Files
rocm-systems/tests/workloads/Axes2/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.kd000905945905950335544322560083264640x00x7fa7a38041804194304311560039855411212076035960858082120760362052070631207603620552962112076036205637263
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00290594590595032768256002424124800x00x7fa7a383510051223496301243212076036220285436120760362205897391207603622059645912076036220601744
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0049059459059504194304256002424129280x7fa8d38339000x7fa7a3835140655361685482150956012076036220667026120760362208890981207603622102093712076036221025311
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0069059459059504194304256003624136320x7fa8d38338000x7fa7a3835180655361545301975707212076036221098317120760362212750151207603622152301412076036221589921
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0089059459059504194304256002824140800x7fa8d38337000x7fa7a38351c0655361706302170385612076036221620828120760362218036531207603622206253112076036222133721
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00109059459059504194304256002424145280x7fa8d38336000x7fa7a3835200655361753602246345612076036222162825120760362223470101207603622248204912076036222485756
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00129059459059504194304256002424149760x7fa8d38335000x7fa7a3835240655361758082249736012076036222541730120760362227049281207603622284220712076036222845715
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00149059459059504194304256002424154240x7fa8d38334000x7fa7a38352801310722629203363664812076036222926414120760362230975661207603622322924512076036223232794
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00169059459059504194304256002824161280x7fa8d38333000x7fa7a38352c01310722078182659655212076036223286694120760362234548441207603622370492212076036223744455
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00189059459059504194304256002824168320x7fa8d3833a000x7fa7a3835300655361770102242903212076036223770373120760362239524411207603622419900012076036224238102
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00209059459059504194304256002424175360x7fa8d38339000x7fa7a38353401310722393583060032012076036224262688120760362244516381207603622457947812076036224583143
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00229059459059504194304256002424182400x7fa8d38338000x7fa7a38353801310722671023411487212076036224635060120760362248063571207603622493947612076036224943082
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00249059459059504194304256002424189440x7fa8d38337000x7fa7a38353c01310722480983177844812076036225010177120760362251761151207603622530843412076036225312108
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00269059459059504194304256002824199040x7fa8d38336000x7fa7a38354001310722001182564379212076036225365167120760362255362731207603622578507112076036225849787
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00289059459059504194304256002824206080x7fa8d38335000x7fa7a3835440655361752022247932012076036225876908120760362260730701207603622632442812076036226390703
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00309059459059504194304256002424213120x7fa8d38334000x7fa7a38354801310722395623058124812076036226417703120760362266028271207603622673066612076036226734171
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00329059459059504194304256002424220160x7fa8d38333000x7fa7a38354c01310722443323120252012076036226784835120760362269577051207603622708874412076036227092487
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00349059459059504194304256002424227200x7fa8d3833a000x7fa7a38355001310722423143118955212076036227156937120760362273252231207603622745658212076036227460361
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00369059459059504194304256002824236800x7fa8d38339000x7fa7a38355401310722164162757956812076036227512007120760362276746611207603622793386012076036227998200
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00389059459059504194304256002824243840x7fa8d38338000x7fa7a3835580655361671522136939212076036228030180120760362282186581207603622850729712076036228573569
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00409059459059504194304256002424250880x7fa8d38337000x7fa7a38355c01310722580523312282412076036228599858120760362287794551207603622891113412076036228914874
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00429059459059504194304256002424257920x7fa8d38336000x7fa7a38356001310722407283091091212076036228966710120760362291424931207603622927481312076036229278670
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00449059459059504194304256002424264960x7fa8d38335000x7fa7a38356401310722382643062259212076036229342208120760362295050511207603622963641112076036229639951
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00469059459059504194304256002824277120x7fa8d38334000x7fa7a38356801310722171282782808012076036229688702120760362298634491207603623011352812076036230179464
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00489059459059504194304256002824284160x7fa8d38333000x7fa7a38356c0655361741082228067212076036230206614120760362303866471207603623063672512076036230702466
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00509059459059504194304256002424291200x7fa8d3833a000x7fa7a38357001310722415083123168012076036230730448120760362309044041207603623103336312076036231037288
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00529059459059504194304256002424300800x7fa8d38339000x7fa7a38357401310722424263107577612076036231089375120760362312564021207603623138808112076036231391647
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00549059459059504194304256002424307840x7fa8d38338000x7fa7a38357801310722379903059602412076036231454043120760362316229601207603623175463912076036231758238
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00569059459059504194304256002824320000x7fa8d38337000x7fa7a38357c01310722172702789702412076036231810064120760362319839181207603623223223712076036232272213
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00589059459059504194304256002824329600x7fa8d38336000x7fa7a3835800655361677022165244012076036232296458120760362324802351207603623272631412076036232790977
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00609059459059504194304256002424339200x7fa8d38335000x7fa7a38358401310722397883064433612076036232816906120760362329992731207603623313031212076036233134025
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00629059459059504194304256002424348800x7fa8d38334000x7fa7a38358801310722591383311255212076036233187344120760362333602311207603623349207012076036233495617
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00649059459059504194304256002424358400x7fa8d38333000x7fa7a38358c01310722400063074454412076036233559456120760362337259891207603623385766812076036233861807
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00669059459059504194304256002824373120x7fa8d3833a000x7fa7a38359001310722185082787868812076036233910788120760362340899871207603623433942512076036234406740
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00689059459059504194304256002824382720x7fa8d38339000x7fa7a3835940655361711922183788812076036234433039120760362346119041207603623485798312076036234922859
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00709059459059504194304256002424392320x7fa8d38338000x7fa7a38359801310722436723115498412076036234948998120760362351376611207603623527366012076036235277498
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00729059459059504194304256002424401920x7fa8d38337000x7fa7a38359c01310722509903211137612076036235327912120760362354974991207603623562997812076036235633710
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00749059459059504194304256002424411520x7fa8d38336000x7fa7a3835a001310722548643264555212076036235694513120760362358563771207603623598709612076036235991034
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00769059459059504194304256002824426240x7fa8d38335000x7fa7a3835a401310722025782577397612076036236041368120760362362136551207603623646709412076036236531469
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00789059459059504194304256002824435840x7fa8d38334000x7fa7a3835a80655361663082118291212076036236556455120760362367331721207603623698421112076036237024936
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00809059459059504194304256002424445440x7fa8d38333000x7fa7a3835ac01310722583463310508012076036237054110120760362372304501207603623736196912076036237365609
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00829059459059504194304256002424457600x7fa8d3833a000x7fa7a3835b001310722425523102591212076036237418527120760362375818081207603623771508712076036237718695
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00849059459059504194304256002424467200x7fa8d38339000x7fa7a3835b401310722433083122286412076036237781211120760362379451661207603623807652512076036238080808
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00869059459059504194304256002824484480x7fa8d38338000x7fa7a3835b801310722148342746784812076036238133256120760362382957241207603623856180312076036238627424
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00889059459059504194304256002824494080x7fa8d38337000x7fa7a3835bc0655361793802304061612076036238655947120760362388296411207603623907764012076036239143283
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00909059459059504194304256002424503680x7fa8d38336000x7fa7a3835c001310722380583041359212076036239171275120760362393480381207603623947859812076036239482243
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00929059459059504194304256002424515840x7fa8d38335000x7fa7a3835c401310722515003230589612076036239532416120760362397048371207603623984435612076036239848243
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00949059459059504194304256002424525440x7fa8d38334000x7fa7a3835c801310722460123154220012076036239909877120760362400742751207603624020691412076036240210987
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00969059459059504194304256002824542720x7fa8d38333000x7fa7a3835cc01310722023662609002412076036240259828120760362404273931207603624068963112076036240729541
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00989059459059504194304256002824554880x7fa8d3833a000x7fa7a3835d00655361749702244032812076036240755138120760362409296301207603624118066912076036241247073
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001009059459059504194304256002424567040x7fa8d38339000x7fa7a3835d401310722441803098426412076036241272901120760362414491471207603624158514612076036241589229
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001029059459059504194304256002424581760x7fa8d38338000x7fa7a3835d801310722464763159488812076036241642397120760362418065851207603624194818412076036241952404
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001049059459059504194304256002424593920x7fa8d38337000x7fa7a3835dc01310722457123155630412076036242019368120760362421833831207603624231634212076036242320458
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001069059459059504194304256002824613760x7fa8d38336000x7fa7a3835e001310722433403123943212076036242374718120760362425344211207603624279618012076036242860972
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001089059459059504194304256002824625920x7fa8d38335000x7fa7a3835e40655361723302201772012076036242889916120760362430598581207603624330977712076036243375248
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001109059459059504194304256002424638080x7fa8d38334000x7fa7a3835e801310722411463097633612076036243409902120760362435856161207603624371857512076036243722363
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001129059459059504194304256002424652800x7fa8d38333000x7fa7a3835ec01310722389343050416012076036243777776120760362439411341207603624407793312076036244082292
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001149059459059504194304256002424664960x7fa8d3833a000x7fa7a3835f001310722416283077588012076036244148805120760362443188921207603624445313112076036244457199
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001169059459059504194304256002824684800x7fa8d38339000x7fa7a3835f401310722432783138480812076036244510417120760362446734501207603624492816812076036244968288
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001189059459059504194304256002824696960x7fa8d38338000x7fa7a3835f80655361688262161055212076036244991091120760362451755271207603624542864612076036245468227
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001209059459059504194304256002424709120x7fa8d38337000x7fa7a3835fc01310722473983144192012076036245493795120760362456787241207603624581120412076036245814802
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001229059459059504194304256002424723840x7fa8d38336000x7fa7a38360001310722386583066955212076036245864384120760362460360031207603624617536212076036246179349
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001249059459059504194304256002424736000x7fa8d38335000x7fa7a38360401310722617983360464012076036246242557120760362464086411207603624653808012076036246541883
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001269059459059504194304256002824758400x7fa8d38334000x7fa7a38360801310722028922596257612076036246592347120760362467566391207603624701871712076036247071497
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001289059459059504194304256002824770560x7fa8d38333000x7fa7a38360c0655361738382236121612076036247095802120760362472887961207603624754239412076036247588257
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001309059459059504194304256002424782720x7fa8d3833a000x7fa7a38361001310722563963260132812076036247613064120760362477935931207603624792159212076036247925484
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001329059459059504194304256002424800000x7fa8d38339000x7fa7a38361401310722036322608231212076036247975417120760362481516711207603624829615012076036248299910
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001349059459059504194304256002424812160x7fa8d38338000x7fa7a38361801310722452383124539212076036248363949120760362485247891207603624865902812076036248662834
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001369059459059504194304256002824834560x7fa8d38337000x7fa7a38361c01310722038642609096812076036248713529120760362488774271207603624914062612076036249189042
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001389059459059504194304256002824849280x7fa8d38336000x7fa7a3836200655361773182266660812076036249214179120760362493947041207603624964670312076036249692578
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001409059459059504194304256002424864000x7fa8d38335000x7fa7a38362401310722369863045025612076036249719779120760362498983821207603625003454112076036250038511
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001429059459059504194304256002424881280x7fa8d38334000x7fa7a38362801310722039922610484812076036250090548120760362502585401207603625040893912076036250412516
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001449059459059504194304256002424896000x7fa8d38333000x7fa7a38362c01310722442643125084812076036250496282120760362506535781207603625078509712076036250789066
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001469059459059504194304256002824920960x7fa8d3833a000x7fa7a38363001310722046422610284012076036250838628120760362510140561207603625128333412076036251328639
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001489059459059504194304256002824935680x7fa8d38339000x7fa7a3836340655361784742275377612076036251355018120760362515367731207603625179309212076036251838937
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001509059459059504194304256002424950400x7fa8d38338000x7fa7a38363801310722444643139300812076036251861569120760362520470101207603625218316912076036252187315
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001529059459059504194304256002424967680x7fa8d38337000x7fa7a38363c01310722563463268629612076036252237107120760362524081281207603625256652712076036252570066
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001549059459059504194304256002424982400x7fa8d38336000x7fa7a38364001310722522023225232812076036252632752120760362527986861207603625293020512076036252934152
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015690594590595041943042560028241007360x7fa8d38335000x7fa7a38364401310722030742597797612076036252984626120760362531564441207603625342204312076036253469978
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015890594590595041943042560028241022080x7fa8d38334000x7fa7a3836480655361755102247536012076036253496217120760362536745211207603625393324012076036253979235
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016090594590595041943042560024241036800x7fa8d38333000x7fa7a38364c01310722434503108183212076036254010092120760362541900391207603625431931812076036254323485
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016290594590595041943042560024241056640x7fa8d3833a000x7fa7a38365001310722646383373333612076036254366815120760362545458771207603625471163612076036254715593
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016490594590595041943042560024241071360x7fa8d38339000x7fa7a38365401310722433343130334412076036254782107120760362549612351207603625509019412076036255094257
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016690594590595041943042560028241098880x7fa8d38338000x7fa7a38365801310721954742501973612076036255147666120760362553061931207603625556475112076036255609745
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016890594590595041943042560028241113600x7fa8d38337000x7fa7a38365c0655361689882169982412076036255634261120760362558103501207603625606010912076036256086211
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017090594590595041943042560024241128320x7fa8d38336000x7fa7a38366001310722441823121480812076036256130733120760362562940271207603625643114712076036256435049
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017290594590595041943042560024241148160x7fa8d38335000x7fa7a38366401310722452083151975212076036256485072120760362566546651207603625682810512076036256831916
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017490594590595041943042560024241162880x7fa8d38334000x7fa7a38366801310722434023125693612076036256894232120760362570721031207603625720874212076036257212955
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017690594590595041943042560028241190400x7fa8d38333000x7fa7a38366c01310722040822595535212076036257262416120760362574309811207603625769050012076036257712904
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017890594590595041943042560028241207680x7fa8d3833a000x7fa7a3836700655361983542533840012076036257756925120760362579160991207603625817017712076036258194899
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018090594590595041943042560024241224960x7fa8d38339000x7fa7a38367401310722416083080761612076036258240154120760362583996161207603625853705512076036258541003
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018290594590595041943042560024241247360x7fa8d38338000x7fa7a38367801310722429943131600012076036258592108120760362587557741207603625893993312076036258946146
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018490594590595041943042560024241264640x7fa8d38337000x7fa7a38367c01310722383103056307212076036259017999120760362591792921207603625931897112076036259323186
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018690594590595041943042560020241279360x7fa8d38336000x7fa7a38368001310722439283126248812076036259376786120760362595420101207603625980936912076036259831781
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018890594590595041943042560028241296640x7fa8d38335000x7fa7a3836840655361986042537189612076036259880552120760362600500071207603626030072612076036260325489
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019090594590595041943042560024241313920x7fa8d38334000x7fa7a38368801310722452083143304012076036260373859120760362605367251207603626066984412076036260673877
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019290594590595041943042560024241336320x7fa8d38333000x7fa7a38368c01310722403843075806412076036260722677120760362608903231207603626108184212076036261105829
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019490594590595041943042560024241353600x7fa8d3833a000x7fa7a38369001310722400563063728812076036261168005120760362613325601207603626146504012076036261469124
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019690594590595041943042560020241368320x7fa8d38339000x7fa7a38369401310722700203441252812076036261521943120760362616802381207603626196423712076036261985444
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019890594590595041943042560028241385600x7fa8d38338000x7fa7a3836980655361772462271976012076036262036849120760362621978361207603626245959412076036262484111
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020090594590595041943042560024241402880x7fa8d38337000x7fa7a38369c01310722406043071485612076036262526620120760362626839131207603626281927212076036262823371
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020290594590595041943042560024241427840x7fa8d38336000x7fa7a3836a001310722457983134290412076036262872933120760362630432711207603626325431012076036263276243
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020490594590595041943042560024241447680x7fa8d38335000x7fa7a3836a401310722417223095414412076036263338128120760362635005491207603626363350812076036263637334
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020690594590595041943042560020241457280x7fa8d38334000x7fa7a3836a801310722368703061455212076036263686195120760362638533471207603626416102512076036264185282
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020890594590595041943042560028241477120x7fa8d38333000x7fa7a3836ac0655361667042133120812076036264229444120760362643890241207603626464214312076036264664703
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021090594590595041943042560024241496960x7fa8d3833a000x7fa7a3836b001310722340342988244812076036264708875120760362648696611207603626500950112076036265013491
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021290594590595041943042560024241521920x7fa8d38339000x7fa7a3836b401310722439803131160812076036265064717120760362652424591207603626547061812076036265492001
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021490594590595041943042560024241541760x7fa8d38338000x7fa7a3836b801310722402943076053612076036265551281120760362657210171207603626586117612076036265865104
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021690594590595041943042560020241556480x7fa8d38337000x7fa7a3836bc01310722423423086816012076036265914155120760362661008551207603626643013312076036266454680
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021890594590595041943042560028241576320x7fa8d38336000x7fa7a3836c00655361908642440928012076036266497840120760362666656521207603626692709012076036266947876
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022090594590595041943042560024241596160x7fa8d38335000x7fa7a3836c401310722405683088002412076036266991087120760362671656491207603626730964812076036267313716
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022290594590595041943042560024241623680x7fa8d38334000x7fa7a3836c801310722433523124288812076036267365232120760362675418071207603626778820612076036267809157
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022490594590595041943042560024241646080x7fa8d38333000x7fa7a3836cc01310722384463053760812076036267865131120760362680410961207603626818349612076036268190686
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022690594590595041943042560020241663360x7fa8d3833a000x7fa7a3836d001310722360703039388812076036268237593120760362684164541207603626881949212076036268840364
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022890594590595041943042560028241685760x7fa8d38339000x7fa7a3836d40655361667722137784812076036268886068120760362690570911207603626931485012076036269338179
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023090594590595041943042560024241708160x7fa8d38338000x7fa7a3836d801310722377323054053612076036269381990120760362695524491207603626969388812076036269697006
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023290594590595041943042560024241740800x7fa8d38337000x7fa7a3836dc01310722374203028927212076036269745716120760362699244471207603627020508612076036270229916
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023490594590595041943042560024241765760x7fa8d38336000x7fa7a3836e001310722406843108543212076036270296440120760362704673251207603627060556412076036270608580
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023690594590595041943042560020241777920x7fa8d38335000x7fa7a3836e401310722351283034819212076036270658392120760362708359631207603627126060112076036271284336
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023890594590595041943042560028241802880x7fa8d38334000x7fa7a3836e80655361770742245816812076036271327686120760362714972401207603627175627912076036271776250
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024090594590595041943042560024241827840x7fa8d38333000x7fa7a3836ec01310722329262991867212076036271820993120760362719869981207603627212507812076036272128374
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024290594590595041943042560024241863040x7fa8d3833a000x7fa7a3836f001310722395163057138412076036272180050120760362723610771207603627267659512076036272697963
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024490594590595041943042560024241893120x7fa8d38339000x7fa7a3836f401310722367623027957612076036272755329120760362729244341207603627307675412076036273080233
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024690594590595041943042560020241907840x7fa8d38338000x7fa7a3836f801310722372783027112012076036273130216120760362733213931207603627383947112076036273859351
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024890594590595041943042560028241937920x7fa8d38337000x7fa7a3836fc0655361729022216108812076036273904806120760362740756301207603627437642812076036274400146
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025090594590595041943042560024241968000x7fa8d38336000x7fa7a38370001310722640583377467212076036274442555120760362746084271207603627476442712076036274767669
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025290594590595041943042560024242010880x7fa8d38335000x7fa7a38370401310722242022854140012076036274817943120760362749985061207603627538474412076036275405555
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025490594590595041943042560024242046080x7fa8d38334000x7fa7a38370801310722373843041303212076036275466678120760362756370631207603627581450212076036275817470
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025690594590595041943042560020242060800x7fa8d38333000x7fa7a38370c01310722445683105056812076036275867674120760362760537011207603627667673912076036276700962
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025890594590595041943042560028242096000x7fa8d3833a000x7fa7a3837100655361800922302808012076036276744383120760362769146571207603627724265612076036277265431
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026090594590595041943042560024242131200x7fa8d38339000x7fa7a38371401310722421803096509612076036277310555120760362774788151207603627765769412076036277661167
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026290594590595041943042560024242181760x7fa8d38338000x7fa7a38371801310722455003134988012076036277709997120760362778876131207603627834425112076036278369162
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026490594590595041943042560024242222080x7fa8d38337000x7fa7a38371c01310722285302927932812076036278428162120760362785988101207603627879960912076036278820501
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026690594590595041943042560020242239360x7fa8d38336000x7fa7a38372001310722426583119397612076036278865254120760362790352881207603627973992612076036279760769
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026890594590595041943042560028242279680x7fa8d38335000x7fa7a3837240655361706702191308812076036279808608120760362799784841207603628035128312076036280375301
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027090594590595041943042560024242320000x7fa8d38334000x7fa7a38372801310722693883422312012076036280418782120760362805844021207603628078792112076036280807734
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027290594590595041943042560024242378240x7fa8d38333000x7fa7a38372c01310722456563129912012076036280852818120760362810223201207603628154855812076036281571764
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027490594590595041943042560024242423680x7fa8d3833a000x7fa7a38373001310722380783037224012076036281631255120760362818034371207603628202807612076036282050624
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027690594590595041943042560020242435840x7fa8d38339000x7fa7a38373401310722662663386818412076036282094616120760362822541551207603628305447112076036283080548
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027890594590595041943042560028242481280x7fa8d38338000x7fa7a3837380655361816162322187212076036283123127120760362832843901207603628370486912076036283725828
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028090594590595041943042560024242526720x7fa8d38337000x7fa7a38373c01310722446503126416012076036283773696120760362839371881207603628416518712076036284190531
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028290594590595041943042560024242592640x7fa8d38336000x7fa7a38374001310722464903136073612076036284239342120760362844019861207603628499878312076036285021345
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028490594590595041943042560024242648320x7fa8d38335000x7fa7a38374401310722428423135188012076036285085514120760362852477421207603628551638112076036285537815
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028690594590595041943042560020242663040x7fa8d38334000x7fa7a38374801310722523083218480812076036285582909120760362857419801207603628672805612076036286772019
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028890594590595041943042560028242718720x7fa8d38333000x7fa7a38374c0655361699582181777612076036286802606120760362869843751207603628751765312076036287586573
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029090594590595041943042560024242774400x7fa8d3833a000x7fa7a38375001310722404223082515212076036287615887120760362877973311207603628806997012076036288136965
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029290594590595041943042560012242799360x7fa8d38339000x7fa7a38375401310722426223097336812076036288166370120760362883434091207603628908196612076036289147423
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029490594590595041943042560024242865280x7fa8d38338000x7fa7a38375801310722242922865311212076036289187227120760362893494851207603628966692312076036289732030
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029690594590595041943042560020242880000x7fa8d38337000x7fa7a38375c01310722382223044196012076036289760753120760362899424421207603629111523712076036291182676
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029890594590595041943042560032242945920x7fa8d38336000x7fa7a3837600655361708102181683212076036291213453120760362913971561207603629200819312076036292073842
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030090594590595041943042560024243011840x7fa8d38335000x7fa7a38376401310722446663131953612076036292105210120760362922827521207603629260275112076036292668347
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030290594590595041943042560012243049600x7fa8d38334000x7fa7a38376801310722389283066298412076036292696920120760362928773101207603629375602612076036293825157
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030490594590595041943042560024243136000x7fa8d38333000x7fa7a38376c01310722291822941451212076036293873797120760362940422651207603629447538312076036294541708
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030690594590595041943042560020243148160x7fa8d3833a000x7fa7a38377001310722456223148502412076036294567456120760362947521821207603629630177512076036296368033
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030890594590595041943042560020243175680x7fa8d38339000x7fa7a3837740655361715622193263212076036296397127120760362965811341207603629737745112076036297443832
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031090594590595041943042560012243203200x7fa8d38338000x7fa7a38377801310722437703127818412076036297476933120760362976454501207603629808320812076036298149533
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031290594590595041943042560012243240960x7fa8d38337000x7fa7a38377c01310722567083277540012076036298182575120760362983606471207603629951968212076036299586424
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031490594590595041943042560012243288960x7fa8d38336000x7fa7a38378001310722677583435988812076036299630536120760362997960001207603630058207712076036300653547
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031690594590595041943042560020243301120x7fa8d38335000x7fa7a38378401310722413663059256012076036300684214120760363008627161207603630391262312076036303979548
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031890594590595041943042560020243328640x7fa8d38334000x7fa7a3837880655361873802397908812076036304014984120760363041964621207603630574141512076036305808627
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032090594590595041943042560012243356160x7fa8d38333000x7fa7a38378c01310722446883138964012076036305838082120760363060271741207603630681725112076036306884888
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032290594590595041943042560012243393920x7fa8d3833a000x7fa7a38379001310722437403116833612076036306908421120760363070962891207603630937884012076036309445937
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032490594590595041943042560012243441920x7fa8d38339000x7fa7a38379401310722549183265459212076036309491592120760363096578791207603631119323212076036311260289
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032690594590595041943042560020243454080x7fa8d38338000x7fa7a38379801310722454123140767212076036311291177120760363114729111207603631752984512076036317597026
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032890594590595041943042560020243481600x7fa8d38337000x7fa7a38379c0655361784982291984812076036317626621120760363178106441207603632085431112076036320923658
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033090594590595041943042560012243509120x7fa8d38336000x7fa7a3837a001310722703423459998412076036320957130120760363211335101207603632267350312076036322739633
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332905945905950419430425600122400x7fa8d38335000x7fa7a3837a401310722447503130140012076036322772504120760363229421421207603632746948312076036327538662