Files
rocm-systems/tests/workloads/dev01p3/mi100/SQ_INST_LEVEL_VMEM.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

43 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_VMEMSQ_INST_LEVEL_VMEMSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000931671931676335544322560083264640x00x7f8101a04180104857610991950140658325612076536745644699120765369906674201207653699099141912076536991092712
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00293167193167632768256002424124800x00x7f8101a3510040961098551406808412076537005633911120765370059656941207653700597225412076537005977540
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0049316719316764194304256002424129280x7f820d5959000x7f8101a3514052428810827501138592464412076537006052800120765370062887331207653700642665312076537006431615
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0069316719316764194304256003624136320x7f820d5958000x7f8101a3518052428813152373168349130412076537006499130120765370067074521207653700695721112076537007029086
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0089316719316764194304256002824140800x7f820d5957000x7f8101a351c052428814200061181763957212076537007068339120765370073048901207653700755640912076537007625185
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00109316719316764194304256002424145280x7f820d5956000x7f8101a3520052428811407226146016018412076537007643849120765370078784881207653700801528812076537008020710
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00129316719316764194304256002424149760x7f820d5955000x7f8101a3524052428810073682128937185212076537008063009120765370083020071207653700844232712076537008446913
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00149316719316764194304256002424154240x7f820d5954000x7f8101a3528052428812069674154491674012076537008531060120765370087373661207653700887032612076537008875250
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00169316719316764194304256002824161280x7f820d5953000x7f8101a352c052428813834162177075926412076537008926375120765370091602451207653700941752412076537009487819
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00189316719316764194304256002824168320x7f820d595a000x7f8101a3530052428813752043176019740812076537009510792120765370097416831207653700999624212076537010065825
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00209316719316764194304256002424175360x7f820d5959000x7f8101a3534052428812622999161569254012076537010086012120765370103279211207653701045784112076537010462452
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00229316719316764194304256002424182400x7f820d5958000x7f8101a3538052428810876400139222625612076537010508829120765370107367201207653701087448012076537010879248
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00249316719316764194304256002424189440x7f820d5957000x7f8101a353c052428812430221159103405612076537010943457120765370111605591207653701129095912076537011296013
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00269316719316764194304256002824199040x7f820d5956000x7f8101a3540052428813681979175124695612076537011345395120765370115640781207653701181911712076537011888365
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00289316719316764194304256002824206080x7f820d5955000x7f8101a3544052428813735217175815317212076537011910246120765370121495161207653701240215512076537012472131
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00309316719316764194304256002424213120x7f820d5954000x7f8101a3548052428812508963160111446812076537012493200120765370127227941207653701285319412076537012857968
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00329316719316764194304256002424220160x7f820d5953000x7f8101a354c052428811865378151877017612076537012902471120765370131343131207653701326711312076537013272179
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00349316719316764194304256002424227200x7f820d595a000x7f8101a3550052428812904609165183055612076537013335076120765370135442321207653701367303212076537013677733
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00369316719316764194304256002824236800x7f820d5959000x7f8101a3554052428813326940170583662412076537013729960120765370139514311207653701420983012076537014281426
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00389316719316764194304256002824243840x7f820d5958000x7f8101a3558052428814016563179408930012076537014304209120765370145391091207653701479206812076537014861345
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00409316719316764194304256002424250880x7f820d5957000x7f8101a355c052428812453533159410304012076537014885710120765370151301471207653701526022712076537015265096
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00429316719316764194304256002424257920x7f820d5956000x7f8101a3560052428811823515151343871212076537015309529120765370155314261207653701566486612076537015669879
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00449316719316764194304256002424264960x7f820d5955000x7f8101a3564052428813009055166520506412076537015731223120765370159386251207653701606742512076537016072638
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00469316719316764194304256002824277120x7f820d5954000x7f8101a3568052428813728992175729325612076537016114786120765370163467841207653701660550312076537016674478
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00489316719316764194304256002824284160x7f820d5953000x7f8101a356c052428814176355181454795212076537016694795120765370169261421207653701717862112076537017249808
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00509316719316764194304256002424291200x7f820d595a000x7f8101a3570052428812000157153596206812076537017277078120765370175063001207653701763830012076537017643230
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00529316719316764194304256002424300800x7f820d5959000x7f8101a3574052428812107321154968784812076537017694325120765370179091791207653701804245912076537018047962
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00549316719316764194304256002424307840x7f820d5958000x7f8101a3578052428812002481153639230012076537018108966120765370183227781207653701845445812076537018459318
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00569316719316764194304256002824320000x7f820d5957000x7f8101a357c052428813300232170237583212076537018508780120765370187392571207653701899781612076537019066878
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00589316719316764194304256002824329600x7f820d5956000x7f8101a3580052428813638264174571328012076537019087336120765370193214951207653701957349412076537019642609
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00609316719316764194304256002424339200x7f820d5955000x7f8101a3584052428813304502170297709612076537019662025120765370198901331207653702001701312076537020022014
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00629316719316764194304256002424348800x7f820d5954000x7f8101a3588052428810787214138072676012076537020071917120765370202904521207653702042869212076537020433440
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00649316719316764194304256002424358400x7f820d5953000x7f8101a358c052428812889254164986464012076537020496016120765370207042111207653702083221112076537020837030
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00669316719316764194304256002824373120x7f820d595a000x7f8101a3590052428814166125181326280012076537020886603120765370211142901207653702136564912076537021436746
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00689316719316764194304256002824382720x7f820d5959000x7f8101a3594052428813076060167365558412076537021456433120765370216856481207653702194180712076537022021484
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00709316719316764194304256002424392320x7f820d5958000x7f8101a3598052428811865526151878395212076537022040339120765370222714061207653702240420612076537022409155
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00729316719316764194304256002424401920x7f820d5957000x7f8101a359c052428811035340141249061612076537022460260120765370226818051207653702281796512076537022822684
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00749316719316764194304256002424411520x7f820d5956000x7f8101a35a0052428812250772156812887212076537022883507120765370230986041207653702322964412076537023234680
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00769316719316764194304256002824426240x7f820d5955000x7f8101a35a4052428814123077180774640412076537023285405120765370235032431207653702376724212076537023836349
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00789316719316764194304256002824435840x7f820d5954000x7f8101a35a8052428814205139181827497612076537023855705120765370240971611207653702434788012076537024419033
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00809316719316764194304256002424445440x7f820d5953000x7f8101a35ac052428813116252167889471612076537024439401120765370246699591207653702479779912076537024802647
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00829316719316764194304256002424457600x7f820d595a000x7f8101a35b0052428811853180151718946012076537024853451120765370250728381207653702520563812076537025210866
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00849316719316764194304256002424467200x7f820d5959000x7f8101a35b4052428813137811168158583612076537025271329120765370254765171207653702560531712076537025610339
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00869316719316764194304256002824484480x7f820d5958000x7f8101a35b8052428812530281160387360812076537025658579120765370258718761207653702613171512076537026201729
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00889316719316764194304256002824494080x7f820d5957000x7f8101a35bc052428813561484173584434012076537026223290120765370264517141207653702670467312076537026773864
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00909316719316764194304256002424503680x7f820d5956000x7f8101a35c0052428812885465164937120012076537026791927120765370270390731207653702716851212076537027173407
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00929316719316764194304256002424515840x7f820d5955000x7f8101a35c4052428811421633146197725612076537027219823120765370274496311207653702758611112076537027590893
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00949316719316764194304256002424525440x7f820d5954000x7f8101a35c8052428813346675170838974812076537027651616120765370278577901207653702798499012076537027989876
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00969316719316764194304256002824542720x7f820d5953000x7f8101a35cc052428813057516167133910812076537028034488120765370282555491207653702851682812076537028587297
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00989316719316764194304256002824554880x7f820d595a000x7f8101a35d0052428813927985178275788812076537028607324120765370288329871207653702908802712076537029159882
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001009316719316764194304256002424567040x7f820d5959000x7f8101a35d4052428812262502156958880812076537029177505120765370294073861207653702953890512076537029543746
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001029316719316764194304256002424581760x7f820d5958000x7f8101a35d8052428810766993137814004012076537029593639120765370298048241207653702994226412076537029946976
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001049316719316764194304256002424593920x7f820d5957000x7f8101a35dc052428812460249159486070812076537030013901120765370302225831207653703035410312076537030358852
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001069316719316764194304256002824613760x7f820d5956000x7f8101a35e0052428811574719148159638012076537030410188120765370306227421207653703088770112076537030957105
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001089316719316764194304256002824625920x7f820d5955000x7f8101a35e4052428813925416178247872412076537030975910120765370312246601207653703147682012076537031547303
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001109316719316764194304256002424638080x7f820d5954000x7f8101a35e8052428812431998159130892012076537031572119120765370318030591207653703193425812076537031938991
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001129316719316764194304256002424652800x7f820d5953000x7f8101a35ec05242889470204121209896812076537031989325120765370322193771207653703235889712076537032363822
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001149316719316764194304256002424664960x7f820d595a000x7f8101a35f0052428812349368158071216812076537032426879120765370326280161207653703275873612076537032763665
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001169316719316764194304256002824684800x7f820d5959000x7f8101a35f4052428812205000156222497612076537032815241120765370330364951207653703329649412076537033360916
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001189316719316764194304256002824696960x7f820d5958000x7f8101a35f8052428813408863171626734812076537033385843120765370336187331207653703387089312076537033921619
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001209316719316764194304256002424709120x7f820d5957000x7f8101a35fc052428812132337155285036012076537033946045120765370341425721207653703427473112076537034278894
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001229316719316764194304256002424723840x7f820d5956000x7f8101a360005242887901381101128826812076537034329157120765370345056111207653703464193012076537034646157
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001249316719316764194304256002424736000x7f820d5955000x7f8101a3604052428812435176159163892412076537034709455120765370348742501207653703500576912076537035010294
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001269316719316764194304256002824758400x7f820d5954000x7f8101a3608052428811989327153461811612076537035058224120765370352446491207653703550512812076537035555829
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001289316719316764194304256002824770560x7f820d5953000x7f8101a360c052428813007964166498551212076537035580395120765370357636871207653703601616612076537036066599
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001309316719316764194304256002424782720x7f820d595a000x7f8101a3610052428812590944161159554812076537036090484120765370362752061207653703640528512076537036409497
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001329316719316764194304256002424800000x7f820d5959000x7f8101a36140524288684179287570055612076537036459260120765370366379241207653703678160412076537036785737
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001349316719316764194304256002424812160x7f820d5958000x7f8101a3618052428812856824164571442812076537036845238120765370370083231207653703713760312076537037141679
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001369316719316764194304256002824834560x7f820d5957000x7f8101a361c052428814168224181345917612076537037192263120765370373716821207653703763392212076537037684839
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001389316719316764194304256002824849280x7f820d5956000x7f8101a3620052428813053157167073576012076537037708343120765370378945611207653703814672012076537038197783
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001409316719316764194304256002424864000x7f820d5955000x7f8101a3624052428812189637156018493612076537038225816120765370384123191207653703854431912076537038548426
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001429316719316764194304256002424881280x7f820d5954000x7f8101a36280524288537516368803967612076537038598669120765370387995181207653703894831812076537038952187
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001449316719316764194304256002424896000x7f820d5953000x7f8101a362c052428811182771143143504012076537039037556120765370392124771207653703934751712076537039351359
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001469316719316764194304256002824920960x7f820d595a000x7f8101a3630052428813300122170242723612076537039400491120765370395793561207653703984671512076537039894359
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001489316719316764194304256002824935680x7f820d5959000x7f8101a3634052428813163914168501948812076537039921009120765370401281541207653704038143412076537040431689
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001509316719316764194304256002424950400x7f820d5958000x7f8101a3638052428812123514155189095212076537040463378120765370406353531207653704076863212076537040772483
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001529316719316764194304256002424967680x7f820d5957000x7f8101a363c0524288515573065988892812076537040831563120765370410057521207653704116351112076537041167297
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001549316719316764194304256002424982400x7f820d5956000x7f8101a3640052428812479243159727452412076537041231577120765370414113511207653704154271012076537041546623
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015693167193167641943042560028241007360x7f820d5955000x7f8101a3644052428812244800156726824812076537041595894120765370417702291207653704203470912076537042083481
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015893167193167641943042560028241022080x7f820d5954000x7f8101a3648052428813934187178350853612076537042119869120765370422980681207653704255822712076537042605563
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016093167193167641943042560024241036800x7f820d5953000x7f8101a364c052428812662941162089001612076537042632433120765370428070261207653704293694612076537042940806
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016293167193167641943042560024241056640x7f820d595a000x7f8101a36500524288367407147016300812076537042990539120765370431751851207653704334126512076537043344998
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016493167193167641943042560024241071360x7f820d5959000x7f8101a3654052428812560686160773402812076537043408476120765370435825441207653704371230412076537043716369
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016693167193167641943042560028241098880x7f820d5958000x7f8101a365805242889566527122451454812076537043764689120765370439455831207653704421006212076537044257936
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016893167193167641943042560028241113600x7f820d5957000x7f8101a365c052428813574083173751334412076537044278074120765370444763021207653704477214112076537044821575
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017093167193167641943042560024241128320x7f820d5956000x7f8101a3660052428812941392165645075212076537044855778120765370450404601207653704516990012076537045173840
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017293167193167641943042560024241148160x7f820d5955000x7f8101a36640524288379656348589560012076537045223322120765370453961391207653704557069812076537045574545
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017493167193167641943042560024241162880x7f820d5954000x7f8101a3668052428812860157164612693612076537045635398120765370458079781207653704593773712076537045941628
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017693167193167641943042560028241190400x7f820d5953000x7f8101a366c05242888808066112741514012076537045989026120765370461759771207653704643325612076537046481262
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017893167193167641943042560028241207680x7f820d595a000x7f8101a3670052428813987492179031914412076537046500828120765370466924551207653704694205412076537046989237
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018093167193167641943042560024241224960x7f820d5959000x7f8101a3674052428811869746151936455612076537047022769120765370472079741207653704734205312076537047346090
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018293167193167641943042560024241247360x7f820d5958000x7f8101a36780524288367604147043904012076537047393098120765370475671731207653704774989212076537047756043
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018493167193167641943042560024241264640x7f820d5957000x7f8101a367c052428810235098131006880812076537047813851120765370479828511207653704812349112076537048127554
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018693167193167641943042560020241279360x7f820d5956000x7f8101a36800524288405903551953392812076537048176345120765370483574101207653704862204912076537048670624
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018893167193167641943042560028241296640x7f820d5955000x7f8101a3684052428813498901172788520812076537048695220120765370488740491207653704913916812076537049189900
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019093167193167641943042560024241313920x7f820d5954000x7f8101a3688052428812079436154615767212076537049216259120765370494026871207653704953596712076537049539531
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019293167193167641943042560024241336320x7f820d5953000x7f8101a368c0524288366896446956238012076537049587670120765370497532461207653704994540612076537049993976
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019493167193167641943042560024241353600x7f820d595a000x7f8101a3690052428811740357150270269612076537050040563120765370502170851207653705035052412076537050354486
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019693167193167641943042560020241368320x7f820d5959000x7f8101a36940524288291033937253888012076537050396424120765370505823641207653705086764312076537050915129
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019893167193167641943042560028241385600x7f820d5958000x7f8101a3698052428813871266177548948012076537050935136120765370511295621207653705137836112076537051428144
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020093167193167641943042560024241402880x7f820d5957000x7f8101a369c052428810902850139550758412076537051457759120765370516252411207653705176236012076537051766473
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020293167193167641943042560024241427840x7f820d5956000x7f8101a36a00524288333933342737326412076537051814793120765370519852401207653705219563912076537052218053
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020493167193167641943042560024241447680x7f820d5955000x7f8101a36a4052428810729796137336520412076537052275480120765370524513181207653705259099812076537052595194
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020693167193167641943042560020241457280x7f820d5954000x7f8101a36a80524288256739732858828812076537052639166120765370528196371207653705312619612076537053177948
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020893167193167641943042560028241477120x7f820d5953000x7f8101a36ac052428814087651180317986412076537053202885120765370533840921207653705364329212076537053696333
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021093167193167641943042560024241496960x7f820d595a000x7f8101a36b0052428810511919134549204012076537053718624120765370538997701207653705403737012076537054040803
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021293167193167641943042560024241521920x7f820d5959000x7f8101a36b40524288344899344133609612076537054089083120765370542613691207653705448968912076537054537557
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021493167193167641943042560024241541760x7f820d5958000x7f8101a36b8052428810589795135551985212076537054581259120765370547535281207653705489128812076537054894872
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021693167193167641943042560020241556480x7f820d5957000x7f8101a36bc0524288247178731644552012076537054943132120765370551208871207653705545048712076537055499136
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021893167193167641943042560028241576320x7f820d5956000x7f8101a36c0052428813426249171856283612076537055526437120765370557053661207653705596856612076537056018392
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022093167193167641943042560024241596160x7f820d5955000x7f8101a36c4052428811301734144652470012076537056044290120765370562252051207653705636104512076537056364305
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022293167193167641943042560024241623680x7f820d5954000x7f8101a36c80524288349078944677702012076537056412325120765370565861641207653705683288412076537056880816
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022493167193167641943042560024241646080x7f820d5953000x7f8101a36cc05242889570521122512466812076537056925479120765370571044031207653705724568312076537057249001
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022693167193167641943042560020241663360x7f820d595a000x7f8101a36d00524288237231830359884812076537057292863120765370574740021207653705785000212076537057897387
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022893167193167641943042560028241685760x7f820d5959000x7f8101a36d4052428812464562159542859212076537057924538120765370581002411207653705835960012076537058408197
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023093167193167641943042560024241708160x7f820d5958000x7f8101a36d805242889076426116174608412076537058435909120765370586135201207653705875528012076537058759080
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023293167193167641943042560024241740800x7f820d5957000x7f8101a36dc0524288333856042718301612076537058808111120765370589837591207653705926407912076537059312970
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023493167193167641943042560024241765760x7f820d5956000x7f8101a36e005242888169712104580321212076537059355399120765370595290381207653705967127812076537059674934
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023693167193167641943042560020241777920x7f820d5955000x7f8101a36e40524288235364130127737212076537059723634120765370598995971207653706032567612076537060373934
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023893167193167641943042560028241802880x7f820d5954000x7f8101a36e805242889843291125986691612076537060400633120765370605807161207653706084311512076537060890996
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024093167193167641943042560024241827840x7f820d5953000x7f8101a36ec05242887934379101556127612076537060915010120765370611032751207653706124007412076537061243822
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024293167193167641943042560024241863040x7f820d595a000x7f8101a36f00524288341439443699479612076537061294446120765370614605541207653706177607312076537061824292
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024493167193167641943042560024241893120x7f820d5959000x7f8101a36f40524288324302941493644812076537061869295120765370620455131207653706219783212076537062201594
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024693167193167641943042560020241907840x7f820d5958000x7f8101a36f80524288230438629499494012076537062243211120765370624349521207653706295319112076537063004657
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024893167193167641943042560028241937920x7f820d5957000x7f8101a36fc05242888029014102772394412076537063034483120765370632019901207653706350166912076537063552536
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025093167193167641943042560024241968000x7f820d5956000x7f8101a37000524288323046041341808012076537063581490120765370637715891207653706392646912076537063929728
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025293167193167641943042560024242010880x7f820d5955000x7f8101a37040524288329024942109737212076537063977818120765370641509481207653706453734712076537064585017
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025493167193167641943042560024242046080x7f820d5954000x7f8101a37080524288356163245597793212076537064625312120765370647963871207653706497382612076537064977427
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025693167193167641943042560020242060800x7f820d5953000x7f8101a370c0524288232106529702508812076537065030806120765370651941461207653706580678412076537065857855
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025893167193167641943042560028242096000x7f820d595a000x7f8101a37100524288409277152394381212076537065882991120765370660760641207653706643238312076537066481665
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026093167193167641943042560024242131200x7f820d5959000x7f8101a37140524288328307842029028412076537066509306120765370666899831207653706686854212076537066871941
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026293167193167641943042560024242181760x7f820d5958000x7f8101a37180524288401122851341972412076537066914841120765370671013421207653706755814112076537067607730
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026493167193167641943042560024242222080x7f820d5957000x7f8101a371c0524288308640539505136412076537067650379120765370678231001207653706802310012076537068072735
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026693167193167641943042560020242239360x7f820d5956000x7f8101a37200524288234363129987700412076537068103281120765370682922191207653706900437812076537069051906
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026893167193167641943042560028242279680x7f820d5955000x7f8101a37240524288351323144972050812076537069071342120765370692563771207653706965525612076537069702486
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027093167193167641943042560024242320000x7f820d5954000x7f8101a37280524288328896642104897212076537069724427120765370699050161207653707010885512076537070158925
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027293167193167641943042560024242378240x7f820d5953000x7f8101a372c0524288436127455825812012076537070178301120765370703614951207653707088853412076537070938746
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027493167193167641943042560024242423680x7f820d595a000x7f8101a37300524288319085140841081612076537070978430120765370711526931207653707141157212076537071460717
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027693167193167641943042560020242435840x7f820d5959000x7f8101a37340524288233268529866993612076537071479061120765370716640521207653707246629012076537072515609
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027893167193167641943042560028242481280x7f820d5958000x7f8101a37380524288345054544172545612076537072538942120765370727286901207653707314932912076537073198138
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028093167193167641943042560024242526720x7f820d5957000x7f8101a373c0524288310846139791115212076537073223355120765370734058081207653707363236812076537073680135
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028293167193167641943042560024242592640x7f820d5956000x7f8101a37400524288449261357501091612076537073712776120765370738853271207653707448388612076537074534885
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028493167193167641943042560024242648320x7f820d5955000x7f8101a37440524288328708542071385612076537074580450120765370747541251207653707502484512076537075073777
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028693167193167641943042560020242663040x7f820d5954000x7f8101a37480524288230598429518209612076537075098513120765370752800441207653707626740212076537076316098
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028893167193167641943042560028242718720x7f820d5953000x7f8101a374c0524288331011842367757212076537076341966120765370765325211207653707704932012076537077097722
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029093167193167641943042560024242774400x7f820d595a000x7f8101a37500524288339815643496522412076537077131816120765370773038801207653707760915912076537077657343
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029293167193167641943042560012242799360x7f820d5959000x7f8101a37540524288219880128144769212076537077691807120765370778629191207653707860163712076537078653045
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029493167193167641943042560024242865280x7f820d5958000x7f8101a37580524288328133442001315612076537078700173120765370788734761207653707919091612076537079240929
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029693167193167641943042560020242880000x7f820d5957000x7f8101a375c0524288228106229194636412076537079265945120765370794536351207653708062547312076537080673754
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029893167193167641943042560032242945920x7f820d5956000x7f8101a37600524288327765441953633612076537080699312120765370808873921207653708149875112076537081548972
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030093167193167641943042560024243011840x7f820d5955000x7f8101a37640524288332642642579193612076537081574089120765370817637101207653708208227012076537082132197
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030293167193167641943042560012243049600x7f820d5954000x7f8101a37680524288223311728591862812076537082162814120765370823387491207653708321810712076537083267408
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030493167193167641943042560024243136000x7f820d5953000x7f8101a376c0524288328060141992834412076537083314145120765370834837061207653708389314612076537083941402
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030693167193167641943042560020243148160x7f820d595a000x7f8101a37700524288235044030084159212076537083965417120765370841632251207653708571458212076537085766818
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030893167193167641943042560020243175680x7f820d5959000x7f8101a37740524288228826329294550012076537085793077120765370859753811207653708677233912076537086822922
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031093167193167641943042560012243203200x7f820d5958000x7f8101a37780524288215371127573837612076537086848490120765370870372991207653708745201812076537087502296
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031293167193167641943042560012243240960x7f820d5957000x7f8101a377c0524288231814429674052412076537087526932120765370877150571207653708887521512076537088925383
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031493167193167641943042560012243288960x7f820d5956000x7f8101a37800524288224171628689461212076537088968353120765370891446541207653708993041312076537089982199
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031693167193167641943042560020243301120x7f820d5955000x7f8101a37840524288261423733452959612076537090021382120765370901940921207653709324736612076537093298057
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031893167193167641943042560020243328640x7f820d5954000x7f8101a37880524288231095929567725212076537093323414120765370935097651207653709505424212076537095104016
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032093167193167641943042560012243356160x7f820d5953000x7f8101a378c0524288231913929677490412076537095135775120765370953083211207653709609839912076537096147156
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032293167193167641943042560012243393920x7f820d595a000x7f8101a37900524288247051331606406012076537096178144120765370963451191207653709862639412076537098675920
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032493167193167641943042560012243441920x7f820d5959000x7f8101a37940524288239156030613951212076537098723479120765370988953531207653710043039012076537100481950
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032693167193167641943042560020243454080x7f820d5958000x7f8101a37980524288295138337781627612076537100509471120765371006881501207653710674653712076537106797798
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032893167193167641943042560020243481600x7f820d5957000x7f8101a379c0524288347757144508144812076537106823726120765371070105361207653711005500912076537110109799
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033093167193167641943042560012243509120x7f820d5956000x7f8101a37a00524288250644932077240812076537110133613120765371103231691207653711186236612076537111911390
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332931671931676419430425600122400x7f820d5955000x7f8101a37a40524288253010832391556812076537111936436120765371121280661207653711665589712076537116710397