2
0
Ficheiros
rocm-systems/tests/workloads/dev1/mi200/SQ_INST_LEVEL_SMEM.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

41 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_SMEMSQ_INST_LEVEL_SMEMSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000229165229165335544322560043241600x00x7fed8e4042803670016321019235939455217703062218323176974970518321770320990858917703210020339
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00222916522916532768256001224138880x00x7fed8e423f805121028281153718417703215180549177032099085891770321531068317703215315516
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0052291652291654194304256001224143360x7fed913693800x7fed8e423fc0655366156186899404017703215349825177032153106831770321568684417703215689607
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0082291652291654194304256001624150400x7fed913692000x7fed8e424000655366489067272209617703215725596177032156868441770321608812617703216090817
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00112291652291654194304256001624154880x7fed913690800x7fed8e424040655366443507222319217703216122186177032160881261770321648092717703216483097
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00142291652291654194304256001224159360x7fed8ed09f000x7fed8e424080655366842247662693617703216515176177032164809271770321678412817703216786459
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00172291652291654194304256001224163840x7fed8ed09d800x7fed8e4240c0655366080906809795217703216817389177032167841281770321708652817703217088672
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00202291652291654194304256001224170880x7fed8ed09c000x7fed8e4241001310726402387162794417703217131511177032170865281770321738556917703217387694
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00232291652291654194304256001624177920x7fed8ed09a800x7fed8e4241401310726819567634304817703217418683177032173855691770321777661017703217778944
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00262291652291654194304256001624184960x7fed8ed099000x7fed8e424180655366444787223108017703217809274177032177766101770321816445117703218167365
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00292291652291654194304256001624192000x7fed8ed097800x7fed8e4241c01310726823847644207217703218199494177032181644511770321849565217703218497996
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00322291652291654194304256001624199040x7fed8ed096000x7fed8e4242001310726844627659191217703218530046177032184956521770321880205317703218804309
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00352291652291654194304256001224206080x7fed913694800x7fed8e4242401310726864487678175217703218843698177032188020531770321910461417703219106861
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00382291652291654194304256001624213120x7fed913693000x7fed8e4242801310726822467632304017703219138310177032191046141770321948637517703219488121
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00412291652291654194304256001624220160x7fed913691800x7fed8e4242c0655366451947217730417703219520191177032194863751770321984813617703219849772
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00442291652291654194304256001624227200x7fed913690000x7fed8e4243001310726786027597282417703219881472177032198481361770322012397717703220125575
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00472291652291654194304256001224234240x7fed8ed09e800x7fed8e4243401310726929147753680817703220156675177032201239771770322040349817703220405178
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00502291652291654194304256001224241280x7fed8ed09d000x7fed8e4243801310726691167492184817703220443767177032204034981770322068765917703220689311
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00532291652291654194304256001624248320x7fed8ed09b800x7fed8e4243c01310726809547633579217703220721710177032206876591770322105246017703221054112
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00562291652291654194304256001624255360x7fed8ed09a000x7fed8e424400655366063726786759217703221085331177032210524601770322142366117703221425333
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00592291652291654194304256001224262400x7fed8ed098800x7fed8e4244401310726835687639712817703221456152177032214236611770322170062117703221702196
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00622291652291654194304256001224269440x7fed8ed097000x7fed8e4244801310726881647707608017703221732895177032217006211770322197710217703221978789
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00652291652291654194304256001224276480x7fed913695800x7fed8e4244c01310726597267401699217703222016328177032219771021770322226830317703222270181
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00682291652291654194304256001624286080x7fed913694000x7fed8e4245001310726755867564106417703222303171177032222683031770322263630417703222637902
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00712291652291654194304256001624293120x7fed913692800x7fed8e424540655366490907276625617703222669141177032226363041770322300094517703223002693
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00742291652291654194304256001224300160x7fed913691000x7fed8e4245801310726493947273212817703223034602177032230009451770322327646617703223278136
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077229165229165419430425600824309760x7fed8ed09f800x7fed8e4245c01310726420247181280817703223309655177032232764661770322355086717703223552529
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00802291652291654194304256001224316800x7fed8ed09e000x7fed8e4246001310726706667514416017703223591668177032235508671770322382670717703223828262
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00832291652291654194304256001624326400x7fed8ed09c800x7fed8e4246401310726406687171508817703223859751177032238267071770322419134817703224193033
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00862291652291654194304256001224336000x7fed8ed09b000x7fed8e424680655366342107102812817703224223532177032241913481770322455951017703224561194
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00892291652291654194304256001224345600x7fed8ed099800x7fed8e4246c01310726809327642843217703224591873177032245595101770322483807017703224839657
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092229165229165419430425600824355200x7fed8ed098000x7fed8e4247001310726870647695804817703224870636177032248380701770322511663117703225118480
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00952291652291654194304256001224362240x7fed8ed096800x7fed8e4247401310726821327637064017703225156079177032251166311770322539535217703225397093
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00982291652291654194304256001224371840x7fed913695000x7fed8e4247801310726737627552559217703225427772177032253953521770322576847317703225770083
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001012291652291654194304256001224381440x7fed913693800x7fed8e4247c0655366508867282908017703225801963177032257684731770322613055417703226132394
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001042291652291654194304256001224391040x7fed913692000x7fed8e4248001310726759707567602417703226165033177032261305541770322641231517703226414037
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107229165229165419430425600824403200x7fed913690800x7fed8e4248401310726681627478443217703226445826177032264123151770322669855617703226700250
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001102291652291654194304256001224412800x7fed8ed09f000x7fed8e4248801310726841667662286417703226738989177032266985561770322698207617703226983803
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001132291652291654194304256001224422400x7fed8ed09d800x7fed8e4248c01310726759287575220017703227014182177032269820761770322735199717703227353624
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001162291652291654194304256001224432000x7fed8ed09c000x7fed8e424900655366000266722396817703227385293177032273519971770322771791817703227719505
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119229165229165419430425600824441600x7fed8ed09a800x7fed8e4249401310726870607697111217703227750234177032277179181770322799439917703227996108
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001222291652291654194304256001224453760x7fed8ed099000x7fed8e4249801310726688267486412817703228026747177032279943991770322827232017703228274091
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001252291652291654194304256001224463360x7fed8ed097800x7fed8e4249c01310726799947631046417703228312040177032282723201770322855808117703228559783
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001282291652291654194304256001224475520x7fed8ed096000x7fed8e424a001310726803187611100817703228590533177032285580811770322892352217703228925164
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001312291652291654194304256001224485120x7fed913694800x7fed8e424a40655366425587185839217703228957464177032289235221770322928784317703229289535
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134229165229165419430425600824494720x7fed913693000x7fed8e424a801310726424887186276017703229320144177032292878431770322957296417703229574658
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001372291652291654194304256001224506880x7fed913691800x7fed8e424ac01310726506907279024817703229606257177032295729641770322985328417703229855011
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001402291652291654194304256001224516480x7fed913690000x7fed8e424b001310726412287183468817703229893120177032298532841770323013776517703230139714
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001432291652291654194304256001224528640x7fed8ed09e800x7fed8e424b401310726900347720529617703230170893177032301377651770323050656617703230508265
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001462291652291654194304256001224540800x7fed8ed09d000x7fed8e424b80655366463407254203217703230539544177032305065661770323087264717703230874405
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149229165229165419430425600824552960x7fed8ed09b800x7fed8e424bc01310726851627674759217703230904755177032308726471770323115296817703231154608
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001522291652291654194304256001224567680x7fed8ed09a000x7fed8e424c001310726684587478226417703231186108177032311529681770323143296917703231434691
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001552291652291654194304256001224577280x7fed8ed098800x7fed8e424c401310726829187643292017703231472710177032314329691770323171713017703231718874
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001582291652291654194304256001224589440x7fed8ed097000x7fed8e424c801310726703807504594417703231749433177032317171301770323208209117703232083805
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001612291652291654194304256001224601600x7fed913695800x7fed8e424cc0655366473867248759217703232114784177032320820911770323244801217703232449616
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164229165229165419430425600824613760x7fed913694000x7fed8e424d001310726828067649260817703232480835177032324480121770323272353317703232725249
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001672291652291654194304256001224628480x7fed913692800x7fed8e424d401310726795987606570417703232758308177032327235331770323300881317703233010462
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001702291652291654194304256001224638080x7fed913691000x7fed8e424d801310726812867635260017703233049831177032330088131770323328513417703233286875
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001732291652291654194304256001224650240x7fed8ed09f800x7fed8e424dc01310726570867362916017703233318494177032332851341770323364673517703233648466
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001762291652291654194304256001224662400x7fed8ed09e000x7fed8e424e00655366105606836289617703233680635177032336467351770323401409617703234015846
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179229165229165419430425600824674560x7fed8ed09c800x7fed8e424e401310726780867596860817703234046756177032340140961770323430209717703234303729
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001822291652291654194304256001224689280x7fed8ed09b000x7fed8e424e801310726895327726058417703234335408177032343020971770323458849817703234590182
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001852291652291654194304256001224701440x7fed8ed099800x7fed8e424ec01310726377807136456017703234628371177032345884981770323487057917703234872305
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001882291652291654194304256001224716160x7fed8ed098000x7fed8e424f001310726738387542676017703234903154177032348705791770323523538017703235237076
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001912291652291654194304256001224728320x7fed8ed096800x7fed8e424f40655366422767198874417703235268125177032352353801770323559938117703235600996
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194229165229165419430425600824740480x7fed913695000x7fed8e424f801310726511867288489617703235631976177032355993811770323588530117703235886939
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001972291652291654194304256001224757760x7fed913693800x7fed8e424fc01310726451347226369617703235917618177032358853011770323617954217703236181202
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002002291652291654194304256001224769920x7fed913692000x7fed8e4250001310726815407626767217703236219431177032361795421770323646034317703236462105
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002032291652291654194304256001224784640x7fed913690800x7fed8e4250401310727041227899159217703236492974177032364603431770323682242417703236824066
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002062291652291654194304256001224799360x7fed8ed09f000x7fed8e425080655366457347235024817703236855405177032368224241770323718658517703237188366
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209229165229165419430425600824814080x7fed8ed09d800x7fed8e4250c01310726748887555509617703237219826177032371865851770323746866617703237470289
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002122291652291654194304256001224831360x7fed8ed09c000x7fed8e4251001310726812647629112017703237500969177032374686661770323776674717703237768382
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002152291652291654194304256001224843520x7fed8ed09a800x7fed8e4251401310726683227482032017703237818421177032377667471770323804658817703238048215
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002182291652291654194304256001224858240x7fed8ed099000x7fed8e4251801310726705907506237617703238087584177032380465881770323842946917703238431355
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002212291652291654194304256001224872960x7fed8ed097800x7fed8e4251c0655366439887213476017703238462394177032384294691770323879891017703238800636
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002242291652291654194304256001224887680x7fed8ed096000x7fed8e4252001310726763087577105617703238831625177032387989101770323907603017703239077739
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002272291652291654194304256001224907520x7fed913694800x7fed8e4252401310726841467662330417703239108858177032390760301770323937971117703239381372
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002302291652291654194304256001224919680x7fed913693000x7fed8e4252801310726807867619728817703239419931177032393797111770323966355217703239665244
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002332291652291654194304256001224934400x7fed913691800x7fed8e4252c01310726751607570991217703239696854177032396635521770324002771317703240029415
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002362291652291654194304256001224949120x7fed913690000x7fed8e425300655366523867293436817703240061055177032400277131770324038915417703240390856
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002392291652291654194304256001224963840x7fed8ed09e800x7fed8e4253401310726802107617298417703240422235177032403891541770324066771517703240669459
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002422291652291654194304256001224983680x7fed8ed09d000x7fed8e4253801310726750587564177617703240700339177032406677151770324097491617703240976532
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002452291652291654194304256001224995840x7fed8ed09b800x7fed8e4253c01310726794087621397617703241014561177032409749161770324125795717703241259755
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024822916522916541943042560012241013120x7fed8ed09a000x7fed8e4254001310726899207722020017703241292104177032412579571770324162403817703241625795
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025122916522916541943042560012241027840x7fed8ed098800x7fed8e425440655366333027099401617703241656585177032416240381770324198611917703241987756
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025422916522916541943042560012241042560x7fed8ed097000x7fed8e4254801310726506207279552017703242018656177032419861191770324227123917703242273259
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025722916522916541943042560012241062400x7fed913695800x7fed8e4254c01310726375827135294417703242304828177032422712391770324258964017703242591311
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026022916522916541943042560012241077120x7fed913694000x7fed8e4255001310726543527330760817703242630650177032425896401770324286836117703242870124
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026322916522916541943042560016241094400x7fed913692800x7fed8e4255401310726823167628912817703242901103177032428683611770324323908217703243240785
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026622916522916541943042560016241111680x7fed913691000x7fed8e425580655366355887125750417703243272424177032432390821770324360404317703243605696
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002692291652291654194304256008241128960x7fed8ed09f800x7fed8e4255c01310726857987683664817703243637245177032436040431770324388388417703243885489
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027222916522916541943042560012241151360x7fed8ed09e000x7fed8e4256001310726823587645372817703243916608177032438838841770324420388517703244205680
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027522916522916541943042560012241166080x7fed8ed09c800x7fed8e4256401310726779707611926417703244243390177032442038851770324448868617703244490343
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027822916522916541943042560016241183360x7fed8ed09b000x7fed8e4256801310726766647587529617703244521683177032444886861770324486116717703244862854
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028122916522916541943042560016241200640x7fed8ed099800x7fed8e4256c0655366405267175815217703244894033177032448611671770324522628817703245228005
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028422916522916541943042560012241217920x7fed8ed098000x7fed8e4257001310726803007610771217703245258244177032452262881770324550852917703245510148
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028722916522916541943042560012241240320x7fed8ed096800x7fed8e4257401310726891127714103217703245541007177032455085291770324583493017703245836609
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029022916522916541943042560012241255040x7fed913695000x7fed8e4257801310726635407456363217703245874858177032458349301770324611301017703246114862
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029322916522916541943042560012241274880x7fed913693800x7fed8e4257c01310726921647753504817703246146462177032461130101770324648373117703246485413
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029622916522916541943042560012241292160x7fed913692000x7fed8e425800655366454227227241617703246516722177032464837311770324684645217703246848274
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029922916522916541943042560012241309440x7fed913690800x7fed8e4258401310726476687248763217703246878963177032468464521770324713125317703247132827
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030222916522916541943042560012241334400x7fed8ed09f000x7fed8e4258801310726497447287772817703247164366177032471312531770324747301417703247474738
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030522916522916541943042560012241349120x7fed8ed09d800x7fed8e4258c0131072100890411311143217703247513207177032474730141770324775893517703247760551
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030822916522916541943042560012241368960x7fed8ed09c000x7fed8e4259001310726430907207668017703247791140177032477589351770324812245617703248124192
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031122916522916541943042560012241388800x7fed8ed09a800x7fed8e425940655366377707149477617703248155451177032481224561770324849989717703248501522
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031422916522916541943042560012241408640x7fed8ed099000x7fed8e4259801310726806227618680817703248531732177032484998971770324878837817703248790115
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031722916522916541943042560012241436160x7fed8ed097800x7fed8e4259c01310726842887673344017703248821324177032487883781770324914181917703249143546
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032022916522916541943042560012241453440x7fed8ed096000x7fed8e425a00131072100288811228469617703249181805177032491418191770324942966017703249431319
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032322916522916541943042560012241475840x7fed913694800x7fed8e425a401310726684247485707217703249462338177032494296601770324979622117703249797840
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032622916522916541943042560012241495680x7fed913693000x7fed8e425a80655366380947145334417703249829259177032497962211770325016198217703250163890
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032922916522916541943042560012241515520x7fed913691800x7fed8e425ac01310726419847189337617703250196020177032501619821770325046518317703250466793
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033222916522916541943042560012241543040x7fed913690000x7fed8e425b001310726421667194848817703250497432177032504651831770325083558417703250837184
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033522916522916541943042560012241562880x7fed8ed09e800x7fed8e425b4013107295988010741037617703250875663177032508355841770325113094417703251132706
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033822916522916541943042560012241587840x7fed8ed09d000x7fed8e425b801310726818967627707217703251163275177032511309441770325150150617703251503197
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034122916522916541943042560012241610240x7fed8ed09b800x7fed8e425bc0655366388127152038417703251534066177032515015061770325187046717703251872318
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034422916522916541943042560012241632640x7fed8ed09a000x7fed8e425c001310726417127181568017703251903417177032518704671770325217558717703252177310
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034722916522916541943042560012241665280x7fed8ed098800x7fed8e425c401310726765167583296817703252209529177032521755871770325256950917703252592320
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035022916522916541943042560012241685120x7fed8ed097000x7fed8e425c80131072100636011280704017703252611679177032525695091770325287606917703252877653
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035322916522916541943042560012241712640x7fed913695800x7fed8e425cc01310726435707208629617703252907722177032528760691770325324567017703253247283
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035622916522916541943042560012241737600x7fed913694000x7fed8e425d00655366439727211657617703253278763177032532456701770325362023217703253621814
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035922916522916541943042560012241762560x7fed913692800x7fed8e425d401310726423407202875217703253652513177032536202321770325394631217703253947876
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036222916522916541943042560012241797760x7fed913691000x7fed8e425d801310726462247236784817703253978835177032539463121770325437079417703254394155
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036522916522916541943042560012241822720x7fed8ed09f800x7fed8e425dc013107296995210863720817703254414144177032543707941770325469799517703254699647
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036822916522916541943042560012241855360x7fed8ed09e000x7fed8e425e001310726725587533948817703254730746177032546979951770325507735617703255080157
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037122916522916541943042560012241885440x7fed8ed09c800x7fed8e425e40655366447267227198417703255110687177032550773561770325546295717703255483817
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037422916522916541943042560012241915520x7fed8ed09b000x7fed8e425e801310726466707237652817703255495207177032554629571770325581735817703255819059
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037722916522916541943042560012241958400x7fed8ed099800x7fed8e425ec01310726411747187425617703255849628177032558173581770325628631917703256306386
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038022916522916541943042560012241985920x7fed8ed098000x7fed8e425f00131072101220211352413617703256326696177032562863191770325662968017703256631418
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038322916522916541943042560012242023680x7fed8ed096800x7fed8e425f4013107297256010863183217703256662128177032566296801770325702456117703257042038
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038622916522916541943042560012242058880x7fed913695000x7fed8e425f80655366329427089988817703257056638177032570245611770325742648217703257443808
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038922916522916541943042560012242094080x7fed913693800x7fed8e425fc01310726521087305831217703257458787177032574264821770325780472317703257806559
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039222916522916541943042560012242144640x7fed913692000x7fed8e4260001310726446047198087217703257837078177032578047231770325832744517703258345555
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039522916522916541943042560012242177280x7fed913690800x7fed8e426040131072100132811203178417703258368715177032583274451770325868872617703258690536
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039822916522916541943042560012242220160x7fed8ed09f000x7fed8e426080131072100824211299131217703258721056177032586887261770325910568717703259123136
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040122916522916541943042560012242260480x7fed8ed09d800x7fed8e4260c0655366367187119360017703259139975177032591056871770325952584817703259542835
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040422916522916541943042560012242300800x7fed8ed09c000x7fed8e4261001310726505827283760817703259557765177032595258481770325992776917703259945015
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040722916522916541943042560012242359040x7fed8ed09a800x7fed8e4261401310726438087201442417703259960364177032599277691770326050601117703260523480
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041022916522916541943042560012242394240x7fed8ed099000x7fed8e426180131072101146211325231217703260545860177032605060111770326088009217703260881751
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041322916522916541943042560012242442240x7fed8ed097800x7fed8e4261c013107296733210837930417703260912711177032608800921770326132169317703261339180
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041622916522916541943042560012242487680x7fed8ed096000x7fed8e426200655366457247231122417703261354919177032613216931770326175993417703261776939
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041922916522916541943042560012242533120x7fed913694800x7fed8e4262401310726463387234641617703261793008177032617599341770326218617617703262205228
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004222291652291654194304256008242555520x7fed913693000x7fed8e426280131072102036611419220017703262220998177032621861761770326283433817703262851592
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042522916522916541943042560012242598400x7fed913691800x7fed8e4262c013107299827811187015217703262874731177032628343381770326325337917703263270331
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042822916522916541943042560012242656640x7fed913690000x7fed8e42630013107296672810820269617703263286801177032632533791770326374154017703263758509
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043122916522916541943042560012242712320x7fed8ed09e800x7fed8e426340655366379927149976817703263773879177032637415401770326422810117703264244747
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004342291652291654194304256008242732160x7fed8ed09d000x7fed8e42638013107297174410871923217703264260367177032642281011770326471338317703264730505
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004372291652291654194304256008242757120x7fed8ed09b800x7fed8e4263c0131072102187411464757617703264745554177032647133831770326545802517703265475906
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044022916522916541943042560012242807680x7fed8ed09a000x7fed8e426400131072103240011557491217703265497986177032654580251770326591610617703265937445
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044322916522916541943042560012242876160x7fed8ed098800x7fed8e426440131072101575611380841617703265948224177032659161061770326646922817703266486871
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044622916522916541943042560012242942080x7fed8ed097000x7fed8e426480655366450407230488817703266502070177032664692281770326700762917703267023617
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004492291652291654194304256008242969600x7fed913695800x7fed8e4264c0131072100404011247852817703267039637177032670076291770326754619117703267561994
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004522291652291654194304256008242999680x7fed913694000x7fed8e42650013107299869011187648817703267579113177032675461911770326839483317703268411482
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004552291652291654194304256008243027200x7fed913692800x7fed8e426540131072100713211266494417703268435352177032683948331770326902891517703269044516
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045822916522916541943042560012243054720x7fed913691000x7fed8e426580131072100106611199394417703269061786177032690289151770326968155717703269697250
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046122916522916541943042560012243082240x7fed8ed09f800x7fed8e4265c0655366358167133844017703269715020177032696815571770327032587917703270345054
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004642291652291654194304256008243109760x7fed8ed09e000x7fed8e426600131072100612011229692817703270358873177032703258791770327098348017703271002737
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004672291652291654194304256008243132160x7fed8ed09c800x7fed8e426640131072107874212079649617703271015817177032709834801770327206700417703272085050
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004702291652291654194304256008243159680x7fed8ed09b000x7fed8e426680131072100240811231877617703272107659177032720668711770327312367317703273145913
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047322916522916541943042560012243187200x7fed8ed099800x7fed8e4266c0131072100785811291182417703273156883177032731236731770327421631517703274258785
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047622916522916541943042560012243214720x7fed8ed098000x7fed8e426700655366417747184400017703274270625177032742163151770327532863817703275393027
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004792291652291654194304256008243242240x7fed8ed096800x7fed8e42674013107299617811190279217703275404217177032753286381770327644240117703276482910
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004822291652291654194304256008243264640x7fed913695000x7fed8e426780131072100310411224539217703276494649177032764424011770327837024617703278415841
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004852291652291654194304256008243292160x7fed913693800x7fed8e4267c0131072100151211228281617703278435151177032783702461770328027473117703280319153
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048822916522916541943042560012243319680x7fed913692000x7fed8e426800131072100231011246784817703280330753177032802747311770328222609617703282294603
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049122916522916541943042560012243347200x7fed913690800x7fed8e426840655366408447178419217703282306123177032822260961770328419986117703284268924
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004942291652291654194304256008243374720x7fed8ed09f000x7fed8e426880131072103073411555504017703284279724177032841998611770328614146617703286212105
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049722916522916541943042560082400x7fed8ed09d800x7fed8e4268c0131072102011811437352017703286224035177032861414661770328976355517703289837694