Files
rocm-systems/tests/workloads/Axes2/mi100/SQ_INST_LEVEL_LDS.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

40 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_LDSSQ_INST_LEVEL_LDSSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000906323906328335544322560083264640x00x7fb33220418000012076038461953928120760387088191041207603870914326212076038709253764
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00290632390632832768256002424124800x00x7fb33223510000012076038723915542120760387242211891207603872422758912076038724233333
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0049063239063284194304256002424129280x7fb43df669000x7fb33223514000012076038724298003120760387245125471207603872464870712076038724652732
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0069063239063284194304256003624136320x7fb43df668000x7fb33223518000012076038724722321120760387248904651207603872514022412076038725211991
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0089063239063284194304256002824140800x7fb43df667000x7fb3322351c000012076038725244151120760387254239031207603872568054212076038725748939
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00109063239063284194304256002424145280x7fb43df666000x7fb33223520000012076038725775579120760387259555801207603872609510012076038726099250
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00129063239063284194304256002424149760x7fb43df665000x7fb33223524000012076038726147991120760387263270981207603872646357812076038726467455
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00149063239063284194304256002424154240x7fb43df664000x7fb33223528000012076038726545049120760387267094971207603872684005612076038726844255
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00169063239063284194304256002824161280x7fb43df663000x7fb3322352c000012076038726892625120760387270646951207603872732085412076038727362939
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00189063239063284194304256002824168320x7fb43df66a000x7fb33223530000012076038727386463120760387275699721207603872782421112076038727865222
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00209063239063284194304256002424175360x7fb43df669000x7fb33223534000012076038727893335120760387280840501207603872821796912076038728222015
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00229063239063284194304256002424182400x7fb43df668000x7fb33223538000012076038728270526120760387284437281207603872858420812076038728588236
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00249063239063284194304256002424189440x7fb43df667000x7fb3322353c000012076038728648829120760387288123671207603872894276612076038728946522
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00269063239063284194304256002824199040x7fb43df666000x7fb33223540000012076038728995743120760387291691651207603872942548412076038729493268
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00289063239063284194304256002824206080x7fb43df665000x7fb33223544000012076038729519517120760387296971621207603872995476112076038730022592
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00309063239063284194304256002424213120x7fb43df664000x7fb33223548000012076038730047348120760387302282001207603873035635912076038730360239
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00329063239063284194304256002424220160x7fb43df663000x7fb3322354c000012076038730412056120760387305720381207603873070499712076038730708917
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00349063239063284194304256002424227200x7fb43df66a000x7fb33223550000012076038730768418120760387309309161207603873106259612076038731066552
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00369063239063284194304256002824236800x7fb43df669000x7fb33223554000012076038731114872120760387312885151207603873155075312076038731616524
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00389063239063284194304256002824243840x7fb43df668000x7fb33223558000012076038731640879120760387318243521207603873207955112076038732148583
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00409063239063284194304256002424250880x7fb43df667000x7fb3322355c000012076038732172617120760387323581091207603873248642912076038732490418
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00429063239063284194304256002424257920x7fb43df666000x7fb33223560000012076038732538167120760387327075481207603873284226712076038732846430
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00449063239063284194304256002424264960x7fb43df665000x7fb33223564000012076038732906451120760387330699461207603873320626512076038733210426
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00469063239063284194304256002824277120x7fb43df664000x7fb33223568000012076038733258866120760387334280241207603873368034312076038733746873
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00489063239063284194304256002824284160x7fb43df663000x7fb3322356c000012076038733774284120760387339499421207603873424242012076038734309990
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00509063239063284194304256002424291200x7fb43df66a000x7fb33223570000012076038734336960120760387345163391207603873464705812076038734651003
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00529063239063284194304256002424300800x7fb43df669000x7fb33223574000012076038734699854120760387348713771207603873504913712076038735053481
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00549063239063284194304256002424307840x7fb43df668000x7fb33223578000012076038735117490120760387352854551207603873541921512076038735423429
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00569063239063284194304256002824320000x7fb43df667000x7fb3322357c000012076038735470827120760387356379341207603873593489212076038736006012
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00589063239063284194304256002824329600x7fb43df666000x7fb33223580000012076038736032912120760387362163311207603873647041012076038736538541
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00609063239063284194304256002424339200x7fb43df665000x7fb33223584000012076038736565271120760387367387281207603873687648812076038736880337
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00629063239063284194304256002424348800x7fb43df664000x7fb33223588000012076038736929578120760387371004871207603873723104612076038737235126
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00649063239063284194304256002424358400x7fb43df663000x7fb3322358c000012076038737296009120760387374627251207603873759440412076038737598471
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00669063239063284194304256002824373120x7fb43df66a000x7fb33223590000012076038737647532120760387378115231207603873806880212076038738136170
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00689063239063284194304256002824382720x7fb43df669000x7fb33223594000012076038738159524120760387383464011207603873860031912076038738666907
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00709063239063284194304256002424392320x7fb43df668000x7fb33223598000012076038738692064120760387388697581207603873900783812076038739012048
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00729063239063284194304256002424401920x7fb43df667000x7fb3322359c000012076038739061390120760387392292761207603873936335612076038739367409
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00749063239063284194304256002424411520x7fb43df666000x7fb332235a0000012076038739428873120760387395931151207603873972415412076038739728249
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00769063239063284194304256002824426240x7fb43df665000x7fb332235a4000012076038739776940120760387399468731207603874020367212076038740274765
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00789063239063284194304256002824435840x7fb43df664000x7fb332235a8000012076038740298349120760387404791901207603874073774912076038740805301
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00809063239063284194304256002424445440x7fb43df663000x7fb332235ac000012076038740834966120760387410124681207603874114510712076038741149110
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00829063239063284194304256002424457600x7fb43df66a000x7fb332235b0000012076038741199514120760387413676661207603874150270612076038741506714
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00849063239063284194304256002424467200x7fb43df669000x7fb332235b4000012076038741567447120760387417276641207603874185854412076038741862606
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00869063239063284194304256002824484480x7fb43df668000x7fb332235b8000012076038741914452120760387420807831207603874234718112076038742414121
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00889063239063284194304256002824494080x7fb43df667000x7fb332235bc000012076038742438296120760387426174201207603874287309912076038742914110
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00909063239063284194304256002424503680x7fb43df666000x7fb332235c0000012076038742940309120760387431214181207603874325581712076038743259732
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00929063239063284194304256002424515840x7fb43df665000x7fb332235c4000012076038743309204120760387434732561207603874361725512076038743621264
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00949063239063284194304256002424525440x7fb43df664000x7fb332235c8000012076038743682248120760387438430141207603874397581412076038743979801
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00969063239063284194304256002824542720x7fb43df663000x7fb332235cc000012076038744028261120760387442084531207603874447789112076038744546474
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00989063239063284194304256002824554880x7fb43df66a000x7fb332235d0000012076038744569917120760387447484501207603874501180912076038745079174
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001009063239063284194304256002424567040x7fb43df669000x7fb332235d4000012076038745109200120760387452903671207603874542140712076038745425317
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001029063239063284194304256002424581760x7fb43df668000x7fb332235d8000012076038745473707120760387456414061207603874578316512076038745787099
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001049063239063284194304256002424593920x7fb43df667000x7fb332235dc000012076038745850748120760387460130841207603874614716312076038746151477
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001069063239063284194304256002824613760x7fb43df666000x7fb332235e0000012076038746201970120760387463727621207603874663644112076038746679277
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001089063239063284194304256002824625920x7fb43df665000x7fb332235e4000012076038746712309120760387468742001207603874712971812076038747197541
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001109063239063284194304256002424638080x7fb43df664000x7fb332235e8000012076038747231043120760387473959571207603874752955712076038747533575
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001129063239063284194304256002424652800x7fb43df663000x7fb332235ec000012076038747584119120760387477497151207603874789227512076038747896580
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001149063239063284194304256002424664960x7fb43df66a000x7fb332235f0000012076038747958304120760387481252341207603874826315312076038748267359
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001169063239063284194304256002824684800x7fb43df669000x7fb332235f4000012076038748317632120760387484853921207603874874059112076038748807463
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001189063239063284194304256002824696960x7fb43df668000x7fb332235f8000012076038748830876120760387490069891207603874926298812076038749331507
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001209063239063284194304256002424709120x7fb43df667000x7fb332235fc000012076038749359258120760387495397871207603874971242612076038749716492
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001229063239063284194304256002424723840x7fb43df666000x7fb33223600000012076038749765834120760387499274651207603875006906412076038750073135
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001249063239063284194304256002424736000x7fb43df665000x7fb33223604000012076038750135952120760387502977031207603875043082312076038750435007
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001269063239063284194304256002824758400x7fb43df664000x7fb33223608000012076038750483818120760387506500221207603875092026012076038750963179
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001289063239063284194304256002824770560x7fb43df663000x7fb3322360c000012076038750986362120760387511706591207603875143001812076038751471614
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001309063239063284194304256002424782720x7fb43df66a000x7fb33223610000012076038751498053120760387516789771207603875181449612076038751818448
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001329063239063284194304256002424800000x7fb43df669000x7fb33223614000012076038751867950120760387520493751207603875219433412076038752198435
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001349063239063284194304256002424812160x7fb43df668000x7fb33223618000012076038752260330120760387524258531207603875255625212076038752560658
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001369063239063284194304256002824834560x7fb43df667000x7fb3322361c000012076038752608066120760387527749711207603875304329012076038753093288
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001389063239063284194304256002824849280x7fb43df666000x7fb33223620000012076038753116411120760387532965691207603875355544812076038753603135
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001409063239063284194304256002424864000x7fb43df665000x7fb33223624000012076038753629695120760387538109661207603875394520612076038753949228
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001429063239063284194304256002424881280x7fb43df664000x7fb33223628000012076038753997929120760387541704851207603875432008412076038754324536
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001449063239063284194304256002424896000x7fb43df663000x7fb3322362c000012076038754405797120760387545674431207603875470664212076038754710994
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001469063239063284194304256002824920960x7fb43df66a000x7fb33223630000012076038754760396120760387549277611207603875519528012076038755245037
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001489063239063284194304256002824935680x7fb43df669000x7fb33223634000012076038755271315120760387554527181207603875574199712076038755791622
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001509063239063284194304256002424950400x7fb43df668000x7fb33223638000012076038755816709120760387559999161207603875614071512076038756144699
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001529063239063284194304256002424967680x7fb43df667000x7fb3322363c000012076038756194130120760387563627941207603875652023312076038756524424
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001549063239063284194304256002424982400x7fb43df666000x7fb33223640000012076038756585037120760387567450321207603875687367212076038756877881
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015690632390632841943042560028241007360x7fb43df665000x7fb33223644000012076038756925960120760387570971911207603875736918912076038757419969
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015890632390632841943042560028241022080x7fb43df664000x7fb33223648000012076038757443452120760387576216681207603875787990712076038757929105
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016090632390632841943042560024241036800x7fb43df663000x7fb3322364c000012076038757954742120760387581330261207603875826166512076038758265961
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016290632390632841943042560024241056640x7fb43df66a000x7fb33223650000012076038758315122120760387584805441207603875864710312076038758651177
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016490632390632841943042560024241071360x7fb43df669000x7fb33223654000012076038758712771120760387588701421207603875900390112076038759008471
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016690632390632841943042560028241098880x7fb43df668000x7fb33223658000012076038759056420120760387592455001207603875951173912076038759565245
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016890632390632841943042560028241113600x7fb43df667000x7fb3322365c000012076038759594380120760387597750981207603876003013612076038760078089
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017090632390632841943042560024241128320x7fb43df666000x7fb33223660000012076038760100951120760387602990951207603876043861512076038760442716
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017290632390632841943042560024241148160x7fb43df665000x7fb33223664000012076038760490625120760387606552531207603876082917312076038760833603
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017490632390632841943042560024241162880x7fb43df664000x7fb33223668000012076038760894295120760387610744511207603876121365112076038761217777
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017690632390632841943042560028241190400x7fb43df663000x7fb3322366c000012076038761265686120760387614341301207603876169380812076038761741610
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017890632390632841943042560028241207680x7fb43df66a000x7fb33223670000012076038761768079120760387619410071207603876219556612076038762244986
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018090632390632841943042560024241224960x7fb43df669000x7fb33223674000012076038762272677120760387624467651207603876258500412076038762589155
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018290632390632841943042560024241247360x7fb43df668000x7fb33223678000012076038762637465120760387628022831207603876298580212076038762992385
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018490632390632841943042560024241264640x7fb43df667000x7fb3322367c000012076038763052386120760387632107611207603876335204112076038763356101
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018690632390632841943042560020241279360x7fb43df666000x7fb33223680000012076038763405783120760387635672391207603876383475812076038763882208
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018890632390632841943042560028241296640x7fb43df665000x7fb33223684000012076038763905231120760387640939571207603876435571612076038764406212
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019090632390632841943042560024241313920x7fb43df664000x7fb33223688000012076038764430748120760387646091541207603876474483412076038764748869
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019290632390632841943042560024241336320x7fb43df663000x7fb3322368c000012076038764798461120760387649582731207603876515091212076038765202192
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019490632390632841943042560024241353600x7fb43df66a000x7fb33223690000012076038765242476120760387654057911207603876554595012076038765550058
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019690632390632841943042560020241368320x7fb43df669000x7fb33223694000012076038765598217120760387657707491207603876608546712076038766131849
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019890632390632841943042560028241385600x7fb43df668000x7fb33223698000012076038766159921120760387663371461207603876660034512076038766647467
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020090632390632841943042560024241402880x7fb43df667000x7fb3322369c000012076038766676511120760387668537841207603876698754312076038766991597
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020290632390632841943042560024241427840x7fb43df666000x7fb332236a0000012076038767043063120760387672069021207603876741746112076038767464967
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020490632390632841943042560024241447680x7fb43df665000x7fb332236a4000012076038767503508120760387676645001207603876780305912076038767807163
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020690632390632841943042560020241457280x7fb43df664000x7fb332236a8000012076038767856564120760387680323381207603876834113712076038768389335
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020890632390632841943042560028241477120x7fb43df663000x7fb332236ac000012076038768413570120760387685924951207603876885521412076038768902188
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021090632390632841943042560024241496960x7fb43df66a000x7fb332236b0000012076038768929468120760387691046531207603876924737212076038769251677
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021290632390632841943042560024241521920x7fb43df669000x7fb332236b4000012076038769300819120760387694632111207603876969201012076038769738201
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021490632390632841943042560024241541760x7fb43df668000x7fb332236b8000012076038769776372120760387699385691207603877007792812076038770081940
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021690632390632841943042560020241556480x7fb43df667000x7fb332236bc000012076038770130440120760387703006471207603877063056612076038770676896
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021890632390632841943042560028241576320x7fb43df666000x7fb332236c0000012076038770701301120760387708766441207603877113696312076038771185792
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022090632390632841943042560024241596160x7fb43df665000x7fb332236c4000012076038771209356120760387713868821207603877152320112076038771527136
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022290632390632841943042560024241623680x7fb43df664000x7fb332236c8000012076038771575796120760387717426401207603877198855912076038772040290
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022490632390632841943042560024241646080x7fb43df663000x7fb332236cc000012076038772077048120760387722498371207603877238951612076038772392775
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022690632390632841943042560020241663360x7fb43df66a000x7fb332236d0000012076038772442637120760387726104751207603877298775412076038773035269
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022890632390632841943042560028241685760x7fb43df669000x7fb332236d4000012076038773061097120760387732378331207603877350407212076038773550857
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023090632390632841943042560024241708160x7fb43df668000x7fb332236d8000012076038773573810120760387737546311207603877389367112076038773896980
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023290632390632841943042560024241740800x7fb43df667000x7fb332236dc000012076038773945621120760387741130301207603877439366912076038774442705
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023490632390632841943042560024241765760x7fb43df666000x7fb332236e0000012076038774481867120760387746429481207603877478038712076038774783849
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023690632390632841943042560020241777920x7fb43df665000x7fb332236e4000012076038774834032120760387749927071207603877541798512076038775465415
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023890632390632841943042560028241802880x7fb43df664000x7fb332236e8000012076038775489280120760387756683841207603877593318312076038775979431
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024090632390632841943042560024241827840x7fb43df663000x7fb332236ec000012076038776010909120760387761930221207603877633366212076038776337316
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024290632390632841943042560024241863040x7fb43df66a000x7fb332236f0000012076038776386447120760387765552611207603877687110012076038776917824
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024490632390632841943042560024241893120x7fb43df669000x7fb332236f4000012076038776953340120760387771310991207603877728373812076038777287081
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024690632390632841943042560020241907840x7fb43df668000x7fb332236f8000012076038777337414120760387775002171207603877801669512076038778064546
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024890632390632841943042560028241937920x7fb43df667000x7fb332236fc000012076038778091816120760387782683751207603877856901312076038778590132
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025090632390632841943042560024241968000x7fb43df666000x7fb33223700000012076038778639815120760387788010131207603877895557212076038778958767
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025290632390632841943042560024242010880x7fb43df665000x7fb33223704000012076038779011355120760387791826111207603877956965012076038779617862
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025490632390632841943042560024242046080x7fb43df664000x7fb33223708000012076038779657696120760387798221291207603877999828812076038780005012
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025690632390632841943042560020242060800x7fb43df663000x7fb3322370c000012076038780050446120760387802203671207603878083092512076038780877463
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025890632390632841943042560028242096000x7fb43df66a000x7fb33223710000012076038780902991120760387810803641207603878140788312076038781457010
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026090632390632841943042560024242131200x7fb43df669000x7fb33223714000012076038781480714120760387816597221207603878183828112076038781841595
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026290632390632841943042560024242181760x7fb43df668000x7fb33223718000012076038781891448120760387820627611207603878251843912076038782567194
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026490632390632841943042560024242222080x7fb43df667000x7fb3322371c000012076038782606957120760387827685181207603878296995712076038783018342
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026690632390632841943042560020242239360x7fb43df666000x7fb33223720000012076038783046244120760387832240361207603878392771412076038783948431
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026890632390632841943042560028242279680x7fb43df665000x7fb33223724000012076038783996810120760387841641931207603878453843112076038784588280
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027090632390632841943042560024242320000x7fb43df664000x7fb33223728000012076038784615851120760387847888301207603878499267012076038785043365
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027290632390632841943042560024242378240x7fb43df663000x7fb3322372c000012076038785071468120760387852430691207603878576930712076038785816282
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027490632390632841943042560024242423680x7fb43df66a000x7fb33223730000012076038785855445120760387860201861207603878624498512076038786293519
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027690632390632841943042560020242435840x7fb43df669000x7fb33223734000012076038786319106120760387864995441207603878729954112076038787349231
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027890632390632841943042560028242481280x7fb43df668000x7fb33223738000012076038787376021120760387875520201207603878797377912076038788023754
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028090632390632841943042560024242526720x7fb43df667000x7fb3322373c000012076038788051556120760387882380981207603878846577712076038788513324
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028290632390632841943042560024242592640x7fb43df666000x7fb33223740000012076038788540445120760387887120161207603878930993412076038789358695
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028490632390632841943042560024242648320x7fb43df665000x7fb33223744000012076038789399040120760387895611331207603878983009212076038789876798
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028690632390632841943042560020242663040x7fb43df664000x7fb33223748000012076038789902686120760387900910511207603879107600712076038791145055
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028890632390632841943042560028242718720x7fb43df663000x7fb3322374c000012076038791176484120760387913488061207603879188192412076038791948248
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029090632390632841943042560024242774400x7fb43df66a000x7fb33223750000012076038791970299120760387921603231207603879243296212076038792501165
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029290632390632841943042560012242799360x7fb43df669000x7fb33223754000012076038792532093120760387927105611207603879344911912076038793516823
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029490632390632841943042560024242865280x7fb43df668000x7fb33223758000012076038793560073120760387937220781207603879404047612076038794106890
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029690632390632841943042560020242880000x7fb43df667000x7fb3322375c000012076038794136364120760387943078351207603879548047112076038795548378
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029890632390632841943042560032242945920x7fb43df666000x7fb33223760000012076038795578965120760387957628701207603879637310812076038796440557
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030090632390632841943042560024243011840x7fb43df665000x7fb33223764000012076038796471354120760387966503871207603879697006612076038797036845
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030290632390632841943042560012243049600x7fb43df664000x7fb33223768000012076038797068053120760387972470251207603879812558112076038798192382
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030490632390632841943042560024243136000x7fb43df663000x7fb3322376c000012076038798231094120760387983918201207603879880477912076038798871685
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030690632390632841943042560020243148160x7fb43df66a000x7fb33223770000012076038798900689120760387990876581207603880063757212076038800706465
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030890632390632841943042560020243175680x7fb43df669000x7fb33223774000012076038800736941120760388009164511207603880171276812076038801780982
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031090632390632841943042560012243203200x7fb43df668000x7fb33223778000012076038801807571120760388019836471207603880239884512076038802465774
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031290632390632841943042560012243240960x7fb43df667000x7fb3322377c000012076038802491692120760388026660451207603880382508012076038803892005
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031490632390632841943042560012243288960x7fb43df666000x7fb33223780000012076038803933171120760388041068391207603880489259612076038804961713
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031690632390632841943042560020243301120x7fb43df665000x7fb33223784000012076038804992400120760388051722751207603880822378412076038808291852
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031890632390632841943042560020243328640x7fb43df664000x7fb33223788000012076038808319844120760388085033031207603881004553712076038810113728
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032090632390632841943042560012243356160x7fb43df663000x7fb3322378c000012076038810143132120760388103264961207603881111625312076038811184107
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032290632390632841943042560012243393920x7fb43df66a000x7fb33223790000012076038811215245120760388113933721207603881367560412076038813743563
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032490632390632841943042560012243441920x7fb43df669000x7fb33223794000012076038813787886120760388139512831207603881548679712076038815555481
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032690632390632841943042560020243454080x7fb43df668000x7fb33223798000012076038815587270120760388157643961207603882182261412076038821890334
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032890632390632841943042560020243481600x7fb43df667000x7fb3322379c000012076038821920820120760388221040531207603882514772212076038825220102
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033090632390632841943042560012243509120x7fb43df666000x7fb332237a0000012076038825248174120760388254309211207603882697123512076038827039293
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332906323906328419430425600122400x7fb43df665000x7fb332237a4000012076038827069920120760388272485141207603883177569712076038831846747