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

40 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_LDSSQ_INST_LEVEL_LDSSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000852721852726335544322560083264640x00x7f6e8fa0418000012074902136846207120749023844907771207490238481589512074902384929407
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00285272185272632768256002424124800x00x7f6e8fa3510000012074902399651707120749023999538921207490239996077212074902399971361
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0048527218527264194304256002424129280x7f6fbfb0d9000x7f6e8fa3514000012074902400033135120749024002492501207490240038412912074902400387534
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0068527218527264194304256003624136320x7f6fbfb0d8000x7f6e8fa3518000012074902400454078120749024006278081207490240088556712074902400955339
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0088527218527264194304256002824140800x7f6fbfb0d7000x7f6e8fa351c000012074902400982059120749024011806051207490240143500412074902401506163
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00108527218527264194304256002424145280x7f6fbfb0d6000x7f6e8fa3520000012074902401535267120749024017241221207490240185164112074902401854510
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00128527218527264194304256002424149760x7f6fbfb0d5000x7f6e8fa3524000012074902401916155120749024020961201207490240223435912074902402237261
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00148527218527264194304256002424154240x7f6fbfb0d4000x7f6e8fa3528000012074902402316439120749024024885981207490240261931712074902402622437
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00168527218527264194304256002824161280x7f6fbfb0d3000x7f6e8fa352c000012074902402670436120749024028465161207490240310811412074902403151581
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00188527218527264194304256002824168320x7f6fbfb0da000x7f6e8fa3530000012074902403178851120749024033625131207490240361755212074902403685934
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00208527218527264194304256002424175360x7f6fbfb0d9000x7f6e8fa3534000012074902403711681120749024039093901207490240404314912074902404046253
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00228527218527264194304256002424182400x7f6fbfb0d8000x7f6e8fa3538000012074902404095475120749024042721081207490240441210712074902404414938
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00248527218527264194304256002424189440x7f6fbfb0d7000x7f6e8fa353c000012074902404475461120749024046450661207490240477626512074902404778995
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00268527218527264194304256002824199040x7f6fbfb0d6000x7f6e8fa3540000012074902404827475120749024049996241207490240526042312074902405331201
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00288527218527264194304256002824206080x7f6fbfb0d5000x7f6e8fa3544000012074902405356679120749024055465011207490240580698012074902405876995
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00308527218527264194304256002424213120x7f6fbfb0d4000x7f6e8fa3548000012074902405903174120749024060944981207490240622249712074902406225423
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00328527218527264194304256002424220160x7f6fbfb0d3000x7f6e8fa354c000012074902406272651120749024064476161207490240658617612074902406588928
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00348527218527264194304256002424227200x7f6fbfb0da000x7f6e8fa3550000012074902406648770120749024068162541207490240694937412074902406952174
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00368527218527264194304256002824236800x7f6fbfb0d9000x7f6e8fa3554000012074902407009250120749024071815321207490240743977112074902407508537
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00388527218527264194304256002824243840x7f6fbfb0d8000x7f6e8fa3558000012074902407534155120749024077236091207490240798472812074902408054753
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00408527218527264194304256002424250880x7f6fbfb0d7000x7f6e8fa355c000012074902408080370120749024082685661207490240840216612074902408405033
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00428527218527264194304256002424257920x7f6fbfb0d6000x7f6e8fa3560000012074902408455327120749024086200841207490240875288412074902408755615
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00448527218527264194304256002424264960x7f6fbfb0d5000x7f6e8fa3564000012074902408815687120749024089826421207490240911240212074902409115564
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00468527218527264194304256002824277120x7f6fbfb0d4000x7f6e8fa3568000012074902409163613120749024093389611207490240960727912074902409676536
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00488527218527264194304256002824284160x7f6fbfb0d3000x7f6e8fa356c000012074902409703627120749024098835981207490241014071612074902410209727
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00508527218527264194304256002424291200x7f6fbfb0da000x7f6e8fa3570000012074902410236848120749024104203951207490241055447412074902410557433
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00528527218527264194304256002424300800x7f6fbfb0d9000x7f6e8fa3574000012074902410605052120749024107787931207490241091607212074902410918975
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00548527218527264194304256002424307840x7f6fbfb0d8000x7f6e8fa3578000012074902410978907120749024111538311207490241129143012074902411294683
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00568527218527264194304256002824320000x7f6fbfb0d7000x7f6e8fa357c000012074902411343484120749024115168691207490241177798712074902411847371
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00588527218527264194304256002824329600x7f6fbfb0d6000x7f6e8fa3580000012074902411871566120749024120735061207490241232566412074902412396421
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00608527218527264194304256002424339200x7f6fbfb0d5000x7f6e8fa3584000012074902412419814120749024126120631207490241274342212074902412746291
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00628527218527264194304256002424348800x7f6fbfb0d4000x7f6e8fa3588000012074902412793799120749024129647011207490241310438012074902413107492
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00648527218527264194304256002424358400x7f6fbfb0d3000x7f6e8fa358c000012074902413168015120749024133363791207490241346965812074902413472451
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00668527218527264194304256002824373120x7f6fbfb0da000x7f6e8fa3590000012074902413519157120749024136971771207490241395653512074902414027412
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00688527218527264194304256002824382720x7f6fbfb0d9000x7f6e8fa3594000012074902414051627120749024142397341207490241449909212074902414542369
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00708527218527264194304256002424392320x7f6fbfb0d8000x7f6e8fa3598000012074902414568097120749024147456511207490241492581012074902414928657
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00728527218527264194304256002424401920x7f6fbfb0d7000x7f6e8fa359c000012074902414977007120749024151600491207490241529876812074902415301620
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00748527218527264194304256002424411520x7f6fbfb0d6000x7f6e8fa35a0000012074902415362944120749024155334871207490241566516612074902415668141
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00768527218527264194304256002824426240x7f6fbfb0d5000x7f6e8fa35a4000012074902415715248120749024158926851207490241614500312074902416214266
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00788527218527264194304256002824435840x7f6fbfb0d4000x7f6e8fa35a8000012074902416238391120749024164238821207490241668596012074902416754931
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00808527218527264194304256002424445440x7f6fbfb0d3000x7f6e8fa35ac000012074902416781650120749024169702791207490241710483812074902417108107
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00828527218527264194304256002424457600x7f6fbfb0da000x7f6e8fa35b0000012074902417156016120749024173334771207490241747379612074902417476592
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00848527218527264194304256002424467200x7f6fbfb0d9000x7f6e8fa35b4000012074902417538938120749024177046751207490241783571412074902417838604
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00868527218527264194304256002824484480x7f6fbfb0d8000x7f6e8fa35b8000012074902417885512120749024180753931207490241834643112074902418391261
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00888527218527264194304256002824494080x7f6fbfb0d7000x7f6e8fa35bc000012074902418415376120749024186000301207490241885890912074902418903203
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00908527218527264194304256002424503680x7f6fbfb0d6000x7f6e8fa35c0000012074902418923921120749024191182671207490241925314712074902419256780
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00928527218527264194304256002424515840x7f6fbfb0d5000x7f6e8fa35c4000012074902419304178120749024194790651207490241961826512074902419621097
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00948527218527264194304256002424525440x7f6fbfb0d4000x7f6e8fa35c8000012074902419680858120749024198449831207490241998498312074902419987949
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00968527218527264194304256002824542720x7f6fbfb0d3000x7f6e8fa35cc000012074902420036509120749024202161811207490242048690012074902420555513
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00988527218527264194304256002824554880x7f6fbfb0da000x7f6e8fa35d0000012074902420579308120749024207608181207490242101121712074902421061874
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001008527218527264194304256002424567040x7f6fbfb0d9000x7f6e8fa35d4000012074902421083264120749024212700961207490242140721512074902421410142
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001028527218527264194304256002424581760x7f6fbfb0d8000x7f6e8fa35d8000012074902421461036120749024216236941207490242176993312074902421772766
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001048527218527264194304256002424593920x7f6fbfb0d7000x7f6e8fa35dc000012074902421834160120749024219966521207490242213313112074902422136361
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001068527218527264194304256002824613760x7f6fbfb0d6000x7f6e8fa35e0000012074902422183839120749024223608101207490242261920812074902422662990
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001088527218527264194304256002824625920x7f6fbfb0d5000x7f6e8fa35e4000012074902422688618120749024228691271207490242312448512074902423170493
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001108527218527264194304256002424638080x7f6fbfb0d4000x7f6e8fa35e8000012074902423197283120749024233761641207490242351456312074902423517478
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001128527218527264194304256002424652800x7f6fbfb0d3000x7f6e8fa35ec000012074902423564746120749024237352021207490242387312112074902423876084
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001148527218527264194304256002424664960x7f6fbfb0da000x7f6e8fa35f0000012074902423938240120749024241163201207490242425151912074902424254598
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001168527218527264194304256002824684800x7f6fbfb0d9000x7f6e8fa35f4000012074902424302036120749024244766381207490242473695712074902424806984
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001188527218527264194304256002824696960x7f6fbfb0d8000x7f6e8fa35f8000012074902424830979120749024250135951207490242527055412074902425342449
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001208527218527264194304256002424709120x7f6fbfb0d7000x7f6e8fa35fc000012074902425367105120749024255548721207490242568335112074902425686318
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001228527218527264194304256002424723840x7f6fbfb0d6000x7f6e8fa3600000012074902425733606120749024259052701207490242604527012074902426048511
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001248527218527264194304256002424736000x7f6fbfb0d5000x7f6e8fa3604000012074902426110416120749024262772681207490242640798812074902426411055
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001268527218527264194304256002824758400x7f6fbfb0d4000x7f6e8fa3608000012074902426457421120749024266299061207490242689726512074902426967319
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001288527218527264194304256002824770560x7f6fbfb0d3000x7f6e8fa360c000012074902426989971120749024271807831207490242743182212074902427501371
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001308527218527264194304256002424782720x7f6fbfb0da000x7f6e8fa3610000012074902427525496120749024277142201207490242784958012074902427852534
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001328527218527264194304256002424800000x7f6fbfb0d9000x7f6e8fa3614000012074902427899912120749024280918181207490242823613812074902428239152
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001348527218527264194304256002424812160x7f6fbfb0d8000x7f6e8fa3618000012074902428299975120749024284655761207490242859949612074902428602568
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001368527218527264194304256002824834560x7f6fbfb0d7000x7f6e8fa361c000012074902428650587120749024288239741207490242909005312074902429142531
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001388527218527264194304256002824849280x7f6fbfb0d6000x7f6e8fa3620000012074902429169952120749024293519711207490242960461012074902429654683
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001408527218527264194304256002424864000x7f6fbfb0d5000x7f6e8fa3624000012074902429681563120749024298596491207490243000028812074902430006357
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001428527218527264194304256002424881280x7f6fbfb0d4000x7f6e8fa3628000012074902430051060120749024302244471207490243037644612074902430379440
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001448527218527264194304256002424896000x7f6fbfb0d3000x7f6e8fa362c000012074902430460010120749024306249251207490243075580412074902430758745
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001468527218527264194304256002824920960x7f6fbfb0da000x7f6e8fa3630000012074902430805251120749024309767631207490243124700112074902431298738
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001488527218527264194304256002824935680x7f6fbfb0d9000x7f6e8fa3634000012074902431323625120749024315065201207490243176843812074902431818845
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001508527218527264194304256002424950400x7f6fbfb0d8000x7f6e8fa3638000012074902431841667120749024320357971207490243217323612074902432176229
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001528527218527264194304256002424967680x7f6fbfb0d7000x7f6e8fa363c000012074902432224158120749024323988351207490243255787412074902432560834
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001548527218527264194304256002424982400x7f6fbfb0d6000x7f6e8fa3640000012074902432620675120749024327823531207490243291851212074902432921554
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015685272185272641943042560028241007360x7f6fbfb0d5000x7f6e8fa3644000012074902432968702120749024331569111207490243342890912074902433482366
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015885272185272641943042560028241022080x7f6fbfb0d4000x7f6e8fa3648000012074902433505469120749024336897081207490243395066612074902434005979
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016085272185272641943042560024241036800x7f6fbfb0d3000x7f6e8fa364c000012074902434033931120749024342156251207490243435834412074902434361700
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016285272185272641943042560024241056640x7f6fbfb0da000x7f6e8fa3650000012074902434407666120749024345793031207490243474650212074902434749892
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016485272185272641943042560024241071360x7f6fbfb0d9000x7f6e8fa3654000012074902434810484120749024349741811207490243511034012074902435114099
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016685272185272641943042560028241098880x7f6fbfb0d8000x7f6e8fa3658000012074902435160735120749024353340191207490243559913712074902435648943
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016885272185272641943042560028241113600x7f6fbfb0d7000x7f6e8fa365c000012074902435673208120749024358562561207490243610825512074902436159271
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017085272185272641943042560024241128320x7f6fbfb0d6000x7f6e8fa3660000012074902436185540120749024363711331207490243651465212074902436517657
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017285272185272641943042560024241148160x7f6fbfb0d5000x7f6e8fa3664000012074902436564865120749024367365711207490243691049012074902436913422
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017485272185272641943042560024241162880x7f6fbfb0d4000x7f6e8fa3668000012074902436973394120749024371450491207490243728392812074902437287177
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017685272185272641943042560028241190400x7f6fbfb0d3000x7f6e8fa366c000012074902437334876120749024375088871207490243777304612074902437823003
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017885272185272641943042560028241207680x7f6fbfb0da000x7f6e8fa3670000012074902437846136120749024380343241207490243829336312074902438345243
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018085272185272641943042560024241224960x7f6fbfb0d9000x7f6e8fa3674000012074902438367595120749024385543211207490243869416112074902438697177
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018285272185272641943042560024241247360x7f6fbfb0d8000x7f6e8fa3678000012074902438743834120749024389143191207490243909799812074902439101729
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018485272185272641943042560024241264640x7f6fbfb0d7000x7f6e8fa367c000012074902439165498120749024393306371207490243947511612074902439478018
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018685272185272641943042560020241279360x7f6fbfb0d6000x7f6e8fa3680000012074902439524455120749024396954351207490243996119412074902440019294
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018885272185272641943042560028241296640x7f6fbfb0d5000x7f6e8fa3684000012074902440042958120749024402338321207490244049335112074902440516809
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019085272185272641943042560024241313920x7f6fbfb0d4000x7f6e8fa3688000012074902440555872120749024407173501207490244085750912074902440860508
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019285272185272641943042560024241336320x7f6fbfb0d3000x7f6e8fa368c000012074902440907094120749024410856681207490244127798712074902441329890
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019485272185272641943042560024241353600x7f6fbfb0da000x7f6e8fa3690000012074902441367269120749024415301451207490244167190412074902441674981
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019685272185272641943042560020241368320x7f6fbfb0d9000x7f6e8fa3694000012074902441725555120749024418882231207490244217222212074902442222659
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019885272185272641943042560028241385600x7f6fbfb0d8000x7f6e8fa3698000012074902442249128120749024424304601207490244269333912074902442743327
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020085272185272641943042560024241402880x7f6fbfb0d7000x7f6e8fa369c000012074902442771198120749024429498171207490244308645712074902443090422
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020285272185272641943042560024241427840x7f6fbfb0d6000x7f6e8fa36a0000012074902443137760120749024433082151207490244352053412074902443569833
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020485272185272641943042560024241447680x7f6fbfb0d5000x7f6e8fa36a4000012074902443607593120749024437734931207490244391605212074902443919202
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020685272185272641943042560020241457280x7f6fbfb0d4000x7f6e8fa36a8000012074902443968574120749024441483711207490244445668912074902444507205
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020885272185272641943042560028241477120x7f6fbfb0d3000x7f6e8fa36ac000012074902444532021120749024447163681207490244498196612074902445033402
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021085272185272641943042560024241496960x7f6fbfb0da000x7f6e8fa36b0000012074902445057888120749024452405251207490244538180412074902445385036
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021285272185272641943042560024241521920x7f6fbfb0d9000x7f6e8fa36b4000012074902445432394120749024456040431207490244583252212074902445882280
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021485272185272641943042560024241541760x7f6fbfb0d8000x7f6e8fa36b8000012074902445922344120749024460947601207490244623860012074902446242169
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021685272185272641943042560020241556480x7f6fbfb0d7000x7f6e8fa36bc000012074902446291350120749024464672381207490244679795612074902446847173
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021885272185272641943042560028241576320x7f6fbfb0d6000x7f6e8fa36c0000012074902446873252120749024470531551207490244731475412074902447338957
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022085272185272641943042560024241596160x7f6fbfb0d5000x7f6e8fa36c4000012074902447378601120749024475408141207490244768049412074902447687445
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022285272185272641943042560024241623680x7f6fbfb0d4000x7f6e8fa36c8000012074902447730314120749024479035311207490244815105012074902448201730
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022485272185272641943042560024241646080x7f6fbfb0d3000x7f6e8fa36cc000012074902448237928120749024484145691207490244855008812074902448552532
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022685272185272641943042560020241663360x7f6fbfb0da000x7f6e8fa36d0000012074902448599259120749024487705671207490244917328612074902449225012
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022885272185272641943042560028241685760x7f6fbfb0d9000x7f6e8fa36d4000012074902449249497120749024494352041207490244970096312074902449750539
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023085272185272641943042560024241708160x7f6fbfb0d8000x7f6e8fa36d8000012074902449773331120749024499636821207490245010640112074902450108965
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023285272185272641943042560024241740800x7f6fbfb0d7000x7f6e8fa36dc000012074902450156212120749024503344001207490245061407912074902450664467
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023485272185272641943042560024241765760x7f6fbfb0d6000x7f6e8fa36e0000012074902450702979120749024508710381207490245101247712074902451015389
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023685272185272641943042560020241777920x7f6fbfb0d5000x7f6e8fa36e4000012074902451062457120749024512391961207490245166383412074902451686937
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023885272185272641943042560028241802880x7f6fbfb0d4000x7f6e8fa36e8000012074902451725970120749024518907131207490245215983212074902452209438
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024085272185272641943042560024241827840x7f6fbfb0d3000x7f6e8fa36ec000012074902452233102120749024524249501207490245256335012074902452565921
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024285272185272641943042560024241863040x7f6fbfb0da000x7f6e8fa36f0000012074902452613068120749024527852691207490245310174712074902453152731
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024485272185272641943042560024241893120x7f6fbfb0d9000x7f6e8fa36f4000012074902453189409120749024533659061207490245351774512074902453520284
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024685272185272641943042560020241907840x7f6fbfb0d8000x7f6e8fa36f8000012074902453566750120749024537403041207490245426078212074902454311625
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024885272185272641943042560028241937920x7f6fbfb0d7000x7f6e8fa36fc000012074902454335309120749024545270211207490245482285912074902454872337
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025085272185272641943042560024241968000x7f6fbfb0d6000x7f6e8fa3700000012074902454894488120749024550882981207490245524477712074902455247654
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025285272185272641943042560024242010880x7f6fbfb0d5000x7f6e8fa3704000012074902455294391120749024554710161207490245585821412074902455881292
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025485272185272641943042560024242046080x7f6fbfb0d4000x7f6e8fa3708000012074902455934170120749024561153331207490245629165212074902456294630
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025685272185272641943042560020242060800x7f6fbfb0d3000x7f6e8fa370c000012074902456343330120749024565169311207490245712844812074902457179013
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025885272185272641943042560028242096000x7f6fbfb0da000x7f6e8fa3710000012074902457202868120749024573862071207490245771548612074902457765062
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026085272185272641943042560024242131200x7f6fbfb0d9000x7f6e8fa3714000012074902457791411120749024579770841207490245815676412074902458159976
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026285272185272641943042560024242181760x7f6fbfb0d8000x7f6e8fa3718000012074902458208296120749024583854031207490245884316012074902458892868
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026485272185272641943042560024242222080x7f6fbfb0d7000x7f6e8fa371c000012074902458931741120749024591065191207490245930667812074902459357872
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026685272185272641943042560020242239360x7f6fbfb0d6000x7f6e8fa3720000012074902459383821120749024595644371207490246026907412074902460320401
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026885272185272641943042560028242279680x7f6fbfb0d5000x7f6e8fa3724000012074902460344396120749024605297131207490246090459112074902460954389
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027085272185272641943042560024242320000x7f6fbfb0d4000x7f6e8fa3728000012074902460976851120749024611706701207490246137370912074902461423712
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027285272185272641943042560024242378240x7f6fbfb0d3000x7f6e8fa372c000012074902461447796120749024616301871207490246215610512074902462207628
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027485272185272641943042560024242423680x7f6fbfb0da000x7f6e8fa3730000012074902462248254120749024624151441207490246264042312074902462690416
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027685272185272641943042560020242435840x7f6fbfb0d9000x7f6e8fa3734000012074902462713949120749024628964211207490246369561812074902463747460
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027885272185272641943042560028242481280x7f6fbfb0d8000x7f6e8fa3738000012074902463774099120749024639552971207490246440057412074902464450937
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028085272185272641943042560024242526720x7f6fbfb0d7000x7f6e8fa373c000012074902464475743120749024646637731207490246489081212074902464940457
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028285272185272641943042560024242592640x7f6fbfb0d6000x7f6e8fa3740000012074902464964922120749024651535311207490246575080812074902465820733
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028485272185272641943042560024242648320x7f6fbfb0d5000x7f6e8fa3744000012074902465859715120749024660370471207490246630728612074902466377447
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028685272185272641943042560020242663040x7f6fbfb0d4000x7f6e8fa3748000012074902466402223120749024665856841207490246757160012074902467641416
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028885272185272641943042560028242718720x7f6fbfb0d3000x7f6e8fa374c000012074902467671823120749024678570381207490246837351612074902468444980
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029085272185272641943042560024242774400x7f6fbfb0da000x7f6e8fa3750000012074902468469545120749024686583151207490246893095312074902468973752
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029285272185272641943042560012242799360x7f6fbfb0d9000x7f6e8fa3754000012074902469005792120749024691874321207490246992598912074902469994710
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029485272185272641943042560024242865280x7f6fbfb0d8000x7f6e8fa3758000012074902470040144120749024702082271207490247052566612074902470595195
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029685272185272641943042560020242880000x7f6fbfb0d7000x7f6e8fa375c000012074902470618930120749024708019851207490247197429912074902472045851
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029885272185272641943042560032242945920x7f6fbfb0d6000x7f6e8fa3760000012074902472078031120749024722597381207490247286981512074902472939883
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030085272185272641943042560024243011840x7f6fbfb0d5000x7f6e8fa3764000012074902472963747120749024731542941207490247350165212074902473573049
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030285272185272641943042560012243049600x7f6fbfb0d4000x7f6e8fa3768000012074902473598487120749024737816511207490247466004712074902474729759
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030485272185272641943042560024243136000x7f6fbfb0d3000x7f6e8fa376c000012074902474771807120749024749397251207490247534932312074902475420493
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030685272185272641943042560020243148160x7f6fbfb0da000x7f6e8fa3770000012074902475447262120749024756286821207490247717667512074902477247598
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030885272185272641943042560020243175680x7f6fbfb0d9000x7f6e8fa3774000012074902477280108120749024774657931207490247826131012074902478330871
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031085272185272641943042560012243203200x7f6fbfb0d8000x7f6e8fa3778000012074902478361618120749024785464281207490247896194612074902479032545
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031285272185272641943042560012243240960x7f6fbfb0d7000x7f6e8fa377c000012074902479064605120749024792475451207490248040690012074902480476899
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031485272185272641943042560012243288960x7f6fbfb0d6000x7f6e8fa3780000012074902480517805120749024806865781207490248147281512074902481542399
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031685272185272641943042560020243301120x7f6fbfb0d5000x7f6e8fa3784000012074902481572856120749024817542531207490248480367912074902484873450
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031885272185272641943042560020243328640x7f6fbfb0d4000x7f6e8fa3788000012074902484906090120749024852631971207490248680559012074902486878876
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032085272185272641943042560012243356160x7f6fbfb0d3000x7f6e8fa378c000012074902486953475120749024873268271207490248811658412074902488188090
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032285272185272641943042560012243393920x7f6fbfb0da000x7f6e8fa3790000012074902488245576120749024885084221207490249079081112074902490861959
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032485272185272641943042560012243441920x7f6fbfb0d9000x7f6e8fa3794000012074902490940905120749024911948091207490249273032212074902492801092
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032685272185272641943042560020243454080x7f6fbfb0d8000x7f6e8fa3798000012074902492854612120749024931176801207490249917557212074902499249576
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032885272185272641943042560020243481600x7f6fbfb0d7000x7f6e8fa379c000012074902499301643120749024995536501207490250259907612074902502670253
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033085272185272641943042560012243509120x7f6fbfb0d6000x7f6e8fa37a0000012074902502723762120749025029737941207490250451394712074902504585011
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332852721852726419430425600122400x7f6fbfb0d5000x7f6e8fa37a4000012074902504639963120749025048795451207490250940880412074902509479677