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

48 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_CYCLESSQ_BUSY_CYCLESSQ_WAVESGRBM_COUNTGRBM_GUI_ACTIVECPF_CPF_STAT_BUSYCPF_CPF_STAT_STALLCPF_CPF_TCIU_BUSYCPF_CPF_TCIU_STALLCPF_CPF_STAT_IDLECPF_CPF_TCIU_IDLECPF_CMP_UTCL1_STALL_ON_TRANSLATIONDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000162887162887335544322560043241600x00x7f0b90204280306668029771665242883833343833343833340289600380125016527598245916165304468363441653044707682216527746399726
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00216288716288732768256001224138880x00x7f0b90223f80269736161104512337163371633716017980031489016527751557277165304518634991653045187725916527751693352
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051628871628874194304256001224143360x7f0baea383800x7f0b90223fc013234561214693655361654311654311654310185500162564016527751728691165304519471781653045203981716527752064919
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081628871628874194304256001624150400x7f0baea382000x7f0b9022400024759922366960655363094983094983094980184600309104016527752103057165304520730971653045225245516527752473314
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111628871628874194304256001624154880x7f0baea380800x7f0b9022404024762402374199655363095293095293095290182300307591016527752506633165304522778951653045245853316527752872929
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141628871628874194304256001224159360x7f0bac409f000x7f0b9022408013254801216078655361656841656841656840178600162298016527752905488165304524825331653045257597216527753178638
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171628871628874194304256001224163840x7f0bac409d800x7f0b902240c013221201207782655361652641652641652640184000162240016527753211147165304526022121653045269405116527753487487
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201628871628874194304256001224170880x7f0bac409c000x7f0b9022410013034801198691655361629341629341629340183700162983016527753532295165304527340511653045282653016527753792776
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231628871628874194304256001624177920x7f0bac409a800x7f0b9022414024763042369047655363095373095373095370182900308583016527753825304165304528586901653045303900816527754190011
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261628871628874194304256001624184960x7f0bac4099000x7f0b9022418024610802353703655363076343076343076340183900307574016527754221890165304530716481653045325180616527754609176
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291628871628874194304256001624192000x7f0bac4097800x7f0b902241c013126321205018655361640781640781640780184600162029016527754641315165304532902061653045338364516527754886496
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321628871628874194304256001624199040x7f0bac4096000x7f0b9022420013189681212892655361648701648701648700179800162759016527754919034165304534126051653045350540416527755163286
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351628871628874194304256001224206080x7f0baea384800x7f0b9022424013243201213026655361655391655391655390180900160902016527755204774165304535377241653045363020316527755441545
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381628871628874194304256001624213120x7f0baea383000x7f0b9022428024808722371525655363101083101083101080189100307752016527755474674165304536596431653045383932116527755806902
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411628871628874194304256001624220160x7f0baea381800x7f0b902242c025093282391788655363136653136653136650180400305754016527755839161165304538649211653045404587916527756173949
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441628871628874194304256001624227200x7f0baea380000x7f0b9022430013110401208082655361638791638791638790179900162021016527756206877165304540738791653045416699816527756450309
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471628871628874194304256001224234240x7f0bac409e800x7f0b9022434013162161207008655361645261645261645260183900161639016527756481967165304541961181653045429019716527756739068
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501628871628874194304256001224241280x7f0bac409d000x7f0b9022438013055201197448655361631891631891631890184400160576016527756779836165304543250771653045441883616527757015328
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531628871628874194304256001624248320x7f0bac409b800x7f0b902243c024724642362078655363090573090573090570182900306159016527757048047165304544740361653045465387416527757383154
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561628871628874194304256001624255360x7f0bac409a000x7f0b9022440024422242333727655363052773052773052770186800305798016527757415683165304546871541653045486651216527757747371
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591628871628874194304256001224262400x7f0bac4098800x7f0b9022444013085281202335655361635651635651635650187400160937016527757779380165304549194721653045501259116527758025281
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621628871628874194304256001224269440x7f0bac4097000x7f0b9022448013064481203391655361633051633051633050189300162104016527758057670165304550383511653045513115016527758309631
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651628871628874194304256001224276480x7f0baea385800x7f0b902244c013085841207858655361635721635721635720183300161344016527758349409165304551650691653045525722916527758588150
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681628871628874194304256001624286080x7f0baea384000x7f0b9022450024602802355799655363075343075343075340183900305420016527758620939165304552825081653045546138716527758951537
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711628871628874194304256001624293120x7f0baea382800x7f0b9022454024449522343679655363056183056183056180185300305982016527758984176165304554881071653045566746516527759322073
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741628871628874194304256001224300160x7f0baea381000x7f0b9022458013003441192507655361625421625421625420188700160334016527759355632165304556909851653045578266416527759598493
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077162887162887419430425600824309760x7f0bac409f800x7f0b902245c012894481188425655361611801611801611800184400160308016527759631602165304558074641653045589914316527759875793
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801628871628874194304256001224316800x7f0bac409e000x7f0b9022460012961041192899655361620121620121620120182400161086016527759914982165304559314631653045602458216527760156483
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831628871628874194304256001624326400x7f0bac409c800x7f0b9022464024501842339341655363062723062723062720181300304030016527760190302165304560500221653045622986016527760521369
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861628871628874194304256001224336000x7f0bac409b000x7f0b9022468024575922354784655363071983071983071980182600304150016527760553698165304562538601653045643433816527760887146
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891628871628874194304256001224345600x7f0bac4099800x7f0b902246c013117681205947655361639701639701639700179500162588016527760919575165304564586581653045655289716527761164756
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092162887162887419430425600824355200x7f0bac4098000x7f0b9022470013056401201221655361632041632041632040178800161868016527761197965165304565789771653045667321616527761458495
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951628871628874194304256001224362240x7f0bac4096800x7f0b9022474013002321199431655361625281625281625280182900160539016527761498824165304567052161653045679833516527761745634
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981628871628874194304256001224371840x7f0baea385000x7f0b9022478024536722347680655363067083067083067080181700304868016527761778523165304568232951653045700425316527762111921
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011628871628874194304256001224381440x7f0baea383800x7f0b902247c024460562341406655363057563057563057560175500303816016527762145770165304570295331653045721097116527762482368
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041628871628874194304256001224391040x7f0baea382000x7f0b9022480013000241196357655361625021625021625020181700160414016527762514946165304572365711653045733017016527762760747
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107162887162887419430425600824403200x7f0baea380800x7f0b9022484013140401207009655361642541642541642540179900160456016527762794086165304573556101653045745048916527763040557
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101628871628874194304256001224412800x7f0bac409f000x7f0b9022488012993521198763655361624181624181624180180100160295016527763080456165304574831291653045757688816527763321727
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131628871628874194304256001224422400x7f0bac409d800x7f0b902248c024564082346224655363070503070503070500180100305336016527763354456165304576029681653045778168616527763689323
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161628871628874194304256001224432000x7f0bac409c000x7f0b9022490024343442329888655363042923042923042920180800302129016527763722262165304578063261653045798712416527764053390
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119162887162887419430425600824441600x7f0bac409a800x7f0b9022494013025201202231655361628141628141628140181200160737016527764085569165304580132041653045810792316527764335470
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221628871628874194304256001224453760x7f0bac4099000x7f0b9022498013085841200679655361635721635721635720180700162576016527764368019165304581314431653045822616216527764614420
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251628871628874194304256001224463360x7f0bac4097800x7f0b902249c012939281191852655361617401617401617400179800159745016527764654558165304582588021653045835176116527764897509
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281628871628874194304256001224475520x7f0bac4096000x7f0b90224a0024394962332363655363049363049363049360181100305021016527764930478165304583759211653045855527916527765262346
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311628871628874194304256001224485120x7f0baea384800x7f0b90224a4024448882335426655363056103056103056100186100302787016527765295745165304585802391653045876199716527765629273
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134162887162887419430425600824494720x7f0baea383000x7f0b90224a8012874161182582655361609261609261609260177600160123016527765661981165304587864771653045887911616527765908292
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371628871628874194304256001224506880x7f0baea381800x7f0b90224ac012982081188991655361622751622751622750179200160392016527765940891165304589043961653045899831516527766198182
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401628871628874194304256001224516480x7f0baea380000x7f0b90224b0012877281183940655361609651609651609650177200158806016527766239560165304590303151653045912231416527766489251
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431628871628874194304256001224528640x7f0bac409e800x7f0b90224b4024241442312053655363030173030173030170180200300809016527766521670165304591498341653045932887216527766853648
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461628871628874194304256001224540800x7f0bac409d000x7f0b90224b8024362882330086655363045353045353045350178400301592016527766886827165304593536721653045953287116527767221304
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149162887162887419430425600824552960x7f0bac409b800x7f0b90224bc013051921195223655361631481631481631480178400159731016527767253303165304595560701653045964967016527767501664
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521628871628874194304256001224567680x7f0bac409a000x7f0b90224c0013016001196100655361626991626991626990180800160722016527767534403165304596743091653045977030816527767783294
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551628871628874194304256001224577280x7f0bac4098800x7f0b90224c4012966721185038655361620831620831620830178600160135016527767822372165304598032681653045989734716527768067613
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581628871628874194304256001224589440x7f0bac4097000x7f0b90224c8024247522313843655363030933030933030930180800300082016527768101762165304599219871653046010246616527768435460
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611628871628874194304256001224601600x7f0baea385800x7f0b90224cc024066242298964655363008273008273008270187800299240016527768468869165304601275851653046030934416527768801597
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164162887162887419430425600824613760x7f0baea384000x7f0b90224d0012981441196196655361622671622671622670181500160829016527768834105165304603357431653046043046316527769084166
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671628871628874194304256001224628480x7f0baea382800x7f0b90224d4013575361249293655361696911696911696910183600166679016527769116815165304604571821653046055622116527769368206
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701628871628874194304256001224638080x7f0baea381000x7f0b90224d8012972961193160655361621611621611621610189100159698016527769408555165304605883811653046068150016527769651296
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731628871628874194304256001224650240x7f0bac409f800x7f0b90224dc023865762281395655362983212983212983210181200297798016527769684994165304607096601653046088853916527770014252
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761628871628874194304256001224662400x7f0bac409e000x7f0b90224e0023985122284666655362998132998132998130178400300425016527770046771165304609144581653046109269716527770392109
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179162887162887419430425600824674560x7f0bac409c800x7f0b90224e4013137601198132655361642191642191642190183800161229016527770424597165304611194161653046121349616527770674658
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821628871628874194304256001224689280x7f0bac409b000x7f0b90224e8014106721306123655361763331763331763330179700173724016527770707057165304612381351653046134325416527770963248
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851628871628874194304256001224701440x7f0bac4099800x7f0b90224ec012920321179503655361615031615031615030186600159945016527771002916165304613750941653046146805316527771242777
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881628871628874194304256001224716160x7f0bac4098000x7f0b90224f0024185522313489655363023183023183023180187500299507016527771274496165304614936531653046167381216527771613604
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911628871628874194304256001224728320x7f0bac4096800x7f0b90224f4024260082318916655363032503032503032500184500299777016527771645493165304617000511653046188005016527771980790
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194162887162887419430425600824740480x7f0baea385000x7f0b90224f8012978881193606655361622351622351622350183500159013016527772013349165304619048491653046199876916527772260420
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971628871628874194304256001224757760x7f0baea383800x7f0b90224fc014539681346302655361817451817451817450180300180334016527772292939165304620245281653046213172716527772552389
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001628871628874194304256001224769920x7f0baea382000x7f0b9022500012873601182226655361609191609191609190186800158917016527772605657165304621664471653046225972616527772834279
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031628871628874194304256001224784640x7f0baea380800x7f0b9022504024228802310198655363028593028593028590184500300272016527772867338165304622837261653046246292516527773203295
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061628871628874194304256001224799360x7f0bac409f000x7f0b9022508023943842285990655362992972992972992970186200298327016527773236424165304624866041653046266628316527773566512
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209162887162887419430425600824814080x7f0bac409d800x7f0b902250c012956561192793655361619561619561619560181900161158016527773599161165304626906031653046278532216527773845552
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121628871628874194304256001224831360x7f0bac409c000x7f0b9022510015363361424919655361920411920411920410183600190563016527773877371165304628085211653046292340016527774148981
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151628871628874194304256001224843520x7f0bac409a800x7f0b9022514012882561185834655361610311610311610310177300159140016527774188629165304629680401653046306195916527774443830
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181628871628874194304256001224858240x7f0bac4099000x7f0b9022518024001842288339655363000223000223000220186600299372016527774476389165304630873991653046326691716527774811556
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211628871628874194304256001224872960x7f0bac4097800x7f0b902251c023904722279329655362988082988082988080181900298097016527774844695165304632918771653046347123616527775176203
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241628871628874194304256001224887680x7f0bac4096000x7f0b9022520013012561194316655361626561626561626560183300161632016527775208692165304634958751653046359075516527775456633
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271628871628874194304256001224907520x7f0baea384800x7f0b9022524016167281499954655362020902020902020900179100201367016527775489042165304636181141653046373875316527775762582
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301628871628874194304256001224919680x7f0baea383000x7f0b9022528012953121190255655361619131619131619130177200159839016527775802350165304637710731653046386403216527776054071
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331628871628874194304256001224934400x7f0baea381800x7f0b902252c024146482310990655363018303018303018300178400302991016527776086020165304638899521653046406947016527776427767
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361628871628874194304256001224949120x7f0baea380000x7f0b9022530023857282281424655362982152982152982150184100297111016527776461236165304640960301653046427586816527776794504
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391628871628874194304256001224963840x7f0bac409e800x7f0b9022534012969921190427655361621231621231621230185000160782016527776827563165304643014681653046439682716527777075374
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421628871628874194304256001224983680x7f0bac409d000x7f0b9022538016837921571279655362104732104732104730182100207574016527777107853165304644219471653046454898616527777387122
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451628871628874194304256001224995840x7f0bac409b800x7f0b902253c012836481181286655361604551604551604550180600159244016527777426691165304645825861653046467666516527777665992
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024816288716288741943042560012241013120x7f0bac409a000x7f0b9022540023899842282523655362987472987472987470181600294791016527777697341165304647021051653046488226316527778028879
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025116288716288741943042560012241027840x7f0bac4098800x7f0b9022544024215842307908655363026973026973026970178900296888016527778061538165304649078631653046508770116527778402345
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025416288716288741943042560012241042560x7f0bac4097000x7f0b9022548012871521183733655361608931608931608930178700158991016527778434734165304651123411653046520626016527778683165
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025716288716288741943042560012241062400x7f0baea385800x7f0b902254c017547441638861655362193422193422193420178600217257016527778715344165304652321801653046536225916527779002903
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026016288716288741943042560012241077120x7f0baea384000x7f0b9022550012820961179182655361602611602611602610176100159506016527779043492165304653945781653046548769816527779287273
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026316288716288741943042560016241094400x7f0baea382800x7f0b9022554023795762277689655362974462974462974460180700297971016527779320172165304655142571653046569345616527779654660
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026616288716288741943042560016241111680x7f0baea381000x7f0b9022558023976642284647655362997072997072997070181400296523016527779687118165304657182561653046589777416527780031636
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691628871628874194304256008241128960x7f0bac409f800x7f0b902255c013018001199807655361627241627241627240179700160398016527780064185165304659220941653046601777316527780314845
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027216288716288741943042560012241151360x7f0bac409e000x7f0b9022560018250881719381655362281352281352281350182100227100016527780346624165304660420931653046618129116527780636264
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027516288716288741943042560012241166080x7f0bac409c800x7f0b9022564012971761193665655361621461621461621460182400159182016527780675982165304662144111653046630865016527780922033
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027816288716288741943042560016241183360x7f0bac409b000x7f0b9022568023735122266418655362966882966882966880184700296044016527780954212165304663326501653046651200916527781288170
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028116288716288741943042560016241200640x7f0bac4099800x7f0b902256c023705202267903655362963142963142963140180000295087016527781320699165304665364881653046671600716527781655177
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028416288716288741943042560012241217920x7f0bac4098000x7f0b9022570013021361199830655361627661627661627660182400162654016527781687785165304667401671653046683696616527781936346
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028716288716288741943042560012241240320x7f0bac4096800x7f0b9022574019075601801246655362384442384442384440180300236070016527781968525165304668620851653046700736416527782283894
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029016288716288741943042560012241255040x7f0baea385000x7f0b9022578012918161182027655361614761614761614760181000159400016527782324192165304670393641653046713488316527782574353
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029316288716288741943042560012241274880x7f0baea383800x7f0b902257c023854322278586655362981782981782981780177800295898016527782607442165304671600031653046733984116527782940589
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029616288716288741943042560012241292160x7f0baea382000x7f0b9022580023983122274055655362997882997882997880179300296195016527782973558165304673654411653046754639916527783304896
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029916288716288741943042560012241309440x7f0baea380800x7f0b9022584013638001257931655361704741704741704740178700168651016527783337305165304675707191653046767055816527783593535
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030216288716288741943042560012241334400x7f0bac409f000x7f0b9022588020740401959043655362592542592542592540181400257540016527783625904165304676943981653046784975716527783940403
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030516288716288741943042560012241349120x7f0bac409d800x7f0b902258c012860801185026655361607591607591607590177300159913016527783980611165304678827161653046797711616527784223562
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030816288716288741943042560012241368960x7f0bac409c000x7f0b9022590023717602264359655362964692964692964690177700295219016527784255221165304680014351653046818063416527784589799
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031116288716288741943042560012241388800x7f0bac409a800x7f0b9022594023676002264092655362959492959492959490180000293234016527784621608165304682059131653046838607216527784953836
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031416288716288741943042560012241408640x7f0bac4099000x7f0b9022598014273041318763655361784121784121784120183300176831016527784986194165304684110321653046851855116527785244245
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031716288716288741943042560012241436160x7f0bac4097800x7f0b902259c022449282132382655362806152806152806150187800278647016527785276814165304685428701653046871278916527785602102
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032016288716288741943042560012241453440x7f0bac4096000x7f0b90225a0012896321183163655361612031612031612030178700160928016527785641970165304687457491653046884190816527785886321
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032316288716288741943042560012241475840x7f0baea384800x7f0b90225a4023756482261798655362969552969552969550189000294213016527785918370165304688665481653046904686616527786252948
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032616288716288741943042560012241495680x7f0baea383000x7f0b90225a8023595522251601655362949432949432949430178800295469016527786285807165304690713461653046925150416527786626104
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032916288716288741943042560012241515520x7f0baea381800x7f0b90225ac014985841378958655361873221873221873220183000186225016527786658603165304692751841653046938526316527786924873
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033216288716288741943042560012241543040x7f0baea380000x7f0b90225b0023975522284041655362996932996932996930182600297343016527786957782165304694087831653046959022116527787292000
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033516288716288741943042560012241562880x7f0bac409e800x7f0b90225b4013746321268032655361718281718281718280184400170310016527787331559165304696227011653046972398016527787585029
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033816288716288741943042560012241587840x7f0bac409d000x7f0b90225b8023830882258516655362978852978852978850182300298581016527787617228165304697486201653046993181816527787952116
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034116288716288741943042560012241610240x7f0bac409b800x7f0b90225bc023867922267076655362983482983482983480181500296575016527787984905165304699577381653047014461616527788324332
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034416288716288741943042560012241632640x7f0bac409a000x7f0b90225c0016499361537583655362062412062412062410178900204270016527788356881165304701702161653047029293516527788633861
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034716288716288741943042560012241665280x7f0bac4098800x7f0b90225c4027163522606837655363395433395433395430179100338883016527788666410165304703209351653047052765316527789073955
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035016288716288741943042560012241685120x7f0bac4097000x7f0b90225c8014682721359603655361835331835331835330178600182122016527789092584165304706014121653047071293116527789362094
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035316288716288741943042560012241712640x7f0baea385800x7f0b90225cc023758162233445655362969762969762969760182200296645016527789397663165304707385311653047092364916527789731861
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035616288716288741943042560012241737600x7f0baea384000x7f0b90225d0023925762252765655362990712990712990710183800296127016527789765360165304709479691653047113340716527790102707
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035916288716288741943042560012241762560x7f0baea382800x7f0b90225d4018030481691804655362253802253802253800182400222786016527790135636165304711596471653047129484616527790426805
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036216288716288741943042560012241797760x7f0baea381000x7f0b90225d8030556162938337655363819513819513819510181700378293016527790459204165304713188461653047155116416527790891388
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036516288716288741943042560012241822720x7f0bac409f800x7f0b90225dc016901681577915655362112702112702112700182400208784016527790910098165304716220431653047174876216527791192417
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036816288716288741943042560012241855360x7f0bac409e000x7f0b90225e0024405922320828655363050733050733050730180700302885016527791224616165304717758021653047196780016527791566194
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037116288716288741943042560012241885440x7f0bac409c800x7f0b90225e4024744002345412655363092993092993092990183600307924016527791597993165304719924401653047218635816527791993628
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037416288716288741943042560012241915520x7f0bac409b000x7f0b90225e8021263682016579655362657952657952657950178500263556016527792004488165304722092381653047236971616527792326546
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037716288716288741943042560012241958400x7f0bac4099800x7f0b90225ec036940003578192655364617494617494617490183600459963016527792359445165304723940361653047267755416527792838327
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038016288716288741943042560012241985920x7f0bac4098000x7f0b90225f0019448481835500655362431052431052431050186000240909016527792856837165304727484331653047289723216527793159766
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038316288716288741943042560012242023680x7f0bac4096800x7f0b90225f4026751282557948655363343903343903343900182400332608016527793194324165304729234721653047313115016527793596190
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038616288716288741943042560012242058880x7f0baea385000x7f0b90225f8026497602524762655363312193312193312190184200329142016527793606679165304731701891653047338090816527793994145
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038916288716288741943042560012242094080x7f0baea383800x7f0b90225fc024557602345421655363069693069693069690182400304352016527794010085165304734157871653047360218616527794360492
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039216288716288741943042560012242144640x7f0baea382000x7f0b9022600043377924224233655365422235422235422230178800540587016527794394110165304736269851653047396170216527794924281
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039516288716288741943042560012242177280x7f0baea380800x7f0b9022604021718802063261655362714842714842714840182800269025016527794943060165304740058621653047417450016527795270488
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039816288716288741943042560012242220160x7f0bac409f000x7f0b9022608029491602828767655363686443686443686440181700363855016527795303537165304741996201653047442633816527795733491
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040116288716288741943042560012242260480x7f0bac409d800x7f0b902260c029353682815450655363669203669203669200176500367015016527795743551165304744666581653047469545616527796181145
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040416288716288741943042560012242300800x7f0bac409c000x7f0b9022610027841362669586655363480163480163480160180400344553016527796191305165304747548151653047496649316527796609679
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040716288716288741943042560012242359040x7f0bac409a800x7f0b9022614049927924873732655366240986240986240980179600622147016527796620189165304750255331653047541128916527797212437
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041016288716288741943042560012242394240x7f0bac4099000x7f0b9022618024276562317986655363034563034563034560177400300673016527797230476165304754820091653047566888716527797571884
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041316288716288741943042560012242442240x7f0bac4097800x7f0b902261c031811923068821655363976483976483976480177000394960016527797605443165304756935271653047594440516527798024897
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041616288716288741943042560012242487680x7f0bac4096000x7f0b9022620031401523034625655363925183925183925180179200389147016527798038677165304760028041653047625144216527798503830
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041916288716288741943042560012242533120x7f0baea384800x7f0b9022624030998722987292655363874833874833874830176900386874016527798514919165304763114411653047654823916527798970833
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221628871628874194304256008242555520x7f0baea383000x7f0b9022628057517685629198655367189707189707189700180000716566016527798981762165304765872791653047704039516527799640678
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042516288716288741943042560012242598400x7f0baea381800x7f0b902262c029182322798266655363647783647783647780179300360331016527799659878165304770827951653047730887316527800079562
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042816288716288741943042560012242656640x7f0baea380000x7f0b9022630037506483640401655364688304688304688300177300466601016527800090202165304773434321653047764183016527800593133
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043116288716288741943042560012242712320x7f0bac409e800x7f0b9022634037617123660866655364702134702134702130180800469296016527800603823165304776794291653047797766716527801107335
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341628871628874194304256008242732160x7f0bac409d000x7f0b9022638038663203752679655364832894832894832890180700481518016527801117654165304780168661653047831350416527801619206
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371628871628874194304256008242757120x7f0bac409b800x7f0b902263c070384486934428655368798058798058798050179400877563016527801630076165304783531831653047891141816527802395128
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044016288716288741943042560012242807680x7f0bac409a000x7f0b9022640034107523301530655364263434263434263430179500424881016527802414347165304789592581653047922245616527802883190
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044316288716288741943042560012242876160x7f0bac4098800x7f0b9022644043936804290125655365492095492095492090178200547587016527802893999165304792603751653047961157216527803456119
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044616288716288741943042560012242942080x7f0bac4097000x7f0b9022648044006484292908655365500805500805500800178600548758016527803466878165304796600521653048001076916527804019498
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491628871628874194304256008242969600x7f0baea385800x7f0b902264c045082004389280655365635245635245635240185300561768016527804030308165304800571681653048040404516527804581378
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521628871628874194304256008242999680x7f0baea384000x7f0b90226500833773682206236553610422161042216104221601820001038552016527804592037165304804442051653048110515916527805456526
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551628871628874194304256008243027200x7f0baea382800x7f0b9022654057673765656019655367209217209217209210182700718325016527805475945165304811541181653048160275416527806142821
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045816288716288741943042560012243054720x7f0baea381000x7f0b9022658057872325671957655367234037234037234030187100721443016527806154180165304816432341653048210883016527806954141
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046116288716288741943042560012243082240x7f0bac409f800x7f0b902265c057889285665413655367236157236157236150181900720629016527806965461165304821521901653048261362516527807764771
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641628871628874194304256008243109760x7f0bac409e000x7f0b9022660058102565692286655367262817262817262810179900723708016527807776401165304826569851653048310914116527808549212
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671628871628874194304256008243132160x7f0bac409c800x7f0b9022664010939624108157366553613674521367452136745201791001365108016527808561152165304831497811653048401873316527809751118
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701628871628874194304256008243159680x7f0bac409b000x7f0b9022668010965032108498106553613706281370628137062801852001368282016527809770388165304840668931653048492160516527810974834
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047316288716288741943042560012243187200x7f0bac4099800x7f0b902266c010991536108626086553613739411373941137394101815001372115016527810987553165304849836841653048586879716527812236547
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047616288716288741943042560012243214720x7f0bac4098000x7f0b9022670010958472108447116553613698081369808136980801776001369335016527812247837165304859310361653048681214816527813492222
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791628871628874194304256008243242240x7f0bac4096800x7f0b9022674011021840108867506553613777291377729137772901813001373206016527813504591165304868804681653048774046016527814737736
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821628871628874194304256008243264640x7f0baea385000x7f0b9022678021309168211829286553626636452663645266364501835002658671016527814750506165304878054191653048950460416527816799321
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851628871628874194304256008243292160x7f0baea383800x7f0b902267c021364368212254756553626705452670545267054501858002668092016527816818000165304896042831653049127002916527818790778
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048816288716288741943042560012243319680x7f0baea382000x7f0b9022680021353920212390366553626692392669239266923901789002666863016527818802708165304913593081653049308585216527820846263
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049116288716288741943042560012243347200x7f0baea380800x7f0b9022684021376880212371116553626721092672109267210901780002669988016527820857503165304931740121653049489079616527822898268
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941628871628874194304256008243374720x7f0bac409f000x7f0b9022688021371392212574726553626714232671423267142301864002669733016527822910287165304949823161653049665686116527824898164
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049716288716288741943042560082400x7f0bac409d800x7f0b902268c042069472419274276553652586835258683525868301841005256262016527824909134165304967445401653050010339016527828581890