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

38 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_LDSSQ_INST_LEVEL_LDSSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000231235231235335544322560043241600x00x7fa30bc0428000017723322357090177226090080581772346956978617723469683016
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00223123523123532768256001224138880x00x7fa30bc23f8000017723474867387177234695697861772347499635617723475001123
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0052312352312354194304256001224143360x7fa3325bd3800x7fa30bc23fc000017723475036342177234749963561772347536819717723475370774
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0082312352312354194304256001624150400x7fa3325bd2000x7fa30bc2400000017723475407493177234753681971772347577587817723475778044
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00112312352312354194304256001624154880x7fa3325bd0800x7fa30bc2404000017723475810163177234757758781772347617155917723476173814
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00142312352312354194304256001224159360x7fa330143f000x7fa30bc2408000017723476207393177234761715591772347647619917723476478446
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00172312352312354194304256001224163840x7fa330143d800x7fa30bc240c000017723476511006177234764761991772347678004017723476782239
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00202312352312354194304256001224170880x7fa330143c000x7fa30bc2410000017723476825498177234767800401772347708276017723477084991
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00232312352312354194304256001624177920x7fa330143a800x7fa30bc2414000017723477117380177234770827601772347747604117723477478451
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00262312352312354194304256001624184960x7fa3301439000x7fa30bc2418000017723477509481177234774760411772347786612217723477868322
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00292312352312354194304256001624192000x7fa3301437800x7fa30bc241c000017723477899311177234778661221772347819316317723478195453
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00322312352312354194304256001624199040x7fa3301436000x7fa30bc2420000017723478228143177234781931631772347850708317723478509176
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00352312352312354194304256001224206080x7fa3325bd4800x7fa30bc2424000017723478548905177234785070831772347881028417723478812598
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00382312352312354194304256001624213120x7fa3325bd3000x7fa30bc2428000017723478845807177234788102841772347921924517723479220748
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00412312352312354194304256001624220160x7fa3325bd1800x7fa30bc242c000017723479252647177234792192451772347958580517723479587518
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00442312352312354194304256001624227200x7fa3325bd0000x7fa30bc2430000017723479618918177234795858051772347986324617723479864801
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00472312352312354194304256001224234240x7fa330143e800x7fa30bc2434000017723479896111177234798632461772348014100717723480142644
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00502312352312354194304256001224241280x7fa330143d000x7fa30bc2438000017723480181553177234801410071772348041748717723480419127
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00532312352312354194304256001624248320x7fa330143b800x7fa30bc243c000017723480451757177234804174871772348078036817723480781928
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00562312352312354194304256001624255360x7fa330143a000x7fa30bc2440000017723480812718177234807803681772348114484917723481146319
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00592312352312354194304256001224262400x7fa3301438800x7fa30bc2444000017723481176988177234811448491772348142804917723481429812
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00622312352312354194304256001224269440x7fa3301437000x7fa30bc2448000017723481460871177234814280491772348170549017723481707055
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00652312352312354194304256001224276480x7fa3325bd5800x7fa30bc244c000017723481745974177234817054901772348198213017723481983828
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00682312352312354194304256001624286080x7fa3325bd4000x7fa30bc2450000017723482014977177234819821301772348235461117723482356409
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00712312352312354194304256001624293120x7fa3325bd2800x7fa30bc2454000017723482388088177234823546111772348272517217723482726969
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00742312352312354194304256001224300160x7fa3325bd1000x7fa30bc2458000017723482758599177234827251721772348300341217723483005032
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077231235231235419430425600824309760x7fa330143f800x7fa30bc245c000017723483036082177234830034121772348328005317723483281576
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00802312352312354194304256001224316800x7fa330143e000x7fa30bc2460000017723483319545177234832800531772348355717317723483558869
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00832312352312354194304256001624326400x7fa330143c800x7fa30bc2464000017723483589958177234835571731772348392053417723483922120
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00862312352312354194304256001224336000x7fa330143b000x7fa30bc2468000017723483953719177234839205341772348428453517723484286200
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00892312352312354194304256001224345600x7fa3301439800x7fa30bc246c000017723484318270177234842845351772348456629517723484567923
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092231235231235419430425600824355200x7fa3301438000x7fa30bc2470000017723484599153177234845662951772348484437617723484845936
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00952312352312354194304256001224362240x7fa3301436800x7fa30bc2474000017723484883755177234848443761772348512709717723485128699
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00982312352312354194304256001224371840x7fa3325bd5000x7fa30bc2478000017723485159699177234851270971772348549285717723485494470
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001012312352312354194304256001224381440x7fa3325bd3800x7fa30bc247c000017723485526729177234854928571772348585861817723485860251
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001042312352312354194304256001224391040x7fa3325bd2000x7fa30bc2480000017723485891680177234858586181772348613253917723486134314
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107231235231235419430425600824403200x7fa3325bd0800x7fa30bc2484000017723486166723177234861325391772348641349917723486415147
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001102312352312354194304256001224412800x7fa330143f000x7fa30bc2488000017723486453816177234864134991772348669158017723486693160
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001132312352312354194304256001224422400x7fa330143d800x7fa30bc248c000017723486724059177234866915801772348705702017723487058561
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001162312352312354194304256001224432000x7fa330143c000x7fa30bc2490000017723487090280177234870570201772348743446117723487436231
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119231235231235419430425600824441600x7fa330143a800x7fa30bc2494000017723487467301177234874344611772348771478217723487716364
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001222312352312354194304256001224453760x7fa3301439000x7fa30bc2498000017723487748204177234877147821772348799270217723487994297
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001252312352312354194304256001224463360x7fa3301437800x7fa30bc249c000017723488032306177234879927021772348826822317723488269820
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001282312352312354194304256001224475520x7fa3301436000x7fa30bc24a0000017723488300800177234882682231772348863382417723488635541
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001312312352312354194304256001224485120x7fa3325bd4800x7fa30bc24a4000017723488667260177234886338241772348899878417723489000372
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134231235231235419430425600824494720x7fa3325bd3000x7fa30bc24a8000017723489031461177234889987841772348927686517723489278485
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001372312352312354194304256001224506880x7fa3325bd1800x7fa30bc24ac000017723489310664177234892768651772348955286517723489554548
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001402312352312354194304256001224516480x7fa3325bd0000x7fa30bc24b0000017723489593327177234895528651772348983126617723489832831
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001432312352312354194304256001224528640x7fa330143e800x7fa30bc24b4000017723489863550177234898312661772349019750717723490199202
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001462312352312354194304256001224540800x7fa330143d000x7fa30bc24b8000017723490231021177234901975071772349057142717723490573113
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149231235231235419430425600824552960x7fa330143b800x7fa30bc24bc000017723490604152177234905714271772349085542817723490856985
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001522312352312354194304256001224567680x7fa330143a000x7fa30bc24c0000017723490888775177234908554281772349113334917723491135068
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001552312352312354194304256001224577280x7fa3301438800x7fa30bc24c4000017723491173448177234911333491772349141350917723491415061
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001582312352312354194304256001224589440x7fa3301437000x7fa30bc24c8000017723491445501177234914135091772349177687017723491778422
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001612312352312354194304256001224601600x7fa3325bd5800x7fa30bc24cc000017723491809652177234917768701772349214599117723492147683
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164231235231235419430425600824613760x7fa3325bd4000x7fa30bc24d0000017723492179482177234921459911772349242343117723492424956
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001672312352312354194304256001224628480x7fa3325bd2800x7fa30bc24d4000017723492455985177234924234311772349270663217723492708079
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001702312352312354194304256001224638080x7fa3325bd1000x7fa30bc24d8000017723492746368177234927066321772349298519217723492986772
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001732312352312354194304256001224650240x7fa330143f800x7fa30bc24dc000017723493018541177234929851921772349335495317723493356433
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001762312352312354194304256001224662400x7fa330143e000x7fa30bc24e0000017723493387642177234933549531772349371799417723493719444
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179231235231235419430425600824674560x7fa330143c800x7fa30bc24e4000017723493751023177234937179941772349400007417723494001727
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001822312352312354194304256001224689280x7fa330143b000x7fa30bc24e8000017723494033066177234940000741772349430439517723494305929
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001852312352312354194304256001224701440x7fa3301439800x7fa30bc24ec000017723494345288177234943043951772349458311617723494584752
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001882312352312354194304256001224716160x7fa3301438000x7fa30bc24f0000017723494615551177234945831161772349494759617723494949113
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001912312352312354194304256001224728320x7fa3301436800x7fa30bc24f4000017723494980792177234949475961772349530983717723495311374
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194231235231235419430425600824740480x7fa3325bd5000x7fa30bc24f8000017723495342033177234953098371772349558663817723495588277
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001972312352312354194304256001224757760x7fa3325bd3800x7fa30bc24fc000017723495619406177234955866381772349587735817723495878910
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002002312352312354194304256001224769920x7fa3325bd2000x7fa30bc2500000017723495917429177234958773581772349616487917723496166573
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002032312352312354194304256001224784640x7fa3325bd0800x7fa30bc2504000017723496198942177234961648791772349653559917723496537213
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002062312352312354194304256001224799360x7fa330143f000x7fa30bc2508000017723496569423177234965355991772349690136017723496903094
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209231235231235419430425600824814080x7fa330143d800x7fa30bc250c000017723496934053177234969013601772349718120117723497182877
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002122312352312354194304256001224831360x7fa330143c000x7fa30bc2510000017723497213446177234971812011772349747784117723497479350
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002152312352312354194304256001224843520x7fa330143a800x7fa30bc2514000017723497529899177234974778411772349775688217723497758793
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002182312352312354194304256001224858240x7fa3301439000x7fa30bc2518000017723497789842177234977568821772349812984317723498131783
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002212312352312354194304256001224872960x7fa3301437800x7fa30bc251c000017723498163333177234981298431772349849896317723498500484
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002242312352312354194304256001224887680x7fa3301436000x7fa30bc2520000017723498532183177234984989631772349877912417723498780677
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002272312352312354194304256001224907520x7fa3325bd4800x7fa30bc2524000017723498811806177234987791241772349908264517723499084139
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002302312352312354194304256001224919680x7fa3325bd3000x7fa30bc2528000017723499123338177234990826451772349936840517723499369982
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002332312352312354194304256001224934400x7fa3325bd1800x7fa30bc252c000017723499401771177234993684051772349973560617723499737263
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002362312352312354194304256001224949120x7fa3325bd0000x7fa30bc2530000017723499768102177234997356061772350009928717723500100794
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002392312352312354194304256001224963840x7fa330143e800x7fa30bc2534000017723500132313177235000992871772350037960717723500381167
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002422312352312354194304256001224983680x7fa330143d000x7fa30bc2538000017723500412226177235003796071772350069320817723500694659
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002452312352312354194304256001224995840x7fa330143b800x7fa30bc253c000017723500733328177235006932081772350097512817723500976692
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024823123523123541943042560012241013120x7fa330143a000x7fa30bc2540000017723501007901177235009751281772350133976917723501341483
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025123123523123541943042560012241027840x7fa3301438800x7fa30bc2544000017723501372432177235013397691772350170265017723501704204
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025423123523123541943042560012241042560x7fa3301437000x7fa30bc2548000017723501736183177235017026501772350198121017723501982856
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025723123523123541943042560012241062400x7fa3325bd5800x7fa30bc254c000017723502014076177235019812101772350230361117723502305498
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026023123523123541943042560012241077120x7fa3325bd4000x7fa30bc2550000017723502344357177235023036111772350259081217723502592391
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026323123523123541943042560016241094400x7fa3325bd2800x7fa30bc2554000017723502623440177235025908121772350295321217723502954782
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026623123523123541943042560016241111680x7fa3325bd1000x7fa30bc2558000017723502986561177235029532121772350331545317723503317063
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002692312352312354194304256008241128960x7fa330143f800x7fa30bc255c000017723503347782177235033154531772350359353417723503595156
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027223123523123541943042560012241151360x7fa330143e000x7fa30bc2560000017723503626505177235035935341772350391817417723503919668
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027523123523123541943042560012241166080x7fa330143c800x7fa30bc2564000017723503958067177235039181741772350420729517723504208931
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027823123523123541943042560016241183360x7fa330143b000x7fa30bc2568000017723504240080177235042072951772350457241617723504573992
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028123123523123541943042560016241200640x7fa3301439800x7fa30bc256c000017723504605271177235045724161772350493513617723504936663
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028423123523123541943042560012241217920x7fa3301438000x7fa30bc2570000017723504968222177235049351361772350521353717723505215096
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028723123523123541943042560012241240320x7fa3301436800x7fa30bc2574000017723505246665177235052135371772350554585817723505547467
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029023123523123541943042560012241255040x7fa3325bd5000x7fa30bc2578000017723505586476177235055458581772350582505817723505826690
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029323123523123541943042560012241274880x7fa3325bd3800x7fa30bc257c000017723505858300177235058250581772350619017917723506192021
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029623123523123541943042560012241292160x7fa3325bd2000x7fa30bc2580000017723506224700177235061901791772350655866017723506560152
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029923123523123541943042560012241309440x7fa3325bd0800x7fa30bc2584000017723506590691177235065586601772350684170017723506843275
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030223123523123541943042560012241334400x7fa330143f000x7fa30bc2588000017723506875984177235068417001772350717898117723507180666
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030523123523123541943042560012241349120x7fa330143d800x7fa30bc258c000017723507219726177235071789811772350745706117723507458620
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030823123523123541943042560012241368960x7fa330143c000x7fa30bc2590000017723507488699177235074570611772350782026217723507821920
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031123123523123541943042560012241388800x7fa330143a800x7fa30bc2594000017723507853190177235078202621772350818362317723508185201
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031423123523123541943042560012241408640x7fa3301439000x7fa30bc2598000017723508216001177235081836231772350847418317723508475804
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031723123523123541943042560012241436160x7fa3301437800x7fa30bc259c000017723508506823177235084741831772350883210417723508833745
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032023123523123541943042560012241453440x7fa3301436000x7fa30bc25a0000017723508872394177235088321041772350911258517723509114198
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032323123523123541943042560012241475840x7fa3325bd4800x7fa30bc25a4000017723509145087177235091125851772350947562517723509477169
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032623123523123541943042560012241495680x7fa3325bd3000x7fa30bc25a8000017723509508978177235094756251772350983898617723509840620
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032923123523123541943042560012241515520x7fa3325bd1800x7fa30bc25ac000017723509871879177235098389861772351013258717723510134343
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033223123523123541943042560012241543040x7fa3325bd0000x7fa30bc25b0000017723510165782177235101325871772351050090717723510502483
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033523123523123541943042560012241562880x7fa330143e800x7fa30bc25b4000017723510541872177235105009071772351078794817723510789506
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033823123523123541943042560012241587840x7fa330143d000x7fa30bc25b8000017723510820035177235107879481772351115770917723511159337
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034123123523123541943042560012241610240x7fa330143b800x7fa30bc25bc000017723511190916177235111577091772351152075017723511522438
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034423123523123541943042560012241632640x7fa330143a000x7fa30bc25c0000017723511552477177235115207501772351183483017723511836510
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034723123523123541943042560012241665280x7fa3301438800x7fa30bc25c4000017723511867659177235118348301772351222491117723512247579
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035023123523123541943042560012241685120x7fa3301437000x7fa30bc25c8000017723512267349177235122249111772351252907217723512530752
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035323123523123541943042560012241712640x7fa3325bd5800x7fa30bc25cc000017723512561471177235125290721772351289403217723512895773
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035623123523123541943042560012241737600x7fa3325bd4000x7fa30bc25d0000017723512927052177235128940321772351326011317723513261764
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035923123523123541943042560012241762560x7fa3325bd2800x7fa30bc25d4000017723513292603177235132601131772351357883417723513580416
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036223123523123541943042560012241797760x7fa3325bd1000x7fa30bc25d8000017723513612445177235135788341772351399675417723514014885
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036523123523123541943042560012241822720x7fa330143f800x7fa30bc25dc000017723514037094177235139967541772351432763517723514329327
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036823123523123541943042560012241855360x7fa330143e000x7fa30bc25e0000017723514360666177235143276351772351471259617723514737427
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037123123523123541943042560012241885440x7fa330143c800x7fa30bc25e4000017723514749167177235147125961772351510491717723515128257
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037423123523123541943042560012241915520x7fa330143b000x7fa30bc25e8000017723515139607177235151049171772351546923717723515470928
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037723123523123541943042560012241958400x7fa3301439800x7fa30bc25ec000017723515502548177235154692371772351593915817723515960216
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038023123523123541943042560012241985920x7fa3301438000x7fa30bc25f0000017723515979016177235159391581772351628443917723516285988
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038323123523123541943042560012242023680x7fa3301436800x7fa30bc25f4000017723516317097177235162844391772351667788017723516694728
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038623123523123541943042560012242058880x7fa3325bd5000x7fa30bc25f8000017723516712227177235166778801772351707452117723517092738
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038923123523123541943042560012242094080x7fa3325bd3800x7fa30bc25fc000017723517108048177235170745211772351745372117723517455489
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039223123523123541943042560012242144640x7fa3325bd2000x7fa30bc2600000017723517487638177235174537211772351797388217723517992095
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039523123523123541943042560012242177280x7fa3325bd0800x7fa30bc2604000017723518015095177235179738821772351833868317723518340267
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039823123523123541943042560012242220160x7fa330143f000x7fa30bc2608000017723518372916177235183386831772351875484417723518776096
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040123123523123541943042560012242260480x7fa330143d800x7fa30bc260c000017723518786935177235187548441772351918892517723519210225
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040423123523123541943042560012242300800x7fa330143c000x7fa30bc2610000017723519221924177235191889251772351959676617723519614555
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040723123523123541943042560012242359040x7fa330143a800x7fa30bc2614000017723519629874177235195967661772352017372717723520191360
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041023123523123541943042560012242394240x7fa3301439000x7fa30bc2618000017723520214019177235201737271772352054956817723520551121
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041323123523123541943042560012242442240x7fa3301437800x7fa30bc261c000017723520581930177235205495681772352099356917723521010489
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041623123523123541943042560012242487680x7fa3301436000x7fa30bc2620000017723521027159177235209935691772352142892917723521447398
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041923123523123541943042560012242533120x7fa3325bd4800x7fa30bc2624000017723521462288177235214289291772352185709017723521874308
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004222312352312354194304256008242555520x7fa3325bd3000x7fa30bc2628000017723521890497177235218570901772352249805217723522520681
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042523123523123541943042560012242598400x7fa3325bd1800x7fa30bc262c000017723522540151177235224980521772352292317217723522946671
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042823123523123541943042560012242656640x7fa3325bd0000x7fa30bc2630000017723522958331177235229231721772352341821317723523438889
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043123123523123541943042560012242712320x7fa330143e800x7fa30bc2634000017723523450448177235234182131772352391357417723523930656
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004342312352312354194304256008242732160x7fa330143d000x7fa30bc2638000017723523946096177235239135741772352440173517723524420524
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004372312352312354194304256008242757120x7fa330143b800x7fa30bc263c000017723524435424177235244017351772352514893717723525166405
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044023123523123541943042560012242807680x7fa330143a000x7fa30bc2640000017723525190375177235251489371772352560861817723525624834
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044323123523123541943042560012242876160x7fa3301438800x7fa30bc2644000017723525641693177235256086181772352614717917723526171700
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044623123523123541943042560012242942080x7fa3301437000x7fa30bc2648000017723526183740177235261471791772352669822017723526716207
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004492312352312354194304256008242969600x7fa3325bd5800x7fa30bc264c000017723526730686177235266982201772352723662117723527253733
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004522312352312354194304256008242999680x7fa3325bd4000x7fa30bc2650000017723527270013177235272366211772352808318317723528100402
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004552312352312354194304256008243027200x7fa3325bd2800x7fa30bc2654000017723528124241177235280831831772352871822417723528735396
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045823123523123541943042560012243054720x7fa3325bd1000x7fa30bc2658000017723528751216177235287182241772352937038517723529387690
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046123123523123541943042560012243082240x7fa330143f800x7fa30bc265c000017723529403549177235293703851772353002542717723530042183
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004642312352312354194304256008243109760x7fa330143e000x7fa30bc2660000017723530058163177235300254271772353066686817723530687707
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004672312352312354194304256008243132160x7fa330143c800x7fa30bc2664000017723530699667177235306668681772353172719017723531745660
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004702312352312354194304256008243159680x7fa330143b000x7fa30bc2668000017723531767190177235317270911772353278581317723532834153
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047323123523123541943042560012243187200x7fa3301439800x7fa30bc266c000017723532845733177235327858131772353391045417723533975274
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047623123523123541943042560012243214720x7fa3301438000x7fa30bc2670000017723533987714177235339104541772353504901717723535116886
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004792312352312354194304256008243242240x7fa3301436800x7fa30bc2674000017723535129265177235350490171772353616789917723536233958
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004822312352312354194304256008243264640x7fa3325bd5000x7fa30bc2678000017723536245908177235361678991772353811910217723538189509
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004852312352312354194304256008243292160x7fa3325bd3800x7fa30bc267c000017723538209718177235381191021772354004646617723540119101
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048823123523123541943042560012243319680x7fa3325bd2000x7fa30bc2680000017723540130700177235400464661772354204390917723542124041
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049123123523123541943042560012243347200x7fa3325bd0800x7fa30bc2684000017723542136650177235420439091772354403207317723544101401
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004942312352312354194304256008243374720x7fa330143f000x7fa30bc2688000017723544113960177235440320731772354596903617723546036092
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049723123523123541943042560082400x7fa330143d800x7fa30bc268c000017723546048142177235459690361772354959576317723549672401