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

40 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_SMEMSQ_INST_LEVEL_SMEMSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd0002144721447335544322560043241600x00x7f998ee042803670016290409432491154414214097043918140954914128941421424579317114214245909711
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]002214472144732768256001224138880x00x7f998ee23f80512941481056552814214251057535142142457931711421425118870214214251193482
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]00521447214474194304256001224143360x7f9991d713800x7f998ee23fc0655366395067164290414214251227932142142511887021421425155958314214251562255
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00821447214474194304256001624150400x7f9991d712000x7f998ee24000655366640107435473614214251598544142142515595831421425196630414214251968817
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]001121447214474194304256001624154880x7f9991d710800x7f998ee24040655366577567375012814214252002266142142519663041421425235974514214252362218
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]001421447214474194304256001224159360x7f998f711f000x7f998ee24080655366929387757806414214252395358142142523597451421425266342614214252665802
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]001721447214474194304256001224163840x7f998f711d800x7f998ee240c0655366331327085232814214252698702142142526634261421425296982614214252972236
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]002021447214474194304256001224170880x7f998f711c000x7f998ee241001310726942007771040814214253015585142142529698261421425327542714214253277950
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002321447214474194304256001624177920x7f998f711a800x7f998ee241401310726986887825120814214253310599142142532754271421425366886814214253671212
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]002621447214474194304256001624184960x7f998f7119000x7f998ee24180655366463287245972014214253702801142142536688681421425405814914214254060474
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]002921447214474194304256001624192000x7f998f7117800x7f998ee241c01310726884807718368814214254094943142142540581491421425441479014214254417166
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]003221447214474194304256001624199040x7f998f7116000x7f998ee242001310726961007802629614214254449976142142544147901421425472055014214254722900
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]003521447214474194304256001224206080x7f9991d714800x7f998ee242401310727031587875841614214254763129142142547205501421425502519114214255027574
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]003821447214474194304256001624213120x7f9991d713000x7f998ee242801310726991247820684814214255060793142142550251911421425541895214214255420916
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]004121447214474194304256001624220160x7f9991d711800x7f998ee242c0655366586907375455214214255453325142142554189521421425579447314214255796098
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]004421447214474194304256001624227200x7f9991d710000x7f998ee243001310726833267655448014214255827998142142557944731421425607143314214256073033
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]004721447214474194304256001224234240x7f998f711e800x7f998ee243401310726850707674290414214256105042142142560714331421425634599414214256347817
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]005021447214474194304256001224241280x7f998f711d000x7f998ee243801310727190248044636014214256386896142142563459941421425662247514214256624312
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]005321447214474194304256001624248320x7f998f711b800x7f998ee243c01310726978547817454414214256657381142142566224751421425698663514214256988554
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]005621447214474194304256001624255360x7f998f711a000x7f998ee24400655366342827102072814214257021623142142569866351421425735543614214257357287
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]005921447214474194304256001224262400x7f998f7118800x7f998ee244401310726937627776332014214257388616142142573554361421425763255714214257634421
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]006221447214474194304256001224269440x7f998f7117000x7f998ee244801310726893167714500814214257665870142142576325571421425791127714214257913185
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]006521447214474194304256001224276480x7f9991d715800x7f998ee244c01310726466907236977614214257952055142142579112771421425820311814214258205009
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]006821447214474194304256001624286080x7f9991d714000x7f998ee245001310726932867773408014214258237799142142582031181421425857511914214258576852
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]007121447214474194304256001624293120x7f9991d712800x7f998ee24540655366514187292966414214258609061142142585751191421425894344014214258945244
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]007421447214474194304256001224300160x7f9991d711000x7f998ee245801310726721987517676014214258976874142142589434401421425921816014214259219919
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00772144721447419430425600824309760x7f998f711f800x7f998ee245c01310726722387532269614214259252708142142592181601421425949160114214259493443
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]008021447214474194304256001224316800x7f998f711e000x7f998ee246001310726866127684597614214259531932142142594916011421425976728214214259768927
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]008321447214474194304256001624326400x7f998f711c800x7f998ee246401310726663667462468014214259800707142142597672821421426012824214214260130070
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]008621447214474194304256001224336000x7f998f711b000x7f998ee24680655366520187300862414214260162159142142601282421421426049320314214260495072
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]008921447214474194304256001224345600x7f998f7119800x7f998ee246c01310726909407747112814214260525932142142604932031421426076920414214260771067
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00922144721447419430425600824355200x7f998f7118000x7f998ee247001310726929867765736814214260802296142142607692041421426104280514214261044601
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]009521447214474194304256001224362240x7f998f7116800x7f998ee247401310727006927844326414214261083750142142610428051421426132760514214261329505
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]009821447214474194304256001224371840x7f9991d715000x7f998ee247801310726979907827222414214261360985142142613276051421426169624614214261697968
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]0010121447214474194304256001224381440x7f9991d713800x7f998ee247c0655366552467337618414214261730007142142616962461421426206232714214262064230
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]0010421447214474194304256001224391040x7f9991d712000x7f998ee248001310727008647842066414214262096420142142620623271421426234664714214262348494
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]001072144721447419430425600824403200x7f9991d710800x7f998ee248401310726870827694337614214262380494142142623466471421426262600814214262627679
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]0011021447214474194304256001224412800x7f998f711f000x7f998ee248801310727174208035857614214262667158142142626260081421426290264914214262904493
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0011321447214474194304256001224422400x7f998f711d800x7f998ee248c01310726921847743119214214262935442142142629026491421426327561014214263277325
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]0011621447214474194304256001224432000x7f998f711c000x7f998ee24900655366146666879293614214263309865142142632756101421426364105014214263642818
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]001192144721447419430425600824441600x7f998f711a800x7f998ee249401310726916267742631214214263673917142142636410501421426391497114214263916852
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]0012221447214474194304256001224453760x7f998f7119000x7f998ee249801310726967387799711214214263947972142142639149711421426419065214214264192527
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]0012521447214474194304256001224463360x7f998f7117800x7f998ee249c01310726944927780469614214264230196142142641906521421426446937214214264471121
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0012821447214474194304256001224475520x7f998f7116000x7f998ee24a001310726838927647175214214264502750142142644693721421426483113314214264832903
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]0013121447214474194304256001224485120x7f9991d714800x7f998ee24a40655366544867331850414214264864743142142648311331421426519545414214265197286
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]001342144721447419430425600824494720x7f9991d713000x7f998ee24a801310726660667456356014214265228395142142651954541421426547209414214265473970
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]0013721447214474194304256001224506880x7f9991d711800x7f998ee24ac01310726522767307631214214265506220142142654720941421426574985514214265751705
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]0014021447214474194304256001224516480x7f9991d710000x7f998ee24b001310726747367560956814214265790764142142657498551421426603177614214266033589
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0014321447214474194304256001224528640x7f998f711e800x7f998ee24b401310726955427801268814214266065208142142660317761421426641305714214266414861
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]0014621447214474194304256001224540800x7f998f711d000x7f998ee24b80655366530207310724014214266446880142142664130571421426677785714214266779534
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001492144721447419430425600824552960x7f998f711b800x7f998ee24bc01310726930907773522414214266811213142142667778571421426705609814214267057788
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]0015221447214474194304256001224567680x7f998f711a000x7f998ee24c001310726896807721177614214267090597142142670560981421426733481914214267336552
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]0015521447214474194304256001224577280x7f998f7118800x7f998ee24c401310726956787790920814214267374781142142673348191421426761193914214267613696
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015821447214474194304256001224589440x7f998f7117000x7f998ee24c801310726845207673046414214267644896142142676119391421426797418014214267975959
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]0016121447214474194304256001224601600x7f9991d715800x7f998ee24cc0655366564467354007214214268008398142142679741801421426833498114214268336722
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001642144721447419430425600824613760x7f9991d714000x7f998ee24d001310726995287839185614214268368931142142683349811421426861146214214268613156
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]0016721447214474194304256001224628480x7f9991d712800x7f998ee24d401310727023747863173614214268645565142142686114621421426890138214214268903210
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]0017021447214474194304256001224638080x7f9991d711000x7f998ee24d801310727012107855404814214268943649142142689013821421426917978314214269181554
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017321447214474194304256001224650240x7f998f711f800x7f998ee24dc01310726676827479631214214269213164142142691797831421426954314414214269544897
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]0017621447214474194304256001224662400x7f998f711e000x7f998ee24e00655366598647396224814214269576836142142695431441421426990554414214269907309
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001792144721447419430425600824674560x7f998f711c800x7f998ee24e401310726940787774065614214269939029142142699055441421427019050514214270192484
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]0018221447214474194304256001224689280x7f998f711b000x7f998ee24e801310726946687788476014214270224673142142701905051421427047898614214270480758
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]0018521447214474194304256001224701440x7f998f7119800x7f998ee24ec01310726571587366396814214270519677142142704789861421427075578614214270757652
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018821447214474194304256001224716160x7f998f7118000x7f998ee24f001310727031187873446414214270789501142142707557861421427111770714214271119565
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]0019121447214474194304256001224728320x7f998f7116800x7f998ee24f40655366579467367276014214271151534142142711177071421427148234814214271483947
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001942144721447419430425600824740480x7f9991d715000x7f998ee24f801310726671867478249614214271515676142142714823481421427176154914214271763511
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]0019721447214474194304256001224757760x7f9991d713800x7f998ee24fc01310726825407643055214214271795241142142717615491421427205194914214272053795
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]0020021447214474194304256001224769920x7f9991d712000x7f998ee250001310726933267766812014214272092975142142720519491421427232763014214272329420
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020321447214474194304256001224784640x7f9991d710800x7f998ee250401310727051447904462414214272361739142142723276301421427269227114214272694062
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]0020621447214474194304256001224799360x7f998f711f000x7f998ee25080655366604167392501614214272726332142142726922711421427305499114214273056795
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]002092144721447419430425600824814080x7f998f711d800x7f998ee250c01310726973267806991214214273087364142142730549911421427333211214214273333969
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]0021221447214474194304256001224831360x7f998f711c000x7f998ee251001310726967627806017614214273365408142142733321121421427362907314214273630843
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]0021521447214474194304256001224843520x7f998f711a800x7f998ee251401310726952747778573614214273681002142142736290731421427390891314214273910687
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021821447214474194304256001224858240x7f998f7119000x7f998ee251801310726925147769754414214273941137142142739089131421427428187414214274283660
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]0022121447214474194304256001224872960x7f998f7117800x7f998ee251c0655366570107364488814214274316129142142742818741421427465147514214274653422
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]0022421447214474194304256001224887680x7f998f7116000x7f998ee252001310727050127900064814214274684002142142746514751421427493547614214274937346
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]0022721447214474194304256001224907520x7f9991d714800x7f998ee252401310727070207916813614214274968626142142749354761421427523723614214275239120
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]0023021447214474194304256001224919680x7f9991d713000x7f998ee252801310726927107758526414214275278129142142752372361421427551835714214275520005
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023321447214474194304256001224934400x7f9991d711800x7f998ee252c01310727000727849785614214275552734142142755183571421427589419814214275896007
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0023621447214474194304256001224949120x7f9991d710000x7f998ee25300655366468767249844014214275928866142142758941981421427625515914214276256990
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0023921447214474194304256001224963840x7f998f711e800x7f998ee253401310726811087624238414214276288869142142762551591421427653371914214276535504
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0024221447214474194304256001224983680x7f998f711d000x7f998ee253801310727079667944801614214276566873142142765337191421427684380014214276845678
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0024521447214474194304256001224995840x7f998f711b800x7f998ee253c01310726882867696172014214276884457142142768438001421427712236114214277124242
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00248214472144741943042560012241013120x7f998f711a000x7f998ee254001310726852027674781614214277155241142142771223611421427748876114214277490654
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]00251214472144741943042560012241027840x7f998f7118800x7f998ee25440655366528247310948014214277524494142142774887611421427786028214214277862127
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]00254214472144741943042560012241042560x7f998f7117000x7f998ee254801310726627527422140014214277893786142142778602821421427813868314214278140751
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]00257214472144741943042560012241062400x7f9991d715800x7f998ee254c01310726722467517297614214278172791142142781386831421427845820414214278459945
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]00260214472144741943042560012241077120x7f9991d714000x7f998ee255001310726653247455728814214278499224142142784582041421427874220414214278743959
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00263214472144741943042560016241094400x7f9991d712800x7f998ee255401310726847087668583214214278775278142142787422041421427910556514214279107441
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]00266214472144741943042560016241111680x7f9991d711000x7f998ee25580655366669367466244814214279140011142142791055651421427946700614214279468854
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0026921447214474194304256008241128960x7f998f711f800x7f998ee255c01310726980107809340014214279500103142142794670061421427974556714214279747518
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]00272214472144741943042560012241151360x7f998f711e000x7f998ee256001310726892287713727214214279778368142142797455671421428006556714214280067232
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]00275214472144741943042560012241166080x7f998f711c800x7f998ee256401310727214748091219214214280105451142142800655671421428034220814214280343976
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00278214472144741943042560016241183360x7f998f711b000x7f998ee256801310726927467757176814214280374685142142803422081421428071068914214280712469
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]00281214472144741943042560016241200640x7f998f7119800x7f998ee256c0655366502587280022414214280744158142142807106891421428107949014214281081381
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]00284214472144741943042560012241217920x7f998f7118000x7f998ee257001310726808727626214414214281112500142142810794901421428135965014214281361245
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]00287214472144741943042560012241240320x7f998f7116800x7f998ee257401310726860487684579214214281393845142142813596501421428168749114214281689398
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]00290214472144741943042560012241255040x7f9991d715000x7f998ee257801310727076927923954414214281728298142142816874911421428196909214214281970803
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00293214472144741943042560012241274880x7f9991d713800x7f998ee257c01310726942227775491214214282003342142142819690921421428234173214214282343565
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]00296214472144741943042560012241292160x7f9991d712000x7f998ee25800655366616687412960014214282376024142142823417321421428271213314214282714027
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]00299214472144741943042560012241309440x7f9991d710800x7f998ee258401310726967247799492814214282745997142142827121331421428299741414214282999332
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]00302214472144741943042560012241334400x7f998f711f000x7f998ee258801310726648007435167214214283031851142142829974141421428333613514214283337825
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]00305214472144741943042560012241349120x7f998f711d800x7f998ee258c0131072103852011594321614214283377334142142833361351421428362461514214283626459
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00308214472144741943042560012241368960x7f998f711c000x7f998ee259001310726540807319498414214283657828142142836246151421428398813614214283990021
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]00311214472144741943042560012241388800x7f998f711a800x7f998ee25940655366543067326073614214284021831142142839881361421428435117714214284352974
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]00314214472144741943042560012241408640x7f998f7119000x7f998ee259801310726955507789792014214284384223142142843511771421428464157814214284643398
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]00317214472144741943042560012241436160x7f998f7117800x7f998ee259c01310726919807748743214214284674807142142846415781421428499581814214284997581
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]00320214472144741943042560012241453440x7f998f7116000x7f998ee25a00131072101595611376797614214285037200142142849958181421428527677914214285278675
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00323214472144741943042560012241475840x7f9991d714800x7f998ee25a401310726916167741552014214285310394142142852767791421428564110014214285642897
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]00326214472144741943042560012241495680x7f9991d713000x7f998ee25a80655366502047276892014214285675217142142856411001421428600622114214286008050
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]00329214472144741943042560012241515520x7f9991d711800x7f998ee25ac01310726884987715682414214286040419142142860062211421428630430114214286306104
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]00332214472144741943042560012241543040x7f9991d710000x7f998ee25b001310726653187453618414214286338263142142863043011421428667694214214286678756
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]00335214472144741943042560012241562880x7f998f711e800x7f998ee25b4013107299817411182596014214286718065142142866769421421428696350314214286965160
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00338214472144741943042560012241587840x7f998f711d000x7f998ee25b801310726960607796116814214286996920142142869635031421428733134414214287333123
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]00341214472144741943042560012241610240x7f998f711b800x7f998ee25bc0655366562007357968014214287364472142142873313441421428769838414214287700185
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]00344214472144741943042560012241632640x7f998f711a000x7f998ee25c001310726713467521363214214287732135142142876983841421428800542514214288007249
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]00347214472144741943042560012241665280x7f998f7118800x7f998ee25c401310726749307550904814214288039908142142880054251421428839630614214288442140
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]00350214472144741943042560012241685120x7f998f7117000x7f998ee25c80131072102997011529622414214288462190142142883963061421428872446714214288726254
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00353214472144741943042560012241712640x7f9991d715800x7f998ee25cc01310726896227731803214214288758424142142887244671421428909134814214289093277
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]00356214472144741943042560012241737600x7f9991d714000x7f998ee25d00655366539527321043214214289124956142142890913481421428945742814214289459189
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]00359214472144741943042560012241762560x7f9991d712800x7f998ee25d401310726640347432916014214289491769142142894574281421428978254914214289784273
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]00362214472144741943042560012241797760x7f9991d711000x7f998ee25d801310727230928100114414214289815602142142897825491421429019887014214290226853
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]00365214472144741943042560012241822720x7f998f711f800x7f998ee25dc013107299602211152118414214290248013142142901988701421429053215114214290533977
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00368214472144741943042560012241855360x7f998f711e000x7f998ee25e001310726828347642788814214290565146142142905321511421429090703214214290952959
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]00371214472144741943042560012241885440x7f998f711c800x7f998ee25e40655366590227376554414214290966218142142909070321421429131663314214291362350
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]00374214472144741943042560012241915520x7f998f711b000x7f998ee25e801310726647887445620814214291374300142142913166331421429169711314214291698863
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]00377214472144741943042560012241958400x7f998f7119800x7f998ee25ec01310726743827553851214214291731313142142916971131421429216335414214292208873
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]00380214472144741943042560012241985920x7f998f7118000x7f998ee25f00131072101778211392113614214292229002142142921633541421429252767514214292529376
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00383214472144741943042560012242023680x7f998f7116800x7f998ee25f4013107298614211038219214214292562476142142925276751421429291999614214292962617
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]00386214472144741943042560012242058880x7f9991d715000x7f998ee25f80655366558247334926414214292974077142142929199961421429334271714214293361119
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]00389214472144741943042560012242094080x7f9991d713800x7f998ee25fc01310726567647355524814214293377019142142933427171421429371743814214293719382
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]00392214472144741943042560012242144640x7f9991d712000x7f998ee260001310726633967424455214214293751291142142937174381421429423439914214294253601
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]00395214472144741943042560012242177280x7f9991d710800x7f998ee26040131072101913811418406414214294276570142142942343991421429459824014214294600054
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00398214472144741943042560012242220160x7f998f711f000x7f998ee26080131072102349411452692814214294632653142142945982401421429501088114214295053365
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]00401214472144741943042560012242260480x7f998f711d800x7f998ee260c0655366557127352840814214295066434142142950108811421429545248214214295494676
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]00404214472144741943042560012242300800x7f998f711c000x7f998ee261001310726698927509268014214295506965142142954524821421429587840314214295920347
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]00407214472144741943042560012242359040x7f998f711a800x7f998ee261401310726789687600188814214295932917142142958784031421429648384414214296526545
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]00410214472144741943042560012242394240x7f998f7119000x7f998ee26180131072102660611496248814214296545864142142964838441421429688224514214296884037
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00413214472144741943042560012242442240x7f998f7117800x7f998ee261c0131072101282211322059214214296916657142142968822451421429731808614214297360368
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]00416214472144741943042560012242487680x7f998f7116000x7f998ee26200655366588727382974414214297372457142142973180861421429778320714214297801439
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]00419214472144741943042560012242533120x7f9991d714800x7f998ee262401310726815127628767214214297818028142142977832071421429820832814214298256839
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0042221447214474194304256008242555520x7f9991d713000x7f998ee26280131072103071611569950414214298269799142142982083281421429888433014214298929006
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]00425214472144741943042560012242598400x7f9991d711800x7f998ee262c0131072102228611437365614214298949165142142988843301421429933521114214299378356
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00428214472144741943042560012242656640x7f9991d710000x7f998ee2630013107298232010998183214214299390416142142993352111421429984817214214299890096
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]00431214472144741943042560012242712320x7f998f711e800x7f998ee26340655366483367252141614214299903746142142998481721421430036017314214300402545
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0043421447214474194304256008242732160x7f998f711d000x7f998ee2638013107299233611124912814214300414705142143003601731421430087201414214300913215
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0043721447214474194304256008242757120x7f998f711b800x7f998ee263c0131072102379411468822414214300926385142143008720141421430164049614214301682359
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]00440214472144741943042560012242807680x7f998f711a000x7f998ee2640013107298610211043692814214301701639142143016404961421430211873714214302141840
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00443214472144741943042560012242876160x7f998f7118800x7f998ee26440131072101749611441740014214302154330142143021187371421430267425814214302716968
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]00446214472144741943042560012242942080x7f998f7117000x7f998ee26480655366567067364940014214302729498142143026742581421430324401914214303285356
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0044921447214474194304256008242969600x7f9991d715800x7f998ee264c013107299166011101308014214303297866142143032440191421430380658114214303847075
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0045221447214474194304256008242999680x7f9991d714000x7f998ee26500131072102572211455518414214303859685142143038065811421430467666314214304718007
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0045521447214474194304256008243027200x7f9991d712800x7f998ee26540131072102361811462720814214304737807142143046766631421430533586414214305376563
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00458214472144741943042560012243054720x7f9991d711000x7f998ee26580131072101758211401737614214305388653142143053358641421430600802614214306024360
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]00461214472144741943042560012243082240x7f998f711f800x7f998ee265c0655366511507288669614214306042450142143060080261421430665874714214306708256
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0046421447214474194304256008243109760x7f998f711e000x7f998ee26600131072102915011538291214214306720106142143066587471421430733714914214307381262
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0046721447214474194304256008243132160x7f998f711c800x7f998ee26640131072103273411582330414214307394132142143073370081421430843797014214308484410
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0047021447214474194304256008243159680x7f998f711b000x7f998ee26680131072102422411475221614214308504509142143084379701421430953461214214309575877
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00473214472144741943042560012243187200x7f998f7119800x7f998ee266c0131072102123611422904814214309589057142143095346121421431064805414214310693084
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]00476214472144741943042560012243214720x7f998f7118000x7f998ee26700655366465767246787214214310705274142143106480541421431175973614214311804202
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0047921447214474194304256008243242240x7f998f7116800x7f998ee26740131072102549211470132014214311817741142143117597361421431284837814214312893309
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0048221447214474194304256008243264640x7f9991d715000x7f998ee26780131072103001611512475214214312905809142143128483781421431477574214214314828650
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0048521447214474194304256008243292160x7f9991d713800x7f998ee267c0131072103271811545977614214314850049142143147757421421431668534614214316753011
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00488214472144741943042560012243319680x7f9991d712000x7f998ee26800131072102880611524504814214316764910142143166853461421431866199014214318735350
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]00491214472144741943042560012243347200x7f9991d710800x7f998ee26840655366537227318906414214318747980142143186619901421432064119314214320705990
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0049421447214474194304256008243374720x7f998f711f000x7f998ee26880131072102970011552132014214320717780142143206411931421432256279714214322633650
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00497214472144741943042560082400x7f998f711d800x7f998ee268c0131072101664411398025614214322646540142143225627971421432619112414214326264276