Files
rocm-systems/tests/workloads/kernels/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.kd000187798187798335544322560043241600x00x7fdf25a042803670016289815632474979217017871486203170045636195031701801705040917018017164238
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00218779818779832768256001224138880x00x7fdf25a23f805121003901123435217018022229652170180170504091701802236656117018022371497
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051877981877984194304256001224143360x7fdf28a163800x7fdf25a23fc0655366467947235919217018022406216170180223665611701802273664117018022739477
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081877981877984194304256001624150400x7fdf28a162000x7fdf25a24000655366627787411254417018022777586170180227366411701802314608017018023148515
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111877981877984194304256001624154880x7fdf28a160800x7fdf25a24040655366597067404558417018023180614170180231460801701802354800017018023550424
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141877981877984194304256001224159360x7fdf2627df000x7fdf25a24080655366613167408080017018023581843170180235480001701802385376017018023856145
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171877981877984194304256001224163840x7fdf2627dd800x7fdf25a240c0655366288647039259217018023887274170180238537601701802416095917018024163346
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201877981877984194304256001224170880x7fdf2627dc000x7fdf25a241001310726575907366208017018024206585170180241609591701802446639917018024468647
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231877981877984194304256001624177920x7fdf2627da800x7fdf25a241401310726950627788459217018024499606170180244663991701802486159817018024863866
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261877981877984194304256001624184960x7fdf2627d9000x7fdf25a24180655366611767400146417018024893295170180248615981701802525343817018025255875
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291877981877984194304256001624192000x7fdf2627d7800x7fdf25a241c01310726911407752304817018025285794170180252534381701802557055817018025573136
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321877981877984194304256001624199040x7fdf2627d6000x7fdf25a242001310726969627821211217018025604545170180255705581701802587551717018025877877
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351877981877984194304256001224206080x7fdf28a164800x7fdf25a242401310727391268268766417018025916796170180258755171701802619599717018026198498
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381877981877984194304256001624213120x7fdf28a163000x7fdf25a242801310727201468068022417018026230077170180261959971701802659631617018026598796
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411877981877984194304256001624220160x7fdf28a161800x7fdf25a242c0655366646667450704817018026631145170180265963161701802699391617018026996515
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441877981877984194304256001624227200x7fdf28a160000x7fdf25a243001310727331048207177617018027027144170180269939161701802730079617018027303116
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471877981877984194304256001224234240x7fdf2627de800x7fdf25a243401310726969527818965617018027333625170180273007961701802760287517018027605197
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501877981877984194304256001224241280x7fdf2627dd000x7fdf25a243801310726957687789480817018027644046170180276028751701802790751517018027909909
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531877981877984194304256001624248320x7fdf2627db800x7fdf25a243c01310726994827833350417018027940558170180279075151701802830223417018028304477
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561877981877984194304256001624255360x7fdf2627da000x7fdf25a24400655366298007071906417018028335506170180283022341701802870591417018028708276
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591877981877984194304256001224262400x7fdf2627d8800x7fdf25a244401310726965847791725617018028737855170180287059141701802901343417018029015657
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621877981877984194304256001224269440x7fdf2627d7000x7fdf25a244801310726998827841654417018029046716170180290134341701802932767317018029329948
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651877981877984194304256001224276480x7fdf28a165800x7fdf25a244c01310726649107453300817018029368547170180293276731701802963327317018029635619
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681877981877984194304256001624286080x7fdf28a164000x7fdf25a245001310727220328098380017018029666358170180296332731701803002655217018030028858
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711877981877984194304256001624293120x7fdf28a162800x7fdf25a24540655366868847683205617018030060287170180300265521701803045295217018030455186
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741877981877984194304256001224300160x7fdf28a161000x7fdf25a245801310726686427489332017018030486785170180304529521701803074991217018030751727
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077187798187798419430425600824309760x7fdf2627df800x7fdf25a245c01310726711947499393617018030783096170180307499121701803102751117018031029329
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801877981877984194304256001224316800x7fdf2627de000x7fdf25a246001310726924407757225617018031067018170180310275111701803130671117018031308781
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831877981877984194304256001624326400x7fdf2627dc800x7fdf25a246401310726639987437493617018031340020170180313067111701803167087017018031672510
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861877981877984194304256001224336000x7fdf2627db000x7fdf25a24680655366526787299989617018031702620170180316708701701803204047017018032042320
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891877981877984194304256001224345600x7fdf2627d9800x7fdf25a246c01310726891147709066417018032073179170180320404701701803231903017018032320942
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092187798187798419430425600824355200x7fdf2627d8000x7fdf25a247001310727236428114010417018032352571170180323190301701803259790917018032599894
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951877981877984194304256001224362240x7fdf2627d6800x7fdf25a247401310726869767685784817018032637243170180325979091701803287598917018032877696
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981877981877984194304256001224371840x7fdf28a165000x7fdf25a247801310726597827393941617018032907415170180328759891701803323838917018033240225
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011877981877984194304256001224381440x7fdf28a163800x7fdf25a247c0655366609847413886417018033271494170180332383891701803360174817018033603465
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041877981877984194304256001224391040x7fdf28a162000x7fdf25a248001310726915547737934417018033634234170180336017481701803387902817018033880707
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107187798187798419430425600824403200x7fdf28a160800x7fdf25a248401310727009167834208817018033912176170180338790281701803415662817018034158649
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101877981877984194304256001224412800x7fdf2627df000x7fdf25a248801310727016607847403217018034197758170180341566281701803445038717018034452230
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131877981877984194304256001224422400x7fdf2627dd800x7fdf25a248c01310726984747830319217018034481809170180344503871701803481870717018034820670
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161877981877984194304256001224432000x7fdf2627dc000x7fdf25a24900655366287347045956817018034851609170180348187071701803518462617018035186349
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119187798187798419430425600824441600x7fdf2627da800x7fdf25a249401310726922627750324817018035217188170180351846261701803546366617018035465801
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221877981877984194304256001224453760x7fdf2627d9000x7fdf25a249801310727233488102582417018035496160170180354636661701803574190617018035743733
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251877981877984194304256001224463360x7fdf2627d7800x7fdf25a249c01310726945947780329617018035781552170180357419061701803601918517018036021055
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281877981877984194304256001224475520x7fdf2627d6000x7fdf25a24a001310726995807839210417018036051884170180360191851701803638270517018036384635
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311877981877984194304256001224485120x7fdf28a164800x7fdf25a24a40655366626287422744017018036415664170180363827051701803674622417018036748154
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134187798187798419430425600824494720x7fdf28a163000x7fdf25a24a801310726641427431845617018036779184170180367462241701803702398417018037025807
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371877981877984194304256001224506880x7fdf28a161800x7fdf25a24ac01310726642067447463217018037057096170180370239841701803730654417018037308268
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401877981877984194304256001224516480x7fdf28a160000x7fdf25a24b001310726704367491252817018037346927170180373065441701803759246317018037594220
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431877981877984194304256001224528640x7fdf2627de800x7fdf25a24b401310726956867783197617018037624839170180375924631701803796062317018037962360
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461877981877984194304256001224540800x7fdf2627dd000x7fdf25a24b80655366576587376584817018037992769170180379606231701803833646317018038338419
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149187798187798419430425600824552960x7fdf2627db800x7fdf25a24bc01310727511888434842417018038369518170180383364631701803862110217018038622961
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521877981877984194304256001224567680x7fdf2627da000x7fdf25a24c001310726951747786339217018038653670170180386211021701803890542217018038907123
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551877981877984194304256001224577280x7fdf2627d8800x7fdf25a24c401310726977207818347217018038945671170180389054221701803919102217018039192784
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581877981877984194304256001224589440x7fdf2627d7000x7fdf25a24c801310726589047381130417018039224183170180391910221701803955742117018039559154
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611877981877984194304256001224601600x7fdf28a165800x7fdf25a24cc0655366516147312116017018039590123170180395574211701803992334117018039925113
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164187798187798419430425600824613760x7fdf28a164000x7fdf25a24d001310727068267918257617018039956952170180399233411701804020238017018040204235
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671877981877984194304256001224628480x7fdf28a162800x7fdf25a24d401310726918347748851217018040235444170180402023801701804049134017018040493207
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701877981877984194304256001224638080x7fdf28a161000x7fdf25a24d801310726926327756453617018040531936170180404913401701804077774017018040779499
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731877981877984194304256001224650240x7fdf2627df800x7fdf25a24dc01310726583507371261617018040810248170180407777401701804114253917018041144298
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761877981877984194304256001224662400x7fdf2627de000x7fdf25a24e00655366155766904502417018041175167170180411425391701804150829917018041510168
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179187798187798419430425600824674560x7fdf2627dc800x7fdf25a24e401310727017487866372017018041541067170180415082991701804179293917018041794690
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821877981877984194304256001224689280x7fdf2627db000x7fdf25a24e801310727045967894753617018041825839170180417929391701804208109817018042086961
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851877981877984194304256001224701440x7fdf2627d9800x7fdf25a24ec01310726590747366821617018042121840170180420810981701804236669817018042368543
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881877981877984194304256001224716160x7fdf2627d8000x7fdf25a24f001310726935207753050417018042399122170180423666981701804274045717018042742183
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911877981877984194304256001224728320x7fdf2627d6800x7fdf25a24f40655366568767363329617018042772792170180427404571701804310941717018043111162
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194187798187798419430425600824740480x7fdf28a165000x7fdf25a24f801310726544947334690417018043140761170180431094171701804339133717018043393314
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971877981877984194304256001224757760x7fdf28a163800x7fdf25a24fc01310726706947506646417018043423433170180433913371701804368285617018043684766
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001877981877984194304256001224769920x7fdf28a162000x7fdf25a250001310727179168039940017018043722884170180436828561701804397213617018043973847
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031877981877984194304256001224784640x7fdf28a160800x7fdf25a250401310727363688251232017018044005626170180439721361701804433981617018044341707
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061877981877984194304256001224799360x7fdf2627df000x7fdf25a25080655366762367575368017018044372836170180443398161701804470797517018044709666
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209187798187798419430425600824814080x7fdf2627dd800x7fdf25a250c01310726914747752087217018044740225170180447079751701804498797517018044989798
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121877981877984194304256001224831360x7fdf2627dc000x7fdf25a251001310726932367771420817018045020507170180449879751701804528509417018045286980
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151877981877984194304256001224843520x7fdf2627da800x7fdf25a251401310727318868205372817018045335558170180452850941701804556765417018045569381
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181877981877984194304256001224858240x7fdf2627d9000x7fdf25a251801310727052887893327217018045607760170180455676541701804593789417018045939591
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211877981877984194304256001224872960x7fdf2627d7800x7fdf25a251c0655366617767412290417018045970910170180459378941701804631629317018046318310
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241877981877984194304256001224887680x7fdf2627d6000x7fdf25a252001310726934247770209617018046348959170180463162931701804659917317018046600902
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271877981877984194304256001224907520x7fdf28a164800x7fdf25a252401310726801447622347217018046631721170180465991731701804691005317018046911723
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301877981877984194304256001224919680x7fdf28a163000x7fdf25a252801310726912467747259217018046951042170180469100531701804718941217018047191155
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331877981877984194304256001224934400x7fdf28a161800x7fdf25a252c01310726889267717408017018047222654170180471894121701804755741217018047559144
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361877981877984194304256001224949120x7fdf28a160000x7fdf25a25300655366649767446812017018047591103170180475574121701804792221117018047923974
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391877981877984194304256001224963840x7fdf2627de800x7fdf25a253401310726976747820754417018047955283170180479222111701804820189117018048203706
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421877981877984194304256001224983680x7fdf2627dd000x7fdf25a253801310726965627796332017018048234265170180482018911701804851037117018048512337
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451877981877984194304256001224995840x7fdf2627db800x7fdf25a253c01310726958347792316017018048550496170180485103711701804879757017018048799258
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024818779818779841943042560012241013120x7fdf2627da000x7fdf25a254001310726525127320667217018048829517170180487975701701804916829017018049169998
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025118779818779841943042560012241027840x7fdf2627d8800x7fdf25a25440655366552087335849617018049200507170180491682901701804953916917018049541137
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025418779818779841943042560012241042560x7fdf2627d7000x7fdf25a254801310726538927329853617018049571706170180495391691701804981932917018049821119
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025718779818779841943042560012241062400x7fdf28a165800x7fdf25a254c01310726618487420256017018049851838170180498193291701805013564917018050137700
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026018779818779841943042560012241077120x7fdf28a164000x7fdf25a255001310726708807512400817018050177319170180501356491701805042044817018050422162
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026318779818779841943042560016241094400x7fdf28a162800x7fdf25a255401310726856447682124817018050454511170180504204481701805078524817018050787031
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026618779818779841943042560016241111680x7fdf28a161000x7fdf25a25580655366583727377613617018050818310170180507852481701805115228817018051154101
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691877981877984194304256008241128960x7fdf2627df800x7fdf25a255c01310726990387820463217018051185730170180511522881701805143596717018051437732
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027218779818779841943042560012241151360x7fdf2627de000x7fdf25a256001310726942267784678417018051469002170180514359671701805176300717018051764823
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027518779818779841943042560012241166080x7fdf2627dc800x7fdf25a256401310726975287807248017018051803102170180517630071701805204492617018052046585
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027818779818779841943042560016241183360x7fdf2627db000x7fdf25a256801310726924747749040817018052076874170180520449261701805241548617018052417314
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028118779818779841943042560016241200640x7fdf2627d9800x7fdf25a256c0655366629987443172017018052447683170180524154861701805278412617018052785904
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028418779818779841943042560012241217920x7fdf2627d8000x7fdf25a257001310726960267797512817018052816763170180527841261701805306636517018053068126
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028718779818779841943042560012241240320x7fdf2627d6800x7fdf25a257401310727099587955340017018053099035170180530663651701805339724517018053398986
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029018779818779841943042560012241255040x7fdf28a165000x7fdf25a257801310726946627790658417018053437385170180533972451701805368156517018053683308
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029318779818779841943042560012241274880x7fdf28a163800x7fdf25a257c01310726909187745447217018053713877170180536815651701805404604417018054047758
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029618779818779841943042560012241292160x7fdf28a162000x7fdf25a25800655366585167384792017018054086816170180540460441701805442620417018054428147
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029918779818779841943042560012241309440x7fdf28a160800x7fdf25a258401310726600047385903217018054459046170180544262041701805473148317018054733288
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030218779818779841943042560012241334400x7fdf2627df000x7fdf25a258801310726606027406648017018054764607170180547314831701805507212317018055073848
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030518779818779841943042560012241349120x7fdf2627dd800x7fdf25a258c0131072102887611532565617018055112687170180550721231701805536140317018055363170
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030818779818779841943042560012241368960x7fdf2627dc000x7fdf25a259001310726586767380181617018055394139170180553614031701805572924217018055731049
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031118779818779841943042560012241388800x7fdf2627da800x7fdf25a25940655366545987331137617018055761748170180557292421701805609420217018056096009
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031418779818779841943042560012241408640x7fdf2627d9000x7fdf25a259801310727368728256528017018056126798170180560942021701805639116117018056392980
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031718779818779841943042560012241436160x7fdf2627d7800x7fdf25a259c01310726940247785879217018056423779170180563911611701805674972117018056751530
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032018779818779841943042560012241453440x7fdf2627d6000x7fdf25a25a00131072101855211395031217018056790889170180567497211701805703772117018057039442
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032318779818779841943042560012241475840x7fdf28a164800x7fdf25a25a401310726940967763772817018057070331170180570377211701805740620017018057407951
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032618779818779841943042560012241495680x7fdf28a163000x7fdf25a25a80655366572247369575217018057438620170180574062001701805777308017018057774911
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032918779818779841943042560012241515520x7fdf28a161800x7fdf25a25ac01310726636087426632017018057805350170180577730801701805806891917018058070632
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033218779818779841943042560012241543040x7fdf28a160000x7fdf25a25b001310726495227270436817018058102331170180580689191701805844875917018058450661
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033518779818779841943042560012241562880x7fdf2627de800x7fdf25a25b4013107299052011093242417018058489090170180584487591701805874587917018058747683
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033818779818779841943042560012241587840x7fdf2627dd000x7fdf25a25b801310726879647703315217018058778222170180587458791701805911611817018059117902
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034118779818779841943042560012241610240x7fdf2627db800x7fdf25a25bc0655366509067294570417018059148801170180591161181701805948603817018059487751
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034418779818779841943042560012241632640x7fdf2627da000x7fdf25a25c001310726643127438917617018059518450170180594860381701805979563717018059797442
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034718779818779841943042560012241665280x7fdf2627d8800x7fdf25a25c401310726667207468240817018059828572170180597956371701806019083717018060212590
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035018779818779841943042560012241685120x7fdf2627d7000x7fdf25a25c80131072103492211601058417018060231240170180601908371701806049643717018060498192
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035318779818779841943042560012241712640x7fdf28a165800x7fdf25a25cc01310726677187486416817018060528981170180604964371701806086635617018060868162
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035618779818779841943042560012241737600x7fdf28a164000x7fdf25a25d00655366591807394361617018060900181170180608663561701806125019617018061252070
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035918779818779841943042560012241762560x7fdf28a162800x7fdf25a25d401310726844007670817617018061283340170180612501961701806157771517018061579521
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036218779818779841943042560012241797760x7fdf28a161000x7fdf25a25d801310726628087425024017018061611200170180615777151701806199755517018062015378
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036518779818779841943042560012241822720x7fdf2627df800x7fdf25a25dc013107299255211119984817018062038558170180619975551701806231963417018062321760
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036818779818779841943042560012241855360x7fdf2627de000x7fdf25a25e001310727153568009911217018062353179170180623196341701806269867417018062744267
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037118779818779841943042560012241885440x7fdf2627dc800x7fdf25a25e40655367013387862855217018062755057170180626986741701806311355317018063158866
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037418779818779841943042560012241915520x7fdf2627db000x7fdf25a25e801310726588847392623217018063169655170180631135531701806349243317018063494096
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037718779818779841943042560012241958400x7fdf2627d9800x7fdf25a25ec01310726853567674764017018063524815170180634924331701806396219217018064004421
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038018779818779841943042560012241985920x7fdf2627d8000x7fdf25a25f00131072103050611541965617018064023631170180639621921701806432507217018064326822
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038318779818779841943042560012242023680x7fdf2627d6800x7fdf25a25f4013107298372811007548017018064357741170180643250721701806472091217018064763760
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038618779818779841943042560012242058880x7fdf28a165000x7fdf25a25f80655366548967338510417018064774629170180647209121701806514971117018065192197
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038918779818779841943042560012242094080x7fdf28a163800x7fdf25a25fc01310726541467324527217018065203047170180651497111701806555067117018065552487
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039218779818779841943042560012242144640x7fdf28a162000x7fdf25a260001310726910587747492817018065583816170180655506711701806607275017018066144310
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039518779818779841943042560012242177280x7fdf28a160800x7fdf25a26040131072102874211524168817018066164409170180660727501701806657338917018066575888
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039818779818779841943042560012242220160x7fdf2627df000x7fdf25a26080131072103489211589848817018066607437170180665733891701806701946917018067052164
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040118779818779841943042560012242260480x7fdf2627dd800x7fdf25a260c0655366623887409454417018067064094170180670194691701806748586817018067518261
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040418779818779841943042560012242300800x7fdf2627dc000x7fdf25a261001310726590567383188817018067530740170180674858681701806793050817018067955128
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040718779818779841943042560012242359040x7fdf2627da800x7fdf25a261401310726852167670027217018067967548170180679305081701806854234717018068594280
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041018779818779841943042560012242394240x7fdf2627d9000x7fdf25a26180131072102058811477519217018068614419170180685423471701806903386717018069036347
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041318779818779841943042560012242442240x7fdf2627d7800x7fdf25a261c0131072100135811208980017018069066786170180690338671701806951930617018069571052
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041618779818779841943042560012242487680x7fdf2627d6000x7fdf25a26200655366604907394605617018069582981170180695193061701807007114517018070132276
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041918779818779841943042560012242533120x7fdf28a164800x7fdf25a262401310726657607468552817018070145015170180700711451701807062890517018070708509
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221877981877984194304256008242555520x7fdf28a163000x7fdf25a26280131072105241011805977617018070719789170180706289051701807141626417018071462127
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042518779818779841943042560012242598400x7fdf28a161800x7fdf25a262c0131072101134811348016017018071481937170180714162641701807189658317018071942854
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042818779818779841943042560012242656640x7fdf28a160000x7fdf25a2630013107298343411033784817018071954963170180718965831701807244458317018072490198
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043118779818779841943042560012242712320x7fdf2627de800x7fdf25a26340655366630747437991217018072501958170180724445831701807299498217018073068841
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341877981877984194304256008242732160x7fdf2627dd000x7fdf25a2638013107298674411084563217018073081021170180729949821701807362330117018073670264
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371877981877984194304256008242757120x7fdf2627db800x7fdf25a263c0131072103123211551719217018073682394170180736233011701807443322017018074509780
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044018779818779841943042560012242807680x7fdf2627da000x7fdf25a2640013107299235211110176017018074530929170180744332201701807506393917018075154281
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044318779818779841943042560012242876160x7fdf2627d8800x7fdf25a26440131072102513011468057617018075166941170180750639391701807576585917018075824602
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044618779818779841943042560012242942080x7fdf2627d7000x7fdf25a26480655366570807356866417018075836152170180757658591701807637657817018076435314
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491877981877984194304256008242969600x7fdf28a165800x7fdf25a264c0131072100446611237751217018076447484170180763765781701807698777717018077047297
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521877981877984194304256008242999680x7fdf28a164000x7fdf25a26500131072102383811459861617018077058606170180769877771701807790601617018077951461
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551877981877984194304256008243027200x7fdf28a162800x7fdf25a26540131072103615811586552817018077971480170180779060161701807858537517018078647811
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045818779818779841943042560012243054720x7fdf28a161000x7fdf25a26580131072102456211478626417018078659610170180785853751701807931481417018079376000
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046118779818779841943042560012243082240x7fdf2627df800x7fdf25a265c0655366585607384303217018079386999170180793146211701808003718017018080084669
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641877981877984194304256008243109760x7fdf2627de000x7fdf25a26600131072108267612114749617018080097499170180800371801701808071381817018080774310
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671877981877984194304256008243132160x7fdf2627dc800x7fdf25a26640131072107162412011684017018080786369170180807138181701808185205617018081933496
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701877981877984194304256008243159680x7fdf2627db000x7fdf25a26680131072103513611614172817018081953486170180818520561701808299877417018083069864
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047318779818779841943042560012243187200x7fdf2627d9800x7fdf25a266c0131072102399811468032817018083082153170180829987741701808413509217018084204201
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047618779818779841943042560012243214720x7fdf2627d8000x7fdf25a26700655366556747352837617018084216311170180841350921701808526149017018085331919
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791877981877984194304256008243242240x7fdf2627d6800x7fdf25a26740131072107148411997482417018085343969170180852614901701808638324917018086454787
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821877981877984194304256008243264640x7fdf28a165000x7fdf25a26780131072103343411559848817018086468176170180863832491701808834628617018088417350
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851877981877984194304256008243292160x7fdf28a163800x7fdf25a267c0131072104899611733277617018088437679170180883462861701809027556317018090347644
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048818779818779841943042560012243319680x7fdf28a162000x7fdf25a26800131072103584411611254417018090359824170180902755631701809226452017018092341397
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049118779818779841943042560012243347200x7fdf28a160800x7fdf25a26840655366571387361244017018092353587170180922645201701809424963617018094320530
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941877981877984194304256008243374720x7fdf2627df000x7fdf25a26880131072106209411915873617018094334470170180942496361701809620099317018096272584
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049718779818779841943042560082400x7fdf2627dd800x7fdf25a268c0131072102174211450789617018096284944170180962009931701809981986817018099890840