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

48 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjGRBM_COUNTGRBM_GUI_ACTIVECPC_ME1_BUSY_FOR_PACKET_DECODESQ_CYCLESSQ_WAVESSQ_WAVE_CYCLESSQ_BUSY_CYCLESSQ_LEVEL_WAVESSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000236725236725335544322560043241600x00x7fc8d4204280388118388118881331049525242882453797003015215099782293217834114824366178334063407671783426159471917834261709089
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00223672523672532768256001224138880x00x7fc8d4223f8034226342263038027381651217328701626740694480817834266862991178342615947191783426700432617834267009117
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0052367252367254194304256001224143360x7fc8d71bf3800x7fc8d4223fc016606816606813553132855265536783381071221027031508370017834267052826178342670043261783426741360617834267416207
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0082367252367254194304256001624150400x7fc8d71bf2000x7fc8d4224000309075309075240402472608655362079744612361927083362748017834267463736178342674136061783426784400717834267846456
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00112367252367254194304256001624154880x7fc8d71bf0800x7fc8d4224040312717312717258352501744655362256902182387810090448870017834267887865178342678440071783426826880717834268271026
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00142367252367254194304256001224159360x7fc8d4b91f000x7fc8d422408016597116597114858132777665536881940641222047035450194817834268313195178342682688071783426860304817834268605407
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00172367252367254194304256001224163840x7fc8d4b91d800x7fc8d42240c016521916521914018132176065536790476991212215031792786417834268645846178342686030481783426893072817834268933069
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00202367252367254194304256001224170880x7fc8d4b91c000x7fc8d422410016437516437514488131500865536914621621207066036758062417834268987318178342689307281783426925936917834269261561
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00232367252367254194304256001624177920x7fc8d4b91a800x7fc8d4224140309703309703248522477632655362197772152368747088084014417834269301450178342692593691783426968656917834269688940
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00262367252367254194304256001624184960x7fc8d4b919000x7fc8d4224180310809310809222572486480655362252122762380921090257964017834269729219178342696865691783427010897017834270111340
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00292367252367254194304256001624192000x7fc8d4b917800x7fc8d42241c016540416540414552132324065536804501161211697032353769217834270152509178342701089701783427045089017834270453171
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00322367252367254194304256001624199040x7fc8d4b916000x7fc8d422420016558516558514733132468865536894658531214515035959185217834270494250178342704508901783427078241117834270784683
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00352367252367254194304256001224206080x7fc8d71bf4800x7fc8d422424016636616636614862133093665536914996481220000036772846417834270836062178342707824111783427111601117834271118425
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00382367252367254194304256001624213120x7fc8d71bf3000x7fc8d4224280312319312319245072498560655362332501312390649093473029617834271160384178342711160111783427155553217834271557414
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00412367252367254194304256001624220160x7fc8d71bf1800x7fc8d42242c0308649308649216192469200655362248511582359776090113407617834271600213178342715555321783427194465217834271946314
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00442367252367254194304256001624227200x7fc8d71bf0000x7fc8d422430016372516372514889130980865536911540351208364036634643217834271989503178342719446521783427225233317834272254047
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00472367252367254194304256001224234240x7fc8d4b91e800x7fc8d422434016346316346314910130771265536954018741206350038334199617834272296706178342722523331783427255137317834272553179
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00502367252367254194304256001224241280x7fc8d4b91d000x7fc8d422438016517416517415006132140065536937832811212963037686044417834272601598178342725513731783427285729417834272859102
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00532367252367254194304256001624248320x7fc8d4b91b800x7fc8d42243c0308899308899240672471200655362310071922364827092575885217834272905440178342728572941783427324993417834273251682
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00562367252367254194304256001624255360x7fc8d4b91a000x7fc8d4224400309717309717240642477744655362238040232368967089694792417834273293911178342732499341783427363889517834273640612
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00592367252367254194304256001224262400x7fc8d4b918800x7fc8d422444016439016439015085131512865536934318981207629037546176017834273682421178342736388951783427393809517834273939705
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00622367252367254194304256001224269440x7fc8d4b917000x7fc8d4224480164938164938149551319512655361078252971214954043302680817834273982454178342739380951783427425057517834274252317
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00652367252367254194304256001224276480x7fc8d71bf5800x7fc8d42244c016368416368415364130948065536985729891202351039602508417834274303036178342742505751783427456033617834274561989
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00682367252367254194304256001624286080x7fc8d71bf4000x7fc8d4224500309216309216242592473736655362294561452366399091955580817834274608288178342745603361783427496705617834274968889
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00712367252367254194304256001624293120x7fc8d71bf2800x7fc8d4224540306859306859223282454880655362113704682340855084721030417834275011958178342749670561783427535937717834275361219
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00742367252367254194304256001224300160x7fc8d71bf1000x7fc8d422458016279616279614816130237665536901308811195582036226446017834275404238178342753593771783427565985717834275661632
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077236725236725419430425600824309760x7fc8d4b91f800x7fc8d42245c016417616417615291131341665536946375301203733038028633617834275703781178342756598571783427596497817834275966724
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00802367252367254194304256001224316800x7fc8d4b91e000x7fc8d422460016448616448615106131589665536982631131206137039477438817834276016083178342759649781783427627137817834276273017
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00832367252367254194304256001624326400x7fc8d4b91c800x7fc8d4224640308147308147244832465184655362254611062358920090357661217834276314886178342762713781783427666321917834276665107
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00862367252367254194304256001224336000x7fc8d4b91b000x7fc8d4224680306784306784218222454280655362127580182344118085276170817834276707936178342766632191783427705217917834277053737
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00892367252367254194304256001224345600x7fc8d4b919800x7fc8d42246c016429116429115379131433665536897689861209049036081108017834277096186178342770521791783427735522017834277357100
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092236725236725419430425600824355200x7fc8d4b918000x7fc8d422470016633816633816385133071265536959495311221575038552909617834277398619178342773552201783427766066017834277662272
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00952367252367254194304256001224362240x7fc8d4b916800x7fc8d422474016284716284715060130278465536975054471200686039175029217834277710811178342776606601783427796770017834277969325
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00982367252367254194304256001224371840x7fc8d71bf5000x7fc8d4224780306864306864240432454920655362285960352350247091611752017834278011794178342779677001783427836258117834278364495
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001012367252367254194304256001224381440x7fc8d71bf3800x7fc8d42247c0307280307280228742458248655362191891652355632087848686417834278407854178342783625811783427875890117834278760595
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001042367252367254194304256001224391040x7fc8d71bf2000x7fc8d422480016364616364615305130917665536927382591205867037268389217834278802324178342787589011783427906562217834279067307
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107236725236725419430425600824403200x7fc8d71bf0800x7fc8d422484016281216281215305130250465536915130721197944036778162817834279109276178342790656221783427936834217834279369940
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001102367252367254194304256001224412800x7fc8d4b91f000x7fc8d422488016369716369714743130958465536975284751204580039184476817834279418069178342793683421783427967602317834279677612
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001132367252367254194304256001224422400x7fc8d4b91d800x7fc8d42248c0306817306817238552454544655362240747962348571089802791217834279723881178342796760231783428007746317834280079182
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001162367252367254194304256001224432000x7fc8d4b91c000x7fc8d4224900303088303088218482424712655362150982262320002086212447217834280121761178342800774631783428046642417834280468003
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119236725236725419430425600824441600x7fc8d4b91a800x7fc8d4224940162715162715146171301728655361001416731199730040229740417834280509402178342804664241783428077026417834280771805
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001222367252367254194304256001224453760x7fc8d4b919000x7fc8d422498016360816360815486130887265536919500431202769036954703217834280813514178342807702641783428107330517834281075087
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001252367252367254194304256001224463360x7fc8d4b917800x7fc8d42249c016229716229714425129838465536943828121195314037925619217834281124096178342810733051783428138434517834281386110
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001282367252367254194304256001224475520x7fc8d4b916000x7fc8d4224a00306664306664247862453320655362254858212347896090367435617834281432619178342813843451783428178866617834281790470
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001312367252367254194304256001224485120x7fc8d71bf4800x7fc8d4224a40304669304669228992437360655362143184492330625085900242017834281832979178342817886661783428218290617834282184770
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134236725236725419430425600824494720x7fc8d71bf3000x7fc8d4224a8016403216403214631131226465536888581981205412035716241617834282227459178342821829061783428248914617834282490792
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001372367252367254194304256001224506880x7fc8d71bf1800x7fc8d4224ac016320116320115807130561665536967218661200217038862231217834282533281178342824891461783428279362717834282795345
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001402367252367254194304256001224516480x7fc8d71bf0000x7fc8d4224b0016146316146314952129171265536887408421187214035669856017834282844754178342827936271783428310082717834283102377
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001432367252367254194304256001224528640x7fc8d4b91e800x7fc8d4224b40303745303745227102429968655362018366252316360080907875617834283144876178342831008271783428349650817834283498217
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001462367252367254194304256001224540800x7fc8d4b91d000x7fc8d4224b80301047301047216012408384655362104370202303682084347857217834283539956178342834965081783428389250817834283894117
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149236725236725419430425600824552960x7fc8d4b91b800x7fc8d4224bc016242816242814903129943265536884743181194758035562720817834283936316178342838925081783428419362917834284195250
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001522367252367254194304256001224567680x7fc8d4b91a000x7fc8d4224c00163629163629169501309040655361012176911198725040660180017834284237269178342841936291783428449586917834284497512
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001552367252367254194304256001224577280x7fc8d4b918800x7fc8d4224c4016339116339114597130713665536917143201200360036858511217834284546191178342844958691783428480579017834284807455
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001582367252367254194304256001224589440x7fc8d4b917000x7fc8d4224c80300221300221218452401776655362127398922297136085269328817834284848824178342848057901783428519251017834285194135
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001612367252367254194304256001224601600x7fc8d71bf5800x7fc8d4224cc0301545301545202832412368655362056294792301410082424661217834285238724178342851925101783428557987117834285581566
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164236725236725419430425600824613760x7fc8d71bf4000x7fc8d4224d0016313216313215667130506465536952106551200481038257285217834285623274178342855798711783428588115117834285882808
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001672367252367254194304256001224628480x7fc8d71bf2800x7fc8d4224d4016906516906516375135252865536978796691245323039326285217834285924347178342858811511783428619939117834286201270
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001702367252367254194304256001224638080x7fc8d71bf1000x7fc8d4224d8016270216270215058130162465536926053281194089037215188817834286252129178342861993911783428650995217834286511732
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001732367252367254194304256001224650240x7fc8d4b91f800x7fc8d4224dc0302903302903226092423232655362150427012319421086190462417834286559221178342865099521783428690515217834286906793
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001762367252367254194304256001224662400x7fc8d4b91e000x7fc8d4224e00299934299934209912399480655362115689342288440084801041217834286949312178342869051521783428729955317834287301333
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179236725236725419430425600824674560x7fc8d4b91c800x7fc8d4224e4016491716491715176131934465536928956531215543037332836817834287342372178342872995531783428760147317834287603155
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001822367252367254194304256001224689280x7fc8d4b91b000x7fc8d4224e80177796177796165781422376655361049945091313234042171441217834287645334178342876014731783428791523417834287916868
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001852367252367254194304256001224701440x7fc8d4b919800x7fc8d4224ec016081116081114705128649665536896297861181277036025806417834287965816178342879152341783428822307417834288224820
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001882367252367254194304256001224716160x7fc8d4b918000x7fc8d4224f00302087302087232942416704655362198516162309099088113885617834288266549178342882230741783428861683517834288618460
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001912367252367254194304256001224728320x7fc8d4b916800x7fc8d4224f40303611303611230052428896655362221379732319977089028259217834288661129178342886168351783428900771517834289009390
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194236725236725419430425600824740480x7fc8d71bf5000x7fc8d4224f8016316116316115630130529665536912359591194973036667794017834289050369178342890077151783428931043617834289312333
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001972367252367254194304256001224757760x7fc8d71bf3800x7fc8d4224fc0183219183219171011465760655361098268851356619044105785217834289355122178342893104361783428962579617834289627395
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002002367252367254194304256001224769920x7fc8d71bf2000x7fc8d422500016299716299715184130398465536886661441192526035640589617834289690813178342896257961783428993891717834289940647
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002032367252367254194304256001224784640x7fc8d71bf0800x7fc8d4225040301969301969221242415760655362147383492310781086068646817834289987216178342899389171783429036515717834290367057
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002062367252367254194304256001224799360x7fc8d4b91f000x7fc8d4225080302753302753231642422032655362102410172311664084269846817834290408876178342903651571783429076739817834290769027
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209236725236725419430425600824814080x7fc8d4b91d800x7fc8d42250c016258116258115730130065665536933380461195432037508805217834290811296178342907673981783429107523817834291077019
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002122367252367254194304256001224831360x7fc8d4b91c000x7fc8d4225100192516192516182591540136655361159887841429576046570140017834291118798178342910752381783429140019817834291402111
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002152367252367254194304256001224843520x7fc8d4b91a800x7fc8d422514016288916288915404130312065536960095141198118038576517617834291450040178342914001981783429171267917834291714363
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002182367252367254194304256001224858240x7fc8d4b919000x7fc8d4225180303894303894229752431160655362202980152321393088293143617834291756322178342917126791783429210627917834292108014
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002212367252367254194304256001224872960x7fc8d4b917800x7fc8d42251c0299823299823220162398592655362137263622293812085664147617834292152253178342921062791783429249748017834292499214
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002242367252367254194304256001224887680x7fc8d4b916000x7fc8d422520016245616245615936129965665536962755641197182038683448817834292541063178342924974801783429280484017834292806386
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002272367252367254194304256001224907520x7fc8d71bf4800x7fc8d4225240203471203471182001627776655361177969291513037047293849617834292847715178342928048401783429314212117834293143698
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002302367252367254194304256001224919680x7fc8d71bf3000x7fc8d422528016229216229215476129834465536939817791192840037766300417834293192997178342931421211783429345204117834293453861
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002332367252367254194304256001224934400x7fc8d71bf1800x7fc8d42252c0301740301740230352413928655362232163112308970089460156817834293501559178342934520411783429384980217834293851431
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002362367252367254194304256001224949120x7fc8d71bf0000x7fc8d4225300299586299586219712396696655362128667022295181085319676017834293895900178342938498021783429424324217834294245081
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002392367252367254194304256001224963840x7fc8d4b91e800x7fc8d422534016261816261815249130095265536984661081197652039559802817834294286870178342942432421783429455396317834294555623
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002422367252367254194304256001224983680x7fc8d4b91d000x7fc8d4225380211130211130190591689048655361399970821578277056173278817834294597952178342945539631783429488884317834294890575
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002452367252367254194304256001224995840x7fc8d4b91b800x7fc8d42253c016245416245415664129964065536956754691195184038443077617834294938784178342948888431783429519748417834295199077
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024823672523672541943042560012241013120x7fc8d4b91a000x7fc8d4225400298352298352228502386824655362181834392281773087446575217834295239986178342951974841783429559172417834295593397
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025123672523672541943042560012241027840x7fc8d4b918800x7fc8d4225440299448299448224282395592655362080030502290833083374356017834295635696178342955917241783429598500517834295986638
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025423672523672541943042560012241042560x7fc8d4b917000x7fc8d422548016183616183615933129469665536984496941189411039553851617834296029047178342959850051783429628948517834296291350
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025723672523672541943042560012241062400x7fc8d71bf5800x7fc8d42254c0220777220777199351766224655361267956731647432050893893617834296332469178342962894851783429663380617834296635512
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026023672523672541943042560012241077120x7fc8d71bf4000x7fc8d422550016188816188815580129511265536899627501188814036158393217834296685250178342966338061783429694324617834296945044
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026323672523672541943042560016241094400x7fc8d71bf2800x7fc8d4225540297291297291214092378336655362066952332272110082851314017834296991243178342969432461783429733828617834297340024
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026623672523672541943042560016241111680x7fc8d71bf1000x7fc8d4225580301879301879237182415040655362159057452301239086535303217834297383633178342973382861783429773236717834297734054
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002692367252367254194304256008241128960x7fc8d4b91f800x7fc8d42255c016460116460116231131681665536998333611209593040109166817834297775473178342977323671783429804180717834298043577
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027223672523672541943042560012241151360x7fc8d4b91e000x7fc8d4225600229723229723197731837792655361491364921730381059829760817834298092205178342980418071783429840404817834298405698
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027523672523672541943042560012241166080x7fc8d4b91c800x7fc8d422564016140216140215123129122465536909210501187708036542297617834298454706178342984040481783429871204817834298713750
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027823672523672541943042560016241183360x7fc8d4b91b000x7fc8d4225680298204298204207922385640655361979861382276652079368538417834298760439178342987120481783429910580917834299107450
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028123672523672541943042560016241200640x7fc8d4b919800x7fc8d42256c0300595300595224942404768655362153797372301175086325426817834299150079178342991058091783429949668917834299498340
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028423672523672541943042560012241217920x7fc8d4b918000x7fc8d4225700164958164958163701319672655361016163311214016040821214417834299539319178342994966891783429980181017834299803813
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028723672523672541943042560012241240320x7fc8d4b916800x7fc8d4225740240645240645205161925168655361577325561813466063267464017834299844102178342998018101783430016357017834300165174
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029023672523672541943042560012241255040x7fc8d71bf5000x7fc8d422578016212616212615768129701665536981870981194453039450401217834300214413178343001635701783430047557117834300477146
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029323672523672541943042560012241274880x7fc8d71bf3800x7fc8d42257c0302955302955209382423648655362057348972308541082467283617834300523855178343004755711783430087253117834300874236
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029623672523672541943042560012241292160x7fc8d71bf2000x7fc8d4225800298432298432207292387464655362026376222282225081228560017834300916045178343008725311783430126277217834301264587
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029923672523672541943042560012241309440x7fc8d71bf0800x7fc8d4225840171091171091160301368736655361008521341263541040515468817834301305746178343012627721783430157397217834301575609
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030223672523672541943042560012241334400x7fc8d4b91f000x7fc8d4225880259655259655212492077248655361667455501964412066873285217834301617628178343015739721783430193893317834301940650
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030523672523672541943042560012241349120x7fc8d4b91d800x7fc8d42258c016181516181515866129452865536958938551188755038532051617834301990029178343019389331783430225941317834302260992
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030823672523672541943042560012241368960x7fc8d4b91c000x7fc8d4225900296539296539209142372320655362026496712263614081233805617834302302771178343022594131783430265525417834302657002
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031123672523672541943042560012241388800x7fc8d4b91a800x7fc8d4225940297031297031211722376256655362059014822265136082534438817834302698781178343026552541783430304437417834303046012
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031423672523672541943042560012241408640x7fc8d4b919000x7fc8d4225980178771178771167381430176655361069475251324370042953785617834303087531178343030443741783430335749517834303359055
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031723672523672541943042560012241436160x7fc8d4b917800x7fc8d42259c0280909280909230932247280655361908023292129530076495706417834303400584178343033574951783430373477517834303736465
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032023672523672541943042560012241453440x7fc8d4b916000x7fc8d4225a00163019163019165901304160655361023318261195152041107335617834303785814178343037347751783430404517617834304046747
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032323672523672541943042560012241475840x7fc8d71bf4800x7fc8d4225a40296769296769213222374160655362037785342261266081687752017834304088806178343040451761783430443749617834304439028
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032623672523672541943042560012241495680x7fc8d71bf3000x7fc8d4225a80296072296072209532368584655362068339222259877082907487617834304479807178343044374961783430482885717834304830788
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032923672523672541943042560012241515520x7fc8d71bf1800x7fc8d4225ac0186912186912174501495304655361031386911380354041430626017834304870297178343048288571783430516037717834305162140
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033223672523672541943042560012241543040x7fc8d71bf0000x7fc8d4225b00300476300476235582403816655361957679352289652078482806017834305202979178343051603771783430555333817834305555040
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033523672523672541943042560012241562880x7fc8d4b91e800x7fc8d4225b40171069171069167661368560655361013006941266522040694706017834305604099178343055533381783430587253817834305874242
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033823672523672541943042560012241587840x7fc8d4b91d000x7fc8d4225b80299366299366192462394936655361642223682269854065863961617834305915891178343058725381783430626661917834306268682
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034123672523672541943042560012241610240x7fc8d4b91b800x7fc8d4225bc0297382297382207082379064655361916018472264334076815206417834306309591178343062666191783430666149917834306663382
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034423672523672541943042560012241632640x7fc8d4b91a000x7fc8d4225c00207412207412190741659304655361233776171541710049527532817834306703341178343066614991783430699301917834306994584
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034723672523672541943042560012241665280x7fc8d4b918800x7fc8d4225c40341044341044255392728360655362307388522613176092471604817834307035523178343069930191783430741126017834307459113
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035023672523672541943042560012241685120x7fc8d4b917000x7fc8d4225c80184919184919180331479360655361156752891368223046444821217834307478252178343074112601783430776758117834307769255
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035323672523672541943042560012241712640x7fc8d71bf5800x7fc8d4225cc0298024298024218632384200655361586069792238111063617721217834307811134178343077675811783430816118117834308162815
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035623672523672541943042560012241737600x7fc8d71bf4000x7fc8d4225d00297180297180205302377448655361845057272259504073977248417834308205604178343081611811783430855606217834308557885
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035923672523672541943042560012241762560x7fc8d71bf2800x7fc8d4225d40224815224815196301798528655361457764011689205058485102817834308598954178343085560621783430890070217834308902377
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036223672523672541943042560012241797760x7fc8d71bf1000x7fc8d4225d803818693818692792630549606553625707085829366530103004263617834308943066178343089007021783430934726317834309366235
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036523672523672541943042560012241822720x7fc8d4b91f800x7fc8d4225dc0212815212815195131702528655361224648611583033049161770817834309397585178343093472631783430968630317834309687957
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036823672523672541943042560012241855360x7fc8d4b91e000x7fc8d4225e00310102310102240972480824655361854647832345934074362811617834309728316178343096863031783431009030417834310096947
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037123672523672541943042560012241885440x7fc8d4b91c800x7fc8d4225e40311821311821209782494576655361796736462366407072045740417834310132456178343100903041783431050982417834310531006
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037423672523672541943042560012241915520x7fc8d4b91b000x7fc8d4225e80266016266016217652128136655361776459792018546071234395217834310551946178343105098241783431087974517834310881678
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037723672523672541943042560012241958400x7fc8d4b919800x7fc8d4225ec04622304622303144536978486553632781499735821850131302120017834310921557178343108797451783431137334517834311392615
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038023672523672541943042560012241985920x7fc8d4b918000x7fc8d4225f00243299243299205371946400655361686325961836482067628942417834311423864178343113733451783431173270617834311734556
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038323672523672541943042560012242023680x7fc8d4b916800x7fc8d4225f40334675334675238182677408655361998776092554723080127726017834311774095178343117327061783431216086617834312179645
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038623672523672541943042560012242058880x7fc8d71bf5000x7fc8d4225f80333944333944232472671560655362073894012543268083133933217834312203145178343121608661783431258406717834312601845
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038923672523672541943042560012242094080x7fc8d71bf3800x7fc8d4225fc0307785307785236452462288655362046597232351204082040593217834312625324178343125840671783431298550817834312987395
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039223672523672541943042560012242144640x7fc8d71bf2000x7fc8d42260005438315438313644643506566553640010870342280410160220361617834313028704178343129855081783431352886817834313545371
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039523672523672541943042560012242177280x7fc8d71bf0800x7fc8d4226040272076272076220792176616655361959692892069235078563008817834313580611178343135288681783431390758917834313909332
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039823672523672541943042560012242220160x7fc8d4b91f000x7fc8d4226080366676366676274482933416655362451830512817157098251276017834313950611178343139075891783431435702917834314375181
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040123672523672541943042560012242260480x7fc8d4b91d800x7fc8d42260c03646983646982812129175926553625564250228069000102433344417834314399810178343143570291783431480263017834314845409
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040423672523672541943042560012242300800x7fc8d4b91c000x7fc8d4226100347899347899257942783200655362424876032672104097172032017834314855839178343148026301783431524519117834315287608
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040723672523672541943042560012242359040x7fc8d4b91a800x7fc8d42261406254816254814068650038566553646003113748790680184189461217834315298628178343152451911783431587607117834315918383
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041023672523672541943042560012242394240x7fc8d4b919000x7fc8d4226180302927302927235962423424655362132616012312174085481376817834315937612178343158760711783431629783217834316299403
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041323672523672541943042560012242442240x7fc8d4b917800x7fc8d42261c03990753990752760831926086553626419577330800750105856939217834316340782178343162978321783431675975317834316801851
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041623672523672541943042560012242487680x7fc8d4b916000x7fc8d42262003921303921302768131370486553628934703130227060115916579217834316812020178343167597531783431723975317834317281259
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041923672523672541943042560012242533120x7fc8d71bf4800x7fc8d42262403879523879522780731036246553628075332929891100112477806417834317291418178343172397531783431770935417834317727518
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004222367252367254194304256008242555520x7fc8d71bf3000x7fc8d42262807199307199304487657594486553654335738656361110217516988017834317752167178343177093541783431837479517834318418700
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042523672523672541943042560012242598400x7fc8d71bf1800x7fc8d42262c03648243648242741129186006553626301756228010390105383544817834318438150178343183747951783431883623517834318879929
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042823672523672541943042560012242656640x7fc8d71bf0000x7fc8d42263004712924712923240337703446553635119724336533220140657883617834318891029178343188362351783431936903617834319411026
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043123672523672541943042560012242712320x7fc8d4b91e800x7fc8d42263404741384741383296837931126553634957259936802000140007853617834319421405178343193690361783431991015717834319951892
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004342367252367254194304256008242732160x7fc8d4b91d000x7fc8d42263804833144833143300138665206553635278308037533360141287368017834319962552178343199101571783432043719817834320479809
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004372367252367254194304256008242757120x7fc8d4b91b800x7fc8d42263c08801388801385298670411126553667541080869297330270338448817834320490389178343204371981783432122983917834321272819
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044023672523672541943042560012242807680x7fc8d4b91a000x7fc8d42264004258814258812966934070566553631812616332993960127427500017834321292269178343212298391783432172455917834321742908
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044323672523672541943042560012242876160x7fc8d4b918800x7fc8d42264405520005520003540844160086553640516808543058900162246586417834321767237178343217245591783432228936017834322335643
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044623672523672541943042560012242942080x7fc8d4b917000x7fc8d42264805515815515813605744126566553640972158242984650164067001217834322347203178343222893601783432287960117834322924048
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004492367252367254194304256008242969600x7fc8d71bf5800x7fc8d42264c05632705632703673345061686553642219821943926940169053826017834322935358178343228796011783432346024217834323501854
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004522367252367254194304256008242999680x7fc8d71bf4000x7fc8d4226500104163010416306150883330486553679758675882189150319208913217834323512054178343234600721783432435479217834324401882
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004552367252367254194304256008243027200x7fc8d71bf2800x7fc8d42265407216387216384456557731126553653824307856591850215471433617834324420811178343243547921783432503831217834325080545
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045823672523672541943042560012243054720x7fc8d71bf1000x7fc8d42265807236597236594522757892806553654168372256715570216847718017834325091305178343250383121783432573223317834325775538
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046123672523672541943042560012243082240x7fc8d4b91f800x7fc8d42265c07240667240664523657925366553655443232556658080221947020417834325786137178343257322331783432642535417834326470040
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004642367252367254194304256008243109760x7fc8d4b91e000x7fc8d42266007275287275284527158202326553654213243257009570217027301617834326481840178343264253541783432712135417834327165433
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004672367252367254194304256008243132160x7fc8d4b91c800x7fc8d4226640136871613687167797410949736655361066748922108131540426873760017834327175473178343271213541783432822631517834328269906
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004702367252367254194304256008243159680x7fc8d4b91b000x7fc8d4226680136982413698247783110958600655361076782474108431150430887166817834328288855178343282263151783432931111617834329374338
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047323672523672541943042560012243187200x7fc8d4b919800x7fc8d42266c0137512413751247806511001000655361071881202108654940428926686817834329385588178343293111161783433045415817834330521830
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047623672523672541943042560012243214720x7fc8d4b918000x7fc8d4226700137123813712387743610969912655361077779295108536970431285798417834330533269178343304541581783433159559917834331662981
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004792367252367254194304256008243242240x7fc8d4b916800x7fc8d4226740137613013761307771311009048655361084688254108869660434049540817834331673821178343315955991783433273192017834332799413
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004822367252367254194304256008243264640x7fc8d71bf5000x7fc8d42267802662336266233614242421298696655362131580032211845140852806138017834332810773178343327319201783433470424217834334776354
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004852367252367254194304256008243292160x7fc8d71bf3800x7fc8d42267c02670852267085214334221366824655362131999864212335210852974075217834334795274178343347042421783433665352417834336720826
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048823672523672541943042560012243319680x7fc8d71bf2000x7fc8d42268002670556267055614272121364456655362122324716212386230849103985217834336731875178343366535241783433865400617834338725046
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049123672523672541943042560012243347200x7fc8d71bf0800x7fc8d42268402669612266961214366621356904655362113520736212294730845582314417834338736746178343386540061783434066392817834340732916
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004942367252367254194304256008243374720x7fc8d4b91f000x7fc8d42268802674293267429314329021394352655362122181246212638140849046805217834340744566178343406639281783434261673017834342688017
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049723672523672541943042560082400x7fc8d4b91d800x7fc8d42268c052568625256862273842420549046553642292103684192895901691858334017834342699137178343426167301783434626105417834346333537