Files
rocm-systems/tests/workloads/dev1/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.kd000926331926336335544322560083264640x00x7ff791c0418000012076420714122644120764209623842271207642096270886312076420962815735
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00292633192633632768256002424124800x00x7ff791c3510000012076420977185327120764209774960481207642097750212812076420977512665
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0049263319263364194304256002424129280x7ff89d82a9000x7ff791c3514000012076420977573458120764209777835641207642097792164312076420977925592
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0069263319263364194304256003624136320x7ff89d82a8000x7ff791c3518000012076420977995703120764209781822801207642097843203712076420978501242
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0089263319263364194304256002824140800x7ff89d82a7000x7ff791c351c000012076420978531258120764209787176331207642097897427012076420979040083
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00109263319263364194304256002424145280x7ff89d82a6000x7ff791c3520000012076420979064318120764209792533071207642097939010612076420979393841
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00129263319263364194304256002424149760x7ff89d82a5000x7ff791c3524000012076420979448402120764209796147431207642097975362112076420979757286
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00149263319263364194304256002424154240x7ff89d82a4000x7ff791c3528000012076420979837515120764209800025781207642098013345712076420980137082
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00169263319263364194304256002824161280x7ff89d82a3000x7ff791c352c000012076420980193767120764209803665741207642098062497112076420980666225
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00189263319263364194304256002824168320x7ff89d82aa000x7ff791c3530000012076420980692895120764209808716881207642098112784512076420981167426
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00209263319263364194304256002424175360x7ff89d82a9000x7ff791c3534000012076420981192373120764209813857621207642098151408112076420981517818
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00229263319263364194304256002424182400x7ff89d82a8000x7ff791c3538000012076420981568131120764209817503981207642098188575612076420981889498
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00249263319263364194304256002424189440x7ff89d82a7000x7ff791c353c000012076420981952686120764209821244731207642098225519212076420982259185
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00269263319263364194304256002824199040x7ff89d82a6000x7ff791c3540000012076420982313356120764209824815891207642098274174612076420982807334
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00289263319263364194304256002824206080x7ff89d82a5000x7ff791c3544000012076420982833963120764209830145431207642098326494012076420983331387
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00309263319263364194304256002424213120x7ff89d82a4000x7ff791c3548000012076420983359239120764209835514971207642098368061512076420983684333
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00329263319263364194304256002424220160x7ff89d82a3000x7ff791c354c000012076420983733996120764209839073321207642098404557112076420984049292
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00349263319263364194304256002424227200x7ff89d82aa000x7ff791c3550000012076420984111928120764209842794881207642098441068712076420984414460
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00369263319263364194304256002824236800x7ff89d82a9000x7ff791c3554000012076420984463391120764209846390041207642098489772112076420984963420
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00389263319263364194304256002824243840x7ff89d82a8000x7ff791c3558000012076420984988797120764209851821971207642098543371512076420985499627
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00409263319263364194304256002424250880x7ff89d82a7000x7ff791c355c000012076420985525745120764209857149911207642098584507012076420985848836
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00429263319263364194304256002424257920x7ff89d82a6000x7ff791c3560000012076420985902736120764209860717871207642098620874512076420986212752
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00449263319263364194304256002424264960x7ff89d82a5000x7ff791c3564000012076420986274977120764209864474631207642098657674112076420986580796
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00469263319263364194304256002824277120x7ff89d82a4000x7ff791c3568000012076420986629907120764209867997781207642098705305512076420987121210
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00489263319263364194304256002824284160x7ff89d82a3000x7ff791c356c000012076420987146016120764209873316121207642098762312912076420987688785
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00509263319263364194304256002424291200x7ff89d82aa000x7ff791c3570000012076420987713781120764209878922461207642098802152412076420988025540
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00529263319263364194304256002424300800x7ff89d82a9000x7ff791c3574000012076420988077026120764209882479211207642098838200012076420988385910
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00549263319263364194304256002424307840x7ff89d82a8000x7ff791c3578000012076420988448266120764209886128771207642098874439612076420988748213
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00569263319263364194304256002824320000x7ff89d82a7000x7ff791c357c000012076420988796864120764209889690331207642098922647012076420989292745
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00589263319263364194304256002824329600x7ff89d82a6000x7ff791c3580000012076420989319425120764209895112671207642098976374412076420989830795
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00609263319263364194304256002424339200x7ff89d82a5000x7ff791c3584000012076420989857985120764209900437401207642099017381912076420990177850
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00629263319263364194304256002424348800x7ff89d82a4000x7ff791c3588000012076420990221701120764209904048561207642099054325412076420990546926
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00649263319263364194304256002424358400x7ff89d82a3000x7ff791c358c000012076420990609341120764209907750921207642099090613012076420990909890
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00669263319263364194304256002824373120x7ff89d82aa000x7ff791c3590000012076420990964381120764209911349271207642099139124412076420991458379
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00689263319263364194304256002824382720x7ff89d82a9000x7ff791c3594000012076420991482274120764209916674011207642099191891812076420991985879
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00709263319263364194304256002424392320x7ff89d82a8000x7ff791c3598000012076420992019061120764209921982751207642099233635312076420992340198
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00729263319263364194304256002424401920x7ff89d82a7000x7ff791c359c000012076420992389159120764209925646711207642099269906912076420992702942
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00749263319263364194304256002424411520x7ff89d82a6000x7ff791c35a0000012076420992766420120764209929304261207642099306210512076420993066247
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00769263319263364194304256002824426240x7ff89d82a5000x7ff791c35a4000012076420993114817120764209932965021207642099354609912076420993613414
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00789263319263364194304256002824435840x7ff89d82a4000x7ff791c35a8000012076420993639182120764209938156961207642099406161312076420994108263
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00809263319263364194304256002424445440x7ff89d82a3000x7ff791c35ac000012076420994133771120764209943172901207642099448800812076420994491946
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00829263319263364194304256002424457600x7ff89d82aa000x7ff791c35b0000012076420994546908120764209947217651207642099485360412076420994857255
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00849263319263364194304256002424467200x7ff89d82a9000x7ff791c35b4000012076420994918358120764209950920011207642099522383912076420995227854
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00869263319263364194304256002824484480x7ff89d82a8000x7ff791c35b8000012076420995277846120764209954524771207642099571743412076420995782945
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00889263319263364194304256002824494080x7ff89d82a7000x7ff791c35bc000012076420995805757120764209959849501207642099627710712076420996344348
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00909263319263364194304256002424503680x7ff89d82a6000x7ff791c35c0000012076420996372791120764209965513441207642099668094212076420996684861
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00929263319263364194304256002424515840x7ff89d82a5000x7ff791c35c4000012076420996733121120764209969033401207642099704509812076420997049068
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00949263319263364194304256002424525440x7ff89d82a4000x7ff791c35c8000012076420997112566120764209972815751207642099740845412076420997412313
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00969263319263364194304256002824542720x7ff89d82a3000x7ff791c35cc000012076420997462556120764209976353311207642099790204812076420997942478
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00989263319263364194304256002824554880x7ff89d82aa000x7ff791c35d0000012076420997967765120764209981548451207642099840924212076420998476370
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001009263319263364194304256002424567040x7ff89d82a9000x7ff791c35d4000012076420998501797120764209986860391207642099881403712076420998818015
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001029263319263364194304256002424581760x7ff89d82a8000x7ff791c35d8000012076420998870863120764209990394751207642099917931312076420999183424
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001049263319263364194304256002424593920x7ff89d82a7000x7ff791c35dc000012076420999246010120764209994081101207642099953578912076420999539836
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001069263319263364194304256002824613760x7ff89d82a6000x7ff791c35e0000012076420999588096120764209997641061207642100003002312076421000097482
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001089263319263364194304256002824625920x7ff89d82a5000x7ff791c35e4000012076421000128089120764210003049001207642100055993712076421000625353
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001109263319263364194304256002424638080x7ff89d82a4000x7ff791c35e8000012076421000650079120764210008272941207642100096361212076421000967519
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001129263319263364194304256002424652800x7ff89d82a3000x7ff791c35ec000012076421001019305120764210011892091207642100132792812076421001331846
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001149263319263364194304256002424664960x7ff89d82aa000x7ff791c35f0000012076421001395274120764210015578451207642100168888312076421001692817
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001169263319263364194304256002824684800x7ff89d82a9000x7ff791c35f4000012076421001740876120764210019116011207642100217895812076421002230816
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001189263319263364194304256002824696960x7ff89d82a8000x7ff791c35f8000012076421002256093120764210024386351207642100268791212076421002735594
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001209263319263364194304256002424709120x7ff89d82a7000x7ff791c35fc000012076421002763106120764210029407091207642100306950712076421003073552
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001229263319263364194304256002424723840x7ff89d82a6000x7ff791c3600000012076421003123966120764210032971841207642100343542312076421003439312
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001249263319263364194304256002424736000x7ff89d82a5000x7ff791c3604000012076421003499734120764210036661401207642100379445912076421003798469
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001269263319263364194304256002824758400x7ff89d82a4000x7ff791c3608000012076421003848082120764210040248561207642100428773312076421004335337
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001289263319263364194304256002824770560x7ff89d82a3000x7ff791c360c000012076421004360794120764210045437301207642100479908712076421004844663
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001309263319263364194304256002424782720x7ff89d82aa000x7ff791c3610000012076421004873437120764210050557241207642100518580212076421005190055
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001329263319263364194304256002424800000x7ff89d82a9000x7ff791c3614000012076421005238906120764210054176401207642100556099812076421005565012
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001349263319263364194304256002424812160x7ff89d82a8000x7ff791c3618000012076421005628500120764210057923551207642100592419412076421005928257
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001369263319263364194304256002824834560x7ff89d82a7000x7ff791c361c000012076421005979572120764210061531511207642100641426812076421006463632
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001389263319263364194304256002824849280x7ff89d82a6000x7ff791c3620000012076421006489169120764210066688251207642100692034212076421006968350
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001409263319263364194304256002424864000x7ff89d82a5000x7ff791c3624000012076421006994458120764210071814591207642100731489712076421007319021
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001429263319263364194304256002424881280x7ff89d82a4000x7ff791c3628000012076421007368533120764210075420951207642100769249312076421007696473
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001449263319263364194304256002424896000x7ff89d82a3000x7ff791c362c000012076421007776502120764210079368101207642100806704812076421008071389
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001469263319263364194304256002824920960x7ff89d82aa000x7ff791c3630000012076421008120861120764210082964861207642100855696312076421008603819
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001489263319263364194304256002824935680x7ff89d82a9000x7ff791c3634000012076421008625679120764210088078401207642100905839712076421009078661
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001509263319263364194304256002424950400x7ff89d82a8000x7ff791c3638000012076421009130728120764210092940741207642100942271212076421009426858
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001529263319263364194304256002424967680x7ff89d82a7000x7ff791c363c000012076421009474607120764210096470301207642100980446812076421009808417
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001549263319263364194304256002424982400x7ff89d82a6000x7ff791c3640000012076421009869631120764210100415851207642101016862412076421010172965
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015692633192633641943042560028241007360x7ff89d82a5000x7ff791c3644000012076421010225743120764210103891011207642101065197812076421010703410
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015892633192633641943042560028241022080x7ff89d82a4000x7ff791c3648000012076421010732084120764210109207751207642101117693212076421011225621
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016092633192633641943042560024241036800x7ff89d82a3000x7ff791c364c000012076421011250457120764210114324491207642101156828712076421011572305
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016292633192633641943042560024241056640x7ff89d82aa000x7ff791c3650000012076421011622458120764210117882851207642101195308312076421011957070
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016492633192633641943042560024241071360x7ff89d82a9000x7ff791c3654000012076421012029585120764210121953201207642101232571812076421012329993
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016692633192633641943042560028241098880x7ff89d82a8000x7ff791c3658000012076421012379194120764210125495561207642101281419312076421012834240
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016892633192633641943042560028241113600x7ff89d82a7000x7ff791c365c000012076421012879193120764210130477901207642101330090712076421013347053
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017092633192633641943042560024241128320x7ff89d82a6000x7ff791c3660000012076421013371137120764210135673041207642101370522212076421013709416
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017292633192633641943042560024241148160x7ff89d82a5000x7ff791c3664000012076421013760401120764210139241001207642101409689712076421014101094
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017492633192633641943042560024241162880x7ff89d82a4000x7ff791c3668000012076421014165714120764210143344951207642101446649312076421014470620
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017692633192633641943042560028241190400x7ff89d82a3000x7ff791c366c000012076421014518429120764210146896911207642101494904712076421014994995
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017892633192633641943042560028241207680x7ff89d82aa000x7ff791c3670000012076421015027044120764210152090441207642101545720112076421015504822
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018092633192633641943042560024241224960x7ff89d82a9000x7ff791c3674000012076421015533516120764210157051991207642101584279712076421015846978
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018292633192633641943042560024241247360x7ff89d82a8000x7ff791c3678000012076421015897973120764210160592741207642101624055212076421016244757
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018492633192633641943042560024241264640x7ff89d82a7000x7ff791c367c000012076421016308686120764210164703101207642101660630812076421016610427
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018692633192633641943042560020241279360x7ff89d82a6000x7ff791c3680000012076421016659217120764210168285451207642101709350212076421017139860
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018892633192633641943042560028241296640x7ff89d82a5000x7ff791c3684000012076421017161711120764210173501391207642101760373612076421017648786
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019092633192633641943042560024241313920x7ff89d82a4000x7ff791c3688000012076421017674915120764210178507731207642101798869212076421017992865
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019292633192633641943042560024241336320x7ff89d82a3000x7ff791c368c000012076421018042538120764210182120491207642101840308712076421018452129
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019492633192633641943042560024241353600x7ff89d82aa000x7ff791c3690000012076421018492524120764210186589241207642101879732212076421018801739
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019692633192633641943042560020241368320x7ff89d82a9000x7ff791c3694000012076421018849617120764210190242001207642101933811612076421019387818
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019892633192633641943042560028241385600x7ff89d82a8000x7ff791c3698000012076421019414858120764210195950731207642101989138912076421019937088
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020092633192633641943042560024241402880x7ff89d82a7000x7ff791c369c000012076421019962876120764210201478661207642102028178512076421020285997
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020292633192633641943042560024241427840x7ff89d82a6000x7ff791c36a0000012076421020334978120764210205045021207642102071442012076421020760598
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020492633192633641943042560024241447680x7ff89d82a5000x7ff791c36a4000012076421020800863120764210209625771207642102109937512076421021103916
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020692633192633641943042560020241457280x7ff89d82a4000x7ff791c36a8000012076421021156484120764210213350521207642102164192912076421021688182
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020892633192633641943042560028241477120x7ff89d82a3000x7ff791c36ac000012076421021711445120764210218945661207642102214304312076421022193170
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021092633192633641943042560024241496960x7ff89d82aa000x7ff791c36b0000012076421022223537120764210224009601207642102253919812076421022543541
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021292633192633641943042560024241521920x7ff89d82a9000x7ff791c36b4000012076421022592743120764210227641561207642102299087312076421023039423
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021492633192633641943042560024241541760x7ff89d82a8000x7ff791c36b8000012076421023080159120764210232435101207642102338142812076421023385706
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021692633192633641943042560020241556480x7ff89d82a7000x7ff791c36bc000012076421023437733120764210236011061207642102392974212076421023976093
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021892633192633641943042560028241576320x7ff89d82a6000x7ff791c36c0000012076421024006780120764210241938991207642102445053612076421024498765
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022092633192633641943042560024241596160x7ff89d82a5000x7ff791c36c4000012076421024524312120764210247036531207642102484189112076421024846230
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022292633192633641943042560024241623680x7ff89d82a4000x7ff791c36c8000012076421024895722120764210250583691207642102530380612076421025350537
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022492633192633641943042560024241646080x7ff89d82a3000x7ff791c36cc000012076421025388358120764210255602291207642102569910812076421025706208
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022692633192633641943042560020241663360x7ff89d82aa000x7ff791c36d0000012076421025750801120764210259211841207642102629798012076421026347079
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022892633192633641943042560028241685760x7ff89d82a9000x7ff791c36d4000012076421026370883120764210265525381207642102681397512076421026858590
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023092633192633641943042560024241708160x7ff89d82a8000x7ff791c36d8000012076421026885870120764210270664521207642102720821112076421027211956
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023292633192633641943042560024241740800x7ff89d82a7000x7ff791c36dc000012076421027259244120764210274326881207642102771140512076421027757059
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023492633192633641943042560024241765760x7ff89d82a6000x7ff791c36e0000012076421027795861120764210279562031207642102809172112076421028095308
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023692633192633641943042560020241777920x7ff89d82a5000x7ff791c36e4000012076421028144419120764210283173191207642102874163412076421028787714
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023892633192633641943042560028241802880x7ff89d82a4000x7ff791c36e8000012076421028815015120764210289899521207642102925042912076421029301209
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024092633192633641943042560024241827840x7ff89d82a3000x7ff791c36ec000012076421029330603120764210295088261207642102964914512076421029652762
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024292633192633641943042560024241863040x7ff89d82aa000x7ff791c36f0000012076421029704338120764210298689821207642103018497912076421030234513
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024492633192633641943042560024241893120x7ff89d82a9000x7ff791c36f4000012076421030271532120764210304444961207642103059697512076421030600493
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024692633192633641943042560020241907840x7ff89d82a8000x7ff791c36f8000012076421030648362120764210308163321207642103133296712076421031380482
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024892633192633641943042560028241937920x7ff89d82a7000x7ff791c36fc000012076421031406090120764210315856041207642103188368112076421031929653
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025092633192633641943042560024241968000x7ff89d82a6000x7ff791c3700000012076421031955621120764210321406381207642103229471712076421032298318
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025292633192633641943042560024242010880x7ff89d82a5000x7ff791c3704000012076421032350234120764210325155141207642103289951012076421032918220
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025492633192633641943042560024242046080x7ff89d82a4000x7ff791c3708000012076421032977931120764210331491071207642103332510612076421033328823
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025692633192633641943042560020242060800x7ff89d82a3000x7ff791c370c000012076421033378615120764210335521431207642103417325712076421034220520
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025892633192633641943042560028242096000x7ff89d82aa000x7ff791c3710000012076421034246478120764210344356541207642103476413012076421034809835
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026092633192633641943042560024242131200x7ff89d82a9000x7ff791c3714000012076421034835512120764210350258881207642103520412612076421035208556
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026292633192633641943042560024242181760x7ff89d82a8000x7ff791c3718000012076421035258118120764210354359631207642103591227812076421035957918
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026492633192633641943042560024242222080x7ff89d82a7000x7ff791c371c000012076421035999215120764210361655551207642103640171312076421036447237
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026692633192633641943042560020242239360x7ff89d82a6000x7ff791c3720000012076421036472224120764210366517901207642103736090312076421037407923
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026892633192633641943042560028242279680x7ff89d82a5000x7ff791c3724000012076421037434873120764210376146601207642103798841612076421038036130
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027092633192633641943042560024242320000x7ff89d82a4000x7ff791c3728000012076421038065975120764210382496931207642103845385112076421038499801
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027292633192633641943042560024242378240x7ff89d82a3000x7ff791c372c000012076421038525179120764210387029681207642103922808312076421039275363
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027492633192633641943042560024242423680x7ff89d82aa000x7ff791c3730000012076421039318974120764210394839201207642103970855812076421039754483
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027692633192633641943042560020242435840x7ff89d82a9000x7ff791c3734000012076421039777215120764210399591151207642104075830712076421040810225
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027892633192633641943042560028242481280x7ff89d82a8000x7ff791c3738000012076421040837215120764210410235841207642104144405912076421041492753
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028092633192633641943042560024242526720x7ff89d82a7000x7ff791c373c000012076421041517739120764210417037371207642104192997412076421041975941
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028292633192633641943042560024242592640x7ff89d82a6000x7ff791c3740000012076421042005696120764210421880511207642104278372512076421042832242
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028492633192633641943042560024242648320x7ff89d82a5000x7ff791c3744000012076421042873328120764210430397221207642104330948012076421043360203
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028692633192633641943042560020242663040x7ff89d82a4000x7ff791c3748000012076421043384137120764210435662771207642104454930612076421044616487
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028892633192633641943042560028242718720x7ff89d82a3000x7ff791c374c000012076421044646563120764210448297831207642104536257812076421045432283
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029092633192633641943042560024242774400x7ff89d82aa000x7ff791c3750000012076421045462560120764210456449751207642104591617212076421045981574
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029292633192633641943042560012242799360x7ff89d82a9000x7ff791c3754000012076421046011650120764210461953691207642104693376112076421047005457
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029492633192633641943042560024242865280x7ff89d82a8000x7ff791c3758000012076421047045892120764210472102381207642104752607512076421047594090
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029692633192633641943042560020242880000x7ff89d82a7000x7ff791c375c000012076421047618025120764210478019121207642104897181912076421049039196
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029892633192633641943042560032242945920x7ff89d82a6000x7ff791c3760000012076421049067087120764210492540561207642104986349012076421049929600
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030092633192633641943042560024243011840x7ff89d82a5000x7ff791c3764000012076421049957823120764210501418871207642105046076412076421050527642
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030292633192633641943042560012243049600x7ff89d82a4000x7ff791c3768000012076421050550033120764210507330811207642105161067112076421051677538
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030492633192633641943042560024243136000x7ff89d82a3000x7ff791c376c000012076421051721730120764210518847491207642105231658412076421052383670
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030692633192633641943042560020243148160x7ff89d82aa000x7ff791c3770000012076421052415119120764210525965811207642105414232512076421054210375
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030892633192633641943042560020243175680x7ff89d82a9000x7ff791c3774000012076421054239549120764210544164021207642105520999312076421055276596
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031092633192633641943042560012243203200x7ff89d82a8000x7ff791c3778000012076421055300861120764210554893501207642105590310612076421055969363
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031292633192633641943042560012243240960x7ff89d82a7000x7ff791c377c000012076421055995272120764210561851831207642105734373112076421057410712
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031492633192633641943042560012243288960x7ff89d82a6000x7ff791c3780000012076421057456757120764210576211681207642105840771912076421058475009
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031692633192633641943042560020243301120x7ff89d82a5000x7ff791c3784000012076421058503041120764210586846761207642106173264412076421061801340
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031892633192633641943042560020243328640x7ff89d82a4000x7ff791c3788000012076421061832138120764210620268811207642106356734412076421063615662
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032092633192633641943042560012243356160x7ff89d82a3000x7ff791c378c000012076421063644816120764210638286221207642106461805312076421064665482
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032292633192633641943042560012243393920x7ff89d82aa000x7ff791c3790000012076421064693725120764210648782111207642106716058612076421067227583
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032492633192633641943042560012243441920x7ff89d82a9000x7ff791c3794000012076421067270673120764210674372231207642106897208712076421069039660
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032692633192633641943042560020243454080x7ff89d82a8000x7ff791c3798000012076421069071810120764210692540041207642107530562012076421075372709
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032892633192633641943042560020243481600x7ff89d82a7000x7ff791c379c000012076421075401162120764210755801771207642107862062512076421078687819
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033092633192633641943042560012243509120x7ff89d82a6000x7ff791c37a0000012076421078718917120764210789007821207642108043932512076421080511758
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332926331926336419430425600122400x7ff89d82a5000x7ff791c37a4000012076421080541754120764210807222021207642108524919412076421085316757