Files
rocm-systems/tests/workloads/Axes3/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.kd000911318911323335544322560083264640x00x7fd3d580418000012076134384262348120761346221861821207613462251194012076134622624233
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00291131891132332768256002424124800x00x7fd3d583510000012076134637155819120761346374540581207613463746141812076134637466817
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0049113189113234194304256002424129280x7fd4e14909000x7fd3d583514000012076134637527059120761346377407771207613463788029612076134637884283
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0069113189113234194304256003624136320x7fd4e14908000x7fd3d583518000012076134637955045120761346381337351207613463838557312076134638454132
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0089113189113234194304256002824140800x7fd4e14907000x7fd3d58351c000012076134638490730120761346386711721207613463892781012076134638991922
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00109113189113234194304256002424145280x7fd4e14906000x7fd3d583520000012076134639028199120761346392078091207613463934396812076134639347653
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00129113189113234194304256002424149760x7fd4e14905000x7fd3d583524000012076134639398217120761346395713271207613463970364612076134639707061
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00149113189113234194304256002424154240x7fd4e14904000x7fd3d583528000012076134639784454120761346399580451207613464009052412076134640094601
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00169113189113234194304256002824161280x7fd4e14903000x7fd3d58352c000012076134640146778120761346403188431207613464061356112076134640656295
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00189113189113234194304256002824168320x7fd4e1490a000x7fd3d583530000012076134640681832120761346408650801207613464111563812076134641155372
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00209113189113234194304256002424175360x7fd4e14909000x7fd3d583534000012076134641183495120761346413765971207613464150635612076134641509891
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00229113189113234194304256002424182400x7fd4e14908000x7fd3d583538000012076134641559794120761346417330751207613464186891412076134641872675
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00249113189113234194304256002424189440x7fd4e14907000x7fd3d58353c000012076134641935652120761346421122731207613464224411212076134642248053
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00269113189113234194304256002824199040x7fd4e14906000x7fd3d583540000012076134642301773120761346424721111207613464273067012076134642795150
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00289113189113234194304256002824206080x7fd4e14905000x7fd3d583544000012076134642820868120761346429972281207613464324938712076134643315256
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00309113189113234194304256002424213120x7fd4e14904000x7fd3d583548000012076134643343268120761346435226651207613464365306512076134643656841
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00329113189113234194304256002424220160x7fd4e14903000x7fd3d58354c000012076134643708597120761346438804241207613464401466312076134644018303
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00349113189113234194304256002424227200x7fd4e1490a000x7fd3d583550000012076134644081881120761346442455421207613464437594112076134644379414
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00369113189113234194304256002824236800x7fd4e14909000x7fd3d583554000012076134644428746120761346445948201207613464484457812076134644909058
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00389113189113234194304256002824243840x7fd4e14908000x7fd3d583558000012076134644932462120761346451264971207613464537865512076134645444273
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00409113189113234194304256002424250880x7fd4e14907000x7fd3d58355c000012076134645468017120761346456488941207613464577849312076134645782291
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00429113189113234194304256002424257920x7fd4e14906000x7fd3d583560000012076134645831623120761346459948121207613464612585112076134646129587
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00449113189113234194304256002424264960x7fd4e14905000x7fd3d583564000012076134646191442120761346463588101207613464648984912076134646493463
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00469113189113234194304256002824277120x7fd4e14904000x7fd3d583568000012076134646541682120761346467152881207613464697240712076134647038065
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00489113189113234194304256002824284160x7fd4e14903000x7fd3d58356c000012076134647062490120761346472472851207613464749528412076134647559704
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00509113189113234194304256002424291200x7fd4e1490a000x7fd3d583570000012076134647586013120761346477604031207613464789256212076134647896290
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00529113189113234194304256002424300800x7fd4e14909000x7fd3d583574000012076134647945612120761346481133611207613464828792012076134648291885
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00549113189113234194304256002424307840x7fd4e14908000x7fd3d583578000012076134648355273120761346485197581207613464864919812076134648652636
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00569113189113234194304256002824320000x7fd4e14907000x7fd3d58357c000012076134648706676120761346488669571207613464912663512076134649191487
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00589113189113234194304256002824329600x7fd4e14906000x7fd3d583580000012076134649215161120761346493999141207613464964855212076134649713147
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00609113189113234194304256002424339200x7fd4e14905000x7fd3d583584000012076134649737632120761346499176711207613465004743012076134650051636
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00629113189113234194304256002424348800x7fd4e14904000x7fd3d583588000012076134650100036120761346502723891207613465040822812076134650412095
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00649113189113234194304256002424358400x7fd4e14903000x7fd3d58358c000012076134650472878120761346506352671207613465076550612076134650769309
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00669113189113234194304256002824373120x7fd4e1490a000x7fd3d583590000012076134650820244120761346509858251207613465123766412076134651303803
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00689113189113234194304256002824382720x7fd4e14909000x7fd3d583594000012076134651329260120761346515083821207613465175974112076134651823779
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00709113189113234194304256002424392320x7fd4e14908000x7fd3d583598000012076134651849417120761346520330191207613465216821912076134652172146
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00729113189113234194304256002424401920x7fd4e14907000x7fd3d58359c000012076134652222811120761346523894981207613465252341712076134652526876
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00749113189113234194304256002424411520x7fd4e14906000x7fd3d5835a0000012076134652587859120761346527501361207613465288197512076134652885682
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00769113189113234194304256002824426240x7fd4e14905000x7fd3d5835a4000012076134652936777120761346531130141207613465337269212076134653437197
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00789113189113234194304256002824435840x7fd4e14904000x7fd3d5835a8000012076134653463867120761346536432511207613465389332912076134653931957
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00809113189113234194304256002424445440x7fd4e14903000x7fd3d5835ac000012076134653957114120761346541421281207613465427348712076134654277319
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00829113189113234194304256002424457600x7fd4e1490a000x7fd3d5835b0000012076134654327803120761346544997261207613465463252512076134654636266
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00849113189113234194304256002424467200x7fd4e14909000x7fd3d5835b4000012076134654698612120761346548594041207613465499172312076134654995634
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00869113189113234194304256002824484480x7fd4e14908000x7fd3d5835b8000012076134655045496120761346552170021207613465548228112076134655546748
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00889113189113234194304256002824494080x7fd4e14907000x7fd3d5835bc000012076134655571805120761346557502791207613465600083812076134656065933
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00909113189113234194304256002424503680x7fd4e14906000x7fd3d5835c0000012076134656089437120761346562715571207613465640355612076134656407407
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00929113189113234194304256002424515840x7fd4e14905000x7fd3d5835c4000012076134656455767120761346566209951207613465675731412076134656760794
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00949113189113234194304256002424525440x7fd4e14904000x7fd3d5835c8000012076134656822719120761346569864331207613465711971212076134657124119
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00969113189113234194304256002824542720x7fd4e14903000x7fd3d5835cc000012076134657178160120761346573480311207613465761122912076134657652241
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00989113189113234194304256002824554880x7fd4e1490a000x7fd3d5835d0000012076134657677167120761346578529881207613465810450712076134658175033
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001009113189113234194304256002424567040x7fd4e14909000x7fd3d5835d4000012076134658202253120761346583763451207613465850786412076134658511578
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001029113189113234194304256002424581760x7fd4e14908000x7fd3d5835d8000012076134658562022120761346587321831207613465887106212076134658874833
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001049113189113234194304256002424593920x7fd4e14907000x7fd3d5835dc000012076134658934514120761346591057811207613465923938012076134659243568
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001069113189113234194304256002824613760x7fd4e14906000x7fd3d5835e0000012076134659292339120761346594616191207613465972849812076134659794442
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001089113189113234194304256002824625920x7fd4e14905000x7fd3d5835e4000012076134659820110120761346599947361207613466025329512076134660318616
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001109113189113234194304256002424638080x7fd4e14904000x7fd3d5835e8000012076134660346308120761346605182541207613466064753312076134660651305
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001129113189113234194304256002424652800x7fd4e14903000x7fd3d5835ec000012076134660699985120761346608638521207613466100385112076134661007527
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001149113189113234194304256002424664960x7fd4e1490a000x7fd3d5835f0000012076134661072257120761346612353701207613466136528912076134661369099
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001169113189113234194304256002824684800x7fd4e14909000x7fd3d5835f4000012076134661416827120761346615867281207613466184496612076134661884647
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001189113189113234194304256002824696960x7fd4e14908000x7fd3d5835f8000012076134661909803120761346620907251207613466234416412076134662410153
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001209113189113234194304256002424709120x7fd4e14907000x7fd3d5835fc000012076134662435871120761346626121621207613466274608212076134662749995
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001229113189113234194304256002424723840x7fd4e14906000x7fd3d583600000012076134662801270120761346629648001207613466310544012076134663109523
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001249113189113234194304256002424736000x7fd4e14905000x7fd3d583604000012076134663172701120761346633363181207613466346751812076134663471446
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001269113189113234194304256002824758400x7fd4e14904000x7fd3d583608000012076134663524344120761346636846361207613466394799512076134663993836
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001289113189113234194304256002824770560x7fd4e14903000x7fd3d58360c000012076134664023341120761346642051141207613466446063212076134664507952
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001309113189113234194304256002424782720x7fd4e1490a000x7fd3d583610000012076134664532668120761346647105511207613466484383012076134664847283
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001329113189113234194304256002424800000x7fd4e14909000x7fd3d583614000012076134664898107120761346650708691207613466521534812076134665219424
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001349113189113234194304256002424812160x7fd4e14908000x7fd3d583618000012076134665282171120761346654393471207613466557102612076134665574945
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001369113189113234194304256002824834560x7fd4e14907000x7fd3d58361c000012076134665625248120761346657892651207613466604958412076134666097757
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001389113189113234194304256002824849280x7fd4e14906000x7fd3d583620000012076134666122102120761346663020621207613466655854112076134666604568
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001409113189113234194304256002424864000x7fd4e14905000x7fd3d583624000012076134666631519120761346668030201207613466693917912076134666943138
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001429113189113234194304256002424881280x7fd4e14904000x7fd3d583628000012076134666992730120761346671617381207613466731245712076134667316712
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001449113189113234194304256002424896000x7fd4e14903000x7fd3d58362c000012076134667398975120761346675566151207613466769053512076134667694514
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001469113189113234194304256002824920960x7fd4e1490a000x7fd3d583630000012076134667747503120761346679023741207613466816813212076134668214621
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001489113189113234194304256002824935680x7fd4e14909000x7fd3d583634000012076134668241711120761346684161311207613466866876912076134668718557
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001509113189113234194304256002424950400x7fd4e14908000x7fd3d583638000012076134668745407120761346689366081207613466907244712076134669076352
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001529113189113234194304256002424967680x7fd4e14907000x7fd3d58363c000012076134669127868120761346692882861207613466944604512076134669450007
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001549113189113234194304256002424982400x7fd4e14906000x7fd3d583640000012076134669514346120761346696729241207613466980316312076134669807631
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015691131891132341943042560028241007360x7fd4e14905000x7fd3d583644000012076134669856993120761346700257221207613467028828112076134670335552
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015891131891132341943042560028241022080x7fd4e14904000x7fd3d583648000012076134670359196120761346705397991207613467079659812076134670840100
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016091131891132341943042560024241036800x7fd4e14903000x7fd3d58364c000012076134670866950120761346710445971207613467117819612076134671182476
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016291131891132341943042560024241056640x7fd4e1490a000x7fd3d583650000012076134671231077120761346714021951207613467156827412076134671572251
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016491131891132341943042560024241071360x7fd4e14909000x7fd3d583654000012076134671634867120761346717913131207613467192763212076134671931578
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016691131891132341943042560028241098880x7fd4e14908000x7fd3d583658000012076134671983815120761346721484311207613467241018912076134672431948
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016891131891132341943042560028241113600x7fd4e14907000x7fd3d58365c000012076134672477804120761346726322681207613467288330712076134672901110
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017091131891132341943042560024241128320x7fd4e14906000x7fd3d583660000012076134672949801120761346731129051207613467324586512076134673250209
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017291131891132341943042560024241148160x7fd4e14905000x7fd3d583664000012076134673300132120761346734604241207613467363450312076134673638431
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017491131891132341943042560024241162880x7fd4e14904000x7fd3d583668000012076134673700967120761346738583411207613467398650112076134673990475
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017691131891132341943042560028241190400x7fd4e14903000x7fd3d58366c000012076134674040408120761346742058601207613467446617812076134674490975
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017891131891132341943042560028241207680x7fd4e1490a000x7fd3d583670000012076134674532292120761346746888971207613467494361612076134674965016
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018091131891132341943042560024241224960x7fd4e14909000x7fd3d583674000012076134675015570120761346751716141207613467531017412076134675313884
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018291131891132341943042560024241247360x7fd4e14908000x7fd3d583678000012076134675362976120761346755296921207613467571305112076134675717134
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018491131891132341943042560024241264640x7fd4e14907000x7fd3d58367c000012076134675781994120761346759367301207613467607560912076134676079928
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018691131891132341943042560020241279360x7fd4e14906000x7fd3d583680000012076134676129500120761346762978481207613467656520712076134676586840
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018891131891132341943042560028241296640x7fd4e14905000x7fd3d583684000012076134676632435120761346767904861207613467704728412076134677069196
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019091131891132341943042560024241313920x7fd4e14904000x7fd3d583688000012076134677114841120761346772724031207613467740280212076134677406764
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019291131891132341943042560024241336320x7fd4e14903000x7fd3d58368c000012076134677455815120761346776199211207613467781224012076134677833347
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019491131891132341943042560024241353600x7fd4e1490a000x7fd3d583690000012076134677890683120761346780538391207613467819127812076134678195410
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019691131891132341943042560020241368320x7fd4e14909000x7fd3d583694000012076134678245603120761346784027971207613467868903512076134678709745
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019891131891132341943042560028241385600x7fd4e14908000x7fd3d583698000012076134678754178120761346789179941207613467920311312076134679227538
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020091131891132341943042560024241402880x7fd4e14907000x7fd3d58369c000012076134679272601120761346794405511207613467957463112076134679578811
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020291131891132341943042560024241427840x7fd4e14906000x7fd3d5836a0000012076134679629715120761346798035891207613468001414812076134680035409
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020491131891132341943042560024241447680x7fd4e14905000x7fd3d5836a4000012076134680094359120761346802645471207613468040150612076134680405617
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020691131891132341943042560020241457280x7fd4e14904000x7fd3d5836a8000012076134680455139120761346806359051207613468094534312076134680967471
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020891131891132341943042560028241477120x7fd4e14903000x7fd3d5836ac000012076134681017594120761346811840621207613468144342012076134681464615
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021091131891132341943042560024241496960x7fd4e1490a000x7fd3d5836b0000012076134681508637120761346816728591207613468180805812076134681812041
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021291131891132341943042560024241521920x7fd4e14909000x7fd3d5836b4000012076134681861312120761346820419771207613468226949612076134682293225
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021491131891132341943042560024241541760x7fd4e14908000x7fd3d5836b8000012076134682351133120761346825189351207613468265445412076134682658504
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021691131891132341943042560020241556480x7fd4e14907000x7fd3d5836bc000012076134682707816120761346828824531207613468321301112076134683237199
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021891131891132341943042560028241576320x7fd4e14906000x7fd3d5836c0000012076134683280590120761346834467701207613468370628812076134683727360
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022091131891132341943042560024241596160x7fd4e14905000x7fd3d5836c4000012076134683771402120761346839352471207613468407076612076134684075147
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022291131891132341943042560024241623680x7fd4e14904000x7fd3d5836c8000012076134684126763120761346843037251207613468454948412076134684570237
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022491131891132341943042560024241646080x7fd4e14903000x7fd3d5836cc000012076134684633825120761346847997221207613468493796112076134684942018
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022691131891132341943042560020241663360x7fd4e1490a000x7fd3d5836d0000012076134684990919120761346851727171207613468555159612076134685576357
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022891131891132341943042560028241685760x7fd4e14909000x7fd3d5836d4000012076134685616271120761346857880741207613468604903312076134686069754
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023091131891132341943042560024241708160x7fd4e14908000x7fd3d5836d8000012076134686127220120761346862967121207613468644023112076134686443108
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023291131891132341943042560024241740800x7fd4e14907000x7fd3d5836dc000012076134686493171120761346866680701207613468694790912076134686968774
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023491131891132341943042560024241765760x7fd4e14906000x7fd3d5836e0000012076134687040949120761346872107881207613468735270812076134687355052
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023691131891132341943042560020241777920x7fd4e14905000x7fd3d5836e4000012076134687405937120761346875799071207613468800374512076134688023625
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023891131891132341943042560028241802880x7fd4e14904000x7fd3d5836e8000012076134688080621120761346882515851207613468851254412076134688532390
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024091131891132341943042560024241827840x7fd4e14903000x7fd3d5836ec000012076134688578486120761346887461431207613468888710212076134688890015
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024291131891132341943042560024241863040x7fd4e1490a000x7fd3d5836f0000012076134688938756120761346891224611207613468943894012076134689463361
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024491131891132341943042560024241893120x7fd4e14909000x7fd3d5836f4000012076134689519695120761346896867791207613468983893912076134689841844
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024691131891132341943042560020241907840x7fd4e14908000x7fd3d5836f8000012076134689890625120761346900678981207613469058437612076134690607888
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024891131891132341943042560028241937920x7fd4e14907000x7fd3d5836fc000012076134690652801120761346908222951207613469112005412076134691143022
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025091131891132341943042560024241968000x7fd4e14906000x7fd3d583700000012076134691187334120761346913566931207613469151157212076134691514783
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025291131891132341943042560024242010880x7fd4e14905000x7fd3d583704000012076134691564045120761346917389321207613469212421012076134692144383
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025491131891132341943042560024242046080x7fd4e14904000x7fd3d583708000012076134692207731120761346923779691207613469255540812076134692558282
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025691131891132341943042560020242060800x7fd4e14903000x7fd3d58370c000012076134692608586120761346927957281207613469341892512076134693443307
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025891131891132341943042560028242096000x7fd4e1490a000x7fd3d583710000012076134693485686120761346936573241207613469401524312076134694035397
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026091131891132341943042560024242131200x7fd4e14909000x7fd3d583714000012076134694088436120761346942568421207613469443588112076134694438787
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026291131891132341943042560024242181760x7fd4e14908000x7fd3d583718000012076134694488119120761346946664411207613469512275912076134695143817
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026491131891132341943042560024242222080x7fd4e14907000x7fd3d58371c000012076134695205742120761346953752381207613469557571712076134695595497
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026691131891132341943042560020242239360x7fd4e14906000x7fd3d583720000012076134695643035120761346958073961207613469651779412076134696542727
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026891131891132341943042560028242279680x7fd4e14905000x7fd3d583724000012076134696588272120761346967600331207613469713347112076134697154033
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027091131891132341943042560024242320000x7fd4e14904000x7fd3d583728000012076134697202974120761346973686701207613469757171012076134697591757
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027291131891132341943042560024242378240x7fd4e14903000x7fd3d58372c000012076134697637692120761346978019491207613469832882712076134698351909
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027491131891132341943042560024242423680x7fd4e1490a000x7fd3d583730000012076134698409577120761346985779461207613469880242512076134698821823
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027691131891132341943042560020242435840x7fd4e14909000x7fd3d583734000012076134698872297120761346990453041207613469984386112076134699868208
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027891131891132341943042560028242481280x7fd4e14908000x7fd3d583738000012076134699910757120761347000838601207613470050353912076134700527202
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028091131891132341943042560024242526720x7fd4e14907000x7fd3d58373c000012076134700569310120761347007459381207613470097361712076134700994310
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028291131891132341943042560024242592640x7fd4e14906000x7fd3d583740000012076134701044333120761347012001761207613470179649412076134701817620
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028491131891132341943042560024242648320x7fd4e14905000x7fd3d583744000012076134701874476120761347020406531207613470231105212076134702334271
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028691131891132341943042560020242663040x7fd4e14904000x7fd3d583748000012076134702377170120761347025334511207613470351888812076134703562714
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028891131891132341943042560028242718720x7fd4e14903000x7fd3d58374c000012076134703590535120761347037721671207613470428704512076134704329889
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029091131891132341943042560024242774400x7fd4e1490a000x7fd3d583750000012076134704359364120761347045364841207613470484000312076134704883027
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029291131891132341943042560012242799360x7fd4e14909000x7fd3d583754000012076134704907533120761347050902421207613470582815912076134705894437
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029491131891132341943042560024242865280x7fd4e14908000x7fd3d583758000012076134705930494120761347060939181207613470641103712076134706476689
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029691131891132341943042560020242880000x7fd4e14907000x7fd3d58375c000012076134706501415120761347066831961207613470785343112076134707918869
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029891131891132341943042560032242945920x7fd4e14906000x7fd3d583760000012076134707949476120761347081398301207613470874926812076134708815526
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030091131891132341943042560024243011840x7fd4e14905000x7fd3d583764000012076134708838729120761347090323071207613470935246612076134709418015
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030291131891132341943042560012243049600x7fd4e14904000x7fd3d583768000012076134709446709120761347096196651207613471049854212076134710563644
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030491131891132341943042560024243136000x7fd4e14903000x7fd3d58376c000012076134710610782120761347107727801207613471118221912076134711248016
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030691131891132341943042560020243148160x7fd4e1490a000x7fd3d583770000012076134711277511120761347114564581207613471300301212076134713069051
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030891131891132341943042560020243175680x7fd4e14909000x7fd3d583774000012076134713098996120761347132732511207613471406844812076134714134130
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031091131891132341943042560012243203200x7fd4e14908000x7fd3d583778000012076134714168494120761347143329271207613471474828612076134714813162
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031291131891132341943042560012243240960x7fd4e14907000x7fd3d58377c000012076134714848438120761347150086051207613471616716012076134716235656
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031491131891132341943042560012243288960x7fd4e14906000x7fd3d583780000012076134716278846120761347164405991207613471722603612076134717289624
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031691131891132341943042560020243301120x7fd4e14905000x7fd3d583784000012076134717325561120761347174881151207613472053962412076134720605266
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031891131891132341943042560020243328640x7fd4e14904000x7fd3d583788000012076134720637917120761347208212231207613472236505712076134722436289
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032091131891132341943042560012243356160x7fd4e14903000x7fd3d58378c000012076134722467698120761347226479361207613472343865312076134723504344
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032291131891132341943042560012243393920x7fd4e1490a000x7fd3d583790000012076134723532046120761347237156121207613472599720412076134726062929
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032491131891132341943042560012243441920x7fd4e14909000x7fd3d583794000012076134726108514120761347262690431207613472780519712076134727874266
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032691131891132341943042560020243454080x7fd4e14908000x7fd3d583798000012076134727905423120761347280943161207613473414965312076134734217394
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032891131891132341943042560020243481600x7fd4e14907000x7fd3d58379c000012076134734246318120761347344266121207613473746548112076134737532936
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033091131891132341943042560012243509120x7fd4e14906000x7fd3d5837a0000012076134737562370120761347377498001207613473928915412076134739355323
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332911318911323419430425600122400x7fd4e14905000x7fd3d5837a4000012076134739383405120761347395653131207613474409249612076134744158649