Files
rocm-systems/tests/workloads/dev0/mi200/SQ_LEVEL_WAVES.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

48 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjGRBM_COUNTGRBM_GUI_ACTIVECPC_ME1_BUSY_FOR_PACKET_DECODESQ_CYCLESSQ_WAVESSQ_WAVE_CYCLESSQ_BUSY_CYCLESSQ_LEVEL_WAVESSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000223519223519335544322560043241600x00x7f1ce5804280387094387094868030967605242882457714773011216099932854817599035568236175983288166421759918581320517599185923274
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00222351922351932768256001224138880x00x7f1ce5823f8033003330032954926403251217390441671250696974417599191082624175991858132051759919122744617599191232450
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0052235192235194194304256001224143360x7f1ce88903800x7f1ce5823fc016405016405013444131240865536808698111211279032521029617599191275709175991912274461759919162888617599191631540
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0082235192235194194304256001624150400x7f1ce88902000x7f1ce5824000311255311255237662490048655362285986622391429091612352417599191677268175991916288861759919206184617599192064219
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00112235192235194194304256001624154880x7f1ce88900800x7f1ce5824040308986308986233542471896655362143667512367416085919556817599192106057175991920618461759919248904617599192491478
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00142235192235194194304256001224159360x7f1ce60edf000x7f1ce582408016422916422913653131384065536797397991213367032068891217599192533847175991924890461759919281976617599192822219
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00172235192235194194304256001224163840x7f1ce60edd800x7f1ce58240c016427016427013901131416865536850851951213013034206964817599192862578175991928197661759919315240717599193154691
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00202235192235194194304256001224170880x7f1ce60edc000x7f1ce5824100163629163629147311309040655361017003221209658040852738817599193208009175991931524071759919347992717599193482142
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00232235192235194194304256001624177920x7f1ce60eda800x7f1ce5824140309902309902243132479224655362313317882381450092705649617599193522181175991934799271759919391352717599193915851
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00262235192235194194304256001624184960x7f1ce60ed9000x7f1ce5824180308147308147207972465184655362232340652366125089466180417599193956680175991939135271759919434312717599194345870
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00292235192235194194304256001624192000x7f1ce60ed7800x7f1ce58241c0164420164420149781315368655361078016661219890043293158817599194385889175991943431271759919468120717599194683762
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00322235192235194194304256001624199040x7f1ce60ed6000x7f1ce582420016385016385014054131080865536957675061210869038479918817599194725201175991946812071759919500712717599195008974
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00352235192235194194304256001224206080x7f1ce88904800x7f1ce5824240163455163455150691307648655361014668031209268040759080417599195059352175991950071271759919530792717599195309736
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00382235192235194194304256001624213120x7f1ce88903000x7f1ce5824280311296311296248912490376655362230277852383286089384314817599195357015175991953079271759919571688717599195718836
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00412235192235194194304256001624220160x7f1ce88901800x7f1ce58242c0307413307413213132459312655362203778752358693088323953217599195762984175991957168871759919610984717599196111616
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00442235192235194194304256001624227200x7f1ce88900000x7f1ce582430016386016386014357131088865536861776721212931034644629617599196153195175991961098471759919641528717599196417118
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00472235192235194194304256001224234240x7f1ce60ede800x7f1ce5824340164511164511146691316096655361018940901212423040930404817599196458717175991964152871759919671544817599196717250
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00502235192235194194304256001224241280x7f1ce60edd000x7f1ce582438016256616256615450130053665536991985551201088039851629617599196765099175991967154481759919702232817599197024232
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00532235192235194194304256001624248320x7f1ce60edb800x7f1ce58243c0308486308486246632467896655362290722152363677091801767617599197068781175991970223281759919741176817599197413713
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00562235192235194194304256001624255360x7f1ce60eda000x7f1ce5824400306838306838204832454712655362107614402347060084477775617599197455062175991974117681759919780040817599197802393
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00592235192235194194304256001224262400x7f1ce60ed8800x7f1ce5824440162963162963144161303712655361027931071207484041290065217599197843782175991978004081759919810280817599198104865
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00622235192235194194304256001224269440x7f1ce60ed7000x7f1ce582448016293416293414706130348065536960902331205611038608862417599198146734175991981028081759919841064817599198412477
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00652235192235194194304256001224276480x7f1ce88905800x7f1ce58244c0162859162859152381302880655361076525551202144043234053217599198460616175991984106481759919871544817599198717769
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00682235192235194194304256001624286080x7f1ce88904000x7f1ce5824500308990308990234232471928655362281612522373553091437486817599198760228175991987154481759919910936817599199111219
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00712235192235194194304256001624293120x7f1ce88902800x7f1ce5824540306147306147201512449184655362090505432343388083793006417599199154828175991991093681759919950200817599199504109
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00742235192235194194304256001224300160x7f1ce88901000x7f1ce5824580162202162202147651297624655361036594101202611041636876017599199546568175991995020081759919980392817599199805552
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077223519223519419430425600824309760x7f1ce60edf800x7f1ce58245c016307916307914477130464065536927184971200483037260599617599199847341175991998039281759920010472917599200106534
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00802235192235194194304256001224316800x7f1ce60ede000x7f1ce5824600162400162400153481299208655361038418201202899041709154817599200155193175992001047291759920040488917599200406786
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00832235192235194194304256001624326400x7f1ce60edc800x7f1ce5824640306398306398235152451192655362233140852344298089498628417599200448415175992004048891759920080808917599200809996
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00862235192235194194304256001224336000x7f1ce60edb000x7f1ce5824680307952307952211042463624655362246500822360765090032793217599200852475175992008080891759920120376917599201205546
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00892235192235194194304256001224345600x7f1ce60ed9800x7f1ce58246c0164008164008147621312072655361038951881212089041730872417599201248205175992012037691759920151064917599201512478
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092223519223519419430425600824355200x7f1ce60ed8000x7f1ce582470016301016301014494130408865536918602891202289036916610417599201553217175992015106491759920181368917599201815460
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00952235192235194194304256001224362240x7f1ce60ed6800x7f1ce5824740162473162473147521299792655361036965321200924041651205217599201863219175992018136891759920211496917599202117173
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00982235192235194194304256001224371840x7f1ce88905000x7f1ce5824780305506305506233012444056655362281692662345763091440897617599202157842175992021149691759920250696917599202508773
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001012235192235194194304256001224381440x7f1ce88903800x7f1ce58247c0305717305717230052445744655362189811742346926087765389217599202549452175992025069691759920289704917599202898983
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001042235192235194194304256001224391040x7f1ce88902000x7f1ce582480016268116268114041130145665536918609451201279036917549617599202940142175992028970491759920320344917599203205385
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107223519223519419430425600824403200x7f1ce88900800x7f1ce582484016319116319115242130553665536903656101203195036319435217599203245884175992032034491759920350680917599203508637
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001102235192235194194304256001224412800x7f1ce60edf000x7f1ce582488016185916185913858129488065536955796701195909038404302817599203556696175992035068091759920381721017599203819140
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001132235192235194194304256001224422400x7f1ce60edd800x7f1ce58248c0305636305636237792445096655362266827332348095090846129217599203859599175992038172101759920420761017599204209530
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001162235192235194194304256001224432000x7f1ce60edc000x7f1ce5824900305030305030221012440248655362212008292340228088653266017599204255839175992042076101759920460073017599204602530
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119223519223519419430425600824441600x7f1ce60eda800x7f1ce582494016258716258714434130070465536994057291197980039934771617599204643099175992046007301759920490425017599204906362
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001222235192235194194304256001224453760x7f1ce60ed9000x7f1ce582498016309116309115330130473665536972768011204513039083325617599204946401175992049042501759920520713017599205208974
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001252235192235194194304256001224463360x7f1ce60ed7800x7f1ce58249c0161124161124144161289000655361000752381192158040202506417599205257133175992052071301759920552233017599205524216
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001282235192235194194304256001224475520x7f1ce60ed6000x7f1ce5824a00303879303879232982431040655362197894562327008088088648817599205564615175992055223301759920591209017599205914126
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001312235192235194194304256001224485120x7f1ce88904800x7f1ce5824a40302284302284207932418280655362130117272317029085377399217599205956235175992059120901759920631049017599206312506
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134223519223519419430425600824494720x7f1ce88903000x7f1ce5824a8016179516179514420129436865536910354531195696036587458017599206353075175992063104901759920662153017599206623439
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001372235192235194194304256001224506880x7f1ce88901800x7f1ce5824ac016210616210616119129685665536980514761192092039394468417599206664607175992066215301759920692585017599206927641
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001402235192235194194304256001224516480x7f1ce88900000x7f1ce5824b0016200516200515343129604865536938658201188512037719298817599206975550175992069258501759920723609117599207238053
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001432235192235194194304256001224528640x7f1ce60ede800x7f1ce5824b40301396301396222832411176655362166740072310551086842685617599207279362175992072360911759920762697117599207628953
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001462235192235194194304256001224540800x7f1ce60edd000x7f1ce5824b80299539299539196422396320655362061940382294934082650518017599207675052175992076269711759920802489117599208026693
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149223519223519419430425600824552960x7f1ce60edb800x7f1ce5824bc016212516212514190129700865536922786151195744037083836417599208066542175992080248911759920832761117599208329595
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001522235192235194194304256001224567680x7f1ce60eda000x7f1ce5824c0016221416221415205129772065536991182821195610039820398417599208369894175992083276111759920863593117599208637747
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001552235192235194194304256001224577280x7f1ce60ed8800x7f1ce5824c4016161316161314120129291265536940418481195216037789392017599208685976175992086359311759920894521117599208947010
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001582235192235194194304256001224589440x7f1ce60ed7000x7f1ce5824c80303465303465237592427728655362222268262324855089064162417599208987999175992089452111759920933689117599209338770
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001612235192235194194304256001224601600x7f1ce88905800x7f1ce5824cc0300746300746209122405976655362137376412304791085667784017599209378479175992093368911759920972617117599209727870
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164223519223519419430425600824613760x7f1ce88904000x7f1ce5824d0016375716375714773131006465536926889801207571037249878017599209768679175992097261711759921003225117599210034002
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001672235192235194194304256001224628480x7f1ce88902800x7f1ce5824d40168983168983159421351872655361071115141248405043017828417599210073981175992100322511759921035241117599210354654
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001702235192235194194304256001224638080x7f1ce88901000x7f1ce5824d8016174516174514451129396865536916225611194499036821126017599210402933175992103524111759921065689217599210658776
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001732235192235194194304256001224650240x7f1ce60edf800x7f1ce5824dc0302236302236220912417896655362230733942317704089402648017599210699905175992106568921759921104393217599211045686
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001762235192235194194304256001224662400x7f1ce60ede000x7f1ce5824e00298968298968203922391752655362142106802293417085857349617599211085865175992110439321759921143273217599211434506
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179223519223519419430425600824674560x7f1ce60edc800x7f1ce5824e4016202016202014214129616865536846577191193390034035819617599211474565175992114327321759921173465217599211736449
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001822235192235194194304256001224689280x7f1ce60edb000x7f1ce5824e80176643176643161231413152655361016402331310164040829576817599211776988175992117346521759921204937217599212051331
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001852235192235194194304256001224701440x7f1ce60ed9800x7f1ce5824ec016020016020014521128160865536917746391182297036883180417599212099949175992120493721759921235721217599212359093
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001882235192235194194304256001224716160x7f1ce60ed8000x7f1ce5824f00300790300790229422406328655362211847502307117088646801617599212400082175992123572121759921275161217599212753523
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001912235192235194194304256001224728320x7f1ce60ed6800x7f1ce5824f40303214303214229792425720655362224763602321620089163433217599212794032175992127516121759921314041217599213142303
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194223519223519419430425600824740480x7f1ce88905000x7f1ce5824f8016157616157615002129261665536933294511194379037504588017599213183432175992131404121759921344425217599213446165
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001972235192235194194304256001224757760x7f1ce88903800x7f1ce5824fc0181529181529163421452240655361140553961352505045796740017599213487164175992134442521759921376009217599213762087
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002002235192235194194304256001224769920x7f1ce88902000x7f1ce582500016054716054714019128438465536935726271185461037602610017599213822025175992137600921759921406601217599214067799
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002032235192235194194304256001224784640x7f1ce88900800x7f1ce5825040302277302277234502418224655362174949282312009087171018017599214122088175992140660121759921447257317599214474469
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002062235192235194194304256001224799360x7f1ce60edf000x7f1ce5825080300853300853225522406832655362182697922309166087480836817599214515098175992144725731759921486921317599214871149
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209223519223519419430425600824814080x7f1ce60edd800x7f1ce58250c016170516170514563129364865536899606581192520036157490817599214911058175992148692131759921517913317599215181001
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002122235192235194194304256001224831360x7f1ce60edc000x7f1ce5825100189879189879172801519040655361211524171416318048635000017599215221200175992151791331759921550089317599215502703
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002152235192235194194304256001224843520x7f1ce60eda800x7f1ce582514016159516159514563129276865536908326271194715036506830417599215550182175992155008931759921580985317599215811795
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002182235192235194194304256001224858240x7f1ce60ed9000x7f1ce5825180304373304373239482434992655362231549072330830089435284417599215852234175992158098531759921620217317599216204095
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002212235192235194194304256001224872960x7f1ce60ed7800x7f1ce58251c0302025302025239492416208655362176355702314395087227116417599216245874175992162021731759921659625317599216598185
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002242235192235194194304256001224887680x7f1ce60ed6000x7f1ce582520016423116423115505131385665536953911881208938038329701217599216637724175992165962531759921690521317599216907147
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002272235192235194194304256001224907520x7f1ce88904800x7f1ce5825240201157201157180601609264655361328080191502674053297610017599216946956175992169052131759921723817317599217240109
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002302235192235194194304256001224919680x7f1ce88903000x7f1ce582528016143916143915055129152065536903948101183386036331352417599217287948175992172381731759921754265317599217544551
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002332235192235194194304256001224934400x7f1ce88901800x7f1ce58252c0301599301599235232412800655362159038202308263086534547617599217591970175992175426531759921794345417599217945341
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002362235192235194194304256001224949120x7f1ce88900000x7f1ce5825300299893299893214002399152655362132093612302281085456856417599217988350175992179434541759921834297417599218345131
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002392235192235194194304256001224963840x7f1ce60ede800x7f1ce582534016185716185715079129486465536954105461195944038337642817599218384950175992183429741759921865145417599218653103
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002422235192235194194304256001224983680x7f1ce60edd000x7f1ce5825380210961210961187261687696655361226719101573016049243000017599218693772175992186514541759921898489417599218986714
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002452235192235194194304256001224995840x7f1ce60edb800x7f1ce58253c016072216072214786128578465536940411261188643037789862017599219034443175992189848941759921928745417599219289297
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024822351922351941943042560012241013120x7f1ce60eda000x7f1ce5825400297215297215223812377728655362173761992272933087124017617599219330136175992192874541759921968217417599219684177
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025122351922351941943042560012241027840x7f1ce60ed8800x7f1ce5825440301892301892231592415144655362157774822310252086483960817599219724166175992196821741759922007337417599220075207
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025422351922351941943042560012241042560x7f1ce60ed7000x7f1ce582548016087516087515512128700865536999350821186832040147776017599220115886175992200733741759922037721417599220378979
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025722351922351941943042560012241062400x7f1ce88905800x7f1ce58254c0218300218300187351746408655361425455571643475057192975217599220419158175992203772141759922071593417599220717570
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026022351922351941943042560012241077120x7f1ce88904000x7f1ce582550016080916080914981128648065536930241881185194037383033617599220765819175992207159341759922102025417599221022052
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026322351922351941943042560016241094400x7f1ce88902800x7f1ce5825540295522295522201512364184655362000996482263590080213138017599221063171175992210202541759922140697517599221408643
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026622351922351941943042560016241111680x7f1ce88901000x7f1ce5825580299497299497218292395984655362094989792296410083972724417599221450281175992214069751759922179817517599221800103
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002692235192235194194304256008241128960x7f1ce60edf800x7f1ce58255c0162801162801158141302416655361037627451199482041678721617599221840192175992217981751759922210841517599222110135
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027222351922351941943042560012241151360x7f1ce60ede000x7f1ce5825600229107229107195731832864655361441806211723384057846867217599222150574175992221084151759922246105517599222463096
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027522351922351941943042560012241166080x7f1ce60edc800x7f1ce582564016068116068114462128545665536885873661188462035608270417599222510745175992224610551759922276537517599222767318
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027822351922351941943042560016241183360x7f1ce60edb000x7f1ce5825680297135297135217392377088655362151659672275049086239840017599222807817175992227653751759922315289517599223154718
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028122351922351941943042560016241200640x7f1ce60ed9800x7f1ce58256c0297121297121203052376976655362074467672276839083151883217599223194867175992231528951759922354329517599223545098
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028422351922351941943042560012241217920x7f1ce60ed8000x7f1ce5825700163001163001151871304016655361013620971204674040718251617599223585347175992235432951759922384841517599223850391
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028722351922351941943042560012241240320x7f1ce60ed6800x7f1ce5825740239925239925195791919408655361464705351808793058762892817599223889670175992238484151759922420569517599224207662
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029022351922351941943042560012241255040x7f1ce88905000x7f1ce582578016104516104514978128836865536978475581190238039311928817599224255930175992242056951759922451561517599224517514
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029322351922351941943042560012241274880x7f1ce88903800x7f1ce58257c0295651295651192512365216655362068741852267595082923299617599224559303175992245156151759922490281617599224904564
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029622351922351941943042560012241292160x7f1ce88902000x7f1ce5825800297826297826197922382616655361951678442278001078240871217599224945893175992249028161759922529161617599225293464
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029922351922351941943042560012241309440x7f1ce88900800x7f1ce5825840169599169599157601356800655361052854521254879042288980017599225333593175992252916161759922560137617599225603426
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030222351922351941943042560012241334400x7f1ce60edf000x7f1ce5825880258737258737206642069904655361751568841963536070237590817599225644165175992256013761759922596569617599225967437
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030522351922351941943042560012241349120x7f1ce60edd800x7f1ce58258c016113316113314947128907265536996687991191612040040665217599226015586175992259656961759922627833617599226280129
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030822351922351941943042560012241368960x7f1ce60edc000x7f1ce5825900296613296613198512372912655362119588122274899084958521217599226320258175992262783361759922667497617599226676669
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031122351922351941943042560012241388800x7f1ce60eda800x7f1ce5825940296549296549206122372400655362158905092271918086529714417599226716468175992266749761759922706473617599227066609
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031422351922351941943042560012241408640x7f1ce60ed9000x7f1ce5825980177585177585163001420688655361110618501320744044599050817599227106748175992270647361759922737977617599227381681
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031722351922351941943042560012241436160x7f1ce60ed7800x7f1ce58259c0279463279463226032235712655361973437472128046079112312817599227421940175992273797761759922775465617599227756442
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032022351922351941943042560012241453440x7f1ce60ed6000x7f1ce5825a0016108116108115306128865665536994566101190651039956127617599227807350175992277546561759922806121617599228063134
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032322351922351941943042560012241475840x7f1ce88904800x7f1ce5825a40296477296477213282371824655362101942672268497084253684817599228103923175992280612161759922844937717599228451204
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032622351922351941943042560012241495680x7f1ce88903000x7f1ce5825a80295165295165200992361328655362018082272257080080896960017599228491953175992284493771759922883913717599228841014
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032922351922351941943042560012241515520x7f1ce88901800x7f1ce5825ac0186107186107169701488864655361111917231383831044651482817599228881633175992288391371759922916425717599229166026
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033222351922351941943042560012241543040x7f1ce88900000x7f1ce5825b00298821298821229562390576655362065644412285325082800916417599229206785175992291642571759922955993717599229561796
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033522351922351941943042560012241562880x7f1ce60ede800x7f1ce5825b40170807170807161461366464655361096182431269968044020978417599229610025175992295599371759922987353717599229875448
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033822351922351941943042560012241587840x7f1ce60edd000x7f1ce5825b80297260297260196732378088655361976401212268866079231865617599229916137175992298735371759923027737717599230279218
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034122351922351941943042560012241610240x7f1ce60edb800x7f1ce5825bc0296572296572196422372584655361949145042267424078140550017599230321996175992302773771759923067369717599230675577
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034422351922351941943042560012241632640x7f1ce60eda000x7f1ce5825c00204886204886176471639096655361292988151534522051894361217599230716236175992306736971759923100873717599231010679
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034722351922351941943042560012241665280x7f1ce60ed8800x7f1ce5825c40339686339686252832717496655362422704642610005097084135617599231050558175992310087371759923142537717599231471227
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035022351922351941943042560012241685120x7f1ce60ed7000x7f1ce5825c8018566418566417222148532065536993111441372031039898898817599231490727175992314253771759923177977817599231781749
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035322351922351941943042560012241712640x7f1ce88905800x7f1ce5825cc0297130297130194332377048655361689804402248208067769010817599231823418175992317797781759923217417817599232175999
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035622351922351941943042560012241737600x7f1ce88904000x7f1ce5825d00297218297218197032377752655361858419992256938074512180417599232217538175992321741781759923256601817599232567829
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035922351922351941943042560012241762560x7f1ce88902800x7f1ce5825d40224070224070192551792568655361545405941688496061990791217599232608188175992325660181759923291209817599232914040
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036222351922351941943042560012241797760x7f1ce88901000x7f1ce5825d803794083794082752430352726553628091253829291230112541068817599232955209175992329120981759923335593817599233375539
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036522351922351941943042560012241822720x7f1ce60edf800x7f1ce5825dc0210274210274184561682200655361341661521577796053841538017599233406918175992333559381759923369865817599233700550
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036822351922351941943042560012241855360x7f1ce60ede000x7f1ce5825e00305566305566228792444536655361873115192330912075100570417599233741359175992336986581759923409993817599234122930
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037122351922351941943042560012241885440x7f1ce60edc800x7f1ce5825e40311488311488206642491912655361753798272359463070329019217599234141379175992340999381759923452169817599234542609
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037422351922351941943042560012241915520x7f1ce60edb000x7f1ce5825e80265298265298217162122392655361891674972016701075843484017599234564818175992345216981759923489481817599234896660
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037722351922351941943042560012241958400x7f1ce60ed9800x7f1ce5825ec04604244604243100736834006553634505739735791760138199385617599234937179175992348948181759923538697917599235407387
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038022351922351941943042560012241985920x7f1ce60ed8000x7f1ce5825f00243092243092204131944744655361591220481834807063823798417599235437666175992353869791759923574857917599235750578
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038322351922351941943042560012242023680x7f1ce60ed6800x7f1ce5825f40335827335827223842686624655362104480502567232084356546417599235791957175992357485791759923617017917599236187327
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038622351922351941943042560012242058880x7f1ce88905000x7f1ce5825f80331346331346222092650776655361986649522529289079642987617599236212287175992361701791759923659033917599236607707
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038922351922351941943042560012242094080x7f1ce88903800x7f1ce5825fc0305461305461229032443696655362219252672342350088946191217599236633026175992365903391759923699513917599236996897
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039222351922351941943042560012242144640x7f1ce88902000x7f1ce58260005410985410983528443287926553640906113142234300163800995217599237038946175992369951391759923753913917599237556653
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039522351922351941943042560012242177280x7f1ce88900800x7f1ce5826040272959272959216522183680655361788723002075612071725370817599237590162175992375391391759923791769917599237919603
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039822351922351941943042560012242220160x7f1ce60edf000x7f1ce5826080364250364250252312914008655362395959382797370096016662817599237960842175992379176991759923836777917599238389651
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040122351922351941943042560012242260480x7f1ce60edd800x7f1ce58260c03610513610512701428884166553625034782027781010100315924417599238410891175992383677791759923881193917599238830550
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040422351922351941943042560012242300800x7f1ce60edc000x7f1ce5826100346530346530251362772248655362444083302664140097939374417599238853770175992388119391759923923354017599239275419
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040722351922351941943042560012242359040x7f1ce60eda800x7f1ce58261406233426233423954049867446553647121888548743740188664580817599239286438175992392335401759923984906017599239890713
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041022351922351941943042560012242394240x7f1ce60ed9000x7f1ce5826180302245302245226522417968655362110978022315171084615684417599239909623175992398490601759924027114017599240272963
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041322351922351941943042560012242442240x7f1ce60ed7800x7f1ce58261c03980163980162736931841366553627501559330796840110184482817599240314332175992402711401759924073098017599240773121
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041622351922351941943042560012242487680x7f1ce60ed6000x7f1ce58262003900133900132749231201126553629160935630177060116821206417599240783620175992407309801759924120938017599241250958
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041922351922351941943042560012242533120x7f1ce88904800x7f1ce58262403872343872342718430978806553628298700229905750113371515617599241261508175992412093801759924167914017599241696477
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004222235192235194194304256008242555520x7f1ce88903000x7f1ce58262807178217178214441357425766553654683836356326970218909302017599241722076175992416791401759924234378017599242387169
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042522351922351941943042560012242598400x7f1ce88901800x7f1ce58262c03646173646172697829169446553626069347927974520104453704017599242407419175992423437801759924280346117599242846368
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042822351922351941943042560012242656640x7f1ce88900000x7f1ce58263004691794691793171737534406553635395550436466510141760864017599242858207175992428034611759924333402117599243375194
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043122351922351941943042560012242712320x7f1ce60ede800x7f1ce58263404716204716203145537729686553634598167736687900138571081217599243386094175992433340211759924386810117599243909021
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004342235192235194194304256008242732160x7f1ce60edd000x7f1ce58263804822094822093242038576806553635455988937498190141998153617599243920091175992438681011759924439306117599244434278
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004372235192235194194304256008242757120x7f1ce60edb800x7f1ce58263c08801768801765208470414166553668149843169238100272773636817599244445347175992443930611759924517738117599245219388
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044022351922351941943042560012242807680x7f1ce60eda000x7f1ce58264004256834256832916534054726553631644362032999760126755126417599245239757175992451773811759924567466117599245715875
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044322351922351941943042560012242876160x7f1ce60ed8800x7f1ce58264405484125484123550943873046553641361055242766430165622392817599245726375175992456746611759924625290217599246298150
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044622351922351941943042560012242942080x7f1ce60ed7000x7f1ce58264805524455524453613144195686553641701536943108000166984786817599246309380175992462529021759924684170217599246885505
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004492235192235194194304256008242969600x7f1ce88905800x7f1ce58264c05630065630063673345040566553642430877343890980169897766817599246896825175992468417021759924742378217599247465411
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004522235192235194194304256008242999680x7f1ce88904000x7f1ce5826500104009310400936037283207526553681054887982169090324393804017599247476150175992474237821759924831994217599248366608
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004552235192235194194304256008243027200x7f1ce88902800x7f1ce58265407213167213164382057705366553654764235056555620219231126817599248385817175992483200101759924900689017599249054840
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045822351922351941943042560012243054720x7f1ce88901000x7f1ce58265807239637239634464357917126553655297626256751030221364745217599249066990175992490068901759924973009017599249773812
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046122351922351941943042560012243082240x7f1ce60edf800x7f1ce58265c07220607220604437857764886553654261524156599510217220189617599249785422175992497300901759925043985017599250485594
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004642235192235194194304256008243109760x7f1ce60ede000x7f1ce58266007268987268984538358151926553656127184756956670224682959217599250497754175992504398501759925114625017599251191836
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004672235192235194194304256008243132160x7f1ce60edc800x7f1ce5826640136659713665977708210932784655361065672643108162290426443166817599251202856175992511462501759925226305117599252307888
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004702235192235194194304256008243159680x7f1ce60edb000x7f1ce5826680137202413720247778210976200655361078387006108510640431528995617599252326697175992522630511759925337393117599253438249
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047322351922351941943042560012243187200x7f1ce60ed9800x7f1ce58266c0137124713712477751810969984655361075762186108553520430478994017599253449938175992533739311759925452593217599254595319
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047622351922351941943042560012243214720x7f1ce60ed8000x7f1ce5826700137255313725537747710980432655361073980519108505840429766272017599254607839175992545259321759925568625217599255751820
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004792235192235194194304256008243242240x7f1ce60ed6800x7f1ce5826740137467313746737710610997392655361076734019108806240430867855217599255763570175992556862521759925681697317599256888421
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004822235192235194194304256008243264640x7f1ce88905000x7f1ce58267802664917266491714314121319344655362130988346211877940852569498017599256899991175992568169731759925879521417599258866681
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004852235192235194194304256008243292160x7f1ce88903800x7f1ce58267c02666982266698214245421335864655362131372878212215920852723270417599258887370175992587952141759926074065417599260807081
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048822351922351941943042560012243319680x7f1ce88902000x7f1ce58268002671177267117714338521369424655362133795562212402290853692326017599260818851175992607406541759926273969517599262809690
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049122351922351941943042560012243347200x7f1ce88900800x7f1ce58268402667766266776614294321342136655362126319326212254800850701714817599262822020175992627396951759926474513617599264813360
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004942235192235194194304256008243374720x7f1ce60edf000x7f1ce58268802672975267297514295921383808655362135790377212632560854490333617599264824699175992647451361759926669601717599266764750
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049722351922351941943042560082400x7f1ce60edd800x7f1ce58268c052555545255554272964420444406553642327563624192660401693276686417599266776960175992666960171759927033425817599270406228