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

43 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_SMEMSQ_INST_LEVEL_SMEMSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000885650885655335544322560083264640x00x7f3db28041804194304315078640322060812075643646573035120756438910532171207564389137433512075643891492447
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00288565088565532768256002424124800x00x7f3db283510051221880277920812075643906340522120756439066465781207564390665313812075643906665255
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0048856508856554194304256002424129280x7f3ebe4d99000x7f3db2835140655361962322507052012075643906724375120756439069377771207564390707761612075643907082491
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0068856508856554194304256003624136320x7f3ebe4d98000x7f3db2835180655361512981938737612075643907149044120756439073209751207564390757729312075643907646779
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0088856508856554194304256002824140800x7f3ebe4d97000x7f3db28351c0655361958542511240012075643907680732120756439078700921207564390812737112075643908197372
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00108856508856554194304256002424145280x7f3ebe4d96000x7f3db2835200655361725962204457612075643908217700120756439084065691207564390854048912075643908544267
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00128856508856554194304256002424149760x7f3ebe4d95000x7f3db2835240655361754382234504812075643908593859120756439087640081207564390889792712075643908901922
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00148856508856554194304256002424154240x7f3ebe4d94000x7f3db28352801310722439923124323212075643908981981120756439091510461207564390927904512075643909282569
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00168856508856554194304256002824161280x7f3ebe4d93000x7f3db28352c01310722168662780243212075643909332733120756439095051241207564390975792312075643909799430
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00188856508856554194304256002824168320x7f3ebe4d9a000x7f3db2835300655361717702195024012075643909826751120756439100019211207564391025584012075643910297105
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00208856508856554194304256002424175360x7f3ebe4d99000x7f3db28353401310722439143120732812075643910321811120756439105217591207564391065471812075643910658246
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00228856508856554194304256002424182400x7f3ebe4d98000x7f3db28353801310722429963104264012075643910708139120756439108779171207564391101679612075643911021361
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00248856508856554194304256002424189440x7f3ebe4d97000x7f3db28353c01310722471283157448812075643911089217120756439112564751207564391138751512075643911391709
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00268856508856554194304256002824199040x7f3ebe4d96000x7f3db28354001310722012062567643212075643911442183120756439116035131207564391186575212075643911932785
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00288856508856554194304256002824206080x7f3ebe4d95000x7f3db2835440655361771622253158412075643911966157120756439121497511207564391240958912075643912476826
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00308856508856554194304256002424213120x7f3ebe4d94000x7f3db28354801310722373123046128812075643912502984120756439126889481207564391281998712075643912824141
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00328856508856554194304256002424220160x7f3ebe4d93000x7f3db28354c01310722527363259869612075643912872611120756439130468661207564391318270612075643913186525
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00348856508856554194304256002424227200x7f3ebe4d9a000x7f3db28355001310722402283085623212075643913249902120756439134172641207564391354686412075643913550872
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00368856508856554194304256002824236800x7f3ebe4d99000x7f3db28355401310722204622822466412075643913599462120756439137691031207564391402654112075643914093270
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00388856508856554194304256002824243840x7f3ebe4d98000x7f3db2835580655361715002194773612075643914122234120756439143118201207564391456701912075643914634145
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00408856508856554194304256002424250880x7f3ebe4d97000x7f3db28355c01310722693243436737612075643914661947120756439148460571207564391502237612075643915027135
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00428856508856554194304256002424257920x7f3ebe4d96000x7f3db28356001310722657703406380012075643915085784120756439152511751207564391538221512075643915386082
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00448856508856554194304256002424264960x7f3ebe4d95000x7f3db28356401310722445843132944812075643915448438120756439156135731207564391574781312075643915751782
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00468856508856554194304256002824277120x7f3ebe4d94000x7f3db28356801310722100262683242412075643915799350120756439159697321207564391622941012075643916296855
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00488856508856554194304256002824284160x7f3ebe4d93000x7f3db28356c0655361673902141617612075643916323374120756439165041291207564391675948812075643916826439
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00508856508856554194304256002424291200x7f3ebe4d9a000x7f3db28357001310722720563464868012075643916851456120756439170399661207564391717356612075643917177552
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00528856508856554194304256002424300800x7f3ebe4d99000x7f3db28357401310722492263184237612075643917227775120756439173950051207564391753196412075643917535727
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00548856508856554194304256002424307840x7f3ebe4d98000x7f3db28357801310722481863180387212075643917596891120756439177601231207564391789596212075643917899884
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00568856508856554194304256002824320000x7f3ebe4d97000x7f3db28357c01310722001702563443212075643917947683120756439181278011207564391838620012075643918428256
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00588856508856554194304256002824329600x7f3ebe4d96000x7f3db2835800655361725882204832012075643918456699120756439186321181207564391888923712075643918956498
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00608856508856554194304256002424339200x7f3ebe4d95000x7f3db28358401310722413103073158412075643918985772120756439191650761207564391929499512075643919299415
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00628856508856554194304256002424348800x7f3ebe4d94000x7f3db28358801310722512823216319212075643919352023120756439195137141207564391965403312075643919658052
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00648856508856554194304256002424358400x7f3ebe4d93000x7f3db28358c01310722389083068673612075643919719536120756439198876321207564392001851212075643920022329
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00668856508856554194304256002824373120x7f3ebe4d9a000x7f3db28359001310722047182623793612075643920071430120756439202445901207564392050218912075643920569065
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00688856508856554194304256002824382720x7f3ebe4d99000x7f3db2835940655361758662253281612075643920592057120756439207729081207564392102666712075643921094541
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00708856508856554194304256002424392320x7f3ebe4d98000x7f3db28359801310722506463206920812075643921119137120756439213095451207564392143978512075643921443901
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00728856508856554194304256002424401920x7f3ebe4d97000x7f3db28359c01310722413303079404812075643921491920120756439216610631207564392179658312075643921800543
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00748856508856554194304256002424411520x7f3ebe4d96000x7f3db2835a001310722563023276952812075643921862609120756439220327421207564392216634112075643922170451
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00768856508856554194304256002824426240x7f3ebe4d95000x7f3db2835a401310722003002551328812075643922218610120756439223935401207564392264921812075643922715394
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00788856508856554194304256002824435840x7f3ebe4d94000x7f3db2835a80655361868882394033612075643922739258120756439229223371207564392317785612075643923247502
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00808856508856554194304256002424445440x7f3ebe4d93000x7f3db2835ac01310722402203077907212075643923273431120756439234631341207564392359353412075643923597303
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00828856508856554194304256002424457600x7f3ebe4d9a000x7f3db2835b001310722648123398986412075643923644821120756439238146531207564392395129212075643923954907
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00848856508856554194304256002424467200x7f3ebe4d99000x7f3db2835b401310722405463089604012075643924020239120756439241842511207564392431817012075643924322110
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00868856508856554194304256002824484480x7f3ebe4d98000x7f3db2835b801310722043562612160012075643924371321120756439245444091207564392481384812075643924880848
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00888856508856554194304256002824494080x7f3ebe4d97000x7f3db2835bc0655361651922118253612075643924908439120756439250898461207564392534280512075643925411624
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00908856508856554194304256002424503680x7f3ebe4d96000x7f3db2835c001310722515043215594412075643925440869120756439256162441207564392574504312075643925749001
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00928856508856554194304256002424515840x7f3ebe4d95000x7f3db2835c401310722408943075685612075643925798814120756439259735221207564392611688112075643926121323
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00948856508856554194304256002424525440x7f3ebe4d94000x7f3db2835c801310722550603261708812075643926183058120756439263495201207564392648231912075643926486863
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00968856508856554194304256002824542720x7f3ebe4d93000x7f3db2835cc01310722093642669911212075643926533740120756439267029581207564392697463712075643927043377
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00988856508856554194304256002824554880x7f3ebe4d9a000x7f3db2835d00655361749362250444812075643927072501120756439272504761207564392750023412075643927567982
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001008856508856554194304256002424567040x7f3ebe4d99000x7f3db2835d401310722437863117874412075643927591175120756439277690331207564392789767212075643927901532
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001028856508856554194304256002424581760x7f3ebe4d98000x7f3db2835d801310722504623195264012075643927951194120756439281224711207564392826487112075643928269225
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001048856508856554194304256002424593920x7f3ebe4d97000x7f3db2835dc01310722414303104357612075643928329858120756439284944691207564392862934912075643928633242
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001068856508856554194304256002824613760x7f3ebe4d96000x7f3db2835e001310722508843223263212075643928682163120756439288474281207564392911990612075643929188033
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001088856508856554194304256002824625920x7f3ebe4d95000x7f3db2835e40655361593902043814412075643929212298120756439293939851207564392964838412075643929714401
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001108856508856554194304256002424638080x7f3ebe4d94000x7f3db2835e801310722441963114496012075643929738866120756439299203821207564393005126212075643930055575
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001128856508856554194304256002424652800x7f3ebe4d93000x7f3db2835ec01310722401723088276012075643930101611120756439302770211207564393041558012075643930419682
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001148856508856554194304256002424664960x7f3ebe4d9a000x7f3db2835f001310722498983191581612075643930483270120756439306459791207564393077637812075643930780552
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001168856508856554194304256002824684800x7f3ebe4d99000x7f3db2835f401310722415183082022412075643930827500120756439309926971207564393126261612075643931331065
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001188856508856554194304256002824696960x7f3ebe4d98000x7f3db2835f80655361755082250414412075643931355531120756439315338141207564393179333312075643931860630
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001208856508856554194304256002424709120x7f3ebe4d97000x7f3db2835fc01310722570563287934412075643931888401120756439320651721207564393219797112075643932201984
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001228856508856554194304256002424723840x7f3ebe4d96000x7f3db28360001310722461663133271212075643932251666120756439324163701207564393255588912075643932560140
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001248856508856554194304256002424736000x7f3ebe4d95000x7f3db28360401310722437363114448012075643932621093120756439327803681207564393291252712075643932916692
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001268856508856554194304256002824758400x7f3ebe4d94000x7f3db28360801310722186102789997612075643932964341120756439331419661207564393341108512075643933460994
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001288856508856554194304256002824770560x7f3ebe4d93000x7f3db28360c0655361659922127416012075643933483616120756439336678841207564393392660212075643933948600
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001308856508856554194304256002424782720x7f3ebe4d9a000x7f3db28361001310722415683097986412075643933991400120756439341566811207564393429156112075643934295785
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001328856508856554194304256002424800000x7f3ebe4d99000x7f3db28361401310722026402580156012075643934343504120756439345134791207564393466115912075643934665172
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001348856508856554194304256002424812160x7f3ebe4d98000x7f3db28361801310722548103263876012075643934726325120756439348845181207564393501955712075643935023668
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001368856508856554194304256002824834560x7f3ebe4d97000x7f3db28361c01310722010382567679212075643935072348120756439352422761207564393551139512075643935559424
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001388856508856554194304256002824849280x7f3ebe4d96000x7f3db2836200655361866622383312012075643935585753120756439357611531207564393602323212075643936049975
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001408856508856554194304256002424864000x7f3ebe4d95000x7f3db28362401310722423523081545612075643936093416120756439362560311207564393639091012075643936395007
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001428856508856554194304256002424881280x7f3ebe4d94000x7f3db28362801310722033802627338412075643936442926120756439366109091207564393676306812075643936767258
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001448856508856554194304256002424896000x7f3ebe4d93000x7f3db28362c01310722409043075228012075643936845704120756439370038671207564393713746612075643937141724
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001468856508856554194304256002824920960x7f3ebe4d9a000x7f3db28363001310722064762646164812075643937190595120756439373630651207564393763602412075643937685886
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001488856508856554194304256002824935680x7f3ebe4d99000x7f3db2836340655361664322122073612075643937709189120756439378877031207564393814066112075643938192307
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001508856508856554194304256002424950400x7f3ebe4d98000x7f3db28363801310722466983158124812075643938219547120756439383979401207564393853409912075643938538210
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001528856508856554194304256002424967680x7f3ebe4d97000x7f3db28363c01310722398763079244012075643938586069120756439387526581207564393891185812075643938915651
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001548856508856554194304256002424982400x7f3ebe4d96000x7f3db28364001310722717363464080012075643938977696120756439391428961207564393928017612075643939284406
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015688565088565541943042560028241007360x7f3ebe4d95000x7f3db28364401310721995582550035212075643939331073120756439395011351207564393976881312075643939792971
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015888565088565541943042560028241022080x7f3ebe4d94000x7f3db2836480655361721302200872012075643939839328120756439400148921207564394027601112075643940323968
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016088565088565541943042560024241036800x7f3ebe4d93000x7f3db28364c01310722392703086326412075643940348434120756439405380891207564394067184912075643940676133
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016288565088565541943042560024241056640x7f3ebe4d9a000x7f3db28365001310722385823059449612075643940724723120756439409049681207564394110912712075643941158740
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016488565088565541943042560024241071360x7f3ebe4d99000x7f3db28365401310722460863165455212075643941196129120756439413704051207564394149856512075643941502669
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016688565088565541943042560028241098880x7f3ebe4d98000x7f3db28365801310721971242527390412075643941545889120756439417268841207564394198928212075643942017816
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016888565088565541943042560028241113600x7f3ebe4d97000x7f3db28365c0655361726202208405612075643942059243120756439422297611207564394248736012075643942535148
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017088565088565541943042560024241128320x7f3ebe4d96000x7f3db28366001310722556363265817612075643942559733120756439427454391207564394288159812075643942886200
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017288565088565541943042560024241148160x7f3ebe4d95000x7f3db28366401310722679363421801612075643942935742120756439431179171207564394329247612075643943296913
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017488565088565541943042560024241162880x7f3ebe4d94000x7f3db28366801310722405323073968812075643943360211120756439435255951207564394366031412075643943664406
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017688565088565541943042560028241190400x7f3ebe4d93000x7f3db28366c01310722107482685124812075643943712736120756439438892731207564394415247212075643944200803
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017888565088565541943042560028241207680x7f3ebe4d9a000x7f3db2836700655361628302077613612075643944221171120756439444131101207564394467726912075643944723785
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018088565088565541943042560024241224960x7f3ebe4d99000x7f3db28367401310722428063103164012075643944749182120756439449396681207564394507870712075643945083223
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018288565088565541943042560024241247360x7f3ebe4d98000x7f3db28367801310722421883088665612075643945122837120756439453108661207564394549342512075643945497653
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018488565088565541943042560024241264640x7f3ebe4d97000x7f3db28367c01310722427583119610412075643945558657120756439457238241207564394586718312075643945871418
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018688565088565541943042560020241279360x7f3ebe4d96000x7f3db28368001310722425543106212812075643945910801120756439460990221207564394636558112075643946413475
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018888565088565541943042560028241296640x7f3ebe4d95000x7f3db2836840655361852302365051212075643946441097120756439466238191207564394688749812075643946936217
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019088565088565541943042560024241313920x7f3ebe4d94000x7f3db28368801310722396403083017612075643946959901120756439471521371207564394729181612075643947296206
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019288565088565541943042560024241336320x7f3ebe4d93000x7f3db28368c01310722495783185688012075643947336010120756439475202951207564394771245412075643947759587
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019488565088565541943042560024241353600x7f3ebe4d9a000x7f3db28369001310722191562796061612075643947799962120756439479657331207564394810413212075643948108586
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019688565088565541943042560020241368320x7f3ebe4d99000x7f3db28369401310722444363125971212075643948148229120756439483342111207564394861756912075643948643640
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019888565088565541943042560028241385600x7f3ebe4d98000x7f3db2836980655361674302147186412075643948682182120756439488606081207564394912076712075643949148789
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020088565088565541943042560024241402880x7f3ebe4d97000x7f3db28369c01310722527983229858412075643949192891120756439493615661207564394949868512075643949502646
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020288565088565541943042560024241427840x7f3ebe4d96000x7f3db2836a001310722473283150207212075643949542150120756439497252441207564394993660312075643949957582
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020488565088565541943042560024241447680x7f3ebe4d95000x7f3db2836a401310722660443407113612075643950023314120756439501914811207564395033036112075643950334272
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020688565088565541943042560020241457280x7f3ebe4d94000x7f3db2836a801310722378323052864012075643950382261120756439505594801207564395086859812075643950893632
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020888565088565541943042560028241477120x7f3ebe4d93000x7f3db2836ac0655361752422254720012075643950932444120756439511001171207564395135931612075643951387529
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021088565088565541943042560024241496960x7f3ebe4d9a000x7f3db2836b001310722380543063725612075643951435038120756439515997941207564395174091412075643951745485
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021288565088565541943042560024241521920x7f3ebe4d99000x7f3db2836b401310722411783135488012075643951786250120756439519719531207564395220011112075643952227571
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021488565088565541943042560024241541760x7f3ebe4d98000x7f3db2836b801310722406323085760012075643952285769120756439524573901207564395259291012075643952597378
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021688565088565541943042560020241556480x7f3ebe4d97000x7f3db2836bc01310722558483248234412075643952646169120756439528308281207564395316042712075643953188987
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021888565088565541943042560028241576320x7f3ebe4d96000x7f3db2836c00655361621662067885612075643953223091120756439534073051207564395366906412075643953694868
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022088565088565541943042560024241596160x7f3ebe4d95000x7f3db2836c401310722397063075886412075643953740222120756439539072501207564395404965012075643954056880
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022288565088565541943042560024241623680x7f3ebe4d94000x7f3db2836c801310722395303068476812075643954092747120756439542813281207564395452676712075643954550738
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022488565088565541943042560024241646080x7f3ebe4d93000x7f3db2836cc01310722621183354478412075643954608906120756439547781261207564395491924512075643954922720
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022688565088565541943042560020241663360x7f3ebe4d9a000x7f3db2836d001310722423743094745612075643954970308120756439551536441207564395553140312075643955558411
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022888565088565541943042560028241685760x7f3ebe4d99000x7f3db2836d40655361858202380652012075643955599157120756439557642021207564395603332112075643956058370
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023088565088565541943042560024241708160x7f3ebe4d98000x7f3db2836d801310722423943087230412075643956101059120756439562688401207564395641043912075643956414111
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023288565088565541943042560024241740800x7f3ebe4d97000x7f3db2836dc01310722773763548394412075643956462381120756439566505981207564395692995712075643956953995
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023488565088565541943042560024241765760x7f3ebe4d96000x7f3db2836e001310722429003087497612075643957013425120756439571816361207564395732467512075643957328390
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023688565088565541943042560020241777920x7f3ebe4d95000x7f3db2836e401310722576003303163212075643957368405120756439575614741207564395798803312075643958012902
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023888565088565541943042560028241802880x7f3ebe4d94000x7f3db2836e80655361727242210118412075643958049290120756439582209921207564395848963112075643958509555
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024088565088565541943042560024241827840x7f3ebe4d93000x7f3db2836ec01310722607903348552812075643958555331120756439587219501207564395886258912075643958866369
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024288565088565541943042560024241863040x7f3ebe4d9a000x7f3db2836f001310722405623083813612075643958907505120756439590969881207564395941330712075643959440285
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024488565088565541943042560024241893120x7f3ebe4d99000x7f3db2836f401310722524703224748012075643959492673120756439596633861207564395985522512075643959878219
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024688565088565541943042560020241907840x7f3ebe4d98000x7f3db2836f801310722403743081277612075643959921960120756439600969841207564396061618212075643960640906
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024888565088565541943042560028241937920x7f3ebe4d97000x7f3db2836fc0655361705482185364012075643960687343120756439608533011207564396115506012075643961183946
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025088565088565541943042560024241968000x7f3ebe4d96000x7f3db28370001310722418063085838412075643961216546120756439614113791207564396156625812075643961569803
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025288565088565541943042560024242010880x7f3ebe4d95000x7f3db28370401310722380543058836812075643961618153120756439618142571207564396220129612075643962248955
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025488565088565541943042560024242046080x7f3ebe4d94000x7f3db28370801310722403643068892012075643962287216120756439624627351207564396263905412075643962642486
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025688565088565541943042560020242060800x7f3ebe4d93000x7f3db28370c01310722397583041525612075643962682260120756439628675331207564396348001012075643963529114
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025888565088565541943042560028242096000x7f3ebe4d9a000x7f3db2837100655361720802203986412075643963554952120756439637451291207564396407424812075643964122096
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026088565088565541943042560024242131200x7f3ebe4d99000x7f3db28371401310722224342831292012075643964149587120756439643422471207564396452208612075643964525686
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026288565088565541943042560024242181760x7f3ebe4d98000x7f3db28371801310722643103404088012075643964575429120756439647521651207564396522960312075643965277203
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026488565088565541943042560024242222080x7f3ebe4d97000x7f3db28371c01310722498103205253612075643965321575120756439654939221207564396569328212075643965740394
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026688565088565541943042560020242239360x7f3ebe4d96000x7f3db28372001310722339863000379212075643965765090120756439659531201207564396665855812075643966709264
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026888565088565541943042560028242279680x7f3ebe4d95000x7f3db2837240655361754082254792812075643966729071120756439669267171207564396729967512075643967348723
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027088565088565541943042560024242320000x7f3ebe4d94000x7f3db28372801310722417723099662412075643967378478120756439675627141207564396776623312075643967813937
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027288565088565541943042560024242378240x7f3ebe4d93000x7f3db28372c01310722542943243456812075643967833634120756439680321521207564396855839012075643968605909
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027488565088565541943042560024242423680x7f3ebe4d9a000x7f3db28373001310722396323076064812075643968645753120756439688187091207564396904430812075643969094397
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027688565088565541943042560020242435840x7f3ebe4d99000x7f3db28373401310722592143277224012075643969120706120756439692982271207564397009870412075643970148636
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027888565088565541943042560028242481280x7f3ebe4d98000x7f3db2837380655361660482138544012075643970172491120756439703527831207564397077342112075643970823170
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028088565088565541943042560024242526720x7f3ebe4d97000x7f3db28373c01310722534743222121612075643970841514120756439710380601207564397126541912075643971315815
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028288565088565541943042560024242592640x7f3ebe4d96000x7f3db28374001310722409823073004012075643971338207120756439715246181207564397212237612075643972189920
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028488565088565541943042560024242648320x7f3ebe4d95000x7f3db28374401310722504883197463212075643972228441120756439723918141207564397266237312075643972729282
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028688565088565541943042560020242663040x7f3ebe4d94000x7f3db28374801310722388343055959212075643972759488120756439729374121207564397392364812075643973993402
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028888565088565541943042560028242718720x7f3ebe4d93000x7f3db28374c0655361761762252734412075643974026373120756439742055671207564397473772512075643974805220
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029088565088565541943042560024242774400x7f3ebe4d9a000x7f3db28375001310722438883096653612075643974828714120756439750084441207564397528156312075643975350724
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029288565088565541943042560012242799360x7f3ebe4d99000x7f3db28375401310722369363049722412075643975376141120756439755554821207564397629499912075643976362544
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029488565088565541943042560024242865280x7f3ebe4d98000x7f3db28375801310722460043132740812075643976408159120756439765722781207564397688939612075643976956458
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029688565088565541943042560020242880000x7f3ebe4d97000x7f3db28375c01310722378583054991212075643976986153120756439771661951207564397833899012075643978406573
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029888565088565541943042560032242945920x7f3ebe4d96000x7f3db2837600655361773182270933612075643978439945120756439786106691207564397921994712075643979288653
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030088565088565541943042560024243011840x7f3ebe4d95000x7f3db28376401310722596543302658412075643979322566120756439794959461207564397981610412075643979882596
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030288565088565541943042560012243049600x7f3ebe4d94000x7f3db28376801310722511243190472012075643979913975120756439801004231207564398097914012075643981049375
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030488565088565541943042560024243136000x7f3ebe4d93000x7f3db28376c01310722427083089017612075643981093567120756439812576991207564398166857712075643981735299
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030688565088565541943042560020243148160x7f3ebe4d9a000x7f3db28377001310722570363312895212075643981758833120756439819452161207564398349321012075643983561774
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030888565088565541943042560020243175680x7f3ebe4d99000x7f3db2837740655361765522255624812075643983593302120756439837746481207564398457032512075643984637683
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031088565088565541943042560012243203200x7f3ebe4d98000x7f3db28377801310722445303159665612075643984669272120756439848485641207564398526408212075643985333927
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031288565088565541943042560012243240960x7f3ebe4d97000x7f3db28377c01310722413103091824012075643985363202120756439855460011207564398670567712075643986773072
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031488565088565541943042560012243288960x7f3ebe4d96000x7f3db28378001310722436863110288012075643986816823120756439869791161207564398776583212075643987836468
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031688565088565541943042560020243301120x7f3ebe4d95000x7f3db28378401310722432343101003212075643987866684120756439880555911207564399110757912075643991177257
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031888565088565541943042560020243328640x7f3ebe4d94000x7f3db2837880655361696082173313612075643991209377120756439913893381207564399293269212075643993004703
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032088565088565541943042560012243356160x7f3ebe4d93000x7f3db28378c01310722430363124604012075643993048034120756439932128501207564399400164712075643994070564
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032288565088565541943042560012243393920x7f3ebe4d9a000x7f3db28379001310722433523109051212075643994100991120756439942880461207564399657059712075643996639188
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032488565088565541943042560012243441920x7f3ebe4d99000x7f3db28379401310722652603400188812075643996684993120756439968473961207564399838275012075643998452147
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032688565088565541943042560020243454080x7f3ebe4d98000x7f3db28379801310722404403081828812075643998483816120756439986649881207564400471920412075644004787231
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032888565088565541943042560020243481600x7f3ebe4d97000x7f3db28379c0655361812062321955212075644004817437120756440050000031207564400804111112075644008112771
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033088565088565541943042560012243509120x7f3ebe4d96000x7f3db2837a001310722425623089552812075644008142576120756440083249491207564400986526312075644009933394
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332885650885655419430425600122400x7f3ebe4d95000x7f3db2837a401310722536103246331212075644009964402120756440101521421207564401467916412075644014751849