Comhaid
rocm-systems/tests/workloads/dispatches/mi100/SQ_LEVEL_WAVES.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

50 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_fillBuffer.kd000896508896513335544322560083264640x00x7fce1aa0418050230950230916285401848052428836655934638227850148102252012075849713232663120758499595503321207584995987369112075849959985773
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00289650889651332768256002424124800x00x7fce1aa351002742227422203822193845121165855789210467778412075849974536505120758499748611051207584997486750512075849974874844
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0048965088965134194304256002424129280x7fcf4aae69000x7fce1aa35140219277219277196621754224655361336852851589660053655230012075849974944253120758499751953441207584997532942312075849975332574
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0068965088965134194304256003624136320x7fcf4aae68000x7fce1aa35180392741392741238353141936655362261659742969768090648109612075849975410399120758499756019021207584997585198112075849975921800
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0088965088965134194304256002824140800x7fcf4aae67000x7fce1aa351c03866123866123138330929046553635123630429273640140676212812075849975955642120758499761732601207584997641901912075849976489224
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00108965088965134194304256002424145280x7fcf4aae66000x7fce1aa35200215917215917200551727344655361312145941565980052667401212075849976515353120758499767294171207584997686141712075849976863860
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00128965088965134194304256002424149760x7fcf4aae65000x7fce1aa35240215077215077218261720624655361489820191556052059774502812075849976924333120758499771246161207584997725597512075849977258434
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00148965088965134194304256002424154240x7fcf4aae64000x7fce1aa35280219773219773194981758192655361496217001578084060030354812075849977344594120758499775313341207584997766557312075849977668606
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00168965088965134194304256002824161280x7fcf4aae63000x7fce1aa352c03947323947323342331578646553635484033529914660142117799212075849977727595120758499779326121207584997818445112075849978227324
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00188965088965134194304256002824168320x7fcf4aae6a000x7fce1aa353004042524042522860532340246553631217193030635440125050603212075849978259785120758499784626901207584997871996912075849978762389
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00208965088965134194304256002424175360x7fcf4aae69000x7fce1aa35340210549210549201111684400655361665936151519950066819107212075849978794328120758499789956481207584997912444712075849979127397
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00228965088965134194304256002424182400x7fcf4aae68000x7fce1aa35380215572215572211421724584655361404788291560982056373393612075849979187559120758499793858861207584997951804512075849979520387
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00248965088965134194304256002424189440x7fcf4aae67000x7fce1aa353c0214525214525235781716208655361550629951546303062206854812075849979593173120758499797754841207584997990668412075849979909180
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00268965088965134194304256002824199040x7fcf4aae66000x7fce1aa354004033734033732984532269926553633432595230594400133912044812075849979967338120758499801705221207584998042812112075849980497934
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00288965088965134194304256002824206080x7fcf4aae65000x7fce1aa354403954363954363226231634966553634995631730000360140164180412075849980524393120758499807337201207584998098603912075849981055390
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00308965088965134194304256002424213120x7fcf4aae64000x7fce1aa35480211244211244218871689960655361509337531522904060555292812075849981079254120758499812869981207584998141595712075849981418635
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00328965088965134194304256002424220160x7fcf4aae63000x7fce1aa354c0223364223364189091786920655361276605801610069051245608812075849981478096120758499816717961207584998180939512075849981811776
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00348965088965134194304256002424227200x7fcf4aae6a000x7fce1aa35500211485211485223691691888655361417534431530636056883176412075849981882427120758499820757941207584998220539412075849982207772
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00368965088965134194304256002824236800x7fcf4aae69000x7fce1aa355403971403971403049331771286553635506287130175820142206874012075849982268324120758499824703531207584998272443112075849982792468
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00388965088965134194304256002824243840x7fcf4aae68000x7fce1aa355804020534020532697032164326553630125175530509780120682525612075849982817044120758499830321101207584998328890912075849983358490
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00408965088965134194304256002424250880x7fcf4aae67000x7fce1aa355c0207669207669208261661360655361645623661504929066007992812075849983384098120758499835887481207584998371594712075849983718329
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00428965088965134194304256002424257920x7fcf4aae66000x7fce1aa35600215636215636234981725096655361430536831559635057403364412075849983776988120758499839770661207584998410922512075849984111750
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00448965088965134194304256002424264960x7fcf4aae65000x7fce1aa35640213468213468222931707752655361578351001540703063315842012075849984186198120758499843711441207584998450202412075849984504260
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00468965088965134194304256002824277120x7fcf4aae64000x7fce1aa356803942763942763348931542166553635550117829866860142382337212075849984562207120758499847586631207584998501114212075849985080711
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00488965088965134194304256002824284160x7fcf4aae63000x7fce1aa356c04022524022522570132180246553632385480230388120129723378012075849985106850120758499853117801207584998556857912075849985638037
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00508965088965134194304256002424291200x7fcf4aae6a000x7fce1aa35700213508213508232751708072655361435796331546767057614417212075849985662091120758499858701781207584998600089712075849986005029
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00528965088965134194304256002424300800x7fcf4aae69000x7fce1aa35740214404214404219321715240655361503540731555352060323760012075849986063778120758499862650561207584998639721612075849986399592
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00548965088965134194304256002424307840x7fcf4aae68000x7fce1aa35780214037214037214611712304655361527658411555966061288591612075849986471255120758499866498551207584998678121412075849986783305
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00568965088965134194304256002824320000x7fcf4aae67000x7fce1aa357c03971163971162705431769366553632286649030134420129328646412075849986840421120758499870420131207584998729705212075849987367942
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00588965088965134194304256002824329600x7fcf4aae66000x7fce1aa358003937323937323234331498646553635846680029935090143568508412075849987395222120758499875968901207584998784872912075849987916471
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00608965088965134194304256002424339200x7fcf4aae65000x7fce1aa35840217508217508203721740072655361523182781581358061109297612075849987940977120758499881492081207584998828296712075849988285096
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00628965088965134194304256002424348800x7fcf4aae64000x7fce1aa35880225469225469238381803760655361404115901635221056349523612075849988338165120758499885370461207584998867608612075849988678477
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00648965088965134194304256002424358400x7fcf4aae63000x7fce1aa358c0215269215269217581722160655361417766191561204056891979612075849988749038120758499889280851207584998906040412075849989062691
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00668965088965134194304256002824373120x7fcf4aae6a000x7fce1aa359003959013959013265231672166553635568226230037190142454916812075849989123424120758499893180031207584998957224212075849989640204
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00688965088965134194304256002824382720x7fcf4aae69000x7fce1aa359404004294004292827132034406553631902582530401440127792021212075849989665592120758499898695211207584999012584012075849990195056
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00708965088965134194304256002424392320x7fcf4aae68000x7fce1aa35980220964220964226131767720655361513920061579670060740536812075849990220703120758499904224781207584999055655812075849990558892
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00728965088965134194304256002424401920x7fcf4aae67000x7fce1aa359c0221500221500240241772008655361368324251607323054916088812075849990619965120758499908093571207584999094583612075849990948135
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00748965088965134194304256002424411520x7fcf4aae66000x7fce1aa35a00216900216900219271735208655361593221781570843063911470012075849991025860120758499912066351207584999133975412075849991342408
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00768965088965134194304256002824426240x7fcf4aae65000x7fce1aa35a404033884033882484432271126553630549742230355880122380654412075849991400967120758499915912731207584999185047212075849991920112
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00788965088965134194304256002824435840x7fcf4aae64000x7fce1aa35a804065884065882959932527126553632035367130644560128323273612075849991945188120758499921629511207584999242135012075849992492365
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00808965088965134194304256002424445440x7fcf4aae63000x7fce1aa35ac0215796215796227311726376655361438248881566567057712140812075849992524836120758499927211881207584999285366812075849992856051
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00828965088965134194304256002424457600x7fcf4aae6a000x7fce1aa35b00215132215132247341721064655361610699541553247064609846412075849992915532120758499931090271207584999324150612075849993244293
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00848965088965134194304256002424467200x7fcf4aae69000x7fce1aa35b40208469208469206111667760655361548783281498735062135379612075849993318460120758499935034251207584999363126412075849993633867
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00868965088965134194304256002824484480x7fcf4aae68000x7fce1aa35b804061494061493293332492006553633229430230800220133100502412075849993692526120758499938819831207584999414294212075849994211320
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00888965088965134194304256002824494080x7fcf4aae67000x7fce1aa35bc03993973993972688231951846553631552792430224080126392762412075849994239372120758499944395811207584999469558012075849994764297
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00908965088965134194304256002424503680x7fcf4aae66000x7fce1aa35c00219204219204225711753640655361465407571590885058798114012075849994789304120758499949918991207584999512677812075849995129807
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00928965088965134194304256002424515840x7fcf4aae65000x7fce1aa35c40225820225820252491806568655361508648161637669060528484412075849995191742120758499953850171207584999552453612075849995527145
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00948965088965134194304256002424525440x7fcf4aae64000x7fce1aa35c80210924210924223331687400655361520351661522711060996076412075849995599209120758499957790951207584999590869512075849995911690
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00968965088965134194304256002824542720x7fcf4aae63000x7fce1aa35cc04175244175243428233402006553634479009231665820138098184412075849995967794120758499961744531207584999644357212075849996514851
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00988965088965134194304256002824554880x7fcf4aae6a000x7fce1aa35d003884773884772888331078246553635214080029389960141038090012075849996540779120758499967453311207584999699461012075849997064142
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001008965088965134194304256002424567040x7fcf4aae69000x7fce1aa35d40222380222380208991779048655361482633121616029059489740812075849997088567120758499972914091207584999742868812075849997430953
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001028965088965134194304256002424581760x7fcf4aae68000x7fce1aa35d80229700229700267371837608655361513570861670062060726176012075849997491606120758499976797271207584999782244612075849997824795
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001048965088965134194304256002424593920x7fcf4aae67000x7fce1aa35dc0216445216445215781731568655361433621491570824057529892412075849997896589120758499980766851207584999821028512075849998213097
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001068965088965134194304256002824613760x7fcf4aae66000x7fce1aa35e004154054154053261633232486553634467341831553570138051730012075849998272738120758499984630841207584999873124212075849998799156
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001088965088965134194304256002824625920x7fcf4aae65000x7fce1aa35e403823573823573239730588646553634580287828985940138502918012075849998824984120758499990288411207584999927492012075849999315946
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001108965088965134194304256002424638080x7fcf4aae64000x7fce1aa35e80214276214276237481714216655361442414961524558057879128012075849999348818120758499995459591207584999967603812075849999678530
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001128965088965134194304256002424652800x7fcf4aae63000x7fce1aa35ec0224348224348276191794792655361751629341622495070249976412075849999738812120758499999310771207585000007075712075850000073645
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001148965088965134194304256002424664960x7fcf4aae6a000x7fce1aa35f00222333222333232791778672655361360529831610476054607415212075850000146230120758500003289961207585000046611512075850000468508
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001168965088965134194304256002824684800x7fcf4aae69000x7fce1aa35f404075244075243189232602006553633348452030793090133580308012075850000527288120758500007217941207585000098467312075850001054157
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001188965088965134194304256002824696960x7fcf4aae68000x7fce1aa35f804517254517251560836138086553632660226229665580130822756412075850001082059120758500012830711207585000157459012075850001644264
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001208965088965134194304256002424709120x7fcf4aae67000x7fce1aa35fc0209908209908221441679272655361496072281507339060028950012075850001669290120758500018677091207585000199570812075850001998151
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001228965088965134194304256002424723840x7fcf4aae66000x7fce1aa36000223189223189276061785520655361828398111614728073321103212075850002059996120758500022510671207585000238978712075850002392344
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001248965088965134194304256002424736000x7fcf4aae65000x7fce1aa36040212301212301230071698416655361434120751536196057549137612075850002463927120758500026422661207585000277298512075850002775215
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001268965088965134194304256002824758400x7fcf4aae64000x7fce1aa360804111174111173231332889446553633461122831130510134027873612075850002833143120758500030283441207585000329394312075850003336929
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001288965088965134194304256002824770560x7fcf4aae63000x7fce1aa360c04011244011242832232090006553628003095030343250112194148812075850003382364120758500035648221207585000382290112075850003890979
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001308965088965134194304256002424782720x7fcf4aae6a000x7fce1aa36100211028211028222021688232655361512377901519553060678360012075850003915615120758500041233791207585000425313912075850004256168
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001328965088965134194304256002424800000x7fcf4aae69000x7fce1aa36140231684231684264051853480655361919890391682573076982802412075850004318043120758500045004981207585000464497712075850004647485
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001348965088965134194304256002424812160x7fcf4aae68000x7fce1aa36180212933212933249741703472655361573204871533208063110512012075850004721683120758500048990561207585000503041512075850005033322
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001368965088965134194304256002824834560x7fcf4aae67000x7fce1aa361c04125884125883423733007126553632902510331160200131795296812075850005093183120758500052880141207585000555441312075850005622327
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001388965088965134194304256002824849280x7fcf4aae66000x7fce1aa362003990293990293107331922406553633860823930302470135625118812075850005645580120758500058457721207585000610273112075850006171477
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001408965088965134194304256002424864000x7fcf4aae65000x7fce1aa36240224572224572238481796584655361437589101635725057690946412075850006197185120758500063985691207585000653728912075850006539762
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001428965088965134194304256002424881280x7fcf4aae64000x7fce1aa36280239365239365271231914928655362046689131750188082052742012075850006600595120758500067886481207585000693808712075850006940637
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001448965088965134194304256002424896000x7fcf4aae63000x7fce1aa362c0217013217013238971736112655361578584171567266063327713612075850007041574120758500072252861207585000735872512075850007361198
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001468965088965134194304256002824920960x7fcf4aae6a000x7fce1aa363004134284134283470233074326553633045183631341840132366722012075850007419787120758500076104041207585000787808312075850007946756
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001488965088965134194304256002824935680x7fcf4aae69000x7fce1aa363403940523940523472831524246553635814587629801500143440234812075850007975871120758500081776021207585000843056112075850008501387
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001508965088965134194304256002424950400x7fcf4aae68000x7fce1aa36380220292220292216041762344655361488104231594296059706782812075850008526273120758500087286391207585000886479912075850008867347
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001528965088965134194304256002424967680x7fcf4aae67000x7fce1aa363c0253477253477283072027824655362237665891867668089691777212075850008926628120758500091198381207585000927871712075850009281727
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001548965088965134194304256002424982400x7fcf4aae66000x7fce1aa36400219253219253212931754032655361541633011590399061847584812075850009353300120758500095319961207585000966751512075850009670049
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015689650889651341943042560028241007360x7fcf4aae65000x7fce1aa364404025324025323319532202646553634960287430479730140024340012075850009728317120758500099161541207585001017679312075850010245458
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015889650889651341943042560028241022080x7fcf4aae64000x7fce1aa364803981243981243399331850006553635450842430177870141986362012075850010270214120758500104721521207585001072895112075850010799278
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016089650889651341943042560024241036800x7fcf4aae63000x7fce1aa364c0224388224388225841795112655361469939521630262058984537212075850010823743120758500110305491207585001116942912075850011172281
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016289650889651341943042560024241056640x7fcf4aae6a000x7fce1aa36500266597266597287662132784655362351263011946606094235722012075850011233174120758500114281481207585001159374712075850011596349
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016489650889651341943042560024241071360x7fcf4aae69000x7fce1aa36540217828217828238711742632655361584397261566300063561942812075850011669214120758500118465461207585001198046512075850011983008
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016689650889651341943042560028241098880x7fcf4aae68000x7fce1aa365804064364064363395232514966553632705293030636970131008058012075850012042418120758500122329441207585001249614312075850012566191
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016889650889651341943042560028241113600x7fcf4aae67000x7fce1aa365c03973643973643111131789206553633051035030003390132385973212075850012590988120758500127905421207585001304622112075850013116053
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017089650889651341943042560024241128320x7fcf4aae66000x7fce1aa36600223212223212258681785704655361405350391618344056397472012075850013141270120758500133430191207585001348109912075850013483657
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017289650889651341943042560024241148160x7fcf4aae65000x7fce1aa36640276524276524300472212200655362456683802050233098452136812075850013541494120758500137321381207585001390669712075850013909318
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017489650889651341943042560024241162880x7fcf4aae64000x7fce1aa36680226380226380258181811048655361441941321641109057862893612075850013981011120758500141668561207585001430701512075850014309752
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017689650889651341943042560028241190400x7fcf4aae63000x7fce1aa366c04035334035333544532282726553633462420130301970134036800412075850014367269120758500145631741207585001482477312075850014893537
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017889650889651341943042560028241207680x7fcf4aae6a000x7fce1aa367004018054018052922832144486553625622123430215250102670338812075850014919465120758500151220521207585001538141112075850015450271
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018089650889651341943042560024241224960x7fcf4aae69000x7fce1aa36740227373227373253451818992655361425631521648640057212761212075850015475839120758500156754891207585001581676912075850015819227
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018289650889651341943042560024241247360x7fcf4aae68000x7fce1aa367802889642889643047523117206553625958498521524830104018526012075850015879509120758500160689281207585001625260712075850016255788
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018489650889651341943042560024241264640x7fcf4aae67000x7fce1aa367c0226796226796250491814376655361489386861650810059764739612075850016361134120758500165463661207585001668684512075850016689394
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018689650889651341943042560020241279360x7fcf4aae66000x7fce1aa368004111404111403713832891286553637933646631234740151916626412075850016747071120758500169391641207585001720652312075850017277287
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018889650889651341943042560028241296640x7fcf4aae65000x7fce1aa368403985723985723166031885846553633675820330196840134885417212075850017301422120758500175090821207585001776700012075850017836997
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019089650889651341943042560024241313920x7fcf4aae64000x7fce1aa36880278980278980152352231848655361507786081534634060494868812075850017863416120758500180764391207585001825211812075850018255094
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019289650889651341943042560024241336320x7fcf4aae63000x7fce1aa368c03030773030773168524246246553627056323422576270108411237212075850018316598120758500185058771207585001869803612075850018766895
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019489650889651341943042560024241353600x7fcf4aae6a000x7fce1aa36900225349225349259251802800655361468855601628453058940677212075850018801590120758500189921151207585001913179512075850019134859
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019689650889651341943042560020241368320x7fcf4aae69000x7fce1aa369404361724361723987234893846553640505137733240940162202528012075850019193759120758500193841131207585001966811212075850019737219
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019889650889651341943042560028241385600x7fcf4aae68000x7fce1aa369804014374014372889832115046553625693341730288460102955788012075850019762025120758500199610711207585002022091012075850020291779
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020089650889651341943042560024241402880x7fcf4aae67000x7fce1aa369c0222381222381266471779056655361448202371604014058115036812075850020317437120758500205234691207585002066170812075850020664261
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020289650889651341943042560024241427840x7fcf4aae66000x7fce1aa36a003314603314603325626516886553629639443724864630118742410812075850020723261120758500209164271207585002112810612075850021199266
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020489650889651341943042560024241447680x7fcf4aae65000x7fce1aa36a40227189227189263111817520655361512748081649737060697117612075850021236254120758500214261851207585002156762412075850021570205
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020689650889651341943042560020241457280x7fcf4aae64000x7fce1aa36a804705724705724137037645846553643857979836013010175613896812075850021627982120758500218197831207585002212730212075850022196419
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020889650889651341943042560028241477120x7fcf4aae63000x7fce1aa36ac03893323893323509931146646553634996567829332750140168754812075850022222898120758500224254311207585002267727012075850022751721
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021089650889651341943042560024241496960x7fcf4aae6a000x7fce1aa36b00226317226317222301810544655361480425431624301059405384412075850022773511120758500229798281207585002312062712075850023123251
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021289650889651341943042560024241521920x7fcf4aae69000x7fce1aa36b403563323563323565528506646553632492091226915270130152478412075850023182181120758500233721461207585002360046512075850023670318
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021489650889651341943042560024241541760x7fcf4aae68000x7fce1aa36b80225197225197244231801584655361485584921634932059608653212075850023706275120758500238942241207585002403438312075850024036999
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021689650889651341943042560020241556480x7fcf4aae67000x7fce1aa36bc05065965065964445240527766553647290520338854330189344042412075850024096600120758500242939021207585002462510112075850024672160
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021889650889651341943042560028241576320x7fcf4aae66000x7fce1aa36c003918523918523439131348246553635052517229636780140393482412075850024696565120758500248956591207585002514925812075850025220018
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022089650889651341943042560024241596160x7fcf4aae65000x7fce1aa36c40227557227557264841820464655361502758741649441060296742812075850025245195120758500254481371207585002558957612075850025592180
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022289650889651341943042560024241623680x7fcf4aae64000x7fce1aa36c803836843836843605830694806553634190281729031380136945580812075850025651861120758500258394951207585002608605412075850026155937
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022489650889651341943042560024241646080x7fcf4aae63000x7fce1aa36cc0223764223764241311790120655361585686671622536063616691212075850026192656120758500263758131207585002651549312075850026518110
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022689650889651341943042560020241663360x7fcf4aae6a000x7fce1aa36d005745975745974857445967846553654010356644302160216223404012075850026576970120758500267697311207585002714653012075850027216689
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022889650889651341943042560028241685760x7fcf4aae69000x7fce1aa36d404062614062613415632500966553635008008330866940140215816012075850027244450120758500274586881207585002772252712075850027792439
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023089650889651341943042560024241708160x7fcf4aae68000x7fce1aa36d80224685224685299281797488655361752545541622466070291083212075850027817385120758500280294061207585002816908512075850028172114
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023289650889651341943042560024241740800x7fcf4aae67000x7fce1aa36dc04345724345723989134765846553640421717033146680161871898812075850028224983120758500284314841207585002871148312075850028781066
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023489650889651341943042560024241765760x7fcf4aae66000x7fce1aa36e00224125224125268171793008655361623887561625331065144842812075850028817464120758500289986821207585002913836112075850029141867
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023689650889651341943042560020241777920x7fcf4aae65000x7fce1aa36e406456046456045189551648406553661313908850045490245437514012075850029202369120758500293950001207585002981995812075850029863247
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023889650889651341943042560028241802880x7fcf4aae64000x7fce1aa36e804029964029963394132239766553630957476730250300124014063612075850029902771120758500300884371207585003034971612075850030420052
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024089650889651341943042560024241827840x7fcf4aae63000x7fce1aa36ec0224476224476253691795816655361664261811623282066761417612075850030444417120758500306501951207585003079019412075850030792925
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024289650889651341943042560024241863040x7fcf4aae6a000x7fce1aa36f004897564897564368639180566553645778930937515660183301054812075850030855341120758500310578731207585003137467212075850031445177
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024489650889651341943042560024241893120x7fcf4aae69000x7fce1aa36f40244204244204272361953640655362130969111792288085427942812075850031490071120758500316722711207585003182571012075850031828279
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024689650889651341943042560020241907840x7fcf4aae68000x7fce1aa36f807849487849486023862795926553675036161961119780300326871212075850031887449120758500320844291207585003260250712075850032673811
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024889650889651341943042560028241937920x7fcf4aae67000x7fce1aa36fc04583004583004164936664086553638210405434787420153026494812075850032698396120758500328994651207585003319914412075850033269027
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025089650889651341943042560024241968000x7fcf4aae66000x7fce1aa37000249052249052279081992424655362191401001830254087845328012075850033294143120758500334980231207585003365498212075850033657459
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025289650889651341943042560024242010880x7fcf4aae65000x7fce1aa370405929095929094847647432806553656171086545822730224869882812075850033718292120758500339058611207585003429193912075850034361457
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025489650889651341943042560024242046080x7fcf4aae64000x7fce1aa370802781732781732956822253926553624953904020640630100004506812075850034398816120758500345885781207585003476489712075850034767842
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025689650889651341943042560020242060800x7fcf4aae63000x7fce1aa370c09249089249086819573992726553688970522072373990356064107212075850034827633120758500350269761207585003563849412075850035707749
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025889650889651341943042560028242096000x7fcf4aae6a000x7fce1aa371005034205034204348840273686553645834581638535040183521827612075850035733106120758500359351321207585003626649112075850036336728
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026089650889651341943042560024242131200x7fcf4aae69000x7fce1aa371402823652823653040322589286553625352594120950710101598755612075850036362005120758500365639301207585003674344912075850036745878
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026289650889651341943042560024242181760x7fcf4aae68000x7fce1aa371806978126978125418355825046553666531570854248230266312039612075850036804087120758500369949681207585003745160612075850037522281
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026489650889651341943042560024242222080x7fcf4aae67000x7fce1aa371c03144133144133171225153126553628551166423559070114393952012075850037559240120758500377504851207585003795176412075850038021830
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026689650889651341943042560020242239360x7fcf4aae66000x7fce1aa372001063541106354174807850833665536102900072983528260411782435212075850038045644120758500382480831207585003895192012075850039022008
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026889650889651341943042560028242279680x7fcf4aae65000x7fce1aa372405715095715094715245720806553652953649543856150211999950412075850039056523120758500392519181207585003962727712075850039696232
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027089650889651341943042560024242320000x7fcf4aae64000x7fce1aa372803201963201963193025615766553629067299424025530116459919212075850039720917120758500399210361207585004012599512075850040196551
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027289650889651341943042560024242378240x7fcf4aae63000x7fce1aa372c08284288284281556566274326553676600897862619650306587893612075850040221307120758500404215131207585004096503112075850041035430
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027489650889651341943042560024242423680x7fcf4aae6a000x7fce1aa373003515253515253554428122086553632031934726379210128317446412075850041073160120758500412581501207585004148326912075850041551860
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027689650889651341943042560020242435840x7fcf4aae69000x7fce1aa373401208164120816415297966532065536116811032394944960467426209212075850041575454120758500417765481207585004257766412075850042647316
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027889650889651341943042560028242481280x7fcf4aae68000x7fce1aa373806398926398925346951191446553660232632049448590241114866412075850042684004120758500428795831207585004330102112075850043373325
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028089650889651341943042560024242526720x7fcf4aae67000x7fce1aa373c03537003537003391428296086553632502486926740730130199410412075850043405265120758500436056601207585004383365912075850043902248
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028289650889651341943042560024242592640x7fcf4aae66000x7fce1aa374009095659095656727072765286553687482783071146430350116410412075850043935099120758500441386181207585004473637512075850044806970
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028489650889651341943042560024242648320x7fcf4aae65000x7fce1aa374404164524164523789633316246553638522486631773080154280226412075850044843517120758500450418141207585004531125312075850045380686
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028689650889651341943042560020242663040x7fcf4aae64000x7fce1aa37480148698014869809993611895848655361448260530117381290579486241612075850045406013120758500456082111207585004659460712075850046664792
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028889650889651341943042560028242718720x7fcf4aae63000x7fce1aa374c08025568025561528564204566553674354319760598310297602027612075850046701450120758500468968461207585004742932412075850047500936
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029089650889651341943042560024242774400x7fcf4aae6a000x7fce1aa375004227884227883941033823126553638906620532121320155815905612075850047532986120758500477350821207585004800820112075850048077588
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029289650889651341943042560012242799360x7fcf4aae69000x7fce1aa375401126813112681379723901451265536109032603188543790436312634812075850048110269120758500483038801207585004904291712075850049113192
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029489650889651341943042560024242865280x7fcf4aae68000x7fce1aa375805314925314921537342519446553645168719837449250180863912412075850049155631120758500493374761207585004968323412075850049752020
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029689650889651341943042560020242880000x7fcf4aae67000x7fce1aa375c01768709176870911795214149680655361725840035139800920690518099612075850049788007120758500499896331207585005116210812075850051234304
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029889650889651341943042560032242945920x7fcf4aae66000x7fce1aa376009223419223416450273787366553680831942172141710323514701612075850051269099120758500514672261207585005207922412075850052148804
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030089650889651341943042560024243011840x7fcf4aae65000x7fce1aa376404934054934054512539472486553646061387837779250184435090412075850052175664120758500523846631207585005270466112075850052774337
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030289650889651341943042560012243049600x7fcf4aae64000x7fce1aa37680133690813369089219510695272655361297522663105363600519191390412075850052810434120758500529995401207585005387857612075850053949300
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030489650889651341943042560024243136000x7fcf4aae63000x7fce1aa376c06291736291735197250333926553659321801748642880237477529612075850053998652120758500541878551207585005459873312075850054669639
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030689650889651341943042560020243148160x7fcf4aae6a000x7fce1aa377002332549233254915072918660400655362284601534184981310914022724012075850054696218120758500549012921207585005645168512075850056521761
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030889650889651341943042560020243175680x7fcf4aae69000x7fce1aa377401199781119978183385959825665536116365838194409000465645684812075850056557978120758500567603241207585005755584112075850057626053
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031089650889651341943042560012243203200x7fcf4aae68000x7fce1aa377806400446400445090251203606553660864871449591810243642650812075850057663493120758500578585591207585005827407812075850058345871
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031289650889651341943042560012243240960x7fcf4aae67000x7fce1aa377c01757140175714011574114057128655361714527034139003980685993095612075850058378011120758500585739161207585005973295112075850059803119
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031489650889651341943042560012243288960x7fcf4aae66000x7fce1aa378001198924119892483726959140065536116158868894275000464818232812075850059847672120758500600358301207585006082222712075850060892915
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031689650889651341943042560020243301120x7fcf4aae65000x7fce1aa3784045838844583884282037366710806553645140450203650799001805800019612075850060917831120758500611235051207585006417389212075850064244634
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031889650889651341943042560020243328640x7fcf4aae64000x7fce1aa37880232467723246778005418597424655362274993684184334420910179852412075850064275070120758500644823711207585006602556512075850066096245
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032089650889651341943042560012243356160x7fcf4aae63000x7fce1aa378c01203636120363684153962909665536116687628694598730466932929612075850066128334120758500663321231207585006712220012075850067192662
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032289650889651341943042560012243393920x7fcf4aae6a000x7fce1aa3790034428763442876214364275430166553633855764372738193501354413502812075850067217839120758500674338791207585006971626912075850069786463
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032489650889651341943042560012243441920x7fcf4aae69000x7fce1aa379402323725232372515077618589808655362274957586184259000910165528812075850069832478120758500700228281207585007155882112075850071631311
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032689650889651341943042560020243454080x7fcf4aae68000x7fce1aa3798090876619087661543854727012966553689784993587253830903591581916412075850071663591120758500718669801207585007792439412075850077996180
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032889650889651341943042560020243481600x7fcf4aae67000x7fce1aa379c045721094572109281873365768806553645027143043641357601801268171612075850078035293120758500782360731207585008127958012075850081351646
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033089650889651341943042560012243509120x7fcf4aae66000x7fce1aa37a002330077233007715045418640624655362281774978184707400912892650412075850081385349120758500815858181207585008312677212075850083197016
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332896508896513419430425600122400x7fcf4aae65000x7fce1aa37a4068134926813492342604545079446553667233139595433763302689508071212075850083229606120758500834295661207585008795755212075850088032432