Files
rocm-systems/tests/workloads/HBM/mi100/SQ_INST_LEVEL_SMEM.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

43 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_SMEMSQ_INST_LEVEL_SMEMSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000875394875399335544322560083264640x00x7f91142041804194304317890240690108012075443676964683120754439218005801207544392212809812075443922232171
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00287539487539932768256002424124800x00x7f911423510051222856292712812075443936949303120754439372666951207544393727357512075443937283263
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0048753948753994194304256002424129280x7f921ff0c9000x7f9114235140655361762562244685612075443937346050120754439375575731207544393768909312075443937693215
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0068753948753994194304256003624136320x7f921ff0c8000x7f9114235180655361609382052478412075443937772482120754439379466911207544393819709012075443938251302
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0088753948753994194304256002824140800x7f921ff0c7000x7f91142351c0655361747362240935212075443938285566120754439384769281207544393872556712075443938772130
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00108753948753994194304256002424145280x7f921ff0c6000x7f9114235200655361795662296283212075443938797107120754439389836461207544393912268512075443939126679
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00128753948753994194304256002424149760x7f921ff0c5000x7f9114235240655361767322251854412075443939185378120754439393545241207544393948620312075443939489924
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00148753948753994194304256002424154240x7f921ff0c4000x7f91142352801310722434783110614412075443939576766120754439397438021207544393987724112075443939880510
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00168753948753994194304256002824161280x7f921ff0c3000x7f91142352c01310722066722658520012075443939939289120754439401086001207544394035771812075443940378355
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00188753948753994194304256002824168320x7f921ff0ca000x7f9114235300655361763862271222412075443940429120120754439405938771207544394084395612075443940889846
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00208753948753994194304256002424175360x7f921ff0c9000x7f91142353401310722656943372948812075443940911977120754439411122741207544394124251312075443941246429
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00228753948753994194304256002424182400x7f921ff0c8000x7f91142353801310722627023363894412075443941303495120754439414753121207544394160971112075443941613581
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00248753948753994194304256002424189440x7f921ff0c7000x7f91142353c01310722520983199592012075443941682389120754439418465101207544394197626912075443941979972
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00268753948753994194304256002824199040x7f921ff0c6000x7f91142354001310722063762645440012075443942042809120754439422066681207544394245802712075443942505308
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00288753948753994194304256002824206080x7f921ff0c5000x7f9114235440655361754662245156812075443942532849120754439427101851207544394296602412075443943019303
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00308753948753994194304256002424213120x7f921ff0c4000x7f91142354801310722489763176377612075443943047365120754439432297031207544394335978212075443943363463
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00328753948753994194304256002424220160x7f921ff0c3000x7f91142354c01310722729943486662412075443943420429120754439435858611207544394371994012075443943723572
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00348753948753994194304256002424227200x7f921ff0ca000x7f91142355001310722431803100722412075443943791549120754439439564191207544394408809812075443944092308
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00368753948753994194304256002824236800x7f921ff0c9000x7f91142355401310722078182669112012075443944149654120754439443165771207544394457289512075443944618826
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00388753948753994194304256002824243840x7f921ff0c8000x7f9114235580655361782102280107212075443944643301120754439448293741207544394508473312075443945131970
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00408753948753994194304256002424250880x7f921ff0c7000x7f91142355c01310722670083402504012075443945159371120754439453386511207544394546937012075443945472883
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00428753948753994194304256002424257920x7f921ff0c6000x7f91142356001310722595723318952012075443945532644120754439456930491207544394582808912075443945831991
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00448753948753994194304256002424264960x7f921ff0c5000x7f91142356401310722602743331367212075443945900628120754439460629671207544394619416712075443946198111
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00468753948753994194304256002824277120x7f921ff0c4000x7f91142356801310722166982780922412075443946255227120754439464156051207544394667032412075443946715953
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00488753948753994194304256002824284160x7f921ff0c3000x7f91142356c0655361750542249704812075443946742212120754439469184831207544394716872112075443947214911
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00508753948753994194304256002424291200x7f921ff0ca000x7f91142357001310722420963111988812075443947241670120754439474234401207544394755319912075443947556936
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00528753948753994194304256002424300800x7f921ff0c9000x7f91142357401310722462823157388012075443947616086120754439477776781207544394795399712075443947957631
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00548753948753994194304256002424307840x7f921ff0c8000x7f91142357801310722545983255566412075443948033181120754439482019961207544394833479512075443948339050
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00568753948753994194304256002824320000x7f921ff0c7000x7f91142357c01310722082502675067212075443948395535120754439485575141207544394881511212075443948861280
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00588753948753994194304256002824329600x7f921ff0c6000x7f9114235800655361769242262188812075443948887770120754439490722311207544394932695012075443949375416
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00608753948753994194304256002424339200x7f921ff0c5000x7f91142358401310722490483179793612075443949399781120754439495853481207544394971750712075443949721068
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00628753948753994194304256002424348800x7f921ff0c4000x7f91142358801310722401583083663212075443949778094120754439499418261207544395007446612075443950078653
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00648753948753994194304256002424358400x7f921ff0c3000x7f91142358c01310722490723196059212075443950146178120754439503146241207544395044550312075443950449262
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00668753948753994194304256002824373120x7f921ff0ca000x7f91142359001310722052922626563212075443950506508120754439506690221207544395091974112075443950965782
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00688753948753994194304256002824382720x7f921ff0c9000x7f9114235940655361733882219633612075443950989766120754439511775001207544395143253812075443951478815
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00708753948753994194304256002424392320x7f921ff0c8000x7f91142359801310722453863140187212075443951505304120754439516845371207544395181317612075443951816903
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00728753948753994194304256002424401920x7f921ff0c7000x7f91142359c01310722447043128094412075443951875813120754439520395751207544395217157412075443952175440
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00748753948753994194304256002424411520x7f921ff0c6000x7f9114235a001310722302702956021612075443952243316120754439524056531207544395253573212075443952539436
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00768753948753994194304256002824426240x7f921ff0c5000x7f9114235a401310722130502727210412075443952596101120754439527568511207544395300405012075443953051458
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00788753948753994194304256002824435840x7f921ff0c4000x7f9114235a80655361765482262751212075443953075623120754439532581281207544395351172712075443953558029
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00808753948753994194304256002424445440x7f921ff0c3000x7f9114235ac01310722532263244452012075443953585190120754439537613261207544395389284512075443953896538
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00828753948753994194304256002424457600x7f921ff0ca000x7f9114235b001310722502443212573612075443953953173120754439541200441207544395425796312075443954262118
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00848753948753994194304256002424467200x7f921ff0c9000x7f9114235b401310722463223159115212075443954332909120754439544941221207544395462484112075443954628358
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00868753948753994194304256002824484480x7f921ff0c8000x7f9114235b801310722071742661199212075443954685875120754439548467601207544395510947812075443955156289
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00888753948753994194304256002824494080x7f921ff0c7000x7f9114235bc0655361998142563100812075443955183730120754439553606771207544395561779512075443955664133
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00908753948753994194304256002424503680x7f921ff0c6000x7f9114235c001310722423003106733612075443955687637120754439558670741207544395599555312075443955999366
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00928753948753994194304256002424515840x7f921ff0c5000x7f9114235c401310722483923175782412075443956056192120754439562174721207544395635059112075443956354095
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00948753948753994194304256002424525440x7f921ff0c4000x7f9114235c801310722712543493715212075443956422733120754439565840301207544395671347012075443956717200
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00968753948753994194304256002824542720x7f921ff0c3000x7f9114235cc01310722111082714293612075443956775248120754439569366681207544395719346712075443957239982
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00988753948753994194304256002824554880x7f921ff0ca000x7f9114235d00655361903642440404812075443957266742120754439574454661207544395770210412075443957748136
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001008753948753994194304256002424567040x7f921ff0c9000x7f9114235d401310722439523116372012075443957770898120754439579513831207544395808242212075443958086565
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001028753948753994194304256002424581760x7f921ff0c8000x7f9114235d801310722731723493584012075443958144493120754439583115411207544395845250012075443958456122
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001048753948753994194304256002424593920x7f921ff0c7000x7f9114235dc01310722458523162575212075443958525070120754439586868991207544395881585812075443958819998
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001068753948753994194304256002824613760x7f921ff0c6000x7f9114235e001310722513523221375212075443958876994120754439590428971207544395930609512075443959352187
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001088753948753994194304256002824625920x7f921ff0c5000x7f9114235e40655361980482537530412075443959376422120754439595579341207544395981345312075443959833933
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001108753948753994194304256002424638080x7f921ff0c4000x7f9114235e801310722560263272230412075443959884837120754439600536111207544396018369112075443960187540
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001128753948753994194304256002424652800x7f921ff0c3000x7f9114235ec01310722644883381470412075443960243764120754439604019301207544396054736912075443960551166
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001148753948753994194304256002424664960x7f921ff0ca000x7f9114235f001310722483883176363212075443960621857120754439607819271207544396091392712075443960917737
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001168753948753994194304256002824684800x7f921ff0c9000x7f9114235f401310722475703175580012075443960974011120754439611425651207544396140688412075443961453482
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001188753948753994194304256002824696960x7f921ff0c8000x7f9114235f80655361722182201867212075443961478038120754439616579231207544396191168112075443961931691
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001208753948753994194304256002424709120x7f921ff0c7000x7f9114235fc01310722481323177240812075443961982075120754439621508801207544396228479912075443962288635
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001228753948753994194304256002424723840x7f921ff0c6000x7f91142360001310722455003132394412075443962347063120754439625118381207544396265007712075443962653954
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001248753948753994194304256002424736000x7f921ff0c5000x7f91142360401310722671163411340012075443962722942120754439628828761207544396301663512075443963020935
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001268753948753994194304256002824758400x7f921ff0c4000x7f91142360801310722074882654074412075443963078953120754439632441541207544396350655312075443963552744
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001288753948753994194304256002824770560x7f921ff0c3000x7f91142360c0655361707342178065612075443963574945120754439637615911207544396405327012075443964099600
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001308753948753994194304256002424782720x7f921ff0ca000x7f91142361001310722290182908476012075443964125338120754439643070281207544396443982812075443964443750
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001328753948753994194304256002424800000x7f921ff0c9000x7f91142361401310722098442684159212075443964499884120754439646612661207544396480670612075443964810822
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001348753948753994194304256002424812160x7f921ff0c8000x7f91142361801310722459823144928012075443964878828120754439650460641207544396517726412075443965181361
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001368753948753994194304256002824834560x7f921ff0c7000x7f91142361c01310722149662752172012075443965241132120754439653974221207544396566126112075443965707138
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001388753948753994194304256002824849280x7f921ff0c6000x7f9114236200655361991802541505612075443965733677120754439659142201207544396617085812075443966220352
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001408753948753994194304256002424864000x7f921ff0c5000x7f91142362401310722482243166180812075443966248895120754439664254171207544396655341612075443966557157
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001428753948753994194304256002424881280x7f921ff0c4000x7f91142362801310722227842851440812075443966613682120754439667750151207544396692461412075443966928588
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001448753948753994194304256002424896000x7f921ff0c3000x7f91142362c01310722461103158410412075443967020128120754439671830131207544396731709212075443967320917
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001468753948753994194304256002824920960x7f921ff0ca000x7f91142363001310722038662626458412075443967379355120754439675393311207544396780636912075443967852966
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001488753948753994194304256002824935680x7f921ff0c9000x7f9114236340655361828522336971212075443967875427120754439680764481207544396833324612075443968379955
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001508753948753994194304256002424950400x7f921ff0c8000x7f91142363801310722486763176034412075443968406895120754439685839651207544396871612412075443968719987
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001528753948753994194304256002424967680x7f921ff0c7000x7f91142363c01310722476303166961612075443968776261120754439689348431207544396909276212075443969096677
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001548753948753994194304256002424982400x7f921ff0c6000x7f91142364001310722445683156565612075443969169633120754439693343611207544396946540012075443969469289
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015687539487539941943042560028241007360x7f921ff0c5000x7f91142364401310722011262571506412075443969524913120754439696837991207544396994667812075443969992322
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015887539487539941943042560028241022080x7f921ff0c4000x7f9114236480655361701682172260812075443970016426120754439702028361207544397045883512075443970506337
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016087539487539941943042560024241036800x7f921ff0c3000x7f91142364c01310722464703173831212075443970532626120754439707073141207544397084587312075443970849545
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016287539487539941943042560024241056640x7f921ff0ca000x7f91142365001310722498503190496812075443970904176120754439710705121207544397123547112075443971239549
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016487539487539941943042560024241071360x7f921ff0c9000x7f91142365401310722448043142991212075443971305282120754439714671501207544397160010912075443971603836
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016687539487539941943042560028241098880x7f921ff0c8000x7f91142365801310722089902670768812075443971660281120754439718231481207544397208618612075443972133631
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016887539487539941943042560028241113600x7f921ff0c7000x7f91142365c0655361777142276577612075443972160170120754439723372251207544397259130312075443972638058
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017087539487539941943042560024241128320x7f921ff0c6000x7f91142366001310722428263124396012075443972665499120754439728399421207544397297514112075443972979092
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017287539487539941943042560024241148160x7f921ff0c5000x7f91142366401310722489363185812812075443973044213120754439732025001207544397337657912075443973380649
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017487539487539941943042560024241162880x7f921ff0c4000x7f91142366801310722474663181228012075443973450128120754439736087381207544397374185712075443973745787
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017687539487539941943042560028241190400x7f921ff0c3000x7f91142366c01310722092942676392812075443973804216120754439739605761207544397422009512075443974248091
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017887539487539941943042560028241207680x7f921ff0ca000x7f9114236700655361781862278136012075443974288285120754439744533731207544397470409212075443974727442
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018087539487539941943042560024241224960x7f921ff0c9000x7f91142367401310722289302943583212075443974771674120754439749322511207544397506457012075443975068776
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018287539487539941943042560024241247360x7f921ff0c8000x7f91142367801310722417143113250412075443975128036120754439752888891207544397547240812075443975478668
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018487539487539941943042560024241264640x7f921ff0c7000x7f91142367c01310722471343179428812075443975549920120754439757098461207544397585032612075443975854276
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018687539487539941943042560020241279360x7f921ff0c6000x7f91142368001310722398383063372812075443975913205120754439760730451207544397633816312075443976362460
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018887539487539941943042560028241296640x7f921ff0c5000x7f9114236840655361747882236943212075443976405210120754439765650421207544397682328012075443976844526
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019087539487539941943042560024241313920x7f921ff0c4000x7f91142368801310722457763154745612075443976897244120754439770600791207544397719447812075443977198554
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019287539487539941943042560024241336320x7f921ff0c3000x7f91142368c01310722663843405713612075443977258235120754439774213571207544397761463612075443977636849
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019487539487539941943042560024241353600x7f921ff0ca000x7f91142369001310722480483169168812075443977688875120754439778480751207544397798183412075443977985937
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019687539487539941943042560020241368320x7f921ff0c9000x7f91142369401310722476123184327212075443978045909120754439782079131207544397849239112075443978518948
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019887539487539941943042560028241385600x7f921ff0c8000x7f9114236980655361902522437580012075443978562329120754439787235901207544397897574912075443979000042
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020087539487539941943042560024241402880x7f921ff0c7000x7f91142369c01310722434543092832812075443979049494120754439792147871207544397934710712075443979350994
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020287539487539941943042560024241427840x7f921ff0c6000x7f9114236a001310722564323272989612075443979408371120754439795696661207544397977974412075443979802533
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020487539487539941943042560024241447680x7f921ff0c5000x7f9114236a401310722441443116592012075443979860882120754439800299831207544398017014212075443980174465
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020687539487539941943042560020241457280x7f921ff0c4000x7f9114236a801310722491523177594412075443980235187120754439803968611207544398070533912075443980728685
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020887539487539941943042560028241477120x7f921ff0c3000x7f9114236ac0655361695242164473612075443980771023120754439809302981207544398118501712075443981210961
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021087539487539941943042560024241496960x7f921ff0ca000x7f9114236b001310722451103134569612075443981258870120754439814307751207544398156645512075443981570559
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021287539487539941943042560024241521920x7f921ff0c9000x7f9114236b401310722465943141885612075443981626934120754439817832541207544398201253212075443982036225
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021487539487539941943042560024241541760x7f921ff0c8000x7f9114236b801310722474023155012812075443982094623120754439822629311207544398240309012075443982407174
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021687539487539941943042560020241556480x7f921ff0c7000x7f9114236bc01310722515203212315212075443982465522120754439826242091207544398295556712075443982978265
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021887539487539941943042560028241576320x7f921ff0c6000x7f9114236c00655361715462183525612075443983027066120754439831874061207544398343572512075443983461864
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022087539487539941943042560024241596160x7f921ff0c5000x7f9114236c401310722418323093340812075443983503742120754439836619631207544398380212312075443983806314
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022287539487539941943042560024241623680x7f921ff0c4000x7f9114236c801310722314842980922412075443983863781120754439840291611207544398427396012075443984297287
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022487539487539941943042560024241646080x7f921ff0c3000x7f9114236cc01310722650463367826412075443984353000120754439845192391207544398466035812075443984664629
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022687539487539941943042560020241663360x7f921ff0ca000x7f9114236d001310722491883198940812075443984722868120754439848823821207544398525822112075443985284792
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022887539487539941943042560028241685760x7f921ff0c9000x7f9114236d40655361754682238864012075443985325067120754439854900591207544398574685812075443985767739
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023087539487539941943042560024241708160x7f921ff0c8000x7f9114236d801310722726803475216812075443985811801120754439859737371207544398611149712075443986114414
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023287539487539941943042560024241740800x7f921ff0c7000x7f9114236dc01310722503443180372812075443986171951120754439863359761207544398661613512075443986638438
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023487539487539941943042560024241765760x7f921ff0c6000x7f9114236e001310722461663132296812075443986693911120754439868567741207544398699837412075443987005540
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023687539487539941943042560020241777920x7f921ff0c5000x7f9114236e401310722485303179737612075443987060241120754439872220531207544398764701112075443987669454
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023887539487539941943042560028241802880x7f921ff0c4000x7f9114236e80655361833702345812812075443987718164120754439878806101207544398814141012075443988163632
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024087539487539941943042560024241827840x7f921ff0c3000x7f9114236ec01310722443143113793612075443988205530120754439883682891207544398850892812075443988511539
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024287539487539941943042560024241863040x7f921ff0ca000x7f9114236f001310722424163120408012075443988568414120754439887289281207544398904460612075443989067021
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024487539487539941943042560024241893120x7f921ff0c9000x7f9114236f401310722462023166825612075443989123105120754439892900461207544398944204512075443989444573
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024687539487539941943042560020241907840x7f921ff0c8000x7f9114236f801310722608803339555212075443989501529120754439896599641207544399017724212075443990199987
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024887539487539941943042560028241937920x7f921ff0c7000x7f9114236fc0655361754222248936012075443990249569120754439904159621207544399071548112075443990736774
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025087539487539941943042560024241968000x7f921ff0c6000x7f91142370001310722506843189998412075443990783581120754439909511601207544399110603912075443991108465
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025287539487539941943042560024242010880x7f921ff0c5000x7f91142370401310722451563128044012075443991166944120754439913333981207544399171867712075443991743766
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025487539487539941943042560024242046080x7f921ff0c4000x7f91142370801310722498363223720812075443991799399120754439919655561207544399214171612075443992144751
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025687539487539941943042560020242060800x7f921ff0c3000x7f91142370c01310722460003151156812075443992207447120754439923727551207544399299627312075443993019156
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025887539487539941943042560028242096000x7f921ff0ca000x7f9114237100655361680242161458412075443993061404120754439932266721207544399355755112075443993578505
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026087539487539941943042560024242131200x7f921ff0c9000x7f91142371401310722516323211236812075443993622688120754439937842701207544399396378912075443993966216
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026287539487539941943042560024242181760x7f921ff0c8000x7f91142371801310722529303219904812075443994028271120754439941892291207544399464602712075443994670785
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026487539487539941943042560024242222080x7f921ff0c7000x7f91142371c01310722438983117949612075443994726028120754439948921061207544399509210512075443995117025
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026687539487539941943042560020242239360x7f921ff0c6000x7f91142372001310722448503123394412075443995160285120754439953258651207544399603066212075443996053505
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026887539487539941943042560028242279680x7f921ff0c5000x7f9114237240655361714142199084012075443996097938120754439962610611207544399663482012075443996656005
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027087539487539941943042560024242320000x7f921ff0c4000x7f91142372801310722553463273776812075443996698814120754439968575391207544399706121912075443997082337
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027287539487539941943042560024242378240x7f921ff0c3000x7f91142372c01310722422843099669612075443997125898120754439972887381207544399781577612075443997836459
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027487539487539941943042560024242423680x7f921ff0ca000x7f91142373001310722438423114028012075443997893755120754439980749751207544399829913412075443998324936
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027687539487539941943042560020242435840x7f921ff0c9000x7f91142373401310722435983108449612075443998369329120754439985352931207544399933481112075443999357445
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027887539487539941943042560028242481280x7f921ff0c8000x7f9114237380655361658662134524012075443999400095120754439995640901207544399998408812075444000015037
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028087539487539941943042560024242526720x7f921ff0c7000x7f91142373c01310722433443122417612075444000054320120754440002202481207544400044792712075444000473509
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028287539487539941943042560024242592640x7f921ff0c6000x7f91142374001310722458843152276012075444000523032120754440006898461207544400128728412075444001310856
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028487539487539941943042560024242648320x7f921ff0c5000x7f91142374401310722448923120757612075444001364495120754440015314431207544400180088212075444001822757
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028687539487539941943042560020242663040x7f921ff0c4000x7f91142374801310722435303124022412075444001866628120754440020381611207544400302359812075444003084692
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028887539487539941943042560028242718720x7f921ff0c3000x7f91142374c0655361686222171808012075444003156035120754440036193161207544400414955412075444004199103
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029087539487539941943042560024242774400x7f921ff0ca000x7f91142375001310722460903152547212075444004266258120754440045026731207544400477547212075444004824736
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029287539487539941943042560012242799360x7f921ff0c9000x7f91142375401310722594263340664812075444004888394120754440051412301207544400588042812075444005929309
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029487539487539941943042560024242865280x7f921ff0c8000x7f91142375801310722257482867187212075444006013826120754440062501871207544400656746512075444006615604
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029687539487539941943042560020242880000x7f921ff0c7000x7f91142375c01310722561843290664012075444006669464120754440069065041207544400807850012075444008126091
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029887539487539941943042560032242945920x7f921ff0c6000x7f9114237600655361666282117983212075444008188247120754440084228191207544400903209712075444009080114
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030087539487539941943042560024243011840x7f921ff0c5000x7f91142376401310722451203120161612075444009136760120754440093792961207544400970041512075444009748977
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030287539487539941943042560012243049600x7f921ff0c4000x7f91142376801310722629503371453612075444009802797120754440100476131207544401092697012075444010975206
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030487539487539941943042560024243136000x7f921ff0c3000x7f91142376c01310722484883207099212075444011060976120754440113005691207544401171112812075444011760185
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030687539487539941943042560020243148160x7f921ff0ca000x7f91142377001310722580483283563212075444011822651120754440120749661207544401362376112075444013672910
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030887539487539941943042560020243175680x7f921ff0c9000x7f9114237740655361816402342097612075444013727161120754440139668001207544401476199712075444014810224
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031087539487539941943042560012243203200x7f921ff0c8000x7f91142377801310722436343110232812075444014872589120754440151290361207544401554343412075444015591716
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031287539487539941943042560012243240960x7f921ff0c7000x7f91142377c01310722459963142520012075444015644704120754440158840731207544401704262912075444017090722
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031487539487539941943042560012243288960x7f921ff0c6000x7f91142378001310722604803344280812075444017166312120754440174064681207544401819206512075444018241240
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031687539487539941943042560020243301120x7f921ff0c5000x7f91142378401310722441263126571212075444018297845120754440185386241207544402158661312075444021636300
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031887539487539941943042560020243328640x7f921ff0c4000x7f9114237880655361894482421486412075444021694057120754440219354121207544402347716712075444023525400
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032087539487539941943042560012243356160x7f921ff0c3000x7f91142378c01310722578823290632812075444023587977120754440238274051207544402461668312075444024665840
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032287539487539941943042560012243393920x7f921ff0ca000x7f91142379001310722421623104700812075444024719620120754440249683611207544402725043412075444027300647
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032487539487539941943042560012243441920x7f921ff0c9000x7f91142379401310722482523185848012075444027377880120754440276161921207544402915122712075444029199876
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032687539487539941943042560020243454080x7f921ff0c8000x7f91142379801310722520543217328012075444029255940120754440294928261207544403554576512075444035624747
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032887539487539941943042560020243481600x7f921ff0c7000x7f91142379c0655361640542097684012075444035655373120754440359782431207544403901951312075444039096529
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033087539487539941943042560012243509120x7f921ff0c6000x7f9114237a001310722557123275384012075444039127496120754440394455911207544404098526612075444041034170
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332875394875399419430425600122400x7f921ff0c5000x7f9114237a401310722605903345766412075444041094792120754440413299051207544404585820912075444045907006