文件
rocm-systems/tests/workloads/dev1/mi100/SQ_INST_LEVEL_VMEM.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

43 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_VMEMSQ_INST_LEVEL_VMEMSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000926143926148335544322560083264640x00x7f15cfa04180104857611235576143814726012076419454465812120764197012149171207641970153987612076419701649649
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00292614392614832768256002424124800x00x7f15cfa3510040961139301456988412076419716046811120764197163515281207641971635792812076419716368830
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0049261439261484194304256002424129280x7f16ffbde9000x7f15cfa351405242889932637127137739612076419716430033120764197166412871207641971678144712076419716785163
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0069261439261484194304256003624136320x7f16ffbde8000x7f15cfa3518052428812650009161913356012076419716858309120764197170368051207641971729376412076419717361805
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0089261439261484194304256002824140800x7f16ffbde7000x7f15cfa351c052428814218994181995954012076419717394686120764197175809631207641971783600212076419717900566
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00109261439261484194304256002424145280x7f16ffbde6000x7f15cfa3520052428810134990129729886412076419717927867120764197181225601207641971826368012076419718267338
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00129261439261484194304256002424149760x7f16ffbde5000x7f15cfa3524052428810522452134683029212076419718315237120764197184969591207641971863583812076419718639199
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00149261439261484194304256002424154240x7f16ffbde4000x7f15cfa3528052428812575047160953408012076419718722002120764197188926371207641971902319612076419719026829
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00169261439261484194304256002824161280x7f16ffbde3000x7f15cfa352c052428813499725172793509212076419719082873120764197192486351207641971950735412076419719548739
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00189261439261484194304256002824168320x7f16ffbdea000x7f15cfa3530052428813945398178498999212076419719577081120764197197548731207641972001023212076419720048998
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00209261439261484194304256002424175360x7f16ffbde9000x7f15cfa3534052428812025815153926042012076419720073384120764197202662311207641972039967012076419720403016
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00229261439261484194304256002424182400x7f16ffbde8000x7f15cfa3538052428810151841129945238812076419720453660120764197206251091207641972076590912076419720769277
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00249261439261484194304256002424189440x7f16ffbde7000x7f15cfa353c052428812422833159005886412076419720832394120764197209972681207641972112766712076419721131219
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00269261439261484194304256002824199040x7f16ffbde6000x7f15cfa3540052428814359223183793496012076419721175461120764197213667061207641972162254512076419721688936
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00289261439261484194304256002824206080x7f16ffbde5000x7f15cfa3544052428813616119174281818412076419721715104120764197219031831207641972216318212076419722229380
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00309261439261484194304256002424213120x7f16ffbde4000x7f15cfa3548052428811963320153120579612076419722255639120764197224393411207641972257326012076419722576665
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00329261439261484194304256002424220160x7f16ffbde3000x7f15cfa354c052428811971440153231064012076419722627249120764197227970991207641972293037912076419722933789
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00349261439261484194304256002424227200x7f16ffbdea000x7f15cfa3550052428812526194160331612012076419722997968120764197231716581207641972330253712076419723305930
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00369261439261484194304256002824236800x7f16ffbde9000x7f15cfa3554052428813579446173811737212076419723361614120764197235228561207641972377933512076419723818994
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00389261439261484194304256002824243840x7f16ffbde8000x7f15cfa3558052428813634272174516162412076419723843128120764197240350141207641972428877312076419724354088
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00409261439261484194304256002424250880x7f16ffbde7000x7f15cfa355c052428812791268163727533612076419724380597120764197245668521207641972469629112076419724699770
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00429261439261484194304256002424257920x7f16ffbde6000x7f15cfa3560052428812614511161458711612076419724750875120764197249191701207641972505020912076419725053648
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00449261439261484194304256002424264960x7f16ffbde5000x7f15cfa3564052428810832190138639526812076419725118218120764197252865281207641972542540812076419725428815
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00469261439261484194304256002824277120x7f16ffbde4000x7f15cfa3568052428813632238174490712012076419725484148120764197256455671207641972590716512076419725971413
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00489261439261484194304256002824284160x7f16ffbde3000x7f15cfa356c052428813771485176270647612076419725998924120764197261854041207641972647548312076419726541643
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00509261439261484194304256002424291200x7f16ffbdea000x7f15cfa3570052428813303305170287709212076419726567631120764197267449221207641972687276112076419726876144
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00529261439261484194304256002424300800x7f16ffbde9000x7f15cfa3574052428812550002160630140412076419726928572120764197271206001207641972725307912076419727256762
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00549261439261484194304256002424307840x7f16ffbde8000x7f15cfa3578052428811732690150173836812076419727321452120764197274853981207641972761867812076419727622151
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00569261439261484194304256002824320000x7f16ffbde7000x7f15cfa357c052428813594804174011722012076419727672434120764197278541971207641972811547612076419728182041
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00589261439261484194304256002824329600x7f16ffbde6000x7f15cfa3580052428814002558179228068812076419728206246120764197283940341207641972865035312076419728714731
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00609261439261484194304256002424339200x7f16ffbde5000x7f15cfa3584052428813297888170219448012076419728740398120764197289189921207641972904619112076419729049663
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00629261439261484194304256002424348800x7f16ffbde4000x7f15cfa3588052428811036975141265648012076419729101870120764197292748301207641972941419012076419729417627
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00649261439261484194304256002424358400x7f16ffbde3000x7f15cfa358c052428812064695154417471212076419729481355120764197296437891207641972977738812076419729781012
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00669261439261484194304256002824373120x7f16ffbdea000x7f15cfa3590052428813992599179103889212076419729832929120764197299993071207641973026426612076419730331876
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00689261439261484194304256002824382720x7f16ffbde9000x7f15cfa3594052428814148259181096893612076419730357393120764197305417051207641973080090412076419730865147
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00709261439261484194304256002424392320x7f16ffbde8000x7f15cfa3598052428811125993142411750012076419730892608120764197310729021207641973121034212076419731214336
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00729261439261484194304256002424401920x7f16ffbde7000x7f15cfa359c052428810084763129083778812076419731265290120764197314458611207641973158762012076419731591076
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00749261439261484194304256002424411520x7f16ffbde6000x7f15cfa35a0052428812558509160753874012076419731652129120764197318149791207641973194489812076419731948430
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00769261439261484194304256002824426240x7f16ffbde5000x7f15cfa35a4052428813082130167449043212076419731999465120764197321704971207641973242841612076419732494144
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00789261439261484194304256002824435840x7f16ffbde4000x7f15cfa35a8052428813847702177249985212076419732520312120764197326992951207641973295753412076419732996277
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00809261439261484194304256002424445440x7f16ffbde3000x7f15cfa35ac052428811468388146783470412076419733026553120764197332096931207641973334649212076419733350495
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00829261439261484194304256002424457600x7f16ffbdea000x7f15cfa35b0052428812082807154653434412076419733401630120764197335685711207641973370201012076419733705735
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00849261439261484194304256002424467200x7f16ffbde9000x7f15cfa35b4052428812626036161606604012076419733768943120764197339346491207641973406536912076419734069211
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00869261439261484194304256002824484480x7f16ffbde8000x7f15cfa35b8052428813597815174045636412076419734123141120764197342895281207641973454776712076419734613873
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00889261439261484194304256002824494080x7f16ffbde7000x7f15cfa35bc052428813489008172653635612076419734640001120764197348178451207641973507608412076419735144909
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00909261439261484194304256002424503680x7f16ffbde6000x7f15cfa35c0052428811695156149691718412076419735168814120764197353562431207641973549144212076419735494890
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00929261439261484194304256002424515840x7f16ffbde5000x7f15cfa35c4052428810806002138309508812076419735544171120764197357189611207641973585784112076419735861231
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00949261439261484194304256002424525440x7f16ffbde4000x7f15cfa35c8052428811546421147788194412076419735925420120764197360991201207641973623367912076419736237209
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00969261439261484194304256002824542720x7f16ffbde3000x7f15cfa35cc052428813282244170010959612076419736289176120764197364586381207641973672487712076419736764098
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00989261439261484194304256002824554880x7f16ffbdea000x7f15cfa35d0052428813800773176649877212076419736790928120764197369675961207641973722711512076419737292550
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001009261439261484194304256002424567040x7f16ffbde9000x7f15cfa35d4052428810684886136763176812076419737320763120764197374986331207641973767783312076419737681353
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001029261439261484194304256002424581760x7f16ffbde8000x7f15cfa35d805242889240099118278764012076419737730654120764197379031121207641973804647112076419738050198
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001049261439261484194304256002424593920x7f16ffbde7000x7f15cfa35dc052428810612981135839724412076419738111913120764197382792701207641973841798912076419738421438
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001069261439261484194304256002824613760x7f16ffbde6000x7f15cfa35e0052428813014361166582361612076419738476370120764197386386281207641973890646712076419738970027
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001089261439261484194304256002824625920x7f16ffbde5000x7f15cfa35e4052428813630352174465932812076419738992188120764197391835861207641973944278512076419739507085
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001109261439261484194304256002424638080x7f16ffbde4000x7f15cfa35e8052428812468798159603806412076419739530358120764197397163831207641973984742312076419739850884
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001129261439261484194304256002424652800x7f16ffbde3000x7f15cfa35ec05242888904529113969851612076419739899504120764197400821421207641974022390112076419740227554
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001149261439261484194304256002424664960x7f16ffbdea000x7f15cfa35f0052428812370887158343128012076419740290230120764197404535001207641974058486012076419740588314
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001169261439261484194304256002824684800x7f16ffbde9000x7f15cfa35f4052428813110109167814883212076419740636744120764197408078991207641974107205712076419741120583
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001189261439261484194304256002824696960x7f16ffbde8000x7f15cfa35f8052428813741493175886294812076419741144608120764197413291761207641974158853512076419741653844
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001209261439261484194304256002424709120x7f16ffbde7000x7f15cfa35fc052428811624397148790077612076419741679472120764197418590941207641974199381312076419741997222
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001229261439261484194304256002424723840x7f16ffbde6000x7f15cfa36000524288756832796878946812076419742052585120764197422166921207641974235669212076419742360077
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001249261439261484194304256002424736000x7f16ffbde5000x7f15cfa3604052428812602644161318708812076419742422933120764197425910911207641974272229012076419742725666
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001269261439261484194304256002824758400x7f16ffbde4000x7f15cfa3608052428812822906164133948812076419742774978120764197429544491207641974322468812076419743270098
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001289261439261484194304256002824770560x7f16ffbde3000x7f15cfa360c052428813272155169884565212076419743295224120764197434805271207641974373828512076419743783522
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001309261439261484194304256002424782720x7f16ffbdea000x7f15cfa3610052428812357104158171468812076419743811033120764197439869241207641974416180312076419744165421
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001329261439261484194304256002424800000x7f16ffbde9000x7f15cfa36140524288745235495393524812076419744216146120764197443840421207641974452852212076419744532243
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001349261439261484194304256002424812160x7f16ffbde8000x7f15cfa3618052428810799160138231505612076419744594849120764197447565211207641974489428012076419744897902
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001369261439261484194304256002824834560x7f16ffbde7000x7f15cfa361c052428811621612148749208812076419744947595120764197451232391207641974539011812076419745438617
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001389261439261484194304256002824849280x7f16ffbde6000x7f15cfa3620052428814245893182343432812076419745464305120764197456448371207641974589875612076419745944277
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001409261439261484194304256002424864000x7f16ffbde5000x7f15cfa3624052428812767954163437567212076419745970616120764197461536351207641974628307412076419746286723
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001429261439261484194304256002424881280x7f16ffbde4000x7f15cfa36280524288569724172912528012076419746333620120764197465102731207641974665987212076419746663443
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001449261439261484194304256002424896000x7f16ffbde3000x7f15cfa362c052428810216473130768906812076419746746287120764197469061111207641974704611112076419747050011
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001469261439261484194304256002824920960x7f16ffbdea000x7f15cfa3630052428813382971171303160812076419747101237120764197472731491207641974754354812076419747587470
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001489261439261484194304256002824935680x7f16ffbde9000x7f15cfa3634052428813468522172395913212076419747613338120764197477888271207641974805250612076419748076549
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001509261439261484194304256002424950400x7f16ffbde8000x7f15cfa3638052428810807028138318982812076419748120330120764197482817851207641974841970412076419748423464
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001529261439261484194304256002424967680x7f16ffbde7000x7f15cfa363c0524288492291563001807612076419748474558120764197486381031207641974879666312076419748800103
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001549261439261484194304256002424982400x7f16ffbde6000x7f15cfa3640052428811576770148175825212076419748863241120764197490283421207641974916306112076419749166705
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015692614392614841943042560028241007360x7f16ffbde5000x7f15cfa3644052428810739718137467161212076419749218120120764197493881801207641974965425912076419749677354
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015892614392614841943042560028241022080x7f16ffbde4000x7f15cfa3648052428813403285171565701612076419749720904120764197498820981207641975014545712076419750171822
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016092614392614841943042560024241036800x7f16ffbde3000x7f15cfa364c052428811599650148473564012076419750214993120764197503758561207641975051089512076419750514509
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016292614392614841943042560024241056640x7f16ffbdea000x7f15cfa36500524288417680653466602812076419750564502120764197507366541207641975090289312076419750906417
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016492614392614841943042560024241071360x7f16ffbde9000x7f15cfa3654052428811916952152545783612076419750967451120764197511358521207641975131185112076419751315888
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016692614392614841943042560028241098880x7f16ffbde8000x7f15cfa365805242889783081125220370812076419751370660120764197515508901207641975181648912076419751834071
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016892614392614841943042560028241113600x7f16ffbde7000x7f15cfa365c052428813787281176473257212076419751879996120764197520456081207641975230288712076419752327889
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017092614392614841943042560024241128320x7f16ffbde6000x7f15cfa3660052428810574874135354879612076419752371330120764197525332861207641975267456512076419752678300
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017292614392614841943042560024241148160x7f16ffbde5000x7f15cfa36640524288366301946876040412076419752728694120764197528955241207641975306960312076419753073064
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017492614392614841943042560024241162880x7f16ffbde4000x7f15cfa3668052428810296488131792815612076419753139617120764197533008021207641975344016212076419753444013
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017692614392614841943042560028241190400x7f16ffbde3000x7f15cfa366c05242888792622112539800812076419753497653120764197536569611207641975392080012076419753941738
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017892614392614841943042560028241207680x7f16ffbdea000x7f15cfa3670052428813463530172327810012076419753987032120764197541518391207641975440959712076419754434093
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018092614392614841943042560024241224960x7f16ffbde9000x7f15cfa3674052428811360430145409946412076419754480980120764197546399961207641975477855612076419754782410
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018292614392614841943042560024241247360x7f16ffbde8000x7f15cfa36780524288328908942110272812076419754833715120764197550001551207641975518367412076419755187573
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018492614392614841943042560024241264640x7f16ffbde7000x7f15cfa367c052428810857078138960076412076419755250600120764197554118331207641975555231212076419755555697
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018692614392614841943042560020241279360x7f16ffbde6000x7f15cfa36800524288429604554982738012076419755606271120764197557723111207641975603887012076419756060805
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018892614392614841943042560028241296640x7f16ffbde5000x7f15cfa3684052428812559210160756272412076419756111780120764197562751891207641975653214812076419756553160
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019092614392614841943042560024241313920x7f16ffbde4000x7f15cfa3688052428811018463141046884412076419756601290120764197567627071207641975690014612076419756904132
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019292614392614841943042560024241336320x7f16ffbde3000x7f15cfa368c0524288328627542071029612076419756954696120764197571254251207641975731678412076419757342487
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019492614392614841943042560024241353600x7f16ffbdea000x7f15cfa3690052428810931657139926369212076419757401026120764197575643031207641975770142312076419757705311
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019692614392614841943042560020241368320x7f16ffbde9000x7f15cfa36940524288288263436902971612076419757758119120764197579297421207641975821326012076419758237710
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019892614392614841943042560028241385600x7f16ffbde8000x7f15cfa3698052428813539606173304708812076419758280350120764197584394991207641975870029812076419758722070
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020092614392614841943042560024241402880x7f16ffbde7000x7f15cfa369c052428810858837138990084412076419758766162120764197589257371207641975906349712076419759067192
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020292614392614841943042560024241427840x7f16ffbde6000x7f15cfa36a00524288349271044715622012076419759116764120764197592866961207641975949709512076419759518120
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020492614392614841943042560024241447680x7f16ffbde5000x7f15cfa36a4052428810311426131984501212076419759583742120764197597471731207641975988781312076419759891654
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020692614392614841943042560020241457280x7f16ffbde4000x7f15cfa36a80524288258423733065051212076419759941657120764197601137321207641976042125012076419760443098
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020892614392614841943042560028241477120x7f16ffbde3000x7f15cfa36ac052428813582899173862392012076419760489094120764197606518091207641976090972812076419760931306
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021092614392614841943042560024241496960x7f16ffbdea000x7f15cfa36b0052428810290712131710692412076419760975468120764197611418871207641976128092712076419761284973
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021292614392614841943042560024241521920x7f16ffbde9000x7f15cfa36b40524288325610241680837612076419761329235120764197615033261207641976173068512076419761752221
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021492614392614841943042560024241541760x7f16ffbde8000x7f15cfa36b805242889672407123809997612076419761812072120764197619727631207641976211500312076419762118912
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021692614392614841943042560020241556480x7f16ffbde7000x7f15cfa36bc0524288247069131615497612076419762169797120764197623409221207641976269900012076419762720430
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021892614392614841943042560028241576320x7f16ffbde6000x7f15cfa36c0052428814169863181366486012076419762766887120764197629330791207641976319483812076419763216732
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022092614392614841943042560024241596160x7f16ffbde5000x7f15cfa36c405242889597579122842552412076419763262888120764197634349971207641976357611612076419763580068
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022292614392614841943042560024241623680x7f16ffbde4000x7f15cfa36c80524288324776441576475212076419763630201120764197638100351207641976405435412076419764076530
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022492614392614841943042560024241646080x7f16ffbde3000x7f15cfa36cc05242889742968124713297612076419764144847120764197643153461207641976445486612076419764462197
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022692614392614841943042560020241663360x7f16ffbdea000x7f15cfa36d00524288241343430889440812076419764508533120764197646863841207641976506382212076419765085605
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022892614392614841943042560028241685760x7f16ffbde9000x7f15cfa36d4052428813213049169134759612076419765136149120764197653052611207641976556702012076419765587678
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023092614392614841943042560024241708160x7f16ffbde8000x7f15cfa36d805242889364538119864808812076419765632572120764197657998191207641976593773912076419765941355
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023292614392614841943042560024241740800x7f16ffbde7000x7f15cfa36dc0524288316388640490576412076419765999223120764197661726181207641976645341612076419766478223
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023492614392614841943042560024241765760x7f16ffbde6000x7f15cfa36e005242888618968110327653212076419766541871120764197667110151207641976685165512076419766855233
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023692614392614841943042560020241777920x7f16ffbde5000x7f15cfa36e40524288239777830675445212076419766899225120764197670967741207641976754541212076419767569561
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023892614392614841943042560028241802880x7f16ffbde4000x7f15cfa36e8052428810266435131414349612076419767611499120764197677828511207641976804861012076419768075591
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024092614392614841943042560024241827840x7f16ffbde3000x7f15cfa36ec0524288728633693267916812076419768119002120764197682900491207641976843004812076419768433687
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024292614392614841943042560024241863040x7f16ffbdea000x7f15cfa36f00524288333454542684995212076419768484070120764197686588481207641976897452612076419768995360
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024492614392614841943042560024241893120x7f16ffbde9000x7f15cfa36f40524288356525545637733212076419769064699120764197692361251207641976938844512076419769392148
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024692614392614841943042560020241907840x7f16ffbde8000x7f15cfa36f80524288231769829653006812076419769442952120764197696194841207641977013708212076419770159113
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024892614392614841943042560028241937920x7f16ffbde7000x7f15cfa36fc05242887938901101617397212076419770208314120764197703742011207641977067291912076419770693666
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025092614392614841943042560024241968000x7f16ffbde6000x7f15cfa37000524288310486439738592412076419770746274120764197709157981207641977107115812076419771074744
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025292614392614841943042560024242010880x7f16ffbde5000x7f15cfa37040524288344016044035471212076419771120720120764197713138771207641977170011512076419771722878
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025492614392614841943042560024242046080x7f16ffbde4000x7f15cfa37080524288349956944776180412076419771781948120764197719514741207641977212907312076419772132750
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025692614392614841943042560020242060800x7f16ffbde3000x7f15cfa370c0524288232227929738281612076419772183164120764197723617131207641977297211012076419772993229
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025892614392614841943042560028242096000x7f16ffbdea000x7f15cfa37100524288468747159996723612076419773044895120764197732133891207641977354282812076419773565172
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026092614392614841943042560024242131200x7f16ffbde9000x7f15cfa37140524288313444540110074812076419773615485120764197737767471207641977395658612076419773959905
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026292614392614841943042560024242181760x7f16ffbde8000x7f15cfa37180524288344960044156563212076419774020248120764197741791451207641977463450312076419774660347
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026492614392614841943042560024242222080x7f16ffbde7000x7f15cfa371c0524288301268838555342412076419774719026120764197748802621207641977508042212076419775103671
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026692614392614841943042560020242239360x7f16ffbde6000x7f15cfa37200524288231767529662978012076419775152782120764197753154611207641977602537812076419776049869
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026892614392614841943042560028242279680x7f16ffbde5000x7f15cfa37240524288358294845855345612076419776098469120764197762586571207641977663273512076419776654853
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027092614392614841943042560024242320000x7f16ffbde4000x7f15cfa37280524288337262143158736812076419776702752120764197768652141207641977706985312076419777091965
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027292614392614841943042560024242378240x7f16ffbde3000x7f15cfa372c0524288423576754213704812076419777138372120764197772996131207641977782569012076419777848812
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027492614392614841943042560024242423680x7f16ffbdea000x7f15cfa37300524288322794541309559212076419777907691120764197780820091207641977830680812076419778331819
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027692614392614841943042560020242435840x7f16ffbde9000x7f15cfa37340524288233135929827612012076419778375040120764197785357681207641977933448412076419779381650
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027892614392614841943042560028242481280x7f16ffbde8000x7f15cfa37380524288364632146665063212076419779413249120764197795946431207641978001624212076419780062846
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028092614392614841943042560024242526720x7f16ffbde7000x7f15cfa373c0524288306937339286075212076419780099003120764197802757601207641978050136012076419780545653
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028292614392614841943042560024242592640x7f16ffbde6000x7f15cfa37400524288449871457585303612076419780571691120764197807474391207641978135767612076419781407464
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028492614392614841943042560024242648320x7f16ffbde5000x7f15cfa37440524288325023941594666012076419781446307120764197816191151207641978188727412076419781932660
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028692614392614841943042560020242663040x7f16ffbde4000x7f15cfa37480524288234863530056524812076419781965291120764197821475931207641978313206912076419783201117
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028892614392614841943042560028242718720x7f16ffbde3000x7f15cfa374c0524288325804441705500012076419783231344120764197834127081207641978392662612076419783991366
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029092614392614841943042560024242774400x7f16ffbdea000x7f15cfa37500524288333100342640704412076419784024598120764197842048651207641978447686312076419784542811
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029292614392614841943042560012242799360x7f16ffbde9000x7f15cfa37540524288220300828199694012076419784567226120764197847539821207641978549237912076419785558758
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029492614392614841943042560024242865280x7f16ffbde8000x7f15cfa37580524288342754043867052412076419785606818120764197857698181207641978608709712076419786152942
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029692614392614841943042560020242880000x7f16ffbde7000x7f15cfa375c0524288230523529497649212076419786181996120764197863629361207641978753205112076419787598639
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029892614392614841943042560032242945920x7f16ffbde6000x7f15cfa37600524288332855542605991612076419787633474120764197878054901207641978841524812076419788487230
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030092614392614841943042560024243011840x7f16ffbde5000x7f15cfa37640524288328204042018765612076419788523107120764197886864461207641978900532512076419789051328
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030292614392614841943042560012243049600x7f16ffbde4000x7f15cfa37680524288220968028287011612076419789081705120764197892667641207641979014548112076419790212626
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030492614392614841943042560024243136000x7f16ffbde3000x7f15cfa376c0524288328591242051997612076419790259744120764197904243591207641979083603812076419790900945
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030692614392614841943042560020243148160x7f16ffbdea000x7f15cfa37700524288234701030031685212076419790935770120764197911171571207641979266611012076419792735033
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030892614392614841943042560020243175680x7f16ffbde9000x7f15cfa37740524288226087328933744412076419792765239120764197929453091207641979374034612076419793810231
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031092614392614841943042560012243203200x7f16ffbde8000x7f15cfa37780524288215422327559813212076419793839095120764197940222651207641979443714312076419794503389
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031292614392614841943042560012243240960x7f16ffbde7000x7f15cfa377c0524288225872928901675612076419794529287120764197947070621207641979586609712076419795933397
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031492614392614841943042560012243288960x7f16ffbde6000x7f15cfa37800524288223204828560534812076419795977028120764197961444961207641979693041312076419796997905
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031692614392614841943042560020243301120x7f16ffbde5000x7f15cfa37840524288266795734149704812076419797040504120764197972028921207641980025056012076419800318495
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031892614392614841943042560020243328640x7f16ffbde4000x7f15cfa37880524288232869529807578412076419800348060120764198005302381207641980207055212076419802137084
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032092614392614841943042560012243356160x7f16ffbde3000x7f15cfa378c0524288225763328902959612076419802171899120764198023547111207641980314446812076419803211461
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032292614392614841943042560012243393920x7f16ffbdea000x7f15cfa37900524288254034232520320412076419803246916120764198034193471207641980570077812076419805767961
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032492614392614841943042560012243441920x7f16ffbde9000x7f15cfa37940524288238572630546164012076419805816361120764198059806161207641980751645012076419807585779
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032692614392614841943042560020243454080x7f16ffbde8000x7f15cfa37980524288290892437222259612076419807619912120764198077930891207641981384458512076419813913898
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032892614392614841943042560020243481600x7f16ffbde7000x7f15cfa379c0524288324182741499526812076419813943082120764198141293831207641981717049112076419817242613
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033092614392614841943042560012243509120x7f16ffbde6000x7f15cfa37a00524288239333330630129612076419817281385120764198174500101207641981898920412076419819055672
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332926143926148419430425600122400x7f16ffbde5000x7f15cfa37a40524288251538632184338012076419819092290120764198192591231207641982378566412076419823852856