Files
rocm-systems/tests/workloads/dev1/mi200/SQ_INST_LEVEL_VMEM.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

41 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_VMEMSQ_INST_LEVEL_VMEMSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000231013231013335544322560043241600x00x7ff8df004280524288545903061138056417722381097853177201215228291772252875963817722528847088
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00223101323101332768256001224138880x00x7ff8df023f80409641280461943617722533966569177225287596381772253409468717722534099686
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0052310132310134194304256001224143360x7ff8e20753800x7ff8df023fc052428810744640120336474417722534135465177225340946871772253446572817722534468237
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0082310132310134194304256001624150400x7ff8e20752000x7ff8df02400052428811602268129942222817722534505476177225344657281772253487020917722534872437
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00112310132310134194304256001624154880x7ff8e20750800x7ff8df02404052428811558892129458274017722534905856177225348702091772253526780917722535270057
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00142310132310134194304256001224159360x7ff8dfa17f000x7ff8df02408052428811002806123226357617722535303986177225352678091772253557341017722535575709
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00172310132310134194304256001224163840x7ff8dfa17d800x7ff8df0240c052428810933758122456048417722535608458177225355734101772253587805117722535880292
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00202310132310134194304256001224170880x7ff8dfa17c000x7ff8df02410052428811077918124061252817722535925700177225358780511772253617853117722536180784
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00232310132310134194304256001624177920x7ff8dfa17a800x7ff8df02414052428811447595128208143617722536213703177225361785311772253656957217722536571764
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00262310132310134194304256001624184960x7ff8dfa179000x7ff8df02418052428811462245128376526817722536604563177225365695721772253696173317722536963945
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00292310132310134194304256001624192000x7ff8dfa177800x7ff8df0241c052428810642263119188009217722536994724177225369617331772253727677317722537278977
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00322310132310134194304256001624199040x7ff8dfa176000x7ff8df02420052428811029195123520721617722537311546177225372767731772253757885417722537581119
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00352310132310134194304256001224206080x7ff8e20754800x7ff8df02424052428810678060119587835217722537621258177225375788541772253789197417722537894531
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00382310132310134194304256001624213120x7ff8e20753000x7ff8df02428052428811481408128591788817722537927330177225378919741772253829133517722538293671
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00412310132310134194304256001624220160x7ff8e20751800x7ff8df0242c052428811391487127585364017722538326060177225382913351772253868989617722538692201
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00442310132310134194304256001624227200x7ff8e20750000x7ff8df02430052428811182290125239914817722538725610177225386898961772253899229617722538994104
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00472310132310134194304256001224234240x7ff8dfa17e800x7ff8df02434052428810755693120455858017722539026443177225389922961772253926781717722539269497
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00502310132310134194304256001224241280x7ff8dfa17d000x7ff8df02438052428811300523126560934017722539309816177225392678171772253954573717722539547390
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00532310132310134194304256001624248320x7ff8dfa17b800x7ff8df0243c052428811479621128567992817722539580439177225395457371772253990781817722539909611
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00562310132310134194304256001624255360x7ff8dfa17a000x7ff8df02440052428811414885127844529217722539941550177225399078181772254027629917722540278011
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00592310132310134194304256001224262400x7ff8dfa178800x7ff8df02444052428810700528119846696017722540310740177225402762991772254055357917722540555154
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00622310132310134194304256001224269440x7ff8dfa177000x7ff8df02448052428811052654123787597217722540587253177225405535791772254082974017722540831457
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00652310132310134194304256001224276480x7ff8e20755800x7ff8df0244c052428810894796122015986817722540871646177225408297401772254110622017722541107920
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00682310132310134194304256001624286080x7ff8e20754000x7ff8df02450052428811308215126649399617722541141800177225411062201772254146926117722541470901
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00712310132310134194304256001624293120x7ff8e20752800x7ff8df02454052428811404222127721383617722541503490177225414692611772254183470217722541836322
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00742310132310134194304256001224300160x7ff8e20751000x7ff8df02458052428810845663121474691217722541869211177225418347021772254210926217722542110935
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077231013231013419430425600824309760x7ff8dfa17f800x7ff8df0245c052428810556196118229612017722542144164177225421092621772254239102317722542392718
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00802310132310134194304256001224316800x7ff8dfa17e000x7ff8df02460052428811062995123904115217722542431757177225423910231772254266574317722542667441
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00832310132310134194304256001624326400x7ff8dfa17c800x7ff8df02464052428811482391128601256017722542699460177225426657431772254303518417722543036842
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00862310132310134194304256001224336000x7ff8dfa17b000x7ff8df02468052428811580308129698435217722543068381177225430351841772254340094517722543402633
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00892310132310134194304256001224345600x7ff8dfa179800x7ff8df0246c052428810609812118830205217722543434592177225434009451772254367774517722543679456
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092231013231013419430425600824355200x7ff8dfa178000x7ff8df02470052428810276978115104452817722543711445177225436777451772254395438617722543956039
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00952310132310134194304256001224362240x7ff8dfa176800x7ff8df02474052428810727205120144039617722543995208177225439543861772254422910617722544230762
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00982310132310134194304256001224371840x7ff8e20755000x7ff8df02478052428811257914126087626017722544262431177225442291061772254459278717722544594393
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001012310132310134194304256001224381440x7ff8e20753800x7ff8df0247c052428811214513125602602817722544627102177225445927871772254495518817722544956774
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001042310132310134194304256001224391040x7ff8e20752000x7ff8df02480052428810867629121714720017722544989213177225449551881772254522958817722545231207
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107231013231013419430425600824403200x7ff8e20750800x7ff8df0248405242889873707110580841217722545264046177225452295881772254550414917722545505760
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001102310132310134194304256001224412800x7ff8dfa17f000x7ff8df02488052428810978873122956724017722545544859177225455041491772254579070917722545792423
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001132310132310134194304256001224422400x7ff8dfa17d800x7ff8df0248c052428811454727128284750017722545824392177225457907091772254615487017722546156584
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001162310132310134194304256001224432000x7ff8dfa17c000x7ff8df02490052428811317829126755522017722546190853177225461548701772254653599017722546537634
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119231013231013419430425600824441600x7ff8dfa17a800x7ff8df02494052428810570583118385319617722546569974177225465359901772254681327117722546814957
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001222310132310134194304256001224453760x7ff8dfa179000x7ff8df0249805242889704097108680294017722546846777177225468132711772254709119217722547092761
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001252310132310134194304256001224463360x7ff8dfa177800x7ff8df0249c052428810489813117482594817722547131840177225470911921772254736943217722547371074
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001282310132310134194304256001224475520x7ff8dfa176000x7ff8df024a0052428811125555124605329617722547402413177225473694321772254773151317722547733184
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001312310132310134194304256001224485120x7ff8e20754800x7ff8df024a4052428811273040126255090817722547765864177225477315131772254809295317722548094605
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134231013231013419430425600824494720x7ff8e20753000x7ff8df024a8052428810339644115806872417722548126785177225480929531772254836671417722548368389
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001372310132310134194304256001224506880x7ff8e20751800x7ff8df024ac05242889186343102890278417722548400878177225483667141772254864735417722548648992
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001402310132310134194304256001224516480x7ff8e20750000x7ff8df024b0052428810637557119132362417722548689291177225486473541772254892191517722548923545
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001432310132310134194304256001224528640x7ff8dfa17e800x7ff8df024b4052428811157941124968423617722548955444177225489219151772254928463617722549286476
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001462310132310134194304256001224540800x7ff8dfa17d000x7ff8df024b8052428811274971126278888017722549319175177225492846361772254964543617722549647007
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149231013231013419430425600824552960x7ff8dfa17b800x7ff8df024bc052428810222384114485880017722549678936177225496454361772254992207717722549923840
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001522310132310134194304256001224567680x7ff8dfa17a000x7ff8df024c00524288777896287120167617722549955219177225499220771772255020815717722550210113
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001552310132310134194304256001224577280x7ff8dfa178800x7ff8df024c4052428810482821117408775217722550249162177225502081571772255048863817722550490275
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001582310132310134194304256001224589440x7ff8dfa177000x7ff8df024c8052428811404093127723293617722550522235177225504886381772255085087917722550852636
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001612310132310134194304256001224601600x7ff8e20755800x7ff8df024cc052428811348006127097505217722550884576177225508508791772255121279917722551214417
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164231013231013419430425600824613760x7ff8e20754000x7ff8df024d0052428810013835112149690017722551247326177225512127991772255149376017722551495410
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001672310132310134194304256001224628480x7ff8e20752800x7ff8df024d40524288593463266470748017722551528019177225514937601772255177456017722551776213
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001702310132310134194304256001224638080x7ff8e20751000x7ff8df024d8052428810300403115362730817722551816722177225517745601772255205120117722552052876
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001732310132310134194304256001224650240x7ff8dfa17f800x7ff8df024dc052428811308472126650525217722552086345177225520512011772255241376117722552415397
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001762310132310134194304256001224662400x7ff8dfa17e000x7ff8df024e0052428811189316125319221617722552447126177225524137611772255277488217722552776448
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179231013231013419430425600824674560x7ff8dfa17c800x7ff8df024e4052428810008093112089740017722552808457177225527748821772255305248317722553054181
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001822310132310134194304256001224689280x7ff8dfa17b000x7ff8df024e80524288581992865179411217722553086380177225530524831772255333776317722553339324
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001852310132310134194304256001224701440x7ff8dfa179800x7ff8df024ec052428810129195113453149617722553379233177225533377631772255361488417722553616707
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001882310132310134194304256001224716160x7ff8dfa178000x7ff8df024f0052428811353637127158306017722553648466177225536148841772255397904417722553980818
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001912310132310134194304256001224728320x7ff8dfa176800x7ff8df024f4052428811336071126961287217722554014767177225539790441772255435808517722554359728
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194231013231013419430425600824740480x7ff8e20755000x7ff8df024f805242889674560108359476417722554392267177225543580851772255463584617722554637421
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001972310132310134194304256001224757760x7ff8e20753800x7ff8df024fc0524288436949448927618417722554669810177225546358461772255492432617722554925974
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002002310132310134194304256001224769920x7ff8e20752000x7ff8df02500052428810248987114786928417722554965443177225549243261772255520224717722555203887
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002032310132310134194304256001224784640x7ff8e20750800x7ff8df02504052428811369303127334919217722555235766177225552022471772255556704717722555568688
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002062310132310134194304256001224799360x7ff8dfa17f000x7ff8df02508052428811267449126194107617722555601037177225555670471772255593056817722555932409
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209231013231013419430425600824814080x7ff8dfa17d800x7ff8df0250c05242889227396103342877617722555963388177225559305681772255620608917722556207762
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002122310132310134194304256001224831360x7ff8dfa17c000x7ff8df025100524288387904043440368417722556240201177225562060891772255650208917722556503744
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002152310132310134194304256001224843520x7ff8dfa17a800x7ff8df02514052428810682895119640930017722556553193177225565020891772255678241017722556784027
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002182310132310134194304256001224858240x7ff8dfa179000x7ff8df02518052428811249975125997538017722556816057177225567824101772255714913017722557150778
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002212310132310134194304256001224872960x7ff8dfa177800x7ff8df0251c052428811198603125420229617722557183677177225571491301772255751521117722557516869
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002242310132310134194304256001224887680x7ff8dfa176000x7ff8df0252005242889492222106312605217722557549358177225575152111772255779425117722557795822
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002272310132310134194304256001224907520x7ff8e20754800x7ff8df025240524288367692241178150417722557827871177225577942511772255809457217722558096595
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002302310132310134194304256001224919680x7ff8e20753000x7ff8df02528052428810053656112605194017722558137044177225580945721772255838545317722558387067
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002332310132310134194304256001224934400x7ff8e20751800x7ff8df0252c052428811117764124516412817722558418927177225583854531772255874737317722558748938
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002362310132310134194304256001224949120x7ff8e20750000x7ff8df02530052428811281882126355169217722558781407177225587473731772255910881417722559110599
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002392310132310134194304256001224963840x7ff8dfa17e800x7ff8df0253405242889189575102927926417722559142658177225591088141772255938545417722559387182
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002422310132310134194304256001224983680x7ff8dfa17d000x7ff8df025380524288354028739653821217722559419021177225593854541772255969697517722559698794
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002452310132310134194304256001224995840x7ff8dfa17b800x7ff8df0253c05242889931522111236201617722559737473177225596969751772255998161617722559983237
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024823101323101341943042560012241013120x7ff8dfa17a000x7ff8df02540052428811209241125541080017722560015306177225599816161772256034833617722560349988
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025123101323101341943042560012241027840x7ff8dfa178800x7ff8df02544052428811214758125606980017722560382927177225603483361772256071073717722560712339
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025423101323101341943042560012241042560x7ff8dfa177000x7ff8df025480524288876276998144762417722560744148177225607107371772256098833717722560990132
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025723101323101341943042560012241062400x7ff8e20755800x7ff8df0254c0524288319915035829401617722561021951177225609883371772256130065817722561302334
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026023101323101341943042560012241077120x7ff8e20754000x7ff8df0255005242889871689110559783617722561342763177225613006581772256158161917722561583217
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026323101323101341943042560016241094400x7ff8e20752800x7ff8df02554052428811189662125321788817722561615636177225615816191772256194433917722561945898
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026623101323101341943042560016241111680x7ff8e20751000x7ff8df02558052428811003234123231216017722561978517177225619443391772256231602017722562317818
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002692310132310134194304256008241128960x7ff8dfa17f800x7ff8df0255c0524288818777991700231617722562350298177225623160201772256259698017722562598581
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027223101323101341943042560012241151360x7ff8dfa17e000x7ff8df025600524288319769935806173617722562630801177225625969801772256291810117722562919693
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027523101323101341943042560012241166080x7ff8dfa17c800x7ff8df0256405242889573284107219059617722562960222177225629181011772256320290217722563204466
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027823101323101341943042560016241183360x7ff8dfa17b000x7ff8df02568052428811087759124179760017722563236095177225632029021772256356434217722563565957
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028123101323101341943042560016241200640x7ff8dfa179800x7ff8df0256c052428811104011124361746817722563598446177225635643421772256392434317722563925948
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028423101323101341943042560012241217920x7ff8dfa178000x7ff8df025700524288681403376311462417722563956967177225639243431772256420370317722564205381
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028723101323101341943042560012241240320x7ff8dfa176800x7ff8df025740524288299684633567214017722564237560177225642037031772256452866417722564530313
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029023101323101341943042560012241255040x7ff8e20755000x7ff8df0257805242889235277103428762817722564568802177225645286641772256480386517722564805516
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029323101323101341943042560012241274880x7ff8e20753800x7ff8df0257c052428810944298122576398417722564836625177225648038651772256516978517722565171547
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029623101323101341943042560012241292160x7ff8e20752000x7ff8df02580052428811100198124318850417722565204076177225651697851772256553154617722565533118
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029923101323101341943042560012241309440x7ff8e20750800x7ff8df025840524288615222468898927617722565564687177225655315461772256581426617722565815921
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030223101323101341943042560012241334400x7ff8dfa17f000x7ff8df025880524288294951733038761617722565847720177225658142661772256615538717722566157432
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030523101323101341943042560012241349120x7ff8dfa17d800x7ff8df0258c0524288836886093732291217722566196801177225661553871772256644482817722566446465
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030823101323101341943042560012241368960x7ff8dfa17c000x7ff8df02590052428810846797121483832017722566477604177225664448281772256680898817722566810566
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031123101323101341943042560012241388800x7ff8dfa17a800x7ff8df02594052428810830429121298514417722566842045177225668089881772256717218917722567173907
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031423101323101341943042560012241408640x7ff8dfa179000x7ff8df025980524288460922451624087617722567204836177225671721891772256746099017722567462700
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031723101323101341943042560012241436160x7ff8dfa177800x7ff8df0259c0524288286097932039066817722567494819177225674609901772256781123017722567812801
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032023101323101341943042560012241453440x7ff8dfa176000x7ff8df025a00524288736324682462783217722567851820177225678112301772256808547117722568087124
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032323101323101341943042560012241475840x7ff8e20754800x7ff8df025a4052428810714497119998906417722568118103177225680854711772256844867117722568450365
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032623101323101341943042560012241495680x7ff8e20753000x7ff8df025a8052428810936150122480939617722568482644177225684486711772256880979217722568811526
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032923101323101341943042560012241515520x7ff8e20751800x7ff8df025ac0524288385791043203585617722568842315177225688097921772256910771317722569109439
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033223101323101341943042560012241543040x7ff8e20750000x7ff8df025b00524288284778931899456417722569141248177225691077131772256947235317722569473949
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033523101323101341943042560012241562880x7ff8dfa17e800x7ff8df025b40524288545709761121559217722569512878177225694723531772256975459417722569756272
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033823101323101341943042560012241587840x7ff8dfa17d000x7ff8df025b805242889856586110389266417722569786852177225697545941772257011891417722570120553
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034123101323101341943042560012241610240x7ff8dfa17b800x7ff8df025bc052428810783907120778880017722570152142177225701189141772257048867517722570490384
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034423101323101341943042560012241632640x7ff8dfa17a000x7ff8df025c00524288347178238880416817722570521573177225704886751772257079443617722570796106
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034723101323101341943042560012241665280x7ff8dfa178800x7ff8df025c40524288288104732258469617722570826685177225707944361772257118595617722571209196
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035023101323101341943042560012241685120x7ff8dfa177000x7ff8df025c80524288407567745652182017722571228215177225711859561772257148947717722571491029
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035323101323101341943042560012241712640x7ff8e20755800x7ff8df025cc05242889460806105963068017722571521138177225714894771772257185347817722571855110
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035623101323101341943042560012241737600x7ff8e20754000x7ff8df025d0052428810349542115912326417722571886839177225718534781772257222707817722572228900
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035923101323101341943042560012241762560x7ff8e20752800x7ff8df025d40524288286926032129138417722572259789177225722270781772257254835917722572550142
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036223101323101341943042560012241797760x7ff8e20751000x7ff8df025d80524288287983632247339617722572581371177225725483591772257296596017722572984331
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036523101323101341943042560012241822720x7ff8dfa17f800x7ff8df025dc0524288317086835510028417722573006671177225729659601772257328580017722573287483
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036823101323101341943042560012241855360x7ff8dfa17e000x7ff8df025e00524288809106190618872817722573319353177225732858001772257366564117722573683404
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037123101323101341943042560012241885440x7ff8dfa17c800x7ff8df025e40524288762858985443644417722573699243177225736656411772257404884217722574051804
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037423101323101341943042560012241915520x7ff8dfa17b000x7ff8df025e80524288280175431374996417722574087503177225740488421772257440852217722574410555
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037723101323101341943042560012241958400x7ff8dfa179800x7ff8df025ec0524288284527331859783617722574441055177225744085221772257487812317722574924742
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038023101323101341943042560012241985920x7ff8dfa178000x7ff8df025f00524288270201830261302017722574943292177225748781231772257524148417722575243294
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038323101323101341943042560012242023680x7ff8dfa176800x7ff8df025f40524288691876977482562017722575274084177225752414841772257563732517722575682793
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038623101323101341943042560012242058880x7ff8e20755000x7ff8df025f80524288579970464957883217722575693703177225756373251772257606260617722576107333
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038923101323101341943042560012242094080x7ff8e20753800x7ff8df025fc0524288281724131550885617722576118533177225760626061772257646772617722576469384
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039223101323101341943042560012242144640x7ff8e20752000x7ff8df026000524288291760032671851217722576501283177225764677261772257698740717722577029010
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039523101323101341943042560012242177280x7ff8e20750800x7ff8df026040524288276171430937361617722577048189177225769874071772257736660817722577368271
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039823101323101341943042560012242220160x7ff8dfa17f000x7ff8df026080524288604161067663943617722577399281177225773666081772257778244917722577801470
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040123101323101341943042560012242260480x7ff8dfa17d800x7ff8df0260c0524288516304957825356417722577814480177225777824491772257820165017722578245039
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040423101323101341943042560012242300800x7ff8dfa17c000x7ff8df026100524288280667831442542417722578256319177225782016501772257863365017722578677618
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040723101323101341943042560012242359040x7ff8dfa17a800x7ff8df026140524288296065933158760017722578689718177225786336501772257923477117722579279543
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041023101323101341943042560012242394240x7ff8dfa179000x7ff8df026180524288281906631574978817722579298693177225792347711772257964277217722579644494
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041323101323101341943042560012242442240x7ff8dfa177800x7ff8df0261c0524288511609357302178017722579677163177225796427721772258007973317722580121602
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041623101323101341943042560012242487680x7ff8dfa176000x7ff8df026200524288322555636123637617722580133582177225800797331772258054005417722580581561
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041923101323101341943042560012242533120x7ff8e20754800x7ff8df026240524288276584230975974817722580592000177225805400541772258098901517722581030649
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004222310132310134194304256008242555520x7ff8e20753000x7ff8df026280524288237051426548774017722581041249177225809890151772258165413617722581696252
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042523101323101341943042560012242598400x7ff8e20751800x7ff8df0262c0524288271893230440100017722581715302177225816541361772258208981717722582113332
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042823101323101341943042560012242656640x7ff8e20750000x7ff8df026300524288315927635375448817722582124832177225820898171772258258949817722582633019
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043123101323101341943042560012242712320x7ff8dfa17e800x7ff8df026340524288366360441021968017722582643669177225825894981772258310389917722583145756
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004342310132310134194304256008242732160x7ff8dfa17d000x7ff8df026380524288239663126842316417722583156566177225831038991772258361238017722583653933
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004372310132310134194304256008242757120x7ff8dfa17b800x7ff8df0263c0524288238137926664058417722583664783177225836123801772258438486117722584427114
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044023101323101341943042560012242807680x7ff8dfa17a000x7ff8df026400524288268309830043669617722584446524177225843848611772258486342217722584905452
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044323101323101341943042560012242876160x7ff8dfa178800x7ff8df026440524288346703238832197217722584916442177225848634221772258542422317722585465798
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044623101323101341943042560012242942080x7ff8dfa177000x7ff8df026480524288359359340244902017722585476548177225854242231772258599158417722586009844
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004492310132310134194304256008242969600x7ff8e20755800x7ff8df0264c0524288238968626758620817722586023544177225859915841772258653270517722586578350
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004522310132310134194304256008242999680x7ff8e20754000x7ff8df026500524288239424526813241617722586589910177225865327051772258740998717722587454458
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004552310132310134194304256008243027200x7ff8e20752800x7ff8df026540524288239330726805754017722587472958177225874099871772258807110817722588112962
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045823101323101341943042560012243054720x7ff8e20751000x7ff8df026580524288259296529041918417722588123852177225880711081772258874678917722588788375
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046123101323101341943042560012243082240x7ff8dfa17f800x7ff8df0265c0524288259733329090528817722588799455177225887467891772258941895017722589462058
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004642310132310134194304256008243109760x7ff8dfa17e000x7ff8df026600524288239285426795056817722589472978177225894189501772259008823217722590112302
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004672310132310134194304256008243132160x7ff8dfa17c800x7ff8df026640524288240109126885032817722590124112177225900882321772259115687417722591201964
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004702310132310134194304256008243159680x7ff8dfa17b000x7ff8df026680524288243824227303350417722591221394177225911567561772259224395717722592292017
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047323101323101341943042560012243187200x7ff8dfa179800x7ff8df0266c0524288259405429049596817722592303977177225922439571772259336315817722593427898
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047623101323101341943042560012243214720x7ff8dfa178000x7ff8df026700524288261417229276251617722593438828177225933631581772259449388017722594560510
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004792310132310134194304256008243242240x7ff8dfa176800x7ff8df026740524288241791927081514417722594572060177225944938801772259561372217722595680832
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004822310132310134194304256008243264640x7ff8e20755000x7ff8df026780524288247067827677070417722595692572177225956137221772259756572517722597632783
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004852310132310134194304256008243292160x7ff8e20753800x7ff8df0267c0524288245705927520688017722597651523177225975657251772259948428817722599560395
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048823101323101341943042560012243319680x7ff8e20752000x7ff8df026800524288262863529437570817722599572934177225994842881772260147837217722601545335
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049123101323101341943042560012243347200x7ff8e20750800x7ff8df026840524288262167229359052817722601556454177226014783721772260346125517722603532155
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004942310132310134194304256008243374720x7ff8dfa17f000x7ff8df026880524288245904527542627617722603543885177226034612551772260539789817722605464867
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049723101323101341943042560082400x7ff8dfa17d800x7ff8df0268c0524288246928927652960817722605476176177226053978981772260900830417722609085176