Files
rocm-systems/tests/workloads/SQ/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.kd000852531852536335544322560083264640x00x7fb7aea04180104857611152581142843150812074900885374645120749011304979711207490113081860912074901130931851
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00285253185253632768256002424124800x00x7fb7aea3510040961015191299894812074901145721305120749011460396521207490114604589212074901146055175
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0048525318525364194304256002424129280x7fb8ba5d79000x7fb7aea3514052428811529184147557234412074901146108474120749011463318101207490114646685012074901146470246
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0068525318525364194304256003624136320x7fb8ba5d78000x7fb7aea3518052428812690631162438175612074901146535317120749011467119681207490114697004712074901147041318
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0088525318525364194304256002824140800x7fb8ba5d77000x7fb7aea351c052428813643678174629361212074901147074600120749011472665261207490114752492412074901147595407
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00108525318525364194304256002424145280x7fb8ba5d76000x7fb7aea3520052428810485116134207800812074901147624782120749011478082831207490114794716212074901147950147
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00128525318525364194304256002424149760x7fb8ba5d75000x7fb7aea3524052428810173655130215880812074901148009076120749011481745211207490114831596012074901148319072
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00148525318525364194304256002424154240x7fb8ba5d74000x7fb7aea3528052428812329244157818911612074901148394052120749011485655591207490114869755812074901148700361
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00168525318525364194304256002824161280x7fb8ba5d73000x7fb7aea352c052428813128940168048168812074901148750454120749011489274771207490114918907612074901149233682
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00188525318525364194304256002824168320x7fb8ba5d7a000x7fb7aea3530052428814345550183622725212074901149261904120749011494460351207490114970283312074901149744331
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00208525318525364194304256002424175360x7fb8ba5d79000x7fb7aea3534052428812115830155082172812074901149769357120749011499612321207490115009435112074901150097517
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00228525318525364194304256002424182400x7fb8ba5d78000x7fb7aea3538052428811387820145773681612074901150147270120749011503271501207490115046315012074901150466042
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00248525318525364194304256002424189440x7fb8ba5d77000x7fb7aea353c052428812119321155127971212074901150528077120749011506964281207490115082954812074901150832413
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00268525318525364194304256002824199040x7fb8ba5d76000x7fb7aea3540052428813729653175734864412074901150880753120749011510743461207490115132906512074901151399867
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00288525318525364194304256002824206080x7fb8ba5d75000x7fb7aea3544052428813890921177805238812074901151425685120749011516103441207490115186762212074901151936575
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00308525318525364194304256002424213120x7fb8ba5d74000x7fb7aea3548052428812180856155912192012074901151962904120749011521511411207490115228410012074901152287217
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00328525318525364194304256002424220160x7fb8ba5d73000x7fb7aea354c052428811714131149933776012074901152337300120749011525023391207490115263625912074901152639391
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00348525318525364194304256002424227200x7fb8ba5d7a000x7fb7aea3550052428813003433166453213212074901152702378120749011528687371207490115299817712074901153005852
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00368525318525364194304256002824236800x7fb8ba5d79000x7fb7aea3554052428813431752171925502012074901153050876120749011532298561207490115348921412074901153558830
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00388525318525364194304256002824243840x7fb8ba5d78000x7fb7aea3558052428814253620182442409212074901153584036120749011537684131207490115402249212074901154068146
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00408525318525364194304256002424250880x7fb8ba5d77000x7fb7aea355c052428810433607133545496412074901154093103120749011542800901207490115441929012074901154422124
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00428525318525364194304256002424257920x7fb8ba5d76000x7fb7aea3560052428810503419134432168412074901154470414120749011546429691207490115478200812074901154784908
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00448525318525364194304256002424264960x7fb8ba5d75000x7fb7aea3564052428813585008173888893212074901154845811120749011550122471207490115513848612074901155141851
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00468525318525364194304256002824277120x7fb8ba5d74000x7fb7aea3568052428813805249176702960012074901155190712120749011553639251207490115562712412074901155695981
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00488525318525364194304256002824284160x7fb8ba5d73000x7fb7aea356c052428813976892178895752412074901155724284120749011559012021207490115615816112074901156230645
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00508525318525364194304256002424291200x7fb8ba5d7a000x7fb7aea3570052428812624501161596152412074901156257976120749011564376801207490115656855912074901156571618
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00528525318525364194304256002424300800x7fb8ba5d79000x7fb7aea3574052428810444904133701496012074901156619447120749011567946381207490115693367712074901156936867
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00548525318525364194304256002424307840x7fb8ba5d78000x7fb7aea3578052428812927437165473664412074901156998422120749011571717561207490115730151512074901157305222
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00568525318525364194304256002824320000x7fb8ba5d77000x7fb7aea357c052428813583119173863088012074901157353622120749011575309541207490115779479312074901157864321
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00588525318525364194304256002824329600x7fb8ba5d76000x7fb7aea3580052428813634359174516483612074901157891441120749011580747911207490115833623012074901158405687
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00608525318525364194304256002424339200x7fb8ba5d75000x7fb7aea3584052428812460218159491302012074901158435462120749011586213491207490115875222812074901158755226
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00628525318525364194304256002424348800x7fb8ba5d74000x7fb7aea3588052428810912118139666466412074901158805009120749011589719071207490115911126612074901159114725
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00648525318525364194304256002424358400x7fb8ba5d73000x7fb7aea358c052428813479259172536901212074901159179565120749011593487051207490115947654412074901159479663
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00668525318525364194304256002824373120x7fb8ba5d7a000x7fb7aea3590052428813600041174082118412074901159526840120749011597032631207490115996518212074901160035556
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00688525318525364194304256002824382720x7fb8ba5d79000x7fb7aea3594052428813997500179167724012074901160060933120749011602485401207490116050677912074901160576982
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00708525318525364194304256002424392320x7fb8ba5d78000x7fb7aea3598052428810956105140247836012074901160604423120749011607819781207490116091909712074901160922203
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00728525318525364194304256002424401920x7fb8ba5d77000x7fb7aea359c052428811256501144079126412074901160971776120749011611563761207490116129301512074901161296770
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00748525318525364194304256002424411520x7fb8ba5d76000x7fb7aea35a0052428811843612151604195212074901161358264120749011615240541207490116165669312074901161660285
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00768525318525364194304256002824426240x7fb8ba5d75000x7fb7aea35a4052428813745714175942372412074901161710939120749011618870921207490116214357112074901162197313
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00788525318525364194304256002824435840x7fb8ba5d74000x7fb7aea35a8052428814292501182939503612074901162225115120749011624064501207490116266212812074901162688566
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00808525318525364194304256002424445440x7fb8ba5d73000x7fb7aea35ac052428812180571155910062812074901162727809120749011628922071207490116302388712074901163027316
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00828525318525364194304256002424457600x7fb8ba5d7a000x7fb7aea35b005242889859554126206316012074901163078451120749011632562051207490116339748512074901163400880
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00848525318525364194304256002424467200x7fb8ba5d79000x7fb7aea35b4052428812042174154133856012074901163462915120749011636301231207490116376340312074901163766720
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00868525318525364194304256002824484480x7fb8ba5d78000x7fb7aea35b8052428813332137170655979612074901163814689120749011639862821207490116425124012074901164322432
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00888525318525364194304256002824494080x7fb8ba5d77000x7fb7aea35bc052428813570704173706266412074901164349432120749011645305991207490116479171812074901164861624
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00908525318525364194304256002424503680x7fb8ba5d76000x7fb7aea35c0052428812580601161046724812074901164887833120749011650747561207490116520579612074901165209140
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00928525318525364194304256002424515840x7fb8ba5d75000x7fb7aea35c4052428810149854129918392412074901165258141120749011654307541207490116557091412074901165574219
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00948525318525364194304256002424525440x7fb8ba5d74000x7fb7aea35c8052428813445194172099414812074901165635232120749011658013131207490116592883212074901165931953
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00968525318525364194304256002824542720x7fb8ba5d73000x7fb7aea35cc052428813500335172801958812074901165980534120749011661545911207490116642562912074901166468460
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00988525318525364194304256002824554880x7fb8ba5d7a000x7fb7aea35d0052428813600274174082122012074901166497013120749011666747481207490116693954712074901167015647
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001008525318525364194304256002424567040x7fb8ba5d79000x7fb7aea35d4052428812440235159222345212074901167043870120749011672241851207490116735506512074901167358224
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001028525318525364194304256002424581760x7fb8ba5d78000x7fb7aea35d805242889033666115630670812074901167406353120749011675713841207490116771618312074901167719325
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001048525318525364194304256002424593920x7fb8ba5d77000x7fb7aea35dc052428811748149150366059612074901167782723120749011679461021207490116808002112074901168083933
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001068525318525364194304256002824613760x7fb8ba5d76000x7fb7aea35e0052428812693721162470876412074901168136009120749011683005001207490116857041912074901168639505
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001088525318525364194304256002824625920x7fb8ba5d75000x7fb7aea35e4052428813852011177301609212074901168663780120749011688492971207490116910753612074901169179529
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001108525318525364194304256002424638080x7fb8ba5d74000x7fb7aea35e8052428812421638159007875212074901169208192120749011693860951207490116951793412074901169521204
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001128525318525364194304256002424652800x7fb8ba5d73000x7fb7aea35ec05242888532937109233929612074901169569714120749011697337731207490116987713212074901169880171
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001148525318525364194304256002424664960x7fb8ba5d7a000x7fb7aea35f0052428811795874150982026012074901169940763120749011701148911207490117024817012074901170251751
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001168525318525364194304256002824684800x7fb8ba5d79000x7fb7aea35f4052428814362465183845791212074901170300121120749011704729691207490117073712812074901170805841
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001188525318525364194304256002824696960x7fb8ba5d78000x7fb7aea35f8052428813799300176633943212074901170832591120749011710099261207490117126992512074901171341306
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001208525318525364194304256002424709120x7fb8ba5d77000x7fb7aea35fc052428811764855150589849612074901171371442120749011715531241207490117168688312074901171689904
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001228525318525364194304256002424723840x7fb8ba5d76000x7fb7aea360005242888091675103573501212074901171738594120749011719088021207490117204544112074901172049332
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001248525318525364194304256002424736000x7fb8ba5d75000x7fb7aea3604052428812325984157761469612074901172110135120749011722745601207490117240543912074901172408489
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001268525318525364194304256002824758400x7fb8ba5d74000x7fb7aea3608052428811794094150958464412074901172457891120749011726303981207490117289759712074901172967398
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001288525318525364194304256002824770560x7fb8ba5d73000x7fb7aea360c052428813551027173453883612074901172991463120749011731809561207490117343919412074901173510678
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001308525318525364194304256002424782720x7fb8ba5d7a000x7fb7aea3610052428812233070156593152812074901173538850120749011737265531207490117385823212074901173861409
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001328525318525364194304256002424800000x7fb8ba5d79000x7fb7aea36140524288750536996061412012074901173912344120749011740889511207490117423311012074901174236276
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001348525318525364194304256002424812160x7fb8ba5d78000x7fb7aea3618052428810745806137555248412074901174299664120749011744633491207490117459966812074901174602867
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001368525318525364194304256002824834560x7fb8ba5d77000x7fb7aea361c052428813516538173011457212074901174649985120749011748219071207490117508974612074901175141598
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001388525318525364194304256002824849280x7fb8ba5d76000x7fb7aea3620052428813712323175512486812074901175169801120749011753487851207490117560702312074901175657617
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001408525318525364194304256002424864000x7fb8ba5d75000x7fb7aea3624052428811207659143451152012074901175685469120749011758615821207490117599822112074901176006265
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001428525318525364194304256002424881280x7fb8ba5d74000x7fb7aea36280524288574386273515323212074901176049956120749011762239801207490117637486012074901176378156
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001448525318525364194304256002424896000x7fb8ba5d73000x7fb7aea362c052428812711182162704244012074901176459397120749011766242981207490117675373812074901176756920
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001468525318525364194304256002824920960x7fb8ba5d7a000x7fb7aea3630052428812852732164517248412074901176806122120749011769774171207490117724861512074901177302063
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001488525318525364194304256002824935680x7fb8ba5d79000x7fb7aea3634052428814194850181687635212074901177329665120749011775126141207490117776861312074901177819134
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001508525318525364194304256002424950400x7fb8ba5d78000x7fb7aea3638052428812608576161389730812074901177848308120749011780332511207490117816493112074901178168483
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001528525318525364194304256002424967680x7fb8ba5d77000x7fb7aea363c0524288476174860950528812074901178216833120749011783895691207490117854668912074901178549852
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001548525318525364194304256002424982400x7fb8ba5d76000x7fb7aea3640052428811745347150337488012074901178609373120749011787756481207490117891004712074901178913298
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015685253185253641943042560028241007360x7fb8ba5d75000x7fb7aea3644052428810212496130723231612074901178960936120749011791417261207490117941116412074901179463851
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015885253185253641943042560028241022080x7fb8ba5d74000x7fb7aea3648052428813570984173709817612074901179491763120749011796706831207490117993420212074901179957598
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016085253185253641943042560024241036800x7fb8ba5d73000x7fb7aea364c052428811623636148788587612074901180007371120749011801767601207490118031196012074901180315694
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016285253185253641943042560024241056640x7fb8ba5d7a000x7fb7aea36500524288388530649721847212074901180363933120749011805401191207490118070587812074901180708975
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016485253185253641943042560024241071360x7fb8ba5d79000x7fb7aea3654052428810495846134344772412074901180772893120749011809375571207490118107723612074901181080936
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016685253185253641943042560028241098880x7fb8ba5d78000x7fb7aea365805242889584283122672889212074901181131941120749011813063551207490118157707312074901181628383
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016885253185253641943042560028241113600x7fb8ba5d77000x7fb7aea365c052428813506754172878956412074901181655684120749011818324321207490118208827112074901182142669
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017085253185253641943042560024241128320x7fb8ba5d76000x7fb7aea3660052428810934942139962624012074901182170641120749011823495501207490118248714912074901182490475
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017285253185253641943042560024241148160x7fb8ba5d75000x7fb7aea36640524288374802647969028012074901182539677120749011827089081207490118288186712074901182885109
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017485253185253641943042560024241162880x7fb8ba5d74000x7fb7aea3668052428811454242146608358412074901182944780120749011831101861207490118324378512074901183247412
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017685253185253641943042560028241190400x7fb8ba5d73000x7fb7aea366c05242888394117107436870412074901183295822120749011834674641207490118372826312074901183754554
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017885253185253641943042560028241207680x7fb8ba5d7a000x7fb7aea3670052428814092935180380607212074901183799328120749011839639411207490118422186012074901184252640
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018085253185253641943042560024241224960x7fb8ba5d79000x7fb7aea367405242889774103125118427612074901184297564120749011844661791207490118460761812074901184611337
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018285253185253641943042560024241247360x7fb8ba5d78000x7fb7aea36780524288366677946930910412074901184659376120749011848311371207490118501321612074901185016470
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018485253185253641943042560024241264640x7fb8ba5d77000x7fb7aea367c052428810691222136850300012074901185077503120749011852407351207490118538009412074901185383351
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018685253185253641943042560020241279360x7fb8ba5d76000x7fb7aea36800524288429360354948838012074901185431250120749011855999331207490118586585212074901185892307
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018885253185253641943042560028241296640x7fb8ba5d75000x7fb7aea3684052428814072512180127891212074901185940567120749011861085711207490118635688912074901186383660
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019085253185253641943042560024241313920x7fb8ba5d74000x7fb7aea3688052428811505896147262434012074901186432611120749011865975281207490118673336812074901186736606
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019285253185253641943042560024241336320x7fb8ba5d73000x7fb7aea368c0524288353346645225370412074901186783664120749011869549661207490118714648612074901187177846
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019485253185253641943042560024241353600x7fb8ba5d7a000x7fb7aea3690052428810279989131595884412074901187234712120749011874031241207490118754168412074901187545039
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019685253185253641943042560020241368320x7fb8ba5d79000x7fb7aea36940524288288097536885544012074901187593308120749011877693621207490118805240112074901188080203
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019885253185253641943042560028241385600x7fb8ba5d78000x7fb7aea3698052428813512065172960836812074901188123363120749011882885601207490118854759812074901188573129
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020085253185253641943042560024241402880x7fb8ba5d77000x7fb7aea369c052428811761857150553790412074901188615708120749011887781571207490118891191712074901188915305
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020285253185253641943042560024241427840x7fb8ba5d76000x7fb7aea36a00524288344665344110809212074901188961851120749011891528751207490118936295412074901189393734
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020485253185253641943042560024241447680x7fb8ba5d75000x7fb7aea36a4052428810110971129411795612074901189449718120749011896168731207490118975847212074901189761928
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020685253185253641943042560020241457280x7fb8ba5d74000x7fb7aea36a80524288256277132794406812074901189810599120749011899835911207490119029063012074901190318483
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020885253185253641943042560028241477120x7fb8ba5d73000x7fb7aea36ac052428813761977176149104012074901190358307120749011905223091207490119077990712074901190801941
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021085253185253641943042560024241496960x7fb8ba5d7a000x7fb7aea36b0052428810372222132762767212074901190848608120749011910119061207490119115110512074901191154697
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021285253185253641943042560024241521920x7fb8ba5d79000x7fb7aea36b40524288339224543426698412074901191206703120749011913731841207490119160070312074901191626974
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021485253185253641943042560024241541760x7fb8ba5d78000x7fb7aea36b8052428810445981133700153612074901191682608120749011918450221207490119198358112074901191986783
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021685253185253641943042560020241556480x7fb8ba5d77000x7fb7aea36bc0524288245647331445876012074901192034091120749011922115801207490119254037812074901192567021
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021885253185253641943042560028241576320x7fb8ba5d76000x7fb7aea36c0052428812079103154617696412074901192610452120749011927725371207490119303973612074901193068293
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022085253185253641943042560024241596160x7fb8ba5d75000x7fb7aea36c4052428810553917135089953612074901193110621120749011932755751207490119341157412074901193415237
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022285253185253641943042560024241623680x7fb8ba5d74000x7fb7aea36c80524288327797341939406812074901193462385120749011936367391207490119388121912074901193911379
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022485253185253641943042560024241646080x7fb8ba5d73000x7fb7aea36cc052428810581741135441916012074901193967744120749011941429771207490119427993612074901194282409
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022685253185253641943042560020241663360x7fb8ba5d7a000x7fb7aea36d00524288238193330498141212074901194330709120749011945144951207490119489001412074901194912219
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022885253185253641943042560028241685760x7fb8ba5d79000x7fb7aea36d4052428811645049149059468412074901194954859120749011951234531207490119539289212074901195420965
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023085253185253641943042560024241708160x7fb8ba5d78000x7fb7aea36d805242889274928118726009612074901195462272120749011956266511207490119576809112074901195770304
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023285253185253641943042560024241740800x7fb8ba5d77000x7fb7aea36dc0524288327184241886078012074901195818824120749011959951301207490119627544912074901196304507
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023485253185253641943042560024241765760x7fb8ba5d76000x7fb7aea36e005242888088581103550962412074901196358627120749011965248881207490119666072812074901196663173
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023685253185253641943042560020241777920x7fb8ba5d75000x7fb7aea36e40524288235800630174430012074901196714649120749011968783271207490119730216512074901197331756
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023885253185253641943042560028241802880x7fb8ba5d74000x7fb7aea36e8052428811656384149200643612074901197373483120749011975434451207490119781464412074901197838908
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024085253185253641943042560024241827840x7fb8ba5d73000x7fb7aea36ec05242888263355105753910412074901197886286120749011980748031207490119821368212074901198216280
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024285253185253641943042560024241863040x7fb8ba5d7a000x7fb7aea36f00524288325776441705834812074901198262626120749011984506411207490119876664012074901198792440
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024485253185253641943042560024241893120x7fb8ba5d79000x7fb7aea36f40524288394025550424237612074901198845208120749011990133591207490119916711912074901199169992
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024685253185253641943042560020241907840x7fb8ba5d78000x7fb7aea36f80524288231230029586082812074901199222169120749011993871181207490119992215612074901199947066
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024885253185253641943042560028241937920x7fb8ba5d77000x7fb7aea36fc05242888434994107970960012074901199989655120749012001583151207490120045815412074901200484435
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025085253185253641943042560024241968000x7fb8ba5d76000x7fb7aea37000524288324412441520924412074901200527625120749012006946331207490120084887312074901200851196
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025285253185253641943042560024242010880x7fb8ba5d75000x7fb7aea37040524288339035343393815612074901200898364120749012010911121207490120150119012074901201528134
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025485253185253641943042560024242046080x7fb8ba5d74000x7fb7aea37080524288321320941124564012074901201585010120749012017512701207490120192678912074901201928929
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025685253185253641943042560020242060800x7fb8ba5d73000x7fb7aea370c0524288235115630085951612074901201979353120749012021503081207490120276054612074901202789618
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025885253185253641943042560028242096000x7fb8ba5d7a000x7fb7aea37100524288486505562264021212074901202829693120749012029928651207490120332166412074901203351172
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026085253185253641943042560024242131200x7fb8ba5d79000x7fb7aea37140524288307337639321511612074901203388111120749012035551031207490120373318212074901203735326
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026285253185253641943042560024242181760x7fb8ba5d78000x7fb7aea37180524288348031144544949212074901203782644120749012039575021207490120441382012074901204440717
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026485253185253641943042560024242222080x7fb8ba5d77000x7fb7aea371c0524288314919040303783212074901204501289120749012046706191207490120487077812074901204895342
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026685253185253641943042560020242239360x7fb8ba5d76000x7fb7aea37200524288229324729359213212074901204942930120749012051091781207490120581237512074901205842061
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026885253185253641943042560028242279680x7fb8ba5d75000x7fb7aea37240524288364800146690298012074901205884300120749012060544541207490120642741312074901206477983
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027085253185253641943042560024242320000x7fb8ba5d74000x7fb7aea37280524288334606042841636412074901206506476120749012066878921207490120689061112074901206938779
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027285253185253641943042560024242378240x7fb8ba5d73000x7fb7aea372c0524288440727156404875212074901206965298120749012071515701207490120767828812074901207729198
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027485253185253641943042560024242423680x7fb8ba5d7a000x7fb7aea37300524288322465941262445212074901207766838120749012079315681207490120815556712074901208204431
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027685253185253641943042560020242435840x7fb8ba5d79000x7fb7aea37340524288228809629278870812074901208230710120749012084144461207490120921380312074901209268258
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027885253185253641943042560028242481280x7fb8ba5d78000x7fb7aea37380524288355554545502042012074901209296741120749012094810021207490120990084012074901209950606
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028085253185253641943042560024242526720x7fb8ba5d77000x7fb7aea373c0524288331225442390207612074901209976244120749012101698001207490121039683912074901210449904
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028285253185253641943042560024242592640x7fb8ba5d76000x7fb7aea37400524288461287159051225212074901210474710120749012106560381207490121125363612074901211304111
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028485253185253641943042560024242648320x7fb8ba5d75000x7fb7aea37440524288334927842859578412074901211344086120749012115107551207490121178131412074901211829798
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028685253185253641943042560020242663040x7fb8ba5d74000x7fb7aea37480524288230705429543961612074901211853202120749012120491531207490121303426912074901213105329
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028885253185253641943042560028242718720x7fb8ba5d73000x7fb7aea374c0524288329393042168333612074901213137418120749012133211481207490121385314612074901213919141
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029085253185253641943042560024242774400x7fb8ba5d7a000x7fb7aea37500524288341376943695766012074901213945781120749012141363451207490121440882412074901214478601
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029285253185253641943042560012242799360x7fb8ba5d79000x7fb7aea37540524288220712728254890812074901214505962120749012146857831207490121542450112074901215493687
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029485253185253641943042560024242865280x7fb8ba5d78000x7fb7aea37580524288336022343016974012074901215535074120749012157041801207490121602273912074901216091819
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029685253185253641943042560020242880000x7fb8ba5d77000x7fb7aea375c0524288229020729306766412074901216123648120749012163048181207490121747473312074901217544679
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029885253185253641943042560032242945920x7fb8ba5d76000x7fb7aea37600524288331371442416570412074901217577329120749012177518531207490121836177012074901218431006
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030085253185253641943042560024243011840x7fb8ba5d75000x7fb7aea37640524288335760342970233612074901218459078120749012186452891207490121896512812074901219035279
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030285253185253641943042560012243049600x7fb8ba5d74000x7fb7aea37680524288220983528272134012074901219068100120749012192547271207490122013312412074901220202117
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030485253185253641943042560024243136000x7fb8ba5d73000x7fb7aea376c0524288331954642502147612074901220243073120749012204094431207490122081952212074901220888252
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030685253185253641943042560020243148160x7fb8ba5d7a000x7fb7aea37700524288230119529468355212074901220920593120749012211208001207490122266911512074901222741256
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030885253185253641943042560020243175680x7fb8ba5d79000x7fb7aea37740524288228807529285648812074901222774007120749012229588741207490122375423112074901223825601
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031085253185253641943042560012243203200x7fb8ba5d78000x7fb7aea37780524288217762727864404012074901223850157120749012240401501207490122445454912074901224524670
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031285253185253641943042560012243240960x7fb8ba5d77000x7fb7aea377c0524288229117429346364412074901224551981120749012247315081207490122588958312074901225961050
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031485253185253641943042560012243288960x7fb8ba5d76000x7fb7aea37800524288223882028654922412074901226007656120749012261747021207490122696046012074901227032220
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031685253185253641943042560020243301120x7fb8ba5d75000x7fb7aea37840524288273841935060372812074901227065853120749012272423791207490123029324812074901230363751
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031885253185253641943042560020243328640x7fb8ba5d74000x7fb7aea37880524288232673029788436012074901230396472120749012305769271207490123211964112074901232189514
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032085253185253641943042560012243356160x7fb8ba5d73000x7fb7aea378c0524288221934428391379612074901232223477120749012324098801207490123319963712074901233270052
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032285253185253641943042560012243393920x7fb8ba5d7a000x7fb7aea37900524288257982833030730412074901233301511120749012334889161207490123577098812074901235841210
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032485253185253641943042560012243441920x7fb8ba5d79000x7fb7aea37940524288235181330095194012074901235889150120749012360777071207490123761258212074901237684215
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032685253185253641943042560020243454080x7fb8ba5d78000x7fb7aea37980524288285170136514436412074901237715263120749012378988211207490124395079912074901244025881
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032885253185253641943042560020243481600x7fb8ba5d77000x7fb7aea379c0524288321431841124318412074901244054704120749012442373581207490124727894712074901247352282
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033085253185253641943042560012243509120x7fb8ba5d76000x7fb7aea37a00524288243485831154728012074901247381887120749012475685461207490124910790112074901249178065
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332852531852536419430425600122400x7fb8ba5d75000x7fb7aea37a40524288256708932861688012074901249211648120749012493877401207490125391492412074901253984828