Files
rocm-systems/tests/workloads/Axes4/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.kd000217617217617335544322560043241600x00x7f34168042803670016290094632528848817519240137891175140407853101751938348405717519383597957
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00221761721761732768256001224138880x00x7f3416823f80512979561098423217519388715876175193834840571751938884630617519388850993
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0052176172176174194304256001224143360x7f34198663800x7f3416823fc0655366050486782814417519388884212175193888463061751938921014717519389212713
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0082176172176174194304256001624150400x7f34198662000x7f3416824000655366862367694953617519389249102175193892101471751938960822717519389610593
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00112176172176174194304256001624154880x7f34198660800x7f3416824040655366355547115552817519389641402175193896082271751938999718817519389999463
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00142176172176174194304256001224159360x7f3417209f000x7f3416824080655366375367127802417519390033332175193899971881751939031062917519390312745
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00172176172176174194304256001224163840x7f3417209d800x7f34168240c0655366351187121486417519390344044175193903106291751939061718917519390619397
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00202176172176174194304256001224170880x7f3417209c000x7f34168241001310726789687603288817519390663476175193906171891751939091319017519390915630
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00232176172176174194304256001624177920x7f3417209a800x7f34168241401310726861247687502417519390946949175193909131901751939130327017519391305680
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00262176172176174194304256001624184960x7f34172099000x7f3416824180655366534247341689617519391336179175193913032701751939169239117519391694560
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00292176172176174194304256001624192000x7f34172097800x7f34168241c01310726790787605028017519391724579175193916923911751939200663217519392008991
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00322176172176174194304256001624199040x7f34172096000x7f34168242001310726782807590884017519392040091175193920066321751939230647217519392308514
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00352176172176174194304256001224206080x7f34198664800x7f34168242401310726841927655704817519392347493175193923064721751939260663317519392608966
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00382176172176174194304256001624213120x7f34198663000x7f34168242801310726758647568207217519392640885175193926066331751939299495317519392997086
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00412176172176174194304256001624220160x7f34198661800x7f34168242c0655366422087195925617519393028065175193929949531751939338151417519393383686
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00442176172176174194304256001624227200x7f34198660000x7f34168243001310726842607665099217519393415325175193933815141751939367911517519393681239
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00472176172176174194304256001224234240x7f3417209e800x7f34168243401310727178328023451217519393711478175193936791151751939397527517519393977471
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00502176172176174194304256001224241280x7f3417209d000x7f34168243801310726729487543220017519394016130175193939752751751939429943617519394301893
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00532176172176174194304256001624248320x7f3417209b800x7f34168243c01310726793987614658417519394333032175193942994361751939469127617519394693383
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00562176172176174194304256001624255360x7f3417209a000x7f3416824400655366122006855452817519394724472175193946912761751939508471717519395086382
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00592176172176174194304256001224262400x7f34172098800x7f34168244401310726793447616874417519395116292175193950847171751939536679817519395368375
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00622176172176174194304256001224269440x7f34172097000x7f34168244801310726743247563004817519395399244175193953667981751939563639817519395638108
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00652176172176174194304256001224276480x7f34198665800x7f34168244c01310726394147160466417519395675417175193956363981751939591015917519395911711
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00682176172176174194304256001624286080x7f34198664000x7f34168245001310726782087607132817519395944420175193959101591751939627399917519396275562
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00712176172176174194304256001624293120x7f34198662800x7f3416824540655366365687139228017519396306091175193962739991751939662744017519396628993
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00742176172176174194304256001224300160x7f34198661000x7f34168245801310726403707171224017519396659872175193966274401751939689816017519396899706
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077217617217617419430425600824309760x7f3417209f800x7f34168245c01310726456587217956017519396930985175193968981601751939716776117519397169349
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00802176172176174194304256001224316800x7f3417209e000x7f34168246001310726819867638261617519397207478175193971677611751939743672117519397438432
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00832176172176174194304256001624326400x7f3417209c800x7f34168246401310726421227200392017519397470001175193974367211751939779208217519397793693
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00862176172176174194304256001224336000x7f3417209b000x7f3416824680655366361867126711217519397824442175193977920821751939815448317519398156394
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00892176172176174194304256001224345600x7f34172099800x7f34168246c01310726802907624800817519398187753175193981544831751939843624317519398437926
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092217617217617419430425600824355200x7f34172098000x7f34168247001310726782347594925617519398468886175193984362431751939870456417519398706140
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00952176172176174194304256001224362240x7f34172096800x7f34168247401310726674867472813617519398743709175193987045641751939897512417519398976613
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00982176172176174194304256001224371840x7f34198665000x7f34168247801310726339247110014417519399007392175193989751241751939933128517519399332903
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001012176172176174194304256001224381440x7f34198663800x7f34168247c0655366425987206217617519399364613175193993312851751939968984617519399691474
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001042176172176174194304256001224391040x7f34198662000x7f34168248001310727118187972816817519399722473175193996898461751939995912617519399960817
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107217617217617419430425600824403200x7f34198660800x7f34168248401310726820547632625617519399991986175193999591261751940022968617519400231380
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001102176172176174194304256001224412800x7f3417209f000x7f34168248801310726863387685812017519400269679175194002296861751940050488717519400506423
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001132176172176174194304256001224422400x7f3417209d800x7f34168248c01310726855507665503217519400537592175194005048871751940087128817519400872844
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001162176172176174194304256001224432000x7f3417209c000x7f3416824900655366039866769700817519400904323175194008712881751940122632817519401227955
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119217617217617419430425600824441600x7f3417209a800x7f34168249401310726708827515941617519401258424175194012263281751940149688917519401498618
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001222176172176174194304256001224453760x7f34172099000x7f34168249801310726832267653592017519401528577175194014968891751940176776917519401769271
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001252176172176174194304256001224463360x7f34172097800x7f34168249c01310726769487593396017519401806360175194017677691751940203625017519402037764
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001282176172176174194304256001224475520x7f34172096000x7f3416824a001310726711907527470417519402068143175194020362501751940241257017519402414194
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001312176172176174194304256001224485120x7f34198664800x7f3416824a40655366334587100534417519402445703175194024125701751940276777117519402769285
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134217617217617419430425600824494720x7f34198663000x7f3416824a801310726442887211703217519402799814175194027677711751940303497217519403036578
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001372176172176174194304256001224506880x7f34198661800x7f3416824ac01310726421027200292817519403067518175194030349721751940330489217519403306521
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001402176172176174194304256001224516480x7f34198660000x7f3416824b001310726393887163736817519403345470175194033048921751940358537317519403586864
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001432176172176174194304256001224528640x7f3417209e800x7f3416824b401310726808367638478417519403617283175194035853731751940394057317519403942085
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001462176172176174194304256001224540800x7f3417209d000x7f3416824b80655366376027145503217519403973284175194039405731751940429977417519404301386
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149217617217617419430425600824552960x7f3417209b800x7f3416824bc01310726850807668583217519404331395175194042997741751940457209417519404573599
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001522176172176174194304256001224567680x7f3417209a000x7f3416824c001310726709807510604017519404605058175194045720941751940484569517519404847242
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001552176172176174194304256001224577280x7f34172098800x7f3416824c401310726942907781176817519404884941175194048456951751940511657517519405118095
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001582176172176174194304256001224589440x7f34172097000x7f3416824c801310726413107186200817519405148644175194051165751751940547289617519405474556
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001612176172176174194304256001224601600x7f34198665800x7f3416824cc0655366325127084091217519405505165175194054728961751940582969717519405831397
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164217617217617419430425600824613760x7f34198664000x7f3416824d001310726699267499128017519405862546175194058296971751940609785717519406099650
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001672176172176174194304256001224628480x7f34198662800x7f3416824d401310726761387564516817519406131579175194060978571751940638121817519406382842
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001702176172176174194304256001224638080x7f34198661000x7f3416824d801310726778227598169617519406421241175194063812181751940665273817519406654215
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001732176172176174194304256001224650240x7f3417209f800x7f3416824dc01310726361647134446417519406685055175194066527381751940700985917519407011416
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001762176172176174194304256001224662400x7f3417209e000x7f3416824e00655366061906790140817519407042235175194070098591751940736537917519407366787
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179217617217617419430425600824674560x7f3417209c800x7f3416824e401310726882567699875217519407397006175194073653791751940763658017519407638220
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001822176172176174194304256001224689280x7f3417209b000x7f3416824e801310726812187629289617519407669009175194076365801751940791690017519407918383
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001852176172176174194304256001224701440x7f34172099800x7f3416824ec01310726458527245517617519407956082175194079169001751940819546117519408197016
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001882176172176174194304256001224716160x7f34172098000x7f3416824f001310726834287659684017519408227525175194081954611751940855434117519408556057
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001912176172176174194304256001224728320x7f34172096800x7f3416824f40655366835567649450417519408586076175194085543411751940891194217519408913437
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194217617217617419430425600824740480x7f34198665000x7f3416824f801310726400047171088017519408943757175194089119421751940918906317519409190870
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001972176172176174194304256001224757760x7f34198663800x7f3416824fc01310726402547164488017519409221049175194091890631751940947370317519409475383
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002002176172176174194304256001224769920x7f34198662000x7f34168250001310726756927569364017519409513862175194094737031751940975034417519409751786
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002032176172176174194304256001224784640x7f34198660800x7f34168250401310726808107621882417519409782585175194097503441751941010650417519410108497
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002062176172176174194304256001224799360x7f3417209f000x7f3416825080655367020827868689617519410140316175194101065041751941046906517519410470807
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209217617217617419430425600824814080x7f3417209d800x7f34168250c01310726854507675701617519410501217175194104690651751941073946517519410741070
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002122176172176174194304256001224831360x7f3417209c000x7f34168251001310726803007614028017519410771220175194107394651751941103082617519411032423
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002152176172176174194304256001224843520x7f3417209a800x7f34168251401310726785207607008017519411083592175194110308261751941130698617519411308596
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002182176172176174194304256001224858240x7f34172099000x7f34168251801310726809527628966417519411339285175194113069861751941166618717519411667857
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002212176172176174194304256001224872960x7f34172097800x7f34168251c0655366444187218236017519411698866175194116661871751941202650817519412028287
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002242176172176174194304256001224887680x7f34172096000x7f34168252001310726708707521649617519412058987175194120265081751941229946817519412301080
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002272176172176174194304256001224907520x7f34198664800x7f34168252401310726766127577274417519412331300175194122994681751941259674917519412598433
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002302176172176174194304256001224919680x7f34198663000x7f34168252801310726699047503052017519412636572175194125967491751941286698917519412868606
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002332176172176174194304256001224934400x7f34198661800x7f34168252c01310726729727555855217519412898865175194128669891751941322363017519413225127
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002362176172176174194304256001224949120x7f34198660000x7f3416825300655366317347063191217519413256016175194132236301751941357803117519413579458
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002392176172176174194304256001224963840x7f3417209e800x7f34168253401310726778487592780817519413609297175194135780311751941384651117519413848011
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002422176172176174194304256001224983680x7f3417209d000x7f34168253801310726835327651460817519413877920175194138465111751941414619217519414147683
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002452176172176174194304256001224995840x7f3417209b800x7f34168253c01310726690747498068017519414185682175194141461921751941442795217519414429556
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024821761721761741943042560012241013120x7f3417209a000x7f34168254001310726435187202356017519414460055175194144279521751941479115317519414792766
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025121761721761741943042560012241027840x7f34172098800x7f3416825440655366412467189006417519414823256175194147911531751941514571317519415147397
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025421761721761741943042560012241042560x7f34172097000x7f34168254801310726439867210530417519415177207175194151457131751941541595417519415417620
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025721761721761741943042560012241062400x7f34198665800x7f34168254c01310726340267092126417519415447460175194154159541751941572171417519415723183
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026021761721761741943042560012241077120x7f34198664000x7f34168255001310726358767114512017519415762562175194157217141751941599627517519415997825
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026321761721761741943042560016241094400x7f34198662800x7f34168255401310726737347551652017519416028545175194159962751751941635163617519416353376
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026621761721761741943042560016241111680x7f34198661000x7f3416825580655366375767141895217519416384256175194163516361751941670683617519416708337
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002692176172176174194304256008241128960x7f3417209f800x7f34168255c01310726817487629651217519416738856175194167068361751941697803717519416979730
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027221761721761741943042560012241151360x7f3417209e000x7f34168256001310726688487506620017519417009789175194169780371751941729195717519417293482
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027521761721761741943042560012241166080x7f3417209c800x7f34168256401310726763367573708817519417330711175194172919571751941756731817519417568975
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027821761721761741943042560016241183360x7f3417209b000x7f34168256801310726837247674724017519417599634175194175673181751941792731817519417929096
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028121761721761741943042560016241200640x7f34172099800x7f34168256c0655366422667196787217519417958675175194179273181751941829051917519418292407
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028421761721761741943042560012241217920x7f34172098000x7f34168257001310726725387541829617519418322346175194182905191751941856556017519418567200
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028721761721761741943042560012241240320x7f34172096800x7f34168257401310726689007503504017519418597879175194185655601751941888556017519418887231
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029021761721761741943042560012241255040x7f34198665000x7f34168257801310727048347907735217519418924690175194188855601751941915516117519419156824
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029321761721761741943042560012241274880x7f34198663800x7f34168257c01310726769067582455217519419186934175194191551611751941951084117519419512535
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029621761721761741943042560012241292160x7f34198662000x7f3416825800655366438767205692817519419542544175194195108411751941986700217519419868566
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029921761721761741943042560012241309440x7f34198660800x7f34168258401310726419247177561617519419899465175194198670021751942014300217519420144399
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030221761721761741943042560012241334400x7f3417209f000x7f34168258801310726555887346599217519420175328175194201430021751942047244317519420474211
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030521761721761741943042560012241349120x7f3417209d800x7f34168258c0131072102850811518672017519420512290175194204724431751942075532317519420756913
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030821761721761741943042560012241368960x7f3417209c000x7f34168259001310726363967124002417519420787872175194207553231751942111804417519421119634
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031121761721761741943042560012241388800x7f3417209a800x7f3416825940655366371107136907217519421149883175194211180441751942147724517519421478915
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031421761721761741943042560012241408640x7f34172099000x7f34168259801310726953507784948017519421508124175194214772451751942176140517519421762927
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031721761721761741943042560012241436160x7f34172097800x7f34168259c01310726726887541342417519421792867175194217614051751942210556617519422107469
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032021761721761741943042560012241453440x7f34172096000x7f3416825a00131072101264211315060817519422146378175194221055661751942238092617519422382622
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032321761721761741943042560012241475840x7f34198664800x7f3416825a401310726825947637899217519422412991175194223809261751942273932717519422740952
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032621761721761741943042560012241495680x7f34198663000x7f3416825a80655366377387134956017519422771292175194227393271751942309628817519423098003
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032921761721761741943042560012241515520x7f34198661800x7f3416825ac01310726361727124751217519423128312175194230962881751942338268817519423384326
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033221761721761741943042560012241543040x7f34198660000x7f3416825b001310727095667954433617519423415015175194233826881751942374812917519423749576
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033521761721761741943042560012241562880x7f3417209e800x7f3416825b4013107296208210782584017519423787955175194237481291751942403436917519424036029
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033821761721761741943042560012241587840x7f3417209d000x7f3416825b801310726796247609930417519424066268175194240343691751942439757017519424399300
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034121761721761741943042560012241610240x7f3417209b800x7f3416825bc0655366427207195867217519424429379175194243975701751942475997117519424761560
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034421761721761741943042560012241632640x7f3417209a000x7f3416825c001310726330127092502417519424791580175194247599711751942505933117519425060963
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034721761721761741943042560012241665280x7f34172098800x7f3416825c401310726304247063807217519425091372175194250593311751942544493217519425463322
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035021761721761741943042560012241685120x7f34172097000x7f3416825c8013107299360411133502417519425485002175194254449321751942574029217519425741815
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035321761721761741943042560012241712640x7f34198665800x7f3416825cc01310726415227179688817519425772024175194257402921751942609869317519426100246
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035621761721761741943042560012241737600x7f34198664000x7f3416825d00655366433067194075217519426131215175194260986931751942646269417519426464267
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035921761721761741943042560012241762560x7f34198662800x7f3416825d401310726328887087658417519426495086175194264626941751942677725417519426778879
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036221761721761741943042560012241797760x7f34198661000x7f3416825d801310726409147170540817519426809368175194267772541751942718685517519427207558
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036521761721761741943042560012241822720x7f3417209f800x7f3416825dc013107295007810645236017519427226347175194271868551751942749965617519427501290
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036821761721761741943042560012241855360x7f3417209e000x7f3416825e001310726698427496177617519427531849175194274996561751942786733617519427887740
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037121761721761741943042560012241885440x7f3417209c800x7f3416825e40655366501647279852017519427899150175194278673361751942825069717519428270290
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037421761721761741943042560012241915520x7f3417209b000x7f3416825e801310726375807148069617519428281590175194282506971751942859357817519428595302
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037721761721761741943042560012241958400x7f34172099800x7f3416825ec01310726374367143927217519428625861175194285935781751942905645817519429078030
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038021761721761741943042560012241985920x7f34172098000x7f3416825f00131072100256611208691217519429096989175194290564581751942939405917519429395641
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038321761721761741943042560012242023680x7f34172096800x7f3416825f4013107293469610457416017519429425551175194293940591751942978334017519429800271
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038621761721761741943042560012242058880x7f34198665000x7f3416825f80655366369147149583217519429814681175194297833401751943017710017519430221230
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038921761721761741943042560012242094080x7f34198663800x7f3416825fc01310726432127205392817519430231860175194301771001751943058350117519430585231
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039221761721761741943042560012242144640x7f34198662000x7f34168260001310726510867305508017519430617120175194305835011751943109438217519431135997
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039521761721761741943042560012242177280x7f34198660800x7f341682604013107299410611140876017519431155146175194310943821751943146734317519431469048
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039821761721761741943042560012242220160x7f3417209f000x7f3416826080131072100067611217184017519431499707175194314673431751943187566417519431917097
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040121761721761741943042560012242260480x7f3417209d800x7f34168260c0655366395007161123217519431929686175194318756641751943231806417519432359625
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040421761721761741943042560012242300800x7f3417209c000x7f34168261001310726349067115117617519432370365175194323180641751943274286517519432761575
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040721761721761741943042560012242359040x7f3417209a800x7f34168261401310726453547229996817519432775025175194327428651751943331326617519433330990
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041021761721761741943042560012242394240x7f34172099000x7f3416826180131072100694811263831217519433352890175194333132661751943368878717519433690461
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041321761721761741943042560012242442240x7f34172097800x7f34168261c0131072102531811471139217519433719790175194336887871751943412414817519434147619
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041621761721761741943042560012242487680x7f34172096000x7f3416826200655366404447177573617519434158759175194341241481751943456558817519434586398
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041921761721761741943042560012242533120x7f34198664800x7f34168262401310726361747122584817519434598038175194345655881751943498606917519435003417
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004222176172176174194304256008242555520x7f34198663000x7f3416826280131072100794811298792817519435018307175194349860691751943561999017519435636641
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042521761721761741943042560012242598400x7f34198661800x7f34168262c0131072100864611311207217519435660131175194356199901751943602415117519436040531
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042821761721761741943042560012242656640x7f34198660000x7f341682630013107296054010774615217519436056230175194360241511751943650575217519436523918
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043121761721761741943042560012242712320x7f3417209e800x7f3416826340655366396387164268817519436537568175194365057521751943698687317519437003206
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004342176172176174194304256008242732160x7f3417209d000x7f341682638013107295959610757064017519437018836175194369868731751943746607417519437487234
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004372176172176174194304256008242757120x7f3417209b800x7f34168263c0131072100323211244948817519437498013175194374660741751943820927517519438229975
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044021761721761741943042560012242807680x7f3417209a000x7f341682640013107296029810754762417519438249064175194382092751751943866783617519438685063
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044321761721761741943042560012242876160x7f34172098800x7f341682644013107298880011062095217519438698983175194386678361751943920239717519439244059
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044621761721761741943042560012242942080x7f34172097000x7f3416826480655366397507165683217519439254098175194392023971751943975711817519439798694
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004492176172176174194304256008242969600x7f34198665800x7f34168264c013107297214810897224817519439809144175194397571181751944030991917519440327691
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004522176172176174194304256008242999680x7f34198664000x7f341682650013107299368411132603217519440342860175194403099191751944114608017519441162369
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004552176172176174194304256008243027200x7f34198662800x7f3416826540131072106190411915900817519441185889175194411460801751944177184117519441788713
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045821761721761741943042560012243054720x7f34198661000x7f341682658013107299059211076064017519441804253175194417718411751944241904317519442437827
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046121761721761741943042560012243082240x7f3417209f800x7f34168265c0655366437447213496817519442451636175194424190431751944306688417519443108909
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004642176172176174194304256008243109760x7f3417209e000x7f3416826600131072100087611208555217519443118919175194430668841751944372240517519443765152
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004672176172176174194304256008243132160x7f3417209c800x7f3416826640131072101065411322067217519443775082175194437224051751944480160717519444844345
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004702176172176174194304256008243159680x7f3417209b000x7f3416826680131072100567211252755217519444862274175194448016071751944586128917519445909907
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047321761721761741943042560012243187200x7f34172099800x7f34168266c0131072100368411248748017519445919697175194458610481751944695864917519447026289
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047621761721761741943042560012243214720x7f34172098000x7f3416826700655366439807222400017519447038338175194469586491751944808441017519448150690
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004792176172176174194304256008243242240x7f34172096800x7f3416826740131072101262211301992817519448161530175194480844101751944919017117519449255521
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004822176172176174194304256008243264640x7f34198665000x7f3416826780131072103441611593087217519449266681175194491901711751945113081417519451200512
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004852176172176174194304256008243292160x7f34198663800x7f34168267c0131072100521411277543217519451220441175194511308141751945304921617519453115742
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048821761721761741943042560012243319680x7f34198662000x7f341682680013107299401611153364017519453126602175194530492161751945501705917519455090162
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049121761721761741943042560012243347200x7f34198660800x7f3416826840655366427307207334417519455101171175194550170591751945699258217519457060401
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004942176172176174194304256008243374720x7f3417209f000x7f3416826880131072101261011346332817519457070931175194569925821751945892346417519458992241
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049721761721761741943042560082400x7f3417209d800x7f34168268c0131072101208611344834417519459003761175194589234641751946253850917519462609109