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

44 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjGRBM_COUNTGRBM_GUI_ACTIVESQ_WAVESSQ_IFETCHSQ_IFETCH_LEVELSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000137044137044335544322560043241600x00x7fb803a0428038448538448552428847185926856857674732015893779864514158931033964041589392639531415893926508014
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00213704413704432768256001224138880x00x7fb803a23f8033460334605128192598165989615893931668709158939263953141589393180124615893931805906
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051370441370444194304256001224143360x7fb8223853800x7fb803a23fc0164874164874655369175041413751590203615893931844195158939318012461589393217724715893932179668
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081370441370444194304256001624150400x7fb8223852000x7fb803a240003096413096416553611141121734811939270415893932218297158939321772471589393258748815893932589859
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111370441370444194304256001624154880x7fb8223850800x7fb803a24040308576308576655369175041386961551816415893932625658158939325874881589393298668915893932989070
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141370441370444194304256001224159360x7fb82014df000x7fb803a240801666001666006553610485761579481773415215893933025099158939329866891589393329725015893933299253
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171370441370444194304256001224163840x7fb82014dd800x7fb803a240c0164661164661655369830401471501655380015893933335142158939332972501589393360765015893933609816
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201370441370444194304256001224170880x7fb82014dc000x7fb803a241001638211638216553611141121635481830455615893933663405158939336076501589393392285115893933924909
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231370441370444194304256001624177920x7fb82014da800x7fb803a241403097273097276553613107201952012186440015893933960178158939339228511589393432973215893934331780
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261370441370444194304256001624184960x7fb82014d9000x7fb803a241803085633085636553611796481773811980072815893934366479158939343297321589393474237315893934744560
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291370441370444194304256001624192000x7fb82014d7800x7fb803a241c01643451643456553612451841939712169597615893934778990158939347423731589393505581415893935058103
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321370441370444194304256001624199040x7fb82014d6000x7fb803a242001647131647136553612451841867312094619215893935093383158939350558141589393536653415893935368686
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351370441370444194304256001224206080x7fb8223854800x7fb803a242401637351637356553612451841867642091734015893935412766158939353665341589393567757515893935680000
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381370441370444194304256001624213120x7fb8223853000x7fb803a242803097213097216553614417922154602413469615893935716579158939356775751589393607581615893936077891
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411370441370444194304256001624220160x7fb8223851800x7fb803a242c03102353102356553613107202008962250012415893936112750158939360758161589393647405715893936476072
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441370441370444194304256001624227200x7fb8223850000x7fb803a243001649061649066553613762562056282303188415893936511631158939364740571589393678109815893936783325
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471370441370444194304256001224234240x7fb82014de800x7fb803a243401632961632966553614417922166852431520815893936817854158939367810981589393708781915893937089878
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501370441370444194304256001224241280x7fb82014dd000x7fb803a243801646081646086553613107201954612187214415893937131967158939370878191589393740621915893937408431
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531370441370444194304256001624248320x7fb82014db800x7fb803a243c03092723092726553615728642336422611014015893937443130158939374062191589393780654015893937808742
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561370441370444194304256001624255360x7fb82014da000x7fb803a244003042303042306553614417922095472346066015893937843471158939378065401589393819822115893938201383
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591370441370444194304256001224262400x7fb82014d8800x7fb803a244401636921636926553615073282252292522780815893938235452158939381982211589393851614215893938518476
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621370441370444194304256001224269440x7fb82014d7000x7fb803a244801648741648746553616384002439242729935215893938553675158939385161421589393882638315893938827799
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651370441370444194304256001224276480x7fb8223855800x7fb803a244c01624201624206553614417922154472407736815893938870318158939388263831589393911086315893939112473
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681370441370444194304256001624286080x7fb8223854000x7fb803a245003082683082686553617039362521552823786015893939148012158939391108631589393947998415893939481435
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711370441370444194304256001624293120x7fb8223852800x7fb803a245403088833088836553615728642510442816042815893939516594158939394799841589393985102515893939852496
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741370441370444194304256001224300160x7fb8223851000x7fb803a245801621091621096553616384002431482732046415893939887996158939398510251589394013294615893940134570
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077137044137044419430425600824309760x7fb82014df800x7fb803a245c01629511629516553618350082705423033025215893940169439158939401329461589394041214615893940413654
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801370441370444194304256001224316800x7fb82014de000x7fb803a246001627751627756553615073282248752511596015893940454863158939404121461589394069342715893940695027
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831370441370444194304256001624326400x7fb82014dc800x7fb803a246403074773074776553618350082723503051703615893940730187158939406934271589394106686815893941068369
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861370441370444194304256001224336000x7fb82014db000x7fb803a246803078133078136553617039362487632788962015893941103438158939410668681589394143374915893941435181
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891370441370444194304256001224345600x7fb82014d9800x7fb803a246c01632651632656553617694722660322975197615893941469930158939414337491589394171359015893941715185
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092137044137044419430425600824355200x7fb82014d8000x7fb803a247001628881628886553620316163075063438956015893941749674158939417135901589394199087015893941992339
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951370441370444194304256001224362240x7fb82014d6800x7fb803a247401623331623336553616384002460132753194015893942033478158939419908701589394228111115893942282692
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981370441370444194304256001224371840x7fb8223855000x7fb803a247803051413051416553619660802905213253357215893942318331158939422811111589394265343215893942655044
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011370441370444194304256001224381440x7fb8223853800x7fb803a247c03049373049376553618350082711933038260415893942690653158939426534321589394302543315893943026945
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041370441370444194304256001224391040x7fb8223852000x7fb803a248001631371631376553619005442864763213584015893943061765158939430254331589394330639315893943307939
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107137044137044419430425600824403200x7fb8223850800x7fb803a248401643391643396553622282243306563708986815893943343528158939433063931589394358575415893943587473
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101370441370444194304256001224412800x7fb82014df000x7fb803a248801631941631946553617039362578572881125215893943629862158939435857541589394386559515893943867017
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131370441370444194304256001224422400x7fb82014dd800x7fb803a248c03070313070316553620971523102233474004815893943903026158939438655951589394423183515893944233498
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161370441370444194304256001224432000x7fb82014dc000x7fb803a249003052753052756553619660802841513178009215893944267438158939442318351589394459807615893944599600
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119137044137044419430425600824441600x7fb82014da800x7fb803a249401620131620136553620316163053223418326415893944633590158939445980761589394487599715893944877514
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221370441370444194304256001224453760x7fb82014d9000x7fb803a249801626591626596553624248323672554112654815893944912143158939448759971589394516559815893945167198
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251370441370444194304256001224463360x7fb82014d7800x7fb803a249c01624011624016553618350082725033052605615893945209057158939451655981589394544591815893945447361
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281370441370444194304256001224475520x7fb82014d6000x7fb803a24a003064093064096553622282243337013726813615893945482131158939454459181589394581343915893945815073
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311370441370444194304256001224485120x7fb8223854800x7fb803a24a403015373015376553620971523096193465050015893945850642158939458134391589394617936015893946181325
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134137044137044419430425600824494720x7fb8223853000x7fb803a24a801631931631936553621626883185993568419615893946217234158939461793601589394646640115893946467929
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371370441370444194304256001224506880x7fb8223851800x7fb803a24ac01612961612966553626214403872664334729215893946502688158939464664011589394674544115893946747112
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401370441370444194304256001224516480x7fb8223850000x7fb803a24b001611701611706553619660802948203299635615893946789851158939467454411589394702544215893947026906
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431370441370444194304256001224528640x7fb82014de800x7fb803a24b403043023043026553623592963500153920181215893947063145158939470254421589394739056315893947392088
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461370441370444194304256001224540800x7fb82014dd000x7fb803a24b803028593028596553622282243297873692168015893947427497158939473905631589394775904415893947760690
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149137044137044419430425600824552960x7fb82014db800x7fb803a24bc01622241622246553622937603475313891825615893947795929158939477590441589394804096515893948042504
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521370441370444194304256001224567680x7fb82014da000x7fb803a24c001623451623456553627525124072474556822015893948077853158939480409651589394832224515893948323907
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551370441370444194304256001224577280x7fb82014d8800x7fb803a24c401620561620566553620316163024513380436415893948364907158939483222451589394860352615893948605071
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581370441370444194304256001224589440x7fb82014d7000x7fb803a24c803009923009926553624903683661304101084815893948640440158939486035261589394896736715893948968913
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611370441370444194304256001224601600x7fb8223855800x7fb803a24cc03037803037806553623592963514923936929615893949003452158939489673671589394933600815893949337345
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164137044137044419430425600824613760x7fb8223854000x7fb803a24d001624071624076553624248323716214154734415893949372444158939493360081589394961712815893949618529
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671370441370444194304256001224628480x7fb8223852800x7fb803a24d401680421680426553629491204393714917128815893949653958158939496171281589394990176915893949903482
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701370441370444194304256001224638080x7fb8223851000x7fb803a24d801623691623696553621626883218193605122015893949945491158939499017691589395019969015893950201196
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731370441370444194304256001224650240x7fb82014df800x7fb803a24dc03026423026426553626214403922844387239615893950237485158939501996901589395056769115893950569428
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761370441370444194304256001224662400x7fb82014de000x7fb803a24e002999732999736553624903683613844045712815893950604787158939505676911589395094865115893950950149
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179137044137044419430425600824674560x7fb82014dc800x7fb803a24e401630661630666553625559043815004269118815893950984448158939509486511589395123169215893951233263
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821370441370444194304256001224689280x7fb82014db000x7fb803a24e801768791768796553631457284713265286108815893951268582158939512316921589395152385315893951525346
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851370441370444194304256001224701440x7fb82014d9800x7fb803a24ec01611701611706553622282243331163728250015893951567095158939515238531589395180497315893951806520
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881370441370444194304256001224716160x7fb82014d8000x7fb803a24f003026173026176553627525124088854585203215893951841099158939518049731589395217377415893952175252
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911370441370444194304256001224728320x7fb82014d6800x7fb803a24f403007323007326553626214403927614397026415893952209941158939521737741589395254097515893952542643
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194137044137044419430425600824740480x7fb8223855000x7fb803a24f801616941616946553626869764020174503115215893952577313158939525409751589395282625615893952827757
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971370441370444194304256001224757760x7fb8223853800x7fb803a24fc01822511822516553633423364990845596470415893952862756158939528262561589395312401715893953125500
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001370441370444194304256001224769920x7fb8223852000x7fb803a250001611901611906553623592963489093909956815893953176759158939531240171589395341409715893953415754
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031370441370444194304256001224784640x7fb8223850800x7fb803a250403025553025556553628835844280004793053615893953450773158939534140971589395379729815893953798905
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061370441370444194304256001224799360x7fb82014df000x7fb803a250803023393023396553626869764027244508940815893953833815158939537972981589395416577915893954167317
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209137044137044419430425600824814080x7fb82014dd800x7fb803a250c01634041634046553628180484291654804206415893954202246158939541657791589395445314015893954454691
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121370441370444194304256001224831360x7fb82014dc000x7fb803a251001913451913456553635389445283515909196815893954489420158939544531401589395475506015893954756604
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151370441370444194304256001224843520x7fb82014da800x7fb803a251401614421614426553624248323583054016934815893954797983158939547550601589395504386115893955045408
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181370441370444194304256001224858240x7fb82014d9000x7fb803a251803024773024776553630146564578005133677615893955079297158939550438611589395542242215893955424059
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211370441370444194304256001224872960x7fb82014d7800x7fb803a251c02991732991736553628180484160164663277615893955459088158939554224221589395578738315893955789021
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241370441370444194304256001224887680x7fb82014d6000x7fb803a252001622941622946553629491204483505015931215893955823160158939557873831589395606866415893956070175
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271370441370444194304256001224907520x7fb8223854800x7fb803a252402022952022956553637355525630606307741215893956105344158939560686641589395637794415893956379518
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301370441370444194304256001224919680x7fb8223853000x7fb803a252801614981614986553625559043880674349972015893956421757158939563779441589395665890515893956660331
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331370441370444194304256001224934400x7fb8223851800x7fb803a252c03042533042536553631457284723155290058015893956695141158939566589051589395703090615893957032633
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361370441370444194304256001224949120x7fb8223850000x7fb803a253002997202997206553629491204331494842314415893957067712158939570309061589395739762715893957399095
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391370441370444194304256001224963840x7fb82014de800x7fb803a253401626261626266553630801924708985283338015893957432544158939573976271589395768018715893957681729
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421370441370444194304256001224983680x7fb82014dd000x7fb803a253802114742114746553639321605935976649272415893957715468158939576801871589395800018815893958001772
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451370441370444194304256001224995840x7fb82014db800x7fb803a253c01612371612376553626214403920384394050415893958043151158939580001881589395829218915893958294015
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024813704413704441943042560012241013120x7fb82014da000x7fb803a254002985542985546553632768004924325514426815893958328554158939582921891589395866739015893958668947
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025113704413704441943042560012241027840x7fb82014d8800x7fb803a254403007273007276553630801924611075163722415893958703856158939586673901589395903779115893959039738
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025413704413704441943042560012241042560x7fb82014d7000x7fb803a254801624961624966553632112644816675390435615893959074048158939590377911589395932019115893959321852
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025713704413704441943042560012241062400x7fb8223855800x7fb803a254c02183802183806553641287686112126840908415893959356041158939593201911589395963779215893959639515
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026013704413704441943042560012241077120x7fb8223854000x7fb803a255001609541609546553627525124144344644376415893959681754158939596377921589395992627315893959927878
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026313704413704441943042560016241094400x7fb8223852800x7fb803a255402966682966686553634078725062225672311615893959962018158939599262731589396029267415893960294510
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026613704413704441943042560016241111680x7fb8223851000x7fb803a255802998832998836553632112644753545328025215893960328680158939602926741589396066531415893960666822
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691370441370444194304256008241128960x7fb82014df800x7fb803a255c01617231617236553632768004907145503742415893960701571158939606653141589396095075515893960952446
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027213704413704441943042560012241151360x7fb82014de000x7fb803a256002292872292876553643253766422237205683615893960986405158939609507551589396127571615893961277238
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027513704413704441943042560012241166080x7fb82014dc800x7fb803a256401617311617316553628180484293054813699215893961318407158939612757161589396156355715893961565122
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027813704413704441943042560016241183360x7fb82014db000x7fb803a256802964322964326553635389445393906037332015893961598771158939615635571589396193203715893961933544
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028113704413704441943042560016241200640x7fb82014d9800x7fb803a256c02979112979116553634078725056985667094815893961968213158939619320371589396230867815893962310505
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028413704413704441943042560012241217920x7fb82014d8000x7fb803a257001633321633326553634078725128395738542815893962345165158939623086781589396259475915893962596269
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028713704413704441943042560012241240320x7fb82014d6800x7fb803a257402394972394976553645219846834597658150815893962630948158939625947591589396292724015893962928692
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029013704413704441943042560012241255040x7fb8223855000x7fb803a257801614581614586553630146564660365217661215893962970521158939629272401589396320852015893963210285
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029313704413704441943042560012241274880x7fb8223853800x7fb803a257c02976462976466553638010885791656487325615893963244065158939632085201589396358084115893963582677
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029613704413704441943042560012241292160x7fb8223852000x7fb803a258002978202978206553636700165524676191292415893963617746158939635808411589396395492215893963956649
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029913704413704441943042560012241309440x7fb8223850800x7fb803a258401697751697756553636700165470556120658415893963991438158939639549221589396424196315893964243842
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030213704413704441943042560012241334400x7fb82014df000x7fb803a258802593022593026553649152007503048399446015893964277822158939642419631589396458308415893964584575
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030513704413704441943042560012241349120x7fb82014dd800x7fb803a258c01609521609526553631457284745335317765615893964626344158939645830841589396487204415893964873748
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030813704413704441943042560012241368960x7fb82014dc000x7fb803a259002957792957796553640632326391017161273615893964910058158939648720441589396523956515893965241080
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031113704413704441943042560012241388800x7fb82014da800x7fb803a259402963222963226553639321606226956976536815893965275090158939652395651589396560708615893965608582
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031413704413704441943042560012241408640x7fb82014d9000x7fb803a259801783041783046553639321606008226725064415893965642031158939656070861589396590452715893965906186
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031713704413704441943042560012241436160x7fb82014d7800x7fb803a259c02788112788116553653084168014098961774815893965940175158939659045271589396626612815893966267798
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032013704413704441943042560012241453440x7fb82014d6000x7fb803a25a001620941620946553633423365029425634173615893966309937158939662661281589396656132815893966563061
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032313704413704441943042560012241475840x7fb8223854800x7fb803a25a402961802961806553643253766751197577685615893966597640158939665613281589396693316915893966934653
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032613704413704441943042560012241495680x7fb8223853000x7fb803a25a802962272962276553641943046282157029195615893966969102158939669331691589396730341015893967304884
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032913704413704441943042560012241515520x7fb8223851800x7fb803a25ac01859391859396553641943046241086996896415893967339234158939673034101589396760421115893967605858
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033213704413704441943042560012241543040x7fb8223850000x7fb803a25b002992962992966553657016328546659555335615893967639987158939676042111589396797637215893967977889
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033513704413704441943042560012241562880x7fb82014de800x7fb803a25b401719591719596553637355525695496378830015893968019878158939679763721589396827157215893968273163
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033813704413704441943042560012241587840x7fb82014dd000x7fb803a25b802973582973586553648496647387228273324015893968308862158939682715721589396864021315893968641834
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034113704413704441943042560012241610240x7fb82014db800x7fb803a25bc02979012979016553647185927143408011622015893968675974158939686402131589396901621415893969017676
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034413704413704441943042560012241632640x7fb82014da000x7fb803a25c002049562049566553647185927102457944662815893969051715158939690162141589396932789515893969329459
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034713704413704441943042560012241665280x7fb82014d8800x7fb803a25c4034023434023465536648806499279711122675615893969363648158939693278951589396972389615893969744550
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035013704413704441943042560012241685120x7fb82014d7000x7fb803a25c801858671858676553641287686286887040615215893969766689158939697238961589397003013715893970031633
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035313704413704441943042560012241712640x7fb8223855800x7fb803a25cc02979422979426553653739528823099882788415893970065563158939700301371589397040581815893970407705
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035613704413704441943042560012241737600x7fb8223854000x7fb803a25d002962592962596553652428808442679465391215893970443124158939704058181589397077845815893970780107
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035913704413704441943042560012241762560x7fb8223852800x7fb803a25d402253962253966553652428807782868730069215893970814616158939707784581589397110565915893971107159
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036213704413704441943042560012241797760x7fb8223851000x7fb803a25d80380803380803655367274496109657812275788415893971141259158939711056591589397153718015893971563599
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036513704413704441943042560012241822720x7fb82014df800x7fb803a25dc02107762107766553649152007489588385564015893971581959158939715371801589397186534115893971866852
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036813704413704441943042560012241855360x7fb82014de000x7fb803a25e00302696302696655366422528100622911266580415893971902042158939718653411589397224822215893972272433
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037113704413704441943042560012241885440x7fb82014dc800x7fb803a25e40310559310559655366291456102546311476056015893972282963158939722482221589397263862315893972658765
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037413704413704441943042560012241915520x7fb82014db000x7fb803a25e8026536626536665536629145697114210873165215893972674074158939726386231589397299670415893972998177
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037713704413704441943042560012241958400x7fb82014d9800x7fb803a25ec0462149462149655368847360134183415014210415893973031986158939729967041589397347398515893973491616
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038013704413704441943042560012241985920x7fb82014d8000x7fb803a25f002438822438826553657016328564509595122815893973516986158939734739851589397381142615893973812999
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038313704413704441943042560012242023680x7fb82014d6800x7fb803a25f40335468335468655367471104121172513567920415893973846938158939738114261589397420870715893974230120
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038613704413704441943042560012242058880x7fb8223855000x7fb803a25f80333817333817655367340032119055313329706815893974244149158939742087071589397462038715893974662690
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038913704413704441943042560012242094080x7fb8223853800x7fb803a25fc0306448306448655367340032111467412475428815893974673310158939746203871589397502182815893975023502
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039213704413704441943042560012242144640x7fb8223852000x7fb803a260005427665427666553610420224159093417819670415893975058341158939750218281589397554423015893975586799
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039513704413704441943042560012242177280x7fb8223850800x7fb803a2604027304627304665536648806499346911118722415893975605719158939755442301589397593191115893975933522
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039813704413704441943042560012242220160x7fb82014df000x7fb803a26080365242365242655368519680135509215173373615893975969601158939759319111589397634903215893976391511
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040113704413704441943042560012242260480x7fb82014dd800x7fb803a260c0367184367184655368388608134117115005242815893976402551158939763490321589397679527315893976837791
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040413704413704441943042560012242300800x7fb82014dc000x7fb803a26100347338347338655368388608127923214314451615893976848781158939767952731589397722151415893977264112
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040713704413704441943042560012242359040x7fb82014da800x7fb803a261406234066234066553611993088182907620479214015893977274452158939772215141589397782343515893977841189
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041013704413704441943042560012242394240x7fb82014d9000x7fb803a26180303922303922655367274496111949812538806815893977866698158939778234351589397820535615893978207371
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041313704413704441943042560012242442240x7fb82014d7800x7fb803a261c0398810398810655369568256153094617153304015893978241580158939782053561589397865111715893978699110
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041613704413704441943042560012242487680x7fb82014d6000x7fb803a26200390815390815655369437184147807216560810015893978709550158939786511171589397911591815893979158420
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041913704413704441943042560012242533120x7fb8223854800x7fb803a26240387696387696655369437184146048316353429215893979168849158939791159181589397956791915893979609879
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221370441370444194304256008242555520x7fb8223853000x7fb803a262807184727184726553616056320230365725810466015893979620399158939795679191589398023528115893980277975
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042513704413704441943042560012242598400x7fb8223851800x7fb803a262c0365032365032655368847360136488115271485215893980296674158939802352811589398067832215893980721165
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042813704413704441943042560012242656640x7fb8223850000x7fb803a263004704204704206553611665408187842721037439615893980732344158939806783221589398119304315893981235023
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043113704413704441943042560012242712320x7fb82014de800x7fb803a263404718984718986553611468800183546020557041615893981245043158939811930431589398170664415893981749282
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341370441370444194304256008242732160x7fb82014dd000x7fb803a263804825484825486553614090240201863122614968815893981759871158939817066441589398222392615893982269390
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371370441370444194304256008242757120x7fb82014db800x7fb803a263c08799048799046553619202048275847830875929615893982279950158939822239261589398300280715893983047003
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044013704413704441943042560012242807680x7fb82014da000x7fb803a264004273664273666553610420224160746218002383215893983065862158939830028071589398348568815893983528642
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044313704413704441943042560012242876160x7fb82014d8800x7fb803a264405483465483466553613762560215085424087193615893983539372158939834856881589398405081015893984093360
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044613704413704441943042560012242942080x7fb82014d7000x7fb803a264805533245533246553613565952219812824617411615893984104149158939840508101589398461657115893984659577
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491370441370444194304256008242969600x7fb8223855800x7fb803a264c05642985642986553615466496222989524974435615893984669417158939846165711589398518201315893985225515
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521370441370444194304256008242999680x7fb8223854000x7fb803a26500104164210416426553622347776321170435965223215893985236534158939851820131589398605593515893986103375
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551370441370444194304256008243027200x7fb8223852800x7fb803a265407226527226526553620250624291051532592207615893986121875158939860559351589398672777615893986772510
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045813704413704441943042560012243054720x7fb8223851000x7fb803a265807242487242486553620447232293945732934879215893986783230158939867277761589398741417815893987458395
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046113704413704441943042560012243082240x7fb82014df800x7fb803a265c07213207213206553619595264282031431567417615893987468625158939874141781589398810249915893988144679
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641370441370444194304256008243109760x7fb82014de000x7fb803a266007277927277926553620381696293055632838278415893988155409158939881024991589398876618115893988808565
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671370441370444194304256008243132160x7fb82014dc800x7fb803a26640136681013668106553631522816451726550571754815893988819364158939887660181589398984938015893989896600
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701370441370444194304256008243159680x7fb82014db000x7fb803a26680137097413709746553638993920558681262584871615893989915200158939898493801589399092090215893990991446
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047313704413704441943042560012243187200x7fb82014d9800x7fb803a266c0137224213722426553639124992560591262818015615893991002286158939909209021589399205402415893992121531
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047613704413704441943042560012243214720x7fb82014d8000x7fb803a26700137225113722516553638469632552193861829223215893992132340158939920540241589399319162615893993257935
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791370441370444194304256008243242240x7fb82014d6800x7fb803a26740137517013751706553639059456559821062706993215893993269045158939931916261589399430458915893994372410
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821370441370444194304256008243264640x7fb8223855000x7fb803a26780266512626651266553660489728864658796902126415893994384240158939943045891589399627275315893996339556
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851370441370444194304256008243292160x7fb8223853800x7fb803a267c026693372669337655367726694411058220123833336415893996357936158939962727531589399819515715893998264693
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048813704413704441943042560012243319680x7fb8223852000x7fb803a2680026718182671818655367739801611072367124018903215893998276603158939981951571589400018460115894000257619
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049113704413704441943042560012243347200x7fb8223850800x7fb803a2684026682452668245655367621836810912402122196904015894000268649158940001846011589400216412515894002232905
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941370441370444194304256008243374720x7fb82014df000x7fb803a2688026751222675122655367733248011062306123923752815894002244485158940021641251589400410092915894004172362
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049713704413704441943042560082400x7fb82014dd800x7fb803a268c0525728352572836553612025856017195740192575214415894004183412158940041009291589400771837615894007789881