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

44 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjGRBM_COUNTGRBM_GUI_ACTIVESQ_WAVESSQ_IFETCHSQ_IFETCH_LEVELSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000236503236503335544322560043241600x00x7fe83c20428038583238583252428847185926820947638686417833173257611178324604872901783332406379317833324177862
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00223650323650332768256001224138880x00x7fe83c223f8034124341245128192554062402017833329373303178333240637931783332950331717833329508120
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0052365032365034194304256001224143360x7fe83f16b3800x7fe83c223fc0166451166451655369175041406621573780017833329547519178333295033171783332988731717833329890091
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0082365032365034194304256001624150400x7fe83f16b2000x7fe83c2240003208133208136553611141121678691897328417833329928940178333298873171783333032651717833330329380
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00112365032365034194304256001624154880x7fe83f16b0800x7fe83c224040323006323006655369175041469781653956817833330364489178333303265171783333074779817833330753919
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00142365032365034194304256001224159360x7fe83cb0bf000x7fe83c2240801685501685506553610485761591741785629217833330784798178333307477981783333106811817833331070481
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00172365032365034194304256001224163840x7fe83cb0bd800x7fe83c2240c0168572168572655369830401480901656943617833331104930178333310681181783333138667817833331389103
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00202365032365034194304256001224170880x7fe83cb0bc000x7fe83c2241001676641676646553611141121626101822486017833331435702178333313866781783333170331817833331705705
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00232365032365034194304256001624177920x7fe83cb0ba800x7fe83c2241403200793200796553613107202022322264798817833331740015178333317033181783333210859917833332110925
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00262365032365034194304256001624184960x7fe83cb0b9000x7fe83c2241803168093168096553611796481762901985541617833332143565178333321085991783333252843917833332530935
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00292365032365034194304256001624192000x7fe83cb0b7800x7fe83c2241c01682811682816553612451841886202116623217833332564054178333325284391783333283995917833332842307
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00322365032365034194304256001624199040x7fe83cb0b6000x7fe83c2242001694941694946553612451842025202261251217833332876086178333328399591783333315403917833333156369
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00352365032365034194304256001224206080x7fe83f16b4800x7fe83c2242401712991712996553612451842007542246797617833333198828178333331540391783333347132017833333473552
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00382365032365034194304256001624213120x7fe83f16b3000x7fe83c2242803207763207766553614417922160932416872817833333508101178333334713201783333387484017833333881351
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00412365032365034194304256001624220160x7fe83f16b1800x7fe83c2242c03163933163936553613107201976172220498817833333911551178333338748401783333428636017833334289041
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00442365032365034194304256001624227200x7fe83f16b0000x7fe83c2243001692641692646553613762562051512303440417833334324160178333342863601783333460844117833334610943
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00472365032365034194304256001224234240x7fe83cb0be800x7fe83c2243401682631682636553614417922217532485885217833334644352178333346084411783333492284117833334925195
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00502365032365034194304256001224241280x7fe83cb0bd000x7fe83c2243801674921674926553613107201957462193132417833334967074178333349228411783333524636117833335248667
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00532365032365034194304256001624248320x7fe83cb0bb800x7fe83c2243c03162913162916553615728642323112611378817833335285227178333352463611783333562444117833335626348
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00562365032365034194304256001624255360x7fe83cb0ba000x7fe83c2244003126733126736553614417922092412338506417833335661197178333356244411783333599964217833336001459
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00592365032365034194304256001224262400x7fe83cb0b8800x7fe83c2244401665551665556553615073282246522519620817833336035928178333359996421783333628812217833336290022
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00622365032365034194304256001224269440x7fe83cb0b7000x7fe83c2244801680331680336553616384002430002717208417833336324411178333362881221783333657788217833336579724
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00652365032365034194304256001224276480x7fe83f16b5800x7fe83c2244c01693251693256553614417922158042416476817833336621253178333365778821783333686524217833336867167
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00682365032365034194304256001624286080x7fe83f16b4000x7fe83c2245003179833179836553617039362518762821638417833336903336178333368652421783333723996317833337241868
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00712365032365034194304256001624293120x7fe83f16b2800x7fe83c2245403160713160716553615728642338912618538417833337276507178333372399631783333761500317833337616889
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00742365032365034194304256001224300160x7fe83f16b1000x7fe83c2245801678271678276553616384002430522725015617833337650858178333376150031783333791180317833337913661
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077236503236503419430425600824309760x7fe83cb0bf800x7fe83c2245c01675611675616553618350082700193031399217833337948630178333379118031783333821612317833338218214
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00802365032365034194304256001224316800x7fe83cb0be000x7fe83c2246001661551661556553615073282235622506553617833338260273178333382161231783333850572417833338507656
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00832365032365034194304256001624326400x7fe83cb0bc800x7fe83c2246403137083137086553618350082725963045448817833338544396178333385057241783333888268417833338884677
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00862365032365034194304256001224336000x7fe83cb0bb000x7fe83c2246803135613135616553617039362482192781604417833338919186178333388826841783333925708417833339259098
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00892365032365034194304256001224345600x7fe83cb0b9800x7fe83c2246c01685311685316553617694722647012965909617833339293197178333392570841783333954524417833339547101
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092236503236503419430425600824355200x7fe83cb0b8000x7fe83c2247001685331685336553620316163037433404136417833339581850178333395452441783333983388517833339835803
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00952365032365034194304256001224362240x7fe83cb0b6800x7fe83c2247401687211687216553616384002438802743323217833339877512178333398338851783334012684517833340128726
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00982365032365034194304256001224371840x7fe83f16b5000x7fe83c2247803118013118016553619660802889083227514417833340163205178333401268451783334050940517833340511177
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001012365032365034194304256001224381440x7fe83f16b3800x7fe83c2247c03145923145926553618350082721593048497617833340546636178333405094051783334088924517833340891087
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001042365032365034194304256001224391040x7fe83f16b2000x7fe83c2248001680111680116553619005442814993145258417833340925936178333408892451783334118140617833341183040
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107236503236503419430425600824403200x7fe83f16b0800x7fe83c2248401686361686366553622282243281963675462017833341218079178333411814061783334147260617833341474483
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001102365032365034194304256001224412800x7fe83cb0bf000x7fe83c2248801691341691346553617039362579502883317217833341515762178333414726061783334176188617833341763986
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001132365032365034194304256001224422400x7fe83cb0bd800x7fe83c2248c03116003116006553620971523113803486261217833341798245178333417618861783334213756617833342139966
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001162365032365034194304256001224432000x7fe83cb0bc000x7fe83c2249003115423115426553619660802840023184430417833342176125178333421375661783334252332717833342525247
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119236503236503419430425600824441600x7fe83cb0ba800x7fe83c2249401683421683426553620316163027653394018817833342559536178333425233271783334281564717833342817649
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001222365032365034194304256001224453760x7fe83cb0b9000x7fe83c2249801691651691656553624248323622674055067217833342852049178333428156471783334311404717833343115852
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001252365032365034194304256001224463360x7fe83cb0b7800x7fe83c2249c01681861681866553618350082721303042478417833343157201178333431140471783334340572717833343407425
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001282365032365034194304256001224475520x7fe83cb0b6000x7fe83c224a003127703127706553622282243270503663477617833343441984178333434057271783334378092817833343782835
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001312365032365034194304256001224485120x7fe83f16b4800x7fe83c224a403060563060566553620971523091233467275217833343818545178333437809281783334415868817833344160556
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134236503236503419430425600824494720x7fe83f16b3000x7fe83c224a801675481675486553621626883174103561906817833344195655178333441586881783334444796817833344449669
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001372365032365034194304256001224506880x7fe83f16b1800x7fe83c224ac01695041695046553626214403849264316137617833344484848178333444479681783334473996817833344741802
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001402365032365034194304256001224516480x7fe83f16b0000x7fe83c224b001655121655126553619660802916353274415617833344783641178333447399681783334503260917833345034574
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001432365032365034194304256001224528640x7fe83cb0be800x7fe83c224b403076353076356553623592963550723981460817833345076833178333450326091783334540732917833345409095
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001462365032365034194304256001224540800x7fe83cb0bd000x7fe83c224b803060443060446553622282243282273684432017833345443604178333454073291783334578396917833345785826
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149236503236503419430425600824552960x7fe83cb0bb800x7fe83c224bc01688451688456553622937603486543897136417833345820455178333457839691783334607532917833346083318
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001522365032365034194304256001224567680x7fe83cb0ba000x7fe83c224c001694981694986553627525124042284535467217833346112458178333460753291783334637341017833346375231
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001552365032365034194304256001224577280x7fe83cb0b8800x7fe83c224c401690711690716553620316163030423391350017833346416440178333463734101783334666701017833346668874
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001582365032365034194304256001224589440x7fe83cb0b7000x7fe83c224c803071223071226553624903683694014142825617833346706213178333466670101783334704093017833347042884
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001612365032365034194304256001224601600x7fe83f16b5800x7fe83c224cc03089593089596553623592963652804088732417833347076864178333470409301783334742045017833347422375
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164236503236503419430425600824613760x7fe83f16b4000x7fe83c224d001699561699566553624248323817804272940017833347457904178333474204501783334771101117833347712878
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001672365032365034194304256001224628480x7fe83f16b2800x7fe83c224d401734071734076553629491204419314948142017833347747547178333477110111783334800509117833348006880
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001702365032365034194304256001224638080x7fe83f16b1000x7fe83c224d801663441663446553621626883219753607224817833348048719178333480050911783334830269117833348304553
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001732365032365034194304256001224650240x7fe83cb0bf800x7fe83c224dc03058143058146553626214403890804338433617833348339332178333483026911783334867805117833348680044
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001762365032365034194304256001224662400x7fe83cb0be000x7fe83c224e003041553041556553624903683645214081481617833348715763178333486780511783334905053217833349052354
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179236503236503419430425600824674560x7fe83cb0bc800x7fe83c224e401700161700166553625559043811394279406817833349087144178333490505321783334934525217833349346957
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001822365032365034194304256001224689280x7fe83cb0bb000x7fe83c224e801770171770176553631457284708835268458017833349382036178333493452521783334964365217833349645520
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001852365032365034194304256001224701440x7fe83cb0b9800x7fe83c224ec01665781665786553622282243278043676491617833349687679178333496436521783334993549217833349937203
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001882365032365034194304256001224716160x7fe83cb0b8000x7fe83c224f003024573024576553627525124061474554445617833349973952178333499354921783335031677317833350318913
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001912365032365034194304256001224728320x7fe83cb0b6800x7fe83c224f403045103045106553626214403864234327296817833350354692178333503167731783335069293317833350694984
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194236503236503419430425600824740480x7fe83f16b5000x7fe83c224f801673391673396553626869763991174468451217833350728583178333506929331783335098205317833350984027
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001972365032365034194304256001224757760x7fe83f16b3800x7fe83c224fc01836141836146553633423364966135563313617833351018986178333509820531783335128253317833351284429
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002002365032365034194304256001224769920x7fe83f16b2000x7fe83c2250001671661671666553623592963501533937362417833351338838178333512825331783335157677417833351578622
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002032365032365034194304256001224784640x7fe83f16b0800x7fe83c2250403036303036306553628835844358484873492817833351615461178333515767741783335195821417833351960042
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002062365032365034194304256001224799360x7fe83cb0bf000x7fe83c2250803031003031006553626869763995944476550417833351995661178333519582141783335233309417833352335093
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209236503236503419430425600824814080x7fe83cb0bd800x7fe83c2250c01704251704256553628180484211124716084017833352369572178333523330941783335262317417833352625026
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002122365032365034194304256001224831360x7fe83cb0bc000x7fe83c2251001924671924676553635389445380816020432417833352659005178333526231741783335292765517833352929528
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002152365032365034194304256001224843520x7fe83cb0ba800x7fe83c2251401693221693226553624248323595774032156817833352971487178333529276551783335322445517833353226431
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002182365032365034194304256001224858240x7fe83cb0b9000x7fe83c2251803080863080866553630146564537095072701217833353260050178333532244551783335361149517833353613361
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002212365032365034194304256001224872960x7fe83cb0b7800x7fe83c2251c03031143031146553628180484144574639543217833353647860178333536114951783335398573517833353987472
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002242365032365034194304256001224887680x7fe83cb0b6000x7fe83c2252001682041682046553629491204398174924416817833354022171178333539857351783335429181617833354293764
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002272365032365034194304256001224907520x7fe83f16b4800x7fe83c2252402018712018716553637355525608706280696417833354328653178333542918161783335460541617833354607396
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002302365032365034194304256001224919680x7fe83f16b3000x7fe83c2252801669161669166553625559043956554439109617833354649265178333546054161783335489565617833354897599
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002332365032365034194304256001224934400x7fe83f16b1800x7fe83c2252c03045773045776553631457284666305228262017833354933938178333548956561783335527261617833355274500
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002362365032365034194304256001224949120x7fe83f16b0000x7fe83c2253003016183016186553629491204380444899941617833355310369178333552726161783335564589717833355647791
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002392365032365034194304256001224963840x7fe83cb0be800x7fe83c2253401688351688356553630801924593385141408017833355681500178333556458971783335593405717833355936003
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002422365032365034194304256001224983680x7fe83cb0bd000x7fe83c2253802114222114226553639321605849626542938817833355970523178333559340571783335625661717833356258445
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002452365032365034194304256001224995840x7fe83cb0bb800x7fe83c2253c01675111675116553626214403888464357800017833356300124178333562566171783335655261717833356554738
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024823650323650341943042560012241013120x7fe83cb0ba000x7fe83c2254003047833047836553632768004872505467688017833356589057178333565526171783335692685817833356928709
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025123650323650341943042560012241027840x7fe83cb0b8800x7fe83c2254403040313040316553630801924659945215236417833356962958178333569268581783335730285817833357304939
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025423650323650341943042560012241042560x7fe83cb0b7000x7fe83c2254801688471688476553632112644729195292914817833357338709178333573028581783335759357817833357595522
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025723650323650341943042560012241062400x7fe83f16b5800x7fe83c2254c02188452188456553641287686092036826765617833357630121178333575935781783335791997817833357921834
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026023650323650341943042560012241077120x7fe83f16b4000x7fe83c2255001672011672016553627525124080074570490417833357964573178333579199781783335821965917833358221797
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026323650323650341943042560016241094400x7fe83f16b2800x7fe83c2255403000533000536553634078725090535699911217833358258066178333582196591783335859709917833358598907
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026623650323650341943042560016241111680x7fe83f16b1000x7fe83c2255803002003002006553632112644742445313124017833358633596178333585970991783335897261917833358974498
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002692365032365034194304256008241128960x7fe83cb0bf800x7fe83c2255c01687881687886553632768004928585520586417833359009827178333589726191783335926237917833359264261
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027223650323650341943042560012241151360x7fe83cb0be000x7fe83c2256002321642321646553643253766487497265856017833359298580178333592623791783335959406017833359595993
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027523650323650341943042560012241166080x7fe83cb0bc800x7fe83c2256401693761693766553628180484296234812955617833359638381178333595940601783335988830017833359890205
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027823650323650341943042560016241183360x7fe83cb0bb000x7fe83c2256803007133007136553635389445244235873219617833359923974178333598883001783336026014017833360262016
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028123650323650341943042560016241200640x7fe83cb0b9800x7fe83c2256c03020083020086553634078725027705635606017833360296845178333602601401783336063054017833360632417
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028423650323650341943042560012241217920x7fe83cb0b8000x7fe83c2257001670771670776553634078725132805744873617833360666996178333606305401783336091902117833360920880
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028723650323650341943042560012241240320x7fe83cb0b6800x7fe83c2257402405482405486553645219846778507602939217833360955349178333609190211783336125742117833361259191
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029023650323650341943042560012241255040x7fe83f16b5000x7fe83c2257801692381692386553630146564603125159596817833361301430178333612574211783336155598117833361557714
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029323650323650341943042560012241274880x7fe83f16b3800x7fe83c2257c03033213033216553638010885650906326502417833361592213178333615559811783336193534117833361937344
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029623650323650341943042560012241292160x7fe83f16b2000x7fe83c2258003041693041696553636700165552136217508817833361972664178333619353411783336232062217833362322655
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029923650323650341943042560012241309440x7fe83f16b0800x7fe83c2258401732571732576553636700165580456246935617833362358914178333623206221783336261710217833362619097
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030223650323650341943042560012241334400x7fe83cb0bf000x7fe83c2258802584612584616553649152007468178359478017833362654677178333626171021783336296558217833362967549
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030523650323650341943042560012241349120x7fe83cb0bd800x7fe83c2258c01709111709116553631457284678695241026017833363011138178333629655821783336326334317833363265301
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030823650323650341943042560012241368960x7fe83cb0bc000x7fe83c2259003019193019196553640632326179226921998817833363300421178333632633431783336363694317833363638762
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031123650323650341943042560012241388800x7fe83cb0ba800x7fe83c2259403018293018296553639321605978576695378417833363674591178333636369431783336400926317833364011223
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031423650323650341943042560012241408640x7fe83cb0b9000x7fe83c2259801779681779686553639321605960566673408417833364045152178333640092631783336431262317833364314605
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031723650323650341943042560012241436160x7fe83cb0b7800x7fe83c2259c02784302784306553653084167953908914403217833364348674178333643126231783336467134417833364673196
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032023650323650341943042560012241453440x7fe83cb0b6000x7fe83c225a001681581681586553633423364961155551157617833364715915178333646713441783336496798417833364969829
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032323650323650341943042560012241475840x7fe83f16b4800x7fe83c225a403021123021126553643253766793607599873617833365004128178333649679841783336534318417833365345140
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032623650323650341943042560012241495680x7fe83f16b3000x7fe83c225a803000383000386553641943046400407157862417833365380529178333653431841783336571806417833365719900
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032923650323650341943042560012241515520x7fe83f16b1800x7fe83c225ac01872961872966553641943046337087097964817833365753980178333657180641783336602110517833366023093
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033223650323650341943042560012241543040x7fe83f16b0000x7fe83c225b003000343000346553657016328666519705684417833366058802178333660211051783336640190517833366403933
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033523650323650341943042560012241562880x7fe83cb0be800x7fe83c225b401718121718126553637355525598956269460017833366446302178333664019051783336670030517833366702346
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033823650323650341943042560012241587840x7fe83cb0bd000x7fe83c225b803033293033296553648496647641368567020417833366739525178333667003051783336707966517833367081477
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034123650323650341943042560012241610240x7fe83cb0bb800x7fe83c225bc03042823042826553647185927380838272623217833367115496178333670796651783336746718617833367469197
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034423650323650341943042560012241632640x7fe83cb0ba000x7fe83c225c002064112064116553647185927169438022873217833367503216178333674671861783336778366617833367785549
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034723650323650341943042560012241665280x7fe83cb0b8800x7fe83c225c4034002334002365536648806498310611007686417833367819648178333677836661783336818286617833368209779
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035023650323650341943042560012241685120x7fe83cb0b7000x7fe83c225c801843791843796553641287686215866957452817833368228628178333681828661783336850078717833368502701
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035323650323650341943042560012241712640x7fe83f16b5800x7fe83c225cc03037033037036553653739528590649625195617833368539740178333685007871783336888030717833368882192
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035623650323650341943042560012241737600x7fe83f16b4000x7fe83c225d003061513061516553652428808480469489967217833368917151178333688803071783336926094717833369265292
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035923650323650341943042560012241762560x7fe83f16b2800x7fe83c225d402266532266536553652428807826518770965217833369297242178333692609471783336958862717833369590554
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036223650323650341943042560012241797760x7fe83f16b1000x7fe83c225d80380709380709655367274496109683512288050417833369624613178333695886271783337001902817833370038103
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036523650323650341943042560012241822720x7fe83cb0bf800x7fe83c225dc02113262113266553649152007342268220299617833370063632178333700190281783337034942817833370351515
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036823650323650341943042560012241855360x7fe83cb0be000x7fe83c225e0030802730802765536642252899060611094562817833370385265178333703494281783337073486817833370784165
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037123650323650341943042560012241885440x7fe83cb0bc800x7fe83c225e40311334311334655366291456101556211368856017833370794694178333707348681783337116094917833371207294
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037423650323650341943042560012241915520x7fe83cb0bb000x7fe83c225e8026639126639165536629145695954110745560417833371218164178333711609491783337154654917833371548436
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037723650323650341943042560012241958400x7fe83cb0b9800x7fe83c225ec0461600461600655368847360133436614953301217833371582655178333715465491783337202206917833372068323
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038023650323650341943042560012241985920x7fe83cb0b8000x7fe83c225f002455332455336553657016328723859774662817833372087512178333720220691783337239935017833372401214
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038323650323650341943042560012242023680x7fe83cb0b6800x7fe83c225f40333240333240655367471104119029313341685617833372438303178333723993501783337280543017833372827754
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038623650323650341943042560012242058880x7fe83f16b5000x7fe83c225f80331906331906655367340032115650612943913617833372840983178333728054301783337321647017833373237694
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038923650323650341943042560012242094080x7fe83f16b3800x7fe83c225fc0306784306784655367340032112289512575816817833373253713178333732164701783337360207017833373604035
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039223650323650341943042560012242144640x7fe83f16b2000x7fe83c2260005428705428706553610420224157279517619111217833373638674178333736020701783337412911117833374151011
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039523650323650341943042560012242177280x7fe83f16b0800x7fe83c226040273524273524655366488064100158011219902017833374174310178333741291111783337450175117833374503742
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039823650323650341943042560012242220160x7fe83cb0bf000x7fe83c226080367402367402655368519680135327415150645217833374538861178333745017511783337492863117833374946841
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040123650323650341943042560012242260480x7fe83cb0bd800x7fe83c2260c0365216365216655368388608130452614609737217833374965361178333749286311783337535327217833375371071
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040423650323650341943042560012242300800x7fe83cb0bc000x7fe83c226100347450347450655368388608130108014574716817833375389370178333753532721783337575983217833375776981
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040723650323650341943042560012242359040x7fe83cb0ba800x7fe83c2261406238836238836553611993088182146020401222417833375795600178333757598321783337634239317833376359956
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041023650323650341943042560012242394240x7fe83cb0b9000x7fe83c226180301927301927655367274496112939112652025217833376386155178333763423931783337672687317833376728867
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041323650323650341943042560012242442240x7fe83cb0b7800x7fe83c2261c0397112397112655369568256151990917023848017833376763316178333767268731783337717279317833377191405
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041623650323650341943042560012242487680x7fe83cb0b6000x7fe83c226200390579390579655369437184151614816985466817833377210205178333771727931783337761935417833377636884
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041923650323650341943042560012242533120x7fe83f16b4800x7fe83c226240388246388246655369437184146965116464691617833377656044178333776193541783337805471417833378073234
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004222365032365034194304256008242555520x7fe83f16b3000x7fe83c2262807190317190316553616056320230556825813648017833378093213178333780547141783337870975417833378756117
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042523650323650341943042560012242598400x7fe83f16b1800x7fe83c2262c0364708364708655368847360137064515351511217833378775936178333787097541783337915903517833379204805
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042823650323650341943042560012242656640x7fe83f16b0000x7fe83c2263004691734691736553611665408183264720529062417833379216425178333791590351783337968607517833379731762
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043123650323650341943042560012242712320x7fe83cb0be800x7fe83c2263404721474721476553611468800183644620566376417833379742592178333796860751783338020687617833380252019
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004342365032365034194304256008242732160x7fe83cb0bd000x7fe83c2263804833194833196553614090240202074522628631617833380262739178333802068761783338073039617833380775826
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004372365032365034194304256008242757120x7fe83cb0bb800x7fe83c2263c08806938806936553619202048275648930885866817833380786746178333807303961783338150911717833381554727
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044023650323650341943042560012242807680x7fe83cb0ba000x7fe83c2264004268234268236553610420224160965918034837617833381573027178333815091171783338199551717833382013656
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044323650323650341943042560012242876160x7fe83cb0b8800x7fe83c2264405501515501516553613762560221066424772685217833382032035178333819955171783338255199717833382597981
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044623650323650341943042560012242942080x7fe83cb0b7000x7fe83c2264805515175515176553613565952214071623972876417833382609251178333825519971783338312735817833383172737
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004492365032365034194304256008242969600x7fe83f16b5800x7fe83c2264c05647775647776553615466496222845624959301617833383183477178333831273581783338369951817833383744933
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004522365032365034194304256008242999680x7fe83f16b4000x7fe83c226500104435910443596553622347776321129935970752017833383755813178333836995181783338458335917833384626841
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004552365032365034194304256008243027200x7fe83f16b2800x7fe83c2265407229457229456553620250624292381332745904817833384644931178333845833591783338525103917833385295565
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045823650323650341943042560012243054720x7fe83f16b1000x7fe83c2265807257697257696553620447232293564232872078417833385306544178333852510391783338594192017833385960188
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046123650323650341943042560012243082240x7fe83cb0bf800x7fe83c2265c07217557217556553619595264281835131561533217833385979718178333859419201783338660384017833386650201
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004642365032365034194304256008243109760x7fe83cb0be000x7fe83c2266007279497279496553620381696292814832790573217833386661111178333866037841783338728186417833387333494
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004672365032365034194304256008243132160x7fe83cb0bc800x7fe83c226640136630713663076553631522816450923850547307217833387344264178333872818641783338839162417833388436797
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004702365032365034194304256008243159680x7fe83cb0bb000x7fe83c226680137324713732476553638993920558396062567923217833388456356178333883916241783338948122517833389547849
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047323650323650341943042560012243187200x7fe83cb0b9800x7fe83c2266c0137392913739296553639124992561580562888348417833389559129178333894812251783339063178617833390703550
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047623650323650341943042560012243214720x7fe83cb0b8000x7fe83c226700137285113728516553638469632550960161705723617833390715150178333906317861783339177898617833391848222
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004792365032365034194304256008243242240x7fe83cb0b6800x7fe83c226740137513213751326553639059456559684562684090017833391858982178333917789861783339289930717833392966684
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004822365032365034194304256008243264640x7fe83f16b5000x7fe83c226780266438626643866553660489728865252196916385217833392977874178333928993071783339486682817833394944075
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004852365032365034194304256008243292160x7fe83f16b3800x7fe83c2267c026695342669534655367726694411073873124055342017833394963545178333948668281783339680827017833396876617
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048823650323650341943042560012243319680x7fe83f16b2000x7fe83c22680026721702672170655367739801611071825124007274817833396887957178333968082701783339879579117833398869628
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049123650323650341943042560012243347200x7fe83f16b0800x7fe83c22684026685922668592655367621836810904144122157683617833398880977178333987957911783340078171217833400848588
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004942365032365034194304256008243374720x7fe83cb0bf000x7fe83c22688026727542672754655367733248011067421123928124017833400859718178334007817121783340271627417833402787070
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049723650323650341943042560082400x7fe83cb0bd800x7fe83c2268c0525577652557766553612025856017187452192570198817833402798580178334027162741783340634043617833406412550