Arquivos
rocm-systems/tests/workloads/HBM/mi200/SQ_INST_LEVEL_LDS.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

38 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_LDSSQ_INST_LEVEL_LDSSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000170915170915335544322560043241600x00x7f158120428000016705461014066167047484172151670560830412716705608417536
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00217091517091532768256001224138880x00x7f1581223f8000016705613583716167056083041271670561372617616705613730821
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051709151709154194304256001224143360x7f15841383800x7f1581223fc000016705613765250167056137261761670561409145416705614093829
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081709151709154194304256001624150400x7f15841382000x7f158122400000016705614130708167056140914541670561450777216705614509885
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111709151709154194304256001624154880x7f15841380800x7f158122404000016705614542874167056145077721670561490249016705614904772
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141709151709154194304256001224159360x7f1581b09f000x7f158122408000016705614938141167056149024901670561520696816705615209052
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171709151709154194304256001224163840x7f1581b09d800x7f15812240c000016705615242121167056152069681670561551256616705615514692
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201709151709154194304256001224170880x7f1581b09c000x7f158122410000016705615558571167056155125661670561581176416705615813843
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231709151709154194304256001624177920x7f1581b09a800x7f158122414000016705615845311167056158117641670561620200216705616204140
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261709151709154194304256001624184960x7f1581b099000x7f158122418000016705616236459167056162020021670561659032016705616592667
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291709151709154194304256001624192000x7f1581b097800x7f15812241c000016705616623716167056165903201670561691031816705616912506
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321709151709154194304256001624199040x7f1581b096000x7f158122420000016705616945745167056169103181670561721127716705617213407
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351709151709154194304256001224206080x7f15841384800x7f158122424000016705617254475167056172112771670561751431516705617516517
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381709151709154194304256001624213120x7f15841383000x7f158122428000016705617549056167056175143151670561790503316705617907234
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411709151709154194304256001624220160x7f15841381800x7f15812242c000016705617938523167056179050331670561831815116705618320420
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441709151709154194304256001624227200x7f15841380000x7f158122430000016705618354059167056183181511670561862918916705618631510
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471709151709154194304256001224234240x7f1581b09e800x7f158122434000016705618664899167056186291891670561893318716705618935370
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501709151709154194304256001224241280x7f1581b09d000x7f158122438000016705618976219167056189331871670561921558616705619217171
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531709151709154194304256001624248320x7f1581b09b800x7f15812243c000016705619250130167056192155861670561957750416705619579089
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561709151709154194304256001624255360x7f1581b09a000x7f158122440000016705619611028167056195775041670561993942216705619941087
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591709151709154194304256001224262400x7f1581b098800x7f158122444000016705619972946167056199394221670562021974016705620221148
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621709151709154194304256001224269440x7f1581b097000x7f158122448000016705620253457167056202197401670562049829816705620499869
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651709151709154194304256001224276480x7f15841385800x7f15812244c000016705620539347167056204982981670562078101716705620782589
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681709151709154194304256001624286080x7f15841384000x7f158122450000016705620814888167056207810171670562114757516705621149197
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711709151709154194304256001624293120x7f15841382800x7f158122454000016705621181846167056211475751670562151493316705621516545
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741709151709154194304256001224300160x7f15841381000x7f158122458000016705621548714167056215149331670562179189116705621793446
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077170915170915419430425600824309760x7f1581b09f800x7f15812245c000016705621824935167056217918911670562206901016705622070507
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801709151709154194304256001224316800x7f1581b09e000x7f158122460000016705622110246167056220690101670562234964816705622351238
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831709151709154194304256001624326400x7f1581b09c800x7f158122464000016705622382937167056223496481670562271620616705622717856
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861709151709154194304256001224336000x7f1581b09b000x7f158122468000016705622749895167056227162061670562308036416705623082014
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891709151709154194304256001224345600x7f1581b099800x7f15812246c000016705623113953167056230803641670562336228316705623363934
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092170915170915419430425600824355200x7f1581b098000x7f158122470000016705623395343167056233622831670562363732116705623638755
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951709151709154194304256001224362240x7f1581b096800x7f158122474000016705623676674167056236373211670562391508016705623916616
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981709151709154194304256001224371840x7f15841385000x7f158122478000016705623948835167056239150801670562428259816705624284174
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011709151709154194304256001224381440x7f15841383800x7f15812247c000016705624316053167056242825981670562464483616705624646502
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041709151709154194304256001224391040x7f15841382000x7f158122480000016705624677771167056246448361670562492291416705624924563
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107170915170915419430425600824403200x7f15841380800x7f158122484000016705624956492167056249229141670562519907216705625200644
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101709151709154194304256001224412800x7f1581b09f000x7f158122488000016705625240123167056251990721670562547827116705625479755
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131709151709154194304256001224422400x7f1581b09d800x7f15812248c000016705625511394167056254782711670562584178916705625843443
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161709151709154194304256001224432000x7f1581b09c000x7f158122490000016705625874812167056258417891670562621698716705626218581
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119170915170915419430425600824441600x7f1581b09a800x7f158122494000016705626252310167056262169871670562650146516705626503051
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221709151709154194304256001224453760x7f1581b099000x7f158122498000016705626534850167056265014651670562678018416705626781762
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251709151709154194304256001224463360x7f1581b097800x7f15812249c000016705626820811167056267801841670562706322216705627064683
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281709151709154194304256001224475520x7f1581b096000x7f1581224a0000016705627096992167056270632221670562742626016705627427841
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311709151709154194304256001224485120x7f15841384800x7f1581224a4000016705627460410167056274262601670562778977816705627791399
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134170915170915419430425600824494720x7f15841383000x7f1581224a8000016705627823198167056277897781670562807073716705628072250
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371709151709154194304256001224506880x7f15841381800x7f1581224ac000016705628104449167056280707371670562834897516705628350641
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401709151709154194304256001224516480x7f15841380000x7f1581224b0000016705628390690167056283489751670562862593316705628627472
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431709151709154194304256001224528640x7f1581b09e800x7f1581224b4000016705628658741167056286259331670562898961116705628991380
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461709151709154194304256001224540800x7f1581b09d000x7f1581224b8000016705629023279167056289896111670562935632916705629357898
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149170915170915419430425600824552960x7f1581b09b800x7f1581224bc000016705629389227167056293563291670562963376816705629635259
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521709151709154194304256001224567680x7f1581b09a000x7f1581224c0000016705629668108167056296337681670562991408616705629915740
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551709151709154194304256001224577280x7f1581b098800x7f1581224c4000016705629953789167056299140861670563020064516705630202360
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581709151709154194304256001224589440x7f1581b097000x7f1581224c8000016705630234109167056302006451670563057040316705630572018
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611709151709154194304256001224601600x7f15841385800x7f1581224cc000016705630604517167056305704031670563093344116705630935096
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164170915170915419430425600824613760x7f15841384000x7f1581224d0000016705630967475167056309334411670563121119916705631212797
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671709151709154194304256001224628480x7f15841382800x7f1581224d4000016705631245236167056312111991670563149183816705631493288
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701709151709154194304256001224638080x7f15841381000x7f1581224d8000016705631533587167056314918381670563176831616705631769949
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731709151709154194304256001224650240x7f1581b09f800x7f1581224dc000016705631801498167056317683161670563213455416705632136097
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761709151709154194304256001224662400x7f1581b09e000x7f1581224e0000016705632168166167056321345541670563249519216705632496835
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179170915170915419430425600824674560x7f1581b09c800x7f1581224e4000016705632527794167056324951921670563277183016705632773426
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821709151709154194304256001224689280x7f1581b09b000x7f1581224e8000016705632805225167056327718301670563306142916705633062946
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851709151709154194304256001224701440x7f1581b099800x7f1581224ec000016705633101775167056330614291670563333934716705633341007
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881709151709154194304256001224716160x7f1581b098000x7f1581224f0000016705633372396167056333393471670563370270516705633704195
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911709151709154194304256001224728320x7f1581b096800x7f1581224f4000016705633735424167056337027051670563406350316705634064994
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194170915170915419430425600824740480x7f15841385000x7f1581224f8000016705634097542167056340635031670563435358216705634355394
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971709151709154194304256001224757760x7f15841383800x7f1581224fc000016705634386893167056343535821670563464718016705634648754
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001709151709154194304256001224769920x7f15841382000x7f158122500000016705634687983167056346471801670563492173916705634923435
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031709151709154194304256001224784640x7f15841380800x7f158122504000016705634956294167056349217391670563528877616705635290333
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061709151709154194304256001224799360x7f1581b09f000x7f158122508000016705635322732167056352887761670563565229416705635653921
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209170915170915419430425600824814080x7f1581b09d800x7f15812250c000016705635686100167056356522941670563592765316705635929382
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121709151709154194304256001224831360x7f1581b09c000x7f158122510000016705635961641167056359276531670563622333116705636224933
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151709151709154194304256001224843520x7f1581b09a800x7f158122514000016705636275471167056362233311670563651053016705636512303
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181709151709154194304256001224858240x7f1581b099000x7f158122518000016705636547462167056365105301670563688028816705636881941
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211709151709154194304256001224872960x7f1581b097800x7f15812251c000016705636913470167056368802881670563724252616705637244019
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241709151709154194304256001224887680x7f1581b096000x7f158122520000016705637275078167056372425261670563751804416705637519600
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271709151709154194304256001224907520x7f15841384800x7f158122524000016705637550909167056375180441670563781932216705637820900
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301709151709154194304256001224919680x7f15841383000x7f158122528000016705637860129167056378193221670563811116116705638112911
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331709151709154194304256001224934400x7f15841381800x7f15812252c000016705638145569167056381111611670563848203916705638483688
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361709151709154194304256001224949120x7f15841380000x7f158122530000016705638516367167056384820391670563884363716705638845166
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391709151709154194304256001224963840x7f1581b09e800x7f158122534000016705638876125167056388436371670563911931516705639120827
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421709151709154194304256001224983680x7f1581b09d000x7f158122538000016705639152206167056391193151670563942763416705639429167
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451709151709154194304256001224995840x7f1581b09b800x7f15812253c000016705639468046167056394276341670563970635216705639707928
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024817091517091541943042560012241013120x7f1581b09a000x7f158122540000016705639739237167056397063521670564007243016705640074076
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025117091517091541943042560012241027840x7f1581b098800x7f158122544000016705640106385167056400724301670564044298816705640444684
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025417091517091541943042560012241042560x7f1581b097000x7f158122548000016705640475543167056404429881670564072154616705640723135
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025717091517091541943042560012241062400x7f15841385800x7f15812254c000016705640754954167056407215461670564103642516705641038054
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026017091517091541943042560012241077120x7f15841384000x7f158122550000016705641077623167056410364251670564132154316705641323145
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026317091517091541943042560016241094400x7f15841382800x7f158122554000016705641355534167056413215431670564168250116705641684083
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026617091517091541943042560016241111680x7f15841381000x7f158122558000016705641715962167056416825011670564204713916705642048651
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691709151709154194304256008241128960x7f1581b09f800x7f15812255c000016705642088470167056420471391670564234009716705642341702
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027217091517091541943042560012241151360x7f1581b09e000x7f158122560000016705642373881167056423400971670564266249616705642664061
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027517091517091541943042560012241166080x7f1581b09c800x7f158122564000016705642702790167056426624961670564294809416705642949592
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027817091517091541943042560016241183360x7f1581b09b000x7f158122568000016705642982481167056429480941670564331001216705643311670
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028117091517091541943042560016241200640x7f1581b099800x7f15812256c000016705643343419167056433100121670564367449016705643676168
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028417091517091541943042560012241217920x7f1581b098000x7f158122570000016705643708237167056436744901670564395592816705643957589
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028717091517091541943042560012241240320x7f1581b096800x7f158122574000016705643989567167056439559281670564428664716705644288298
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029017091517091541943042560012241255040x7f15841385000x7f158122578000016705644327316167056442866471670564456328516705644564759
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029317091517091541943042560012241274880x7f15841383800x7f15812257c000016705644598077167056445632851670564493064316705644932357
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029617091517091541943042560012241292160x7f15841382000x7f158122580000016705644966025167056449306431670564529368116705645295355
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029917091517091541943042560012241309440x7f15841380800x7f158122584000016705645326764167056452936811670564557591916705645577375
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030217091517091541943042560012241334400x7f1581b09f000x7f158122588000016705645609904167056455759191670564591303816705645914684
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030517091517091541943042560012241349120x7f1581b09d800x7f15812258c000016705645954183167056459130381670564620231616705646203785
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030817091517091541943042560012241368960x7f1581b09c000x7f158122590000016705646235244167056462023161670564656615416705646567743
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031117091517091541943042560012241388800x7f1581b09a800x7f158122594000016705646599482167056465661541670564692695216705646928371
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031417091517091541943042560012241408640x7f1581b099000x7f158122598000016705646960660167056469269521670564721655016705647218111
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031717091517091541943042560012241436160x7f1581b097800x7f15812259c000016705647250470167056472165501670564757334816705647574770
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032017091517091541943042560012241453440x7f1581b096000x7f1581225a0000016705647614498167056475733481670564785638716705647857970
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032317091517091541943042560012241475840x7f15841384800x7f1581225a4000016705647889909167056478563871670564821654516705648218339
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032617091517091541943042560012241495680x7f15841383000x7f1581225a8000016705648249878167056482165451670564857686316705648578207
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032917091517091541943042560012241515520x7f15841381800x7f1581225ac000016705648610286167056485768631670564887094116705648872517
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033217091517091541943042560012241543040x7f15841380000x7f1581225b0000016705648904166167056488709411670564923637916705649237945
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033517091517091541943042560012241562880x7f1581b09e800x7f1581225b4000016705649277154167056492363791670564952293816705649524456
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033817091517091541943042560012241587840x7f1581b09d000x7f1581225b8000016705649556755167056495229381670564989013616705649891814
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034117091517091541943042560012241610240x7f1581b09b800x7f1581225bc000016705649923533167056498901361670565025509316705650256942
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034417091517091541943042560012241632640x7f1581b09a000x7f1581225c0000016705650288611167056502550931670565056757216705650569171
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034717091517091541943042560012241665280x7f1581b098800x7f1581225c4000016705650601080167056505675721670565095781016705651003527
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035017091517091541943042560012241685120x7f1581b097000x7f1581225c8000016705651023086167056509578101670565128484816705651286288
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035317091517091541943042560012241712640x7f15841385800x7f1581225cc000016705651318327167056512848481670565165044616705651652016
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035617091517091541943042560012241737600x7f15841384000x7f1581225d0000016705651683975167056516504461670565201700416705652018544
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035917091517091541943042560012241762560x7f15841382800x7f1581225d4000016705652050313167056520170041670565233300216705652334563
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036217091517091541943042560012241797760x7f15841381000x7f1581225d8000016705652366742167056523330021670565275028016705652772479
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036517091517091541943042560012241822720x7f1581b09f800x7f1581225dc000016705652791468167056527502801670565306995816705653071509
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036817091517091541943042560012241855360x7f1581b09e000x7f1581225e0000016705653103148167056530699581670565345027616705653468276
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037117091517091541943042560012241885440x7f1581b09c800x7f1581225e4000016705653483656167056534502761670565383379416705653851773
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037417091517091541943042560012241915520x7f1581b09b000x7f1581225e8000016705653867373167056538337941670565418867216705654190362
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037717091517091541943042560012241958400x7f1581b099800x7f1581225ec000016705654222511167056541886721670565466866916705654712335
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038017091517091541943042560012241985920x7f1581b098000x7f1581225f0000016705654732005167056546686691670565503874716705655040204
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038317091517091541943042560012242023680x7f1581b096800x7f1581225f4000016705655072343167056550387471670565542882516705655471580
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038617091517091541943042560012242058880x7f15841385000x7f1581225f8000016705655483290167056554288251670565584850216705655890756
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038917091517091541943042560012242094080x7f15841383800x7f1581225fc000016705655902996167056558485021670565624722016705656248815
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039217091517091541943042560012242144640x7f15841382000x7f158122600000016705656280594167056562472201670565676369716705656806546
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039517091517091541943042560012242177280x7f15841380800x7f158122604000016705656825826167056567636971670565714497516705657146445
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039817091517091541943042560012242220160x7f1581b09f000x7f158122608000016705657178134167056571449751670565755713316705657576841
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040117091517091541943042560012242260480x7f1581b09d800x7f15812260c000016705657590051167056575571331670565798241116705658000557
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040417091517091541943042560012242300800x7f1581b09c000x7f158122610000016705658015917167056579824111670565839104816705658409674
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040717091517091541943042560012242359040x7f1581b09a800x7f158122614000016705658424283167056583910481670565896928516705659012224
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041017091517091541943042560012242394240x7f1581b099000x7f158122618000016705659030953167056589692851670565937024316705659371872
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041317091517091541943042560012242442240x7f1581b097800x7f15812261c000016705659403231167056593702431670565980400116705659847066
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041617091517091541943042560012242487680x7f1581b096000x7f158122620000016705659860736167056598040011670566027119816705660313751
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041917091517091541943042560012242533120x7f15841384800x7f158122624000016705660324991167056602711981670566072303516705660765716
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221709151709154194304256008242555520x7f15841383000x7f158122628000016705660776996167056607230351670566138719216705661429964
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042517091517091541943042560012242598400x7f15841381800x7f15812262c000016705661448984167056613871921670566182350916705661843211
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042817091517091541943042560012242656640x7f15841380000x7f158122630000016705661856820167056618235091670566231358716705662357434
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043117091517091541943042560012242712320x7f1581b09e800x7f158122634000016705662368954167056623135871670566283454416705662879177
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341709151709154194304256008242732160x7f1581b09d000x7f158122638000016705662890137167056628345441670566334606116705663388510
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371709151709154194304256008242757120x7f1581b09b800x7f15812263c000016705663399780167056633460611670566411341716705664155555
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044017091517091541943042560012242807680x7f1581b09a000x7f158122640000016705664174995167056641134171670566459309416705664634860
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044317091517091541943042560012242876160x7f1581b098800x7f158122644000016705664645999167056645930941670566515933116705665201781
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044617091517091541943042560012242942080x7f1581b097000x7f158122648000016705665214081167056651593311670566572428816705665766703
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491709151709154194304256008242969600x7f15841385800x7f15812264c000016705665777872167056657242881670566629532516705666341184
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521709151709154194304256008242999680x7f15841384000x7f158122650000016705666352533167056662953251670566717388016705667217895
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551709151709154194304256008243027200x7f15841382800x7f158122654000016705667236994167056671738801670566783595616705667883413
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045817091517091541943042560012243054720x7f15841381000x7f158122658000016705667894903167056678359561670566852811216705668569771
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046117091517091541943042560012243082240x7f1581b09f800x7f15812265c000016705668580890167056685281121670566920810816705669251418
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641709151709154194304256008243109760x7f1581b09e000x7f158122660000016705669262958167056692081081670566988890516705669909047
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671709151709154194304256008243132160x7f1581b09c800x7f158122664000016705669920926167056698886371670567098047116705671030870
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701709151709154194304256008243159680x7f1581b09b000x7f158122668000016705671050849167056709804711670567207294316705672118434
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047317091517091541943042560012243187200x7f1581b099800x7f15812266c000016705672129754167056720729431670567318733616705673252977
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047617091517091541943042560012243214720x7f1581b098000x7f158122670000016705673264076167056731873361670567431805016705674388629
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791709151709154194304256008243242240x7f1581b096800x7f158122674000016705674400419167056743180501670567543788316705675504513
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821709151709154194304256008243264640x7f15841385000x7f158122678000016705675515892167056754378831670567738635116705677458599
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851709151709154194304256008243292160x7f15841383800x7f15812267c000016705677477468167056773863511670567930857916705679379225
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048817091517091541943042560012243319680x7f15841382000x7f158122680000016705679391365167056793085791670568129992716705681367280
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049117091517091541943042560012243347200x7f15841380800x7f158122684000016705681378720167056812999271670568326855516705683340085
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941709151709154194304256008243374720x7f1581b09f000x7f158122688000016705683351845167056832685551670568520374316705685270182
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049717091517091541943042560082400x7f1581b09d800x7f15812268c000016705685281242167056852037431670568881492216705688888143