Files
rocm-systems/tests/workloads_old/dispatches/mi200/SQ_IFETCH_LEVEL.csv
T
Jose Santos 989e29cf81 Moving workloads to old
Signed-off-by: Jose Santos <josantos@login1.hpcfund>
2024-02-23 10:00:23 -06:00

44 KiB

1Dispatch_IDKernel_NameGPU_IDqueue-idqueue-indexpidtidgrdWorkgroup_SizeLDS_Per_WorkgroupscrvgprSGPRfbarsigobjGRBM_COUNTGRBM_GUI_ACTIVESQ_WAVESSQ_IFETCHSQ_IFETCH_LEVELSQ_ACCUM_PREV_HIRESDispatchNsStart_TimestampEnd_TimestampCompleteNs
20__amd_rocclr_fillBufferAligned.kd000194110194110335544322560043241600x00x7fa3acc0428038367738367752428847185926816457634844417124839786112171241287384951712498733257817124987421057
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00219411019411032768256001224138880x00x7fa3acc23f8033756337565128192722981006417124992545544171249873325781712499267865317124992683360
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051941101941104194304256001224143360x7fa3afc743800x7fa3acc23fc0163849163849655369175041420641592518417124992722299171249926786531712499305529217124993058100
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081941101941104194304256001624150400x7fa3afc742000x7fa3acc240003101673101676553611141121683961880849217124993098329171249930552921712499346889217124993471488
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111941101941104194304256001624154880x7fa3afc740800x7fa3acc24040310879310879655369175041397271560196817124993507907171249934688921712499387945217124993881827
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141941101941104194304256001224159360x7fa3ad617f000x7fa3acc240801653711653716553610485761592081775319617124993916786171249938794521712499419913117124994201998
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171941101941104194304256001224163840x7fa3ad617d800x7fa3acc240c0164555164555655369830401486901666906017124994236427171249941991311712499452185117124994524339
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201941101941104194304256001224170880x7fa3ad617c000x7fa3acc241001634971634976553611141121631281822879217124994571468171249945218511712499483945117124994841730
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231941101941104194304256001624177920x7fa3ad617a800x7fa3acc241403103493103496553613107202106882355687217124994877989171249948394511712499524537117124995247699
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261941101941104194304256001624184960x7fa3ad6179000x7fa3acc241803100293100296553611796481779441988495217124995282478171249952453711712499566201017124995664427
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291941101941104194304256001624192000x7fa3ad6177800x7fa3acc241c01645731645736553612451841891752123576417124995698696171249956620101712499597529017124995977749
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321941101941104194304256001624199040x7fa3ad6176000x7fa3acc242001644581644586553612451841861672080992817124996012858171249959752901712499629033017124996292730
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351941101941104194304256001224206080x7fa3afc744800x7fa3acc242401640531640536553612451841881652112023217124996335359171249962903301712499660425017124996606791
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381941101941104194304256001624213120x7fa3afc743000x7fa3acc242803115323115326553614417922151172407942017124996641770171249966042501712499700712917124997009430
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411941101941104194304256001624220160x7fa3afc741800x7fa3acc242c03099753099756553613107202002362237408417124997043879171249970071291712499741016917124997412579
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441941101941104194304256001624227200x7fa3afc740000x7fa3acc243001644121644126553613762562073792319983617124997447118171249974101691712499773208917124997734290
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471941101941104194304256001224234240x7fa3ad617e800x7fa3acc243401633511633516553614417922158752417350817124997770429171249977320891712499804392917124998046371
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501941101941104194304256001224241280x7fa3ad617d000x7fa3acc243801625221625226553613107201960282194234417124998110789171249980439291712499840152817124998404431
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531941101941104194304256001624248320x7fa3ad617b800x7fa3acc243c03088043088046553615728642348162629169617124998438620171249984015281712499880744817124998809240
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561941101941104194304256001624255360x7fa3ad617a000x7fa3acc244003071603071606553614417922087172339553217124998845229171249988074481712499917944817124999181240
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591941101941104194304256001224262400x7fa3ad6178800x7fa3acc244401639901639906553615073282265812533383217124999215719171249991794481712499946376817124999465552
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621941101941104194304256001224269440x7fa3ad6177000x7fa3acc244801638361638366553616384002440372732729217124999500631171249994637681712499975128717124999752984
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651941101941104194304256001224276480x7fa3afc745800x7fa3acc244c01633081633086553614417922167142428190817124999795453171249997512871712500003816717125000039746
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681941101941104194304256001624286080x7fa3afc744000x7fa3acc245003075203075206553617039362517392823398417125000076095171250000381671712500040936717125000411286
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711941101941104194304256001624293120x7fa3afc742800x7fa3acc245403045083045086553615728642337092618697217125000446305171250004093671712500078248717125000784205
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741941101941104194304256001224300160x7fa3afc741000x7fa3acc245801628901628906553616384002441542727139217125000819284171250007824871712500107192617125001073787
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077194110194110419430425600824309760x7fa3ad617f800x7fa3acc245c01623311623316553618350082749223072746417125001109856171250010719261712500135672617125001358479
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801941101941104194304256001224316800x7fa3ad617e000x7fa3acc246001624401624406553615073282238192507314817125001400348171250013567261712500164440617125001646181
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831941101941104194304256001624326400x7fa3ad617c800x7fa3acc246403078453078456553618350082707703027594017125001682570171250016444061712500201880617125002020421
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861941101941104194304256001224336000x7fa3ad617b000x7fa3acc246803070643070646553617039362505312805415617125002055540171250020188061712500239816517125002399900
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891941101941104194304256001224345600x7fa3ad6179800x7fa3acc246c01632351632356553617694722658692976299217125002434950171250023981651712500269352517125002695402
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092194110194110419430425600824355200x7fa3ad6178000x7fa3acc247001635441635446553620316163053963422142417125002732001171250026935251712500298216517125002983894
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951941101941104194304256001224362240x7fa3ad6176800x7fa3acc247401635121635126553616384002467962766171617125003025993171250029821651712500327016517125003271956
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981941101941104194304256001224371840x7fa3afc745000x7fa3acc247803055733055736553619660802885333234034417125003308285171250032701651712500365160417125003653436
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011941101941104194304256001224381440x7fa3afc743800x7fa3acc247c03070723070726553618350082730963061184017125003689235171250036516041712500402728417125004029075
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041941101941104194304256001224391040x7fa3afc742000x7fa3acc248001637951637956553619005442808353150210817125004065334171250040272841712500431544417125004317057
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107194110194110419430425600824403200x7fa3afc740800x7fa3acc248401630861630866553622282243289853689184817125004352666171250043154441712500460152417125004603409
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101941101941104194304256001224412800x7fa3ad617f000x7fa3acc248801635671635676553617039362566202872511217125004646158171250046015241712500489432417125004896041
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131941101941104194304256001224422400x7fa3ad617d800x7fa3acc248c03063263063266553620971523112263481384817125004933430171250048943241712500527304317125005274660
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161941101941104194304256001224432000x7fa3ad617c000x7fa3acc249003061633061636553619660802840513179526017125005310059171250052730431712500564744317125005649150
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119194110194110419430425600824441600x7fa3ad617a800x7fa3acc249401622861622866553620316163010713371525217125005683859171250056474431712500593112317125005933022
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221941101941104194304256001224453760x7fa3ad6179000x7fa3acc249801623191623196553624248323622004059364817125005967791171250059311231712500623000317125006231894
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251941101941104194304256001224463360x7fa3ad6177800x7fa3acc249c01617081617086553618350082717633056238017125006274013171250062300031712500652616217125006528066
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281941101941104194304256001224475520x7fa3ad6176000x7fa3acc24a003026253026256553622282243277303663290817125006564125171250065261621712500690008217125006901775
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311941101941104194304256001224485120x7fa3afc744800x7fa3acc24a403021063021066553620971523221593609786817125006937424171250069000821712500727480217125007276485
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134194110194110419430425600824494720x7fa3afc743000x7fa3acc24a801608751608756553621626883305943699272017125007312714171250072748021712500756088217125007562637
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371941101941104194304256001224506880x7fa3afc741800x7fa3acc24ac01619181619186553626214403861494324744417125007598156171250075608821712500784984117125007851619
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401941101941104194304256001224516480x7fa3afc740000x7fa3acc24b001615001615006553619660803124963495662417125007893967171250078498411712500813944117125008141241
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431941101941104194304256001224528640x7fa3ad617e800x7fa3acc24b403025403025406553623592963525433940226017125008176290171250081394411712500851272117125008514500
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461941101941104194304256001224540800x7fa3ad617d000x7fa3acc24b803013553013556553622282243290043682260417125008549369171250085127211712500888840117125008890120
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149194110194110419430425600824552960x7fa3ad617b800x7fa3acc24bc01630531630536553622937603417683823796817125008924159171250088884011712500917944017125009181332
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521941101941104194304256001224567680x7fa3ad617a000x7fa3acc24c001633151633156553627525124079814566163217125009216811171250091794401712500946776017125009469554
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551941101941104194304256001224577280x7fa3ad6178800x7fa3acc24c401625891625896553620316162996783355379217125009511132171250094677601712500976200017125009763755
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581941101941104194304256001224589440x7fa3ad6177000x7fa3acc24c803042683042686553624903683658604100888017125009798824171250097620001712501013688017125010138705
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611941101941104194304256001224601600x7fa3afc745800x7fa3acc24cc03019323019326553623592963522343948780817125010175194171250101368801712501051431917125010516204
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164194110194110419430425600824613760x7fa3afc744000x7fa3acc24d001633051633056553624248323638634074089617125010551513171250105143191712501080839917125010810246
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671941101941104194304256001224628480x7fa3afc742800x7fa3acc24d401681781681786553629491204402104933066017125010845385171250108083991712501110039917125011102228
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701941101941104194304256001224638080x7fa3afc741000x7fa3acc24d801630851630856553621626883225823614770817125011145027171250111003991712501139639917125011398270
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731941101941104194304256001224650240x7fa3ad617f800x7fa3acc24dc02995882995886553626214403900644366092817125011435029171250113963991712501176855817125011770250
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761941101941104194304256001224662400x7fa3ad617e000x7fa3acc24e003005493005496553624903683639434079018817125011806939171250117685581712501213991817125012141719
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179194110194110419430425600824674560x7fa3ad617c800x7fa3acc24e401627121627126553625559043828854283956817125012176608171250121399181712501242791817125012429791
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821941101941104194304256001224689280x7fa3ad617b000x7fa3acc24e801768781768786553631457284713425280491617125012465560171250124279181712501272839817125012730193
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851941101941104194304256001224701440x7fa3ad6179800x7fa3acc24ec01603351603356553622282243320163715108417125012772122171250127283981712501302039717125013022155
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881941101941104194304256001224716160x7fa3ad6178000x7fa3acc24f003030563030566553627525124068804556838417125013060194171250130203971712501339751717125013399204
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911941101941104194304256001224728320x7fa3ad6176800x7fa3acc24f403032693032696553626214403879884341232817125013434153171250133975171712501377591717125013777594
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194194110194110419430425600824740480x7fa3afc745000x7fa3acc24f801615501615506553626869763977184461046817125013812473171250137759171712501406679717125014068656
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971941101941104194304256001224757760x7fa3afc743800x7fa3acc24fc01814001814006553633423365009695612772017125014104115171250140667971712501437271617125014374487
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001941101941104194304256001224769920x7fa3afc742000x7fa3acc250001620691620696553623592963922204389810417125014427786171250143727161712501466007617125014661779
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031941101941104194304256001224784640x7fa3afc740800x7fa3acc250403008753008756553628835844254044768685617125014697248171250146600761712501503735617125015039119
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061941101941104194304256001224799360x7fa3ad617f000x7fa3acc250803026343026346553626869763961714436616417125015074698171250150373561712501541063617125015412318
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209194110194110419430425600824814080x7fa3ad617d800x7fa3acc250c01638811638816553628180484238624760359217125015447107171250154106361712501570631617125015708050
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121941101941104194304256001224831360x7fa3ad617c000x7fa3acc251001919441919446553635389445255145885326817125015743409171250157063161712501602039517125016022231
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151941101941104194304256001224843520x7fa3ad617a800x7fa3acc251401623821623826553624248323571383999262417125016064500171250160203951712501631399517125016315773
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181941101941104194304256001224858240x7fa3ad6179000x7fa3acc251803023133023136553630146564597965154840817125016350762171250163139951712501669143517125016693213
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211941101941104194304256001224872960x7fa3ad6177800x7fa3acc251c02987282987286553628180484173644668572417125016728562171250166914351712501706119417125017062923
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241941101941104194304256001224887680x7fa3ad6176000x7fa3acc252001637071637076553629491204419194951057617125017097712171250170611941712501734647417125017348445
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271941101941104194304256001224907520x7fa3afc744800x7fa3acc252402014322014326553637355525675026354732417125017383284171250173464741712501765927417125017660966
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301941101941104194304256001224919680x7fa3afc743000x7fa3acc252801612701612706553625559043932034403094817125017702825171250176592741712501794999417125017951628
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331941101941104194304256001224934400x7fa3afc741800x7fa3acc252c03030833030836553631457284651665202686817125017986877171250179499941712501833383417125018335797
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361941101941104194304256001224949120x7fa3afc740000x7fa3acc253002985852985856553629491204320454843969617125018371616171250183338341712501870951317125018711237
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391941101941104194304256001224963840x7fa3ad617e800x7fa3acc253401621871621876553630801924582375132660017125018746056171250187095131712501899655317125018998429
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421941101941104194304256001224983680x7fa3ad617d000x7fa3acc253802113162113166553639321605834006540943217125019032948171250189965531712501932199317125019323790
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451941101941104194304256001224995840x7fa3ad617b800x7fa3acc253c01622171622176553626214403890614358482417125019365879171250193219931712501960903317125019610962
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024819411019411041943042560012241013120x7fa3ad617a000x7fa3acc254003012333012336553632768004903345487934817125019645611171250196090331712501998279217125019984621
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025119411019411041943042560012241027840x7fa3ad6178800x7fa3acc254402987592987596553630801924635675195714017125020019720171250199827921712502035671217125020358501
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025419411019411041943042560012241042560x7fa3ad6177000x7fa3acc254801614451614456553632112644813225391712017125020393080171250203567121712502064439217125020646053
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025719411019411041943042560012241062400x7fa3afc745800x7fa3acc254c02196652196656553641287686342507106667217125020681452171250206443921712502097911217125020980884
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026019411019411041943042560012241077120x7fa3afc744000x7fa3acc255001607131607136553627525124138574637073217125021023193171250209791121712502127063117125021272576
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026319411019411041943042560016241094400x7fa3afc742800x7fa3acc255402986992986996553634078725041245649424017125021307475171250212706311712502164407117125021645965
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026619411019411041943042560016241111680x7fa3afc741000x7fa3acc255802977452977456553632112644709075281589617125021680694171250216440711712502202151117125022023165
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691941101941104194304256008241128960x7fa3ad617f800x7fa3acc255c01620451620456553632768004934995525662017125022059174171250220215111712502233655117125022338606
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027219411019411041943042560012241151360x7fa3ad617e000x7fa3acc256002304292304296553643253766442467222021617125022374015171250223365511712502266615017125022667907
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027519411019411041943042560012241166080x7fa3ad617c800x7fa3acc256401622731622736553628180484247834768456417125022710296171250226661501712502295895017125022960759
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027819411019411041943042560016241183360x7fa3ad617b000x7fa3acc256802969082969086553635389445274765909444417125022998148171250229589501712502333047017125023332258
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028119411019411041943042560016241200640x7fa3ad6179800x7fa3acc256c02979172979176553634078725050675654922817125023367847171250233304701712502370295017125023704598
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028419411019411041943042560012241217920x7fa3ad6178000x7fa3acc257001651291651296553634078725172515789167617125023739357171250237029501712502399878917125024000500
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028719411019411041943042560012241240320x7fa3ad6176800x7fa3acc257402399752399756553645219846739597548588417125024035769171250239987891712502433558917125024337510
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029019411019411041943042560012241255040x7fa3afc745000x7fa3acc257801606681606686553630146564540815090558817125024379629171250243355891712502462918917125024631112
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029319411019411041943042560012241274880x7fa3afc743800x7fa3acc257c02967012967016553638010885707946397261617125024665531171250246291891712502500630917125025008142
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029619411019411041943042560012241292160x7fa3afc742000x7fa3acc258002997762997766553636700165542056205948817125025043371171250250063091712502537878817125025380561
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029919411019411041943042560012241309440x7fa3afc740800x7fa3acc258401696251696256553636700165524186179750817125025415850171250253787881712502567062817125025672383
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030219411019411041943042560012241334400x7fa3ad617f000x7fa3acc258802589502589506553649152007331048209800817125025707942171250256706281712502601846817125026020273
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030519411019411041943042560012241349120x7fa3ad617d800x7fa3acc258c01611071611076553631457284688045248536017125026062052171250260184681712502631798817125026320065
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030819411019411041943042560012241368960x7fa3ad617c000x7fa3acc259002959822959826553640632326297647053410017125026355114171250263179881712502669366717125026695315
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031119411019411041943042560012241388800x7fa3ad617a800x7fa3acc259402977332977336553639321605896876593347217125026730464171250266936671712502706630717125027068054
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031419411019411041943042560012241408640x7fa3ad6179000x7fa3acc259801780261780266553639321605850546556616017125027102033171250270663071712502736790717125027369786
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031719411019411041943042560012241436160x7fa3ad6177800x7fa3acc259c02793952793956553653084168005888966691617125027404835171250273679071712502772950717125027731236
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032019411019411041943042560012241453440x7fa3ad6176000x7fa3acc25a001618081618086553633423364981495583341617125027774105171250277295071712502802086617125028022658
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032319411019411041943042560012241475840x7fa3afc744800x7fa3acc25a402955332955336553643253766517907292093617125028057277171250280208661712502839494617125028396827
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032619411019411041943042560012241495680x7fa3afc743000x7fa3acc25a802960832960836553641943046273707031050417125028432726171250283949461712502876982617125028771497
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032919411019411041943042560012241515520x7fa3afc741800x7fa3acc25ac01872201872206553641943046288697051596417125028807446171250287698261712502907606617125029077908
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033219411019411041943042560012241543040x7fa3afc740000x7fa3acc25b002993732993736553657016328652169683716817125029113257171250290760661712502945126517125029453018
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033519411019411041943042560012241562880x7fa3ad617e800x7fa3acc25b401719441719446553637355525783436490680017125029495777171250294512651712502975910517125029761019
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033819411019411041943042560012241587840x7fa3ad617d000x7fa3acc25b802975852975856553648496647609248526152817125029795508171250297591051712503013862517125030140639
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034119411019411041943042560012241610240x7fa3ad617b800x7fa3acc25bc02965522965526553647185927639988560064017125030176088171250301386251712503052390517125030525588
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034419411019411041943042560012241632640x7fa3ad617a000x7fa3acc25c002070042070046553647185927124857983181217125030559957171250305239051712503084054417125030842289
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034719411019411041943042560012241665280x7fa3ad6178800x7fa3acc25c4033921033921065536648806497144110894336017125030877438171250308405441712503123878417125031262247
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035019411019411041943042560012241685120x7fa3ad6177000x7fa3acc25c801850151850156553641287686211686958734817125031282307171250312387841712503154950417125031551359
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035319411019411041943042560012241712640x7fa3afc745800x7fa3acc25cc02965482965486553653739528501279531329217125031585528171250315495041712503192566317125031927439
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035619411019411041943042560012241737600x7fa3afc744000x7fa3acc25d002991412991416553652428808358809363149217125031962858171250319256631712503230486317125032306518
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035919411019411041943042560012241762560x7fa3afc742800x7fa3acc25d402249742249746553652428807934278890548017125032341277171250323048631712503263510317125032636999
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036219411019411041943042560012241797760x7fa3afc741000x7fa3acc25d80380706380706655367274496109933012321264817125032671888171250326351031712503306390317125033084657
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036519411019411041943042560012241822720x7fa3ad617f800x7fa3acc25dc02109942109946553649152007351208233272417125033108436171250330639031712503339462217125033396558
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036819411019411041943042560012241855360x7fa3ad617e000x7fa3acc25e00305333305333655366422528100036411198759617125033431807171250333946221712503378054217125033798447
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037119411019411041943042560012241885440x7fa3ad617c800x7fa3acc25e4030699830699865536629145699719911177929617125033818116171250337805421712503416710217125034191776
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037419411019411041943042560012241915520x7fa3ad617b000x7fa3acc25e8026562126562165536629145696890610853267217125034203836171250341671021712503453206217125034533706
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037719411019411041943042560012241958400x7fa3ad6179800x7fa3acc25ec0462427462427655368847360134018715024299217125034568695171250345320621712503500774117125035050682
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038019411019411041943042560012241985920x7fa3ad6178000x7fa3acc25f002445022445026553657016328495299515396017125035070462171250350077411712503537638117125035378143
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038319411019411041943042560012242023680x7fa3ad6176800x7fa3acc25f40334458334458655367471104120807913526248017125035414682171250353763811712503577654117125035797641
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038619411019411041943042560012242058880x7fa3afc745000x7fa3acc25f80332743332743655367340032116422913040498817125035813721171250357765411712503618710017125036204750
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038919411019411041943042560012242094080x7fa3afc743800x7fa3acc25fc0306308306308655367340032113790712751166817125036223290171250361871001712503656902017125036570900
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039219411019411041943042560012242144640x7fa3afc742000x7fa3acc260005431085431086553610420224157259217619113617125036606339171250365690201712503709702017125037116015
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039519411019411041943042560012242177280x7fa3afc740800x7fa3acc2604027380827380865536648806497698610939534017125037141624171250370970201712503746613917125037467945
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039819411019411041943042560012242220160x7fa3ad617f000x7fa3acc26080366967366967655368519680136093615242154017125037503694171250374661391712503788933917125037907523
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040119411019411041943042560012242260480x7fa3ad617d800x7fa3acc260c0365858365858655368388608132318314817733217125037927142171250378893391712503831365917125038332161
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040419411019411041943042560012242300800x7fa3ad617c000x7fa3acc26100347437347437655368388608128513314388174017125038351461171250383136591712503872453817125038743210
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040719411019411041943042560012242359040x7fa3ad617a800x7fa3acc261406238026238026553611993088181668520342093217125038761729171250387245381712503930837817125039326064
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041019411019411041943042560012242394240x7fa3ad6179000x7fa3acc26180302679302679655367274496111807712517712017125039352493171250393083781712503969381817125039695583
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041319411019411041943042560012242442240x7fa3ad6177800x7fa3acc261c0397529397529655369568256152414017082347617125039730282171250396938181712504014021717125040157980
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041619411019411041943042560012242487680x7fa3ad6176000x7fa3acc26200390811390811655369437184147854416551408017125040177640171250401402171712504058069717125040598598
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041919411019411041943042560012242533120x7fa3afc744800x7fa3acc26240387357387357655369437184148940316696960417125040618848171250405806971712504101349717125041031216
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221941101941104194304256008242555520x7fa3afc743000x7fa3acc262807185957185956553616056320230241025791667617125041051055171250410134971712504166117617125041678488
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042519411019411041943042560012242598400x7fa3afc741800x7fa3acc262c0364355364355655368847360135659215195021217125041706337171250416611761712504208421617125042104156
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042819411019411041943042560012242656640x7fa3afc740000x7fa3acc263004688894688896553611665408184434420665086417125042121736171250420842161712504258277617125042601462
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043119411019411041943042560012242712320x7fa3ad617e800x7fa3acc263404711734711736553611468800181431020327075217125042620122171250425827761712504307589517125043093529
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341941101941104194304256008242732160x7fa3ad617d000x7fa3acc263804830954830956553614090240201933222612336417125043112338171250430758951712504357189517125043590595
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371941101941104194304256008242757120x7fa3ad617b800x7fa3acc263c08808048808046553619202048276096730910912017125043609424171250435718951712504432165417125044338594
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044019411019411041943042560012242807680x7fa3ad617a000x7fa3acc264004254714254716553610420224159310717844804417125044365953171250443216541712504478565417125044802521
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044319411019411041943042560012242876160x7fa3ad6178800x7fa3acc264405492145492146553613762560216009424183687617125044822480171250447856541712504533125417125045348766
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044619411019411041943042560012242942080x7fa3ad6177000x7fa3acc264805501725501726553613565952214465024020475617125045368715171250453312541712504587397317125045891351
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491941101941104194304256008242969600x7fa3afc745800x7fa3acc264c05637225637226553615466496223088324981038417125045911200171250458739731712504641717317125046435866
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521941101941104194304256008242999680x7fa3afc744000x7fa3acc26500104501210450126553622347776322168336082123217125046454975171250464171731712504728437217125047308081
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551941101941104194304256008243027200x7fa3afc742800x7fa3acc265407226107226106553620250624290817832561027217125047328391171250472843721712504793045217125047947293
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045819411019411041943042560012243054720x7fa3afc741000x7fa3acc265807238187238186553620447232293858332909030417125047967193171250479304521712504858933117125048606725
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046119411019411041943042560012243082240x7fa3ad617f800x7fa3acc265c07216257216256553619595264281895631574286017125048627114171250485893311712504924309117125049260897
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641941101941104194304256008243109760x7fa3ad617e000x7fa3acc266007271227271226553620381696292673132790634017125049280286171250492430911712504989589017125049913579
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671941101941104194304256008243132160x7fa3ad617c800x7fa3acc26640136648213664826553631522816451689550577526417125049933608171250498960871712505096696517125050986849
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701941101941104194304256008243159680x7fa3ad617b000x7fa3acc26680137351413735146553638993920559037362643799217125051012128171250509669651712505202632517125052045170
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047319411019411041943042560012243187200x7fa3ad6179800x7fa3acc266c0137244813724486553639124992561379562856985217125052062499171250520263251712505311496417125053153549
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047619411019411041943042560012243214720x7fa3ad6178000x7fa3acc26700137186313718636553638469632551226361727668017125053164989171250531149641712505421208417125054276468
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791941101941104194304256008243242240x7fa3ad6176800x7fa3acc26740137661613766166553639059456560355562738512817125054288518171250542120841712505531960417125055384407
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821941101941104194304256008243264640x7fa3afc745000x7fa3acc26780266446826644686553660489728865402396898333617125055395407171250553196041712505726600317125057331773
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851941101941104194304256008243292160x7fa3afc743800x7fa3acc267c026687682668768655367726694411057079123830717617125057351662171250572660031712505919240217125059262919
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048819411019411041943042560012243319680x7fa3afc742000x7fa3acc2680026719602671960655367739801611072496124015620817125059275909171250591924021712506118552117125061253854
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049119411019411041943042560012243347200x7fa3afc740800x7fa3acc2684026698002669800655367621836810903808122138714817125061265373171250611855211712506316440117125063234388
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941941101941104194304256008243374720x7fa3ad617f000x7fa3acc2688026744662674466655367733248011067459123938855217125063247628171250631644011712506510568017125065177274
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049719411019411041943042560082400x7fa3ad617d800x7fa3acc268c0525652852565286553612025856017190479192581149617125065188994171250651056801712506873079917125068804774