Files
rocm-systems/tests/workloads/Axes2/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.kd000207917207917335544322560043241600x00x7ff54c204280524288549000361488870417354329285041173520751522621735447664992217354476742662
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00220791720791732768256001224138880x00x7ff54c223f80409638964435938817354481900826173544766499221735448202864517354482033612
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0052079172079174194304256001224143360x7ff56a9d13800x7ff54c223fc052428810857982121604420817354482068181173544820286451735448241200517354482414992
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0082079172079174194304256001624150400x7ff56a9d12000x7ff54c22400052428811440844128135388817354482451201173544824120051735448282432517354482826771
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00112079172079174194304256001624154880x7ff56a9d10800x7ff54c22404052428811563274129506335217354482858941173544828243251735448322160617354483224051
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00142079172079174194304256001224159360x7ff568331f000x7ff54c22408052428810915927122254674417354483256080173544832216061735448353680617354483539213
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00172079172079174194304256001224163840x7ff568331d800x7ff54c2240c052428810662008119416969217354483570782173544835368061735448385024617354483852814
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00202079172079174194304256001224170880x7ff568331c000x7ff54c22410052428810973678122901693617354483895843173544838502461735448416592617354484168406
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00232079172079174194304256001624177920x7ff568331a800x7ff54c22414052428811527675129108897217354484199805173544841659261735448456416617354484566656
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00262079172079174194304256001624184960x7ff5683319000x7ff54c22418052428811527101129100604817354484596665173544845641661735448496144717354484963925
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00292079172079174194304256001624192000x7ff5683317800x7ff54c2241c052428811200150125440866417354484994414173544849614471735448528112717354485283697
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00322079172079174194304256001624199040x7ff5683316000x7ff54c22420052428811034518123582908017354485314786173544852811271735448558672717354485589099
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00352079172079174194304256001224206080x7ff56a9d14800x7ff54c22424052428811173012125134250817354485628148173544855867271735448589184717354485894371
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00382079172079174194304256001624213120x7ff56a9d13000x7ff54c22428052428811622798130171730817354485925970173544858918471735448629936717354486301990
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00412079172079174194304256001624220160x7ff56a9d11800x7ff54c2242c052428811442532128150693617354486333409173544862993671735448670160817354486703399
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00442079172079174194304256001624227200x7ff56a9d10000x7ff54c22430052428811364325127277082817354486734538173544867016081735448698560817354486987322
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00472079172079174194304256001224234240x7ff568331e800x7ff54c22434052428810924955122356641217354487017751173544869856081735448726800817354487269924
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00502079172079174194304256001224241280x7ff568331d000x7ff54c22438052428811238357125866728817354487307143173544872680081735448754912817354487550917
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00532079172079174194304256001624248320x7ff568331b800x7ff54c2243c052428811439307128121592417354487582766173544875491281735448791616817354487918087
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00562079172079174194304256001624255360x7ff568331a000x7ff54c22440052428811474076128506804817354487948296173544879161681735448829088917354488292747
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00592079172079174194304256001224262400x7ff5683318800x7ff54c22444052428810853660121561272817354488323457173544882908891735448857360917354488575600
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00622079172079174194304256001224269440x7ff5683317000x7ff54c22448052428811131606124668024017354488606069173544885736091735448885440917354488856263
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00652079172079174194304256001224276480x7ff56a9d15800x7ff54c2244c052428811001424123216891617354488893692173544888544091735448913504917354489136925
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00682079172079174194304256001624286080x7ff56a9d14000x7ff54c22450052428811317552126754850417354489167874173544891350491735448950160917354489503575
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00712079172079174194304256001624293120x7ff56a9d12800x7ff54c22454052428811508613128891609617354489534455173544895016091735448987393017354489875816
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00742079172079174194304256001224300160x7ff56a9d11000x7ff54c22458052428810981444122991770417354489906525173544898739301735449015297017354490155418
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077207917207917419430425600824309760x7ff568331f800x7ff54c2245c052428810421587116714158417354490185858173544901529701735449043633017354490438301
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00802079172079174194304256001224316800x7ff568331e000x7ff54c22460052428811185337125276076017354490476260173544904363301735449071441017354490716254
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00832079172079174194304256001624326400x7ff568331c800x7ff54c22464052428811501667128816488817354490746123173544907144101735449108513017354491086894
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00862079172079174194304256001224336000x7ff568331b000x7ff54c22468052428811400002127679069217354491117613173544910851301735449144833117354491450244
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00892079172079174194304256001224345600x7ff5683319800x7ff54c2246c052428810727380120142927217354491481423173544914483311735449172737117354491729177
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092207917207917419430425600824355200x7ff5683318000x7ff54c22470052428810157877113763592417354491759816173544917273711735449200625117354492008180
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00952079172079174194304256001224362240x7ff5683316800x7ff54c22474052428810859785121627071217354492045729173544920062511735449228305117354492284932
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00982079172079174194304256001224371840x7ff56a9d15000x7ff54c22478052428811513943128955841617354492316541173544922830511735449264801117354492649833
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001012079172079174194304256001224381440x7ff56a9d13800x7ff54c2247c052428811439502128120517617354492680972173544926480111735449301537217354493017323
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001042079172079174194304256001224391040x7ff56a9d12000x7ff54c22480052428810467232117229750817354493048442173544930153721735449329169217354493293596
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107207917207917419430425600824403200x7ff56a9d10800x7ff54c2248405242889840371110210995617354493325715173544932916921735449357169217354493573438
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001102079172079174194304256001224412800x7ff568331f000x7ff54c22488052428810625621119008561617354493612277173544935716921735449385441217354493856241
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001132079172079174194304256001224422400x7ff568331d800x7ff54c2248c052428811513491128950381617354493887880173544938544121735449422097217354494222961
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001162079172079174194304256001224432000x7ff568331c000x7ff54c22490052428811452299128262934417354494254810173544942209721735449458993317354494591751
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119207917207917419430425600824441600x7ff568331a800x7ff54c22494052428810646810119242367617354494622901173544945899331735449487137317354494873114
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001222079172079174194304256001224453760x7ff5683319000x7ff54c2249805242889780940109547954817354494904353173544948713731735449515041317354495152246
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001252079172079174194304256001224463360x7ff5683317800x7ff54c2249c052428810705375119901719617354495190375173544951504131735449543473317354495436549
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001282079172079174194304256001224475520x7ff5683316000x7ff54c224a0052428811446343128195910417354495468008173544954347331735449579937317354495801219
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001312079172079174194304256001224485120x7ff56a9d14800x7ff54c224a4052428811401805127698334017354495833638173544957993731735449616401417354496165930
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134207917207917419430425600824494720x7ff56a9d13000x7ff54c224a8052428810575191118449122417354496197009173544961640141735449644209417354496443832
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001372079172079174194304256001224506880x7ff56a9d11800x7ff54c224ac05242889138510102347661617354496475331173544964420941735449673073417354496732525
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001402079172079174194304256001224516480x7ff56a9d10000x7ff54c224b0052428810673787119541182817354496771244173544967307341735449700833417354497010197
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001432079172079174194304256001224528640x7ff568331e800x7ff54c224b4052428811388099127541782417354497040816173544970083341735449737617417354497378067
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001462079172079174194304256001224540800x7ff568331d000x7ff54c224b8052428811207260125513500817354497408337173544973761741735449774577517354497747758
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149207917207917419430425600824552960x7ff568331b800x7ff54c224bc052428810284526115177328817354497778197173544977457751735449802817517354498029880
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001522079172079174194304256001224567680x7ff568331a000x7ff54c224c00524288797334589294922017354498061009173544980281751735449832241517354498324142
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001552079172079174194304256001224577280x7ff5683318800x7ff54c224c4052428810962463122778035217354498362511173544983224151735449860737517354498609145
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001582079172079174194304256001224589440x7ff5683317000x7ff54c224c8052428811331266126907835217354498639544173544986073751735449897473517354498976565
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001612079172079174194304256001224601600x7ff56a9d15800x7ff54c224cc052428811360197127228832017354499007354173544989747351735449934385617354499345776
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164207917207917419430425600824613760x7ff56a9d14000x7ff54c224d0052428810291971115255734017354499376575173544993438561735449963105617354499632988
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001672079172079174194304256001224628480x7ff56a9d12800x7ff54c224d40524288600967567309220417354499663427173544996310561735449991505617354499916980
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001702079172079174194304256001224638080x7ff56a9d11000x7ff54c224d8052428810156304113742836417354499955029173544999150561735450019601617354500197793
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001732079172079174194304256001224650240x7ff568331f800x7ff54c224dc052428811239424125878566017354500229442173545001960161735450056289617354500564703
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001762079172079174194304256001224662400x7ff568331e000x7ff54c224e0052428811225938125727482017354500596903173545005628961735450092897717354500930954
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179207917207917419430425600824674560x7ff568331c800x7ff54c224e4052428810083755112934686017354500961313173545009289771735450120929717354501211416
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001822079172079174194304256001224689280x7ff568331b000x7ff54c224e80524288588142465872426817354501241556173545012092971735450149953717354501501429
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001852079172079174194304256001224701440x7ff5683319800x7ff54c224ec052428810349529115913843217354501539028173545014995371735450178097717354501782891
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001882079172079174194304256001224716160x7ff5683318000x7ff54c224f0052428811282018126357572817354501813561173545017809771735450214561717354502147902
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001912079172079174194304256001224728320x7ff5683316800x7ff54c224f4052428811311141126682153217354502179021173545021456171735450252705817354502528892
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194207917207917419430425600824740480x7ff56a9d15000x7ff54c224f805242889783000109560159217354502559431173545025270581735450280849817354502810484
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001972079172079174194304256001224757760x7ff56a9d13800x7ff54c224fc0524288457806351270267217354502841603173545028084981735450310465817354503106506
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002002079172079174194304256001224769920x7ff56a9d12000x7ff54c22500052428810432135116843600417354503144595173545031046581735450338305817354503385019
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002032079172079174194304256001224784640x7ff56a9d10800x7ff54c22504052428811154898124932418017354503416498173545033830581735450374769817354503749500
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002062079172079174194304256001224799360x7ff568331f000x7ff54c22508052428811160342124994708017354503780509173545037476981735450411473917354504116640
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209207917207917419430425600824814080x7ff568331d800x7ff54c2250c05242889442052105747202417354504147729173545041147391735450439745917354504399382
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002122079172079174194304256001224831360x7ff568331c000x7ff54c225100524288381714642747590417354504429942173545043974591735450469697917354504698824
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002152079172079174194304256001224843520x7ff568331a800x7ff54c22514052428810363380116068734817354504749733173545046969791735450497777917354504979627
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002182079172079174194304256001224858240x7ff5683319000x7ff54c22518052428811137512124738260017354505010026173545049777791735450534465917354505346597
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002212079172079174194304256001224872960x7ff5683317800x7ff54c2251c052428811318350126762094417354505378167173545053446591735450572114017354505723118
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002242079172079174194304256001224887680x7ff5683316000x7ff54c2252005242889538306106826136017354505754277173545057211401735450600546017354506007250
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002272079172079174194304256001224907520x7ff56a9d14800x7ff54c225240524288357997340094293217354506038489173545060054601735450632514017354506327142
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002302079172079174194304256001224919680x7ff56a9d13000x7ff54c2252805242889988094111869711617354506365761173545063251401735450661490017354506616734
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002332079172079174194304256001224934400x7ff56a9d11800x7ff54c2252c052428811185722125276938417354506647393173545066149001735450697938017354506981294
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002362079172079174194304256001224949120x7ff56a9d10000x7ff54c22530052428811261041126122263617354507013354173545069793801735450734482117354507346575
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002392079172079174194304256001224963840x7ff568331e800x7ff54c2253405242889354010104765726817354507377324173545073448211735450762562117354507627547
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002422079172079174194304256001224983680x7ff568331d000x7ff54c225380524288334847137500643217354507657777173545076256211735450794226117354507944179
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002452079172079174194304256001224995840x7ff568331b800x7ff54c2253c052428810154973113733166817354507982728173545079422611735450822946117354508231191
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024820791720791741943042560012241013120x7ff568331a000x7ff54c22540052428811235130125829535617354508262381173545082294611735450860226117354508603972
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025120791720791741943042560012241027840x7ff5683318800x7ff54c22544052428811139944124764540417354508634911173545086022611735450896882217354508970592
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025420791720791741943042560012241042560x7ff5683317000x7ff54c225480524288882423798825356417354509001531173545089688221735450925042217354509252355
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025720791720791741943042560012241062400x7ff56a9d15800x7ff54c2254c0524288327150936637894017354509282894173545092504221735450956754217354509569426
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026020791720791741943042560012241077120x7ff56a9d14000x7ff54c2255005242889682416108435951617354509608355173545095675421735450984514217354509847179
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026320791720791741943042560016241094400x7ff56a9d12800x7ff54c22554052428811137183124732594017354509877898173545098451421735451020962217354510211759
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026620791720791741943042560016241111680x7ff56a9d11000x7ff54c22558052428811196174125392788817354510243428173545102096221735451057762317354510579590
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002692079172079174194304256008241128960x7ff568331f800x7ff54c2255c0524288816031391397940017354510609859173545105776231735451086530317354510866972
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027220791720791741943042560012241151360x7ff568331e000x7ff54c225600524288320078335841861217354510898291173545108653031735451119378317354511195713
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027520791720791741943042560012241166080x7ff568331c800x7ff54c2256405242889667161108271376017354511233662173545111937831735451148114317354511483006
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027820791720791741943042560016241183360x7ff568331b000x7ff54c22568052428811074463124033495617354511513625173545114811431735451184594317354511847936
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028120791720791741943042560016241200640x7ff5683319800x7ff54c2256c052428811123849124588530817354511879185173545118459431735451221010417354512211957
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028420791720791741943042560012241217920x7ff5683318000x7ff54c225700524288682010976389853617354512242376173545122101041735451249154417354512493479
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028720791720791741943042560012241240320x7ff5683316800x7ff54c225740524288295635433109174417354512523938173545124915441735451282290417354512824830
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029020791720791741943042560012241255040x7ff56a9d15000x7ff54c2257805242889383948105091798017354512862889173545128229041735451310706417354513109003
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029320791720791741943042560012241274880x7ff56a9d13800x7ff54c2257c052428811098067124299822017354513139792173545131070641735451347202417354513473923
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029620791720791741943042560012241292160x7ff56a9d12000x7ff54c22580052428811135337124712966417354513505452173545134720241735451383698517354513838864
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029920791720791741943042560012241309440x7ff56a9d10800x7ff54c225840524288562716963016321617354513870213173545138369851735451412578517354514128256
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030220791720791741943042560012241334400x7ff568331f000x7ff54c225880524288289270332398501217354514159265173545141257851735451447650517354514478437
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030520791720791741943042560012241349120x7ff568331d800x7ff54c2258c0524288831361193107880817354514516396173545144765051735451476658517354514768299
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030820791720791741943042560012241368960x7ff568331c000x7ff54c22590052428811008670123293306817354514798778173545147665851735451513362517354515135490
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031120791720791741943042560012241388800x7ff568331a800x7ff54c22594052428810971379122878665617354515165939173545151336251735451550130617354515503200
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031420791720791741943042560012241408640x7ff5683319000x7ff54c225980524288474517453153890017354515533789173545155013061735451579410617354515796032
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031720791720791741943042560012241436160x7ff5683317800x7ff54c2259c0524288287053432140198017354515826431173545157941061735451614818617354516149983
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032020791720791741943042560012241453440x7ff5683316000x7ff54c225a00524288754788984538168817354516188372173545161481861735451642898617354516430815
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032320791720791741943042560012241475840x7ff56a9d14800x7ff54c225a4052428810975381122924575617354516461445173545164289861735451679586717354516797886
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032620791720791741943042560012241495680x7ff56a9d13000x7ff54c225a8052428810962953122783395217354516828075173545167958671735451716114717354517163056
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032920791720791741943042560012241515520x7ff56a9d11800x7ff54c225ac0524288389214743588682417354517194135173545171611471735451746418717354517466058
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033220791720791741943042560012241543040x7ff56a9d10000x7ff54c225b00524288283152831711430817354517497587173545174641871735451783266717354517834538
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033520791720791741943042560012241562880x7ff568331e800x7ff54c225b40524288553728762019502417354517872517173545178326671735451812802717354518130081
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033820791720791741943042560012241587840x7ff568331d000x7ff54c225b8052428810590000118606338017354518161800173545181280271735451850098817354518502971
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034120791720791741943042560012241610240x7ff568331b800x7ff54c225bc052428810735241120232116817354518533990173545185009881735451887106817354518872981
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034420791720791741943042560012241632640x7ff568331a000x7ff54c225c00524288354519039697296417354518903200173545188710681735451918034817354519182333
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034720791720791741943042560012241665280x7ff5683318800x7ff54c225c40524288286407532071162017354519213082173545191803481735451957410817354519597332
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035020791720791741943042560012241685120x7ff5683317000x7ff54c225c80524288409509345873836417354519616381173545195741081735451988626817354519888154
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035320791720791741943042560012241712640x7ff56a9d15800x7ff54c225cc052428810360306116033329217354519919143173545198862681735452025602917354520257904
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035620791720791741943042560012241737600x7ff56a9d14000x7ff54c225d0052428810539476118035946817354520288963173545202560291735452063410917354520635954
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035920791720791741943042560012241762560x7ff56a9d12800x7ff54c225d40524288277196831042598017354520666893173545206341091735452095762917354520959546
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036220791720791741943042560012241797760x7ff56a9d11000x7ff54c225d80524288286576232105517217354520990335173545209576291735452137666917354521396174
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036520791720791741943042560012241822720x7ff568331f800x7ff54c225dc0524288308574634561131217354521417163173545213766691735452170291017354521704786
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036820791720791741943042560012241855360x7ff568331e000x7ff54c225e00524288831673493144550417354521735255173545217029101735452207955017354522081846
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037120791720791741943042560012241885440x7ff568331c800x7ff54c225e40524288755208384581642817354522113575173545220795501735452246515017354522487545
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037420791720791741943042560012241915520x7ff568331b000x7ff54c225e80524288279472331301606017354522498995173545224651501735452282339017354522825246
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037720791720791741943042560012241958400x7ff5683319800x7ff54c225ec0524288286072832035302017354522856125173545228233901735452329747117354523318643
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038020791720791741943042560012241985920x7ff5683318000x7ff54c225f00524288270166330251297617354523337783173545232974711735452363923117354523641245
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038320791720791741943042560012242023680x7ff5683316800x7ff54c225f40524288677252075849354417354523672754173545236392311735452404019117354524061264
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038620791720791741943042560012242058880x7ff56a9d15000x7ff54c225f80524288621518369612528817354524073813173545240401911735452444419117354524463953
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038920791720791741943042560012242094080x7ff56a9d13800x7ff54c225fc0524288282137031597040417354524477113173545244441911735452482531217354524827164
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039220791720791741943042560012242144640x7ff56a9d12000x7ff54c226000524288290465632531158817354524858613173545248253121735452534659217354525364639
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039520791720791741943042560012242177280x7ff56a9d10800x7ff54c226040524288276929831016567617354525388069173545253465921735452570547217354525707410
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039820791720791741943042560012242220160x7ff568331f000x7ff54c226080524288575716764475741217354525738750173545257054721735452612771217354526147669
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040120791720791741943042560012242260480x7ff568331d800x7ff54c2260c0524288520721458318730817354526162328173545261277121735452655843317354526578067
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040420791720791741943042560012242300800x7ff568331c000x7ff54c226100524288280571631423420417354526591537173545265584331735452696483317354526982737
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040720791720791741943042560012242359040x7ff568331a800x7ff54c226140524288295435233094100017354526997876173545269648331735452754627317354527563441
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041020791720791741943042560012242394240x7ff5683319000x7ff54c226180524288279244931271154817354527587201173545275462731735452792931317354527931312
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041320791720791741943042560012242442240x7ff5683317800x7ff54c2261c0524288517907458008892817354527962151173545279293131735452837011417354528388260
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041620791720791741943042560012242487680x7ff5683316000x7ff54c226200524288323011036174854017354528403219173545283701141735452881091417354528828948
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041920791720791741943042560012242533120x7ff56a9d14800x7ff54c226240524288278948031240420417354528844128173545288109141735452924115417354529258727
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004222079172079174194304256008242555520x7ff56a9d13000x7ff54c226280524288236063226439768017354529274366173545292411541735452988339517354529900840
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042520791720791741943042560012242598400x7ff56a9d11800x7ff54c2262c0524288273185530581990817354529923699173545298833951735453029795517354530315699
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042820791720791741943042560012242656640x7ff56a9d10000x7ff54c226300524288314273335196613617354530332758173545302979551735453079171517354530833935
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043120791720791741943042560012242712320x7ff568331e800x7ff54c226340524288355746939851476017354530846255173545307917151735453130387617354531346052
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004342079172079174194304256008242732160x7ff568331d000x7ff54c226380524288239230526787908017354531356382173545313038761735453181571617354531857888
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004372079172079174194304256008242757120x7ff568331b800x7ff54c2263c0524288237405126583229217354531869048173545318157161735453259331617354532611508
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044020791720791741943042560012242807680x7ff568331a000x7ff54c226400524288263514629513504417354532633098173545325933161735453304995717354533072086
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044320791720791741943042560012242876160x7ff5683318800x7ff54c226440524288362318240572929217354533083006173545330499571735453359651717354533639601
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044620791720791741943042560012242942080x7ff5683317000x7ff54c226480524288341195138212504417354533652511173545335965171735453416467717354534210786
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004492079172079174194304256008242969600x7ff56a9d15800x7ff54c2264c0524288238711326739009617354534223126173545341646771735453474083817354534785391
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004522079172079174194304256008242999680x7ff56a9d14000x7ff54c226500524288240229026907906017354534796871173545347408381735453561891817354535661788
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004552079172079174194304256008243027200x7ff56a9d12800x7ff54c226540524288239154826770274817354535680918173545356189181735453628115917354536324651
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045820791720791741943042560012243054720x7ff56a9d11000x7ff54c226580524288259289229039019617354536335700173545362811591735453696643917354537009243
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046120791720791741943042560012243082240x7ff568331f800x7ff54c2265c0524288259857829100116817354537021182173545369664391735453764292017354537685635
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004642079172079174194304256008243109760x7ff568331e000x7ff54c226600524288240538626934612017354537696794173545376429201735453831764017354538363797
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004672079172079174194304256008243132160x7ff568331c800x7ff54c226640524288241779027077189617354538375387173545383174981735453941077817354539460378
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004702079172079174194304256008243159680x7ff568331b000x7ff54c226680524288243238927243607617354539480397173545394107781735454048773817354540530780
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047320791720791741943042560012243187200x7ff5683319800x7ff54c2266c0524288259074929016674417354540541880173545404877381735454158981817354541654180
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047620791720791741943042560012243214720x7ff5683318000x7ff54c226700524288259861429103756417354541666540173545415898181735454270709917354542781361
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004792079172079174194304256008243242240x7ff5683316800x7ff54c226740524288243236027233721617354542792300173545427070991735454382053917354543888851
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004822079172079174194304256008243264640x7ff56a9d15000x7ff54c226780524288246888727655548817354543900581173545438205391735454577622017354545845160
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004852079172079174194304256008243292160x7ff56a9d13800x7ff54c2267c0524288244812127415769617354545864339173545457762201735454770406017354547776529
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048820791720791741943042560012243319680x7ff56a9d12000x7ff54c226800524288262409829381165217354547787798173545477040601735454969078117354549759966
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049120791720791741943042560012243347200x7ff56a9d10800x7ff54c226840524288262853429442169617354549771606173545496907811735455167734217354551753513
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004942079172079174194304256008243374720x7ff568331f000x7ff54c226880524288245012827439252017354551764853173545516773421735455362150217354553687413
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049720791720791741943042560082400x7ff568331d800x7ff54c2268c0524288246286127587000417354553698472173545536215021735455723894417354557311637