001509109409109454194304256002424950400x7fbc34dd98000x7fbb292363801310722112682720202412076132168839843120761321689984021207613216913536212076132169139640
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001529109409109454194304256002424967680x7fbc34dd97000x7fbb292363c01310722221702844344812076132169185706120761321693320011207613216948896012076132169493067
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001549109409109454194304256002424982400x7fbc34dd96000x7fbb292364001310722269762907513612076132169552598120761321696833591207613216981679912076132169820646
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015691094091094541943042560028241007360x7fbc34dd95000x7fbb292364401310721766882258863212076132169866030120761321700212781207613217028959612076132170341484
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015891094091094541943042560028241022080x7fbc34dd94000x7fbb29236480655361780482278203212076132170361822120761321705201551207613217081839412076132170866600
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016091094091094541943042560024241036800x7fbc34dd93000x7fbb292364c01310722266342911332012076132170888230120761321710521531207613217119359212076132171197605
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016291094091094541943042560024241056640x7fbc34dd9a000x7fbb292365001310722279602913685612076132171242829120761321713982311207613217156367112076132171567513
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016491094091094541943042560024241071360x7fbc34dd99000x7fbb292365401310722458203143431212076132171626422120761321717635101207613217189150912076132171895723
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016691094091094541943042560028241098880x7fbc34dd98000x7fbb292365801310721867082393124812076132171938692120761321720950281207613217236270712076132172411281
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016891094091094541943042560028241113600x7fbc34dd97000x7fbb292365c0655361774922275389612076132172432079120761321725899061207613217284782512076132172896242
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017091094091094541943042560024241128320x7fbc34dd96000x7fbb292366001310722250442859888812076132172917762120761321730807841207613217321902312076132173223119
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017291094091094541943042560024241148160x7fbc34dd95000x7fbb292366401310722240082876355212076132173269716120761321734147021207613217358798112076132173591955
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017491094091094541943042560024241162880x7fbc34dd94000x7fbb292366801310722361743016449612076132173652397120761321737835011207613217392286012076132173926717
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017691094091094541943042560028241190400x7fbc34dd93000x7fbb292366c01310721818922330566412076132173973764120761321741262191207613217438909812076132174438328
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017891094091094541943042560028241207680x7fbc34dd9a000x7fbb29236700655361534421967678412076132174460259120761321746130971207613217490989512076132174957022
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018091094091094541943042560024241224960x7fbc34dd99000x7fbb292367401310722175922816557612076132174977339120761321751498941207613217529085412076132175294810
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018291094091094541943042560024241247360x7fbc34dd98000x7fbb292367801310722238262860216812076132175340865120761321754919731207613217567453212076132175678422
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018491094091094541943042560024241264640x7fbc34dd97000x7fbb292367c01310722196122809435212076132175738975120761321758716511207613217600973012076132176013916
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018691094091094541943042560020241279360x7fbc34dd96000x7fbb292368001310722262182883235212076132176059411120761321762042901207613217646828812076132176493658
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018891094091094541943042560028241296640x7fbc34dd95000x7fbb29236840655361422501827442412076132176533672120761321766663671207613217692556612076132176948823
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019091094091094541943042560024241313920x7fbc34dd94000x7fbb292368801310722244562871128012076132176989459120761321771292451207613217726332512076132177267746
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019291094091094541943042560024241336320x7fbc34dd93000x7fbb292368c01310722119702723759212076132177313090120761321774593241207613217765068312076132177675394
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019491094091094541943042560024241353600x7fbc34dd9a000x7fbb292369001310722235842869044812076132177727591120761321778602821207613217799516112076132177999376
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019691094091094541943042560020241368320x7fbc34dd99000x7fbb292369401310722267202911368812076132178046123120761321781985201207613217851403912076132178542225
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019891094091094541943042560028241385600x7fbc34dd98000x7fbb29236980655361476941890311212076132178578262120761321787282781207613217899211712076132179021105
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020091094091094541943042560024241402880x7fbc34dd97000x7fbb292369c01310722294942940802412076132179061800120761321791943561207613217933307512076132179337202
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020291094091094541943042560024241427840x7fbc34dd96000x7fbb29236a001310722249362886761612076132179381444120761321795257141207613217973531412076132179757333
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020491094091094541943042560024241447680x7fbc34dd95000x7fbb29236a401310722266402892291212076132179810522120761321799434731207613218008043212076132180084611
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020691094091094541943042560020241457280x7fbc34dd94000x7fbb29236a801310722263162879728012076132180130627120761321802773911207613218058363012076132180607944
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020891094091094541943042560028241477120x7fbc34dd93000x7fbb29236ac0655361483501897496812076132180646886120761321807770691207613218103466812076132181062799
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021091094091094541943042560024241496960x7fbc34dd9a000x7fbb29236b001310722222382852908812076132181103926120761321812469871207613218138938612076132181393504
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021291094091094541943042560024241521920x7fbc34dd99000x7fbb29236b401310722256902893483212076132181436874120761321815876251207613218181594412076132181841025
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021491094091094541943042560024241541760x7fbc34dd98000x7fbb29236b801310722242282871611212076132181895346120761321820329031207613218217226212076132182176619
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021691094091094541943042560020241556480x7fbc34dd97000x7fbb29236bc01310722213082843612812076132182221673120761321823719421207613218270138012076132182727443
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021891094091094541943042560028241576320x7fbc34dd96000x7fbb29236c00655361779142280240012076132182767307120761321828973791207613218315641812076132183184332
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022091094091094541943042560024241596160x7fbc34dd95000x7fbb29236c401310722268962907508012076132183223485120761321833567371207613218349705612076132183501020
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022291094091094541943042560024241623680x7fbc34dd94000x7fbb29236c801310722193582792918412076132183545183120761321836922561207613218393705412076132183958430
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022491094091094541943042560024241646080x7fbc34dd93000x7fbb29236cc01310722302082934604012076132184020516120761321841554531207613218429177312076132184295797
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022691094091094541943042560020241663360x7fbc34dd9a000x7fbb29236d001310722213382867476012076132184340911120761321844932241207613218486874312076132184896594
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022891094091094541943042560028241685760x7fbc34dd99000x7fbb29236d40655361509941932185612076132184934474120761321850799411207613218534634012076132185371296
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023091094091094541943042560024241708160x7fbc34dd98000x7fbb29236d801310722267502906858412076132185416130120761321855492191207613218568361912076132185687073
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023291094091094541943042560024241740800x7fbc34dd97000x7fbb29236dc01310722307102950132812076132185732377120761321858760981207613218615689712076132186185720
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023491094091094541943042560024241765760x7fbc34dd96000x7fbb29236e001310722254862893583212076132186235813120761321863706561207613218651561512076132186519129
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023691094091094541943042560020241777920x7fbc34dd95000x7fbb29236e401310722245062866856012076132186564003120761321867080951207613218715465312076132187179577
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023891094091094541943042560028241802880x7fbc34dd94000x7fbb29236e80655361766602264752812076132187220172120761321873527321207613218762153112076132187645012
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024091094091094541943042560024241827840x7fbc34dd93000x7fbb29236ec01310722233742848112812076132187683824120761321878119311207613218795305012076132187956491
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024291094091094541943042560024241863040x7fbc34dd9a000x7fbb29236f001310722450523114584812076132188007726120761321881623291207613218847656812076132188504159
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024491094091094541943042560024241893120x7fbc34dd99000x7fbb29236f401310722224802847690412076132188555454120761321886869671207613218883848712076132188841906
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024691094091094541943042560020241907840x7fbc34dd98000x7fbb29236f801310722455003130715212076132188887130120761321890402461207613218955720412076132189581150
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024891094091094541943042560028241937920x7fbc34dd97000x7fbb29236fc0655361461421874796012076132189621345120761321897576831207613219005560212076132190081169
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025091094091094541943042560024241968000x7fbc34dd96000x7fbb292370001310722271302895730412076132190120863120761321902546421207613219040920112076132190412876
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025291094091094541943042560024242010880x7fbc34dd95000x7fbb292370401310722259402904382412076132190456076120761321906117601207613219099815912076132191024543
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025491094091094541943042560024242046080x7fbc34dd94000x7fbb292370801310722263462891348012076132191080737120761321912167181207613219139271712076132191396143
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025691094091094541943042560020242060800x7fbc34dd93000x7fbb292370c01310722254582860806412076132191438913120761321915872771207613219219863412076132192223341
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025891094091094541943042560028242096000x7fbc34dd9a000x7fbb29237100655361455981854115212076132192265809120761321924000741207613219272567212076132192748486
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026091094091094541943042560024242131200x7fbc34dd99000x7fbb292371401310722253542884737612076132192788571120761321929221521207613219309975112076132193103246
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026291094091094541943042560024242181760x7fbc34dd98000x7fbb292371801310722238302873104012076132193150253120761321933061501207613219376198812076132193787327
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026491094091094541943042560024242222080x7fbc34dd97000x7fbb292371c01310722328642972320812076132193839204120761321939722281207613219417142712076132194198942
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026691094091094541943042560020242239360x7fbc34dd96000x7fbb292372001310721961742511353612076132194238606120761321943739861207613219507638412076132195102481
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026891094091094541943042560028242279680x7fbc34dd95000x7fbb29237240655361510161926265612076132195139169120761321952914231207613219566390112076132195688270
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027091094091094541943042560024242320000x7fbc34dd94000x7fbb292372801310722281102914459212076132195727503120761321958576611207613219606150012076132196086670
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027291094091094541943042560024242378240x7fbc34dd93000x7fbb292372c01310722348942992830412076132196131494120761321962635791207613219680645712076132196831474
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027491094091094541943042560024242423680x7fbc34dd9a000x7fbb292373001310722472123164716012076132196884904120761321970243761207613219724821612076132197276211
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027691094091094541943042560020242435840x7fbc34dd99000x7fbb292373401310722271002895545612076132197312969120761321974530151207613219825109212076132198277742
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027891094091094541943042560028242481280x7fbc34dd98000x7fbb29237380655361695662165696812076132198311986120761321984552511207613219887700912076132198898706
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028091094091094541943042560024242526720x7fbc34dd97000x7fbb292373c01310722355323006571212076132198945453120761321990861291207613219931268812076132199340758
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028291094091094541943042560024242592640x7fbc34dd96000x7fbb292374001310722601463372269612076132199386934120761321995194071207613220011524512076132200164589
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028491094091094541943042560024242648320x7fbc34dd95000x7fbb292374401310722231742874680012076132200202990120761322003429241207613220061316312076132200662093
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028691094091094541943042560020242663040x7fbc34dd94000x7fbb292374801310722249682885067212076132200689414120761322008429221207613220182707812076132201877863
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028891094091094541943042560028242718720x7fbc34dd93000x7fbb292374c0655361539441950524812076132201900976120761322020561981207613220257123612076132202621455
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029091094091094541943042560024242774400x7fbc34dd9a000x7fbb292375001310722577983299058412076132202645209120761322027989151207613220306995412076132203119080
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029291094091094541943042560012242799360x7fbc34dd99000x7fbb292375401310722413543079616012076132203140650120761322032958731207613220403395012076132204101886
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029491094091094541943042560024242865280x7fbc34dd98000x7fbb292375801310722147382759267212076132204140708120761322042819491207613220459906812076132204665584
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029691094091094541943042560020242880000x7fbc34dd97000x7fbb292375c01310722266322911009612076132204685200120761322048392271207613220600930312076132206090953
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029891094091094541943042560032242945920x7fbc34dd96000x7fbb29237600655361731282212729612076132206115238120761322062809821207613220689010012076132206956401
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030091094091094541943042560024243011840x7fbc34dd95000x7fbb292376401310722286322935101612076132206977771120761322071500991207613220747105712076132207537391
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030291094091094541943042560012243049600x7fbc34dd94000x7fbb292376801310722229622876756012076132207557548120761322077120171207613220858993312076132208656551
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030491094091094541943042560024243136000x7fbc34dd93000x7fbb292376c01310722223582862637612076132208691546120761322088435321207613220927617112076132209347605
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030691094091094541943042560020243148160x7fbc34dd9a000x7fbb292377001310722255162871879212076132209370027120761322095296101207613221107632412076132211144485
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030891094091094541943042560020243175680x7fbc34dd99000x7fbb29237740655361510601938595212076132211170052120761322113251231207613221212016012076132212190428
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031091094091094541943042560012243203200x7fbc34dd98000x7fbb292377801310722616823318996012076132212215796120761322123748791207613221278895812076132212855394
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031291094091094541943042560012243240960x7fbc34dd97000x7fbb292377c01310722297022937185612076132212876283120761322130395171207613221419775212076132214267689
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031491094091094541943042560012243288960x7fbc34dd96000x7fbb292378001310722256322885469612076132214308034120761322144425511207613221522830912076132215298244
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031691094091094541943042560020243301120x7fbc34dd95000x7fbb292378401310722089642653296812076132215327999120761322154807881207613221853037612076132218599199
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031891094091094541943042560020243328640x7fbc34dd94000x7fbb29237880655361779582269612812076132218623123120761322187826951207613222032333012076132220393784
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032091094091094541943042560012243356160x7fbc34dd93000x7fbb292378c01310722303362939519212076132220419281120761322205828491207613222137212612076132221440349
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032291094091094541943042560012243393920x7fbc34dd9a000x7fbb292379001310722281642917820812076132221467550120761322216294051207613222390971612076132223977945
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032491094091094541943042560012243441920x7fbc34dd99000x7fbb292379401310722349902991840012076132224021556120761322241705151207613222570651012076132225774514
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032691094091094541943042560020243454080x7fbc34dd98000x7fbb292379801310722652823382261612076132225805000120761322259599491207613223201256612076132232085593
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032891094091094541943042560020243481600x7fbc34dd97000x7fbb292379c0655361773462294019212076132232110399120761322322744851207613223531511412076132235386026
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033091094091094541943042560012243509120x7fbc34dd96000x7fbb29237a001310722202262814860812076132235410692120761322355703131207613223710950712076132237178077
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332910940910945419430425600122400x7fbc34dd95000x7fbb29237a401310722502423198416812076132237206470120761322373611861207613224188804912076132241956417