Files
rocm-systems/tests/workloads/Axes1/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.kd000901123901128335544322560083264640x00x7f34bac04180104857611105144142209670412075941073738305120759413198420271207594132016698512075941320278178
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00290112390112832768256002424124800x00x7f34bac3510040961141851460222012075941334761004120759413350620341207594133506859412075941335073605
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0049011239011284194304256002424129280x7f35ead599000x7f34bac3514052428812413352158889120412075941335135089120759413353487531207594133548187212075941335485801
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0069011239011284194304256003624136320x7f35ead598000x7f34bac3518052428813402692171551182012075941335555170120759413357245911207594133597547012075941336049198
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0089011239011284194304256002824140800x7f35ead597000x7f34bac351c052428813545990173390412012075941336080867120759413362693891207594133652378812075941336590725
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00109011239011284194304256002424145280x7f35ead596000x7f34bac3520052428811846202151628910812075941336618556120759413368039461207594133693802612075941336941276
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00129011239011284194304256002424149760x7f35ead595000x7f34bac3524052428812320378157689411612075941336992060120759413371666651207594133729738412075941337300834
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00149011239011284194304256002424154240x7f35ead594000x7f34bac3528052428812661711162072548812075941337380412120759413375516231207594133768170212075941337685018
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00169011239011284194304256002824161280x7f35ead593000x7f34bac352c052428813923625178220651612075941337740571120759413379020211207594133815626012075941338224401
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00189011239011284194304256002824168320x7f35ead59a000x7f34bac3530052428814364290183860180812075941338250970120759413384303391207594133868105812075941338721194
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00209011239011284194304256002424175360x7f35ead599000x7f34bac3534052428812121934155154508012075941338745309120759413389349761207594133906649612075941339070293
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00229011239011284194304256002424182400x7f35ead598000x7f34bac3538052428812295928157396177612075941339121768120759413392965751207594133942905412075941339432706
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00249011239011284194304256002424189440x7f35ead597000x7f34bac353c052428812754550163262085612075941339495172120759413396567331207594133978633212075941339789439
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00269011239011284194304256002824199040x7f35ead596000x7f34bac3540052428813435440171975417212075941339840194120759413400021711207594134025737012075941340324974
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00289011239011284194304256002824206080x7f35ead595000x7f34bac3544052428813925867178259242812075941340349891120759413405341691207594134078600812075941340852705
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00309011239011284194304256002424213120x7f35ead594000x7f34bac3548052428812809035163952377212075941340879635120759413410680861207594134119800612075941341201373
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00329011239011284194304256002424220160x7f35ead593000x7f34bac354c052428812558038160735581212075941341250775120759413414160851207594134154648412075941341549961
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00349011239011284194304256002424227200x7f35ead59a000x7f34bac3550052428813017882166622191612075941341610984120759413417720831207594134190120212075941341904690
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00369011239011284194304256002824236800x7f35ead599000x7f34bac3554052428814287812182882056412075941341953000120759413421320811207594134238568012075941342454352
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00389011239011284194304256002824243840x7f35ead598000x7f34bac3558052428813836888177116408812075941342478867120759413426661591207594134292023812075941342961484
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00409011239011284194304256002424250880x7f35ead597000x7f34bac355c052428812824198164148949212075941342988815120759413431799161207594134330951612075941343313208
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00429011239011284194304256002424257920x7f35ead596000x7f34bac3560052428812501384160022079212075941343358482120759413435451951207594134367719412075941343680671
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00449011239011284194304256002424264960x7f35ead595000x7f34bac3564052428813061932167187455612075941343743187120759413439055131207594134403303212075941344036502
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00469011239011284194304256002824277120x7f35ead594000x7f34bac3568052428814229473182132737612075941344086746120759413442597511207594134451351012075941344580523
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00489011239011284194304256002824284160x7f35ead593000x7f34bac356c052428814281620182809158012075941344606992120759413447867891207594134503910812075941345110338
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00509011239011284194304256002424291200x7f35ead59a000x7f34bac3570052428812216801156386868812075941345135484120759413453175061207594134544854612075941345451953
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00529011239011284194304256002424300800x7f35ead599000x7f34bac3574052428811178209143079628812075941345501034120759413456631051207594134580038412075941345803857
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00549011239011284194304256002424307840x7f35ead598000x7f34bac3578052428812957083165848655212075941345867355120759413460343031207594134616406312075941346168144
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00569011239011284194304256002824320000x7f35ead597000x7f34bac357c052428814211379181901423612075941346218127120759413463970211207594134665270012075941346695053
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00589011239011284194304256002824329600x7f35ead596000x7f34bac3580052428814173967181426981612075941346720981120759413468963791207594134714325812075941347212885
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00609011239011284194304256002424339200x7f35ead595000x7f34bac3584052428811387218145742056812075941347239234120759413474178171207594134755317612075941347556664
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00629011239011284194304256002424348800x7f35ead594000x7f34bac3588052428813140501168198664012075941347605104120759413477730151207594134790213412075941347905623
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00649011239011284194304256002424358400x7f35ead593000x7f34bac358c052428812083419154662662412075941347966917120759413481318931207594134826485312075941348268838
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00669011239011284194304256002824373120x7f35ead59a000x7f34bac3590052428813812879176810190412075941348317608120759413484898121207594134874501012075941348812318
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00689011239011284194304256002824382720x7f35ead599000x7f34bac3594052428813663026174880395212075941348838547120759413490133291207594134927108812075941349341632
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00709011239011284194304256002424392320x7f35ead598000x7f34bac3598052428811935524152768327212075941349368131120759413495459671207594134967876612075941349682425
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00729011239011284194304256002424401920x7f35ead597000x7f34bac359c052428811997706153569697612075941349732328120759413499019651207594135003588412075941350039729
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00749011239011284194304256002424411520x7f35ead596000x7f34bac35a0052428812513785160171882812075941350101924120759413502656431207594135039668312075941350400159
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00769011239011284194304256002824426240x7f35ead595000x7f34bac35a4052428813045409166983785612075941350449450120759413506123621207594135087076112075941350912601
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00789011239011284194304256002824435840x7f35ead594000x7f34bac35a8052428813718177175595183612075941350937588120759413511168391207594135140579812075941351474485
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00809011239011284194304256002424445440x7f35ead593000x7f34bac35ac052428812607261161358648012075941351501345120759413516771571207594135180931612075941351812824
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00829011239011284194304256002424457600x7f35ead59a000x7f34bac35b0052428812281335157211303212075941351862026120759413520363551207594135216883412075941352172513
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00849011239011284194304256002424467200x7f35ead599000x7f34bac35b4052428812200786156179286412075941352233295120759413523939531207594135252595312075941352529586
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00869011239011284194304256002824484480x7f35ead598000x7f34bac35b8052428814159216181232808812075941352578637120759413527371521207594135299219112075941353060603
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00889011239011284194304256002824494080x7f35ead597000x7f34bac35bc052428814265797182600181212075941353084708120759413532633891207594135351426812075941353582122
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00909011239011284194304256002424503680x7f35ead596000x7f34bac35c0052428811014339140982088412075941353600697120759413537851471207594135392194612075941353925510
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00929011239011284194304256002424515840x7f35ead595000x7f34bac35c4052428811574756148157458012075941353974652120759413541441851207594135428098512075941354284748
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00949011239011284194304256002424525440x7f35ead594000x7f34bac35c8052428812231612156560024412075941354347685120759413545110641207594135464306312075941354646540
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00969011239011284194304256002824542720x7f35ead593000x7f34bac35cc052428813401925171540604412075941354698657120759413548581021207594135512626112075941355195771
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00989011239011284194304256002824554880x7f35ead59a000x7f34bac35d0052428814241911182294324412075941355220868120759413554032191207594135565633812075941355724794
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001009011239011284194304256002424567040x7f35ead599000x7f34bac35d4052428812877435164828566812075941355750542120759413559243371207594135605361612075941356057392
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001029011239011284194304256002424581760x7f35ead598000x7f34bac35d8052428811153587142769654012075941356099621120759413562736151207594135640785512075941356411521
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001049011239011284194304256002424593920x7f35ead597000x7f34bac35dc052428811663651149299370812075941356473666120759413566316941207594135676641312075941356769957
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001069011239011284194304256002824613760x7f35ead596000x7f34bac35e0052428813892877177831840412075941356818317120759413569843321207594135725137112075941357320410
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001089011239011284194304256002824625920x7f35ead595000x7f34bac35e4052428814207833181862977612075941357344054120759413575316891207594135777776812075941357845085
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001109011239011284194304256002424638080x7f35ead594000x7f34bac35e8052428812370766158357567612075941357868378120759413580499271207594135818064612075941358184395
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001129011239011284194304256002424652800x7f35ead593000x7f34bac35ec05242888879272113649105212075941358232565120759413583998451207594135853504512075941358538463
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001149011239011284194304256002424664960x7f35ead59a000x7f34bac35f0052428811394146145849194812075941358599867120759413587574441207594135889296312075941358896459
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001169011239011284194304256002824684800x7f35ead599000x7f34bac35f4052428812986316166217536012075941358944428120759413591126421207594135937552112075941359427145
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001189011239011284194304256002824696960x7f35ead598000x7f34bac35f8052428814111739180629964412075941359449336120759413596265601207594135987471812075941359924229
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001209011239011284194304256002424709120x7f35ead597000x7f34bac35fc052428811823209151332629612075941359950057120759413601297571207594136026351712075941360267226
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001229011239011284194304256002424723840x7f35ead596000x7f34bac36000524288735970194200035212075941360316488120759413604823961207594136062063512075941360624270
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001249011239011284194304256002424736000x7f35ead595000x7f34bac3604052428811046478141396358412075941360683881120759413608438341207594136098095312075941360984720
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001269011239011284194304256002824758400x7f35ead594000x7f34bac3608052428811790360150914813612075941361031456120759413612100721207594136147679112075941361526426
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001289011239011284194304256002824770560x7f35ead593000x7f34bac360c052428813937127178391853212075941361549469120759413617267101207594136198158912075941362031685
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001309011239011284194304256002424782720x7f35ead59a000x7f34bac3610052428811716925149976094012075941362057884120759413622331071207594136236574712075941362369323
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001329011239011284194304256002424800000x7f35ead599000x7f34bac36140524288730408593511506412075941362423103120759413625843061207594136272942512075941362732838
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001349011239011284194304256002424812160x7f35ead598000x7f34bac3618052428811969279153196427212075941362793601120759413629531041207594136308606312075941363089822
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001369011239011284194304256002824834560x7f35ead597000x7f34bac361c052428814020291179456838412075941363139394120759413633089421207594136357486112075941363626339
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001389011239011284194304256002824849280x7f35ead596000x7f34bac3620052428814135678180935929612075941363656044120759413638291001207594136407757912075941364126238
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001409011239011284194304256002424864000x7f35ead595000x7f34bac3624052428812516572160214654812075941364151946120759413643334181207594136446429712075941364467993
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001429011239011284194304256002424881280x7f35ead594000x7f34bac36280524288599934376792736812075941364517275120759413646807761207594136483101512075941364834604
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001449011239011284194304256002424896000x7f35ead593000x7f34bac362c052428813160509168457198012075941364911708120759413650793341207594136520733412075941365211204
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001469011239011284194304256002824920960x7f35ead59a000x7f34bac3630052428812382816158502045212075941365258943120759413654279731207594136569405112075941365741590
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001489011239011284194304256002824935680x7f35ead599000x7f34bac3634052428814119658180728838812075941365765014120759413659430101207594136622652912075941366276825
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001509011239011284194304256002424950400x7f35ead598000x7f34bac3638052428811111074142220963612075941366300308120759413664809281207594136661532712075941366619031
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001529011239011284194304256002424967680x7f35ead597000x7f34bac363c0524288456707358445858412075941366667932120759413668332461207594136699068512075941366994198
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001549011239011284194304256002424982400x7f35ead596000x7f34bac3640052428811072032141724766812075941367055732120759413672167641207594136735276412075941367356722
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015690112390112841943042560028241007360x7f35ead595000x7f34bac3644052428810940691140043235612075941367400794120759413675700431207594136783676112075941367884002
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015890112390112841943042560028241022080x7f35ead594000x7f34bac3648052428814150327181120232812075941367910451120759413680906801207594136834475912075941368395372
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016090112390112841943042560024241036800x7f35ead593000x7f34bac364c052428812556595160718139212075941368422262120759413685972381207594136872923712075941368733029
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016290112390112841943042560024241056640x7f35ead59a000x7f34bac36500524288361955546319572012075941368781099120759413689537161207594136912043512075941369124347
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016490112390112841943042560024241071360x7f35ead599000x7f34bac3654052428811346463145224677612075941369185841120759413693442741207594136948059412075941369484175
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016690112390112841943042560028241098880x7f35ead598000x7f34bac365805242889861627126240558812075941369533167120759413696930731207594136995707112075941370011806
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016890112390112841943042560028241113600x7f35ead597000x7f34bac365c052428813578265173798780812075941370039077120759413702156301207594137047066912075941370521183
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017090112390112841943042560024241128320x7f35ead596000x7f34bac3660052428810862889139033278012075941370545758120759413707196281207594137085674712075941370860213
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017290112390112841943042560024241148160x7f35ead595000x7f34bac36640524288376839948246637212075941370908963120759413710685861207594137124362512075941371247322
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017490112390112841943042560024241162880x7f35ead594000x7f34bac3668052428811125523142418924812075941371310259120759413714701841207594137160602412075941371609836
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017690112390112841943042560028241190400x7f35ead593000x7f34bac366c052428810166911130141241212075941371658025120759413718237831207594137209242112075941372143728
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017890112390112841943042560028241207680x7f35ead59a000x7f34bac3670052428814193603181678727212075941372162573120759413723503401207594137260473912075941372652243
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018090112390112841943042560024241224960x7f35ead599000x7f34bac3674052428811340321145151234012075941372678592120759413728509781207594137298729712075941372990913
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018290112390112841943042560024241247360x7f35ead598000x7f34bac36780524288350409144848229212075941373041597120759413732098561207594137339305512075941373396667
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018490112390112841943042560024241264640x7f35ead597000x7f34bac367c052428810317857132050520012075941373457229120759413736143341207594137375561412075941373759341
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018690112390112841943042560020241279360x7f35ead596000x7f34bac36800524288410182852495618812075941373808222120759413739719331207594137423801112075941374285769
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018890112390112841943042560028241296640x7f35ead595000x7f34bac3684052428812508930160115688812075941374312719120759413744919301207594137474888912075941374769799
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019090112390112841943042560024241313920x7f35ead594000x7f34bac3688052428811711559149900693212075941374817227120759413749746481207594137510968712075941375113568
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019290112390112841943042560024241336320x7f35ead593000x7f34bac368c0524288365362146787000812075941375153953120759413753332061207594137552552512075941375575596
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019490112390112841943042560024241353600x7f35ead59a000x7f34bac3690052428810432998133556282412075941375611563120759413757706441207594137590920412075941375912863
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019690112390112841943042560020241368320x7f35ead599000x7f34bac36940524288288503536928546812075941375962936120759413761381621207594137642392112075941376472032
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019890112390112841943042560028241385600x7f35ead598000x7f34bac3698052428813860509177417816412075941376500756120759413766724001207594137692983912075941376977942
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020090112390112841943042560024241402880x7f35ead597000x7f34bac369c052428811868610151899454812075941377006776120759413771808781207594137731639712075941377319938
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020290112390112841943042560024241427840x7f35ead596000x7f34bac36a00524288327784641950448412075941377362196120759413775315961207594137774279512075941377790993
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020490112390112841943042560024241447680x7f35ead595000x7f34bac36a4052428810948403140152046012075941377828162120759413779850341207594137812247312075941378126647
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020690112390112841943042560020241457280x7f35ead594000x7f34bac36a80524288253979232519684812075941378174306120759413783421521207594137865079112075941378675718
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020890112390112841943042560028241477120x7f35ead593000x7f34bac36ac052428813250388169601680012075941378718527120759413788765501207594137913670812075941379165287
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021090112390112841943042560024241496960x7f35ead59a000x7f34bac36b0052428810710142137096132812075941379205863120759413793639071207594137950342712075941379507223
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021290112390112841943042560024241521920x7f35ead599000x7f34bac36b40524288312083539933456812075941379554831120759413797184661207594137994550512075941379970494
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021490112390112841943042560024241541760x7f35ead598000x7f34bac36b8052428811216129143565388412075941380032038120759413801923841207594138032822312075941380332046
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021690112390112841943042560020241556480x7f35ead597000x7f34bac36bc0524288249311431924640812075941380380325120759413805531821207594138088358012075941380907776
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021890112390112841943042560028241576320x7f35ead596000x7f34bac36c0052428814094306180407639612075941380954984120759413811206991207594138137941812075941381407685
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022090112390112841943042560024241596160x7f35ead595000x7f34bac36c4052428810111014129425476412075941381449422120759413816046971207594138174629612075941381749951
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022290112390112841943042560024241623680x7f35ead594000x7f34bac36c80524288343674543976008812075941381798130120759413819608551207594138220613412075941382231466
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022490112390112841943042560024241646080x7f35ead593000x7f34bac36cc05242889693626124083982012075941382288051120759413824469331207594138258933212075941382593068
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022690112390112841943042560020241663360x7f35ead59a000x7f34bac36d00524288236067030222860012075941382641207120759413828087021207594138318470112075941383219211
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022890112390112841943042560028241685760x7f35ead599000x7f34bac36d4052428813997276179162942012075941383254647120759413834163791207594138367685812075941383700696
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023090112390112841943042560024241708160x7f35ead598000x7f34bac36d805242889437555120795189212075941383744728120759413839013371207594138404629612075941384049735
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023290112390112841943042560024241740800x7f35ead597000x7f34bac36dc0524288346118744308155212075941384099047120759413842706151207594138458117412075941384605047
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023490112390112841943042560024241765760x7f35ead596000x7f34bac36e005242887941659101669762012075941384662484120759413848232531207594138496437212075941384967761
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023690112390112841943042560020241777920x7f35ead595000x7f34bac36e40524288234056629945668412075941385023475120759413851840521207594138560805012075941385635833
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023890112390112841943042560028241802880x7f35ead594000x7f34bac36e8052428812630735161679520412075941385677660120759413858349291207594138610420812075941386133127
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024090112390112841943042560024241827840x7f35ead593000x7f34bac36ec0524288734449594008846012075941386176097120759413863394071207594138647956612075941386482907
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024290112390112841943042560024241863040x7f35ead59a000x7f34bac36f00524288346256944323255612075941386532158120759413866910851207594138700772412075941387032769
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024490112390112841943042560024241893120x7f35ead599000x7f34bac36f40524288351151344936162412075941387092670120759413872547631207594138740692312075941387410230
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024690112390112841943042560020241907840x7f35ead598000x7f34bac36f80524288230442829501020012075941387461906120759413876197221207594138813732012075941388162919
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024890112390112841943042560028241937920x7f35ead597000x7f34bac36fc05242887922407101402054012075941388205629120759413883632391207594138866051712075941388684398
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025090112390112841943042560024241968000x7f35ead596000x7f34bac37000524288363498946536212812075941388732738120759413888902771207594138904627612075941389049647
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025290112390112841943042560024242010880x7f35ead595000x7f34bac37040524288326432041797042412075941389101774120759413892613151207594138964659312075941389673356
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025490112390112841943042560024242046080x7f35ead594000x7f34bac37080524288341979543780828012075941389730973120759413898904321207594139006803212075941390071316
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025690112390112841943042560020242060800x7f35ead593000x7f34bac370c0524288234297230002883612075941390119265120759413902992311207594139090978812075941390934560
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025890112390112841943042560028242096000x7f35ead59a000x7f34bac37100524288423902254272415612075941390978792120759413911414671207594139146930612075941391497476
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026090112390112841943042560024242131200x7f35ead599000x7f34bac37140524288315683140433525212075941391537831120759413916942651207594139187442412075941391877753
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026290112390112841943042560024242181760x7f35ead598000x7f34bac37180524288352763645160682412075941391926033120759413920945841207594139255106212075941392576111
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026490112390112841943042560024242222080x7f35ead597000x7f34bac371c0524288312376239962888012075941392632325120759413927933011207594139299330012075941393018132
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026690112390112841943042560020242239360x7f35ead596000x7f34bac37200524288231863029692974412075941393067013120759413932259391207594139392961612075941393979940
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026890112390112841943042560028242279680x7f35ead595000x7f34bac37240524288372317747651445612075941394010046120759413941878551207594139456337412075941394611393
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027090112390112841943042560024242320000x7f35ead594000x7f34bac37280524288302786038742904412075941394638474120759413948131321207594139501649212075941395064505
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027290112390112841943042560024242378240x7f35ead593000x7f34bac372c0524288327151741871094812075941395091606120759413952660911207594139579280912075941395840247
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027490112390112841943042560024242423680x7f35ead59a000x7f34bac37300524288319121540840428412075941395880592120759413960464071207594139627168712075941396319047
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027690112390112841943042560020242435840x7f35ead599000x7f34bac37340524288229687529417312012075941396345706120759413965212861207594139732016212075941397369589
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027890112390112841943042560028242481280x7f35ead598000x7f34bac37380524288368410247160830012075941397393574120759413975726411207594139801568012075941398041819
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028090112390112841943042560024242526720x7f35ead597000x7f34bac373c0524288323922341454853612075941398090679120759413982668781207594139852815712075941398577294
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028290112390112841943042560024242592640x7f35ead596000x7f34bac37400524288372215247635820412075941398606488120759413987758361207594139937311412075941399422695
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028490112390112841943042560024242648320x7f35ead595000x7f34bac37440524288327940841968498412075941399458271120759413996281531207594139989695212075941399946949
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028690112390112841943042560020242663040x7f35ead594000x7f34bac37480524288230599229505720812075941399968670120759414001599911207594140114446712075941401214194
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028890112390112841943042560028242718720x7f35ead593000x7f34bac374c0524288345454644231896012075941401242968120759414014236661207594140193934412075941402013450
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029090112390112841943042560024242774400x7f35ead59a000x7f34bac37500524288323306941373631612075941402046701120759414022203021207594140249246112075941402560186
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029290112390112841943042560012242799360x7f35ead599000x7f34bac37540524288220811728258820812075941402585062120759414027580601207594140349677712075941403564622
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029490112390112841943042560024242865280x7f35ead598000x7f34bac37580524288312197939973271212075941403601481120759414037618961207594140407837512075941404147235
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029690112390112841943042560020242880000x7f35ead597000x7f34bac375c0524288227676229126614812075941404176329120759414043532541207594140552380912075941405593203
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029890112390112841943042560032242945920x7f35ead596000x7f34bac37600524288347003144404684412075941405624671120759414058057281207594140641628512075941406487715
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030090112390112841943042560024243011840x7f35ead595000x7f34bac37640524288321631841164414012075941406514144120759414066895641207594140700908312075941407076649
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030290112390112841943042560012243049600x7f35ead594000x7f34bac37680524288221035228285986812075941407101796120759414072929221207594140817131812075941408240462
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030490112390112841943042560024243136000x7f35ead593000x7f34bac376c0524288313482940116746012075941408285486120759414084489171207594140888059512075941408948408
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030690112390112841943042560020243148160x7f35ead59a000x7f34bac37700524288230456229481489612075941408979766120759414091605941207594141070890812075941410778710
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030890112390112841943042560020243175680x7f35ead599000x7f34bac37740524288225601128872258412075941410809577120759414109882671207594141178394412075941411854970
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031090112390112841943042560012243203200x7f35ead598000x7f34bac37780524288216574427729775612075941411885597120759414120609031207594141247610112075941412543139
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031290112390112841943042560012243240960x7f35ead597000x7f34bac377c0524288226884329024963212075941412569468120759414127450601207594141390505512075941413972776
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031490112390112841943042560012243288960x7f35ead596000x7f34bac37800524288218301527941227212075941414017429120759414141792941207594141496553112075941415035310
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031690112390112841943042560020243301120x7f35ead595000x7f34bac37840524288260742933388648412075941415065987120759414152426501207594141829223712075941418360760
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031890112390112841943042560020243328640x7f35ead594000x7f34bac37880524288230523929501831612075941418397589120759414185607161207594142010279012075941420171956
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032090112390112841943042560012243356160x7f35ead593000x7f34bac378c0524288221270728306344812075941420205950120759414203850291207594142117542612075941421243638
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032290112390112841943042560012243393920x7f35ead59a000x7f34bac37900524288254301632574377612075941421275077120759414214544651207594142373701512075941423805660
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032490112390112841943042560012243441920x7f35ead599000x7f34bac37940524288235614730168282412075941423852016120759414240136541207594142554900812075941425619971
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032690112390112841943042560020243454080x7f35ead598000x7f34bac37980524288291611237330639612075941425649997120759414258275671207594143188322212075941431952370
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032890112390112841943042560020243481600x7f35ead597000x7f34bac379c0524288334592742839063212075941431982816120759414321625811207594143520608912075941435276628
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033090112390112841943042560012243509120x7f35ead596000x7f34bac37a00524288227865629171687212075941435308106120759414354872081207594143702624112075941437095168
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332901123901128419430425600122400x7f35ead595000x7f34bac37a40524288254690332601851212075941437125083120759414373024001207594144182910212075941441898384