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

41 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_VMEMSQ_INST_LEVEL_VMEMSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd0002313123131335544322560043241600x00x7ffac3c04280524288545280461078381614232413425811142307014388401423256120520414232561296504
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]002231312313132768256001224138880x00x7ffac3c23f80409641990470363614232566502467142325612052041423256663306014232566637894
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]00523131231314194304256001224143360x7ffada1953800x7ffac3c23fc052428810975998122925482014232566672914142325666330601423256701322214232567016057
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00823131231314194304256001624150400x7ffada1952000x7ffac3c2400052428811539795129243974414232567052946142325670132221423256742394314232567426668
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]001123131231314194304256001624154880x7ffada1950800x7ffac3c2404052428811549812129357833214232567459778142325674239431423256782170414232567824020
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]001423131231314194304256001224159360x7ffacc34df000x7ffac3c2408052428810687367119695058014232567856159142325678217041423256812746514232568129824
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]001723131231314194304256001224163840x7ffacc34dd800x7ffac3c240c052428810836356121361722014232568162853142325681274651423256843658614232568438698
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]002023131231314194304256001224170880x7ffacc34dc000x7ffac3c2410052428811410208127790945214232568482307142325684365861423256874042714232568742591
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002323131231314194304256001624177920x7ffacc34da800x7ffac3c2414052428811612774130060768814232568774481142325687404271423256913466814232569136933
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]002623131231314194304256001624184960x7ffacc34d9000x7ffac3c2418052428811641331130379564814232569168763142325691346681423256953275014232569535135
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]002923131231314194304256001624192000x7ffacc34d7800x7ffac3c241c052428810811066121083028414232569564914142325695327501423256985659114232569858838
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]003223131231314194304256001624199040x7ffacc34d6000x7ffac3c2420052428811039190123635814014232569891198142325698565911423257016731214232570169922
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]003523131231314194304256001224206080x7ffada1954800x7ffac3c2424052428810966363122827820414232570211031142325701673121423257048811314232570490515
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]003823131231314194304256001624213120x7ffada1953000x7ffac3c2428052428811552362129387163214232570522575142325704881131423257088251414232570884737
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]004123131231314194304256001624220160x7ffada1951800x7ffac3c242c052428811464201128394712414232570917707142325708825141423257127499514232571276809
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]004423131231314194304256001624227200x7ffada1950000x7ffac3c2430052428811148978124863242414232571310029142325712749951423257155451614232571556164
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]004723131231314194304256001224234240x7ffacc34de800x7ffac3c2434052428811200247125437679214232571588253142325715545161423257183387714232571835548
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]005023131231314194304256001224241280x7ffacc34dd000x7ffac3c2438052428811317702126757081214232571875557142325718338771423257211579814232572117482
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]005323131231314194304256001624248320x7ffacc34db800x7ffac3c243c052428811458641128333301614232572149941142325721157981423257248219914232572483905
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]005623131231314194304256001624255360x7ffacc34da000x7ffac3c2440052428811452755128267093614232572516224142325724821991423257285228014232572853957
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]005923131231314194304256001224262400x7ffacc34d8800x7ffac3c2444052428811168212125078174814232572885316142325728522801423257313388114232573135541
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]006223131231314194304256001224269440x7ffacc34d7000x7ffac3c2448052428811079769124097808014232573167311142325731338811423257341580214232573417565
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]006523131231314194304256001224276480x7ffada1955800x7ffac3c244c052428811197299125405964414232573456685142325734158021423257369852314232573700190
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]006823131231314194304256001624286080x7ffada1954000x7ffac3c2450052428811473660128499099614232573732709142325736985231423257406844414232574070002
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]007123131231314194304256001624293120x7ffada1952800x7ffac3c2454052428811520070129021665614232574103801142325740684441423257444092514232574442674
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]007423131231314194304256001224300160x7ffada1951000x7ffac3c2458052428811030865123543169214232574475234142325744409251423257472060614232574722219
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00772313123131419430425600824309760x7ffacc34df800x7ffac3c245c052428810474321117313186414232574754398142325747206061423257499932714232575000943
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]008023131231314194304256001224316800x7ffacc34de000x7ffac3c2460052428811297535126532850014232575040252142325749993271423257527788814232575279657
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]008323131231314194304256001624326400x7ffacc34dc800x7ffac3c2464052428811423371127943457214232575311997142325752778881423257564956914232575651300
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]008623131231314194304256001224336000x7ffacc34db000x7ffac3c2468052428811572868129614406414232575683109142325756495691423257601677014232576018362
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]008923131231314194304256001224345600x7ffacc34d9800x7ffac3c246c052428810926996122373163214232576050461142325760167701423257629789114232576299476
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00922313123131419430425600824355200x7ffacc34d8000x7ffac3c2470052428810454400117089376014232576331146142325762978911423257657645214232576578131
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]009523131231314194304256001224362240x7ffacc34d6800x7ffac3c2474052428811108854124424197214232576616730142325765764521423257685661314232576858305
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]009823131231314194304256001224371840x7ffada1955000x7ffac3c2478052428811381272127467400814232576889224142325768566131423257722157414232577223247
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]0010123131231314194304256001224381440x7ffada1953800x7ffac3c247c052428811391554127582492414232577255357142325772215741423257758461514232577586300
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]0010423131231314194304256001224391040x7ffada1952000x7ffac3c2480052428810846762121482820414232577617949142325775846151423257786333614232577865004
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]001072313123131419430425600824403200x7ffada1950800x7ffac3c2484052428810313724115504830014232577897134142325778633361423257814221714232578143929
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]0011023131231314194304256001224412800x7ffacc34df000x7ffac3c2488052428810923119122335722414232578184488142325781422171423257842589814232578427543
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0011323131231314194304256001224422400x7ffacc34dd800x7ffac3c248c052428811438022128106217214232578459932142325784258981423257879821914232578799905
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]0011623131231314194304256001224432000x7ffacc34dc000x7ffac3c2490052428811438589128108245614232578831725142325787982191423257916222014232579163838
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]001192313123131419430425600824441600x7ffacc34da800x7ffac3c2494052428810564591118318452814232579196107142325791622201423257944014114232579441752
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]0012223131231314194304256001224453760x7ffacc34d9000x7ffac3c249805242889844774110256682814232579473692142325794401411423257972142214232579723076
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]0012523131231314194304256001224463360x7ffacc34d7800x7ffac3c249c052428810969802122853568814232579762706142325797214221423258001134314232580013281
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0012823131231314194304256001224475520x7ffacc34d6000x7ffac3c24a0052428811323537126820878414232580045170142325800113431423258037646414232580378113
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]0013123131231314194304256001224485120x7ffada1954800x7ffac3c24a4052428811329709126890814014232580410842142325803764641423258074462514232580746486
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]001342313123131419430425600824494720x7ffada1953000x7ffac3c24a8052428810409887116593288814232580777805142325807446251423258102590614232581027510
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]0013723131231314194304256001224506880x7ffada1951800x7ffac3c24ac05242889125077102192540014232581060179142325810259061423258130510714232581306754
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]0014023131231314194304256001224516480x7ffada1950000x7ffac3c24b0052428810638025119146488414232581346003142325813051071423258159198814232581593668
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0014323131231314194304256001224528640x7ffacc34de800x7ffac3c24b4052428811208454125534700814232581625048142325815919881423258195982914232581961441
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]0014623131231314194304256001224540800x7ffacc34dd000x7ffac3c24b8052428811384358127500085214232581993410142325819598291423258234527014232582346933
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001492313123131419430425600824552960x7ffacc34db800x7ffac3c24bc052428810408591116580672014232582379282142325823452701423258262687114232582628607
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]0015223131231314194304256001224567680x7ffacc34da000x7ffac3c24c00524288769151986143030414232582660987142325826268711423258290671214232582908362
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]0015523131231314194304256001224577280x7ffacc34d8800x7ffac3c24c4052428810729915120169603614232582947231142325829067121423258318639314232583188176
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015823131231314194304256001224589440x7ffacc34d7000x7ffac3c24c8052428811395932127637760814232583219645142325831863931423258355519414232583556858
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]0016123131231314194304256001224601600x7ffada1955800x7ffac3c24cc052428811370525127349026414232583588548142325835551941423258392111514232583922701
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001642313123131419430425600824613760x7ffada1954000x7ffac3c24d0052428810259284114898046014232583954540142325839211151423258419951614232584201135
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]0016723131231314194304256001224628480x7ffada1952800x7ffac3c24d40524288629069270447509614232584233594142325841995161423258448671714232584488449
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]0017023131231314194304256001224638080x7ffada1951000x7ffac3c24d8052428810285930115204750814232584528738142325844867171423258476815814232584769823
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017323131231314194304256001224650240x7ffacc34df800x7ffac3c24dc052428811228088125751076014232584801613142325847681581423258513647914232585138246
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]0017623131231314194304256001224662400x7ffacc34de000x7ffac3c24e0052428811283060126369547214232585169535142325851364791423258550128014232585502878
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001792313123131419430425600824674560x7ffacc34dc800x7ffac3c24e4052428810162472113817658414232585534368142325855012801423258578192114232585783503
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]0018223131231314194304256001224689280x7ffacc34db000x7ffac3c24e80524288610034668316878814232585815332142325857819211423258607008214232586071737
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]0018523131231314194304256001224701440x7ffacc34d9800x7ffac3c24ec052428810207442114321235214232586111136142325860700821423258636368314232586365281
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018823131231314194304256001224716160x7ffacc34d8000x7ffac3c24f0052428811405017127737189614232586397300142325863636831423258673040414232586732203
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]0019123131231314194304256001224728320x7ffacc34d6800x7ffac3c24f4052428811232365125797559614232586764272142325867304041423258709808514232587099716
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001942313123131419430425600824740480x7ffada1955000x7ffac3c24f805242889578903107290381614232587131175142325870980851423258738528614232587387100
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]0019723131231314194304256001224757760x7ffada1953800x7ffac3c24fc0524288469963352631299614232587419289142325873852861423258767808714232587679764
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]0020023131231314194304256001224769920x7ffada1952000x7ffac3c2500052428810223244114499380814232587719013142325876780871423258795744814232587959078
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020323131231314194304256001224784640x7ffada1950800x7ffac3c2504052428811279937126334687614232587990507142325879574481423258832464914232588326380
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]0020623131231314194304256001224799360x7ffacc34df000x7ffac3c2508052428811302088126583077614232588358140142325883246491423258869265014232588694313
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]002092313123131419430425600824814080x7ffacc34dd800x7ffac3c250c05242889580606107300798814232588726052142325886926501423258897265114232588974317
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]0021223131231314194304256001224831360x7ffacc34dc000x7ffac3c25100524288398675344646825614232589005746142325889726511423258926993214232589271541
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]0021523131231314194304256001224843520x7ffacc34da800x7ffac3c2514052428810675394119557223614232589321090142325892699321423258955521314232589556955
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021823131231314194304256001224858240x7ffacc34d9000x7ffac3c2518052428811314999126726890014232589589035142325895552131423258992753414232589929128
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]0022123131231314194304256001224872960x7ffacc34d7800x7ffac3c251c052428811223008125695420014232589963167142325899275341423259031761514232590319350
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]0022423131231314194304256001224887680x7ffacc34d6000x7ffac3c252005242889484750106222625614232590351269142325903176151423259059953614232590601164
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]0022723131231314194304256001224907520x7ffada1954800x7ffac3c25240524288370791941529048014232590633123142325905995361423259090353714232590905388
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]0023023131231314194304256001224919680x7ffada1953000x7ffac3c2528052428810079472112886766814232590944437142325909035371423259118177814232591183492
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023323131231314194304256001224934400x7ffada1951800x7ffac3c252c052428811327253126870158814232591214881142325911817781423259154897914232591550664
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0023623131231314194304256001224949120x7ffada1950000x7ffac3c2530052428811322923126813150814232591583294142325915489791423259191442014232591916267
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0023923131231314194304256001224963840x7ffacc34de800x7ffac3c253405242889179491102791356014232591947066142325919144201423259219570114232592197771
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0024223131231314194304256001224983680x7ffacc34dd000x7ffac3c25380524288338254337874025214232592228840142325921957011423259250978214232592511475
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0024523131231314194304256001224995840x7ffacc34db800x7ffac3c253c052428810121232113358381614232592551064142325925097821423259278962314232592791319
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00248231312313141943042560012241013120x7ffacc34da000x7ffac3c2540052428811165524125053510414232592823588142325927896231423259316066414232593162291
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]00251231312313141943042560012241027840x7ffacc34d8800x7ffac3c2544052428811089775124202232414232593194431142325931606641423259352978514232593531534
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]00254231312313141943042560012241042560x7ffacc34d7000x7ffac3c25480524288875968198106535614232593562913142325935297851423259381154614232593813428
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]00257231312313141943042560012241062400x7ffada1955800x7ffac3c254c0524288332564537239688014232593845157142325938115461423259412898714232594130691
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]00260231312313141943042560012241077120x7ffada1954000x7ffac3c255005242889886312110726110414232594171801142325941289871423259441826814232594420075
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00263231312313141943042560016241094400x7ffada1952800x7ffac3c2554052428811307021126635089214232594452665142325944182681423259478498914232594786758
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]00266231312313141943042560016241111680x7ffada1951000x7ffac3c2558052428811195412125384687614232594819637142325947849891423259515203114232595153640
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0026923131231314194304256008241128960x7ffacc34df800x7ffac3c255c0524288817151691517166014232595184990142325951520311423259543427214232595435885
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]00272231312313141943042560012241151360x7ffacc34de000x7ffac3c25600524288297484633321669614232595467904142325954342721423259575875314232595760378
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]00275231312313141943042560012241166080x7ffacc34dc800x7ffac3c256405242889765423109367179614232595799437142325957587531423259604787314232596049452
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00278231312313141943042560016241183360x7ffacc34db000x7ffac3c2568052428811076533124056949614232596081031142325960478731423259641251514232596414155
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]00281231312313141943042560016241200640x7ffacc34d9800x7ffac3c256c052428811144457124817833614232596445974142325964125151423259677651614232596778327
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]00284231312313141943042560012241217920x7ffacc34d8000x7ffac3c25700524288724392181126601214232596809896142325967765161423259706099714232597062711
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]00287231312313141943042560012241240320x7ffacc34d6800x7ffac3c25740524288295264833061394414232597094571142325970609971423259738787814232597389485
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]00290231312313141943042560012241255040x7ffada1955000x7ffac3c257805242889312383104295261214232597427944142325973878781423259766531914232597667029
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00293231312313141943042560012241274880x7ffada1953800x7ffac3c257c052428811039739123639743214232597698558142325976653191423259802772014232598029331
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]00296231312313141943042560012241292160x7ffada1952000x7ffac3c2580052428811024893123480814414232598062981142325980277201423259840020114232598401854
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]00299231312313141943042560012241309440x7ffada1950800x7ffac3c25840524288586539665685329214232598433673142325984002011423259868500214232598686608
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]00302231312313141943042560012241334400x7ffacc34df000x7ffac3c25880524288290134232489921614232598719707142325986850021423259903124314232599033071
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]00305231312313141943042560012241349120x7ffacc34dd800x7ffac3c258c0524288832326593222333614232599073090142325990312431423259931700414232599318705
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00308231312313141943042560012241368960x7ffacc34dc000x7ffac3c2590052428810969840122861678814232599351175142325993170041423259968164514232599683268
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]00311231312313141943042560012241388800x7ffacc34da800x7ffac3c2594052428811155903124944430414232599715207142325996816451423260004580614232600047410
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]00314231312313141943042560012241408640x7ffacc34d9000x7ffac3c25980524288446066149951733614232600078870142326000458061423260033860714232600340504
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]00317231312313141943042560012241436160x7ffacc34d7800x7ffac3c259c0524288283407331729768814232600372254142326003386071423260069268814232600694317
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]00320231312313141943042560012241453440x7ffacc34d6000x7ffac3c25a00524288733556782155992014232600733866142326006926881423260097428914232600976022
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00323231312313141943042560012241475840x7ffada1954800x7ffac3c25a4052428810978813122957261214232601007611142326009742891423260134325014232601344874
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]00326231312313141943042560012241495680x7ffada1953000x7ffac3c25a8052428811007157123279485214232601376453142326013432501423260170757114232601709277
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]00329231312313141943042560012241515520x7ffada1951800x7ffac3c25ac0524288383762942985073214232601740206142326017075711423260200805214232602009831
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]00332231312313141943042560012241543040x7ffada1950000x7ffac3c25b00524288286978032136090014232602041510142326020080521423260238453414232602386303
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]00335231312313141943042560012241562880x7ffacc34de800x7ffac3c25b40524288572670964133984814232602425772142326023845341423260267445414232602676137
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00338231312313141943042560012241587840x7ffacc34dd000x7ffac3c25b8052428810691516119741265614232602707766142326026744541423260304389614232603045539
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]00341231312313141943042560012241610240x7ffacc34db800x7ffac3c25bc052428810783459120771698814232603077269142326030438961423260341045714232603412272
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]00344231312313141943042560012241632640x7ffacc34da000x7ffac3c25c00524288368717041291741614232603444041142326034104571423260371829814232603719935
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]00347231312313141943042560012241665280x7ffacc34d8800x7ffac3c25c40524288292211932727472814232603751405142326037182981423260410901914232604154587
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]00350231312313141943042560012241685120x7ffacc34d7000x7ffac3c25c80524288423262847406755614232604174656142326041090191423260444374014232604445301
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00353231312313141943042560012241712640x7ffada1955800x7ffac3c25cc052428810448956117027516014232604477190142326044437401423260481126114232604812963
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]00356231312313141943042560012241737600x7ffada1954000x7ffac3c25d005242889831368110109636414232604847182142326048112611423260518454214232605186085
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]00359231312313141943042560012241762560x7ffada1952800x7ffac3c25d40524288284963331920564414232605218245142326051845421423260550710314232605508689
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]00362231312313141943042560012241797760x7ffada1951000x7ffac3c25d80524288286230632059938814232605541378142326055071031423260592598514232605945500
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]00365231312313141943042560012241822720x7ffacc34df800x7ffac3c25dc0524288304165434064382414232605967089142326059259851423260625830614232606259983
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00368231312313141943042560012241855360x7ffacc34de000x7ffac3c25e00524288781934387573694014232606292223142326062583061423260663990714232606641576
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]00371231312313141943042560012241885440x7ffacc34dc800x7ffac3c25e40524288777506387076210814232606673185142326066399071423260702198814232607067307
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]00374231312313141943042560012241915520x7ffacc34db000x7ffac3c25e80524288281398031511339214232607079687142326070219881423260740582914232607407510
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]00377231312313141943042560012241958400x7ffacc34d9800x7ffac3c25ec0524288284020931813909214232607439569142326074058291423260787655114232607921849
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]00380231312313141943042560012241985920x7ffacc34d8000x7ffac3c25f00524288278168831166062414232607942519142326078765511423260825239214232608253992
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00383231312313141943042560012242023680x7ffacc34d6800x7ffac3c25f40524288692924977598586814232608286562142326082523921423260864887314232608691234
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]00386231312313141943042560012242058880x7ffada1955000x7ffac3c25f80524288656296373502890814232608702973142326086488731423260908039514232609122715
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]00389231312313141943042560012242094080x7ffada1953800x7ffac3c25fc0524288277967031122174014232609134434142326090803951423260948919614232609490777
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]00392231312313141943042560012242144640x7ffada1952000x7ffac3c26000524288298547633436240414232609522966142326094891961423261000823814232610025576
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]00395231312313141943042560012242177280x7ffada1950800x7ffac3c26040524288278382231175927614232610049576142326100082381423261037351914232610375579
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00398231312313141943042560012242220160x7ffacc34df000x7ffac3c26080524288589311365996573214232610407848142326103735191423261079064014232610835620
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]00401231312313141943042560012242260480x7ffacc34dd800x7ffac3c260c0524288525597958874159214232610847629142326107906401423261123960214232611282530
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]00404231312313141943042560012242300800x7ffacc34dc000x7ffac3c26100524288277041331029326014232611294330142326112396021423261166536314232611708172
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]00407231312313141943042560012242359040x7ffacc34da800x7ffac3c26140524288293735932891887614232611720301142326116653631423261226696514232612308579
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]00410231312313141943042560012242394240x7ffacc34d9000x7ffac3c26180524288282774931668360414232612327839142326122669651423261267000614232612671872
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00413231312313141943042560012242442240x7ffacc34d7800x7ffac3c261c0524288531126559487354414232612703401142326126700061423261311592714232613158582
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]00416231312313141943042560012242487680x7ffacc34d6000x7ffac3c26200524288327092536638064814232613169832142326131159271423261358120914232613622972
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]00419231312313141943042560012242533120x7ffada1954800x7ffac3c26240524288277697231101546014232613635592142326135812091423261403417014232614052154
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0042223131231314194304256008242555520x7ffada1953000x7ffac3c26280524288236886726531918814232614068113142326140341701423261470441214232614748419
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]00425231312313141943042560012242598400x7ffada1951800x7ffac3c262c0524288281040031475646414232614769759142326147044121423261514921414232615193070
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00428231312313141943042560012242656640x7ffada1950000x7ffac3c26300524288328509036794368814232615205210142326151492141423261566825614232615710890
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]00431231312313141943042560012242712320x7ffacc34de800x7ffac3c26340524288364129740785717614232615722950142326156682561423261618185714232616223979
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0043423131231314194304256008242732160x7ffacc34dd000x7ffac3c26380524288240019926879607214232616236669142326161818571423261669497914232616736629
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0043723131231314194304256008242757120x7ffacc34db800x7ffac3c263c0524288238841126754874814232616748989142326166949791423261746538114232617507923
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]00440231312313141943042560012242807680x7ffacc34da000x7ffac3c26400524288268814830105670014232617527813142326174653811423261795322314232617970954
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00443231312313141943042560012242876160x7ffacc34d8800x7ffac3c26440524288350404939250307214232617987244142326179532231423261850058414232618546422
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]00446231312313141943042560012242942080x7ffacc34d7000x7ffac3c26480524288334187637423848414232618559772142326185005841423261907258614232619116680
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0044923131231314194304256008242969600x7ffada1955800x7ffac3c264c0524288239827826862108414232619128190142326190725861423261964042814232619682999
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0045223131231314194304256008242999680x7ffada1954000x7ffac3c26500524288239098026780032414232619695129142326196404281423262051739114232620559771
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0045523131231314194304256008243027200x7ffada1952800x7ffac3c26540524288239871326866788814232620579080142326205173911423262118187314232621228757
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00458231312313141943042560012243054720x7ffada1951000x7ffac3c26580524288258879028990243214232621241137142326211818731423262186955514232621911613
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]00461231312313141943042560012243082240x7ffacc34df800x7ffac3c265c0524288259951629115310814232621923533142326218695551423262254715714232622593569
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0046423131231314194304256008243109760x7ffacc34de000x7ffac3c26600524288239419426815696414232622606609142326225471571423262323643914232623282555
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0046723131231314194304256008243132160x7ffacc34dc800x7ffac3c26640524288240914726977592814232623295195142326232363391423262434946214232624399932
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0047023131231314194304256008243159680x7ffacc34db000x7ffac3c26680524288244147527338853214232624419882142326243494621423262544162514232625506409
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00473231312313141943042560012243187200x7ffacc34d9800x7ffac3c266c0524288259861329106092414232625519049142326254416251423262657922814232626649556
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]00476231312313141943042560012243214720x7ffacc34d8000x7ffac3c26700524288259868329101090414232626663496142326265792281423262772387114232627790873
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0047923131231314194304256008243242240x7ffacc34d6800x7ffac3c26740524288242970027211414814232627803222142326277238711423262883667514232628903900
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0048223131231314194304256008243264640x7ffada1955000x7ffac3c26780524288246201727578480814232628916299142326288366751423263078852014232630865740
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0048523131231314194304256008243292160x7ffada1953800x7ffac3c267c0524288246270527576519614232630886359142326307885201423263272484614232632791640
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00488231312313141943042560012243319680x7ffada1952000x7ffac3c26800524288263441829500245614232632803770142326327248461423263470325214232634775129
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]00491231312313141943042560012243347200x7ffada1950800x7ffac3c26840524288262809329434696014232634787859142326347032521423263668597814232636753889
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0049423131231314194304256008243374720x7ffacc34df000x7ffac3c26880524288245570227497090814232636766199142326366859781423263862854414232638697790
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00497231312313141943042560082400x7ffacc34dd800x7ffac3c268c0524288248068527779934814232638709629142326386285441423264225095414232642323175