Files
rocm-systems/tests/workloads/invdev/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.kd000238351238351335544322560043241600x00x7ff888c0428000017852547584485178518380275681785269116401117852691281181
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00223835123835132768256001224138880x00x7ff888c23f8000017852696444493178526911640111785269657233517852696576630
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0052383512383514194304256001224143360x7ff88bbf23800x7ff888c23fc000017852696612159178526965723351785269693633617852696938901
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0082383512383514194304256001624150400x7ff88bbf22000x7ff888c2400000017852696975310178526969363361785269733969617852697341881
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00112383512383514194304256001624154880x7ff88bbf20800x7ff888c2404000017852697374780178526973396961785269773185617852697734031
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00142383512383514194304256001224159360x7ff8895c3f000x7ff888c2408000017852697767750178526977318561785269803649717852698038724
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00172383512383514194304256001224163840x7ff8895c3d800x7ff888c240c000017852698071613178526980364971785269836993717852698372295
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00202383512383514194304256001224170880x7ff8895c3c000x7ff888c2410000017852698416344178526983699371785269867681717852698679058
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00232383512383514194304256001624177920x7ff8895c3a800x7ff888c2414000017852698711897178526986768171785269906929717852699071448
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00262383512383514194304256001624184960x7ff8895c39000x7ff888c2418000017852699103227178526990692971785269946033817852699462438
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00292383512383514194304256001624192000x7ff8895c37800x7ff888c241c000017852699493987178526994603381785269977585817852699778060
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00322383512383514194304256001624199040x7ff8895c36000x7ff888c2420000017852699811880178526997758581785270007985817852700082053
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00352383512383514194304256001224206080x7ff88bbf24800x7ff888c2424000017852700121632178527000798581785270038129917852700383605
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00382383512383514194304256001624213120x7ff88bbf23000x7ff888c2428000017852700416035178527003812991785270077121917852700773606
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00412383512383514194304256001624220160x7ff88bbf21800x7ff888c242c000017852700806585178527007712191785270116001917852701162216
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00442383512383514194304256001624227200x7ff88bbf20000x7ff888c2430000017852701194595178527011600191785270146354017852701465598
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00472383512383514194304256001224234240x7ff8895c3e800x7ff888c2434000017852701497488178527014635401785270176402017852701766161
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00502383512383514194304256001224241280x7ff8895c3d000x7ff888c2438000017852701805360178527017640201785270206610017852702068263
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00532383512383514194304256001624248320x7ff8895c3b800x7ff888c243c000017852702100643178527020661001785270248306117852702485313
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00562383512383514194304256001624255360x7ff8895c3a000x7ff888c2440000017852702517042178527024830611785270287378117852702876263
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00592383512383514194304256001224262400x7ff8895c38800x7ff888c2444000017852702907713178527028737811785270320290117852703204495
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00622383512383514194304256001224269440x7ff8895c37000x7ff888c2448000017852703236464178527032029011785270348018117852703481768
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00652383512383514194304256001224276480x7ff88bbf25800x7ff888c244c000017852703520677178527034801811785270375410217852703755692
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00682383512383514194304256001624286080x7ff88bbf24000x7ff888c2450000017852703787681178527037541021785270411842217852704119943
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00712383512383514194304256001624293120x7ff88bbf22800x7ff888c2454000017852704151352178527041184221785270447970217852704481324
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00742383512383514194304256001224300160x7ff88bbf21000x7ff888c2458000017852704513273178527044797021785270475554317852704757237
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077238351238351419430425600824309760x7ff8895c3f800x7ff888c245c000017852704788706178527047555431785270503042317852705031860
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00802383512383514194304256001224316800x7ff8895c3e000x7ff888c2460000017852705070659178527050304231785270530770317852705309243
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00832383512383514194304256001624326400x7ff8895c3c800x7ff888c2464000017852705340412178527053077031785270567186317852705673524
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00862383512383514194304256001224336000x7ff8895c3b000x7ff888c2468000017852705705043178527056718631785270603586417852706037365
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00892383512383514194304256001224345600x7ff8895c39800x7ff888c246c000017852706068534178527060358641785270632546417852706327138
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092238351238351419430425600824355200x7ff8895c38000x7ff888c2470000017852706359087178527063254641785270660626417852706607841
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00952383512383514194304256001224362240x7ff8895c36800x7ff888c2474000017852706646370178527066062641785270688482417852706886384
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00982383512383514194304256001224371840x7ff88bbf25000x7ff888c2478000017852706918173178527068848241785270725106517852707252885
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001012383512383514194304256001224381440x7ff88bbf23800x7ff888c247c000017852707284684178527072510651785270761522517852707616896
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001042383512383514194304256001224391040x7ff88bbf22000x7ff888c2480000017852707648045178527076152251785270789010517852707891729
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107238351238351419430425600824403200x7ff88bbf20800x7ff888c2484000017852707923748178527078901051785270816658617852708168142
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001102383512383514194304256001224412800x7ff8895c3f000x7ff888c2488000017852708207321178527081665861785270844290617852708444485
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001132383512383514194304256001224422400x7ff8895c3d800x7ff888c248c000017852708475035178527084429061785270880626617852708807837
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001162383512383514194304256001224432000x7ff8895c3c000x7ff888c2490000017852708841876178527088062661785270917346717852709175027
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119238351238351419430425600824441600x7ff8895c3a800x7ff888c2494000017852709206277178527091734671785270944962717852709451181
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001222383512383514194304256001224453760x7ff8895c39000x7ff888c2498000017852709482650178527094496271785270972850717852709730184
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001252383512383514194304256001224463360x7ff8895c37800x7ff888c249c000017852709769003178527097285071785271000722717852710008837
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001282383512383514194304256001224475520x7ff8895c36000x7ff888c24a0000017852710040166178527100072271785271038354817852710385288
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001312383512383514194304256001224485120x7ff88bbf24800x7ff888c24a4000017852710418027178527103835481785271074434817852710745959
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134238351238351419430425600824494720x7ff88bbf23000x7ff888c24a8000017852710777528178527107443481785271102210817852711023662
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001372383512383514194304256001224506880x7ff88bbf21800x7ff888c24ac000017852711055971178527110221081785271130418817852711305805
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001402383512383514194304256001224516480x7ff88bbf20000x7ff888c24b0000017852711344854178527113041881785271159698917852711598567
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001432383512383514194304256001224528640x7ff8895c3e800x7ff888c24b4000017852711631277178527115969891785271196114917852711962848
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001462383512383514194304256001224540800x7ff8895c3d000x7ff888c24b8000017852711994718178527119611491785271232754917852712329159
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149238351238351419430425600824552960x7ff8895c3b800x7ff888c24bc000017852712360458178527123275491785271260499017852712606592
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001522383512383514194304256001224567680x7ff8895c3a000x7ff888c24c0000017852712639062178527126049901785271288467017852712886435
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001552383512383514194304256001224577280x7ff8895c38800x7ff888c24c4000017852712924404178527128846701785271316547017852713167208
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001582383512383514194304256001224589440x7ff8895c37000x7ff888c24c8000017852713198898178527131654701785271352947017852713531039
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001612383512383514194304256001224601600x7ff88bbf25800x7ff888c24cc000017852713563649178527135294701785271389075117852713892420
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164238351238351419430425600824613760x7ff88bbf24000x7ff888c24d0000017852713925370178527138907511785271416899117852714170743
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001672383512383514194304256001224628480x7ff88bbf22800x7ff888c24d4000017852714203523178527141689911785271445283117852714454446
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001702383512383514194304256001224638080x7ff88bbf21000x7ff888c24d8000017852714493475178527144528311785271473059117852714732310
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001732383512383514194304256001224650240x7ff8895c3f800x7ff888c24dc000017852714764259178527147305911785271509795217852715099550
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001762383512383514194304256001224662400x7ff8895c3e000x7ff888c24e0000017852715131050178527150979521785271546179217852715463411
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179238351238351419430425600824674560x7ff8895c3c800x7ff888c24e4000017852715495341178527154617921785271573939217852715741084
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001822383512383514194304256001224689280x7ff8895c3b000x7ff888c24e8000017852715773124178527157393921785271602707317852716028717
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001852383512383514194304256001224701440x7ff8895c39800x7ff888c24ec000017852716068486178527160270731785271630627317852716307960
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001882383512383514194304256001224716160x7ff8895c38000x7ff888c24f0000017852716339270178527163062731785271667011317852716671741
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001912383512383514194304256001224728320x7ff8895c36800x7ff888c24f4000017852716703121178527166701131785271703091417852717032592
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194238351238351419430425600824740480x7ff88bbf25000x7ff888c24f8000017852717063472178527170309141785271730819417852717309915
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001972383512383514194304256001224757760x7ff88bbf23800x7ff888c24fc000017852717341515178527173081941785271759827417852717599928
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002002383512383514194304256001224769920x7ff88bbf22000x7ff888c2500000017852717638877178527175982741785271787443417852717875971
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002032383512383514194304256001224784640x7ff88bbf20800x7ff888c2504000017852717908151178527178744341785271824211517852718243902
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002062383512383514194304256001224799360x7ff8895c3f000x7ff888c2508000017852718276721178527182421151785271861027517852718611863
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209238351238351419430425600824814080x7ff8895c3d800x7ff888c250c000017852718642982178527186102751785271888835517852718889966
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002122383512383514194304256001224831360x7ff8895c3c000x7ff888c2510000017852718921995178527188883551785271918291517852719184579
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002152383512383514194304256001224843520x7ff8895c3a800x7ff888c2514000017852719235378178527191829151785271946883617852719471082
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002182383512383514194304256001224858240x7ff8895c39000x7ff888c2518000017852719502231178527194688361785271984179617852719843403
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002212383512383514194304256001224872960x7ff8895c37800x7ff888c251c000017852719875732178527198417961785272020515617852720206694
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002242383512383514194304256001224887680x7ff8895c36000x7ff888c2520000017852720237623178527202051561785272048563717852720487157
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002272383512383514194304256001224907520x7ff88bbf24800x7ff888c2524000017852720519426178527204856371785272079123717852720792699
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002302383512383514194304256001224919680x7ff88bbf23000x7ff888c2528000017852720831258178527207912371785272107523717852721076832
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002332383512383514194304256001224934400x7ff88bbf21800x7ff888c252c000017852721109001178527210752371785272143747717852721439053
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002362383512383514194304256001224949120x7ff88bbf20000x7ff888c2530000017852721471482178527214374771785272180259817852721804134
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002392383512383514194304256001224963840x7ff8895c3e800x7ff888c2534000017852721835423178527218025981785272208387817852722085677
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002422383512383514194304256001224983680x7ff8895c3d000x7ff888c2538000017852722117666178527220838781785272239427817852722395829
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002452383512383514194304256001224995840x7ff8895c3b800x7ff888c253c000017852722435088178527223942781785272268035917852722681982
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024823835123835141943042560012241013120x7ff8895c3a000x7ff888c2540000017852722713441178527226803591785272304307917852723044603
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025123835123835141943042560012241027840x7ff8895c38800x7ff888c2544000017852723076572178527230430791785272340563917852723407144
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025423835123835141943042560012241042560x7ff8895c37000x7ff888c2548000017852723438243178527234056391785272368323917852723685007
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025723835123835141943042560012241062400x7ff88bbf25800x7ff888c254c000017852723715457178527236832391785272399556017852723997160
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026023835123835141943042560012241077120x7ff88bbf24000x7ff888c2550000017852724036629178527239955601785272428084017852724282463
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026323835123835141943042560016241094400x7ff88bbf22800x7ff888c2554000017852724316172178527242808401785272464276017852724644394
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026623835123835141943042560016241111680x7ff88bbf21000x7ff888c2558000017852724677643178527246427601785272500948117852725011105
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002692383512383514194304256008241128960x7ff8895c3f800x7ff888c255c000017852725042374178527250094811785272528948117852725291098
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027223835123835141943042560012241151360x7ff8895c3e000x7ff888c2560000017852725322377178527252894811785272561156117852725613050
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027523835123835141943042560012241166080x7ff8895c3c800x7ff888c2564000017852725651419178527256115611785272588836117852725889983
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027823835123835141943042560016241183360x7ff8895c3b000x7ff888c2568000017852725921822178527258883611785272625348217852726255414
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028123835123835141943042560016241200640x7ff8895c39800x7ff888c256c000017852726287623178527262534821785272661748217852726619115
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028423835123835141943042560012241217920x7ff8895c38000x7ff888c2570000017852726650804178527266174821785272689652217852726898098
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028723835123835141943042560012241240320x7ff8895c36800x7ff888c2574000017852726929667178527268965221785272722740317852727229120
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029023835123835141943042560012241255040x7ff88bbf25000x7ff888c2578000017852727267889178527272274031785272751140317852727512983
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029323835123835141943042560012241274880x7ff88bbf23800x7ff888c257c000017852727544622178527275114031785272787252317852727874214
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029623835123835141943042560012241292160x7ff88bbf22000x7ff888c2580000017852727907013178527278725231785272823572417852728237265
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029923835123835141943042560012241309440x7ff88bbf20800x7ff888c2584000017852728269444178527282357241785272851748417852728519148
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030223835123835141943042560012241334400x7ff8895c3f000x7ff888c2588000017852728551127178527285174841785272885780417852728859459
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030523835123835141943042560012241349120x7ff8895c3d800x7ff888c258c000017852728899498178527288578041785272913956417852729141132
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030823835123835141943042560012241368960x7ff8895c3c000x7ff888c2590000017852729172291178527291395641785272950308517852729504743
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031123835123835141943042560012241388800x7ff8895c3a800x7ff888c2594000017852729536092178527295030851785272986548517852729867124
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031423835123835141943042560012241408640x7ff8895c39000x7ff888c2598000017852729898743178527298654851785273015588517852730157467
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031723835123835141943042560012241436160x7ff8895c37800x7ff888c259c000017852730190876178527301558851785273052500617852730526718
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032023835123835141943042560012241453440x7ff8895c36000x7ff888c25a0000017852730566577178527305250061785273080964617852730811381
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032323835123835141943042560012241475840x7ff88bbf24800x7ff888c25a4000017852730843010178527308096461785273117412617852731175882
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032623835123835141943042560012241495680x7ff88bbf23000x7ff888c25a8000017852731208061178527311741261785273153732717852731538893
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032923835123835141943042560012241515520x7ff88bbf21800x7ff888c25ac000017852731570982178527315373271785273183380717852731835685
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033223835123835141943042560012241543040x7ff88bbf20000x7ff888c25b0000017852731867534178527318338071785273220452717852732206096
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033523835123835141943042560012241562880x7ff8895c3e800x7ff888c25b4000017852732245085178527322045271785273249028717852732491899
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033823835123835141943042560012241587840x7ff8895c3d000x7ff888c25b8000017852732523968178527324902871785273285604817852732857640
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034123835123835141943042560012241610240x7ff8895c3b800x7ff888c25bc000017852732889679178527328560481785273322164817852733223301
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034423835123835141943042560012241632640x7ff8895c3a000x7ff888c25c0000017852733254330178527332216481785273353236817852733533913
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034723835123835141943042560012241665280x7ff8895c38800x7ff888c25c4000017852733565032178527335323681785273392100917852733941203
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035023835123835141943042560012241685120x7ff8895c37000x7ff888c25c8000017852733962372178527339210091785273423092917852734232796
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035323835123835141943042560012241712640x7ff88bbf25800x7ff888c25cc000017852734265345178527342309291785273460916917852734610756
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035623835123835141943042560012241737600x7ff88bbf24000x7ff888c25d0000017852734643356178527346091691785273497749017852734979187
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035923835123835141943042560012241762560x7ff88bbf22800x7ff888c25d4000017852735011617178527349774901785273529685017852735298459
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036223835123835141943042560012241797760x7ff88bbf21000x7ff888c25d8000017852735330689178527352968501785273571157017852735757648
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036523835123835141943042560012241822720x7ff8895c3f800x7ff888c25dc000017852735776978178527357115701785273606085117852736062501
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036823835123835141943042560012241855360x7ff8895c3e000x7ff888c25e0000017852736095700178527360608511785273643573117852736480820
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037123835123835141943042560012241885440x7ff8895c3c800x7ff888c25e4000017852736492510178527364357311785273684405117852736886710
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037423835123835141943042560012241915520x7ff8895c3b000x7ff888c25e8000017852736898080178527368440511785273722373217852737225292
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037723835123835141943042560012241958400x7ff8895c39800x7ff888c25ec000017852737256371178527372237321785273769061217852737709180
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038023835123835141943042560012241985920x7ff8895c38000x7ff888c25f0000017852737731449178527376906121785273803381217852738035472
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038323835123835141943042560012242023680x7ff8895c36800x7ff888c25f4000017852738067181178527380338121785273845669317852738501100
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038623835123835141943042560012242058880x7ff88bbf25000x7ff888c25f8000017852738514830178527384566931785273888053317852738924380
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038923835123835141943042560012242094080x7ff88bbf23800x7ff888c25fc000017852738935080178527388805331785273928261317852739284311
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039223835123835141943042560012242144640x7ff88bbf22000x7ff888c2600000017852739317490178527392826131785273980741417852739849997
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039523835123835141943042560012242177280x7ff88bbf20800x7ff888c2604000017852739870166178527398074141785274018965417852740191278
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039823835123835141943042560012242220160x7ff8895c3f000x7ff888c2608000017852740223318178527401896541785274060373517852740646387
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040123835123835141943042560012242260480x7ff8895c3d800x7ff888c260c000017852740658167178527406037351785274105397517852741096566
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040423835123835141943042560012242300800x7ff8895c3c000x7ff888c2610000017852741108566178527410539751785274147797517852741520635
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040723835123835141943042560012242359040x7ff8895c3a800x7ff888c2614000017852741533345178527414779751785274207813617852742100261
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041023835123835141943042560012242394240x7ff8895c39000x7ff888c2618000017852742120520178527420781361785274246261617852742464122
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041323835123835141943042560012242442240x7ff8895c37800x7ff888c261c000017852742495881178527424626161785274289973717852742943690
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041623835123835141943042560012242487680x7ff8895c36000x7ff888c2620000017852742956040178527428997371785274336069717852743403809
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041923835123835141943042560012242533120x7ff88bbf24800x7ff888c2624000017852743415308178527433606971785274381269717852743854887
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004222383512383514194304256008242555520x7ff88bbf23000x7ff888c2628000017852743866867178527438126971785274447685817852744519781
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042523835123835141943042560012242598400x7ff88bbf21800x7ff888c262c000017852744539460178527444768581785274492133817852744964010
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042823835123835141943042560012242656640x7ff88bbf20000x7ff888c2630000017852744975050178527449213381785274543589917852745478337
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043123835123835141943042560012242712320x7ff8895c3e800x7ff888c2634000017852745489317178527454358991785274595445917852745972385
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004342383512383514194304256008242732160x7ff8895c3d000x7ff888c2638000017852745987614178527459544591785274644694017852746492852
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004372383512383514194304256008242757120x7ff8895c3b800x7ff888c263c000017852746505581178527464469401785274721910117852747263173
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044023835123835141943042560012242807680x7ff8895c3a000x7ff888c2640000017852747283402178527472191011785274770550117852747747881
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044323835123835141943042560012242876160x7ff8895c38800x7ff888c2644000017852747758960178527477055011785274826886117852748310857
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044623835123835141943042560012242942080x7ff8895c37000x7ff888c2648000017852748322856178527482688611785274883222217852748874753
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004492383512383514194304256008242969600x7ff88bbf25800x7ff888c264c000017852748886262178527488322221785274939478217852749436889
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004522383512383514194304256008242999680x7ff88bbf24000x7ff888c2650000017852749448568178527493947821785275026486317852750309257
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004552383512383514194304256008243027200x7ff88bbf22800x7ff888c2654000017852750329727178527502648631785275092982417852750974811
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045823835123835141943042560012243054720x7ff88bbf21000x7ff888c2658000017852750986220178527509298241785275160870417852751652374
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046123835123835141943042560012243082240x7ff8895c3f800x7ff888c265c000017852751663494178527516087041785275228822517852752330757
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004642383512383514194304256008243109760x7ff8895c3e000x7ff888c2660000017852752342157178527522882251785275295030617852752993191
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004672383512383514194304256008243132160x7ff8895c3c800x7ff888c2664000017852753004871178527529500141785275403641417852754087294
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004702383512383514194304256008243159680x7ff8895c3b000x7ff888c2668000017852754107573178527540364141785275511673417852755164557
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047323835123835141943042560012243187200x7ff8895c39800x7ff888c266c000017852755175877178527551167341785275621641417852756283989
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047623835123835141943042560012243214720x7ff8895c38000x7ff888c2670000017852756296649178527562164141785275734729517852757413671
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004792383512383514194304256008243242240x7ff8895c36800x7ff888c2674000017852757426311178527573472951785275845561517852758522824
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004822383512383514194304256008243264640x7ff88bbf25000x7ff888c2678000017852758535493178527584556151785276041369617852760480545
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004852383512383514194304256008243292160x7ff88bbf23800x7ff888c267c000017852760500774178527604136961785276232985617852762401667
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048823835123835141943042560012243319680x7ff88bbf22000x7ff888c2680000017852762414887178527623298561785276433193717852764406557
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049123835123835141943042560012243347200x7ff88bbf20800x7ff888c2684000017852764419157178527643319371785276631241717852766383018
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004942383512383514194304256008243374720x7ff8895c3f000x7ff888c2688000017852766395418178527663124171785276825001817852768319691
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049723835123835141943042560082400x7ff8895c3d800x7ff888c268c000017852768331360178527682500181785277186345917852771934051