Files
rocm-systems/tests/workloads/Axes3/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.kd000211527211527335544322560043241600x00x7f46882042803670016305415434185715217413315644610174045796246331741346333334317413463447223
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00221152721152732768256001224138880x00x7f4688223f80512963221080019217413468616208174134633333431741346874454817413468748994
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0052115272115274194304256001224143360x7f468b1cd3800x7f4688223fc0655366216946963417617413468781314174134687445481741346910310917413469105425
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0082115272115274194304256001624150400x7f468b1cd2000x7f4688224000655366435147216404017413469140564174134691031091741346950118917413469503305
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00112115272115274194304256001624154880x7f468b1cd0800x7f4688224040655366364627134396817413469536664174134695011891741346989191017413469894275
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00142115272115274194304256001224159360x7f4688b2df000x7f4688224080655366292387047362417413469926374174134698919101741347020327017413470205907
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00172115272115274194304256001224163840x7f4688b2dd800x7f46882240c0655365999586722130417413470237096174134702032701741347050951017413470511529
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00202115272115274194304256001224170880x7f4688b2dc000x7f46882241001310726401307179296017413470555557174134705095101741347080759117413470809741
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00232115272115274194304256001624177920x7f4688b2da800x7f46882241401310726771247585138417413470841170174134708075911741347119591117413471198001
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00262115272115274194304256001624184960x7f4688b2d9000x7f4688224180655366352487130504017413471229740174134711959111741347158007217413471582150
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00292115272115274194304256001624192000x7f4688b2d7800x7f46882241c01310726785367595071217413471612380174134715800721741347188935217413471891562
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00322115272115274194304256001624199040x7f4688b2d6000x7f46882242001310726773327592373617413471922862174134718893521741347218759217413472189595
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00352115272115274194304256001224206080x7f468b1cd4800x7f46882242401310726758287565336017413472229074174134721875921741347249863317413472500816
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00382115272115274194304256001624213120x7f468b1cd3000x7f46882242801310726955567806388017413472533496174134724986331741347288535317413472887726
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00412115272115274194304256001624220160x7f468b1cd1800x7f46882242c0655366411607173844017413472918585174134728853531741347326919417413473271376
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00442115272115274194304256001624227200x7f468b1cd0000x7f46882243001310726743867549232017413473302925174134732691941741347356679417413473568838
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00472115272115274194304256001224234240x7f4688b2de800x7f46882243401310727190648060626417413473600928174134735667941741347386551417413473867451
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00502115272115274194304256001224241280x7f4688b2dd000x7f46882243801310726710807515001617413473906620174134738655141741347416167517413474164013
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00532115272115274194304256001624248320x7f4688b2db800x7f46882243c01310726740907557556817413474196162174134741616751741347455831517413474560633
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00562115272115274194304256001624255360x7f4688b2da000x7f4688224400655365987626714497617413474591742174134745583151741347495223517413474953842
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00592115272115274194304256001224262400x7f4688b2d8800x7f46882244401310726818147636690417413474984912174134749522351741347522071617413475222265
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00622115272115274194304256001224269440x7f4688b2d7000x7f46882244801310726718747528431217413475253725174134752207161741347549223617413475493798
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00652115272115274194304256001224276480x7f468b1cd5800x7f46882244c01310726363707113256817413475532707174134754922361741347576679617413475768341
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00682115272115274194304256001624286080x7f468b1cd4000x7f46882245001310726711347518173617413475801540174134757667961741347612247717413476124062
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00712115272115274194304256001624293120x7f468b1cd2800x7f4688224540655366372287138602417413476155191174134761224771741347647879717413476480433
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00742115272115274194304256001224300160x7f468b1cd1000x7f46882245801310726487827266765617413476512992174134764787971741347675223717413476753916
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077211527211527419430425600824309760x7f4688b2df800x7f46882245c01310726336327111980817413476785985174134767522371741347702279817413477024339
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00802115272115274194304256001224316800x7f4688b2de000x7f46882246001310726711207526843217413477061778174134770227981741347729447817413477296021
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00832115272115274194304256001624326400x7f4688b2dc800x7f46882246401310726283467038617617413477327881174134772944781741347765463817413477656132
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00862115272115274194304256001224336000x7f4688b2db000x7f4688224680655366227846976761617413477686391174134776546381741347801911917413478020673
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00892115272115274194304256001224345600x7f4688b2d9800x7f46882246c01310726885827718867217413478052652174134780191191741347829991917413478301695
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092211527211527419430425600824355200x7f4688b2d8000x7f46882247001310727023727877239217413478332484174134782999191741347857416017413478575648
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00952115272115274194304256001224362240x7f4688b2d6800x7f46882247401310726756567562168017413478614557174134785741601741347885048017413478851881
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00982115272115274194304256001224371840x7f468b1cd5000x7f46882247801310726346067113876817413478882710174134788504801741347920808017413479209661
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001012115272115274194304256001224381440x7f468b1cd3800x7f46882247c0655366340487101249617413479240981174134792080801741347956456117413479566142
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001042115272115274194304256001224391040x7f468b1cd2000x7f46882248001310726718027517792817413479597711174134795645611741347983384117413479835435
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107211527211527419430425600824403200x7f468b1cd0800x7f46882248401310726782047598454417413479867424174134798338411741348010424117413480105818
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001102115272115274194304256001224412800x7f4688b2df000x7f46882248801310726733307532747217413480143647174134801042411741348037624217413480377741
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001132115272115274194304256001224422400x7f4688b2dd800x7f46882248c01310727159348020990417413480409320174134803762421741348074040217413480741931
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001162115272115274194304256001224432000x7f4688b2dc000x7f4688224900655365957726674358417413480773041174134807404021741348109640217413481097932
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119211527211527419430425600824441600x7f4688b2da800x7f46882249401310726770447581480017413481129091174134810964021741348136520317413481366725
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001222115272115274194304256001224453760x7f4688b2d9000x7f46882249801310726731467538265617413481397994174134813652031741348163464317413481636228
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001252115272115274194304256001224463360x7f4688b2d7800x7f46882249c01310726701707502644817413481674937174134816346431741348190744317413481909081
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001282115272115274194304256001224475520x7f4688b2d6000x7f4688224a001310726933827752592017413481940420174134819074431741348226536417413482267031
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001312115272115274194304256001224485120x7f468b1cd4800x7f4688224a40655366270767028857617413482299501174134822653641741348262696417413482628532
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134211527211527419430425600824494720x7f468b1cd3000x7f4688224a801310726436327205052817413482660141174134826269641741348289640417413482897975
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001372115272115274194304256001224506880x7f468b1cd1800x7f4688224ac01310726414327180736817413482929354174134828964041741348316680517413483168338
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001402115272115274194304256001224516480x7f468b1cd0000x7f4688224b001310726350027103543217413483207277174134831668051741348344472517413483446221
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001432115272115274194304256001224528640x7f4688b2de800x7f4688224b401310726746527557158417413483477090174134834447251741348380312517413483804651
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001462115272115274194304256001224540800x7f4688b2dd000x7f4688224b80655366280227044148017413483836561174134838031251741348416104617413484162552
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149211527211527419430425600824552960x7f4688b2db800x7f4688224bc01310726756607574888017413484193671174134841610461741348443368617413484435175
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001522115272115274194304256001224567680x7f4688b2da000x7f4688224c001310726701067503095217413484467314174134844336861741348470568617413484707258
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001552115272115274194304256001224577280x7f4688b2d8800x7f4688224c401310726923307746588817413484747897174134847056861741348497816717413484979701
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001582115272115274194304256001224589440x7f4688b2d7000x7f4688224c801310726629967421259217413485010180174134849781671741348533832717413485339872
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001612115272115274194304256001224601600x7f468b1cd5800x7f4688224cc0655366420727187033617413485370621174134853383271741348569464817413485696212
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164211527211527419430425600824613760x7f468b1cd4000x7f4688224d001310726731307537825617413485727761174134856946481741348596648817413485968055
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001672115272115274194304256001224628480x7f468b1cd2800x7f4688224d401310726753387558221617413485999824174134859664881741348625560817413486257338
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001702115272115274194304256001224638080x7f468b1cd1000x7f4688224d801310726744307571283217413486296507174134862556081741348652808817413486529681
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001732115272115274194304256001224650240x7f4688b2df800x7f4688224dc01310726441067226293617413486561460174134865280881741348688808917413486889711
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001762115272115274194304256001224662400x7f4688b2de000x7f4688224e00655365976726697002417413486921570174134868880891741348724264917413487244012
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179211527211527419430425600824674560x7f4688b2dc800x7f4688224e401310726943567789293617413487276031174134872426491741348751353017413487515115
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001822115272115274194304256001224689280x7f4688b2db000x7f4688224e801310726698907506416017413487546844174134875135301741348779145017413487793057
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001852115272115274194304256001224701440x7f4688b2d9800x7f4688224ec01310726864127690408817413487831106174134877914501741348806377017413488065250
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001882115272115274194304256001224716160x7f4688b2d8000x7f4688224f001310727005127845167217413488097059174134880637701741348842457117413488426101
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001912115272115274194304256001224728320x7f4688b2d6800x7f4688224f40655366447307217402417413488457630174134884245711741348878345117413488785051
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194211527211527419430425600824740480x7f468b1cd5000x7f4688224f801310726362307125561617413488816841174134887834511741348905801117413489059634
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001972115272115274194304256001224757760x7f468b1cd3800x7f4688224fc01310726398407170427217413489091353174134890580111741348934281217413489344297
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002002115272115274194304256001224769920x7f468b1cd2000x7f46882250001310726698667516031217413489382476174134893428121741348961433217413489615920
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002032115272115274194304256001224784640x7f468b1cd0800x7f46882250401310727112127972912817413489647389174134896143321741348997177217413489973410
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002062115272115274194304256001224799360x7f4688b2df000x7f4688225080655366413067179185617413490005200174134899717721741349033785317413490339491
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209211527211527419430425600824814080x7f4688b2dd800x7f46882250c01310726738707549248017413490371060174134903378531741349061257317413490614084
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002122115272115274194304256001224831360x7f4688b2dc000x7f46882251001310726736507540853617413490646333174134906125731741349090553317413490907266
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002152115272115274194304256001224843520x7f4688b2da800x7f46882251401310726754067564195217413490956145174134909055331741349118169417413491183129
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002182115272115274194304256001224858240x7f4688b2d9000x7f46882251801310726735507557154417413491215168174134911816941741349154121417413491542810
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002212115272115274194304256001224872960x7f4688b2d7800x7f46882251c0655366494827268116817413491574629174134915412141741349190601517413491907410
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002242115272115274194304256001224887680x7f4688b2d6000x7f46882252001310726778667585453617413491938639174134919060151741349217753517413492179103
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002272115272115274194304256001224907520x7f468b1cd4800x7f46882252401310726732287544851217413492210892174134921775351741349247145517413492473115
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002302115272115274194304256001224919680x7f468b1cd3000x7f46882252801310726710747516561617413492511544174134924714551741349274745517413492748978
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002332115272115274194304256001224934400x7f468b1cd1800x7f46882252c01310726733587530708817413492780237174134927474551741349310185617413493103429
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002362115272115274194304256001224949120x7f468b1cd0000x7f4688225300655366436187212199217413493134688174134931018561741349345721617413493458710
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002392115272115274194304256001224963840x7f4688b2de800x7f46882253401310726715627520141617413493489799174134934572161741349372713717413493728633
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002422115272115274194304256001224983680x7f4688b2dd000x7f46882253801310726863787679644017413493759902174134937271371741349402873717413494030285
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002452115272115274194304256001224995840x7f4688b2db800x7f46882253c01310726698927496772017413494068534174134940287371741349431385717413494315407
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024821152721152741943042560012241013120x7f4688b2da000x7f46882254001310726307467066996017413494347177174134943138571741349467769817413494679198
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025121152721152741943042560012241027840x7f4688b2d8800x7f4688225440655366710887518677617413494711617174134946776981741349503481817413495036218
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025421152721152741943042560012241042560x7f4688b2d7000x7f46882254801310726426147191496817413495067338174134950348181741349530601817413495307401
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025721152721152741943042560012241062400x7f468b1cd5800x7f46882254c01310726368167133853617413495338291174134953060181741349561177917413495613203
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026021152721152741943042560012241077120x7f468b1cd4000x7f46882255001310726250947010926417413495652102174134956117791741349588841917413495889916
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026321152721152741943042560016241094400x7f468b1cd2800x7f46882255401310726792887610473617413495923205174134958884191741349624409917413496245667
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026621152721152741943042560016241111680x7f468b1cd1000x7f4688225580655366863587696130417413496277496174134962440991741349660074017413496602287
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002692115272115274194304256008241128960x7f4688b2df800x7f46882255c01310726765007571629617413496633477174134966007401741349687226017413496873850
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027221152721152741943042560012241151360x7f4688b2de000x7f46882256001310726697487508178417413496904950174134968722601741349718538017413497187092
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027521152721152741943042560012241166080x7f4688b2dc800x7f46882256401310726702427505092017413497224991174134971853801741349745450117413497455895
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027821152721152741943042560016241183360x7f4688b2db000x7f46882256801310726769947580326417413497486424174134974545011741349781706117413497818496
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028121152721152741943042560016241200640x7f4688b2d9800x7f46882256c0655366419107202283217413497849715174134978170611741349817402217413498175696
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028421152721152741943042560012241217920x7f4688b2d8000x7f46882257001310726749587558632817413498207435174134981740221741349845562217413498457219
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028721152721152741943042560012241240320x7f4688b2d6800x7f46882257401310726684547485946417413498488208174134984556221741349877498217413498776541
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029021152721152741943042560012241255040x7f468b1cd5000x7f46882257801310726765247574640017413498814050174134987749821741349904730317413499048734
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029321152721152741943042560012241274880x7f468b1cd3800x7f46882257c01310726697827514933617413499079423174134990473031741349940650317413499408084
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029621152721152741943042560012241292160x7f468b1cd2000x7f4688225800655366414127190411217413499439343174134994065031741349976218317413499763695
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029921152721152741943042560012241309440x7f468b1cd0800x7f46882258401310726316047068706417413499795904174134997621831741350003898417413500040548
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030221152721152741943042560012241334400x7f4688b2df000x7f46882258801310726397607165441617413500071887174135000389841741350036954417413500371029
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030521152721152741943042560012241349120x7f4688b2dd800x7f46882258c013107299448011153956817413500409808174135003695441741350065434417413500655932
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030821152721152741943042560012241368960x7f4688b2dc000x7f46882259001310726429887192797617413500686361174135006543441741350101146517413501012963
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031121152721152741943042560012241388800x7f4688b2da800x7f4688225940655366374107131142417413501044422174135010114651741350136714517413501368783
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031421152721152741943042560012241408640x7f4688b2d9000x7f46882259801310726729467542203217413501399762174135013671451741350164890517413501650426
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031721152721152741943042560012241436160x7f4688b2d7800x7f46882259c01310726761827573252817413501681055174135016489051741350199482617413501996377
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032021152721152741943042560012241453440x7f4688b2d6000x7f4688225a0013107299723211175200017413502035826174135019948261741350227338617413502274920
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032321152721152741943042560012241475840x7f468b1cd4800x7f4688225a401310726771667576298417413502307739174135022733861741350263130717413502633020
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032621152721152741943042560012241495680x7f468b1cd3000x7f4688225a80655366739507545516017413502664589174135026313071741350298858717413502990161
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032921152721152741943042560012241515520x7f468b1cd1800x7f4688225ac01310726287887040028817413503021400174135029885871741350327498717413503276363
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033221152721152741943042560012241543040x7f468b1cd0000x7f4688225b001310726319287073280017413503307513174135032749871741350363674817413503638184
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033521152721152741943042560012241562880x7f4688b2de800x7f4688225b4013107294821810627649617413503677053174135036367481741350391978817413503921267
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033821152721152741943042560012241587840x7f4688b2dd000x7f4688225b801310726750027555300017413503952736174135039197881741350427706817413504278637
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034121152721152741943042560012241610240x7f4688b2db800x7f4688225bc0655366426467190376817413504309896174135042770681741350463482917413504636358
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034421152721152741943042560012241632640x7f4688b2da000x7f4688225c001310726616207416740817413504666797174135046348291741350493290917413504934580
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034721152721152741943042560012241665280x7f4688b2d8800x7f4688225c401310726367567123160017413504965609174135049329091741350531547017413505338309
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035021152721152741943042560012241685120x7f4688b2d7000x7f4688225c8013107299856411163376817413505357019174135053154701741350561419017413505615752
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035321152721152741943042560012241712640x7f468b1cd5800x7f4688225cc01310726309667076877617413505646691174135056141901741350597371017413505975193
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035621152721152741943042560012241737600x7f468b1cd4000x7f4688225d00655366610987406961617413506007432174135059737101741350634267117413506344233
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035921152721152741943042560012241762560x7f468b1cd2800x7f4688225d401310726324287076396817413506375882174135063426711741350666379117413506665435
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036221152721152741943042560012241797760x7f468b1cd1000x7f4688225d801310726318787074222417413506697514174135066637911741350707403217413507097764
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036521152721152741943042560012241822720x7f4688b2df800x7f4688225dc013107293431010471096817413507116453174135070740321741350739451217413507396036
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036821152721152741943042560012241855360x7f4688b2de000x7f4688225e001310726808867623616817413507426895174135073945121741350776027217413507761636
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037121152721152741943042560012241885440x7f4688b2dc800x7f4688225e40655366348127113836817413507792885174135077602721741350812955317413508150686
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037421152721152741943042560012241915520x7f4688b2db000x7f4688225e801310726330307098233617413508161796174135081295531741350847483317413508476318
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037721152721152741943042560012241958400x7f4688b2d9800x7f4688225ec01310726477247248162417413508507047174135084748331741350893595417413508955045
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038021152721152741943042560012241985920x7f4688b2d8000x7f4688225f00131072100622011265866417413508976235174135089359541741350926651417413509268077
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038321152721152741943042560012242023680x7f4688b2d6800x7f4688225f4013107293238410452375217413509298256174135092665141741350965131417413509668197
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038621152721152741943042560012242058880x7f468b1cd5000x7f4688225f80655366312147056356817413509684506174135096513141741351004395517413510060277
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038921152721152741943042560012242094080x7f468b1cd3800x7f4688225fc01310726395947162964017413510083796174135100439551741351042139517413510422957
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039221152721152741943042560012242144640x7f468b1cd2000x7f46882260001310726382327152964017413510454706174135104213951741351093259617413510953073
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039521152721152741943042560012242177280x7f468b1cd0800x7f468822604013107299943611203995217413510973783174135109325961741351128075617413511282135
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039821152721152741943042560012242220160x7f4688b2df000x7f4688226080131072100903211308290417413511312904174135112807561741351168827717413511706373
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040121152721152741943042560012242260480x7f4688b2dd800x7f46882260c0655366403427166410417413511721623174135116882771741351210171717413512118493
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040421152721152741943042560012242300800x7f4688b2dc000x7f46882261001310726365687132080017413512135042174135121017171741351249435817413512510492
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040721152721152741943042560012242359040x7f4688b2da800x7f46882261401310726833807652924017413512527492174135124943581741351305947817413513075858
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041021152721152741943042560012242394240x7f4688b2d9000x7f4688226180131072103934811630321617413513099067174135130594781741351343611917413513437738
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041321152721152741943042560012242442240x7f4688b2d7800x7f46882261c013107293729210488298417413513468387174135134361191741351387179917413513888476
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041621152721152741943042560012242487680x7f4688b2d6000x7f4688226200655366393427170541617413513906676174135138717991741351430188017413514318615
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041921152721152741943042560012242533120x7f468b1cd4800x7f46882262401310726276787028400017413514335525174135143018801741351472204017413514742714
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004222115272115274194304256008242555520x7f468b1cd3000x7f468822628013107299519411152005617413514755034174135147220401741351535724117413515376458
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042521152721152741943042560012242598400x7f468b1cd1800x7f46882262c0131072101035411321736817413515398027174135153572411741351576396117413515780047
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042821152721152741943042560012242656640x7f468b1cd0000x7f468822630013107293884010512927217413515797057174135157639611741351624364217413516260635
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043121152721152741943042560012242712320x7f4688b2de800x7f4688226340655366330267091322417413516276494174135162436421741351672620217413516742402
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004342115272115274194304256008242732160x7f4688b2dd000x7f468822638013107293789410492907217413516760282174135167262021741351720540317413517221650
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004372115272115274194304256008242757120x7f4688b2db800x7f46882263c013107299518811163779217413517238409174135172054031741351793932417413517956390
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044021152721152741943042560012242807680x7f4688b2da000x7f468822640013107297964810967583217413517979840174135179393241741351840204417413518423778
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044321152721152741943042560012242876160x7f4688b2d8800x7f468822644013107299781011162994417413518434538174135184020441741351893756517413518958054
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044621152721152741943042560012242942080x7f4688b2d7000x7f4688226480655366396527170799217413518970534174135189375651741351947084617413519490660
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004492115272115274194304256008242969600x7f468b1cd5800x7f46882264c0131072101758611395896017413519503010174135194708461741352000284617413520019286
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004522115272115274194304256008242999680x7f468b1cd4000x7f4688226500131072102317411484903217413520036326174135200028461741352084028717413520857205
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004552115272115274194304256008243027200x7f468b1cd2800x7f4688226540131072103335611560941617413520881174174135208402871741352146540817413521480938
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045821152721152741943042560012243054720x7f468b1cd1000x7f4688226580131072101304011339156017413521498188174135214654081741352210620817413522127571
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046121152721152741943042560012243082240x7f4688b2df800x7f46882265c0655366434987202418417413522140231174135221062081741352275724917413522773824
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004642115272115274194304256008243109760x7f4688b2de000x7f468822660013107299484411140716817413522789804174135227572491741352338957017413523406398
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004672115272115274194304256008243132160x7f4688b2dc800x7f4688226640131072100210411211515217413523421978174135233895701741352444205117413524458951
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004702115272115274194304256008243159680x7f4688b2db000x7f4688226680131072100714011292402417413524482520174135244420511741352547501217413525495634
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047321152721152741943042560012243187200x7f4688b2d9800x7f46882266c013107299394011111560017413525506823174135254746151741352654293517413526586465
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047621152721152741943042560012243214720x7f4688b2d8000x7f4688226700655366595887390494417413526598205174135265429351741352763541517413527703086
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004792115272115274194304256008243242240x7f4688b2d6800x7f468822674013107299988411193802417413527714176174135276354151741352874261517413528808057
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004822115272115274194304256008243264640x7f468b1cd5000x7f468822678013107299460411131024017413528820287174135287426151741353068229617413530753366
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004852115272115274194304256008243292160x7f468b1cd3800x7f46882267c0131072105498411821800817413530773466174135306822961741353260261717413532669706
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048821152721152741943042560012243319680x7f468b1cd2000x7f468822680013107298278611031002417413532681386174135326026171741353457861717413534654945
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049121152721152741943042560012243347200x7f468b1cd0800x7f4688226840655366426487189460817413534666554174135345786171741353655685817413536628063
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004942115272115274194304256008243374720x7f4688b2df000x7f4688226880131072102977611523861617413536640143174135365568581741353848869917413538559253
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049721152721152741943042560082400x7f4688b2dd800x7f46882268c0131072102275611429233617413538571642174135384886991741354211142017413542184158