Fichiers
rocm-systems/tests/workloads/L2/mi200/SQ_IFETCH_LEVEL.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

44 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjGRBM_COUNTGRBM_GUI_ACTIVESQ_WAVESSQ_IFETCHSQ_IFETCH_LEVELSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000175157175157335544322560043241600x00x7fc664e0428038092938092952428847185926831477643869616791755331355167910471556311679190176041816791901870857
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00217515717515732768256001224138880x00x7fc664e23f8033336333365128192556563382816791907048544167919017604181679190718247816791907187250
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051751571751574194304256001224143360x7fc667eb53800x7fc664e23fc0164297164297655369175041420231590944416791907224319167919071824781679190756039616791907563038
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081751571751574194304256001624150400x7fc667eb52000x7fc664e240003081963081966553611141121699261902661616791907601317167919075603961679190797559516791907978045
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111751571751574194304256001624154880x7fc667eb50800x7fc664e24040310425310425655369175041398301557154416791908013464167919079755951679190837959316791908382112
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141751571751574194304256001224159360x7fc665887f000x7fc664e240801657401657406553610485761588571776995616791908417831167919083795931679190870343216791908705742
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171751571751574194304256001224163840x7fc665887d800x7fc664e240c0165453165453655369830401479131654758416791908741531167919087034321679190901831116791909020592
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201751571751574194304256001224170880x7fc665887c000x7fc664e241001634461634466553611141121634321828000816791909067221167919090183111679190933159016791909333812
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231751571751574194304256001624177920x7fc665887a800x7fc664e241403085363085366553613107201957462192329216791909370651167919093315901679190973094816791909733140
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261751571751574194304256001624184960x7fc6658879000x7fc664e241803105203105206553611796481779421991896816791909767179167919097309481679191014646716791910149497
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291751571751574194304256001624192000x7fc6658877800x7fc664e241c01665901665906553612451841928582165668416791910183786167919101464671679191046886616791910471407
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321751571751574194304256001624199040x7fc6658876000x7fc664e242001640111640116553612451841863552091077216791910507156167919104688661679191078214516791910784497
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351751571751574194304256001224206080x7fc667eb54800x7fc664e242401649241649246553612451841902292134056016791910828406167919107821451679191109414416791911095917
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381751571751574194304256001624213120x7fc667eb53000x7fc664e242803089763089766553614417922150772415229216791911132936167919110941441679191146486216791911466715
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411751571751574194304256001624220160x7fc667eb51800x7fc664e242c03103043103046553613107202001332236128416791911502144167919114648621679191183750116791911839124
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441751571751574194304256001624227200x7fc667eb50000x7fc664e243001648221648226553613762562072572321862416791911874253167919118375011679191212358016791912125285
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471751571751574194304256001224234240x7fc665887e800x7fc664e243401640841640846553614417922173622431330816791912161213167919121235801679191240565916791912407356
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501751571751574194304256001224241280x7fc665887d000x7fc664e243801637641637646553613107201958212194945216791912449444167919124056591679191269205816791912693767
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531751571751574194304256001624248320x7fc665887b800x7fc664e243c03082783082786553615728642343212630909616791912729526167919126920581679191306245716791913064115
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561751571751574194304256001624255360x7fc665887a000x7fc664e244003077763077766553614417922088642338088016791913099334167919130624571679191343301516791913434723
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591751571751574194304256001224262400x7fc6658878800x7fc664e244401644001644006553615073282233382507825216791913469082167919134330151679191372117416791913722814
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621751571751574194304256001224269440x7fc6658877000x7fc664e244801634221634226553616384002438912726078416791913757743167919137211741679191400245316791914004075
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651751571751574194304256001224276480x7fc667eb55800x7fc664e244c01629421629426553614417922267462543217216791914046214167919140024531679191429253216791914294536
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681751571751574194304256001624286080x7fc667eb54000x7fc664e245003080613080616553617039362524822830618016791914329745167919142925321679191466885116791914670554
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711751571751574194304256001624293120x7fc667eb52800x7fc664e245403067913067916553615728642338782618313216791914705613167919146688511679191503924916791915041173
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741751571751574194304256001224300160x7fc667eb51000x7fc664e245801617611617616553616384002431412717845216791915075912167919150392491679191532612816791915327894
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077175157175157419430425600824309760x7fc665887f800x7fc664e245c01629451629456553618350082748023077635216791915362843167919153261281679191560948716791915611155
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801751571751574194304256001224316800x7fc665887e000x7fc664e246001624451624456553615073282262322532880416791915653364167919156094871679191589220616791915894026
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831751571751574194304256001624326400x7fc665887c800x7fc664e246403074613074616553618350082817333158785216791915928855167919158922061679191626324516791916264945
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861751571751574194304256001224336000x7fc665887b000x7fc664e246803075993075996553617039362493112789470816791916299313167919162632451679191663396416791916635673
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891751571751574194304256001224345600x7fc6658879800x7fc664e246c01626091626096553617694722636912952005216791916670602167919166339641679191691460316791916916294
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092175157175157419430425600824355200x7fc6658878000x7fc664e247001644491644496553620316163029763403373616791916951933167919169146031679191719828216791917200215
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951751571751574194304256001224362240x7fc6658876800x7fc664e247401651081651086553616384002634152946483216791917242534167919171982821679191748548116791917487196
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981751571751574194304256001224371840x7fc667eb55000x7fc664e247803058733058736553619660802895963245317616791917522605167919174854811679191786019916791917861954
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011751571751574194304256001224381440x7fc667eb53800x7fc664e247c03064543064546553618350082769073103612816791917897433167919178601991679191822931816791918231273
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041751571751574194304256001224391040x7fc667eb52000x7fc664e248001640741640746553619005442836573186394816791918267422167919182293181679191851619716791918517934
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107175157175157419430425600824403200x7fc667eb50800x7fc664e248401617561617566553622282243360093756942816791918552973167919185161971679191879859616791918800315
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101751571751574194304256001224412800x7fc665887f000x7fc664e248801625611625616553617039362548732853776416791918843104167919187985961679191908243516791919084106
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131751571751574194304256001224422400x7fc665887d800x7fc664e248c03066843066846553620971523106713482564016791919119935167919190824351679191945571416791919457444
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161751571751574194304256001224432000x7fc665887c000x7fc664e249003039353039356553619660802853803193607216791919493023167919194557141679191982627216791919827923
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119175157175157419430425600824441600x7fc665887a800x7fc664e249401646711646716553620316163072563446966816791919862841167919198262721679192011091116791920112634
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221751571751574194304256001224453760x7fc6658879000x7fc664e249801649011649016553624248323615494053118416791920148122167919201109111679192040051016791920402204
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251751571751574194304256001224463360x7fc6658877800x7fc664e249c01632131632136553618350082732453059407616791920444593167919204005101679192068786916791920689675
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281751571751574194304256001224475520x7fc6658876000x7fc664e24a003062793062796553622282243343563737078416791920726164167919206878691679192106146816791921063154
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311751571751574194304256001224485120x7fc667eb54800x7fc664e24a403029433029436553620971523082483461453216791921098712167919210614681679192143058716791921432312
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134175157175157419430425600824494720x7fc667eb53000x7fc664e24a801628571628576553621626883192223568171216791921467751167919214305871679192171042616791921712213
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371751571751574194304256001224506880x7fc667eb51800x7fc664e24ac01612051612056553626214403952194424218816791921747732167919217104261679192199394516791921995654
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401751571751574194304256001224516480x7fc667eb50000x7fc664e24b001607631607636553619660802972123324634016791922038273167919219939451679192228946416791922291075
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431751571751574194304256001224528640x7fc665887e800x7fc664e24b403046383046386553623592963598064032306816791922327474167919222894641679192266530216791922667113
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461751571751574194304256001224540800x7fc665887d000x7fc664e24b803023073023076553622282243315103721804416791922701782167919226653021679192303874116791923040641
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149175157175157419430425600824552960x7fc665887b800x7fc664e24bc01632931632936553622937603431173844812816791923075570167919230387411679192332178016791923323543
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521751571751574194304256001224567680x7fc665887a000x7fc664e24c001641591641596553627525124044124526570816791923358131167919233217801679192360465916791923606344
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551751571751574194304256001224577280x7fc6658878800x7fc664e24c401633171633176553620316163162773545322016791923649012167919236046591679192388785816791923889565
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581751571751574194304256001224589440x7fc6658877000x7fc664e24c803035653035656553624903683670744106849216791923924234167919238878581679192425889716791924260543
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611751571751574194304256001224601600x7fc667eb55800x7fc664e24cc03034743034746553623592963510423935641616791924296402167919242588971679192462945516791924631202
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164175157175157419430425600824613760x7fc667eb54000x7fc664e24d001627011627016553624248323653384088928816791924666490167919246294551679192491457416791924916253
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671751571751574194304256001224628480x7fc667eb52800x7fc664e24d401682901682906553629491204415814950022816791924951361167919249145741679192520321316791925204994
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701751571751574194304256001224638080x7fc667eb51000x7fc664e24d801627851627856553621626883356103763968016791925247582167919252032131679192549041216791925492145
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731751571751574194304256001224650240x7fc665887f800x7fc664e24dc03032963032966553626214403865824327130016791925528533167919254904121679192586049116791925862093
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761751571751574194304256001224662400x7fc665887e000x7fc664e24e003011633011636553624903683615324058085216791925897402167919258604911679192622896916791926230921
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179175157175157419430425600824674560x7fc665887c800x7fc664e24e401640861640866553625559043806784274112016791926266440167919262289691679192651936816791926521082
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821751571751574194304256001224689280x7fc665887b000x7fc664e24e801768271768276553631457284715495287873216791926556361167919265193681679192681104716791926812733
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851751571751574194304256001224701440x7fc6658879800x7fc664e24ec01604951604956553622282243331303736171616791926854572167919268110471679192709168616791927093394
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881751571751574194304256001224716160x7fc6658878000x7fc664e24f003030523030526553627525124071224560164416791927128583167919270916861679192745920516791927460863
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911751571751574194304256001224728320x7fc6658876800x7fc664e24f403062293062296553626214403970214443810016791927496521167919274592051679192782864416791927830341
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194175157175157419430425600824740480x7fc667eb55000x7fc664e24f801624061624066553626869764012904492717216791927864570167919278286441679192811456316791928116182
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971751571751574194304256001224757760x7fc667eb53800x7fc664e24fc01827471827476553633423365004025610430816791928151891167919281145631679192841072216791928412473
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001751571751574194304256001224769920x7fc667eb52000x7fc664e250001615501615506553623592963579003999969616791928466941167919284107221679192869440116791928696214
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031751571751574194304256001224784640x7fc667eb50800x7fc664e250403038973038976553628835844393714916530416791928732892167919286944011679192906703916791929068942
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061751571751574194304256001224799360x7fc665887f000x7fc664e250803011893011896553626869763980304454049616791929104271167919290670391679192943615816791929437840
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209175157175157419430425600824814080x7fc665887d800x7fc664e250c01622481622486553628180484200134700681616791929472999167919294361581679192971791716791929719561
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121751571751574194304256001224831360x7fc665887c000x7fc664e251001929981929986553635389445509176170940416791929754010167919297179171679193002143616791930023022
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151751571751574194304256001224843520x7fc665887a800x7fc664e251401606861606866553624248323639324083627216791930065970167919300214361679193032111516791930322862
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181751571751574194304256001224858240x7fc6658879000x7fc664e251803010583010586553630146564785415356936416791930357811167919303211151679193069759416791930699281
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211751571751574194304256001224872960x7fc6658877800x7fc664e251c02999662999666553628180484165344670084016791930734190167919306975941679193106879216791931070759
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241751571751574194304256001224887680x7fc6658876000x7fc664e252001619581619586553629491204396304921475216791931104888167919310687921679193135359116791931355250
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271751571751574194304256001224907520x7fc667eb54800x7fc664e252402027142027146553637355525597186270513216791931390809167919313535911679193166239016791931664090
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301751571751574194304256001224919680x7fc667eb53000x7fc664e252801617311617316553625559043841204295291616791931706369167919316623901679193194478916791931946442
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331751571751574194304256001224934400x7fc667eb51800x7fc664e252c03009803009806553631457284717975295406016791931982360167919319447891679193231022816791932311890
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361751571751574194304256001224949120x7fc667eb50000x7fc664e253003006623006626553629491204345864867186416791932346249167919323102281679193267758616791932679379
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391751571751574194304256001224963840x7fc665887e800x7fc664e253401623061623066553630801924637825200145616791932713667167919326775861679193295998516791932961730
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421751571751574194304256001224983680x7fc665887d000x7fc664e253802119902119906553639321605833466534468016791932996009167919329599851679193328014416791933281890
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451751571751574194304256001224995840x7fc665887b800x7fc664e253c01618261618266553626214403988874464783616791933323398167919332801441679193356494316791933566871
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024817515717515741943042560012241013120x7fc665887a000x7fc664e254003001403001406553632768004922485523665216791933600880167919335649431679193393630216791933938029
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025117515717515741943042560012241027840x7fc6658878800x7fc664e254403008183008186553630801924550765093644016791933973328167919339363021679193431662116791934318327
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025417515717515741943042560012241042560x7fc6658877000x7fc664e254801621961621966553632112644774325337649616791934352106167919343166211679193460606016791934607968
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025717515717515741943042560012241062400x7fc667eb55800x7fc664e254c02186032186036553641287686210286950552816791934642677167919346060601679193492669816791934928378
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026017515717515741943042560012241077120x7fc667eb54000x7fc664e255001617501617506553627525124075514564850016791934970267167919349266981679193521085716791935212649
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026317515717515741943042560016241094400x7fc667eb52800x7fc664e255402966962966966553634078725121065729067616791935249408167919352108571679193557805616791935579697
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026617515717515741943042560016241111680x7fc667eb51000x7fc664e255802986822986826553632112644863895449699216791935614066167919355780561679193595405516791935955775
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691751571751574194304256008241128960x7fc665887f800x7fc664e255c01627311627316553632768004909095503160816791935990084167919359540551679193624173416791936243426
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027217515717515741943042560012241151360x7fc665887e000x7fc664e256002294102294106553643253766450077223400016791936277955167919362417341679193656733316791936569176
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027517515717515741943042560012241166080x7fc665887c800x7fc664e256401622581622586553628180484394884911952016791936611085167919365673331679193685373216791936855377
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027817515717515741943042560016241183360x7fc665887b000x7fc664e256802975472975476553635389445369476021152416791936889306167919368537321679193722349016791937225175
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028117515717515741943042560016241200640x7fc6658879800x7fc664e256c02973312973316553634078725036025640550816791937259434167919372234901679193759356916791937595164
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028417515717515741943042560012241217920x7fc6658878000x7fc664e257001654391654396553634078725041545651232416791937629233167919375935691679193788076816791937882545
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028717515717515741943042560012241240320x7fc6658876800x7fc664e257402378392378396553645219846765827581616416791937917664167919378807681679193821372716791938216064
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029017515717515741943042560012241255040x7fc667eb55000x7fc664e257801623751623756553630146564759385323569616791938257493167919382137271679193850940616791938511225
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029317515717515741943042560012241274880x7fc667eb53800x7fc664e257c02991472991476553638010885660166337891216791938545884167919385094061679193888284416791938884653
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029617515717515741943042560012241292160x7fc667eb52000x7fc664e258002978612978616553636700165523136176166016791938920042167919388828441679193925356316791939255281
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029917515717515741943042560012241309440x7fc667eb50800x7fc664e258401705861705866553636700165585446251777616791939289880167919392535631679193954380216791939545522
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030217515717515741943042560012241334400x7fc665887f000x7fc664e258802598812598816553649152007493728386125616791939580781167919395438021679193988860116791939890201
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030517515717515741943042560012241349120x7fc665887d800x7fc664e258c01622341622346553631457284737195294067216791939932470167919398886011679194018060016791940182352
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030817515717515741943042560012241368960x7fc665887c000x7fc664e259002955752955756553640632326073156803503216791940217011167919401806001679194054987816791940551611
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031117515717515741943042560012241388800x7fc665887a800x7fc664e259402962282962286553639321606088526810047216791940586150167919405498781679194091899716791940920729
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031417515717515741943042560012241408640x7fc6658879000x7fc664e259801790551790556553639321606081736803926016791940953948167919409189971679194121771616791941219780
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031717515717515741943042560012241436160x7fc6658877800x7fc664e259c02798422798426553653084168007548975842416791941253109167919412177161679194157515516791941576948
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032017515717515741943042560012241453440x7fc6658876000x7fc664e25a001619291619296553633423365117535731007616791941619227167919415751551679194186523416791941867119
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032317515717515741943042560012241475840x7fc667eb54800x7fc664e25a402984882984886553643253767229488100964016791941901478167919418652341679194223691216791942238827
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032617515717515741943042560012241495680x7fc667eb53000x7fc664e25a802978912978916553641943046255277015085216791942273656167919422369121679194261035116791942612026
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032917515717515741943042560012241515520x7fc667eb51800x7fc664e25ac01870161870166553641943046256397013110016791942646705167919426103511679194291051016791942912226
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033217515717515741943042560012241543040x7fc667eb50000x7fc664e25b002995832995836553657016328623629668105616791942946735167919429105101679194328106916791943282755
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033517515717515741943042560012241562880x7fc665887e800x7fc664e25b401714301714306553637355525755296441691216791943324743167919432810691679194357658716791943578265
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033817515717515741943042560012241587840x7fc665887d000x7fc664e25b803006233006236553648496647580698494427216791943612374167919435765871679194395034616791943952004
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034117515717515741943042560012241610240x7fc665887b800x7fc664e25bc02982822982826553647185927252718118376016791943986213167919439503461679194432922516791944331192
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034417515717515741943042560012241632640x7fc665887a000x7fc664e25c002066252066256553647185927175308032033216791944365331167919443292251679194464138416791944643222
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034717515717515741943042560012241665280x7fc6658878800x7fc664e25c4034038634038665536648806497170210889958016791944677951167919446413841679194503850216791945061749
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035017515717515741943042560012241685120x7fc6658877000x7fc664e25c801848291848296553641287686325397091312416791945082118167919450385021679194534698116791945348730
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035317515717515741943042560012241712640x7fc667eb55800x7fc664e25cc02957812957816553653739528683929727800816791945383029167919453469811679194572186016791945723538
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035617515717515741943042560012241737600x7fc667eb54000x7fc664e25d002985532985536553652428808384919377564816791945758267167919457218601679194609513816791946097037
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035917515717515741943042560012241762560x7fc667eb52800x7fc664e25d402254532254536553652428807965028922856816791946133035167919460951381679194642729716791946428906
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036217515717515741943042560012241797760x7fc667eb51000x7fc664e25d80380685380685655367274496111414512471826416791946462655167919464272971679194685545616791946876352
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036517515717515741943042560012241822720x7fc665887f800x7fc664e25dc02118572118576553649152007601368518579616791946899281167919468554561679194718025516791947181932
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036817515717515741943042560012241855360x7fc665887e000x7fc664e25e00306383306383655366422528102727411503815616791947216871167919471802551679194756969316791947593039
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037117515717515741943042560012241885440x7fc665887c800x7fc664e25e40310071310071655366291456100439811251375616791947605309167919475696931679194796153216791947962998
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037417515717515741943042560012241915520x7fc665887b000x7fc664e25e8026649926649965536629145699270511123327216791947996817167919479615321679194831945116791948321206
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037717515717515741943042560012241958400x7fc6658879800x7fc664e25ec0461557461557655368847360133886014994622816791948355785167919483194511679194879432916791948814701
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038017515717515741943042560012241985920x7fc6658878000x7fc664e25f002427532427536553657016328914479979974416791948837510167919487943291679194913688816791949138581
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038317515717515741943042560012242023680x7fc6658876800x7fc664e25f40337505337505655367471104118535413286666416791949172700167919491368881679194953848616791949555078
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038617515717515741943042560012242058880x7fc667eb55000x7fc664e25f80332239332239655367340032116380113044514416791949574287167919495384861679194994216516791949958305
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038917515717515741943042560012242094080x7fc667eb53800x7fc664e25fc0308685308685655367340032112166512563371616791949977844167919499421651679195032936316791950331513
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039217515717515741943042560012242144640x7fc667eb52000x7fc664e260005444375444376553610420224160300017957272816791950366622167919503293631679195086360116791950906175
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039517515717515741943042560012242177280x7fc667eb50800x7fc664e2604027184927184965536648806499773711167711616791950925044167919508636011679195124904016791951250844
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039817515717515741943042560012242220160x7fc665887f000x7fc664e26080366276366276655368519680138489515511337616791951287123167919512490401679195166887916791951711470
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040117515717515741943042560012242260480x7fc665887d800x7fc664e260c0366540366540655368388608131823514756898416791951721679167919516688791679195211719716791952160046
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040417515717515741943042560012242300800x7fc665887c000x7fc664e26100347689347689655368388608128681514410632016791952171215167919521171971679195254807516791952590552
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040717515717515741943042560012242359040x7fc665887a800x7fc664e261406237706237706553611993088182585520441708416791952601072167919525480751679195315175316791953194523
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041017515717515741943042560012242394240x7fc6658879000x7fc664e26180303948303948655367274496113533312714608016791953212483167919531517531679195356151216791953563212
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041317515717515741943042560012242442240x7fc6658877800x7fc664e261c0399118399118655369568256152266217053703616791953598731167919535615121679195400231016791954021247
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041617515717515741943042560012242487680x7fc6658876000x7fc664e26200392495392495655369437184151303316949807216791954039917167919540023101679195447638916791954524492
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041917515717515741943042560012242533120x7fc667eb54800x7fc664e26240388817388817655369437184144713816201904816791954535111167919544763891679195493990716791954984027
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221751571751574194304256008242555520x7fc667eb53000x7fc664e262807195117195116553616056320230605725822041616791954994397167919549399071679195561238416791955656316
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042517515717515741943042560012242598400x7fc667eb51800x7fc664e262c0362718362718655368847360138143315473136416791955675105167919556123841679195605622316791956098762
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042817515717515741943042560012242656640x7fc667eb50000x7fc664e263004693994693996553611665408184426220638135216791956109452167919560562231679195657126116791956613586
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043117515717515741943042560012242712320x7fc665887e800x7fc664e263404697894697896553611468800182286220421007616791956623465167919565712611679195708453916791957128009
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341751571751574194304256008242732160x7fc665887d000x7fc664e263804841914841916553614090240202461322684775216791957137969167919570845391679195760469716791957647033
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371751571751574194304256008242757120x7fc665887b800x7fc664e263c08788758788756553619202048275457430875732416791957657413167919576046971679195837989516791958425189
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044017515717515741943042560012242807680x7fc665887a000x7fc664e264004276394276396553610420224165020118489998416791958444488167919583798951679195886853316791958912393
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044317515717515741943042560012242876160x7fc6658878800x7fc664e264405507655507656553613762560225840625293499616791958923293167919588685331679195943813116791959480666
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044617515717515741943042560012242942080x7fc6658877000x7fc664e264805517195517196553613565952216799724300490816791959491295167919594381311679196000644916791960049088
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491751571751574194304256008242969600x7fc667eb55800x7fc664e264c05635115635116553615466496222892824962327216791960059037167919600064491679196057060716791960613340
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521751571751574194304256008242999680x7fc667eb54000x7fc664e26500104127910412796553622347776320762135938192016791960623700167919605706071679196144532416791961488183
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551751571751574194304256008243027200x7fc667eb52800x7fc664e265407228477228476553620250624290785232561368416791961507152167919614453241679196211124116791962143642
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045817515717515741943042560012243054720x7fc667eb51000x7fc664e265807226357226356553620447232293788432905710016791962154972167919621112411679196279219916791962836760
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046117515717515741943042560012243082240x7fc665887f800x7fc664e265c07228557228556553619595264281439631532519616791962846720167919627921991679196347539616791963519269
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641751571751574194304256008243109760x7fc665887e000x7fc664e266007259487259486553620381696292801132812024816791963529478167919634753961679196416115416791964205837
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671751571751574194304256008243132160x7fc665887c800x7fc664e26640136714313671436553631522816451666450564750816791964217497167919641610571679196526233316791965311142
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701751571751574194304256008243159680x7fc665887b000x7fc664e26680136982013698206553638993920558963662615678016791965331022167919652623331679196635384816791966420527
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047317515717515741943042560012243187200x7fc6658879800x7fc664e266c0137526613752666553639124992560810862818188816791966431577167919663538481679196749992316791967567231
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047617515717515741943042560012243214720x7fc6658878000x7fc664e26700137071713707176553638469632551210961740554016791967578201167919674999231679196863783916791968704855
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791751571751574194304256008243242240x7fc6658876800x7fc664e26740137616913761696553639059456559718962690011616791968715695167919686378391679196975431516791969799951
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821751571751574194304256008243264640x7fc667eb55000x7fc664e26780266216226621626553660489728865426796900628016791969811090167919697543151679197169574716791971769029
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851751571751574194304256008243292160x7fc667eb53800x7fc664e267c026698182669818655367726694411053549123826985616791971787268167919716957471679197363078016791973698078
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048817515717515741943042560012243319680x7fc667eb52000x7fc664e2680026695702669570655367739801611071439124026583216791973709768167919736307801679197561205316791975685336
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049117515717515741943042560012243347200x7fc667eb50800x7fc664e2684026721142672114655367621836810910636122196636816791975696316167919756120531679197760532516791977671273
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941751571751574194304256008243374720x7fc665887f000x7fc664e2688026730582673058655367733248011062404123941930016791977682143167919776053251679197954467816791979616092
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049717515717515741943042560082400x7fc665887d800x7fc664e268c0525713752571376553612025856017195038192549115616791979627492167919795446781679198317378416791983245738