ファイル
rocm-systems/tests/workloads/CPF/mi100/pmc_perf.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

50 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_CYCLESSQ_BUSY_CYCLESSQ_WAVESGRBM_COUNTGRBM_GUI_ACTIVECPF_CPF_STAT_BUSYCPF_CPF_STAT_STALLCPF_CPF_TCIU_BUSYCPF_CPF_TCIU_STALLCPF_CPF_STAT_IDLECPF_CPF_TCIU_IDLECPF_CMP_UTCL1_STALL_ON_TRANSLATIONDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000869685869690335544322560083264640x00x7fdec2404180404078438307665242885050975050975050970417800482832012075315587403796120753197379805101207531973830546712075315835499200
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00286968586969032768256002424124800x00x7fdec243510021911274883512273882738827388023430026941012075315849868370120753197533414631207531975334818312075315850220494
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0048696858696904194304256002424129280x7fdfcdfa69000x7fdec243514018093841646053655362261722261722261720235500215251012075315850313286120753197533998631207531975353042212075315850719822
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0068696858696904194304256003624136320x7fdfcdfa68000x7fdec243518031699363005273655363962413962413962410234700392231012075315850814648120753197535742621207531975382178012075315851358448
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0088696858696904194304256002824140800x7fdfcdfa67000x7fdec24351c031893523021400655363986683986683986680235900398419012075315851432586120753197539566581207531975420401612075315851956329
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00108696858696904194304256002424145280x7fdfcdfa66000x7fdec243520017934881638838655362241852241852241850243400217278012075315851984842120753197543380951207531975446337412075315852385677
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00128696858696904194304256002424149760x7fdfcdfa65000x7fdec243524017174081550057655362146752146752146750232700220394012075315852437914120753197544931341207531975461841312075315852816578
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00148696858696904194304256002424154240x7fdfcdfa64000x7fdec243528017143201556658655362142892142892142890231800209547012075315852896025120753197546756931207531975479985212075315853264290
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00168696858696904194304256002824161280x7fdfcdfa63000x7fdec24352c032573123078800655364071634071634071630250500397597012075315853313741120753197548336111207531975508464912075315853868222
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00188696858696904194304256002824168320x7fdfcdfa6a000x7fdec24353003180112301650765536397513397513397513025000039845115812075315853890914120753197552190481207531975546320612075315854451385
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00208696858696904194304256002424175360x7fdfcdfa69000x7fdec243534017375761575579655362171962171962171960238000208961012075315854480008120753197555980851207531975572336412075315854860956
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00228696858696904194304256002424182400x7fdfcdfa68000x7fdec243538017711521616521655362213932213932213930233800212395012075315854910338120753197557521641207531975587712312075315855297958
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00248696858696904194304256002424189440x7fdfcdfa67000x7fdec24353c016943041525377655362117872117872117870241000212491012075315855357649120753197559203221207531975604512112075315855730422
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00268696858696904194304256002824199040x7fdfcdfa66000x7fdec243540032297123064323655364037134037134037130252900405416012075315855780796120753197560752011207531975632575912075315856338081
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00288696858696904194304256002824206080x7fdfcdfa65000x7fdec24354403643816300407865536455476455476455476158251000390636012075315856367586120753197564601581207531975670879612075315856941753
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00308696858696904194304256002424213120x7fdfcdfa64000x7fdec243548017181601552053655362147692147692147690228100216843012075315856976567120753197568398351207531975696479412075315857370039
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00328696858696904194304256002424220160x7fdfcdfa63000x7fdec24354c017400641576789655362175072175072175070238900216268012075315857418979120753197569969541207531975712191312075315857806269
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00348696858696904194304256002424227200x7fdfcdfa6a000x7fdec243550017070241546990655362133772133772133770229600210444012075315857865810120753197571641521207531975728815112075315858249563
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00368696858696904194304256002824236800x7fdfcdfa69000x7fdec243554032213523046256655364026684026684026680250100392492012075315858300477120753197573182311207531975756718912075315858849608
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00388696858696904194304256002824243840x7fdfcdfa68000x7fdec24355803144592298463065536393073393073393073025660040076415812075315858879614120753197576990281207531975798190612075315859423314
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00408696858696904194304256002424250880x7fdfcdfa67000x7fdec24355c017656721607605655362207082207082207080230500214500012075315859450855120753197580516651207531975817630412075315859834117
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00428696858696904194304256002424257920x7fdfcdfa66000x7fdec243560016615841501547655362076972076972076970224900215644012075315859883369120753197582099041207531975833486312075315860264657
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00448696858696904194304256002424264960x7fdfcdfa65000x7fdec243564017229761564474655362153712153712153710234700215499012075315860323707120753197583783821207531975850222112075315860695518
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00468696858696904194304256002824277120x7fdfcdfa64000x7fdec24356803255760306644565536406969406969406969024680039986715812075315860737576120753197585337411207531975877917912075315861290153
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00488696858696904194304256002824284160x7fdfcdfa63000x7fdec24356c03170080299994365536396259396259396259025300040344415812075315861315460120753197588647781207531975911437612075315861865602
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00508696858696904194304256002424291200x7fdfcdfa6a000x7fdec243570016746401520178655362093292093292093290230600216155012075315861892973120753197592092561207531975933309512075315862275694
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00528696858696904194304256002424300800x7fdfcdfa69000x7fdec243574017705281606221655362213152213152213150237100211010012075315862325356120753197593647741207531975948925312075315862709420
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00548696858696904194304256002424307840x7fdfcdfa68000x7fdec243578017493921585041655362186732186732186730238100210845012075315862767638120753197595298931207531975965485212075315863136984
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00568696858696904194304256002824320000x7fdfcdfa67000x7fdec24357c032286403056689655364035794035794035790245600393939012075315863188350120753197596878121207531975993581012075315863733292
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00588696858696904194304256002824329600x7fdfcdfa66000x7fdec243580032002083016637655364000254000254000250250700405570012075315863765382120753197600508491207531976029420712075315864306187
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00608696858696904194304256002424339200x7fdfcdfa65000x7fdec243584016721601505023655362090192090192090190234000210084012075315864329931120753197604303661207531976055516512075315864712031
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00628696858696904194304256002424348800x7fdfcdfa64000x7fdec243588017701921603134655362212732212732212730229000213014012075315864761353120753197605831641207531976070876312075315865152028
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00648696858696904194304256002424358400x7fdfcdfa63000x7fdec24358c016750401515023655362093792093792093790235200214578012075315865211409120753197607500431207531976087436212075315865578982
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00668696858696904194304256002824373120x7fdfcdfa6a000x7fdec243590031136802925202655363892093892093892090223900393465012075315865626741120753197609039621207531976115100012075315866171663
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00688696858696904194304256002824382720x7fdfcdfa69000x7fdec24359403640872301332065536455108455108455108158229900392748012075315866196539120753197612697191207531976151371712075315866783119
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00708696858696904194304256002424392320x7fdfcdfa68000x7fdec243598017413921569335655362176732176732176730227500208551012075315866820739120753197616249161207531976175035512075315867205634
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00728696858696904194304256002424401920x7fdfcdfa67000x7fdec24359c017918401633357655362239792239792239790235100215906012075315867247572120753197617804351207531976190667312075315867644670
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00748696858696904194304256002424411520x7fdfcdfa66000x7fdec2435a0017420321580598655362177532177532177530442500214796012075315867702437120753197619482731207531976207243212075315868078666
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00768696858696904194304256002824426240x7fdfcdfa65000x7fdec2435a4031986243027370655363998273998273998270253000396804012075315868128289120753197621010721207531976235003012075315868679603
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00788696858696904194304256002824435840x7fdfcdfa64000x7fdec2435a8031396002974211655363924493924493924490249000395918012075315868707275120753197623981891207531976264218712075315869260813
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00808696858696904194304256002424445440x7fdfcdfa63000x7fdec2435ac017158801558726655362144842144842144840226400213692012075315869284387120753197626861871207531976281114612075315869693347
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00828696858696904194304256002424457600x7fdfcdfa6a000x7fdec2435b0018174881658876655362271852271852271850232100221438012075315869743690120753197628402661207531976296570512075315870082821
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00848696858696904194304256002424467200x7fdfcdfa69000x7fdec2435b4016622481502006655362077802077802077800229700219443012075315870145487120753197630076241207531976313242312075315870453700
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00868696858696904194304256002824484480x7fdfcdfa68000x7fdec2435b8032082083029913655364010254010254010250249300413315012075315870504013120753197631621831207531976341226112075315870989235
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00888696858696904194304256002824494080x7fdfcdfa67000x7fdec2435bc03684008302790465536460500460500460500158247400400634012075315871024430120753197634572211207531976373977812075315871551790
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00908696858696904194304256002424503680x7fdfcdfa66000x7fdec2435c0016724641500763655362090572090572090570232600218189012075315871581736120753197637861781207531976391113712075315871900859
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00928696858696904194304256002424515840x7fdfcdfa65000x7fdec2435c4017543361589687655362192912192912192910231500219284012075315871951823120753197639448971207531976407177612075315872283289
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00948696858696904194304256002424525440x7fdfcdfa64000x7fdec2435c8016573601494334655362071692071692071690229100217406012075315872344593120753197641144951207531976423993412075315872649650
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00968696858696904194304256002824542720x7fdfcdfa63000x7fdec2435cc032519363086276655364064914064914064910245300409653012075315872698331120753197642685741207531976452217212075315873184554
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00988696858696904194304256002824554880x7fdfcdfa6a000x7fdec2435d0031462562963988655363932813932813932810247700398124012075315873208398120753197645671321207531976481177012075315873700913
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001008696858696904194304256002424567040x7fdfcdfa69000x7fdec2435d4017727121613211655362215882215882215880414300209665012075315873725409120753197648602491207531976498472812075315874054200
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001028696858696904194304256002424581760x7fdfcdfa68000x7fdec2435d8017827361624303655362228412228412228410249700225310012075315874103231120753197650180081207531976514648712075315874429698
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001048696858696904194304256002424593920x7fdfcdfa67000x7fdec2435dc017160721555585655362145082145082145080233200209489012075315874489068120753197651892071207531976531448612075315874799495
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001068696858696904194304256002824613760x7fdfcdfa66000x7fdec2435e0031433762966495655363929213929213929210232800416211012075315874849157120753197653463251207531976559816312075315875332685
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001088696858696904194304256002824625920x7fdfcdfa65000x7fdec2435e4031940243016831655363992523992523992520253700394249012075315875355508120753197656418431207531976588632112075315875856218
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001108696858696904194304256002424638080x7fdfcdfa64000x7fdec2435e8016998561543353655362124812124812124810229800268359012075315875887607120753197659325611207531976605800012075315876207301
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001128696858696904194304256002424652800x7fdfcdfa63000x7fdec2435ec018121281641405655362265152265152265150237400226059012075315876258145120753197660856791207531976621575812075315876586746
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001148696858696904194304256002424664960x7fdfcdfa6a000x7fdec2435f0016997921540917655362124732124732124730473600215804012075315876648390120753197662584781207531976638375712075315876952215
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001168696858696904194304256002824684800x7fdfcdfa69000x7fdec2435f4032662163062308655364082764082764082760247400415635012075315877007377120753197664163971207531976667079512075315877496246
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001188696858696904194304256002824696960x7fdfcdfa68000x7fdec2435f8031515042969093655363939373939373939370247100397002012075315877519168120753197667109541207531976695511212075315878016021
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001208696858696904194304256002424709120x7fdfcdfa67000x7fdec2435fc017240081562109655362155002155002155000237100278390012075315878039325120753197669941521207531976711895112075315878374147
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001228696858696904194304256002424723840x7fdfcdfa66000x7fdec243600017987361629771655362248412248412248410246200221798012075315878423659120753197671467911207531976728423012075315878752350
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001248696858696904194304256002424736000x7fdfcdfa65000x7fdec243604016881681527612655362110202110202110200247100208450012075315878812862120753197673282291207531976745286812075315879116186
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001268696858696904194304256002824758400x7fdfcdfa64000x7fdec243608032097443030054655364012174012174012170251300408694012075315879166048120753197674816681207531976773974612075315879652833
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001288696858696904194304256002824770560x7fdfcdfa63000x7fdec24360c03202016302499965536400251400251400251025160039294015812075315879682949120753197677840651207531976803014312075315880163953
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001308696858696904194304256002424782720x7fdfcdfa6a000x7fdec243610017043361547526655362130412130412130410234700208865012075315880190843120753197680829431207531976820790212075315880514183
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001328696858696904194304256002424800000x7fdfcdfa69000x7fdec243614018690881685810655362336352336352336350234700229472012075315880564357120753197682386221207531976838102112075315880890012
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001348696858696904194304256002424812160x7fdfcdfa68000x7fdec243618016858401522231655362107292107292107290229000217990012075315880953109120753197684235801207531976854885912075315881263335
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001368696858696904194304256002824834560x7fdfcdfa67000x7fdec24361c032625043066923655364078124078124078120254200412569012075315881311836120753197685778191207531976883141712075315881801866
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001388696858696904194304256002824849280x7fdfcdfa66000x7fdec243620031404322955754655363925533925533925530246600399940012075315881829628120753197688778161207531976912405412075315882322704
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001408696858696904194304256002424864000x7fdfcdfa65000x7fdec243624017887121627335655362235882235882235880227300225217012075315882345787120753197691749341207531976930053312075315882683063
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001428696858696904194304256002424881280x7fdfcdfa64000x7fdec243628019157281760416655362394652394652394650233700239501012075315882731523120753197693302931207531976947861212075315883066065
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001448696858696904194304256002424896000x7fdfcdfa63000x7fdec24362c017215041558477655362151872151872151870234600220439012075315883148378120753197695858111207531976971141012075315883453776
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001468696858696904194304256002824920960x7fdfcdfa6a000x7fdec243630032582563075537655364072814072814072810248200415160012075315883502035120753197697434091207531977000468712075315883987407
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001488696858696904194304256002824935680x7fdfcdfa69000x7fdec243634031595842978848655363949473949473949470245800388300012075315884015519120753197700594071207531977030708512075315884502795
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001508696858696904194304256002424950400x7fdfcdfa68000x7fdec243638016743201504545655362092892092892092890227500222023012075315884530506120753197703600441207531977048532312075315884855260
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001528696858696904194304256002424967680x7fdfcdfa67000x7fdec24363c020130321851755655362516282516282516280235400250938012075315884903028120753197705157231207531977067172212075315885251967
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001548696858696904194304256002424982400x7fdfcdfa66000x7fdec243640017403681574023655362175452175452175450233400217470012075315885316567120753197707171611207531977084228012075315885626833
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015686968586969041943042560028241007360x7fdfcdfa65000x7fdec243644032582083061829655364072754072754072750232400411828012075315885674281120753197708722001207531977112915812075315886163090
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015886968586969041943042560028241022080x7fdfcdfa64000x7fdec243648031498402982199655363937293937293937290237300398782012075315886187044120753197711784381207531977145779512075315886679099
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016086968586969041943042560024241036800x7fdfcdfa63000x7fdec24364c017791041614984655362223872223872223870232600221933012075315886703564120753197715465951207531977167235412075315887040039
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016286968586969041943042560024241056640x7fdfcdfa6a000x7fdec243650021014561941218655362626812626812626810231500262303012075315887089672120753197717027531207531977186835212075315887447937
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016486968586969041943042560024241071360x7fdfcdfa69000x7fdec243654016897041525493655362112122112122112120231000220903012075315887509421120753197719157121207531977204131112075315887815751
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016686968586969041943042560028241098880x7fdfcdfa68000x7fdec243658032780323092273655364097534097534097530253500404114012075315887863790120753197720689901207531977232322812075315888364260
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016886968586969041943042560028241113600x7fdfcdfa67000x7fdec24365c03623080299165065536452884452884452884158251800401253012075315888387643120753197723694681207531977262066612075315888919942
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017086968586969041943042560024241128320x7fdfcdfa66000x7fdec243660017822241610564655362227772227772227770235800224183012075315888943656120753197726696261207531977279474412075315889278719
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017286968586969041943042560024241148160x7fdfcdfa65000x7fdec243664022036882040406655362754602754602754600237600273836012075315889328672120753197728230641207531977299506312075315889685134
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017486968586969041943042560024241162880x7fdfcdfa64000x7fdec243668017468961579678655362183612183612183610233100214030012075315889749664120753197730385821207531977316434112075315890056494
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017686968586969041943042560028241190400x7fdfcdfa63000x7fdec24366c032560403053749655364070044070044070040243600401940012075315890104754120753197731958611207531977345537912075315890594734
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017886968586969041943042560028241207680x7fdfcdfa6a000x7fdec243670031458722975449655363932333932333932330243900396925012075315890618358120753197735017791207531977374881712075315891105283
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018086968586969041943042560024241224960x7fdfcdfa69000x7fdec243674017551681589910655362193952193952193950230700224344012075315891128476120753197737945761207531977392017512075315891458279
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018286968586969041943042560024241247360x7fdfcdfa68000x7fdec243678023040162146117655362880012880012880010253700288302012075315891508001120753197739478551207531977413009412075315891871447
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018486968586969041943042560024241264640x7fdfcdfa67000x7fdec24367c017834001621132655362229242229242229240229000226669012075315891934464120753197741715331207531977429745212075315892246333
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018686968586969041943042560020241279360x7fdfcdfa66000x7fdec243680032774563114069655364096814096814096810242500407978012075315892295374120753197743288121207531977459185012075315892783802
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018886968586969041943042560028241296640x7fdfcdfa65000x7fdec24368403595944298341565536449492449492449492158244300403305012075315892805662120753197746345691207531977488032712075315893332481
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019086968586969041943042560024241313920x7fdfcdfa64000x7fdec243688017269281555361655362158652158652158650264600221427012075315893356636120753197749177671207531977504432612075315893684756
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019286968586969041943042560024241336320x7fdfcdfa63000x7fdec24368c02848424224964465536356052356052356052158237200352580012075315893734288120753197750763261207531977526688412075315894185226
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019486968586969041943042560024241353600x7fdfcdfa6a000x7fdec243690017825441605987655362228172228172228170237800211404012075315894220622120753197753075241207531977543456312075315894534856
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019686968586969041943042560020241368320x7fdfcdfa69000x7fdec24369403876768333275965536484595484595484595158469000435515012075315894582995120753197754652831207531977574656012075315895121896
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019886968586969041943042560028241385600x7fdfcdfa68000x7fdec243698031458722932143655363932333932333932330240200400195012075315895144989120753197757926401207531977604319812075315895638506
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020086968586969041943042560024241402880x7fdfcdfa67000x7fdec24369c018091841647957655362261472261472261470236300222765012075315895661800120753197760935981207531977621919612075315895997453
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020286968586969041943042560024241427840x7fdfcdfa66000x7fdec2436a0026359842469422655363294973294973294970232000330020012075315896047997120753197762471961207531977645551512075315896481743
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020486968586969041943042560024241447680x7fdfcdfa65000x7fdec2436a4018160401651470655362270042270042270040232700225204012075315896519884120753197765139141207531977664143312075315896831523
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020686968586969041943042560020241457280x7fdfcdfa64000x7fdec2436a803784400361991065536473049473049473049025060051222315812075315896884461120753197766686331207531977697423012075315897398667
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020886968586969041943042560028241477120x7fdfcdfa63000x7fdec2436ac031542162960287655363942763942763942760244800398366012075315897439904120753197770206301207531977727038812075315897886734
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021086968586969041943042560024241496960x7fdfcdfa6a000x7fdec2436b0017525921572698655362190732190732190730425800214497012075315897931026120753197773190281207531977744686612075315898245751
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021286968586969041943042560024241521920x7fdfcdfa69000x7fdec2436b4028497042690377655363562123562123562120243600355526012075315898291796120753197774772661207531977770478412075315898721084
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021486968586969041943042560024241541760x7fdfcdfa68000x7fdec2436b8017776801592381655362222092222092222090239700222800012075315898782528120753197777599841207531977788702312075315899092244
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021686968586969041943042560020241556480x7fdfcdfa67000x7fdec2436bc04037864387694565536504732504732504732024600054340415812075315899142928120753197779207831207531977824846012075315899678854
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021886968586969041943042560028241576320x7fdfcdfa66000x7fdec2436c0031390242961123655363923773923773923770245100396251012075315899722395120753197782932601207531977854125812075315900170928
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022086968586969041943042560024241596160x7fdfcdfa65000x7fdec2436c4017874241627018655362234272234272234270231200228658012075315900213507120753197785828571207531977871101612075315900525778
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022286968586969041943042560024241623680x7fdfcdfa64000x7fdec2436c8030535842892792655363816973816973816970250600427751012075315900574047120753197787431761207531977898669412075315901023262
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022486968586969041943042560024241646080x7fdfcdfa63000x7fdec2436cc018196801654431655362274592274592274590227600222686012075315901080568120753197790444531207531977917421212075315901396786
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022686968586969041943042560020241663360x7fdfcdfa6a000x7fdec2436d0045880484424360655365735055735055735050244200571778012075315901445036120753197792017321207531977957596912075315902019663
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022886968586969041943042560028241685760x7fdfcdfa69000x7fdec2436d4031837122999084655363979633979633979630250600408103012075315902067332120753197796198091207531977987100712075315902517869
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023086968586969041943042560024241708160x7fdfcdfa68000x7fdec2436d8017806881616816655362225852225852225850229800217123012075315902561280120753197799233261207531978005340512075315902868601
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023286968586969041943042560024241740800x7fdfcdfa67000x7fdec2436dc034785683312687655364348204348204348200229200433157012075315902916550120753197800858851207531978036332312075315903407963
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023486968586969041943042560024241765760x7fdfcdfa66000x7fdec2436e0018252961656842655362281612281612281610235200217185012075315903463055120753197804634821207531978059932112075315903776628
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023686968586969041943042560020241777920x7fdfcdfa65000x7fdec2436e4051663045004683655366457876457876457870425300675009012075315903824026120753197806292401207531978105083712075315904455970
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023886968586969041943042560028241802880x7fdfcdfa64000x7fdec2436e8032544803076317655364068094068094068090408600397458012075315904497267120753197811383561207531978139963412075315904947574
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024086968586969041943042560024241827840x7fdfcdfa63000x7fdec2436ec017863361613291655362232912232912232910235000226529012075315904990814120753197814465141207531978158155312075315905305409
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024286968586969041943042560024241863040x7fdfcdfa6a000x7fdec2436f00424091237349486553653011353011353011315824950048550815812075315905354891120753197816113121207531978192443012075315905900024
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024486968586969041943042560024241893120x7fdfcdfa69000x7fdec2436f4019524801785754655362440592440592440590231600239716012075315905956519120753197819834691207531978217434812075315906288976
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024686968586969041943042560020241907840x7fdfcdfa68000x7fdec2436f8062921126122417655367865137865137865130432700806421012075315906337316120753197822031481207531978271834312075315907059007
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024886968586969041943042560028241937920x7fdfcdfa67000x7fdec2436fc036572483471055655364571554571554571550245100457902012075315907104181120753197827642631207531978306506112075315907594823
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025086968586969041943042560024241968000x7fdfcdfa66000x7fdec243700019676961811449655362459612459612459610238600244996012075315907646679120753197831119401207531978326601912075315907975941
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025286968586969041943042560024242010880x7fdfcdfa65000x7fdec243704047505604585272655365938195938195938190250700590381012075315908029200120753197832940191207531978367961612075315908633893
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025486968586969041943042560024242046080x7fdfcdfa64000x7fdec243708022261922069831655362782732782732782730235900277114012075315908688475120753197837396151207531978391401412075315909039136
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025686968586969041943042560020242060800x7fdfcdfa63000x7fdec24370c074142407243515655369267799267799267790232700922718012075315909088608120753197839415331207531978454984812075315909908502
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025886968586969041943042560028242096000x7fdfcdfa6a000x7fdec243710040118563848541655365014815014815014810247100502684012075315909953826120753197846008881207531978493192512075315910500201
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026086968586969041943042560024242131200x7fdfcdfa69000x7fdec243714022584082100363655362823002823002823000233600281005012075315910523144120753197849768851207531978515400312075315910895576
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026286968586969041943042560024242181760x7fdfcdfa68000x7fdec243718055814565424385655366976816976816976810242000696483012075315910944437120753197851863231207531978564071912075315911630001
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026486968586969041943042560024242222080x7fdfcdfa67000x7fdec24371c025138322354343655363142283142283142280229800310783012075315911666909120753197856991191207531978589863712075315912084916
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026686968586969041943042560020242239360x7fdfcdfa66000x7fdec2437200851304083568206553610641291064129106412904340001062892012075315912109792120753197859418371207531978664391112075315913048386
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026886968586969041943042560028242279680x7fdfcdfa65000x7fdec243724045719364394802655365714915714915714910243400565400012075315913072130120753197867013511207531978707254812075315913684759
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027086968586969041943042560024242320000x7fdfcdfa64000x7fdec243728025352482377512655363169053169053169050231700316075012075315913707040120753197871186271207531978732038612075315914147038
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027286968586969041943042560024242378240x7fdfcdfa63000x7fdec24372c064292246264254655368036528036528036520246200825517012075315914170291120753197873688651207531978789398112075315914929872
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027486968586969041943042560024242423680x7fdfcdfa6a000x7fdec243730027906722633764655363488333488333488330246100399195012075315914965839120753197879519011207531978821029812075315915418710
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027686968586969041943042560020242435840x7fdfcdfa69000x7fdec2437340967228894949696553612090351209035120903502415001204584012075315915442254120753197882624581207531978905861212075315916479201
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027886968586969041943042560028242481280x7fdfcdfa68000x7fdec24373805097936493313565536637241637241637241024430063718315812075315916503376120753197891056511207531978952356812075315917160367
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028086968586969041943042560024242526720x7fdfcdfa67000x7fdec24373c028199442653711655363524923524923524920255400352588012075315917190753120753197895678871207531978979156612075315917649666
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028286968586969041943042560024242592640x7fdfcdfa66000x7fdec243740072672167110963655369084019084019084010246100906583012075315917675304120753197898413251207531979043668012075315918502340
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028486968586969041943042560024242648320x7fdfcdfa65000x7fdec243744033384723170744655364173084173084173080250600414882012075315918539700120753197905032401207531979077091812075315919028508
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028686968586969041943042560020242663040x7fdfcdfa64000x7fdec243748011902416117406186553614878011487801148780102465001484318012075315919051831120753197908161971207531979179938912075315920275896
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028886968586969041943042560028242718720x7fdfcdfa63000x7fdec24374c062273606054824655367784197784197784190242900778418012075315920298528120753197918454691207531979235858512075315921062738
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029086968586969041943042560024242774400x7fdfcdfa6a000x7fdec243750033730723213750655364216334216334216330241500420803012075315921092253120753197924169841207531979268706212075315921603783
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029286968586969041943042560012242799360x7fdfcdfa69000x7fdec2437540900969688414196553611262111126211112621102442001123923012075315921626505120753197927328221207531979346913612075315922600736
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029486968586969041943042560024242865280x7fdfcdfa68000x7fdec243758038948003736105655364868494868494868490240300487515012075315922639428120753197935299351207531979384593212075315923176005
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029686968586969041943042560020242880000x7fdfcdfa67000x7fdec24375c014145632139770796553617682031768203176820302506001765941012075315923199138120753197938902521207531979505824312075315924604318
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029886968586969041943042560032242945920x7fdfcdfa66000x7fdec243760073428647172130655369178579178579178570245600915849012075315924634284120753197951140821207531979572271712075315925480977
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030086968586969041943042560024243011840x7fdfcdfa65000x7fdec243764039578643760747655364947324947324947320249600531722012075315925504682120753197957707171207531979608863412075315926066526
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030286968586969041943042560012243049600x7fdfcdfa64000x7fdec243768010690576105267036553613363211336321133632102395001335518012075315926090280120753197961403141207531979701662712075315927204540
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030486968586969041943042560024243136000x7fdfcdfa63000x7fdec24376c05295456485819465536661931661931661931158437000661579012075315927239435120753197970764661207531979748702312075315927906615
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030686968586969041943042560020243148160x7fdfcdfa6a000x7fdec243770018663568184951206553623329452332945233294502507002331478012075315927929347120753197975355021207531979908205012075315929727458
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030886968586969041943042560020243175680x7fdfcdfa69000x7fdec243774096172569436837655361202156120215612021561582300001197048012075315929751182120753197991310091207531979992268312075315930789361
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031086968586969041943042560012243203200x7fdfcdfa68000x7fdec24377805118992495190565536639873639873639873024560063814115812075315930821731120753197999922821207531980040507912075315931464035
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031286968586969041943042560012243240960x7fdfcdfa67000x7fdec24377c014050720138916706553617563391756339175633902376001756290012075315931494261120753198004753161207531980163322812075315932888321
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031486968586969041943042560012243288960x7fdfcdfa66000x7fdec2437800958516894232286553611981451198145119814502428001196429012075315932928356120753198017431461207531980252746112075315933950164
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031686968586969041943042560020243301120x7fdfcdfa65000x7fdec243784036666728365068376553645833404583340458334002560004581013012075315933980120120753198026194601207531980567047912075315937268310
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031886968586969041943042560020243328640x7fdfcdfa64000x7fdec243788018597072184254776553623246332324633232463302570002322087012075315937295110120753198057597581207531980730022712075315939083833
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032086968586969041943042560012243356160x7fdfcdfa63000x7fdec24378c0960758494523076553612009471200947120094702535001199674012075315939111385120753198073944671207531980818502112075315940139555
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032286968586969041943042560012243393920x7fdfcdfa6a000x7fdec243790027541072273798426553634426333442633344263302393003440013012075315940163019120753198082773411207531981055764512075315942686708
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032486968586969041943042560012243441920x7fdfcdfa69000x7fdec24379401858025618419864655362322531232253123225311582352002321590012075315942730379120753198106714041207531981220563312075315944485490
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032686968586969041943042560020243454080x7fdfcdfa68000x7fdec2437980727135527253196065536908919390891939089193158466700908438015812075315944516959120753198122947521207531981835135012075315950808660
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032886968586969041943042560020243481600x7fdfcdfa67000x7fdec24379c036587616364197126553645734514573451457345104154004569115012075315950836822120753198184411091207531982148396812075315954129921
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033086968586969041943042560012243509120x7fdfcdfa66000x7fdec2437a0018620624184683326553623275772327577232757702488002327718012075315954160448120753198215729281207531982311115712075315955938041
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332869685869690419430425600122400x7fdfcdfa65000x7fdec2437a4054490728543259426553668113406811340681134002452006809737012075315955966774120753198231997961207531982772616412075315960741406