Files
rocm-systems/tests/workloads/Axes4/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.kd000916321916326335544322560083264640x00x7f78de80418000012076230351865750120762305994369621207623059976080012076230599868612
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00291632191632632768256002424124800x00x7f78de83510000012076230614261882120762306145633271207623061456988712076230614575334
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0049163219163264194304256002424129280x7f7a0e8e29000x7f78de83514000012076230614633973120762306148492451207623061498140512076230614985526
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0069163219163264194304256003624136320x7f7a0e8e28000x7f78de83518000012076230615053653120762306152246031207623061547644212076230615545287
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0089163219163264194304256002824140800x7f7a0e8e27000x7f78de8351c000012076230615577236120762306157620411207623061601563912076230616082555
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00109163219163264194304256002424145280x7f7a0e8e26000x7f78de83520000012076230616108073120762306162994781207623061643355712076230616437244
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00129163219163264194304256002424149760x7f7a0e8e25000x7f78de83524000012076230616486696120762306166645961207623061680043612076230616804046
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00149163219163264194304256002424154240x7f7a0e8e24000x7f78de83528000012076230616882592120762306170581941207623061718651412076230617190474
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00169163219163264194304256002824161280x7f7a0e8e23000x7f78de8352c000012076230617241158120762306174151531207623061766971112076230617714127
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00189163219163264194304256002824168320x7f7a0e8e2a000x7f78de83530000012076230617736028120762306179239501207623061817706912076230618220599
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00209163219163264194304256002424175360x7f7a0e8e29000x7f78de83534000012076230618244253120762306184365881207623061856954712076230618573234
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00229163219163264194304256002424182400x7f7a0e8e28000x7f78de83538000012076230618620973120762306187938661207623061892714512076230618930839
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00249163219163264194304256002424189440x7f7a0e8e27000x7f78de8353c000012076230618992493120762306191631441207623061929770312076230619301638
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00269163219163264194304256002824199040x7f7a0e8e26000x7f78de83540000012076230619351410120762306195217021207623061977994112076230619848524
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00289163219163264194304256002824206080x7f7a0e8e25000x7f78de83544000012076230619871697120762306200548201207623062030825812076230620378339
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00309163219163264194304256002424213120x7f7a0e8e24000x7f78de83548000012076230620405219120762306205852171207623062071961612076230620723280
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00329163219163264194304256002424220160x7f7a0e8e23000x7f78de8354c000012076230620771209120762306209477751207623062107785512076230621081746
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00349163219163264194304256002424227200x7f7a0e8e2a000x7f78de83550000012076230621142248120762306213087341207623062143913312076230621443238
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00369163219163264194304256002824236800x7f7a0e8e29000x7f78de83554000012076230621491658120762306216607321207623062191513112076230621982400
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00389163219163264194304256002824243840x7f7a0e8e28000x7f78de83558000012076230622010071120762306221957691207623062245048812076230622518316
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00409163219163264194304256002424250880x7f7a0e8e27000x7f78de8355c000012076230622541218120762306227226471207623062285832612076230622862215
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00429163219163264194304256002424257920x7f7a0e8e26000x7f78de83560000012076230622912198120762306230836051207623062321496412076230623218958
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00449163219163264194304256002424264960x7f7a0e8e25000x7f78de83564000012076230623280242120762306234463231207623062357400212076230623578155
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00469163219163264194304256002824277120x7f7a0e8e24000x7f78de83568000012076230623626265120762306237989611207623062405448012076230624124561
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00489163219163264194304256002824284160x7f7a0e8e23000x7f78de8356c000012076230624152543120762306243306391207623062458535812076230624652923
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00509163219163264194304256002424291200x7f7a0e8e2a000x7f78de83570000012076230624676747120762306248559161207623062498727612076230624991141
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00529163219163264194304256002424300800x7f7a0e8e29000x7f78de83574000012076230625040333120762306252112741207623062535047412076230625354206
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00549163219163264194304256002424307840x7f7a0e8e28000x7f78de83578000012076230625415370120762306255770331207623062571303212076230625717000
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00569163219163264194304256002824320000x7f7a0e8e27000x7f78de8357c000012076230625765641120762306259368711207623062619175012076230626260881
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00589163219163264194304256002824329600x7f7a0e8e26000x7f78de83580000012076230626284355120762306264722281207623062672150712076230626788492
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00609163219163264194304256002424339200x7f7a0e8e25000x7f78de83584000012076230626816354120762306269959061207623062712742512076230627131229
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00629163219163264194304256002424348800x7f7a0e8e24000x7f78de83588000012076230627180019120762306273519041207623062749014312076230627494173
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00649163219163264194304256002424358400x7f7a0e8e23000x7f78de8358c000012076230627555267120762306277176621207623062785414212076230627857919
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00669163219163264194304256002824373120x7f7a0e8e2a000x7f78de83590000012076230627904917120762306280821401207623062833733912076230628407380
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00689163219163264194304256002824382720x7f7a0e8e29000x7f78de83594000012076230628431565120762306286104581207623062886261712076230628904705
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00709163219163264194304256002424392320x7f7a0e8e28000x7f78de83598000012076230628933168120762306291152551207623062924565512076230629249566
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00729163219163264194304256002424401920x7f7a0e8e27000x7f78de8359c000012076230629299478120762306294710941207623062961093312076230629614754
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00749163219163264194304256002424411520x7f7a0e8e26000x7f78de835a0000012076230629675317120762306298370121207623062997029112076230629974222
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00769163219163264194304256002824426240x7f7a0e8e25000x7f78de835a4000012076230630029485120762306302069301207623063045860912076230630527180
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00789163219163264194304256002824435840x7f7a0e8e24000x7f78de835a8000012076230630550413120762306307293271207623063098004612076230631049130
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00809163219163264194304256002424445440x7f7a0e8e23000x7f78de835ac000012076230631070981120762306312546051207623063138948412076230631393279
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00829163219163264194304256002424457600x7f7a0e8e2a000x7f78de835b0000012076230631446919120762306316054831207623063174404212076230631747939
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00849163219163264194304256002424467200x7f7a0e8e29000x7f78de835b4000012076230631808621120762306319688411207623063210324112076230632107517
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00869163219163264194304256002824484480x7f7a0e8e28000x7f78de835b8000012076230632151348120762306323270801207623063259283812076230632637572
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00889163219163264194304256002824494080x7f7a0e8e27000x7f78de835bc000012076230632663380120762306328398771207623063309251612076230633162287
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00909163219163264194304256002424503680x7f7a0e8e26000x7f78de835c0000012076230633189387120762306333673951207623063349907412076230633502880
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00929163219163264194304256002424515840x7f7a0e8e25000x7f78de835c4000012076230633556690120762306337176331207623063390003212076230633903975
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00949163219163264194304256002424525440x7f7a0e8e24000x7f78de835c8000012076230633965670120762306341377911207623063426899012076230634273182
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00969163219163264194304256002824542720x7f7a0e8e23000x7f78de835cc000012076230634322153120762306344974691207623063476258812076230634830457
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00989163219163264194304256002824554880x7f7a0e8e2a000x7f78de835d0000012076230634853841120762306350400261207623063529298512076230635361454
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001009163219163264194304256002424567040x7f7a0e8e29000x7f78de835d4000012076230635384657120762306355648241207623063569842312076230635702298
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001029163219163264194304256002424581760x7f7a0e8e28000x7f78de835d8000012076230635755947120762306359171421207623063605762112076230636061345
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001049163219163264194304256002424593920x7f7a0e8e27000x7f78de835dc000012076230636122178120762306362835401207623063642178012076230636425712
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001069163219163264194304256002824613760x7f7a0e8e26000x7f78de835e0000012076230636474843120762306366417781207623063690865712076230636952892
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001089163219163264194304256002824625920x7f7a0e8e25000x7f78de835e4000012076230636975033120762306371601761207623063740881512076230637477346
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001109163219163264194304256002424638080x7f7a0e8e24000x7f78de835e8000012076230637500980120762306376793731207623063781265312076230637816597
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001129163219163264194304256002424652800x7f7a0e8e23000x7f78de835ec000012076230637862843120762306380387321207623063817905112076230638183098
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001149163219163264194304256002424664960x7f7a0e8e2a000x7f78de835f0000012076230638244723120762306384086501207623063854000912076230638544099
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001169163219163264194304256002824684800x7f7a0e8e29000x7f78de835f4000012076230638592078120762306387630481207623063903296712076230639102046
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001189163219163264194304256002824696960x7f7a0e8e28000x7f78de835f8000012076230639125379120762306393075251207623063956304412076230639630658
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001209163219163264194304256002424709120x7f7a0e8e27000x7f78de835fc000012076230639655615120762306398376031207623063997024212076230639974047
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001229163219163264194304256002424723840x7f7a0e8e26000x7f78de83600000012076230640032515120762306401934411207623064033456012076230640338534
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001249163219163264194304256002424736000x7f7a0e8e25000x7f78de83604000012076230640398936120762306405563191207623064068991912076230640693774
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001269163219163264194304256002824758400x7f7a0e8e24000x7f78de83608000012076230640742034120762306409094381207623064117327612076230641223599
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001289163219163264194304256002824770560x7f7a0e8e23000x7f78de8360c000012076230641246391120762306414286351207623064168511412076230641733186
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001309163219163264194304256002424782720x7f7a0e8e2a000x7f78de83610000012076230641759384120762306419353531207623064207455212076230642078718
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001329163219163264194304256002424800000x7f7a0e8e29000x7f78de83614000012076230642127058120762306423015911207623064244495012076230642448776
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001349163219163264194304256002424812160x7f7a0e8e28000x7f78de83618000012076230642509899120762306426713491207623064280942812076230642813383
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001369163219163264194304256002824834560x7f7a0e8e27000x7f78de8361c000012076230642854860120762306430332671207623064329726612076230643348147
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001389163219163264194304256002824849280x7f7a0e8e26000x7f78de83620000012076230643374666120762306435542251207623064380990312076230643832688
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001409163219163264194304256002424864000x7f7a0e8e25000x7f78de83624000012076230643874415120762306440388621207623064417342212076230644177468
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001429163219163264194304256002424881280x7f7a0e8e24000x7f78de83628000012076230644226950120762306443999811207623064455134012076230644555351
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001449163219163264194304256002424896000x7f7a0e8e23000x7f78de8362c000012076230644635049120762306447937391207623064492605812076230644930027
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001469163219163264194304256002824920960x7f7a0e8e2a000x7f78de83630000012076230644980731120762306451548571207623064542093612076230645470872
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001489163219163264194304256002824935680x7f7a0e8e29000x7f78de83634000012076230645497121120762306456721341207623064592909312076230645976852
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001509163219163264194304256002424950400x7f7a0e8e28000x7f78de83638000012076230646007109120762306461903721207623064633053112076230646334667
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001529163219163264194304256002424967680x7f7a0e8e27000x7f78de8363c000012076230646381454120762306465519701207623064671100912076230646715104
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001549163219163264194304256002424982400x7f7a0e8e26000x7f78de83640000012076230646774966120762306469350081207623064706780712076230647072098
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015691632191632641943042560028241007360x7f7a0e8e25000x7f78de83644000012076230647120137120762306472921261207623064755852512076230647583158
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015891632191632641943042560028241022080x7f7a0e8e24000x7f78de83648000012076230647624965120762306477839641207623064803820312076230648094428
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016091632191632641943042560024241036800x7f7a0e8e23000x7f78de8364c000012076230648124073120762306483052411207623064844524112076230648449097
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016291632191632641943042560024241056640x7f7a0e8e2a000x7f78de83650000012076230648496826120762306486662001207623064883243912076230648836367
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016491632191632641943042560024241071360x7f7a0e8e29000x7f78de83654000012076230648898853120762306490754781207623064921019712076230649214239
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016691632191632641943042560028241098880x7f7a0e8e28000x7f78de83658000012076230649262930120762306494381961207623064969963512076230649747260
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016891632191632641943042560028241113600x7f7a0e8e27000x7f78de8365c000012076230649772096120762306499623531207623065025867212076230650307982
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017091632191632641943042560024241128320x7f7a0e8e26000x7f78de83660000012076230650331105120762306505191511207623065065691012076230650660767
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017291632191632641943042560024241148160x7f7a0e8e25000x7f78de83664000012076230650712203120762306508740291207623065104858812076230651052596
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017491632191632641943042560024241162880x7f7a0e8e24000x7f78de83668000012076230651115312120762306512765871207623065141338612076230651417283
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017691632191632641943042560028241190400x7f7a0e8e23000x7f78de8366c000012076230651459702120762306516319451207623065189338412076230651940365
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017891632191632641943042560028241207680x7f7a0e8e2a000x7f78de83670000012076230651966464120762306521516231207623065241162112076230652462245
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018091632191632641943042560024241224960x7f7a0e8e29000x7f78de83674000012076230652489195120762306526665001207623065280249912076230652806285
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018291632191632641943042560024241247360x7f7a0e8e28000x7f78de83678000012076230652853723120762306530293781207623065321177712076230653216036
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018491632191632641943042560024241264640x7f7a0e8e27000x7f78de8367c000012076230653276769120762306534370561207623065357561612076230653579482
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018691632191632641943042560020241279360x7f7a0e8e26000x7f78de83680000012076230653622942120762306537965751207623065409737312076230654147367
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018891632191632641943042560028241296640x7f7a0e8e25000x7f78de83684000012076230654170670120762306543557721207623065461273112076230654659899
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019091632191632641943042560024241313920x7f7a0e8e24000x7f78de83688000012076230654685517120762306548610491207623065499832912076230655004720
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019291632191632641943042560024241336320x7f7a0e8e23000x7f78de8368c000012076230655049353120762306552202481207623065541304712076230655436182
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019491632191632641943042560024241353600x7f7a0e8e2a000x7f78de83690000012076230655492377120762306556530451207623065578504512076230655789158
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019691632191632641943042560020241368320x7f7a0e8e29000x7f78de83694000012076230655837909120762306560064841207623065629128212076230656342446
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019891632191632641943042560028241385600x7f7a0e8e28000x7f78de83698000012076230656365449120762306565464811207623065680456012076230656852184
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020091632191632641943042560024241402880x7f7a0e8e27000x7f78de8369c000012076230656875748120762306570784781207623065721687812076230657221220
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020291632191632641943042560024241427840x7f7a0e8e26000x7f78de836a0000012076230657270922120762306574392771207623065765111612076230657698947
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020491632191632641943042560024241447680x7f7a0e8e25000x7f78de836a4000012076230657736086120762306578963941207623065803351412076230658037637
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020691632191632641943042560020241457280x7f7a0e8e24000x7f78de836a8000012076230658085826120762306582594331207623065856743112076230658615280
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020891632191632641943042560028241477120x7f7a0e8e23000x7f78de836ac000012076230658638734120762306588173501207623065907606912076230659126070
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021091632191632641943042560024241496960x7f7a0e8e2a000x7f78de836b0000012076230659152809120762306593299871207623065947190712076230659475980
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021291632191632641943042560024241521920x7f7a0e8e29000x7f78de836b4000012076230659528367120762306596915861207623065991926512076230659966411
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021491632191632641943042560024241541760x7f7a0e8e28000x7f78de836b8000012076230660009762120762306601687031207623066030950312076230660313617
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021691632191632641943042560020241556480x7f7a0e8e27000x7f78de836bc000012076230660361425120762306605317421207623066086246012076230660910306
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021891632191632641943042560028241576320x7f7a0e8e26000x7f78de836c0000012076230660936043120762306611128591207623066136597712076230661415925
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022091632191632641943042560024241596160x7f7a0e8e25000x7f78de836c4000012076230661439339120762306616166961207623066175829612076230661762610
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022291632191632641943042560024241623680x7f7a0e8e24000x7f78de836c8000012076230661808715120762306619781341207623066222389312076230662272978
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022491632191632641943042560024241646080x7f7a0e8e23000x7f78de836cc000012076230662310458120762306624842691207623066262170912076230662628990
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022691632191632641943042560020241663360x7f7a0e8e2a000x7f78de836d0000012076230662672170120762306628415471207623066321850512076230663267186
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022891632191632641943042560028241685760x7f7a0e8e29000x7f78de836d4000012076230663291451120762306634724241207623066372618312076230663747639
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023091632191632641943042560024241708160x7f7a0e8e28000x7f78de836d8000012076230663788124120762306639453821207623066408554212076230664089203
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023291632191632641943042560024241740800x7f7a0e8e27000x7f78de836dc000012076230664131111120762306643079411207623066458794012076230664636320
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023491632191632641943042560024241765760x7f7a0e8e26000x7f78de836e0000012076230664672357120762306648319391207623066496745812076230664970712
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023691632191632641943042560020241777920x7f7a0e8e25000x7f78de836e4000012076230665024552120762306652016971207623066562617512076230665674640
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023891632191632641943042560028241802880x7f7a0e8e24000x7f78de836e8000012076230665696721120762306658746541207623066613609312076230666184768
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024091632191632641943042560024241827840x7f7a0e8e23000x7f78de836ec000012076230666211548120762306663893721207623066652953212076230666532955
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024291632191632641943042560024241863040x7f7a0e8e2a000x7f78de836f0000012076230666580493120762306667471311207623066706217012076230667111600
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024491632191632641943042560024241893120x7f7a0e8e29000x7f78de836f4000012076230667147387120762306673330491207623066748584812076230667489132
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024691632191632641943042560020241907840x7f7a0e8e28000x7f78de836f8000012076230667536500120762306677053671207623066822328512076230668246960
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024891632191632641943042560028241937920x7f7a0e8e27000x7f78de836fc000012076230668293627120762306684541641207623066875320312076230668800259
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025091632191632641943042560024241968000x7f7a0e8e26000x7f78de83700000012076230668825576120762306690095221207623066916696112076230669170567
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025291632191632641943042560024242010880x7f7a0e8e25000x7f78de83704000012076230669222333120762306693951201207623066980583912076230669853436
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025491632191632641943042560024242046080x7f7a0e8e24000x7f78de83708000012076230669898159120762306700653581207623067024199712076230670245374
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025691632191632641943042560020242060800x7f7a0e8e23000x7f78de8370c000012076230670294786120762306704651961207623067107543412076230671123617
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025891632191632641943042560028242096000x7f7a0e8e2a000x7f78de83710000012076230671147230120762306713352731207623067166183112076230671708814
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026091632191632641943042560024242131200x7f7a0e8e29000x7f78de83714000012076230671735704120762306719167101207623067209750912076230672101123
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026291632191632641943042560024242181760x7f7a0e8e28000x7f78de83718000012076230672151868120762306723311091207623067278678712076230672834256
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026491632191632641943042560024242222080x7f7a0e8e27000x7f78de8371c000012076230672874050120762306730419861207623067324214512076230673291986
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026691632191632641943042560020242239360x7f7a0e8e26000x7f78de83720000012076230673314358120762306734963841207623067419910112076230674249065
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026891632191632641943042560028242279680x7f7a0e8e25000x7f78de83724000012076230674278139120762306744536601207623067482741912076230674874267
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027091632191632641943042560024242320000x7f7a0e8e24000x7f78de83728000012076230674901488120762306750890171207623067529333712076230675342317
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027291632191632641943042560024242378240x7f7a0e8e23000x7f78de8372c000012076230675364628120762306755446961207623067607077412076230676119792
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027491632191632641943042560024242423680x7f7a0e8e2a000x7f78de83730000012076230676155658120762306763205331207623067654421212076230676591028
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027691632191632641943042560020242435840x7f7a0e8e29000x7f78de83734000012076230676615593120762306767914111207623067759028712076230677641209
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027891632191632641943042560028242481280x7f7a0e8e28000x7f78de83738000012076230677664332120762306778466061207623067826916512076230678320051
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028091632191632641943042560024242526720x7f7a0e8e27000x7f78de8373c000012076230678344877120762306785286841207623067875572312076230678804241
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028291632191632641943042560024242592640x7f7a0e8e26000x7f78de83740000012076230678827524120762306790061221207623067960403912076230679653469
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028491632191632641943042560024242648320x7f7a0e8e25000x7f78de83744000012076230679693373120762306798563581207623068012579712076230680176842
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028691632191632641943042560020242663040x7f7a0e8e24000x7f78de83748000012076230680200065120762306803821161207623068136739212076230681436843
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028891632191632641943042560028242718720x7f7a0e8e23000x7f78de8374c000012076230681468212120762306816486711207623068218050912076230682249473
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029091632191632641943042560024242774400x7f7a0e8e2a000x7f78de83750000012076230682280411120762306824611481207623068273474712076230682801640
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029291632191632641943042560012242799360x7f7a0e8e29000x7f78de83754000012076230682828199120762306830085061207623068374818312076230683817868
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029491632191632641943042560024242865280x7f7a0e8e28000x7f78de83758000012076230683854697120762306840225821207623068433858012076230684407885
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029691632191632641943042560020242880000x7f7a0e8e27000x7f78de8375c000012076230684430697120762306846168191207623068578897512076230685858701
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029891632191632641943042560032242945920x7f7a0e8e26000x7f78de83760000012076230685888266120762306860784131207623068669025112076230686760096
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030091632191632641943042560024243011840x7f7a0e8e25000x7f78de83764000012076230686787547120762306869696101207623068728896912076230687358899
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030291632191632641943042560012243049600x7f7a0e8e24000x7f78de83768000012076230687384497120762306875617671207623068844016412076230688508506
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030491632191632641943042560024243136000x7f7a0e8e23000x7f78de8376c000012076230688544873120762306887064031207623068911584112076230689184081
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030691632191632641943042560020243148160x7f7a0e8e2a000x7f78de83770000012076230689213636120762306893947201207623069094303412076230691017569
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030891632191632641943042560020243175680x7f7a0e8e29000x7f78de83774000012076230691047815120762306912263931207623069202175012076230692090793
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031091632191632641943042560012243203200x7f7a0e8e28000x7f78de83778000012076230692113976120762306923011081207623069271598712076230692783330
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031291632191632641943042560012243240960x7f7a0e8e27000x7f78de8377c000012076230692809328120762306929902261207623069415006112076230694220221
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031491632191632641943042560012243288960x7f7a0e8e26000x7f78de83780000012076230694260155120762306944227001207623069520925712076230695278387
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031691632191632641943042560020243301120x7f7a0e8e25000x7f78de83784000012076230695307782120762306954868561207623069853756312076230698606562
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031891632191632641943042560020243328640x7f7a0e8e24000x7f78de83788000012076230698635416120762306988218821207623070036507612076230700435521
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032091632191632641943042560012243356160x7f7a0e8e23000x7f78de8378c000012076230700459045120762307006468351207623070143803212076230701506592
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032291632191632641943042560012243393920x7f7a0e8e2a000x7f78de83790000012076230701537650120762307017194711207623070400074112076230704069245
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032491632191632641943042560012243441920x7f7a0e8e29000x7f78de83794000012076230704112665120762307042753001207623070581113412076230705880451
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032691632191632641943042560020243454080x7f7a0e8e28000x7f78de83798000012076230705909214120762307060964131207623071215206912076230712225232
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032891632191632641943042560020243481600x7f7a0e8e27000x7f78de8379c000012076230712249607120762307124301481207623071547237512076230715544972
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033091632191632641943042560012243509120x7f7a0e8e26000x7f78de837a0000012076230715572553120762307157587741207623071729860812076230717367910
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332916321916326419430425600122400x7f7a0e8e25000x7f78de837a4000012076230717396984120762307175760471207623072210402912076230722176526