Files
rocm-systems/tests/workloads/Axes1/mi200/SQ_INST_LEVEL_SMEM.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

41 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_SMEMSQ_INST_LEVEL_SMEMSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000199978199978335544322560043241600x00x7fe1d2a042803670016304045234032189617229574411755172240268515851722972383723717229723948727
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00219997819997832768256001224138880x00x7fe1d2a23f80512975981094899217229729109777172297238372371722972923564117229729240263
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051999781999784194304256001224143360x7fe1d5a503800x7fe1d2a23fc0655366197146939478417229729274252172297292356411722972959564117229729597774
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081999781999784194304256001624150400x7fe1d5a502000x7fe1d2a24000655366503187287980817229729633863172297295956411722972999788117229729999983
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111999781999784194304256001624154880x7fe1d5a500800x7fe1d2a24040655366605407384161617229730033752172297299978811722973040540217229730407522
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141999781999784194304256001224159360x7fe1d32edf000x7fe1d2a24080655366515247295841617229730439761172297304054021722973071228217229730714413
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171999781999784194304256001224163840x7fe1d32edd800x7fe1d2a240c0655366217626962907217229730746023172297307122821722973101628217229731018485
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201999781999784194304256001224170880x7fe1d32edc000x7fe1d2a241001310726580367378504817229731061514172297310162821722973131868217229731320617
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231999781999784194304256001624177920x7fe1d32eda800x7fe1d2a241401310726927147762496017229731352936172297313186821722973170540317229731707457
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261999781999784194304256001624184960x7fe1d32ed9000x7fe1d2a24180655366577947381688817229731738516172297317054031722973209228317229732094766
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291999781999784194304256001624192000x7fe1d32ed7800x7fe1d2a241c01310726968687811181617229732125465172297320922831722973240508317229732407348
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321999781999784194304256001624199040x7fe1d32ed6000x7fe1d2a242001310726889847708972017229732439337172297324050831722973270524317229732707560
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351999781999784194304256001224206080x7fe1d5a504800x7fe1d2a242401310726975727820535217229732747848172297327052431722973300508417229733007491
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381999781999784194304256001624213120x7fe1d5a503000x7fe1d2a242801310726996867831512017229733039281172297330050841722973339228417229733394351
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411999781999784194304256001624220160x7fe1d5a501800x7fe1d2a242c0655366611367406004017229733425900172297333922841722973378108417229733783221
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441999781999784194304256001624227200x7fe1d5a500000x7fe1d2a243001310726927747757580817229733814700172297337810841722973408140517229734103252
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471999781999784194304256001224234240x7fe1d32ede800x7fe1d2a243401310726960027798230417229734116062172297340814051722973440076517229734403004
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501999781999784194304256001224241280x7fe1d32edd000x7fe1d2a243801310726948707778042417229734442153172297344007651722973470348517229734705525
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531999781999784194304256001624248320x7fe1d32edb800x7fe1d2a243c01310726931427761222417229734737245172297347034851722973507884517229735080325
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561999781999784194304256001624255360x7fe1d32eda000x7fe1d2a24400655366321227073988817229735111904172297350788451722973544252617229735444085
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591999781999784194304256001224262400x7fe1d32ed8800x7fe1d2a244401310726965147811588817229735474235172297354425261722973571340617229735714958
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621999781999784194304256001224269440x7fe1d32ed7000x7fe1d2a244801310726971227807346417229735745907172297357134061722973598892617229735990371
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651999781999784194304256001224276480x7fe1d5a505800x7fe1d2a244c01310726562607345876817229736028670172297359889261722973626796617229736269463
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681999781999784194304256001624286080x7fe1d5a504000x7fe1d2a245001310726940927772942417229736300782172297362679661722973662812717229736629553
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711999781999784194304256001624293120x7fe1d5a502800x7fe1d2a24540655366534807312003217229736661042172297366281271722973698780717229736989253
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741999781999784194304256001224300160x7fe1d5a501000x7fe1d2a245801310726516547296352017229737021073172297369878071722973725932717229737260826
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077199978199978419430425600824309760x7fe1d32edf800x7fe1d2a245c01310726766387586201617229737292915172297372593271722973753628717229737537729
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801999781999784194304256001224316800x7fe1d32ede000x7fe1d2a246001310726974087815796817229737575827172297375362871722973780972817229737811211
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831999781999784194304256001624326400x7fe1d32edc800x7fe1d2a246401310726514907295389617229737842360172297378097281722973817180817229738173581
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861999781999784194304256001224336000x7fe1d32edb000x7fe1d2a24680655366475707253061617229738204170172297381718081722973853868817229738540131
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891999781999784194304256001224345600x7fe1d32ed9800x7fe1d2a246c01310726953367788232817229738570871172297385386881722973881292817229738814384
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092199978199978419430425600824355200x7fe1d32ed8000x7fe1d2a247001310726923927756748017229738845563172297388129281722973908732917229739088797
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951999781999784194304256001224362240x7fe1d32ed6800x7fe1d2a247401310726869967702899217229739127145172297390873291722973936540917229739366779
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981999781999784194304256001224371840x7fe1d5a505000x7fe1d2a247801310726508527289107217229739397518172297393654091722973972620917229739727719
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011999781999784194304256001224381440x7fe1d5a503800x7fe1d2a247c0655366525327309475217229739759308172297397262091722974008508917229740086490
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041999781999784194304256001224391040x7fe1d5a502000x7fe1d2a248001310726882187713692817229740117329172297400850891722974035821017229740359662
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107199978199978419430425600824403200x7fe1d5a500800x7fe1d2a248401310726898547724072817229740391301172297403582101722974063069017229740632135
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101999781999784194304256001224412800x7fe1d32edf000x7fe1d2a248801310726986127818310417229740670384172297406306901722974090797017229740909567
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131999781999784194304256001224422400x7fe1d32edd800x7fe1d2a248c01310726887327720593617229740939887172297409079701722974128349017229741285027
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161999781999784194304256001224432000x7fe1d32edc000x7fe1d2a24900655366433607208484817229741316056172297412834901722974164493117229741646397
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119199978199978419430425600824441600x7fe1d32eda800x7fe1d2a249401310726943127783532817229741677187172297416449311722974191757117229741919010
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221999781999784194304256001224453760x7fe1d32ed9000x7fe1d2a249801310726905127734424817229741949439172297419175711722974220333117229742204862
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251999781999784194304256001224463360x7fe1d32ed7800x7fe1d2a249c01310726943447780759217229742242981172297422033311722974248717117229742488715
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281999781999784194304256001224475520x7fe1d32ed6000x7fe1d2a24a001310726994567833870417229742520354172297424871711722974284813217229742849545
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311999781999784194304256001224485120x7fe1d5a504800x7fe1d2a24a40655366551707344870417229742881104172297428481321722974320525217229743206795
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134199978199978419430425600824494720x7fe1d5a503000x7fe1d2a24a801310726574207366989617229743238224172297432052521722974347837217229743479828
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371999781999784194304256001224506880x7fe1d5a501800x7fe1d2a24ac01310726555347326202417229743511727172297434783721722974374909217229743750621
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401999781999784194304256001224516480x7fe1d5a500000x7fe1d2a24b001310726534627329148817229743789280172297437490921722974403373217229744035243
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431999781999784194304256001224528640x7fe1d32ede800x7fe1d2a24b401310727012367851234417229744067372172297440337321722974439277317229744394223
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461999781999784194304256001224540800x7fe1d32edd000x7fe1d2a24b80655366517407296363217229744425492172297443927731722974475085317229744752374
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149199978199978419430425600824552960x7fe1d32edb800x7fe1d2a24bc01310726909707744442417229744783923172297447508531722974502333317229745024756
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521999781999784194304256001224567680x7fe1d32eda000x7fe1d2a24c001310726918947757794417229745055765172297450233331722974529789317229745299439
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551999781999784194304256001224577280x7fe1d32ed8800x7fe1d2a24c401310726903327726791217229745337298172297452978931722974557085417229745572301
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581999781999784194304256001224589440x7fe1d32ed7000x7fe1d2a24c801310726500307278544817229745603361172297455708541722974593005417229745931472
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611999781999784194304256001224601600x7fe1d5a505800x7fe1d2a24cc0655366482147265844017229745962451172297459300541722974629773417229746299172
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164199978199978419430425600824613760x7fe1d5a504000x7fe1d2a24d001310726940887766571217229746330791172297462977341722974657709517229746578664
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671999781999784194304256001224628480x7fe1d5a502800x7fe1d2a24d401310726972367808118417229746610213172297465770951722974685757517229746859106
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701999781999784194304256001224638080x7fe1d5a501000x7fe1d2a24d801310726914327748247217229746898285172297468575751722974713133517229747132849
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731999781999784194304256001224650240x7fe1d32edf800x7fe1d2a24dc01310726471607239672817229747164348172297471313351722974748781517229747489279
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761999781999784194304256001224662400x7fe1d32ede000x7fe1d2a24e00655366222866967818417229747520279172297474878151722974784541617229747846890
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179199978199978419430425600824674560x7fe1d32edc800x7fe1d2a24e401310726957087797376817229747877299172297478454161722974811789617229748119392
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821999781999784194304256001224689280x7fe1d32edb000x7fe1d2a24e801310726929247769284817229748150211172297481178961722974839933617229748400855
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851999781999784194304256001224701440x7fe1d32ed9800x7fe1d2a24ec01310726544027318531217229748438944172297483993361722974867389617229748675347
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881999781999784194304256001224716160x7fe1d32ed8000x7fe1d2a24f001310727031787874142417229748706376172297486738961722974903469617229749036317
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911999781999784194304256001224728320x7fe1d32ed6800x7fe1d2a24f40655366583767376275217229749067076172297490346961722974939549717229749396898
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194199978199978419430425600824740480x7fe1d5a505000x7fe1d2a24f801310726541887316432017229749427517172297493954971722974967261717229749674240
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971999781999784194304256001224757760x7fe1d5a503800x7fe1d2a24fc01310726519987305289617229749704559172297496726171722974996061717229749962062
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001999781999784194304256001224769920x7fe1d5a502000x7fe1d2a250001310726934487770836017229750000561172297499606171722975024829717229750250064
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031999781999784194304256001224784640x7fe1d5a500800x7fe1d2a250401310726983587813225617229750280964172297502482971722975061069817229750612285
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061999781999784194304256001224799360x7fe1d32edf000x7fe1d2a25080655366560227348931217229750644654172297506106981722975096925817229750970705
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209199978199978419430425600824814080x7fe1d32edd800x7fe1d2a250c01310726876567707520817229751001264172297509692581722975124141817229751242788
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121999781999784194304256001224831360x7fe1d32edc000x7fe1d2a251001310726948167785568817229751273967172297512414181722975153661817229751538090
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151999781999784194304256001224843520x7fe1d32eda800x7fe1d2a251401310727231268099357617229751588728172297515366181722975181597917229751817492
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181999781999784194304256001224858240x7fe1d32ed9000x7fe1d2a251801310726954907793452017229751847561172297518159791722975217917917229752180572
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211999781999784194304256001224872960x7fe1d32ed7800x7fe1d2a251c0655366653047453098417229752211071172297521791791722975254509917229752546532
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241999781999784194304256001224887680x7fe1d32ed6000x7fe1d2a252001310726900027728980817229752577211172297525450991722975281741917229752818915
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271999781999784194304256001224907520x7fe1d5a504800x7fe1d2a252401310726909727739806417229752849594172297528174191722975311646017229753117937
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301999781999784194304256001224919680x7fe1d5a503000x7fe1d2a252801310726937827770043217229753155996172297531164601722975338990017229753391319
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331999781999784194304256001224934400x7fe1d5a501800x7fe1d2a252c01310726807587621861617229753421929172297533899001722975375118017229753752650
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361999781999784194304256001224949120x7fe1d5a500000x7fe1d2a25300655366587887372133617229753785469172297537511801722975411758117229754119130
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391999781999784194304256001224963840x7fe1d32ede800x7fe1d2a253401310726919427755405617229754150369172297541175811722975439694117229754398312
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421999781999784194304256001224983680x7fe1d32edd000x7fe1d2a253801310726887587718788017229754428951172297543969411722975470510117229754706604
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451999781999784194304256001224995840x7fe1d32edb800x7fe1d2a253c01310726911047737246417229754744113172297547051011722975498126117229754982856
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024819997819997841943042560012241013120x7fe1d32eda000x7fe1d2a254001310726496387273373617229755013586172297549812611722975534846117229755349957
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025119997819997841943042560012241027840x7fe1d32ed8800x7fe1d2a25440655366579007365104817229755380396172297553484611722975571150217229755713037
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025419997819997841943042560012241042560x7fe1d32ed7000x7fe1d2a254801310727030287874284017229755743076172297557115021722975598750217229755988979
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025719997819997841943042560012241062400x7fe1d5a505800x7fe1d2a254c01310726536187334405617229756019558172297559875021722975629838217229756299841
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026019997819997841943042560012241077120x7fe1d5a504000x7fe1d2a255001310726427847197993617229756337770172297562983821722975657726217229756578843
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026319997819997841943042560016241094400x7fe1d5a502800x7fe1d2a255401310727113607961348017229756610223172297565772621722975693582317229756937314
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026619997819997841943042560016241111680x7fe1d5a501000x7fe1d2a25580655366480647261381617229756968403172297569358231722975729470317229757296194
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691999781999784194304256008241128960x7fe1d32edf800x7fe1d2a255c01310726950147774840017229757326353172297572947031722975756990317229757571307
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027219997819997841943042560012241151360x7fe1d32ede000x7fe1d2a256001310726869587702911217229757601606172297575699031722975788910417229757890628
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027519997819997841943042560012241166080x7fe1d32edc800x7fe1d2a256401310726926307768010417229757928397172297578891041722975816670417229758168340
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027819997819997841943042560016241183360x7fe1d32edb000x7fe1d2a256801310726947747790012017229758198560172297581667041722975853950417229758541150
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028119997819997841943042560016241200640x7fe1d32ed9800x7fe1d2a256c0655366488327266361617229758571899172297585395041722975889710417229758898601
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028419997819997841943042560012241217920x7fe1d32ed8000x7fe1d2a257001310726996487838587217229758929200172297588971041722975917230517229759173773
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028719997819997841943042560012241240320x7fe1d32ed6800x7fe1d2a257401310726888947715849617229759204292172297591723051722975949326517229759494544
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029019997819997841943042560012241255040x7fe1d5a505000x7fe1d2a257801310727026527875502417229759532313172297594932651722975976462517229759766167
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029319997819997841943042560012241274880x7fe1d5a503800x7fe1d2a257c01310726939647773377617229759797796172297597646251722976012142517229760122967
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029619997819997841943042560012241292160x7fe1d5a502000x7fe1d2a25800655366620767410983217229760154256172297601214251722976047998617229760481618
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029919997819997841943042560012241309440x7fe1d5a500800x7fe1d2a258401310726489447263978417229760513127172297604799861722976075822617229760759580
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030219997819997841943042560012241334400x7fe1d32edf000x7fe1d2a258801310726555807338317617229760790439172297607582261722976109086617229761092411
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030519997819997841943042560012241349120x7fe1d32edd800x7fe1d2a258c0131072102922811550148817229761131190172297610908661722976137086617229761372383
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030819997819997841943042560012241368960x7fe1d32edc000x7fe1d2a259001310726587687373702417229761402583172297613708661722976173342717229761735133
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031119997819997841943042560012241388800x7fe1d32eda800x7fe1d2a25940655366566087335402417229761765903172297617334271722976209134717229762093114
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031419997819997841943042560012241408640x7fe1d32ed9000x7fe1d2a259801310726998787835934417229762123673172297620913471722976238126717229762382796
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031719997819997841943042560012241436160x7fe1d32ed7800x7fe1d2a259c01310726925107754680017229762412755172297623812671722976272830717229762729827
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032019997819997841943042560012241453440x7fe1d32ed6000x7fe1d2a25a00131072103139011554109617229762768226172297627283071722976300286817229763004429
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032319997819997841943042560012241475840x7fe1d5a504800x7fe1d2a25a401310726890147723896017229763034908172297630028681722976336638817229763367859
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032619997819997841943042560012241495680x7fe1d5a503000x7fe1d2a25a80655366478627266493617229763399298172297633663881722976372750817229763729040
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032919997819997841943042560012241515520x7fe1d5a501800x7fe1d2a25ac01310726779727591520817229763759869172297637275081722976401806817229764019522
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033219997819997841943042560012241543040x7fe1d5a500000x7fe1d2a25b001310726551587329708017229764050841172297640180681722976438526917229764386732
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033519997819997841943042560012241562880x7fe1d32ede800x7fe1d2a25b4013107297943810978013617229764425461172297643852691722976466782917229764669154
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033819997819997841943042560012241587840x7fe1d32edd000x7fe1d2a25b801310727496568389567217229764699523172297646678291722976503150917229765033024
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034119997819997841943042560012241610240x7fe1d32edb800x7fe1d2a25bc0655366558367338077617229765063114172297650315091722976539502917229765396425
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034419997819997841943042560012241632640x7fe1d32eda000x7fe1d2a25c001310726540927328587217229765426734172297653950291722976569583017229765697276
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034719997819997841943042560012241665280x7fe1d32ed8800x7fe1d2a25c401310726532587308417617229765727446172297656958301722976608303017229766106585
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035019997819997841943042560012241685120x7fe1d32ed7000x7fe1d2a25c80131072102969211522185617229766125805172297660830301722976638911017229766390578
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035319997819997841943042560012241712640x7fe1d5a505800x7fe1d2a25cc01310726575027361845617229766420967172297663891101722976675247117229766753848
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035619997819997841943042560012241737600x7fe1d5a504000x7fe1d2a25d00655366604307387312817229766784717172297667524711722976712143117229767122838
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035919997819997841943042560012241762560x7fe1d5a502800x7fe1d2a25d401310726744327557238417229767153587172297671214311722976744447117229767445949
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036219997819997841943042560012241797760x7fe1d5a501000x7fe1d2a25d801310726739067544107217229767476208172297674444711722976786143117229767881467
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036519997819997841943042560012241822720x7fe1d32edf800x7fe1d2a25dc013107298180010994234417229767901777172297678614311722976817727217229768178769
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036819997819997841943042560012241855360x7fe1d32ede000x7fe1d2a25e001310726907587737243217229768210099172297681772721722976855071217229768570789
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037119997819997841943042560012241885440x7fe1d32edc800x7fe1d2a25e40655366599467390100817229768583418172297685507121722976893263217229768949579
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037419997819997841943042560012241915520x7fe1d32edb000x7fe1d2a25e801310726587827385122417229768965188172297689326321722976927887317229769280260
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037719997819997841943042560012241958400x7fe1d32ed9800x7fe1d2a25ec01310726477047256740817229769310839172297692788731722976974207317229769759407
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038019997819997841943042560012241985920x7fe1d32ed8000x7fe1d2a25f00131072102804411506471217229769784646172297697420731722977008031317229770081958
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038319997819997841943042560012242023680x7fe1d32ed6800x7fe1d2a25f4013107297323810898421617229770112147172297700803131722977047071417229770487457
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038619997819997841943042560012242058880x7fe1d5a505000x7fe1d2a25f80655366552887345332817229770503197172297704707141722977086783417229770885196
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038919997819997841943042560012242094080x7fe1d5a503800x7fe1d2a25fc01310726670307475037617229770900176172297708678341722977123999417229771241506
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039219997819997841943042560012242144640x7fe1d5a502000x7fe1d2a260001310726522707309172017229771272126172297712399941722977175263517229771770542
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039519997819997841943042560012242177280x7fe1d5a500800x7fe1d2a26040131072103728611597706417229771793031172297717526351722977211055517229772111913
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039819997819997841943042560012242220160x7fe1d32edf000x7fe1d2a26080131072104821011758034417229772143032172297721105551722977252015517229772536881
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040119997819997841943042560012242260480x7fe1d32edd800x7fe1d2a260c0655366548947336643217229772553831172297725201551722977293519517229772952460
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040419997819997841943042560012242300800x7fe1d32edc000x7fe1d2a261001310726654487455600017229772967760172297729351951722977333215617229773349379
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040719997819997841943042560012242359040x7fe1d32eda800x7fe1d2a261401310726986027822881617229773365059172297733321561722977390271617229773919264
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041019997819997841943042560012242394240x7fe1d32ed9000x7fe1d2a26180131072102557211481578417229773941983172297739027161722977427295717229774274564
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041319997819997841943042560012242442240x7fe1d32ed7800x7fe1d2a261c013107299169811084108817229774305373172297742729571722977471183717229774757221
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041619997819997841943042560012242487680x7fe1d32ed6000x7fe1d2a26200655366531267315976817229774768521172297747118371722977517327717229775214729
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041919997819997841943042560012242533120x7fe1d5a504800x7fe1d2a262401310726584247369491217229775226108172297751732771722977561935817229775660587
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221999781999784194304256008242555520x7fe1d5a503000x7fe1d2a26280131072103075411555016017229775671386172297756193581722977629215817229776334988
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042519997819997841943042560012242598400x7fe1d5a501800x7fe1d2a262c0131072102039011436510417229776353308172297762921581722977672511817229776766297
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042819997819997841943042560012242656640x7fe1d5a500000x7fe1d2a2630013107298172010967236017229776777566172297767251181722977723199917229777272883
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043119997819997841943042560012242712320x7fe1d32ede800x7fe1d2a26340655366558767348752017229777284863172297772319991722977773887917229777756560
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341999781999784194304256008242732160x7fe1d32edd000x7fe1d2a2638013107298612211043216817229777771220172297777388791722977822080017229778265086
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371999781999784194304256008242757120x7fe1d32edb800x7fe1d2a263c0131072102080411472454417229778275936172297782208001722977899456017229779037965
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044019997819997841943042560012242807680x7fe1d32eda000x7fe1d2a2640013107298989011075736817229779057215172297789945601722977947680117229779518252
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044319997819997841943042560012242876160x7fe1d32ed8800x7fe1d2a26440131072103760411595845617229779529302172297794768011722978003376117229780075157
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044619997819997841943042560012242942080x7fe1d32ed7000x7fe1d2a26480655366911107741400817229780087117172297800337611722978058976217229780631282
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491999781999784194304256008242969600x7fe1d5a505800x7fe1d2a264c013107295450010715600817229780642192172297805897621722978114368217229781184837
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521999781999784194304256008242999680x7fe1d5a504000x7fe1d2a26500131072103553211629040017229781195507172297811436821722978201056317229782052583
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551999781999784194304256008243027200x7fe1d5a502800x7fe1d2a26540131072102371211467006417229782071263172297820105631722978267376317229782717285
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045819997819997841943042560012243054720x7fe1d5a501000x7fe1d2a26580131072103312411560277617229782727805172297826737631722978334864417229783389767
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046119997819997841943042560012243082240x7fe1d32edf800x7fe1d2a265c0655366573707359175217229783401007172297833486441722978401872417229784059619
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641999781999784194304256008243109760x7fe1d32ede000x7fe1d2a26600131072103258011570843217229784070059172297840187241722978468000517229784720851
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671999781999784194304256008243132160x7fe1d32edc800x7fe1d2a26640131072103119611586314417229784731231172297846800051722978576384617229785804932
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701999781999784194304256008243159680x7fe1d32edb000x7fe1d2a26680131072102907211505407217229785826221172297857635631722978683252317229786881313
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047319997819997841943042560012243187200x7fe1d32ed9800x7fe1d2a266c0131072102127611463595217229786892063172297868325231722978793556317229787999693
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047619997819997841943042560012243214720x7fe1d32ed8000x7fe1d2a26700655366445847213541617229788010422172297879355631722978906164317229789125802
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791999781999784194304256008243242240x7fe1d32ed6800x7fe1d2a26740131072101893211436670417229789136902172297890616431722979016436317229790229782
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821999781999784194304256008243264640x7fe1d5a505000x7fe1d2a26780131072101563011380912817229790241082172297901643631722979211380417229792177919
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851999781999784194304256008243292160x7fe1d5a503800x7fe1d2a267c0131072107801612053545617229792196739172297921138041722979402660417229794104317
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048819997819997841943042560012243319680x7fe1d5a502000x7fe1d2a26800131072102462411458572817229794115877172297940266041722979602212517229796096693
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049119997819997841943042560012243347200x7fe1d5a500800x7fe1d2a26840655366559847335723217229796107923172297960221251722979800148517229798066830
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941999781999784194304256008243374720x7fe1d32edf000x7fe1d2a26880131072106281411904812017229798084779172297980014851722980009908617229800169393
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049719997819997841943042560082400x7fe1d32edd800x7fe1d2a268c0131072102530011490227217229800180823172298000990861722980371588717229803767726