Files
rocm-systems/tests/workloads/mixbench/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.kd000748123748128335544322560083264640x00x7f14cf20418000012073198620537158120731988637029011207319886402817912073198864137881
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00274812374812832768256002424124800x00x7f14cf23510000012073198878460684120731988787472601207319887875366012073198878758598
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0047481237481284194304256002424129280x7f15ff4009000x7f14cf23514000012073198878825182120731988790502991207319887918165812073198879185611
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0067481237481284194304256003624136320x7f15ff4008000x7f14cf23518000012073198879253898120731988794224571207319887967381512073198879743237
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0087481237481284194304256002824140800x7f15ff4007000x7f14cf2351c000012073198879778633120731988799539741207319888021173312073198880280476
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00107481237481284194304256002424145280x7f15ff4006000x7f14cf23520000012073198880309449120731988804899711207319888062709012073198880630526
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00127481237481284194304256002424149760x7f15ff4005000x7f14cf23524000012073198880680960120731988808446891207319888097972912073198880983221
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00147481237481284194304256002424154240x7f15ff4004000x7f14cf23528000012073198881061868120731988812362071207319888137348612073198881377043
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00167481237481284194304256002824161280x7f15ff4003000x7f14cf2352c000012073198881430703120731988815941251207319888188500412073198881928378
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00187481237481284194304256002824168320x7f15ff400a000x7f14cf23530000012073198881956830120731988821403621207319888239220112073198882462019
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00207481237481284194304256002424175360x7f15ff4009000x7f14cf23534000012073198882488438120731988826717201207319888280163912073198882805187
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00227481237481284194304256002424182400x7f15ff4008000x7f14cf23538000012073198882855560120731988830341181207319888316483712073198883168422
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00247481237481284194304256002424189440x7f15ff4007000x7f14cf2353c000012073198883234544120731988834006761207319888353555512073198883539231
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00267481237481284194304256002824199040x7f15ff4006000x7f14cf23540000012073198883589204120731988837545941207319888401267212073198884081969
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00287481237481284194304256002824206080x7f15ff4005000x7f14cf23544000012073198884108659120731988842931511207319888454963012073198884617725
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00307481237481284194304256002424213120x7f15ff4004000x7f14cf23548000012073198884647951120731988848307481207319888496370712073198884967214
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00327481237481284194304256002424220160x7f15ff4003000x7f14cf2354c000012073198885020232120731988851902661207319888536610512073198885369692
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00347481237481284194304256002424227200x7f15ff400a000x7f14cf23550000012073198885436205120731988855979441207319888572898312073198885732666
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00367481237481284194304256002824236800x7f15ff4009000x7f14cf23554000012073198885782890120731988859448221207319888620274112073198886272790
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00387481237481284194304256002824243840x7f15ff4008000x7f14cf23558000012073198886299630120731988864819391207319888673985812073198886807383
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00407481237481284194304256002424250880x7f15ff4007000x7f14cf2355c000012073198886833121120731988870076971207319888714209612073198887145812
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00427481237481284194304256002424257920x7f15ff4006000x7f14cf23560000012073198887190896120731988873649751207319888749841412073198887502074
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00447481237481284194304256002424264960x7f15ff4005000x7f14cf23564000012073198887565191120731988877251331207319888785265212073198887856222
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00467481237481284194304256002824277120x7f15ff4004000x7f14cf23568000012073198887907307120731988880739311207319888832833012073198888396095
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00487481237481284194304256002824284160x7f15ff4003000x7f14cf2356c000012073198888422715120731988886000081207319888885392712073198888921752
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00507481237481284194304256002424291200x7f15ff400a000x7f14cf23570000012073198888947890120731988891316851207319888926480512073198889268657
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00527481237481284194304256002424300800x7f15ff4009000x7f14cf23574000012073198889317958120731988894784041207319888961232312073198889615952
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00547481237481284194304256002424307840x7f15ff4008000x7f14cf23578000012073198889677897120731988898372821207319888996800112073198889971523
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00567481237481284194304256002824320000x7f15ff4007000x7f14cf2357c000012073198890029530120731988901942401207319889045087812073198890495707
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00587481237481284194304256002824329600x7f15ff4006000x7f14cf23580000012073198890520002120731988907047971207319889095967612073198891028667
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00607481237481284194304256002424339200x7f15ff4005000x7f14cf23584000012073198891053172120731988912319941207319889136671412073198891370231
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00627481237481284194304256002424348800x7f15ff4004000x7f14cf23588000012073198891419393120731988915875121207319889172191212073198891725542
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00647481237481284194304256002424358400x7f15ff4003000x7f14cf2358c000012073198891787316120731988919457511207319889208191012073198892085581
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00667481237481284194304256002824373120x7f15ff400a000x7f14cf23590000012073198892135944120731988923012691207319889259806712073198892667402
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00687481237481284194304256002824382720x7f15ff4009000x7f14cf23594000012073198892694081120731988928675061207319889312542412073198893194611
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00707481237481284194304256002424392320x7f15ff4008000x7f14cf23598000012073198893221832120731988933983831207319889353278212073198893536426
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00727481237481284194304256002424401920x7f15ff4007000x7f14cf2359c000012073198893586129120731988937543811207319889389198012073198893895664
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00747481237481284194304256002424411520x7f15ff4006000x7f14cf235a0000012073198893956557120731988941206191207319889425453812073198894258648
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00767481237481284194304256002824426240x7f15ff4005000x7f14cf235a4000012073198894307389120731988944798171207319889473821612073198894807037
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00787481237481284194304256002824435840x7f15ff4004000x7f14cf235a8000012073198894830631120731988950058941207319889525965312073198895330109
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00807481237481284194304256002424445440x7f15ff4003000x7f14cf235ac000012073198895352992120731988955359721207319889566717112073198895670742
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00827481237481284194304256002424457600x7f15ff400a000x7f14cf235b0000012073198895722027120731988958823701207319889601932912073198896023107
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00847481237481284194304256002424467200x7f15ff4009000x7f14cf235b4000012073198896085543120731988962508481207319889638588712073198896389518
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00867481237481284194304256002824484480x7f15ff4008000x7f14cf235b8000012073198896438519120731988966057261207319889687772512073198896945641
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00887481237481284194304256002824494080x7f15ff4007000x7f14cf235bc000012073198896971639120731988971538831207319889741212212073198897482479
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00907481237481284194304256002424503680x7f15ff4006000x7f14cf235c0000012073198897508246120731988976810801207319889781308012073198897816720
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00927481237481284194304256002424515840x7f15ff4005000x7f14cf235c4000012073198897865360120731988980399581207319889817995812073198898184002
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00947481237481284194304256002424525440x7f15ff4004000x7f14cf235c8000012073198898244665120731988984047561207319889853611612073198898539663
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00967481237481284194304256002824542720x7f15ff4003000x7f14cf235cc000012073198898588203120731988987596351207319889903131312073198899100946
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00987481237481284194304256002824554880x7f15ff400a000x7f14cf235d0000012073198899133727120731988993087521207319889956747012073198899635188
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001007481237481284194304256002424567040x7f15ff4009000x7f14cf235d4000012073198899662339120731988998354691207319889996538812073198899969019
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001027481237481284194304256002424581760x7f15ff4008000x7f14cf235d8000012073198900017779120731989001881071207319890032778612073198900331612
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001047481237481284194304256002424593920x7f15ff4007000x7f14cf235dc000012073198900391353120731989005525851207319890068602412073198900689778
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001067481237481284194304256002824613760x7f15ff4006000x7f14cf235e0000012073198900738589120731989008996231207319890117050212073198901241714
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001087481237481284194304256002824625920x7f15ff4005000x7f14cf235e4000012073198901280075120731989014410601207319890169593912073198901763764
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001107481237481284194304256002424638080x7f15ff4004000x7f14cf235e8000012073198901793409120731989019708181207319890210585712073198902109887
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001127481237481284194304256002424652800x7f15ff4003000x7f14cf235ec000012073198902158848120731989023282561207319890246505512073198902468603
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001147481237481284194304256002424664960x7f15ff400a000x7f14cf235f0000012073198902529907120731989026877741207319890282121312073198902824865
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001167481237481284194304256002824684800x7f15ff4009000x7f14cf235f4000012073198902873796120731989030472921207319890331289112073198903383313
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001187481237481284194304256002824696960x7f15ff4008000x7f14cf235f8000012073198903407909120731989035848891207319890384392812073198903911735
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001207481237481284194304256002424709120x7f15ff4007000x7f14cf235fc000012073198903938254120731989041136861207319890425000612073198904253860
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001227481237481284194304256002424723840x7f15ff4006000x7f14cf23600000012073198904305296120731989044642441207319890460376412073198904607367
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001247481237481284194304256002424736000x7f15ff4005000x7f14cf23604000012073198904668341120731989048252031207319890495896212073198904962697
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001267481237481284194304256002824758400x7f15ff4004000x7f14cf23608000012073198905014784120731989051866411207319890545847912073198905531084
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001287481237481284194304256002824770560x7f15ff4003000x7f14cf2360c000012073198905553726120731989057307981207319890598999612073198906077800
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001307481237481284194304256002424782720x7f15ff400a000x7f14cf23610000012073198906101824120731989062858351207319890642039412073198906424233
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001327481237481284194304256002424800000x7f15ff4009000x7f14cf23614000012073198906474186120731989066445531207319890678871212073198906792427
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001347481237481284194304256002424812160x7f15ff4008000x7f14cf23618000012073198906854172120731989070115911207319890714695012073198907150843
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001367481237481284194304256002824834560x7f15ff4007000x7f14cf2361c000012073198907200355120731989073688691207319890763046812073198907681048
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001387481237481284194304256002824849280x7f15ff4006000x7f14cf23620000012073198907708119120731989078781461207319890817078512073198908223496
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001407481237481284194304256002424864000x7f15ff4005000x7f14cf23624000012073198908246339120731989084267841207319890856150312073198908565261
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001427481237481284194304256002424881280x7f15ff4004000x7f14cf23628000012073198908614232120731989087835821207319890893366112073198908937303
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001447481237481284194304256002424896000x7f15ff4003000x7f14cf2362c000012073198909028542120731989091898191207319890932101912073198909324672
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001467481237481284194304256002824920960x7f15ff400a000x7f14cf23630000012073198909377240120731989095422981207319890980661612073198909830843
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001487481237481284194304256002824935680x7f15ff4009000x7f14cf23634000012073198909882549120731989100512551207319891031013412073198910361930
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001507481237481284194304256002424950400x7f15ff4008000x7f14cf23638000012073198910387407120731989105720521207319891070869112073198910712571
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001527481237481284194304256002424967680x7f15ff4007000x7f14cf2363c000012073198910764879120731989109221301207319891107956912073198911083551
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001547481237481284194304256002424982400x7f15ff4006000x7f14cf23640000012073198911144133120731989113024481207319891144196812073198911445704
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015674812374812841943042560028241007360x7f15ff4005000x7f14cf23644000012073198911492871120731989116621261207319891193156512073198911981860
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015874812374812841943042560028241022080x7f15ff4004000x7f14cf23648000012073198912014400120731989121912441207319891245316212073198912504551
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016074812374812841943042560024241036800x7f15ff4003000x7f14cf2364c000012073198912529858120731989127037211207319891284244012073198912846286
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016274812374812841943042560024241056640x7f15ff400a000x7f14cf23650000012073198912893574120731989130669191207319891323331812073198913237283
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016474812374812841943042560024241071360x7f15ff4009000x7f14cf23654000012073198913298346120731989134595571207319891359091612073198913594616
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016674812374812841943042560028241098880x7f15ff4008000x7f14cf23658000012073198913642756120731989138176351207319891408147412073198914133979
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016874812374812841943042560028241113600x7f15ff4007000x7f14cf2365c000012073198914161480120731989143376321207319891459187112073198914639608
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017074812374812841943042560024241128320x7f15ff4006000x7f14cf23660000012073198914663212120731989148416301207319891497666912073198914980632
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017274812374812841943042560024241148160x7f15ff4005000x7f14cf23664000012073198915029603120731989152070681207319891538018712073198915384131
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017474812374812841943042560024241162880x7f15ff4004000x7f14cf23668000012073198915443852120731989156024261207319891574034512073198915744371
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017674812374812841943042560028241190400x7f15ff4003000x7f14cf2366c000012073198915791899120731989159582641207319891621810212073198916250361
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017874812374812841943042560028241207680x7f15ff400a000x7f14cf23670000012073198916290926120731989164509011207319891670978012073198916736003
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018074812374812841943042560024241224960x7f15ff4009000x7f14cf23674000012073198916780556120731989169390591207319891707905812073198917082908
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018274812374812841943042560024241247360x7f15ff4008000x7f14cf23678000012073198917132330120731989172939371207319891747681612073198917480677
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018474812374812841943042560024241264640x7f15ff4007000x7f14cf2367c000012073198917541921120731989177012951207319891783633412073198917840155
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018674812374812841943042560020241279360x7f15ff4006000x7f14cf23680000012073198917887062120731989180670531207319891833425112073198918366152
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018874812374812841943042560028241296640x7f15ff4005000x7f14cf23684000012073198918403251120731989185654501207319891882256912073198918848479
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019074812374812841943042560024241313920x7f15ff4004000x7f14cf23688000012073198918891348120731989190529671207319891919376712073198919197808
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019274812374812841943042560024241336320x7f15ff4003000x7f14cf2368c000012073198919252459120731989194092851207319891960128412073198919627226
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019474812374812841943042560024241353600x7f15ff400a000x7f14cf23690000012073198919682298120731989198414431207319891997904212073198919982716
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019674812374812841943042560020241368320x7f15ff4009000x7f14cf23694000012073198920031226120731989202032011207319892048720012073198920516929
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019874812374812841943042560028241385600x7f15ff4008000x7f14cf23698000012073198920558947120731989207158391207319892097647712073198921005126
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020074812374812841943042560024241402880x7f15ff4007000x7f14cf2369c000012073198921047334120731989212054361207319892134527512073198921349025
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020274812374812841943042560024241427840x7f15ff4006000x7f14cf236a0000012073198921396984120731989215630341207319892177311312073198921794062
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020474812374812841943042560024241447680x7f15ff4005000x7f14cf236a4000012073198921849665120731989220078321207319892214783112073198922152087
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020674812374812841943042560020241457280x7f15ff4004000x7f14cf236a8000012073198922200617120731989223727901207319892271086812073198922737024
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020874812374812841943042560028241477120x7f15ff4003000x7f14cf236ac000012073198922780324120731989229355071207319892319678512073198923223357
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021074812374812841943042560024241496960x7f15ff400a000x7f14cf236b0000012073198923265556120731989234233441207319892355774412073198923561726
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021274812374812841943042560024241521920x7f15ff4009000x7f14cf236b4000012073198923611409120731989237775821207319892400574112073198924032361
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021474812374812841943042560024241541760x7f15ff4008000x7f14cf236b8000012073198924091981120731989242532601207319892439453912073198924398341
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021674812374812841943042560020241556480x7f15ff4007000x7f14cf236bc000012073198924446550120731989246092581207319892496701612073198924992785
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021874812374812841943042560028241576320x7f15ff4006000x7f14cf236c0000012073198925037839120731989251982151207319892546237412073198925487404
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022074812374812841943042560024241596160x7f15ff4005000x7f14cf236c4000012073198925532538120731989256868521207319892582845212073198925832295
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022274812374812841943042560024241623680x7f15ff4004000x7f14cf236c8000012073198925880595120731989260511701207319892629628912073198926326083
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022474812374812841943042560024241646080x7f15ff4003000x7f14cf236cc000012073198926379121120731989265389661207319892667608612073198926683387
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022674812374812841943042560020241663360x7f15ff400a000x7f14cf236d0000012073198926728240120731989268928841207319892727128212073198927299622
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022874812374812841943042560028241685760x7f15ff4009000x7f14cf236d4000012073198927342131120731989275052011207319892777144012073198927795182
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023074812374812841943042560024241708160x7f15ff4008000x7f14cf236d8000012073198927839535120731989279946391207319892813239812073198928136146
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023274812374812841943042560024241740800x7f15ff4007000x7f14cf236dc000012073198928183694120731989283491971207319892863015612073198928654860
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023474812374812841943042560024241765760x7f15ff4006000x7f14cf236e0000012073198928710523120731989288699951207319892900519412073198929008647
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023674812374812841943042560020241777920x7f15ff4005000x7f14cf236e4000012073198929057037120731989292293531207319892965351112073198929679844
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023874812374812841943042560028241802880x7f15ff4004000x7f14cf236e8000012073198929722123120731989298791101207319893014326912073198930171468
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024074812374812841943042560024241827840x7f15ff4003000x7f14cf236ec000012073198930214117120731989303751081207319893051670712073198930520206
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024274812374812841943042560024241863040x7f15ff400a000x7f14cf236f0000012073198930572813120731989307307861207319893104630512073198931071560
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024474812374812841943042560024241893120x7f15ff4009000x7f14cf236f4000012073198931130890120731989312899841207319893144262312073198931445986
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024674812374812841943042560020241907840x7f15ff4008000x7f14cf236f8000012073198931493634120731989316707821207319893218918012073198932214774
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024874812374812841943042560028241937920x7f15ff4007000x7f14cf236fc000012073198932262713120731989324213391207319893272229712073198932745931
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025074812374812841943042560024241968000x7f15ff4006000x7f14cf23700000012073198932790895120731989329494961207319893310469512073198933108204
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025274812374812841943042560024242010880x7f15ff4005000x7f14cf23704000012073198933159580120731989333194141207319893370549312073198933730270
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025474812374812841943042560024242046080x7f15ff4004000x7f14cf23708000012073198933790192120731989339496521207319893412549112073198934129332
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025674812374812841943042560020242060800x7f15ff4003000x7f14cf2370c000012073198934177902120731989343490101207319893495924712073198934984270
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025874812374812841943042560028242096000x7f15ff400a000x7f14cf23710000012073198935035956120731989351938061207319893552260412073198935547537
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026074812374812841943042560024242131200x7f15ff4009000x7f14cf23714000012073198935595696120731989357546031207319893593348312073198935936800
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026274812374812841943042560024242181760x7f15ff4008000x7f14cf23718000012073198935984419120731989361634021207319893661940012073198936645998
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026474812374812841943042560024242222080x7f15ff4007000x7f14cf2371c000012073198936700630120731989368614781207319893706163812073198937090644
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026674812374812841943042560020242239360x7f15ff4006000x7f14cf23720000012073198937122754120731989372957161207319893800003312073198938027264
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026874812374812841943042560028242279680x7f15ff4005000x7f14cf23724000012073198938069673120731989382275521207319893860115112073198938626548
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027074812374812841943042560024242320000x7f15ff4004000x7f14cf23728000012073198938669748120731989388275501207319893903058912073198939056457
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027274812374812841943042560024242378240x7f15ff4003000x7f14cf2372c000012073198939100909120731989392584281207319893978546512073198939812031
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027474812374812841943042560024242423680x7f15ff400a000x7f14cf23730000012073198939867263120731989400334641207319894025746312073198940282244
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027674812374812841943042560020242435840x7f15ff4009000x7f14cf23734000012073198940326577120731989404841821207319894128529812073198941311627
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027874812374812841943042560028242481280x7f15ff4008000x7f14cf23738000012073198941354427120731989415137771207319894193233512073198941959932
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028074812374812841943042560024242526720x7f15ff4007000x7f14cf2373c000012073198942010716120731989421680141207319894239393312073198942422471
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028274812374812841943042560024242592640x7f15ff4006000x7f14cf23740000012073198942467515120731989426224121207319894321953012073198943271138
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028474812374812841943042560024242648320x7f15ff4005000x7f14cf23744000012073198943315200120731989434729681207319894374272712073198943790543
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028674812374812841943042560020242663040x7f15ff4004000x7f14cf23748000012073198943816221120731989439904061207319894497568212073198945047118
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028874812374812841943042560028242718720x7f15ff4003000x7f14cf2374c000012073198945078887120731989452516801207319894576943812073198945837276
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029074812374812841943042560024242774400x7f15ff400a000x7f14cf23750000012073198945864176120731989460412771207319894631407612073198946384453
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029274812374812841943042560012242799360x7f15ff4009000x7f14cf23754000012073198946408177120731989465873541207319894732591112073198947395472
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029474812374812841943042560024242865280x7f15ff4008000x7f14cf23758000012073198947440345120731989476006301207319894791726812073198947985308
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029674812374812841943042560020242880000x7f15ff4007000x7f14cf2375c000012073198948019261120731989481971071207319894936926212073198949440391
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029874812374812841943042560032242945920x7f15ff4006000x7f14cf23760000012073198949469305120731989496523001207319895026269812073198950332769
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030074812374812841943042560024243011840x7f15ff4005000x7f14cf23764000012073198950362725120731989505406161207319895085965512073198950901706
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030274812374812841943042560012243049600x7f15ff4004000x7f14cf23768000012073198950928376120731989511169341207319895199501012073198952066541
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030474812374812841943042560024243136000x7f15ff4003000x7f14cf2376c000012073198952100825120731989522646091207319895269804712073198952765810
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030674812374812841943042560020243148160x7f15ff400a000x7f14cf23770000012073198952796818120731989529722851207319895452043812073198954591322
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030874812374812841943042560020243175680x7f15ff4009000x7f14cf23774000012073198954622540120731989547924371207319895558779412073198955658645
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031074812374812841943042560012243203200x7f15ff4008000x7f14cf23778000012073198955686707120731989558657121207319895628091012073198956350371
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031274812374812841943042560012243240960x7f15ff4007000x7f14cf2377c000012073198956381559120731989565580291207319895771658412073198957786108
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031474812374812841943042560012243288960x7f15ff4006000x7f14cf23780000012073198957832234120731989579916231207319895877801912073198958849494
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031674812374812841943042560020243301120x7f15ff4005000x7f14cf23784000012073198958872617120731989590559381207319896210488412073198962175093
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031874812374812841943042560020243328640x7f15ff4004000x7f14cf23788000012073198962208225120731989623919231207319896393463612073198964012377
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032074812374812841943042560012243356160x7f15ff4003000x7f14cf2378c000012073198964029529120731989642210351207319896501063112073198965079530
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032274812374812841943042560012243393920x7f15ff400a000x7f14cf23790000012073198965111449120731989652887101207319896757013912073198967639677
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032474812374812841943042560012243441920x7f15ff4009000x7f14cf23794000012073198967684010120731989678448581207319896938005112073198969450542
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032674812374812841943042560020243454080x7f15ff4008000x7f14cf23798000012073198969483253120731989696578101207319897571410212073198975784150
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032874812374812841943042560020243481600x7f15ff4007000x7f14cf2379c000012073198975815358120731989759921811207319897903392712073198979107455
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033074812374812841943042560012243509120x7f15ff4006000x7f14cf237a0000012073198979135848120731989793116861207319898085103912073198980920875
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332748123748128419430425600122400x7f15ff4005000x7f14cf237a4000012073198980946092120731989811337581207319898566093712073198985735170