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

44 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjGRBM_COUNTGRBM_GUI_ACTIVESQ_WAVESSQ_IFETCHSQ_IFETCH_LEVELSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000188020188020335544322560043241600x00x7ff00360428038187238187252428847185926800457623840417018811649857170180998197521701895512169417018955231973
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00218802018802032768256001224138880x00x7ff003623f8032726327265128192748883584017018960426954170189551216941701896055864717018960563330
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051880201880204194304256001224143360x7ff0066f63800x7ff003623fc0165172165172655369175041528781712667217018960599629170189605586471701896092760617018960930139
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081880201880204194304256001624150400x7ff0066f62000x7ff0036240003097123097126553611141121696051902960417018960968868170189609276061701896133528617018961337457
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111880201880204194304256001624154880x7ff0066f60800x7ff003624040310378310378655369175041471761648284017018961372806170189613352861701896174024517018961742256
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141880201880204194304256001224159360x7ff0040c9f000x7ff0036240801656281656286553610485761586941776004817018961778105170189617402451701896205128517018962053687
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171880201880204194304256001224163840x7ff0040c9d800x7ff0036240c0164494164494655369830401503411686496017018962097476170189620512851701896238168517018962383947
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201880201880204194304256001224170880x7ff0040c9c000x7ff0036241001640541640546553611141121637651827612417018962430156170189623816851701896269640417018962698558
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231880201880204194304256001624177920x7ff0040c9a800x7ff0036241403092143092146553613107201953422187524817018962733657170189626964041701896309720417018963099327
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261880201880204194304256001624184960x7ff0040c99000x7ff0036241803093503093506553611796481790251998661617018963133536170189630972041701896351288317018963514785
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291880201880204194304256001624192000x7ff0040c97800x7ff0036241c01639541639546553612451841879062105884417018963548874170189635128831701896382216317018963824246
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321880201880204194304256001624199040x7ff0040c96000x7ff0036242001655761655766553612451841859042081890817018963859205170189638221631701896413336317018964135427
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351880201880204194304256001224206080x7ff0066f64800x7ff0036242401629491629496553612451841890182113606017018964178296170189641333631701896444264217018964444588
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381880201880204194304256001624213120x7ff0066f63000x7ff0036242803106633106636553614417922237562505236017018964481607170189644426421701896483848217018964840577
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411880201880204194304256001624220160x7ff0066f61800x7ff0036242c03075133075136553613107201996312233394417018964876016170189648384821701896523640217018965238296
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441880201880204194304256001624227200x7ff0066f60000x7ff0036243001632551632556553613762562070672319374017018965273955170189652364021701896554632117018965548347
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471880201880204194304256001224234240x7ff0040c9e800x7ff0036243401636971636976553614417922184402442459617018965583756170189655463211701896585832117018965860318
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501880201880204194304256001224241280x7ff0040c9d000x7ff0036243801636991636996553613107201965822198936417018965901177170189658583211701896617640017018966178589
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531880201880204194304256001624248320x7ff0040c9b800x7ff0036243c03102433102436553615728642357342630672017018966215358170189661764001701896658744017018966588947
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561880201880204194304256001624255360x7ff0040c9a000x7ff0036244003054373054376553614417922077292328189617018966622636170189665874401701896695544017018966956806
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591880201880204194304256001224262400x7ff0040c98800x7ff0036244401624441624446553615073282236102514667217018966991105170189669554401701896723959917018967240928
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621880201880204194304256001224269440x7ff0040c97000x7ff0036244801626091626096553616384002431762718146817018967276127170189672395991701896752039917018967522060
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651880201880204194304256001224276480x7ff0066f65800x7ff0036244c01625681625686553614417922289912577106017018967563869170189675203991701896782039917018967821791
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681880201880204194304256001624286080x7ff0066f64000x7ff0036245003085053085056553617039362521042823264417018967858710170189678203991701896819159817018968192970
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711880201880204194304256001624293120x7ff0066f62800x7ff0036245403052993052996553615728642335622620436817018968228149170189681915981701896856023817018968561690
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741880201880204194304256001224300160x7ff0066f61000x7ff0036245801621361621366553616384002445502737578417018968595989170189685602381701896884551817018968846982
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077188020188020419430425600824309760x7ff0040c9f800x7ff0036245c01623231623236553618350082717433043080417018968882081170189688455181701896913063717018969132053
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801880201880204194304256001224316800x7ff0040c9e000x7ff0036246001620271620276553615073282244932513151217018969174242170189691306371701896941959717018969421055
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831880201880204194304256001624326400x7ff0040c9c800x7ff0036246403058283058286553618350082721393042662417018969456134170189694195971701896978951717018969791034
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861880201880204194304256001224336000x7ff0040c9b000x7ff0036246803051043051046553617039362501162790922817018969824903170189697895171701897015735617018970158784
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891880201880204194304256001224345600x7ff0040c99800x7ff0036246c01639931639936553617694722629812949417617018970194483170189701573561701897044791617018970449405
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092188020188020419430425600824355200x7ff0040c98000x7ff0036247001646711646716553620316163054773418332017018970484844170189704479161701897073399517018970735527
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951880201880204194304256001224362240x7ff0040c96800x7ff0036247401623031623036553616384002456122748906017018970776866170189707339951701897102087517018971022339
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981880201880204194304256001224371840x7ff0066f65000x7ff0036247803046533046536553619660802900283253730017018971056448170189710208751701897139431517018971395838
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011880201880204194304256001224381440x7ff0066f63800x7ff0036247c03087853087856553618350082718663039239217018971430227170189713943151701897176519417018971766668
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041880201880204194304256001224391040x7ff0066f62000x7ff0036248001638361638366553619005442824983155571217018971801757170189717651941701897204727417018972048660
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107188020188020419430425600824403200x7ff0066f60800x7ff0036248401632121632126553622282243294133690145617018972083299170189720472741701897232903417018972330362
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101880201880204194304256001224412800x7ff0040c9f000x7ff0036248801621841621846553617039362564512868396417018972371680170189723290341701897260983317018972611353
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131880201880204194304256001224422400x7ff0040c9d800x7ff0036248c03064943064946553620971523111683480418417018972647422170189726098331701897297927317018972980693
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161880201880204194304256001224432000x7ff0040c9c000x7ff0036249003070873070876553619660802853723187376817018973014892170189729792731701897334855317018973350002
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119188020188020419430425600824441600x7ff0040c9a800x7ff0036249401622241622246553620316163021223394544817018973383961170189733485531701897362855217018973630084
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221880201880204194304256001224453760x7ff0040c99000x7ff0036249801637641637646553624248323813084269708417018973664413170189736285521701897391447217018973915826
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251880201880204194304256001224463360x7ff0040c97800x7ff0036249c01631551631556553618350082717073043759617018973957125170189739144721701897420967217018974211138
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281880201880204194304256001224475520x7ff0040c96000x7ff003624a003048473048476553622282243273193671213217018974246147170189742096721701897458679117018974588237
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311880201880204194304256001224485120x7ff0066f64800x7ff003624a403040693040696553620971523092763458484417018974623176170189745867911701897495831117018974959736
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134188020188020419430425600824494720x7ff0066f63000x7ff003624a801613471613476553621626883193353571254417018974994285170189749583111701897524455117018975246078
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371880201880204194304256001224506880x7ff0066f61800x7ff003624ac01611691611696553626214403907124383316417018975280867170189752445511701897552743017018975528990
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401880201880204194304256001224516480x7ff0066f60000x7ff003624b001606951606956553619660802971033326744017018975570429170189755274301701897580983017018975811252
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431880201880204194304256001224528640x7ff0040c9e800x7ff003624b403046663046666553623592963489563916122417018975847171170189758098301701897617943017018976180871
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461880201880204194304256001224540800x7ff0040c9d000x7ff003624b803000953000956553622282243387863791270417018976215070170189761794301701897655158917018976553040
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149188020188020419430425600824552960x7ff0040c9b800x7ff003624bc01624791624796553622937603440153853644017018976587449170189765515891701897683638917018976837822
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521880201880204194304256001224567680x7ff0040c9a000x7ff003624c001640761640766553627525124055124536944417018976872371170189768363891701897712054817018977121864
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551880201880204194304256001224577280x7ff0040c98800x7ff003624c401619441619446553620316162992473350386417018977163353170189771205481701897740870817018977410156
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581880201880204194304256001224589440x7ff0040c97000x7ff003624c803030733030736553624903683691484130621617018977444485170189774087081701897777862817018977780125
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611880201880204194304256001224601600x7ff0066f65800x7ff003624cc03027483027486553623592963485953905905217018977814404170189777786281701897814982717018978151295
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164188020188020419430425600824613760x7ff0066f64000x7ff003624d001620091620096553624248323670094104937617018978187544170189781498271701897843830717018978439726
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671880201880204194304256001224628480x7ff0066f62800x7ff003624d401690521690526553629491204450804982120017018978474625170189784383071701897873062717018978732088
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701880201880204194304256001224638080x7ff0066f61000x7ff003624d801615391615396553621626883221833614005217018978774527170189787306271701897901910617018979020420
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731880201880204194304256001224650240x7ff0040c9f800x7ff003624dc03020323020326553626214403878544339985217018979055149170189790191061701897938966617018979391139
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761880201880204194304256001224662400x7ff0040c9e000x7ff003624e002994762994766553624903683636184067190417018979425608170189793896661701897976166617018979763168
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179188020188020419430425600824674560x7ff0040c9c800x7ff003624e401630171630176553625559043815034269629217018979797977170189797616661701898004502517018980046380
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821880201880204194304256001224689280x7ff0040c9b000x7ff003624e801763561763566553631457284654495211906817018980080669170189800450251701898033414517018980335532
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851880201880204194304256001224701440x7ff0040c99800x7ff003624ec01605671605676553622282243285743680454017018980376911170189803341451701898061846517018980619814
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881880201880204194304256001224716160x7ff0040c98000x7ff003624f003006863006866553627525124102344593867617018980654173170189806184651701898099238417018980993743
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911880201880204194304256001224728320x7ff0040c96800x7ff003624f402996052996056553626214403874394344792817018981028212170189809923841701898136166417018981363062
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194188020188020419430425600824740480x7ff0066f65000x7ff003624f801604591604596553626869763973454450198417018981396961170189813616641701898165046417018981652004
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971880201880204194304256001224757760x7ff0066f63800x7ff003624fc01826331826336553633423365099115700837617018981686673170189816504641701898195078317018981952316
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001880201880204194304256001224769920x7ff0066f62000x7ff0036250001633251633256553623592963516463936349617018982007144170189819507831701898224422317018982245687
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031880201880204194304256001224784640x7ff0066f60800x7ff0036250403021093021096553628835844332974850573217018982280176170189822442231701898261878217018982620106
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061880201880204194304256001224799360x7ff0040c9f000x7ff0036250803004293004296553626869764018534500627617018982654865170189826187821701898298678217018982988206
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209188020188020419430425600824814080x7ff0040c9d800x7ff0036250c01622391622396553628180484152654656738417018983022325170189829867821701898327094217018983272378
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121880201880204194304256001224831360x7ff0040c9c000x7ff0036251001905091905096553635389445281105921018017018983307077170189832709421701898357302117018983574499
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151880201880204194304256001224843520x7ff0040c9a800x7ff0036251401608911608916553624248323633064072932417018983615508170189835730211701898386086117018983862331
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181880201880204194304256001224858240x7ff0040c99000x7ff0036251803014213014216553630146564726225305806817018983896670170189838608611701898423686117018984238170
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211880201880204194304256001224872960x7ff0040c97800x7ff0036251c03016793016796553628180484189834695701617018984272549170189842368611701898460502017018984606359
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241880201880204194304256001224887680x7ff0040c96000x7ff0036252001621481621486553629491204371894902651217018984640318170189846050201701898488950017018984890791
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271880201880204194304256001224907520x7ff0066f64800x7ff0036252402009192009196553637355525604816277764017018984925450170189848895001701898519638017018985197672
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301880201880204194304256001224919680x7ff0066f63000x7ff0036252801609501609506553625559043939224416077617018985239171170189851963801701898548405917018985485454
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331880201880204194304256001224934400x7ff0066f61800x7ff0036252c02990862990866553631457284677705233940017018985521953170189854840591701898585333917018985854634
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361880201880204194304256001224949120x7ff0066f60000x7ff0036253002985682985686553629491204597095149646817018985889553170189858533391701898622069817018986222403
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391880201880204194304256001224963840x7ff0040c9e800x7ff0036253401627651627656553630801924607265160560417018986257392170189862206981701898650997817018986511535
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421880201880204194304256001224983680x7ff0040c9d000x7ff0036253802099102099106553639321605871566572934017018986546254170189865099781701898682885817018986830175
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451880201880204194304256001224995840x7ff0040c9b800x7ff0036253c01616391616396553626214403905004370908817018986872084170189868288581701898711221817018987113607
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024818802018802041943042560012241013120x7ff0040c9a000x7ff0036254002970022970026553632768004986085582944017018987147966170189871122181701898747925717018987480637
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025118802018802041943042560012241027840x7ff0040c98800x7ff0036254402988112988116553630801924536575076658417018987515326170189874792571701898785029717018987851656
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025418802018802041943042560012241042560x7ff0040c97000x7ff0036254801600601600606553632112644760225326087217018987885785170189878502971701898812917617018988130578
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025718802018802041943042560012241062400x7ff0066f65800x7ff0036254c02185232185236553641287686139166864241217018988164937170189881291761701898844949617018988450759
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026018802018802041943042560012241077120x7ff0066f64000x7ff0036255001617081617086553627525124215024721150017018988493427170189884494961701898873589617018988737290
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026318802018802041943042560016241094400x7ff0066f62800x7ff0036255402965732965736553634078725127925740249217018988772399170189887358961701898910581517018989107260
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026618802018802041943042560016241111680x7ff0066f61000x7ff0036255802982672982676553632112644701485260171217018989141939170189891058151701898948021517018989481699
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691880201880204194304256008241128960x7ff0040c9f800x7ff0036255c01634871634876553632768004943645537880417018989516528170189894802151701898976565517018989767271
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027218802018802041943042560012241151360x7ff0040c9e000x7ff0036256002310642310646553643253766547177331485617018989800910170189897656551701899009189417018990093471
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027518802018802041943042560012241166080x7ff0040c9c800x7ff0036256401602551602556553628180484333514844210417018990135990170189900918941701899038501417018990386423
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027818802018802041943042560016241183360x7ff0040c9b000x7ff0036256803002103002106553635389445310245936676017018990422332170189903850141701899075365417018990755122
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028118802018802041943042560016241200640x7ff0040c99800x7ff0036256c02964612964616553634078725145745769501617018990789981170189907536541701899111973317018991121102
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028418802018802041943042560012241217920x7ff0040c98000x7ff0036257001630441630446553634078725208425831936817018991155751170189911197331701899140581317018991407244
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028718802018802041943042560012241240320x7ff0040c96800x7ff0036257402402532402536553645219846896147730494817018991441323170189914058131701899173909217018991740704
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029018802018802041943042560012241255040x7ff0066f65000x7ff0036257801604981604986553630146564644595204344817018991782533170189917390921701899203749217018992038866
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029318802018802041943042560012241274880x7ff0066f63800x7ff0036257c02974192974196553638010885789616488998817018992073545170189920374921701899241317217018992414685
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029618802018802041943042560012241292160x7ff0066f62000x7ff0036258002964902964906553636700165658996334857217018992449984170189924131721701899278021117018992781594
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029918802018802041943042560012241309440x7ff0066f60800x7ff0036258401688121688126553636700165483826144664817018992816523170189927802111701899306917117018993070586
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030218802018802041943042560012241334400x7ff0040c9f000x7ff0036258802584522584526553649152007459988348893217018993104865170189930691711701899341253117018993413956
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030518802018802041943042560012241349120x7ff0040c9d800x7ff0036258c01606921606926553631457284761425328772017018993455755170189934125311701899370325017018993704528
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030818802018802041943042560012241368960x7ff0040c9c000x7ff0036259002956442956446553640632326319367073514817018993740027170189937032501701899407301017018994074497
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031118802018802041943042560012241388800x7ff0040c9a800x7ff0036259402946892946896553639321605977986691073617018994109986170189940730101701899444452917018994445917
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031418802018802041943042560012241408640x7ff0040c99000x7ff0036259801780441780446553639321606237546990552417018994479926170189944445291701899475300917018994754358
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031718802018802041943042560012241436160x7ff0040c97800x7ff0036259c02781972781976553653084167938128902696417018994788957170189947530091701899511268917018995114097
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032018802018802041943042560012241453440x7ff0040c96000x7ff003625a001608791608796553633423364997875607528017018995156286170189951126891701899540276817018995404099
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032318802018802041943042560012241475840x7ff0066f64800x7ff003625a402970632970636553643253766805447619551217018995438598170189954027681701899577524817018995776638
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032618802018802041943042560012241495680x7ff0066f63000x7ff003625a802973792973796553641943046368357121629217018995811127170189957752481701899614324817018996144658
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032918802018802041943042560012241515520x7ff0066f61800x7ff003625ac01856891856896553641943046283357042059617018996179227170189961432481701899644292717018996444389
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033218802018802041943042560012241543040x7ff0066f60000x7ff003625b002981252981256553657016328592389620805217018996478678170189964429271701899681332717018996814799
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033518802018802041943042560012241562880x7ff0040c9e800x7ff003625b401706971706976553637355525769766459712417018996856627170189968133271701899710516717018997106530
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033818802018802041943042560012241587840x7ff0040c9d000x7ff003625b802969712969716553648496647854728790271217018997142279170189971051671701899747604617018997477440
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034118802018802041943042560012241610240x7ff0040c9b800x7ff003625bc02980662980666553647185927343358216761217018997511669170189974760461701899785188617018997853339
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034418802018802041943042560012241632640x7ff0040c9a000x7ff003625c002052772052776553647185927205898062784417018997887428170189978518861701899816580517018998167400
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034718802018802041943042560012241665280x7ff0040c98800x7ff003625c4034016434016465536648806497783310950516817018998202819170189981658051701899856660517018998614517
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035018802018802041943042560012241685120x7ff0040c97000x7ff003625c801836021836026553641287686226236973560817018998633246170189985666051701899890228517018998903679
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035318802018802041943042560012241712640x7ff0066f65800x7ff003625cc02956882956886553653739528671299721586017018998938718170189989022851701899927316417018999274618
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035618802018802041943042560012241737600x7ff0066f64000x7ff003625d002987752987756553652428808313499309028817018999309987170189992731641701899964628417018999647697
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035918802018802041943042560012241762560x7ff0066f62800x7ff003625d402248692248696553652428807878058822660417018999681696170189996462841701899997076317018999972268
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036218802018802041943042560012241797760x7ff0066f61000x7ff003625d80379301379301655367274496110739012397176017019000007477170189999707631701900039860317019000443864
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036518802018802041943042560012241822720x7ff0040c9f800x7ff003625dc02106072106076553649152007607118518754417019000463704170190003986031701900074436317019000745806
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036818802018802041943042560012241855360x7ff0040c9e000x7ff003625e00306497306497655366422528102521311483570017019000780295170190007443631701900112404217019001143384
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037118802018802041943042560012241885440x7ff0040c9c800x7ff003625e40311041311041655366291456101849911398402417019001160654170190011240421701900151220217019001529473
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037418802018802041943042560012241915520x7ff0040c9b000x7ff003625e8026657326657365536629145697641310930673217019001548253170190015122021701900186484117019001866324
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037718802018802041943042560012241958400x7ff0040c99800x7ff003625ec0460744460744655368847360134059815024721617019001901093170190018648411701900233668117019002358110
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038018802018802041943042560012241985920x7ff0040c98000x7ff003625f002434912434916553657016328682169730981217019002381209170190023366811701900268644017019002687990
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038318802018802041943042560012242023680x7ff0040c96800x7ff003625f40333893333893655367471104118908213316673217019002722469170190026864401701900308388017019003126047
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038618802018802041943042560012242058880x7ff0066f65000x7ff003625f80330302330302655367340032120670313514535217019003137197170190030838801701900351044017019003552295
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038918802018802041943042560012242094080x7ff0066f63800x7ff003625fc0306821306821655367340032112138512552457617019003564585170190035104401701900391571917019003917255
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039218802018802041943042560012242144640x7ff0066f62000x7ff0036260005423625423626553610420224159231517824724817019003952424170190039157191701900444019817019004481758
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039518802018802041943042560012242177280x7ff0066f60800x7ff00362604027231127231165536648806499406511127937617019004501368170190044401981701900482419817019004825558
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039818802018802041943042560012242220160x7ff0040c9f000x7ff003626080366833366833655368519680136094615241336017019004860177170190048241981701900524435817019005286705
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040118802018802041943042560012242260480x7ff0040c9d800x7ff0036260c0364837364837655368388608131334014696445617019005297405170190052443581701900569107717019005708943
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040418802018802041943042560012242300800x7ff0040c9c000x7ff003626100346203346203655368388608130750814643878417019005726852170190056910771701900609315717019006116021
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040718802018802041943042560012242359040x7ff0040c9a800x7ff0036261406229856229856553611993088181263020294363217019006129931170190060931571701900667811617019006700214
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041018802018802041943042560012242394240x7ff0040c99000x7ff003626180301129301129655367274496113565712718073617019006722794170190066781161701900706483617019007066174
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041318802018802041943042560012242442240x7ff0040c97800x7ff0036261c0398649398649655369568256152374117070771617019007102083170190070648361701900750595517019007527191
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041618802018802041943042560012242487680x7ff0040c96000x7ff003626200390816390816655369437184148205416599982017019007541660170190075059551701900794707517019007963988
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041918802018802041943042560012242533120x7ff0066f64800x7ff003626240386746386746655369437184145685516312157617019007983478170190079470751701900837539417019008392476
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221880201880204194304256008242555520x7ff0066f63000x7ff0036262807173897173896553616056320230615325824590017019008411865170190083753941701900901763317019009034767
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042518802018802041943042560012242598400x7ff0066f61800x7ff0036262c0363681363681655368847360138229415479270017019009061167170190090176331701900943251317019009448506
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042818802018802041943042560012242656640x7ff0066f60000x7ff0036263004695594695596553611665408186390420866217217019009470325170190094325131701900992211217019009939421
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043118802018802041943042560012242712320x7ff0040c9e800x7ff0036263404707184707186553611468800183578920566398417019009958581170190099221121701901041875217019010468006
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341880201880204194304256008242732160x7ff0040c9d000x7ff0036263804825954825956553614090240202316922670231217019010478716170190104187521701901094883117019010992981
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371880201880204194304256008242757120x7ff0040c9b800x7ff0036263c08790468790466553619202048275872530899124417019011003931170190109488311701901172243117019011764389
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044018802018802041943042560012242807680x7ff0040c9a000x7ff0036264004265894265896553610420224164798618456431617019011784129170190117224311701901220883017019012250905
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044318802018802041943042560012242876160x7ff0040c98800x7ff0036264405489765489766553613762560221471024810625217019012262025170190122088301701901278066917019012822589
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044618802018802041943042560012242942080x7ff0040c97000x7ff0036264805521525521526553613565952222020224861428817019012833348170190127806691701901334674917019013388643
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491880201880204194304256008242969600x7ff0066f65800x7ff0036264c05635945635946553615466496222872424946066017019013399332170190133467491701901391074817019013928457
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521880201880204194304256008242999680x7ff0066f64000x7ff003626500104109010410906553622347776321209435974546417019013947406170190139107481701901477138717019014816772
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551880201880204194304256008243027200x7ff0066f62800x7ff0036265407211107211106553620250624290891032574268417019014836071170190147713871701901544530617019015489212
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045818802018802041943042560012243054720x7ff0066f61000x7ff0036265807228237228236553620447232293764932898434017019015501412170190154453061701901613106617019016172903
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046118802018802041943042560012243082240x7ff0040c9f800x7ff0036265c07199627199626553619595264281855731565998417019016184302170190161310661701901680402517019016846383
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641880201880204194304256008243109760x7ff0040c9e000x7ff0036266007263477263476553620381696292994532807793217019016857173170190168040251701901746994417019017511644
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671880201880204194304256008243132160x7ff0040c9c800x7ff003626640136504613650466553631522816451589050570600817019017522294170190174697751701901855345417019018603573
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701880201880204194304256008243159680x7ff0040c9b000x7ff003626680137115213711526553638993920558547562559308417019018623522170190185534541701901965297117019019698881
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047318802018802041943042560012243187200x7ff0040c99800x7ff0036266c0137188613718866553639124992561038162814260417019019710961170190196529711701902077184917019020838068
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047618802018802041943042560012243214720x7ff0040c98000x7ff003626700137159013715906553638469632551527061774558417019020848978170190207718491701902190496817019021970716
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791880201880204194304256008243242240x7ff0040c96800x7ff003626740137481913748196553639059456561908662940134817019021983075170190219049681701902302736617019023095113
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821880201880204194304256008243264640x7ff0066f65000x7ff003626780266357626635766553660489728865325996897879217019023106843170190230273661701902499504317019025061667
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851880201880204194304256008243292160x7ff0066f63800x7ff0036267c026667372666737655367726694411059862123863526817019025080336170190249950431701902691856117019026989612
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048818802018802041943042560012243319680x7ff0066f62000x7ff00362680026696782669678655367739801611070589124015598817019027002461170190269185611701902890991817019028974155
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049118802018802041943042560012243347200x7ff0066f60800x7ff00362684026691952669195655367621836810907321122159045217019028986174170190289099181701903087855517019030945878
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941880201880204194304256008243374720x7ff0040c9f000x7ff00362688026726822672682655367733248011065165123913272417019030958418170190308785551701903281407217019032882213
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049718802018802041943042560082400x7ff0040c9d800x7ff0036268c0525424952542496553612025856017198681192552503617019032893642170190328140721701903642734717019036498219