Files
rocm-systems/tests/workloads/LDS/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.kd000181810181810335544322560043241600x00x7f42bde04280383039383039890430643205242882416511992976525098286071216906212789798169055050407201690635726287416906357372203
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00218181018181032768256001224138880x00x7f42bde23f8034254342543069427404051218695631752580749225616906362486000169063572628741690636261949916906362623886
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051818101818104194304256001224143360x7f42c0e263800x7f42bde23fc016742916742914593133944065536935431151236719037589526016906362668124169063626194991690636301053816906363013154
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081818101818104194304256001624150400x7f42c0e262000x7f42bde24000321997321997236112575984655362352583892471745094276303216906363058913169063630105381690636344221716906363448711
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111818101818104194304256001624154880x7f42c0e260800x7f42bde24040321221321221235032569776655362354932852465722094370344016906363486230169063634422171690636386749616906363872458
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141818101818104194304256001224159360x7f42be803f000x7f42bde2408016765716765715089134126465536944006821234789037932686416906363911847169063638674961690636420173516906364203958
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171818101818104194304256001224163840x7f42be803d800x7f42bde240c017067917067916294136544065536965791751258781038804420416906364243617169063642017351690636452845416906364530749
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201818101818104194304256001224170880x7f42be803c000x7f42bde24100167860167860162751342888655361111081611238117044616196416906364584577169063645284541690636485101316906364853219
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231818101818104194304256001624177920x7f42be803a800x7f42bde24140320981320981243642567856655362410234832466817096582251216906364893348169063648510131690636528141216906365286706
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261818101818104194304256001624184960x7f42be8039000x7f42bde24180318527318527233772548224655362329675552443016093360037216906365324395169063652814121690636570029116906365702573
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291818101818104194304256001624192000x7f42be8037800x7f42bde241c0167700167700153361341608655361038197991235999041700874816906365742942169063657002911690636602573116906366028074
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321818101818104194304256001624199040x7f42be8036000x7f42bde24200168470168470156611347768655361067828261242922042885859616906366069582169063660257311690636638925016906366391493
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351818101818104194304256001224206080x7f42c0e264800x7f42bde24240170029170029163831360240655361126401991256165045228369216906366441451169063663892501690636671836916906366720643
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381818101818104194304256001624213120x7f42c0e263000x7f42bde24280322316322316244412578536655362426447092476535097230704816906366762002169063667183691690636711532816906367117201
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411818101818104194304256001624220160x7f42c0e261800x7f42bde242c0316627316627233422533024655362276560522428705091235488416906367160740169063671153281690636751084716906367512339
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441818101818104194304256001624227200x7f42c0e260000x7f42bde24300168460168460159151347688655361058056331244039042494715216906367553668169063675108471690636781148616906367812980
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471818101818104194304256001224234240x7f42be803e800x7f42bde24340166368166368156571330952655361112702221228462044680027216906367853799169063678114861690636810396516906368105272
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501818101818104194304256001224241280x7f42be803d000x7f42bde24380169297169297166041354384655361114294731246606044744308816906368153530169063681039651690636840140416906368402893
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531818101818104194304256001624248320x7f42be803b800x7f42bde243c0321267321267256642570144655362389021232458813095733876816906368444451169063684014041690636879036316906368793271
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561818101818104194304256001624255360x7f42be803a000x7f42bde24400316693316693234852533552655362308093752430536092497082016906368833420169063687903631690636917596216906369177500
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591818101818104194304256001224262400x7f42be8038800x7f42bde24440167403167403161771339232655361098519141235304044113247216906369218018169063691759621690636947196216906369473491
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621818101818104194304256001224269440x7f42be8037000x7f42bde24480169477169477161491355824655361075681631250786043199427616906369514339169063694719621690636976844116906369769992
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651818101818104194304256001224276480x7f42c0e265800x7f42bde244c0166047166047155631328384655361089558541225746043755382416906369817940169063697684411690637006876016906370070503
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681818101818104194304256001624286080x7f42c0e264000x7f42bde24500318353318353254202546832655362355871122439009094407980016906370116292169063700687601690637047371916906370475371
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711818101818104194304256001624293120x7f42c0e262800x7f42bde24540314869314869235512518960655362289968982414281091771717216906370516889169063704737191690637086091816906370862609
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741818101818104194304256001224300160x7f42c0e261000x7f42bde24580167086167086155871336696655361121598331233869045036556416906370903368169063708609181690637115611716906371157600
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077181810181810419430425600824309760x7f42be803f800x7f42bde245c0169371169371158471354976655361049394791248271042148538416906371199129169063711561171690637145211716906371453741
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801818101818104194304256001224316800x7f42be803e000x7f42bde24600165580165580161321324648655361075515961220026043192519616906371502030169063714521171690637175067616906371752422
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831818101818104194304256001624326400x7f42be803c800x7f42bde24640314321314321251322514576655362327525702407550093274430416906371793311169063717506761690637214043516906372141951
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861818101818104194304256001224336000x7f42be803b000x7f42bde24680312814312814237192502520655362257880172395784090488156816906372182190169063721404351690637252651416906372528149
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891818101818104194304256001224345600x7f42be8039800x7f42bde246c0167819167819152251342560655361056328511237429042425702816906372569328169063725265141690637282811316906372829800
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092181810181810419430425600824355200x7f42be8038000x7f42bde24700167680167680152701341448655361023890271238504041127789616906372870239169063728281131690637312427216906373125741
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951818101818104194304256001224362240x7f42be8036800x7f42bde24740168978168978162981351832655361132832931243410045485389616906373173450169063731242721690637342459216906373426152
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981818101818104194304256001224371840x7f42c0e265000x7f42bde24780313393313393246782507152655362339040802405571093734880416906373466901169063734245921690637380875116906373810491
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011818101818104194304256001224381440x7f42c0e263800x7f42bde247c0314211314211252172513696655362283358612403592091507425216906373851609169063738087511690637419627016906374198159
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041818101818104194304256001224391040x7f42c0e262000x7f42bde24800168641168641160131349136655361048903161241555042128701616906374238758169063741962701690637450346916906374505190
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107181810181810419430425600824403200x7f42c0e260800x7f42bde24840171087171087164561368704655361001743041260904040241789216906374546189169063745034691690637480442816906374805901
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101818101818104194304256001224412800x7f42be803f000x7f42bde24880168083168083164641344672655361079222191236109043341071216906374853889169063748044281690637510682716906375108432
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131818101818104194304256001224422400x7f42be803d800x7f42bde248c0314017314017241622512144655362344367462406100093947595216906375148531169063751068271690637549466616906375496350
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161818101818104194304256001224432000x7f42be803c000x7f42bde24900309817309817247722478544655362254750792372293090363256016906375537029169063754946661690637587898516906375880589
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119181810181810419430425600824441600x7f42be803a800x7f42bde24940167157167157147431337264655361069044371234935042933958816906375920668169063758789851690637617386516906376175540
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221818101818104194304256001224453760x7f42be8039000x7f42bde24980167831167831158421342656655361017529951235990040873095216906376215269169063761738651690637647018416906376471801
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251818101818104194304256001224463360x7f42be8037800x7f42bde249c0168352168352161141346824655361033885911237136041527654816906376519040169063764701841690637677290316906376774412
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281818101818104194304256001224475520x7f42be8036000x7f42bde24a00310410310410248352483288655362309100892379227092536895216906376815931169063767729031690637715754216906377158961
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311818101818104194304256001224485120x7f42c0e264800x7f42bde24a40306861306861232412454896655362141174322347100085820470016906377200879169063771575421690637754010116906377541659
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134181810181810419430425600824494720x7f42c0e263000x7f42bde24a80168469168469147851347760655361040619661240420041797402416906377582458169063775401011690637783658016906377838180
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371818101818104194304256001224506880x7f42c0e261800x7f42bde24ac0167744167744165921341960655361005926031233607040410023616906377879069169063778365801690637813354016906378135601
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401818101818104194304256001224516480x7f42c0e260000x7f42bde24b00166683166683159361333472655361008578061226083040515676416906378183620169063781335401690637843241916906378434083
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431818101818104194304256001224528640x7f42be803e800x7f42bde24b40309858309858249272478872655362279881392370045091368315616906378475391169063784324191690637881577816906378817581
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461818101818104194304256001224540800x7f42be803d000x7f42bde24b80307281307281234502458256655362209819722350882088565794416906378857490169063788157781690637920233716906379203920
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149181810181810419430425600824552960x7f42be803b800x7f42bde24bc016748616748615008133989665536990677121236204039798934416906379243388169063792023371690637949865616906379500271
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521818101818104194304256001224567680x7f42be803a000x7f42bde24c00169099169099165121352800655361054133861246352042337578416906379540450169063794986561690637979721616906379798822
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551818101818104194304256001224577280x7f42be8038800x7f42bde24c40169496169496169761355976655361043424421248088041908863216906379846840169063797972161690638010041516906380102063
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581818101818104194304256001224589440x7f42be8037000x7f42bde24c80310176310176251342481416655362279324522370208091346462816906380142802169063801004151690638048457416906380485991
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611818101818104194304256001224601600x7f42c0e265800x7f42bde24cc0305030305030232762440248655362177969632328507087291708416906380526100169063804845741690638086825316906380869760
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164181810181810419430425600824613760x7f42c0e264000x7f42bde24d00167330167330159361338648655361003039241236055040293754816906380910619169063808682531690638117001216906381171661
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671818101818104194304256001224628480x7f42c0e262800x7f42bde24d40172075172075163861376608655361082587451270811043476785616906381214450169063811700121690638148601116906381487771
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701818101818104194304256001224638080x7f42c0e261000x7f42bde24d80167460167460164281339688655361046084501232225042015460416906381536220169063814860111690638178361016906381785173
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731818101818104194304256001224650240x7f42be803f800x7f42bde24dc0305203305203235652441632655362249207342334464090141574416906381826151169063817836101690638216712916906382169451
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761818101818104194304256001224662400x7f42be803e000x7f42bde24e00303350303350228782426808655362165296952317030086785516416906382209840169063821671291690638255576816906382557309
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179181810181810419430425600824674560x7f42be803c800x7f42bde24e40168338168338155461346712655361024457901240610041150749616906382597488169063825557681690638285320816906382854870
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821818101818104194304256001224689280x7f42be803b000x7f42bde24e80177280177280171751418248655361117760851308879044883970416906382895079169063828532081690638315624716906383157791
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851818101818104194304256001224701440x7f42be8039800x7f42bde24ec016742816742816226133943265536999513321234104040153598416906383207050169063831562471690638345896616906383460542
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881818101818104194304256001224716160x7f42be8038000x7f42bde24f00304440304440245002435528655362189007902324879087733582816906383501161169063834589661690638383944516906383841141
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911818101818104194304256001224728320x7f42be8036800x7f42bde24f40303110303110228782424888655362235174532320354089579927616906383882920169063838394451690638422152416906384223089
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194181810181810419430425600824740480x7f42c0e265000x7f42bde24f8016753316753316129134027265536955371001228365038387695616906384262838169063842215241690638451832416906384519730
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971818101818104194304256001224757760x7f42c0e263800x7f42bde24fc0182307182307171361458464655361144458261354054045952276816906384560339169063845183241690638483464316906384836341
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001818101818104194304256001224769920x7f42c0e262000x7f42bde25000167708167708163791341672655361033469921239145041511976816906384895749169063848346431690638513192216906385133472
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031818101818104194304256001224784640x7f42c0e260800x7f42bde25040305249305249242422442000655362208089262331595088496860016906385174391169063851319221690638551576116906385517381
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061818101818104194304256001224799360x7f42be803f000x7f42bde25080304042304042231122432344655362219520322328996088953916416906385557829169063855157611690638590376016906385905359
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209181810181810419430425600824814080x7f42be803d800x7f42bde250c0171492171492169621371944655361000944161261199040210185216906385944778169063859037601690638621271916906386214210
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121818101818104194304256001224831360x7f42be803c000x7f42bde25100191254191254180571530040655361236328831423572049626933616906386254468169063862127191690638652759816906386529200
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151818101818104194304256001224843520x7f42be803a800x7f42bde25140167191167191149141337536655361047523491233711042073508416906386576909169063865275981690638682599816906386827561
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181818101818104194304256001224858240x7f42be8039000x7f42bde25180308485308485252312467888655362262252622357301090663516816906386868410169063868259981690638721079716906387212410
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211818101818104194304256001224872960x7f42be8037800x7f42bde251c0304321304321241862434576655362174358922330799087147648416906387252879169063872107971690638759383616906387595468
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241818101818104194304256001224887680x7f42be8036000x7f42bde25200170227170227169681361824655361031936821247476041449895216906387635387169063875938361690638789399516906387895629
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271818101818104194304256001224907520x7f42c0e264800x7f42bde25240201189201189180191609520655361258243761497569050503801616906387936088169063878939951690638821991416906388221570
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301818101818104194304256001224919680x7f42c0e263000x7f42bde25280168663168663167751349312655361055223081238587042381796016906388270018169063882199141690638851815316906388519661
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331818101818104194304256001224934400x7f42c0e261800x7f42bde252c0305737305737245002445904655362242731882334859089882625616906388560340169063885181531690638890231216906388903889
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361818101818104194304256001224949120x7f42c0e260000x7f42bde25300304245304245234572433968655362178035762327677087294792416906388944278169063889023121690638928359116906389285338
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391818101818104194304256001224963840x7f42be803e800x7f42bde2534016904916904917479135240065536999636381242269040158317216906389324637169063892835911690638958151116906389582939
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421818101818104194304256001224983680x7f42be803d000x7f42bde25380210257210257186291682064655361355801661574804054406336816906389623368169063895815111690638990471016906389906179
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451818101818104194304256001224995840x7f42be803b800x7f42bde253c016682516682515584133460865536959762871227536038563314016906389953308169063899047101690639022134916906390223010
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024818181018181041943042560012241013120x7f42be803a000x7f42bde25400303097303097245282424784655362213036422320191088694964816906390263689169063902213491690639061062816906390612128
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025118181018181041943042560012241027840x7f42be8038800x7f42bde25440304225304225234902433808655362185235782322281087582458016906390652807169063906106281690639099238716906390994117
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025418181018181041943042560012241042560x7f42be8037000x7f42bde25480169741169741166131357936655361034549091254293041554952016906391033616169063909923871690639129190616906391293578
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025718181018181041943042560012241062400x7f42c0e265800x7f42bde254c0219267219267194771754144655361367156711643728054861626816906391334307169063912919061690639162086516906391622298
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026018181018181041943042560012241077120x7f42c0e264000x7f42bde25500166965166965150781335728655361017631811232159040877956416906391671787169063916208651690639192214516906391923669
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026318181018181041943042560016241094400x7f42c0e262800x7f42bde25540301734301734232722413880655362148807642306943086125666816906391965848169063919221451690639230134416906392302948
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026618181018181041943042560016241111680x7f42c0e261000x7f42bde25580303320303320229652426568655362180716172320993087401852416906392344607169063923013441690639268230316906392684037
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691818101818104194304256008241128960x7f42be803f800x7f42bde255c0170674170674162501365400655361065193551261447042780864816906392724145169063926823031690639298486216906392986477
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027218181018181041943042560012241151360x7f42be803e000x7f42bde25600230788230788201751846312655361514339821734488060748105616906393026146169063929848621690639332278116906393324297
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027518181018181041943042560012241166080x7f42be803c800x7f42bde2564016764016764015797134112865536993449831230829039910546416906393371936169063933227811690639361942016906393621079
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027818181018181041943042560016241183360x7f42be803b000x7f42bde25680299876299876228162399016655362175514102290375087193691216906393661457169063936194201690639399813916906393999867
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028118181018181041943042560016241200640x7f42be8039800x7f42bde256c0302426302426225822419416655362105618772312645084398389616906394039926169063939981391690639439093816906394392645
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028418181018181041943042560012241217920x7f42be8038000x7f42bde25700170846170846164251366776655361085200341260047043580894416906394432854169063943909381690639469173816906394693406
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028718181018181041943042560012241240320x7f42be8036800x7f42bde25740240514240514207571924120655361460702731806179058602394016906394732945169063946917381690639503957716906395041236
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029018181018181041943042560012241255040x7f42c0e265000x7f42bde25780169955169955162161359648655361047551171254851042074382416906395088555169063950395771690639534261616906395344217
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029318181018181041943042560012241274880x7f42c0e263800x7f42bde257c0302211302211216572417696655362106411632312473084429793216906395390336169063953426161690639573317516906395734705
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029618181018181041943042560012241292160x7f42c0e262000x7f42bde25800299961299961220342399696655362119066932295711084936435616906395776894169063957331751690639611605416906396117684
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029918181018181041943042560012241309440x7f42c0e260800x7f42bde25840172078172078172201376632655361079092931269920043337996416906396158572169063961160541690639641493316906396416665
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030218181018181041943042560012241334400x7f42be803f000x7f42bde25880258889258889211552071120655361730141521959327069380828416906396457383169063964149331690639676933216906396770964
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030518181018181041943042560012241349120x7f42be803d800x7f42bde258c0170539170539171891364320655361032285131255006041464061216906396818703169063967693321690639707381216906397075265
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030818181018181041943042560012241368960x7f42be803c000x7f42bde25900301742301742229132413944655362131501322304600085433719616906397115604169063970738121690639746117116906397462873
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031118181018181041943042560012241388800x7f42be803a800x7f42bde25940299444299444220862395560655362154618002290807086358496016906397503102169063974611711690639784357016906397845322
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031418181018181041943042560012241408640x7f42be8039000x7f42bde25980179261179261176991434096655361181801531324468047445540816906397884841169063978435701690639814948916906398151613
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031718181018181041943042560012241436160x7f42be8037800x7f42bde259c0281143281143233132249152655361994537252127906079956088016906398192141169063981494891690639852228816906398524162
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032018181018181041943042560012241453440x7f42be8036000x7f42bde25a00170478170478175631363832655361029410951249280041349492816906398572020169063985222881690639882884716906398830352
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032318181018181041943042560012241475840x7f42c0e264800x7f42bde25a40301503301503243122412032655362127063532300082085256080416906398876921169063988288471690639922084616906399222631
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032618181018181041943042560012241495680x7f42c0e263000x7f42bde25a80302254302254235662418040655362141496962306610085833762816906399263379169063992208461690639960420516906399605669
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032918181018181041943042560012241515520x7f42c0e261800x7f42bde25ac0186043186043178201488352655361184445621377487047551792016906399645908169063996042051690639992004416906399921620
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033218181018181041943042560012241543040x7f42c0e260000x7f42bde25b00298589298589234432388720655362086181272282931083622072416906399963079169063999200441690640029764316906400299159
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033518181018181041943042560012241562880x7f42be803e800x7f42bde25b40172869172869171081382960655361096831071279273044047114016906400347327169064002976431690640060484316906400606369
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033818181018181041943042560012241587840x7f42be803d000x7f42bde25b80303345303345222082426768655362035995922322159081614274416906400646028169064006048431690640098804216906400989748
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034118181018181041943042560012241610240x7f42be803b800x7f42bde25bc0305119305119232722440960655362110158132330780084580696016906401030407169064009880421690640137508116906401376626
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034418181018181041943042560012241632640x7f42be803a000x7f42bde25c00206905206905182841655248655361283714161546548051523420416906401416455169064013750811690640169668016906401698357
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034718181018181041943042560012241665280x7f42be8038800x7f42bde25c40341931341931268612735456655362346651612612188094041183216906401737946169064016966801690640210275916906402127664
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035018181018181041943042560012241685120x7f42be8037000x7f42bde25c80185381185381175341483056655361011473221367754040633503616906402153043169064021027591690640242851816906402430045
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035318181018181041943042560012241712640x7f42c0e265800x7f42bde25cc0302577302577225492420624655362031516042307779081436583616906402470404169064024285181690640281331716906402814803
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035618181018181041943042560012241737600x7f42c0e264000x7f42bde25d00301214301214223932409720655362033668662298442081521595216906402855802169064028133171690640319731616906403198912
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035918181018181041943042560012241762560x7f42c0e262800x7f42bde25d40224878224878197941799032655361486554491691404059636650416906403239271169064031973161690640353059516906403532392
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036218181018181041943042560012241797760x7f42c0e261000x7f42bde25d803804503804502796430436086553627179164829334050108892072416906403572781169064035305951690640396579416906403986678
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036518181018181041943042560012241822720x7f42be803f800x7f42bde25dc0211140211140190861689128655361338522791576805053715695616906404015807169064039657941690640429971316906404301269
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036818181018181041943042560012241855360x7f42be803e000x7f42bde25e00303948303948239002431592655361912848482323771076689259616906404342547169064042997131690640468883216906404691597
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037118181018181041943042560012241885440x7f42be803c800x7f42bde25e40309817309817220442478544655361987505552363753079676262416906404730416169064046888321690640508515116906405102665
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037418181018181041943042560012241915520x7f42be803b000x7f42bde25e80266221266221218492129776655361772075012017987071058360416906405127054169064050851511690640544675016906405448234
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037718181018181041943042560012241958400x7f42be8039800x7f42bde25ec04620144620143184336961206553633731408935803810135101622016906405488063169064054467501690640593090916906405948199
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038018181018181041943042560012241985920x7f42be8038000x7f42bde25f00244267244267210431954144655361577776041841719063286399216906405980498169064059309091690640630226816906406304119
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038318181018181041943042560012242023680x7f42be8036800x7f42bde25f40334684334684228952677480655362025003652566424081177151616906406344157169064063022681690640671938716906406765165
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038618181018181041943042560012242058880x7f42c0e265000x7f42bde25f80330785330785261742646288655362189469082517351087755086016906406776465169064067193871690640715058616906407195582
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038918181018181041943042560012242094080x7f42c0e263800x7f42bde25fc0306420306420239042451368655362165469972340889086794198016906407206432169064071505861690640756402516906407565681
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039218181018181041943042560012242144640x7f42c0e262000x7f42bde260005432595432593601243460806553640601766542339270162583124016906407606940169064075640251690640810290416906408145494
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039518181018181041943042560012242177280x7f42c0e260800x7f42bde26040273640273640221002189128655361723272922077964069106881216906408165173169064081029041690640849106316906408492623
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039818181018181041943042560012242220160x7f42be803f000x7f42bde26080365893365893295342927152655362400231812806836096186986016906408538122169064084910631690640892610116906408968319
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040118181018181041943042560012242260480x7f42be803d800x7f42bde260c03624863624862705028998966553625390157927812370101737152416906408978849169064089261011690640937442016906409392166
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040418181018181041943042560012242300800x7f42be803c000x7f42bde26100347084347084257872776680655362474865532666742099170360416906409416266169064093744201690640978721916906409802374
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040718181018181041943042560012242359040x7f42be803a800x7f42bde261406236726236724007249893846553647419455048711260189854269216906409828803169064097872191690641037409816906410395006
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041018181018181041943042560012242394240x7f42be8039000x7f42bde26180303466303466237152427736655362020557012316396080998530816906410424516169064103740981690641077233716906410773835
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041318181018181041943042560012242442240x7f42be8037800x7f42bde261c03972123972122755931777046553626363375530606720105631380016906410814124169064107723371690641122257616906411243891
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041618181018181041943042560012242487680x7f42be8036000x7f42bde262003909143909142777231273206553628408175730186540113809851216906411263441169064112225761690641167521416906411692538
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041918181018181041943042560012242533120x7f42c0e264800x7f42bde262403877083877082850731016726553628158431429892500112809603616906411717927169064116752141690641211633316906412133715
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221818101818104194304256008242555520x7f42c0e263000x7f42bde262807203647203644650657629206553653446112156334840213958515616906412158164169064121163331690641276897216906412786435
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042518181018181041943042560012242598400x7f42c0e261800x7f42bde262c03658793658792774429270406553625663506028041760102829884016906412819144169064127689721690641320049116906413217072
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042818181018181041943042560012242656640x7f42c0e260000x7f42bde263004684704684703177337477686553634817283536415720139447514016906413242711169064132004911690641369840916906413714557
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043118181018181041943042560012242712320x7f42be803e800x7f42bde263404715064715063197237720566553635164049236673180140834604816906413740177169064136984091690641420352816906414224872
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341818101818104194304256008242732160x7f42be803d000x7f42bde263804838684838683362238709526553635127568437550750140684347216906414246382169064142035281690641470768716906414749736
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371818101818104194304256008242757120x7f42be803b800x7f42bde263c08807418807415341570459366553667600905969342760270577770816906414759906169064147076871690641548416516906415526753
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044018181018181041943042560012242807680x7f42be803a000x7f42bde264004265844265842987934126806553631116166333057610124641427216906415545812169064154841651690641596832416906416010479
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044318181018181041943042560012242876160x7f42be8038800x7f42bde264405482755482753587243862086553640943743142763810163953501216906416021748169064159683241690641653680216906416579271
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044618181018181041943042560012242942080x7f42be8037000x7f42bde264805512765512763578544102166553641623693943007700166673250816906416589131169064165368021690641710736116906417149054
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491818101818104194304256008242969600x7f42c0e265800x7f42bde264c05648075648073741445184646553641037804243940660164325534816906417159704169064171073611690641767455916906417692868
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521818101818104194304256008242999680x7f42c0e264000x7f42bde26500104252510425256094383402086553680521065282197110322258393616906417716317169064176745591690641853983716906418588551
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551818101818104194304256008243027200x7f42c0e262800x7f42bde265407227067227064508557816566553654379559356613590217692321216906418607861169064185398371690641921999516906419264461
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045818181018181041943042560012243054720x7f42c0e261000x7f42bde265807237257237254485157898086553655128745456687980220689077616906419275451169064192197741690641990601216906419954070
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046118181018181041943042560012243082240x7f42be803f800x7f42bde265c07218127218124499457745046553654508672256641670218208625616906419965150169064199060121690642060680916906420651080
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641818101818104194304256008243109760x7f42be803e000x7f42bde266007260937260934455558087526553655929778356928060223893280816906420662249169064206068091690642129592716906421339399
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671818101818104194304256008243132160x7f42be803c800x7f42bde26640136798513679857796710943888655361067622701108192520427223276016906421350149169064212959271690642240024316906422446396
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701818101818104194304256008243159680x7f42be803b000x7f42bde26680137225913722597754810978080655361069447636108531040427953216816906422466295169064224002431690642350744016906423572762
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047318181018181041943042560012243187200x7f42be8039800x7f42bde266c0137287113728717789710982976655361064015513108622820425780327616906423584582169064235074401690642465463616906424719698
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047618181018181041943042560012243214720x7f42be8038000x7f42bde26700137340013734007748810987208655361073914331108558730429739890416906424730397169064246546361690642579735316906425861963
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791818101818104194304256008243242240x7f42be8036800x7f42bde26740137607713760777887911008624655361084523263108809980433983552016906425872783169064257973531690642691527016906426985550
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821818101818104194304256008243264640x7f42c0e265000x7f42bde267802664968266496814222221319752655362128950921211833760851754587616906426996900169064269152701690642888454416906428950931
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851818101818104194304256008243292160x7f42c0e263800x7f42bde267c02669053266905314262021352432655362129286680212270920851888702016906428970011169064288845441690643081061816906430880374
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048818181018181041943042560012243319680x7f42c0e262000x7f42bde268002673088267308814443921384712655362133605641212431330853616370816906430892443169064308106181690643280661216906432872164
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049118181018181041943042560012243347200x7f42c0e260800x7f42bde268402669467266946714311021355744655362123842847212269450849711210416906432883824169064328066121690643479092616906434864265
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941818101818104194304256008243374720x7f42be803f000x7f42bde268802675746267574614379221405976655362119073866212665170847803738016906434875304169064347909261690643674132016906436812376
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049718181018181041943042560082400x7f42be803d800x7f42bde268c052565735256573273978420525926553642292299854192971901691866124816906436823096169064367413201690644036675016906440437678