Files
rocm-systems/tests/workloads/dispatches/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.kd000896318896323335544322560083264640x00x7f421420418000012075848456376772120758487008354211207584870115781912075848701272961
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00289631889632332768256002424124800x00x7f421423510000012075848716121136120758487164256261207584871643234512075848716441912
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0048963188963234194304256002424129280x7f431ff599000x7f421423514000012075848716497545120758487167208241207584871685410312075848716856793
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0068963188963234194304256003624136320x7f431ff598000x7f421423518000012075848716924839120758487171061021207584871735938112075848717433144
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0088963188963234194304256002824140800x7f431ff597000x7f42142351c000012075848717466596120758487176521801207584871790817812075848717978968
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00108963188963234194304256002424145280x7f431ff596000x7f421423520000012075848718013853120758487181980971207584871832929612075848718332065
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00128963188963234194304256002424149760x7f431ff595000x7f421423524000012075848718380004120758487185571351207584871868785512075848718690581
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00148963188963234194304256002424154240x7f431ff594000x7f421423528000012075848718763446120758487189323341207584871906337312075848719066259
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00168963188963234194304256002824161280x7f431ff593000x7f42142352c000012075848719114629120758487192932921207584871954881112075848719592197
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00188963188963234194304256002824168320x7f431ff59a000x7f421423530000012075848719619648120758487198004891207584872005184812075848720095251
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00208963188963234194304256002424175360x7f431ff599000x7f421423534000012075848720118775120758487203200071207584872044864612075848720451233
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00228963188963234194304256002424182400x7f431ff598000x7f421423538000012075848720498250120758487206795251207584872081648512075848720819017
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00248963188963234194304256002424189440x7f431ff597000x7f42142353c000012075848720879359120758487210545641207584872118880312075848721191739
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00268963188963234194304256002824199040x7f431ff596000x7f421423540000012075848721238787120758487214166421207584872167440112075848721743665
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00288963188963234194304256002824206080x7f431ff595000x7f421423544000012075848721771226120758487219510391207584872220735812075848722277727
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00308963188963234194304256002424213120x7f431ff594000x7f421423548000012075848722305479120758487224907171207584872262175612075848722624612
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00328963188963234194304256002424220160x7f431ff593000x7f42142354c000012075848722672832120758487228446351207584872298063412075848722983529
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00348963188963234194304256002424227200x7f431ff59a000x7f421423550000012075848723048520120758487232203131207584872335311312075848723355971
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00368963188963234194304256002824236800x7f431ff599000x7f421423554000012075848723407357120758487235745521207584872382431012075848723868815
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00388963188963234194304256002824243840x7f431ff598000x7f421423558000012075848723892308120758487240883091207584872434158812075848724385775
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00408963188963234194304256002424250880x7f431ff597000x7f42142355c000012075848724408157120758487245959871207584872472750612075848724729995
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00428963188963234194304256002424257920x7f431ff596000x7f421423560000012075848724777263120758487249433451207584872508126412075848725083883
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00448963188963234194304256002424264960x7f431ff595000x7f421423564000012075848725146679120758487253182231207584872544702312075848725449843
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00468963188963234194304256002824277120x7f431ff594000x7f421423568000012075848725497521120758487256719821207584872592286012075848725992612
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00488963188963234194304256002824284160x7f431ff593000x7f42142356c000012075848726026124120758487262070191207584872645837812075848726528768
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00508963188963234194304256002424291200x7f431ff59a000x7f421423570000012075848726555798120758487267329371207584872686509612075848726867708
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00528963188963234194304256002424300800x7f431ff599000x7f421423574000012075848726914885120758487270951751207584872722925412075848727232055
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00548963188963234194304256002424307840x7f431ff598000x7f421423578000012075848727292357120758487274623731207584872759085312075848727593627
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00568963188963234194304256002824320000x7f431ff597000x7f42142357c000012075848727642137120758487278084511207584872806093012075848728130986
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00588963188963234194304256002824329600x7f431ff596000x7f421423580000012075848728155832120758487283460491207584872859564812075848728665669
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00608963188963234194304256002424339200x7f431ff595000x7f421423584000012075848728692128120758487288758061207584872900588612075848729009017
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00628963188963234194304256002424348800x7f431ff594000x7f421423588000012075848729057888120758487292354851207584872937116412075848729374006
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00648963188963234194304256002424358400x7f431ff593000x7f42142358c000012075848729434518120758487295993231207584872972732212075848729730047
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00668963188963234194304256002824373120x7f431ff59a000x7f421423590000012075848729776734120758487299487611207584873019916012075848730269259
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00688963188963234194304256002824382720x7f431ff599000x7f421423594000012075848730296640120758487304801191207584873073163812075848730801619
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00708963188963234194304256002424392320x7f431ff598000x7f421423598000012075848730827587120758487310082761207584873114539612075848731148654
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00728963188963234194304256002424401920x7f431ff597000x7f42142359c000012075848731199598120758487313663551207584873150539412075848731508232
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00748963188963234194304256002424411520x7f431ff596000x7f4214235a0000012075848731569255120758487317346731207584873186779212075848731870716
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00768963188963234194304256002824426240x7f431ff595000x7f4214235a4000012075848731919867120758487321017111207584873236171012075848732431718
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00788963188963234194304256002824435840x7f431ff594000x7f4214235a8000012075848732456084120758487326434691207584873290250712075848732972082
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00808963188963234194304256002424445440x7f431ff593000x7f4214235ac000012075848732999383120758487331897061207584873332586512075848733328916
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00828963188963234194304256002424457600x7f431ff59a000x7f4214235b0000012075848733378418120758487335418641207584873367834412075848733680990
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00848963188963234194304256002424467200x7f431ff599000x7f4214235b4000012075848733741633120758487339068231207584873403354212075848734036411
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00868963188963234194304256002824484480x7f431ff598000x7f4214235b8000012075848734085422120758487342573811207584873451946012075848734589478
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00888963188963234194304256002824494080x7f431ff597000x7f4214235bc000012075848734614876120758487347989781207584873505609712075848735127087
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00908963188963234194304256002424503680x7f431ff596000x7f4214235c0000012075848735151242120758487353335361207584873546441512075848735467350
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00928963188963234194304256002424515840x7f431ff595000x7f4214235c4000012075848735516030120758487356877741207584873582537312075848735828200
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00948963188963234194304256002424525440x7f431ff594000x7f4214235c8000012075848735889795120758487360724121207584873620377212075848736206484
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00968963188963234194304256002824542720x7f431ff593000x7f4214235cc000012075848736255264120758487364312911207584873669336912075848736763569
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00988963188963234194304256002824554880x7f431ff59a000x7f4214235d0000012075848736787784120758487369692081207584873722216712075848737293013
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001008963188963234194304256002424567040x7f431ff599000x7f4214235d4000012075848737319913120758487374997651207584873763032512075848737633175
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001028963188963234194304256002424581760x7f431ff598000x7f4214235d8000012075848737683378120758487378500041207584873799192312075848737994647
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001048963188963234194304256002424593920x7f431ff597000x7f4214235dc000012075848738056942120758487382224821207584873835336112075848738356068
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001068963188963234194304256002824613760x7f431ff596000x7f4214235e0000012075848738404458120758487385690401207584873887351912075848738916841
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001088963188963234194304256002824625920x7f431ff595000x7f4214235e4000012075848738943320120758487391359181207584873939159612075848739461813
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001108963188963234194304256002424638080x7f431ff594000x7f4214235e8000012075848739490797120758487396664751207584873979991512075848739802967
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001128963188963234194304256002424652800x7f431ff593000x7f4214235ec000012075848739850826120758487400274331207584874016839312075848740171232
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001148963188963234194304256002424664960x7f431ff59a000x7f4214235f0000012075848740232967120758487403994321207584874053591112075848740538675
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001168963188963234194304256002824684800x7f431ff599000x7f4214235f4000012075848740586393120758487407595901207584874102134912075848741091472
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001188963188963234194304256002824696960x7f431ff598000x7f4214235f8000012075848741116779120758487413005471207584874154982612075848741619463
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001208963188963234194304256002424709120x7f431ff597000x7f4214235fc000012075848741645482120758487418344651207584874196550412075848741968281
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001228963188963234194304256002424723840x7f431ff596000x7f421423600000012075848742024827120758487421997431207584874233910212075848742341986
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001248963188963234194304256002424736000x7f431ff595000x7f421423604000012075848742404192120758487425675811207584874269782112075848742700593
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001268963188963234194304256002824758400x7f431ff594000x7f421423608000012075848742751928120758487429162201207584874317541812075848743247349
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001288963188963234194304256002824770560x7f431ff593000x7f42142360c000012075848743272265120758487434557371207584874370453612075848743774498
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001308963188963234194304256002424782720x7f431ff59a000x7f421423610000012075848743801278120758487439795751207584874411813412075848744121323
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001328963188963234194304256002424800000x7f431ff599000x7f421423614000012075848744172278120758487443494931207584874449301212075848744496099
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001348963188963234194304256002424812160x7f431ff598000x7f421423618000012075848744557143120758487447186111207584874485413112075848744856810
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001368963188963234194304256002824834560x7f431ff597000x7f42142361c000012075848744905881120758487450816491207584874534420812075848745396723
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001388963188963234194304256002824849280x7f431ff596000x7f421423620000012075848745423122120758487456042071207584874586132612075848745911089
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001408963188963234194304256002424864000x7f431ff595000x7f421423624000012075848745940824120758487461251641207584874625348412075848746256591
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001428963188963234194304256002424881280x7f431ff594000x7f421423628000012075848746305392120758487464747631207584874662644212075848746629214
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001448963188963234194304256002424896000x7f431ff593000x7f42142362c000012075848746708842120758487468750811207584874701044012075848747013608
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001468963188963234194304256002824920960x7f431ff59a000x7f421423630000012075848747064142120758487472304391207584874749539812075848747547500
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001488963188963234194304256002824935680x7f431ff599000x7f421423634000012075848747574671120758487477529971207584874800563612075848748056536
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001508963188963234194304256002424950400x7f431ff598000x7f421423638000012075848748082675120758487482672341207584874839635412075848748399153
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001528963188963234194304256002424967680x7f431ff597000x7f42142363c000012075848748447984120758487486125131207584874877043212075848748773348
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001548963188963234194304256002424982400x7f431ff596000x7f421423640000012075848748834743120758487489979511207584874913043012075848749133648
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015689631889632341943042560028241007360x7f431ff595000x7f421423644000012075848749182499120758487493558691207584874961634812075848749644828
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015889631889632341943042560028241022080x7f431ff594000x7f421423648000012075848749684682120758487498461071207584875010354612075848750130340
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016089631889632341943042560024241036800x7f431ff593000x7f42142364c000012075848750173511120758487503371441207584875047506412075848750478007
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016289631889632341943042560024241056640x7f431ff59a000x7f421423650000012075848750526176120758487506997031207584875086530212075848750868162
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016489631889632341943042560024241071360x7f431ff599000x7f421423654000012075848750929886120758487510985811207584875123090012075848751234142
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016689631889632341943042560028241098880x7f431ff598000x7f421423658000012075848751281229120758487514512191207584875171329812075848751736105
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016889631889632341943042560028241113600x7f431ff597000x7f42142365c000012075848751778023120758487519406571207584875219297612075848752220435
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017089631889632341943042560024241128320x7f431ff596000x7f421423660000012075848752264507120758487524315351207584875256545412075848752568752
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017289631889632341943042560024241148160x7f431ff595000x7f421423664000012075848752617002120758487527881731207584875296225212075848752965139
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017489631889632341943042560024241162880x7f431ff594000x7f421423668000012075848753034608120758487531979311207584875332673012075848753329576
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017689631889632341943042560028241190400x7f431ff593000x7f42142366c000012075848753382524120758487535456091207584875380368812075848753829786
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017889631889632341943042560028241207680x7f431ff59a000x7f421423670000012075848753877564120758487540500871207584875430448612075848754333802
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018089631889632341943042560024241224960x7f431ff599000x7f421423674000012075848754372815120758487545366451207584875467472412075848754677651
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018289631889632341943042560024241247360x7f431ff598000x7f421423678000012075848754723937120758487548977631207584875508160212075848755084998
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018489631889632341943042560024241264640x7f431ff597000x7f42142367c000012075848755146853120758487553153611207584875545264012075848755455447
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018689631889632341943042560020241279360x7f431ff596000x7f421423680000012075848755501593120758487556739191207584875594159812075848755966847
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018889631889632341943042560028241296640x7f431ff595000x7f421423684000012075848756015959120758487561809571207584875643503612075848756461947
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019089631889632341943042560024241313920x7f431ff594000x7f421423688000012075848756503545120758487566679941207584875680623412075848756809233
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019289631889632341943042560024241336320x7f431ff593000x7f42142368c000012075848756857853120758487570359931207584875722735212075848757255833
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019489631889632341943042560024241353600x7f431ff59a000x7f421423690000012075848757293002120758487574575911207584875759983012075848757602878
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019689631889632341943042560020241368320x7f431ff599000x7f421423694000012075848757657209120758487578211091207584875813534712075848758162408
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019889631889632341943042560028241385600x7f431ff598000x7f421423698000012075848758213112120758487583814261207584875864366512075848758670933
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020089631889632341943042560024241402880x7f431ff597000x7f42142369c000012075848758721607120758487588892641207584875903038312075848759033276
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020289631889632341943042560024241427840x7f431ff596000x7f4214236a0000012075848759085112120758487592591821207584875946862112075848759495956
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020489631889632341943042560024241447680x7f431ff595000x7f4214236a4000012075848759549125120758487597164601207584875985341912075848759856436
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020689631889632341943042560020241457280x7f431ff594000x7f4214236a8000012075848759905217120758487600857381207584876039293712075848760419813
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020889631889632341943042560028241477120x7f431ff593000x7f4214236ac000012075848760461009120758487606270161207584876089245412075848760916997
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021089631889632341943042560024241496960x7f431ff59a000x7f4214236b0000012075848760958624120758487611282931207584876126109312075848761264252
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021289631889632341943042560024241521920x7f431ff599000x7f4214236b4000012075848761311580120758487614814121207584876171005012075848761735448
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021489631889632341943042560024241541760x7f431ff598000x7f4214236b8000012075848761791592120758487619546891207584876209468912075848762097882
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021689631889632341943042560020241556480x7f431ff597000x7f4214236bc000012075848762145560120758487623111681207584876264268612075848762667610
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021889631889632341943042560028241576320x7f431ff596000x7f4214236c0000012075848762709468120758487628713251207584876312780412075848763157240
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022089631889632341943042560024241596160x7f431ff595000x7f4214236c4000012075848763198156120758487633609231207584876350380212075848763506720
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022289631889632341943042560024241623680x7f431ff594000x7f4214236c8000012075848763554739120758487637264741207584876397079412075848763998814
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022489631889632341943042560024241646080x7f431ff593000x7f4214236cc000012075848764057313120758487642242321207584876436455112075848764366518
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022689631889632341943042560020241663360x7f431ff59a000x7f4214236d0000012075848764414256120758487645869501207584876496374912075848764988213
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022889631889632341943042560028241685760x7f431ff599000x7f4214236d4000012075848765043927120758487652075881207584876546934712075848765494744
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023089631889632341943042560024241708160x7f431ff598000x7f4214236d8000012075848765544377120758487657099861207584876585062612075848765852690
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023289631889632341943042560024241740800x7f431ff597000x7f4214236dc000012075848765900488120758487660741451207584876635382412075848766382083
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023489631889632341943042560024241765760x7f431ff596000x7f4214236e0000012075848766434200120758487666023031207584876674006312075848766742022
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023689631889632341943042560020241777920x7f431ff595000x7f4214236e4000012075848766788369120758487669591021207584876738438012075848767413310
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023889631889632341943042560028241802880x7f431ff594000x7f4214236e8000012075848767454386120758487676224591207584876788741812075848767910484
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024089631889632341943042560024241827840x7f431ff593000x7f4214236ec000012075848767953454120758487681176581207584876825669712075848768258851
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024289631889632341943042560024241863040x7f431ff59a000x7f4214236f0000012075848768307051120758487684808561207584876879589512075848768820064
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024489631889632341943042560024241893120x7f431ff599000x7f4214236f4000012075848768881469120758487690544541207584876920709412075848769209719
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024689631889632341943042560020241907840x7f431ff598000x7f4214236f8000012075848769257217120758487694426131207584876995925112075848769984939
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024889631889632341943042560028241937920x7f431ff597000x7f4214236fc000012075848770031466120758487701968501207584877049764912075848770522528
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025089631889632341943042560024241968000x7f431ff596000x7f421423700000012075848770569926120758487707357281207584877088980812075848770891825
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025289631889632341943042560024242010880x7f431ff595000x7f421423704000012075848770938802120758487711179671207584877150436512075848771530862
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025489631889632341943042560024242046080x7f431ff594000x7f421423708000012075848771584612120758487717515641207584877192692412075848771929313
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025689631889632341943042560020242060800x7f431ff593000x7f42142370c000012075848771975819120758487721550831207584877276532112075848772791054
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025889631889632341943042560028242096000x7f431ff59a000x7f421423710000012075848772836599120758487730000401207584877332899912075848773357397
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026089631889632341943042560024242131200x7f431ff599000x7f421423714000012075848773402481120758487735662781207584877374643712075848773748444
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026289631889632341943042560024242181760x7f431ff598000x7f421423718000012075848773797084120758487739792361207584877443507512075848774460948
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026489631889632341943042560024242222080x7f431ff597000x7f42142371c000012075848774515740120758487746848341207584877488659312075848774910052
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026689631889632341943042560020242239360x7f431ff596000x7f421423720000012075848774953463120758487751187521207584877582227012075848775851682
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026889631889632341943042560028242279680x7f431ff595000x7f421423724000012075848775891186120758487760728291207584877647314712075848776498625
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027089631889632341943042560024242320000x7f431ff594000x7f421423728000012075848776539601120758487767041871207584877690706612075848776926560
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027289631889632341943042560024242378240x7f431ff593000x7f42142372c000012075848776977805120758487771517051207584877767874312075848777706620
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027489631889632341943042560024242423680x7f431ff59a000x7f421423730000012075848777761702120758487779281821207584877818674112075848778211778
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027689631889632341943042560020242435840x7f431ff599000x7f421423734000012075848778260639120758487784302601207584877922897712075848779256069
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027889631889632341943042560028242481280x7f431ff598000x7f421423738000012075848779297005120758487794619371207584877988305512075848779908191
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028089631889632341943042560024242526720x7f431ff597000x7f42142373c000012075848779955058120758487801281741207584878035425312075848780384426
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028289631889632341943042560024242592640x7f431ff596000x7f421423740000012075848780427637120758487805928121207584878120241012075848781230258
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028489631889632341943042560024242648320x7f431ff595000x7f421423744000012075848781288727120758487814585691207584878172960812075848781755003
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028689631889632341943042560020242663040x7f431ff594000x7f421423748000012075848781797172120758487819595281207584878294496412075848783024132
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028889631889632341943042560028242718720x7f431ff593000x7f42142374c000012075848783053497120758487832396831207584878375472112075848783823908
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029089631889632341943042560024242774400x7f431ff59a000x7f421423750000012075848783852652120758487840361601207584878430863912075848784379090
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029289631889632341943042560012242799360x7f431ff599000x7f421423754000012075848784406711120758487845892781207584878532751512075848785396892
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029489631889632341943042560024242865280x7f431ff598000x7f421423758000012075848785434552120758487856007941207584878591903312075848785961952
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029689631889632341943042560020242880000x7f431ff597000x7f42142375c000012075848785992599120758487861849521207584878735454812075848787424580
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029889631889632341943042560032242945920x7f431ff596000x7f421423760000012075848787455838120758487876430271207584878825422512075848788323270
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030089631889632341943042560024243011840x7f431ff595000x7f421423764000012075848788346624120758487885407841207584878885950312075848788928094
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030289631889632341943042560012243049600x7f431ff594000x7f421423768000012075848788955515120758487891467021207584879002541812075848790096496
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030489631889632341943042560024243136000x7f431ff593000x7f42142376c000012075848790138454120758487903049371207584879073837612075848790808138
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030689631889632341943042560020243148160x7f431ff59a000x7f421423770000012075848790839737120758487910220551207584879257180912075848792643329
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030889631889632341943042560020243175680x7f431ff599000x7f421423774000012075848792675188120758487928598081207584879365500512075848793725400
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031089631889632341943042560012243203200x7f431ff598000x7f421423778000012075848793749535120758487939337241207584879434812312075848794417376
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031289631889632341943042560012243240960x7f431ff597000x7f42142377c000012075848794443695120758487946242821207584879578315812075848795853334
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031489631889632341943042560012243288960x7f431ff596000x7f421423780000012075848795892708120758487960599571207584879684651412075848796917693
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031689631889632341943042560020243301120x7f431ff595000x7f421423784000012075848796948650120758487971433131207584880019450212075848800267598
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031889631889632341943042560020243328640x7f431ff594000x7f421423788000012075848800295921120758488004871401207584880202921512075848802099673
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032089631889632341943042560012243356160x7f431ff593000x7f42142378c000012075848802132684120758488023143341207584880310377112075848803174240
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032289631889632341943042560012243393920x7f431ff59a000x7f421423790000012075848803201521120758488033893701207584880567080212075848805741221
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032489631889632341943042560012243441920x7f431ff599000x7f421423794000012075848805786866120758488059535211207584880748951512075848807560782
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032689631889632341943042560020243454080x7f431ff598000x7f421423798000012075848807592982120758488077736741207584881382741212075848813897669
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032889631889632341943042560020243481600x7f431ff597000x7f42142379c000012075848813930590120758488141214911207584881716452012075848817238688
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033089631889632341943042560012243509120x7f431ff596000x7f4214237a0000012075848817267742120758488174563591207584881899619412075848819066535
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332896318896323419430425600122400x7f431ff595000x7f4214237a4000012075848819097954120758488192833921207584882381137612075848823881474