Files
rocm-systems/tests/workloads/Axes1/mi200/SQ_INST_LEVEL_VMEM.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

41 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_VMEMSQ_INST_LEVEL_VMEMSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000201826201826335544322560043241600x00x7f4602604280524288546489461200427617248909572510172466519886211724905620139517249056314154
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00220182620182632768256001224138880x00x7f4602623f80409640146449680417249061450266172490562013951724906158027117249061585092
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0052018262018264194304256001224143360x7f46056313800x7f4602623fc052428810522350117843778817249061620532172490615802711724906195147117249061954023
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0082018262018264194304256001624150400x7f46056312000x7f460262400052428811578892129680239217249061992232172490619514711724906237067117249062373351
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00112018262018264194304256001624154880x7f46056310800x7f460262404052428811405389127738554817249062407200172490623706711724906277899017249062781460
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00142018262018264194304256001224159360x7f4602ecdf000x7f460262408052428810771586120642297217249062814199172490627789901724906309323017249063095452
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00172018262018264194304256001224163840x7f4602ecdd800x7f46026240c052428811089437124196607617249063128461172490630932301724906340603017249063408703
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00202018262018264194304256001224170880x7f4602ecdc000x7f460262410052428811133938124702794417249063451652172490634060301724906371483017249063717215
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00232018262018264194304256001624177920x7f4602ecda800x7f460262414052428811642591130394696417249063750054172490637148301724906411451017249064116854
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00262018262018264194304256001624184960x7f4602ecd9000x7f460262418052428811447045128204956817249064148813172490641145101724906450955017249064512013
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00292018262018264194304256001624192000x7f4602ecd7800x7f46026241c052428811168649125087188417249064543053172490645095501724906483562917249064838055
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00322018262018264194304256001624199040x7f4602ecd6000x7f460262420052428810950607122650893617249064870714172490648356291724906514378917249065146276
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00352018262018264194304256001224206080x7f46056314800x7f460262424052428810792735120882268017249065185875172490651437891724906545930917249065461728
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00382018262018264194304256001624213120x7f46056313000x7f460262428052428811465287128413382017249065493057172490654593091724906585578917249065858167
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00412018262018264194304256001624220160x7f46056311800x7f46026242c052428811659215130579030017249065891436172490658557891724906625194917249066254886
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00442018262018264194304256001624227200x7f46056310000x7f460262430052428810964963122805318417249066286326172490662519491724906656922917249066570968
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00472018262018264194304256001224234240x7f4602ecde800x7f460262434052428811017684123396439617249066602867172490665692291724906685034817249066852110
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00502018262018264194304256001224241280x7f4602ecdd000x7f460262438052428811130003124651282417249066890149172490668503481724906713370817249067135723
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00532018262018264194304256001624248320x7f4602ecdb800x7f46026243c052428811495331128744606417249067167882172490671337081724906750234817249067504053
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00562018262018264194304256001624255360x7f4602ecda000x7f460262440052428811451355128252054817249067535012172490675023481724906787594817249067877823
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00592018262018264194304256001224262400x7f4602ecd8800x7f460262444052428810933782122460522817249067908822172490678759481724906815674817249068158535
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00622018262018264194304256001224269440x7f4602ecd7000x7f460262448052428810923690122344778417249068189744172490681567481724906843978817249068441357
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00652018262018264194304256001224276480x7f46056315800x7f46026244c052428811208563125533960817249068479546172490684397881724906871962817249068721470
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00682018262018264194304256001624286080x7f46056314000x7f460262450052428811482302128599458817249068752419172490687196281724906908906717249069090770
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00712018262018264194304256001624293120x7f46056312800x7f460262454052428811497488128772660017249069122629172490690890671724906945594717249069457760
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00742018262018264194304256001224300160x7f46056311000x7f460262458052428810905647122148877217249069488969172490694559471724906973546717249069737342
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077201826201826419430425600824309760x7f4602ecdf800x7f46026245c052428810621894118972097617249069769461172490697354671724907001482717249070016595
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00802018262018264194304256001224316800x7f4602ecde000x7f460262460052428811236993125849534817249070054104172490700148271724907030202717249070303937
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00832018262018264194304256001624326400x7f4602ecdc800x7f460262464052428811382138127474498817249070335636172490703020271724907067530717249070677047
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00862018262018264194304256001224336000x7f4602ecdb000x7f460262468052428811522714129054758417249070708346172490706753071724907104346617249071045357
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00892018262018264194304256001224345600x7f4602ecd9800x7f46026246c052428810645747119231106417249071077096172490710434661724907132314617249071324950
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092201826201826419430425600824355200x7f4602ecd8000x7f460262470052428810269042115012056817249071356779172490713231461724907160650617249071608332
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00952018262018264194304256001224362240x7f4602ecd6800x7f460262474052428810943920122571642817249071647101172490716065061724907188602617249071887855
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00982018262018264194304256001224371840x7f46056315000x7f460262478052428811582338129721100817249071919414172490718860261724907225530617249072257145
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001012018262018264194304256001224381440x7f46056313800x7f46026247c052428811250668126000637217249072289144172490722553061724907262154617249072623375
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001042018262018264194304256001224391040x7f46056312000x7f460262480052428810404206116517360417249072655764172490726215461724907290218617249072903937
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107201826201826419430425600824403200x7f46056310800x7f460262484052428810004092112044459217249072936126172490729021861724907318458517249073186140
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001102018262018264194304256001224412800x7f4602ecdf000x7f460262488052428810541861118070689617249073224349172490731845851724907347466517249073476512
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001132018262018264194304256001224422400x7f4602ecdd800x7f46026248c052428811396323127634987617249073507581172490734746651724907384410517249073845932
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001162018262018264194304256001224432000x7f4602ecdc000x7f460262490052428811404589127729035217249073877281172490738441051724907421370517249074215592
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119201826201826419430425600824441600x7f4602ecda800x7f460262494052428810704374119888175617249074248151172490742137051724907449962517249074501624
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001222018262018264194304256001224453760x7f4602ecd9000x7f46026249805242889721293108877306817249074532843172490744996251724907479210517249074793946
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001252018262018264194304256001224463360x7f4602ecd7800x7f46026249c052428810790063120846777617249074832015172490747921051724907507194517249075073659
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001282018262018264194304256001224475520x7f4602ecd6000x7f4602624a0052428811227370125745596017249075104888172490750719451724907543754417249075439119
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001312018262018264194304256001224485120x7f46056314800x7f4602624a4052428811400305127683295217249075472218172490754375441724907580410417249075805949
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134201826201826419430425600824494720x7f46056313000x7f4602624a8052428810036111112397564417249075837598172490758041041724907608570417249076087551
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001372018262018264194304256001224506880x7f46056311800x7f4602624ac05242889048223101336210017249076120561172490760857041724907636986417249076371724
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001402018262018264194304256001224516480x7f46056310000x7f4602624b0052428810287369115217888817249076410253172490763698641724907665034417249076652246
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001432018262018264194304256001224528640x7f4602ecde800x7f4602624b4052428811434914128070690417249076683795172490766503441724907701786417249077019726
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001462018262018264194304256001224540800x7f4602ecdd000x7f4602624b8052428811202466125466300417249077051085172490770178641724907738410317249077385866
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149201826201826419430425600824552960x7f4602ecdb800x7f4602624bc052428810453953117084698017249077417756172490773841031724907766474317249077666609
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001522018262018264194304256001224567680x7f4602ecda000x7f4602624c00524288780171787382541217249077698378172490776647431724907794602317249077947941
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001552018262018264194304256001224577280x7f4602ecd8800x7f4602624c4052428810397669116452728017249077986230172490779460231724907823418317249078236203
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001582018262018264194304256001224589440x7f4602ecd7000x7f4602624c8052428811346280127075074017249078268413172490782341831724907860330317249078605133
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001612018262018264194304256001224601600x7f46056315800x7f4602624cc052428811296973126524493217249078637073172490786033031724907896810317249078969914
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164201826201826419430425600824613760x7f46056314000x7f4602624d0052428810186663114084798417249079001653172490789681031724907925610317249079257946
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001672018262018264194304256001224628480x7f46056312800x7f4602624d40524288629920270553486017249079289485172490792561031724907954410217249079545928
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001702018262018264194304256001224638080x7f46056311000x7f4602624d8052428810306115115421675217249079584987172490795441021724907982522217249079826930
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001732018262018264194304256001224650240x7f4602ecdf800x7f4602624dc052428811320974126794128817249079860670172490798252221724908018874217249080190611
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001762018262018264194304256001224662400x7f4602ecde000x7f4602624e0052428811174915125155230817249080222540172490801887421724908055130217249080553011
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179201826201826419430425600824674560x7f4602ecdc800x7f4602624e4052428810032926112380741617249080584350172490805513021724908083418217249080836003
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001822018262018264194304256001224689280x7f4602ecdb000x7f4602624e80524288593957166520984017249080867792172490808341821724908112698217249081128785
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001852018262018264194304256001224701440x7f4602ecd9800x7f4602624ec052428810002538112023679217249081167994172490811269821724908141082217249081412558
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001882018262018264194304256001224716160x7f4602ecd8000x7f4602624f0052428811313475126711473617249081443487172490814108221724908177962117249081781538
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001912018262018264194304256001224728320x7f4602ecd6800x7f4602624f4052428811321778126797758817249081812997172490817796211724908216058117249082162637
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194201826201826419430425600824740480x7f46056315000x7f4602624f805242889799168109747878017249082195516172490821605811724908244634117249082448030
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001972018262018264194304256001224757760x7f46056313800x7f4602624fc0524288482853954072001617249082480129172490824463411724908274138117249082743192
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002002018262018264194304256001224769920x7f46056312000x7f460262500052428810032332112358702017249082782161172490827413811724908302074117249083022494
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002032018262018264194304256001224784640x7f46056310800x7f460262504052428811270953126235203617249083053713172490830207411724908338538117249083387184
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002062018262018264194304256001224799360x7f4602ecdf000x7f460262508052428811212773125582121217249083420474172490833853811724908375450017249083756185
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209201826201826419430425600824814080x7f4602ecdd800x7f46026250c05242889705000108694460817249083787354172490837545001724908403306017249084034807
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002122018262018264194304256001224831360x7f4602ecdc000x7f4602625100524288416246846612484017249084066606172490840330601724908433722017249084338969
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002152018262018264194304256001224843520x7f4602ecda800x7f460262514052428810335929115757531217249084388388172490843372201724908462298017249084624851
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002182018262018264194304256001224858240x7f4602ecd9000x7f460262518052428811233967125819133617249084656620172490846229801724908499354017249084995271
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002212018262018264194304256001224872960x7f4602ecd7800x7f46026251c052428811251050126009831617249085028350172490849935401724908536650017249085368301
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002242018262018264194304256001224887680x7f4602ecd6000x7f46026252005242889538965106826572417249085399630172490853665001724908565242017249085654144
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002272018262018264194304256001224907520x7f46056314800x7f4602625240524288384527343065435617249085685043172490856524201724908595913917249085960945
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002302018262018264194304256001224919680x7f46056313000x7f460262528052428810008285112083045217249085999104172490859591391724908625241917249086254167
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002332018262018264194304256001224934400x7f46056311800x7f46026252c052428811252972126029065617249086286167172490862524191724908662729917249086629157
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002362018262018264194304256001224949120x7f46056310000x7f460262530052428811158331124966931617249086660906172490866272991724908699513917249086996727
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002392018262018264194304256001224963840x7f4602ecde800x7f46026253405242889243940103526339617249087028197172490869951391724908727753917249087279290
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002422018262018264194304256001224983680x7f4602ecdd000x7f4602625380524288344314638558820017249087310249172490872775391724908758857917249087590411
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002452018262018264194304256001224995840x7f4602ecdb800x7f46026253c052428810134374113503372817249087630020172490875885791724908787113817249087872844
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024820182620182641943042560012241013120x7f4602ecda000x7f460262540052428811046720123721223617249087903913172490878711381724908824793817249088249714
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025120182620182641943042560012241027840x7f4602ecd8800x7f460262544052428810920083122304481617249088282163172490882479381724908861849817249088620344
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025420182620182641943042560012241042560x7f4602ecd7000x7f4602625480524288858230996118186817249088651703172490886184981724908889945817249088901096
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025720182620182641943042560012241062400x7f46056315800x7f46026254c0524288312290434983586417249088933465172490888994581724908921833817249089220047
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026020182620182641943042560012241077120x7f46056314000x7f46026255005242889868636110531659217249089258846172490892183381724908949929817249089501280
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026320182620182641943042560016241094400x7f46056312800x7f460262554052428811187215125294510817249089532399172490894992981724908986585817249089867700
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026620182620182641943042560016241111680x7f46056311000x7f460262558052428811040859123654984417249089899859172490898658581724909023305717249090235200
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002692018262018264194304256008241128960x7f4602ecdf800x7f46026255c0524288802811589912905217249090267589172490902330571724909052233717249090524072
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027220182620182641943042560012241151360x7f4602ecde000x7f4602625600524288318570335688139217249090555771172490905223371724909084793717249090849633
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027520182620182641943042560012241166080x7f4602ecdc800x7f46026256405242889764110109361200417249090888642172490908479371724909113769717249091139615
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027820182620182641943042560016241183360x7f4602ecdb000x7f460262568052428811086681124168768817249091172475172490911376971724909150697717249091508716
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028120182620182641943042560016241200640x7f4602ecd9800x7f46026256c052428811124997124600359217249091540555172490915069771724909187417717249091876036
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028420182620182641943042560012241217920x7f4602ecd8000x7f4602625700524288697979778168332417249091906875172490918741771724909215977617249092161558
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028720182620182641943042560012241240320x7f4602ecd6800x7f4602625740524288294824933012226417249092193187172490921597761724909248985617249092491609
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029020182620182641943042560012241255040x7f46056315000x7f46026257805242889305908104219066817249092530598172490924898561724909277673617249092778591
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029320182620182641943042560012241274880x7f46056313800x7f46026257c052428811098917124304103217249092810010172490927767361724909314217617249093144011
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029620182620182641943042560012241292160x7f46056312000x7f460262580052428811071627123998014017249093176170172490931421761724909350937617249093511261
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029920182620182641943042560012241309440x7f46056310800x7f4602625840524288608949368202072017249093542171172490935093761724909379497617249093796864
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030220182620182641943042560012241334400x7f4602ecdf000x7f4602625880524288289405932412148417249093828013172490937949761724909414073517249094142844
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030520182620182641943042560012241349120x7f4602ecdd800x7f46026258c0524288851220995335333217249094182543172490941407351724909442585517249094427837
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030820182620182641943042560012241368960x7f4602ecdc000x7f460262590052428810978651122958160817249094458766172490944258551724909479113517249094792987
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031120182620182641943042560012241388800x7f4602ecda800x7f460262594052428810906645122151519617249094824236172490947911351724909515673517249095158407
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031420182620182641943042560012241408640x7f4602ecd9000x7f4602625980524288475545753263274817249095190246172490951567351724909544889517249095450799
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031720182620182641943042560012241436160x7f4602ecd7800x7f46026259c0524288291191032606629617249095482518172490954488951724909580233517249095804180
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032020182620182641943042560012241453440x7f4602ecd6000x7f4602625a00524288755409884609070417249095843169172490958023351724909608361517249096085372
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032320182620182641943042560012241475840x7f46056314800x7f4602625a4052428810902436122107959617249096116781172490960836151724909645113417249096453002
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032620182620182641943042560012241495680x7f46056313000x7f4602625a8052428810960057122745949617249096484662172490964511341724909681945417249096821322
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032920182620182641943042560012241515520x7f46056311800x7f4602625ac0524288378779142420388417249096852582172490968194541724909712025417249097122154
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033220182620182641943042560012241543040x7f46056310000x7f4602625b00524288286981932130561617249097154004172490971202541724909748809417249097489875
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033520182620182641943042560012241562880x7f4602ecde800x7f4602625b40524288553783562026442817249097527434172490974880941724909777657417249097778367
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033820182620182641943042560012241587840x7f4602ecdd000x7f4602625b8052428810613095118863758417249097808806172490977765741724909814361417249098145657
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034120182620182641943042560012241610240x7f4602ecdb800x7f4602625bc052428810845487121468149617249098177776172490981436141724909851689317249098518727
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034420182620182641943042560012241632640x7f4602ecda000x7f4602625c00524288372236041692182817249098549736172490985168931724909882505317249098827038
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034720182620182641943042560012241665280x7f4602ecd8800x7f4602625c40524288289713932428648817249098857858172490988250531724909921529317249099237347
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035020182620182641943042560012241685120x7f4602ecd7000x7f4602625c80524288398449044621456417249099257707172490992152931724909952537317249099527140
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035320182620182641943042560012241712640x7f46056315800x7f4602625cc052428810074109112824691217249099558349172490995253731724909990057317249099902419
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035620182620182641943042560012241737600x7f46056314000x7f4602625d005242889640308107970406817249099934919172490999005731724910027673317249100278609
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035920182620182641943042560012241762560x7f46056312800x7f4602625d40524288295934433140335617249100309838172491002767331724910060249217249100604240
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036220182620182641943042560012241797760x7f46056311000x7f4602625d80524288286638932094044817249100635960172491006024921724910102153217249101039489
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036520182620182641943042560012241822720x7f4602ecdf800x7f4602625dc0524288311298534864999617249101063018172491010215321724910134873217249101350480
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036820182620182641943042560012241855360x7f4602ecde000x7f4602625e00524288828491092791357617249101382199172491013487321724910172665217249101744380
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037120182620182641943042560012241885440x7f4602ecdc800x7f4602625e40524288769943386235222017249101759819172491017266521724910211193217249102133309
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037420182620182641943042560012241915520x7f4602ecdb000x7f4602625e80524288283354931736726417249102146209172491021119321724910247913117249102480840
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037720182620182641943042560012241958400x7f4602ecd9800x7f4602625ec0524288286068132038721217249102512209172491024791311724910295033117249102969597
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038020182620182641943042560012241985920x7f4602ecd8000x7f4602625f00524288279868831345197217249102990996172491029503311724910329113117249103292848
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038320182620182641943042560012242023680x7f4602ecd6800x7f4602625f40524288693653777683518017249103323687172491032911311724910369241117249103710297
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038620182620182641943042560012242058880x7f46056315000x7f4602625f80524288667498374758452417249103726246172491036924111724910409113117249104108486
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038920182620182641943042560012242094080x7f46056313800x7f4602625fc0524288285391731969476817249104124965172491040911311724910446937117249104471526
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039220182620182641943042560012242144640x7f46056312000x7f4602626000524288293315532850938417249104504965172491044693711724910499145017249105008892
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039520182620182641943042560012242177280x7f46056310800x7f4602626040524288282817231673468817249105032371172491049914501724910535545017249105357182
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039820182620182641943042560012242220160x7f4602ecdf000x7f4602626080524288595337766678639617249105390681172491053554501724910577081017249105788110
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040120182620182641943042560012242260480x7f4602ecdd800x7f46026260c0524288507799856870126017249105805380172491057708101724910619337017249106211759
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040420182620182641943042560012242300800x7f4602ecdc000x7f4602626100524288277885331120953217249106226989172491061933701724910660377017249106646447
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040720182620182641943042560012242359040x7f4602ecda800x7f4602626140524288290558932540356817249106659267172491066037701724910720792917249107250171
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041020182620182641943042560012242394240x7f4602ecd9000x7f4602626180524288275723330884542017249107270111172491072079291724910761496917249107616761
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041320182620182641943042560012242442240x7f4602ecd7800x7f46026261c0524288526488458963512817249107649130172491076149691724910805800917249108076499
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041620182620182641943042560012242487680x7f4602ecd6000x7f4602626200524288318523635676157617249108091369172491080580091724910849384917249108510847
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041920182620182641943042560012242533120x7f46056314800x7f4602626240524288273025430577869617249108527587172491084938491724910892216817249108939076
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004222018262018264194304256008242555520x7f46056313000x7f4602626280524288237942726648518417249108956565172491089221681724910956648817249109583329
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042520182620182641943042560012242598400x7f46056311800x7f46026262c0524288273163030592538417249109608408172491095664881724910998248817249109998847
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042820182620182641943042560012242656640x7f46056310000x7f4602626300524288337128137753014817249110015397172491099824881724911048296817249110503344
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043120182620182641943042560012242712320x7f4602ecde800x7f4602626340524288356690239951005217249110516973172491104829681724911097928717249110996290
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004342018262018264194304256008242732160x7f4602ecdd000x7f4602626380524288240908526984678017249111013160172491109792871724911146840717249111485817
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004372018262018264194304256008242757120x7f4602ecdb800x7f46026263c0524288238409926698202017249111502227172491114684071724911222040717249112237417
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044020182620182641943042560012242807680x7f4602ecda000x7f4602626400524288265398329721954417249112261306172491122204071724911268184717249112698484
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044320182620182641943042560012242876160x7f4602ecd8800x7f4602626440524288345548438700058817249112715134172491126818471724911322312617249113240020
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044620182620182641943042560012242942080x7f4602ecd7000x7f4602626480524288334961037513519617249113257529172491132231261724911376408617249113782325
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004492018262018264194304256008242969600x7f46056315800x7f46026264c0524288239156826784852417249113797165172491137640861724911430488617249114323011
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004522018262018264194304256008242999680x7f46056314000x7f4602626500524288239573426831107217249114339820172491143048861724911515896517249115181307
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004552018262018264194304256008243027200x7f46056312800x7f4602626540524288239686626841293217249115200707172491151589651724911580520517249115822320
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045820182620182641943042560012243054720x7f46056311000x7f4602626580524288260073829130788817249115839690172491158052051724911646232517249116481172
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046120182620182641943042560012243082240x7f4602ecdf800x7f46026265c0524288261685529310710017249116498462172491164623251724911711720517249117134615
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004642018262018264194304256008243109760x7f4602ecde000x7f4602626600524288240516226936100817249117151334172491171172051724911776296417249117780437
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004672018262018264194304256008243132160x7f4602ecdc800x7f4602626640524288241913627094445617249117796607172491177627991724911882359917249118869908
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004702018262018264194304256008243159680x7f4602ecdb000x7f4602626680524288244254627355390417249118890617172491188235991724911990695717249119954289
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047320182620182641943042560012243187200x7f4602ecd9800x7f46026266c0524288260070929128496017249119965408172491199069571724912101671617249121055609
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047620182620182641943042560012243214720x7f4602ecd8000x7f4602626700524288259142329021603617249121067449172491210167161724912210919517249122175659
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004792018262018264194304256008243242240x7f4602ecd6800x7f4602626740524288242629327169334417249122187259172491221091951724912321575417249123256420
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004822018262018264194304256008243264640x7f46056315000x7f4602626780524288246049527553566417249123267940172491232157541724912512679217249125167788
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004852018262018264194304256008243292160x7f46056313800x7f46026267c0524288245634227507306017249125187048172491251267921724912702311117249127088467
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048820182620182641943042560012243319680x7f46056312000x7f4602626800524288262476629402402817249127100496172491270231111724912900566917249129072943
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049120182620182641943042560012243347200x7f46056310800x7f4602626840524288261338429264322017249129083973172491290056691724913099270817249131063310
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004942018262018264194304256008243374720x7f4602ecdf000x7f4602626880524288246582927616560417249131075829172491309927081724913293270617249133005247
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049720182620182641943042560082400x7f4602ecdd800x7f46026268c0524288247271527688795617249133017057172491329327061724913655126317249136623859