Файли
rocm-systems/tests/workloads/SQ/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.kd000852343852348335544322560083264640x00x7f1281c041804194304311341439815275212074899625250804120748998700916261207489987041386412074899870526486
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00285234385234832768256002424124800x00x7f1281c3510051224164309158412074899885466780120748998857620691207489988576814912074899885772278
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0048523438523484194304256002424129280x7f138d92a9000x7f1281c35140655361860702389232012074899885835055120748998860604681207489988619918712074899886202548
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0068523438523484194304256003624136320x7f138d92a8000x7f1281c35180655361633022082663212074899886271406120748998864459061207489988669630512074899886766606
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0088523438523484194304256002824140800x7f138d92a7000x7f1281c351c0655361755162254821612074899886799166120748998869883031207489988723646212074899887307090
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00108523438523484194304256002424145280x7f138d92a6000x7f1281c35200655361871462394045612074899887333139120748998875222211207489988766110012074899887663603
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00128523438523484194304256002424149760x7f138d92a5000x7f1281c35240655361975902523301612074899887716561120748998878836591207489988801405812074899888016659
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00148523438523484194304256002424154240x7f138d92a4000x7f1281c352801310722491383159102412074899888090326120748998882582171207489988838877712074899888391335
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00168523438523484194304256002824161280x7f138d92a3000x7f1281c352c01310722227222844572812074899888440537120748998886161361207489988887181412074899888915499
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00188523438523484194304256002824168320x7f138d92aa000x7f1281c35300655361844762359795212074899888941057120748998891327731207489988942717212074899889470360
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00208523438523484194304256002424175360x7f138d92a9000x7f1281c353401310722774063557690412074899889494555120748998896865301207489988981901012074899889821523
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00228523438523484194304256002424182400x7f138d92a8000x7f1281c353801310722589223311743212074899889868821120748998900521291207489989018892812074899890191821
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00248523438523484194304256002424189440x7f138d92a7000x7f1281c353c01310722581283304703212074899890261781120748998904298871207489989055852612074899890561067
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00268523438523484194304256002824199040x7f138d92a6000x7f1281c354001310722152942759888812074899890610689120748998907839651207489989104428412074899891113113
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00288523438523484194304256002824206080x7f138d92a5000x7f1281c35440655361843302366218412074899891141796120748998913252431207489989157980112074899891648258
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00308523438523484194304256002424213120x7f138d92a4000x7f1281c354801310722573243301802412074899891674226120748998918567601207489989198683912074899891989432
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00328523438523484194304256002424220160x7f138d92a3000x7f1281c354c01310722639623396504012074899892038503120748998922146781207489989234779812074899892350252
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00348523438523484194304256002424227200x7f138d92aa000x7f1281c355001310722534063272176012074899892413410120748998925781961207489989271035612074899892712846
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00368523438523484194304256002824236800x7f138d92a9000x7f1281c355401310722190782797372812074899892762649120748998929314751207489989318843412074899893256667
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00388523438523484194304256002824243840x7f138d92a8000x7f1281c35580655361843062356692812074899893281322120748998934724321207489989372155112074899893789407
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00408523438523484194304256002424250880x7f138d92a7000x7f1281c355c01310722522623233930412074899893815495120748998939956301207489989412282912074899894125611
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00428523438523484194304256002424257920x7f138d92a6000x7f1281c356001310722592443319500012074899894181395120748998943535481207489989448970712074899894492183
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00448523438523484194304256002424264960x7f138d92a5000x7f1281c356401310722776043552945612074899894552785120748998947186661207489989485066612074899894853174
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00468523438523484194304256002824277120x7f138d92a4000x7f1281c356801310722124462710629612074899894900341120748998950802641207489989533450312074899895402665
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00488523438523484194304256002824284160x7f138d92a3000x7f1281c356c0655361849882366510412074899895430476120748998956140221207489989586634112074899895934092
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00508523438523484194304256002424291200x7f138d92aa000x7f1281c357001310722605303337773612074899895959980120748998961509791207489989627897912074899896281919
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00528523438523484194304256002424300800x7f138d92a9000x7f1281c357401310722589803316846412074899896329958120748998965055381207489989663833712074899896640936
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00548523438523484194304256002424307840x7f138d92a8000x7f1281c357801310722568543287933612074899896700216120748998968666561207489989699961512074899897006125
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00568523438523484194304256002824320000x7f138d92a7000x7f1281c357c01310722226442852630412074899897052801120748998972309741207489989748153312074899897549334
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00588523438523484194304256002824329600x7f138d92a6000x7f1281c35800655361885142402077612074899897573679120748998977560921207489989800985012074899898078918
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00608523438523484194304256002424339200x7f138d92a5000x7f1281c358401310722578223311668812074899898106289120748998982968891207489989842792812074899898430492
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00628523438523484194304256002424348800x7f138d92a4000x7f1281c358801310722789723571175212074899898477359120748998986501671207489989878168712074899898784139
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00648523438523484194304256002424358400x7f138d92a3000x7f1281c358c01310722578483294892012074899898843429120748998990072861207489989913496512074899899137876
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00668523438523484194304256002824373120x7f138d92aa000x7f1281c359001310722172902786801612074899899189061120748998993612041207489989961960312074899899687237
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00688523438523484194304256002824382720x7f138d92a9000x7f1281c35940655361882602400364012074899899715720120748998998916011207489990014072012074899900208596
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00708523438523484194304256002424392320x7f138d92a8000x7f1281c359801310722595443321540812074899900234534120748999004152791207489990055207812074899900554970
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00728523438523484194304256002424401920x7f138d92a7000x7f1281c359c01310722630263367160812074899900602859120748999007837571207489990091863612074899900921070
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00748523438523484194304256002424411520x7f138d92a6000x7f1281c35a001310722533243242657612074899900981192120748999011515951207489990128151512074899901283994
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00768523438523484194304256002824426240x7f138d92a5000x7f1281c35a401310722124642719130412074899901332424120748999015043941207489990176711212074899901834387
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00788523438523484194304256002824435840x7f138d92a4000x7f1281c35a80655361895002426241612074899901860416120748999020522311207489990230759012074899902378178
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00808523438523484194304256002424445440x7f138d92a3000x7f1281c35ac01310722562243279706412074899902401942120748999025871081207489990272230812074899902725042
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00828523438523484194304256002424457600x7f138d92aa000x7f1281c35b001310722656403407115212074899902774675120748999029453471207489990308214612074899903085091
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00848523438523484194304256002424467200x7f138d92a9000x7f1281c35b401310722633983352904812074899903152447120748999033192651207489990344758412074899903450120
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00868523438523484194304256002824484480x7f138d92a8000x7f1281c35b801310722201502824900012074899903500844120748999036650231207489990393302212074899904010091
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00888523438523484194304256002824494080x7f138d92a7000x7f1281c35bc0655361832242345083212074899904034346120748999042216611207489990451429912074899904582945
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00908523438523484194304256002424503680x7f138d92a6000x7f1281c35c001310722540963250007212074899904609484120748999047954181207489990493093712074899904933507
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00928523438523484194304256002424515840x7f138d92a5000x7f1281c35c401310722442083121638412074899904984111120748999051722161207489990530629512074899905309215
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00948523438523484194304256002424525440x7f138d92a4000x7f1281c35c801310722533343241461612074899905370368120748999055381341207489990566981412074899905672470
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00968523438523484194304256002824542720x7f138d92a3000x7f1281c35cc01310722169022773675212074899905719918120748999058909331207489990615429112074899906224275
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00988523438523484194304256002824554880x7f138d92aa000x7f1281c35d00655361900202430652012074899906254211120748999064334901207489990668884912074899906757156
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001008523438523484194304256002424567040x7f138d92a9000x7f1281c35d401310722534323232553612074899906782493120748999069606871207489990709460712074899907097618
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001028523438523484194304256002424581760x7f138d92a8000x7f1281c35d801310722583703301112812074899907150196120748999073192461207489990745652512074899907459150
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001048523438523484194304256002424593920x7f138d92a7000x7f1281c35dc01310722602423319875212074899907518220120748999076818041207489990781172312074899907814400
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001068523438523484194304256002824613760x7f138d92a6000x7f1281c35e001310722730703498999212074899907864253120748999080398821207489990829732112074899908366737
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001088523438523484194304256002824625920x7f138d92a5000x7f1281c35e40655361889502412884012074899908393637120748999085749201207489990883075812074899908899817
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001108523438523484194304256002424638080x7f138d92a4000x7f1281c35e801310722598363341833612074899908923261120748999091197171207489990925107612074899909253735
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001128523438523484194304256002424652800x7f138d92a3000x7f1281c35ec01310722590003320612812074899909305281120748999094741151207489990962051512074899909623142
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001148523438523484194304256002424664960x7f138d92aa000x7f1281c35f001310722610683346013612074899909684075120748999098485131207489990998755312074899909990264
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001168523438523484194304256002824684800x7f138d92a9000x7f1281c35f401310722583903310756812074899910045947120748999102144321207489991048195012074899910550475
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001188523438523484194304256002824696960x7f138d92a8000x7f1281c35f80655361828442349975212074899910577635120748999107552291207489991100274812074899911045795
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001208523438523484194304256002424709120x7f138d92a7000x7f1281c35fc01310722793483578944812074899911070131120748999112531471207489991138802612074899911390556
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001228523438523484194304256002424723840x7f138d92a6000x7f1281c360001310722573503301247212074899911441361120748999116059451207489991174658412074899911749123
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001248523438523484194304256002424736000x7f138d92a5000x7f1281c360401310722621383363850412074899911808242120748999119749031207489991210802312074899912110855
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001268523438523484194304256002824758400x7f138d92a4000x7f1281c360801310722218262830588012074899912162861120748999123288221207489991259218012074899912661067
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001288523438523484194304256002824770560x7f138d92a3000x7f1281c360c0655361781602287000812074899912687707120748999128670591207489991312513812074899913194499
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001308523438523484194304256002424782720x7f138d92aa000x7f1281c361001310722595943327664012074899913219335120748999134009761207489991353537612074899913537927
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001328523438523484194304256002424800000x7f138d92a9000x7f1281c361401310722297602940243212074899913584984120748999137542551207489991390017412074899913902905
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001348523438523484194304256002424812160x7f138d92a8000x7f1281c361801310722712863464940012074899913964610120748999141361731207489991427425212074899914276860
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001368523438523484194304256002824834560x7f138d92a7000x7f1281c361c01310722449403140006412074899914324639120748999144952111207489991476305012074899914786848
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001388523438523484194304256002824849280x7f138d92a6000x7f1281c36200655361886002405370412074899914827814120748999149894491207489991524560812074899915296585
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001408523438523484194304256002424864000x7f138d92a5000x7f1281c362401310722605383307833612074899915323545120748999155024061207489991563328612074899915636196
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001428523438523484194304256002424881280x7f138d92a4000x7f1281c362801310722204082816512812074899915687612120748999158542451207489991600432412074899916007005
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001448523438523484194304256002424896000x7f138d92a3000x7f1281c362c01310722574863300442412074899916095470120748999162587231207489991639264212074899916395347
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001468523438523484194304256002824920960x7f138d92aa000x7f1281c363001310722229182836920812074899916442715120748999166161611207489991688144012074899916930842
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001488523438523484194304256002824935680x7f138d92a9000x7f1281c36340655361844382350787212074899916957191120748999171420781207489991739967712074899917449897
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001508523438523484194304256002424950400x7f138d92a8000x7f1281c363801310722601543332026412074899917473901120748999176542361207489991778639512074899917789317
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001528523438523484194304256002424967680x7f138d92a7000x7f1281c363c01310722605343341033612074899917835573120748999180039941207489991816255412074899918165597
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001548523438523484194304256002424982400x7f138d92a6000x7f1281c364001310722612923336581612074899918226630120748999183956721207489991852799212074899918530886
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015685234385234841943042560028241007360x7f138d92a5000x7f1281c364401310722188502791727212074899918577362120748999187502311207489991901406912074899919064407
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015885234385234841943042560028241022080x7f138d92a4000x7f1281c36480655361898822430998412074899919092359120748999192732681207489991952734712074899919576519
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016085234385234841943042560024241036800x7f138d92a3000x7f1281c364c01310722568843288745612074899919599491120748999197814261207489991991790512074899919920518
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016285234385234841943042560024241056640x7f138d92aa000x7f1281c365001310722591403311800812074899919970571120748999201515041207489992031710312074899920320080
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016485234385234841943042560024241071360x7f138d92a9000x7f1281c365401310722566563293023212074899920380623120748999205439821207489992067838112074899920681482
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016685234385234841943042560028241098880x7f138d92a8000x7f1281c365801310722164682766888012074899920730844120748999209025401207489992116253912074899921211567
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016885234385234841943042560028241113600x7f138d92a7000x7f1281c365c0655361957322514620812074899921237576120748999214162981207489992167213712074899921721525
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017085234385234841943042560024241128320x7f138d92a6000x7f1281c366001310722593143306878412074899921744247120748999219316551207489992207005512074899922073609
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017285234385234841943042560024241148160x7f138d92a5000x7f1281c366401310722560703278760012074899922124363120748999222922941207489992246733312074899922469956
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017485234385234841943042560024241162880x7f138d92a4000x7f1281c366801310722561723280964812074899922531250120748999226943721207489992282925112074899922831898
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017685234385234841943042560028241190400x7f138d92a3000x7f1281c366c01310722156322767873612074899922879266120748999230599701207489992331916912074899923369968
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017885234385234841943042560028241207680x7f138d92aa000x7f1281c36700655361773022259532012074899923394163120748999235759671207489992382828612074899923877552
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018085234385234841943042560024241224960x7f138d92a9000x7f1281c367401310722544743248209612074899923901726120748999240924451207489992422876412074899924231740
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018285234385234841943042560024241247360x7f138d92a8000x7f1281c367801310722574443314953612074899924280691120748999244540431207489992463628212074899924639287
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018485234385234841943042560024241264640x7f138d92a7000x7f1281c367c01310722583563288416812074899924698878120748999248633211207489992499996112074899925005748
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018685234385234841943042560020241279360x7f138d92a6000x7f1281c368001310722603863315104812074899925054699120748999252204401207489992548731812074899925536234
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018885234385234841943042560028241296640x7f138d92a5000x7f1281c36840655361777082277436012074899925562753120748999257396371207489992599723612074899926020724
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019085234385234841943042560024241313920x7f138d92a4000x7f1281c368801310722723143482692812074899926063804120748999262287551207489992635963412074899926362570
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019285234385234841943042560024241336320x7f138d92a3000x7f1281c368c01310722572563303036812074899926411721120748999265831531207489992677515212074899926824448
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019485234385234841943042560024241353600x7f138d92aa000x7f1281c369001310722511183220233612074899926865053120748999270367511207489992717627012074899927179057
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019685234385234841943042560020241368320x7f138d92a9000x7f1281c369401310722612803335646412074899927226315120748999274015491207489992768730812074899927736663
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019885234385234841943042560028241385600x7f138d92a8000x7f1281c36980655361910162461102412074899927761690120748999279458661207489992819898512074899928250268
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020085234385234841943042560024241402880x7f138d92a7000x7f1281c369c01310722578583300304012074899928274112120748999284567441207489992859658312074899928599316
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020285234385234841943042560024241427840x7f138d92a6000x7f1281c36a001310722600223323788012074899928653407120748999288138621207489992902410112074899929073638
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020485234385234841943042560024241447680x7f138d92a5000x7f1281c36a401310722596343318450412074899929115075120748999292801001207489992941721912074899929420072
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020685234385234841943042560020241457280x7f138d92a4000x7f1281c36a801310722588343327216812074899929467440120748999296370581207489992994393712074899929970004
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020885234385234841943042560028241477120x7f138d92a3000x7f1281c36ac0655361831802350808012074899930017893120748999301816961207489993043945512074899930467708
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021085234385234841943042560024241496960x7f138d92aa000x7f1281c36b001310722599283315066412074899930511019120748999306768931207489993081257312074899930815375
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021285234385234841943042560024241521920x7f138d92a9000x7f1281c36b401310722599163318239212074899930868273120748999310359321207489993126425112074899931291028
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021485234385234841943042560024241541760x7f138d92a8000x7f1281c36b801310722853943648601612074899931354877120748999315223291207489993166104912074899931663921
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021685234385234841943042560020241556480x7f138d92a7000x7f1281c36bc01310722587743307739212074899931711820120748999318922481207489993225192612074899932280367
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021885234385234841943042560028241576320x7f138d92a6000x7f1281c36c00655361875462400980812074899932323337120748999324919251207489993275192312074899932776629
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022085234385234841943042560024241596160x7f138d92a5000x7f1281c36c401310722544563259076812074899932819198120748999329804711207489993312047112074899933127421
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022285234385234841943042560024241623680x7f138d92a4000x7f1281c36c801310722499683178526412074899933171493120748999333470291207489993359182712074899933616961
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022485234385234841943042560024241646080x7f138d92a3000x7f1281c36cc01310722547503273518412074899933672053120748999338366261207489993397806612074899933980607
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022685234385234841943042560020241663360x7f138d92aa000x7f1281c36d001310722580443314940012074899934034577120748999342086251207489993458478312074899934612391
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022885234385234841943042560028241685760x7f138d92a9000x7f1281c36d40655361721062213603212074899934649099120748999348103821207489993506782112074899935095609
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023085234385234841943042560024241708160x7f138d92a8000x7f1281c36d801310722298082939942412074899935137807120748999353028601207489993544621912074899935449026
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023285234385234841943042560024241740800x7f138d92a7000x7f1281c36dc01310722605683336471212074899935500692120748999356670181207489993594733712074899935973841
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023485234385234841943042560024241765760x7f138d92a6000x7f1281c36e001310722635303354047212074899936037269120748999362070161207489993635021512074899936352895
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023685234385234841943042560020241777920x7f138d92a5000x7f1281c36e401310722554963276028012074899936401315120748999365742141207489993700045212074899937026687
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023885234385234841943042560028241802880x7f138d92a4000x7f1281c36e80655361917842463112012074899937075168120748999372465311207489993750557012074899937530263
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024085234385234841943042560024241827840x7f138d92a3000x7f1281c36ec01310722628183334060812074899937581278120748999377489291207489993789292812074899937895422
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024285234385234841943042560024241863040x7f138d92aa000x7f1281c36f001310722592043319308812074899937947839120748999381174071207489993843228612074899938461384
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024485234385234841943042560024241893120x7f138d92a9000x7f1281c36f401310722561403300658412074899938518710120748999386828441207489993883468412074899938837182
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024685234385234841943042560020241907840x7f138d92a8000x7f1281c36f801310722599403305101612074899938890812120748999390732431207489993959164012074899939618744
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024885234385234841943042560028241937920x7f138d92a7000x7f1281c36fc0655361832882353069612074899939670240120748999398348391207489994013291812074899940160391
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025085234385234841943042560024241968000x7f138d92a6000x7f1281c370001310722538663252681612074899940204924120748999403700371207489994052443612074899940526942
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025285234385234841943042560024242010880x7f138d92a5000x7f1281c370401310722580603313571212074899940576645120748999407500351207489994113643312074899941163876
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025485234385234841943042560024242046080x7f138d92a4000x7f1281c370801310722630363348188812074899941223517120748999413903521207489994156571112074899941568297
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025685234385234841943042560020242060800x7f138d92a3000x7f1281c370c01310722606543342824012074899941615034120748999417967501207489994240874812074899942438705
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025885234385234841943042560028242096000x7f138d92aa000x7f1281c37100655362123722733720012074899942479681120748999426442661207489994297130512074899942997203
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026085234385234841943042560024242131200x7f138d92a9000x7f1281c371401310722561583282321612074899943048869120748999432194641207489994339834312074899943401294
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026285234385234841943042560024242181760x7f138d92a8000x7f1281c371801310722591423309812812074899943449684120748999436212221207489994407722012074899944102397
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026485234385234841943042560024242222080x7f138d92a7000x7f1281c371c01310722580183320612812074899944164372120748999443301791207489994453049812074899944579323
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026685234385234841943042560020242239360x7f138d92a6000x7f1281c372001310722608303340997612074899944609749120748999447839371207489994548809412074899945538335
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026885234385234841943042560028242279680x7f138d92a5000x7f1281c37240655361858502371345612074899945562720120748999457495321207489994612377112074899946173686
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027085234385234841943042560024242320000x7f138d92a4000x7f1281c372801310722574283292361612074899946198161120748999463884101207489994659176912074899946639742
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027285234385234841943042560024242378240x7f138d92a3000x7f1281c372c01310722559043281146412074899946666572120748999468442471207489994737048512074899947422096
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027485234385234841943042560024242423680x7f138d92aa000x7f1281c373001310722593183319500812074899947462000120748999476279241207489994785240312074899947900836
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027685234385234841943042560020242435840x7f138d92a9000x7f1281c373401310722494983222932812074899947926964120748999481218421207489994892199812074899948974771
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027885234385234841943042560028242481280x7f138d92a8000x7f1281c37380655361879402398767212074899949007071120748999491877571207489994960919512074899949660325
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028085234385234841943042560024242526720x7f138d92a7000x7f1281c373c01310722514523230643212074899949687085120748999498639141207489995008999312074899950141620
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028285234385234841943042560024242592640x7f138d92a6000x7f1281c374001310722614943360911212074899950169271120748999503503121207489995094726912074899950996969
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028485234385234841943042560024242648320x7f138d92a5000x7f1281c374401310722711663457955212074899951047724120748999512141481207489995151510612074899951566698
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028685234385234841943042560020242663040x7f138d92a4000x7f1281c374801310722449003161836812074899951591464120748999517760651207489995276294112074899952831889
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028885234385234841943042560028242718720x7f138d92a3000x7f1281c374c0655361935302472204812074899952863658120748999530549391207489995356997712074899953639210
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029085234385234841943042560024242774400x7f138d92aa000x7f1281c375001310722599083324308812074899953663375120748999538523761207489995412341512074899954192728
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029285234385234841943042560012242799360x7f138d92a9000x7f1281c375401310722554603282720812074899954224067120748999544006931207489995514021012074899955208726
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029485234385234841943042560024242865280x7f138d92a8000x7f1281c375801310722772523537398412074899955250374120748999554182891207489995573508712074899955803892
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029685234385234841943042560020242880000x7f138d92a7000x7f1281c375c01310722788143572678412074899955834589120748999560240461207489995719684112074899957267943
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029885234385234841943042560032242945920x7f138d92a6000x7f1281c37600655361911142427322412074899957300143120748999574750791207489995808739712074899958156925
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030085234385234841943042560024243011840x7f138d92a5000x7f1281c376401310722534683241712012074899958187602120748999583717151207489995869091412074899958759836
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030285234385234841943042560012243049600x7f138d92a4000x7f1281c376801310722567043286684812074899958791555120748999589680331207489995984706912074899959917988
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030485234385234841943042560024243136000x7f138d92a3000x7f1281c376c01310722717483501888012074899959964615120748999601393871207489996055106512074899960620874
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030685234385234841943042560020243148160x7f138d92aa000x7f1281c377001310722611563330048012074899960645089120748999608326641207489996238193712074899962451696
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030885234385234841943042560020243175680x7f138d92a9000x7f1281c37740655362037342616014412074899962486030120748999626664161207489996346321212074899963533747
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031085234385234841943042560012243203200x7f138d92a8000x7f1281c377801310722574923301869612074899963565216120748999637438511207489996415920912074899964229290
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031285234385234841943042560012243240960x7f138d92a7000x7f1281c377c01310722685043429576812074899964261420120748999644374481207489996559648312074899965665769
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031485234385234841943042560012243288960x7f138d92a6000x7f1281c378001310722556563271676812074899965710523120748999658790411207489996666447812074899966734706
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031685234385234841943042560020243301120x7f138d92a5000x7f1281c378401310722598003337648012074899966765974120748999669495971207489997000222312074899970073070
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031885234385234841943042560020243328640x7f138d92a4000x7f1281c37880655361893962408156812074899970104107120748999702859011207489997182941412074899971898532
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032085234385234841943042560012243356160x7f138d92a3000x7f1281c378c01310722583503331928012074899971930321120748999721113331207489997290221012074899972973440
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032285234385234841943042560012243393920x7f138d92aa000x7f1281c379001310722598543329220812074899973010378120748999731993281207489997548267812074899975552723
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032485234385234841943042560012243441920x7f138d92a9000x7f1281c379401310722741123507482412074899975599209120748999757658771207489997730251012074899977373236
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032685234385234841943042560020243454080x7f138d92a8000x7f1281c379801310722752383531284012074899977404083120748999775884281207489998364840112074899983722075
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032885234385234841943042560020243481600x7f138d92a7000x7f1281c379c0655361867882376310412074899983748965120748999839343201207489998697990612074899987051622
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033085234385234841943042560012243509120x7f138d92a6000x7f1281c37a001310722531623241008012074899987082349120748999872679051207489998880725812074899988877435
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332852343852348419430425600122400x7f138d92a5000x7f1281c37a401310722718883453036812074899988908453120748999890981361207489999362659612074899993701430