Files
rocm-systems/tests/workloads/dev0/mi200/SQ_INST_LEVEL_SMEM.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

41 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_SMEMSQ_INST_LEVEL_SMEMSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000223075223075335544322560043241600x00x7f931ec042803670016292422432728124817597154367976175887194303191759730673881117597306856651
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00222307522307532768256001224138880x00x7f931ec23f80512969901086503217597311964571175973067388111759731209785417597312102767
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0052230752230754194304256001224143360x7f9321c133800x7f931ec23fc0655366355427113872017597312138116175973120978541759731246857417597312471268
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0082230752230754194304256001624150400x7f9321c132000x7f931ec24000655366689547484487217597312508957175973124685741759731288073417597312883107
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00112230752230754194304256001624154880x7f9321c130800x7f931ec24040655366650307455221617597312916436175973128807341759731328057417597313282907
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00142230752230754194304256001224159360x7f931f46df000x7f931ec24080655366642667426469617597313316306175973132805741759731358745517597313589829
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00172230752230754194304256001224163840x7f931f46dd800x7f931ec240c0655366626887418479217597313622909175973135874551759731389881517597313901412
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00202230752230754194304256001224170880x7f931f46dc000x7f931ec241001310726741747545784017597313946930175973138988151759731421321517597314215744
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00232230752230754194304256001624177920x7f931f46da800x7f931ec241401310727260988130612817597314248903175973142132151759731461865517597314621123
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00262230752230754194304256001624184960x7f931f46d9000x7f931ec24180655366790347616525617597314652482175973146186551759731501497617597315017543
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00292230752230754194304256001624192000x7f931f46d7800x7f931ec241c01310727125547982349617597315047612175973150149761759731533657617597315338935
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00322230752230754194304256001624199040x7f931f46d6000x7f931ec242001310727033467869644817597315372044175973153365761759731564697617597315649507
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00352230752230754194304256001224206080x7f9321c134800x7f931ec242401310727042807875616017597315689836175973156469761759731595913617597315961459
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00382230752230754194304256001624213120x7f9321c133000x7f931ec242801310727141927998028017597315994668175973159591361759731635561617597316358149
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00412230752230754194304256001624220160x7f9321c131800x7f931ec242c0655366740667545830417597316390698175973163556161759731675081717597316753269
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00442230752230754194304256001624227200x7f9321c130000x7f931ec243001310727068667905755217597316786328175973167508171759731705737717597317059851
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00472230752230754194304256001224234240x7f931f46de800x7f931ec243401310727182488042047217597317091891175973170573771759731736265717597317365124
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00502230752230754194304256001224241280x7f931f46dd000x7f931ec243801310727032507885350417597317404783175973173626571759731766793717597317670476
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00532230752230754194304256001624248320x7f931f46db800x7f931ec243c01310727146367996080817597317703385175973176679371759731806057717597318062946
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00562230752230754194304256001624255360x7f931f46da000x7f931ec24400655366303267062692017597318105805175973180605771759731850617817597318508775
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00592230752230754194304256001224262400x7f931f46d8800x7f931ec244401310727157908005802417597318540724175973185061781759731881369817597318816247
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00622230752230754194304256001224269440x7f931f46d7000x7f931ec244801310726914547740227217597318850086175973188136981759731911817817597319120109
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00652230752230754194304256001224276480x7f9321c135800x7f931ec244c01310726691127489892817597319159448175973191181781759731939737817597319399412
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00682230752230754194304256001624286080x7f9321c134000x7f931ec245001310727087487926164017597319432951175973193973781759731976185817597319763613
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00712230752230754194304256001624293120x7f9321c132800x7f931ec24540655366882407708765617597319796522175973197618581759732013097917597320132803
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00742230752230754194304256001224300160x7f9321c131000x7f931ec245801310726781807597433617597320165302175973201309791759732040793917597320410176
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077223075223075419430425600824309760x7f931f46df800x7f931ec245c01310726603207400180017597320442495175973204079391759732068553917597320687419
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00802230752230754194304256001224316800x7f931f46de000x7f931ec246001310726947607782615217597320725998175973206855391759732097193917597320973862
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00832230752230754194304256001624326400x7f931f46dc800x7f931ec246401310726522227302460017597321006161175973209719391759732133977917597321341672
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00862230752230754194304256001224336000x7f931f46db000x7f931ec24680655366447607217524817597321373252175973213397791759732171210017597321713953
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00892230752230754194304256001224345600x7f931f46d9800x7f931ec246c01310726979507822406417597321744992175973217121001759732199658017597321998466
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092223075223075419430425600824355200x7f931f46d8000x7f931ec247001310727150628007953617597322030445175973219965801759732228554017597322287398
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00952230752230754194304256001224362240x7f931f46d6800x7f931ec247401310726978087819400017597322326607175973222855401759732256762017597322569481
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00982230752230754194304256001224371840x7f9321c135000x7f931ec247801310726827927645123217597322600290175973225676201759732293594017597322937742
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001012230752230754194304256001224381440x7f9321c133800x7f931ec247c0655366642227443662417597322970181175973229359401759732330490117597323306962
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001042230752230754194304256001224391040x7f9321c132000x7f931ec248001310727358728231356017597323338562175973233049011759732358442117597323586475
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107223075223075419430425600824403200x7f9321c130800x7f931ec248401310726978107812933617597323618265175973235844211759732386442117597323866248
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001102230752230754194304256001224412800x7f931f46df000x7f931ec248801310726948987783046417597323905857175973238644211759732414778117597324149601
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001132230752230754194304256001224422400x7f931f46dd800x7f931ec248c01310727025607871511217597324181220175973241477811759732451802117597324519812
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001162230752230754194304256001224432000x7f931f46dc000x7f931ec24900655366346447097799217597324551461175973245180211759732488986217597324891632
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119223075223075419430425600824441600x7f931f46da800x7f931ec249401310726971407813115217597324922462175973248898621759732516938217597325171185
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001222230752230754194304256001224453760x7f931f46d9000x7f931ec249801310726979807808474417597325203334175973251693821759732544954217597325451328
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001252230752230754194304256001224463360x7f931f46d7800x7f931ec249c01310726962267804996817597325489587175973254495421759732572858217597325730501
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001282230752230754194304256001224475520x7f931f46d6000x7f931ec24a001310727021087873735217597325762170175973257285821759732609130217597326093172
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001312230752230754194304256001224485120x7f9321c134800x7f931ec24a40655366664107465507217597326126661175973260913021759732646250317597326464312
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134223075223075419430425600824494720x7f9321c133000x7f931ec24a801310726735307543006417597326496362175973264625031759732674602317597326747925
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001372230752230754194304256001224506880x7f9321c131800x7f931ec24ac01310726670147467076017597326780364175973267460231759732702890317597327030658
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001402230752230754194304256001224516480x7f9321c130000x7f931ec24b001310726712527526488017597327069437175973270289031759732731914317597327320991
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001432230752230754194304256001224528640x7f931f46de800x7f931ec24b401310727122287979979217597327352480175973273191431759732768474317597327686711
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001462230752230754194304256001224540800x7f931f46dd000x7f931ec24b80655366587507367762417597327718170175973276847431759732804842417597328050372
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149223075223075419430425600824552960x7f931f46db800x7f931ec24bc01310726971007822347217597328081711175973280484241759732832714417597328329005
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001522230752230754194304256001224567680x7f931f46da000x7f931ec24c001310727106447968632017597328361274175973283271441759732861050417597328612358
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001552230752230754194304256001224577280x7f931f46d8800x7f931ec24c401310727104087958752017597328651187175973286105041759732888922417597328891190
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001582230752230754194304256001224589440x7f931f46d7000x7f931ec24c801310726720387522380817597328922200175973288892241759732925770417597329259461
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001612230752230754194304256001224601600x7f9321c135800x7f931ec24cc0655366627107430459217597329291530175973292577041759732962266517597329624542
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164223075223075419430425600824613760x7f9321c134000x7f931ec24d001310727060967908277617597329656121175973296226651759732990394517597329905965
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001672230752230754194304256001224628480x7f9321c132800x7f931ec24d401310727027307871276017597329937524175973299039451759733020138517597330203447
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001702230752230754194304256001224638080x7f9321c131000x7f931ec24d801310727166148025802417597330242846175973302013851759733048442517597330486270
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001732230752230754194304256001224650240x7f931f46df800x7f931ec24dc01310726569127359850417597330519099175973304844251759733084810517597330850041
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001762230752230754194304256001224662400x7f931f46de000x7f931ec24e00655366330707086988817597330882520175973308481051759733121210617597331213981
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179223075223075419430425600824674560x7f931f46dc800x7f931ec24e401310727058187902276017597331245461175973312121061759733149050617597331492484
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001822230752230754194304256001224689280x7f931f46db000x7f931ec24e801310727182888055437617597331523804175973314905061759733177834617597331780317
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001852230752230754194304256001224701440x7f931f46d9800x7f931ec24ec01310726618747413684817597331818476175973317783461759733205658617597332058540
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001882230752230754194304256001224716160x7f931f46d8000x7f931ec24f001310727030607857280017597332089789175973320565861759733242426617597332426101
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001912230752230754194304256001224728320x7f931f46d6800x7f931ec24f40655366622147434491217597332457410175973324242661759733279034617597332792111
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194223075223075419430425600824740480x7f9321c135000x7f931ec24f801310726678487481180017597332823461175973327903461759733307610717597333078104
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001972230752230754194304256001224757760x7f9321c133800x7f931ec24fc01310726702027505865617597333109323175973330761071759733336826717597333370227
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002002230752230754194304256001224769920x7f9321c132000x7f931ec250001310727080887924645617597333409146175973333682671759733365354717597333655430
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002032230752230754194304256001224784640x7f9321c130800x7f931ec250401310727044067891680817597333688409175973336535471759733401962717597334021430
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002062230752230754194304256001224799360x7f931f46df000x7f931ec25080655366765107578779217597334053709175973340196271759733440458717597334406740
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209223075223075419430425600824814080x7f931f46dd800x7f931ec250c01310727086767936168017597334438370175973344045871759733468842817597334690223
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002122230752230754194304256001224831360x7f931f46dc000x7f931ec251001310727031887875803217597334721262175973346884281759733498682817597334988716
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002152230752230754194304256001224843520x7f931f46da800x7f931ec251401310727113747975070417597335038064175973349868281759733526698817597335269488
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002182230752230754194304256001224858240x7f931f46d9000x7f931ec251801310727093567935042417597335302398175973352669881759733564122817597335643189
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002212230752230754194304256001224872960x7f931f46d7800x7f931ec251c0655366657507468274417597335674408175973356412281759733601242817597336014399
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002242230752230754194304256001224887680x7f931f46d6000x7f931ec252001310726925827759999217597336045289175973360124281759733629098917597336293122
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002272230752230754194304256001224907520x7f9321c134800x7f931ec252401310727022807856991217597336324782175973362909891759733659226917597336594275
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002302230752230754194304256001224919680x7f9321c133000x7f931ec252801310726938607779191217597336633174175973365922691759733687162917597336873568
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002332230752230754194304256001224934400x7f9321c131800x7f931ec252c01310727060807906434417597336905237175973368716291759733723962917597337241428
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002362230752230754194304256001224949120x7f9321c130000x7f931ec25300655366662587463020817597337273267175973372396291759733760330917597337605369
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002392230752230754194304256001224963840x7f931f46de800x7f931ec253401310727100707968248017597337636328175973376033091759733788267017597337884502
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002422230752230754194304256001224983680x7f931f46dd000x7f931ec253801310727021047864840817597337916431175973378826701759733819707017597338198944
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002452230752230754194304256001224995840x7f931f46db800x7f931ec253c01310727005387845481617597338239503175973381970701759733848987017597338491926
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024822307522307541943042560012241013120x7f931f46da000x7f931ec254001310726668567476167217597338524835175973384898701759733886091017597338862717
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025122307522307541943042560012241027840x7f931f46d8800x7f931ec25440655366590987378475217597338894486175973388609101759733922395017597339225938
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025422307522307541943042560012241042560x7f931f46d7000x7f931ec254801310726627327423668017597339257507175973392239501759733950251117597339504391
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025722307522307541943042560012241062400x7f9321c135800x7f931ec254c01310726678807468428017597339536040175973395025111759733981787117597339819773
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026022307522307541943042560012241077120x7f9321c134000x7f931ec255001310726610667407256017597339859702175973398178711759734010139117597340103275
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026322307522307541943042560016241094400x7f9321c132800x7f931ec255401310727102307948210417597340135205175973401013911759734046859117597340470596
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026622307522307541943042560016241111680x7f9321c131000x7f931ec25580655366616787417480817597340502315175973404685911759734083595117597340838057
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002692230752230754194304256008241128960x7f931f46df800x7f931ec255c01310727072127929387217597340870236175973408359511759734111787217597341119770
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027222307522307541943042560012241151360x7f931f46de000x7f931ec256001310726998747836979217597341151399175973411178721759734143915217597341441202
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027522307522307541943042560012241166080x7f931f46dc800x7f931ec256401310727250928109684017597341479951175973414391521759734171931217597341721264
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027822307522307541943042560016241183360x7f931f46db000x7f931ec256801310726986887827348017597341752264175973417193121759734208827217597342090355
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028122307522307541943042560016241200640x7f931f46d9800x7f931ec256c0655366565867360817617597342122474175973420882721759734245771217597342459566
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028422307522307541943042560012241217920x7f931f46d8000x7f931ec257001310726985167833824817597342490885175973424577121759734274027317597342742229
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028722307522307541943042560012241240320x7f931f46d6800x7f931ec257401310727003707847759217597342773698175973427402731759734306875317597343070740
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029022307522307541943042560012241255040x7f9321c135000x7f931ec257801310727309828186050417597343108739175973430687531759734334603317597343347943
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029322307522307541943042560012241274880x7f9321c133800x7f931ec257c01310727032987879771217597343380002175973433460331759734371259317597343714574
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029622307522307541943042560012241292160x7f9321c132000x7f931ec25800655366655947464943217597343746363175973437125931759734407771317597344079695
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029922307522307541943042560012241309440x7f9321c130800x7f931ec258401310726606587399039217597344110364175973440777131759734436331417597344365207
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030222307522307541943042560012241334400x7f931f46df000x7f931ec258801310726667147469707217597344396947175973443633141759734470891417597344710799
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030522307522307541943042560012241349120x7f931f46dd800x7f931ec258c0131072103838611625765617597344749948175973447089141759734500155417597345003581
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030822307522307541943042560012241368960x7f931f46dc000x7f931ec259001310726705347507611217597345033950175973450015541759734536811417597345370072
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031122307522307541943042560012241388800x7f931f46da800x7f931ec25940655366668947462108817597345400881175973453681141759734573579417597345737533
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031422307522307541943042560012241408640x7f931f46d9000x7f931ec259801310727181268044383217597345769252175973457357941759734602891517597346030965
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031722307522307541943042560012241436160x7f931f46d7800x7f931ec259c01310726978427825368017597346062644175973460289151759734639131517597346393496
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032022307522307541943042560012241453440x7f931f46d6000x7f931ec25a00131072103109011586113617597346433055175973463913151759734667579517597346677779
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032322307522307541943042560012241475840x7f9321c134800x7f931ec25a401310727056487905456017597346708888175973466757951759734704443517597347046459
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032622307522307541943042560012241495680x7f9321c133000x7f931ec25a80655366709547506408817597347078618175973470444351759734740971517597347411750
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032922307522307541943042560012241515520x7f9321c131800x7f931ec25ac01310726634967429422417597347443289175973474097151759734770747617597347709542
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033222307522307541943042560012241543040x7f9321c130000x7f931ec25b001310726684007479324017597347741332175973477074761759734808267617597348084693
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033522307522307541943042560012241562880x7f931f46de800x7f931ec25b40131072102663611489761617597348123932175973480826761759734837355617597348375415
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033822307522307541943042560012241587840x7f931f46dd000x7f931ec25b801310726984307818268017597348407765175973483735561759734874123617597348743166
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034122307522307541943042560012241610240x7f931f46db800x7f931ec25bc0655366834027651444817597348774895175973487412361759734911323717597349115207
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034422307522307541943042560012241632640x7f931f46da000x7f931ec25c001310726728087541340017597349146026175973491132371759734942043717597349422399
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034722307522307541943042560012241665280x7f931f46d8800x7f931ec25c401310726715307519513617597349454338175973494204371759734981275717597349833198
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035022307522307541943042560012241685120x7f931f46d7000x7f931ec25c80131072103297011545492017597349854798175973498127571759735011835717597350120291
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035322307522307541943042560012241712640x7f9321c135800x7f931ec25cc01310726763687572196817597350151800175973501183571759735049051717597350492541
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035622307522307541943042560012241737600x7f9321c134000x7f931ec25d00655366696107489778417597350524561175973504905171759735085851817597350860582
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035922307522307541943042560012241762560x7f9321c132800x7f931ec25d401310726687507490058417597350892281175973508585181759735118235817597351184154
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036222307522307541943042560012241797760x7f9321c131000x7f931ec25d801310726701767502382417597351216313175973511823581759735159851817597351620443
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036522307522307541943042560012241822720x7f931f46df800x7f931ec25dc0131072100115811199672017597351639712175973515985181759735192235817597351924465
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036822307522307541943042560012241855360x7f931f46de000x7f931ec25e001310726971527822134417597351955654175973519223581759735230091917597352304986
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037122307522307541943042560012241885440x7f931f46dc800x7f931ec25e40655366724527538240817597352334805175973523009191759735268203917597352703415
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037422307522307541943042560012241915520x7f931f46db000x7f931ec25e801310726721207527211217597352714855175973526820391759735303755917597353039557
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037722307522307541943042560012241958400x7f931f46d9800x7f931ec25ec01310726706807508257617597353070026175973530375591759735350731917597353526105
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038022307522307541943042560012241985920x7f931f46d8000x7f931ec25f00131072104034811665901617597353549374175973535073191759735385195917597353853856
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038322307522307541943042560012242023680x7f931f46d6800x7f931ec25f40131072100654211270083217597353885225175973538519591759735424572017597354269046
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038622307522307541943042560012242058880x7f9321c135000x7f931ec25f80655366711227525872817597354281075175973542457201759735466092017597354680075
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038922307522307541943042560012242094080x7f9321c133800x7f931ec25fc01310726536967330125617597354694815175973546609201759735504428017597355046316
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039222307522307541943042560012242144640x7f9321c132000x7f931ec260001310726665827469353617597355078635175973550442801759735556588117597355608712
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039522307522307541943042560012242177280x7f9321c130800x7f931ec26040131072104187411659750417597355629221175973555658811759735594636117597355948133
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039822307522307541943042560012242220160x7f931f46df000x7f931ec26080131072103223611577571217597355980002175973559463611759735636044117597356403071
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040122307522307541943042560012242260480x7f931f46dd800x7f931ec260c0655366652947449658417597356415051175973563604411759735680748117597356826960
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040422307522307541943042560012242300800x7f931f46dc000x7f931ec261001310726640307437997617597356840870175973568074811759735721324217597357230970
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040722307522307541943042560012242359040x7f931f46da800x7f931ec261401310726816107631744017597357247050175973572132421759735779196217597357810505
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041022307522307541943042560012242394240x7f931f46d9000x7f931ec26180131072104280611690442417597357833835175973577919621759735817532217597358177346
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041322307522307541943042560012242442240x7f931f46d7800x7f931ec261c0131072101195211355816817597358208925175973581753221759735862268217597358669334
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041622307522307541943042560012242487680x7f931f46d6000x7f931ec26200655366642867436874417597358681623175973586226821759735909564317597359137992
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041922307522307541943042560012242533120x7f9321c134800x7f931ec262401310726667567464840017597359149211175973590956431759735955164317597359594280
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004222230752230754194304256008242555520x7f9321c133000x7f931ec26280131072103806211646522417597359606080175973595516431759736022300317597360265703
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042522307522307541943042560012242598400x7f9321c131800x7f931ec262c0131072104525611701499217597360286333175973602230031759736066524417597360707782
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042822307522307541943042560012242656640x7f9321c130000x7f931ec26300131072100705811255800817597360719592175973606652441759736118252417597361224979
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043122307522307541943042560012242712320x7f931f46de800x7f931ec26340655366575327368093617597361237358175973611825241759736169916417597361717576
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004342230752230754194304256008242732160x7f931f46dd000x7f931ec26380131072100595411268456017597361732206175973616991641759736219084517597362239043
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004372230752230754194304256008242757120x7f931f46db800x7f931ec263c0131072104237411696131217597362251443175973621908451759736297244517597363015383
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044022307522307541943042560012242807680x7f931f46da000x7f931ec26400131072106452011920377617597363035773175973629724451759736346028517597363504371
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044322307522307541943042560012242876160x7f931f46d8800x7f931ec26440131072104296411671824017597363515870175973634602851759736402780617597364070626
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044622307522307541943042560012242942080x7f931f46d7000x7f931ec26480655366636187438165617597364083626175973640278061759736459276617597364635562
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004492230752230754194304256008242969600x7f9321c135800x7f931ec264c0131072100022011209896817597364647432175973645927661759736515788617597365200478
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004522230752230754194304256008242999680x7f9321c134000x7f931ec26500131072104390611697033617597365212197175973651578861759736603292717597366080735
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004552230752230754194304256008243027200x7f9321c132800x7f931ec26540131072103903011623457617597366103624175973660329271759736670828717597366753068
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045822307522307541943042560012243054720x7f9321c131000x7f931ec26580131072102933611520305617597366765068175973667082871759736739740817597367439831
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046122307522307541943042560012243082240x7f931f46df800x7f931ec265c0655366768507591493617597367452270175973673974081759736807932817597368123053
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004642230752230754194304256008243109760x7f931f46de000x7f931ec26600131072103090411537428017597368134303175973680793281759736874524917597368788626
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004672230752230754194304256008243132160x7f931f46dc800x7f931ec26640131072103031211531464017597368800216175973687450991759736984013917597369888059
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004702230752230754194304256008243159680x7f931f46db000x7f931ec26680131072103064811539986417597369908628175973698401391759737092461917597370974181
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047322307522307541943042560012243187200x7f931f46d9800x7f931ec266c0131072102875011507068017597370986871175973709246191759737205757917597372122792
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047622307522307541943042560012243214720x7f931f46d8000x7f931ec26700655366678587477264017597372135112175973720575791759737319278017597373258383
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004792230752230754194304256008243242240x7f931f46d6800x7f931ec26740131072104861211753872817597373270383175973731927801759737430734017597374377395
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004822230752230754194304256008243264640x7f9321c135000x7f931ec26780131072104263811710462417597374390544175973743073401759737627502117597376340695
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004852230752230754194304256008243292160x7f9321c133800x7f931ec267c0131072103095611549589617597376361114175973762750211759737820366117597378279105
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048822307522307541943042560012243319680x7f9321c132000x7f931ec26800131072103298211551958417597378292145175973782036611759738019950217597380268425
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049122307522307541943042560012243347200x7f9321c130800x7f931ec26840655366722407521241617597380281674175973801995021759738217422317597382243035
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004942230752230754194304256008243374720x7f931f46df000x7f931ec26880131072104126811648273617597382255654175973821742231759738412254317597384191705
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049722307522307541943042560082400x7f931f46dd800x7f931ec268c0131072104548011681884017597384204405175973841225431759738774270417597387818633