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

43 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_VMEMSQ_INST_LEVEL_VMEMSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000747934747939335544322560083264640x00x7fe2d6a04180104857611096515142009772012073197371357776120731976117777121207319761210299012073197612215562
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00274793474793932768256002424124800x00x7fe2d6a3510040961123411438537612073197626636267120731976269380011207319762694456112073197626949650
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0047479347479394194304256002424129280x7fe3e26d09000x7fe2d6a3514052428811212591143525561612073197627020481120731976272365591207319762737415912073197627378076
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0067479347479394194304256003624136320x7fe3e26d08000x7fe2d6a3518052428812581433161044471212073197627448026120731976276152781207319762786743612073197627935912
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0087479347479394194304256002824140800x7fe3e26d07000x7fe2d6a351c052428814324548183349210412073197627967661120731976281563951207319762840791412073197628477489
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00107479347479394194304256002424145280x7fe3e26d06000x7fe2d6a3520052428811593738148402829212073197628502375120731976286851931207319762881991212073197628823452
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00127479347479394194304256002424149760x7fe3e26d05000x7fe2d6a3524052428812315750157629854412073197628866191120731976290480711207319762917975012073197629183200
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00147479347479394194304256002424154240x7fe3e26d04000x7fe2d6a3528052428813325288170565074812073197629264140120731976294368691207319762956486912073197629568756
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00167479347479394194304256002824161280x7fe3e26d03000x7fe2d6a352c052428812835714164290422012073197629620062120731976297911081207319763004390612073197630086659
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00187479347479394194304256002824168320x7fe3e26d0a000x7fe2d6a3530052428814318433183273532412073197630111124120731976302923851207319763054134412073197630608719
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00207479347479394194304256002424175360x7fe3e26d09000x7fe2d6a3534052428812116124155083526412073197630632803120731976308176631207319763095062212073197630954090
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00227479347479394194304256002424182400x7fe3e26d08000x7fe2d6a3538052428812218697156396338812073197631007700120731976311802211207319763131334112073197631317255
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00247479347479394194304256002424189440x7fe3e26d07000x7fe2d6a353c052428813446116172100446812073197631378489120731976315407001207319763166757912073197631671053
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00267479347479394194304256002824199040x7fe3e26d06000x7fe2d6a3540052428813451240172173094812073197631718531120731976318888581207319763214149712073197632211757
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00287479347479394194304256002824206080x7fe3e26d05000x7fe2d6a3544052428813645516174654058012073197632237736120731976324152551207319763266853412073197632735490
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00307479347479394194304256002424213120x7fe3e26d04000x7fe2d6a3548052428812672645162214780012073197632762190120731976329398931207319763306949212073197633073128
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00327479347479394194304256002424220160x7fe3e26d03000x7fe2d6a354c052428811887780152169968812073197633121447120731976332914111207319763342517112073197633428799
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00347479347479394194304256002424227200x7fe3e26d0a000x7fe2d6a3550052428812791971163728225212073197633489942120731976336482101207319763377764912073197633781264
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00367479347479394194304256002824236800x7fe3e26d09000x7fe2d6a3554052428814345063183616781212073197633829974120731976339968481207319763425156712073197634296431
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00387479347479394194304256002824243840x7fe3e26d08000x7fe2d6a3558052428813701027175366191212073197634319614120731976345053261207319763475652512073197634823300
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00407479347479394194304256002424250880x7fe3e26d07000x7fe2d6a355c052428811344749145208593212073197634849719120731976350397231207319763517492312073197635178590
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00427479347479394194304256002424257920x7fe3e26d06000x7fe2d6a3560052428812472074159643633212073197635228893120731976353939621207319763552580112073197635529692
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00447479347479394194304256002424264960x7fe3e26d05000x7fe2d6a3564052428812827671164192526412073197635591146120731976357510801207319763588084012073197635884602
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00467479347479394194304256002824277120x7fe3e26d04000x7fe2d6a3568052428813913086178087622012073197635936548120731976361046791207319763635331712073197636423974
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00487479347479394194304256002824284160x7fe3e26d03000x7fe2d6a356c052428814010039179329720012073197636447608120731976366273961207319763688131512073197636948919
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00507479347479394194304256002424291200x7fe3e26d0a000x7fe2d6a3570052428811848617151659502012073197636976050120731976371577941207319763728995312073197637293660
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00527479347479394194304256002424300800x7fe3e26d09000x7fe2d6a3574052428812692558162462919612073197637341729120731976375126721207319763764371112073197637647487
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00547479347479394194304256002424307840x7fe3e26d08000x7fe2d6a3578052428813151693168330515612073197637708170120731976378681901207319763799667012073197638005202
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00567479347479394194304256002824320000x7fe3e26d07000x7fe2d6a357c052428813984724179006435212073197638049755120731976382237091207319763847874812073197638547029
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00587479347479394194304256002824329600x7fe3e26d06000x7fe2d6a3580052428813980321178945757212073197638570262120731976387509061207319763900450512073197639073136
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00607479347479394194304256002424339200x7fe3e26d05000x7fe2d6a3584052428811951647152988594012073197639100808120731976392841841207319763941650312073197639420081
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00627479347479394194304256002424348800x7fe3e26d04000x7fe2d6a3588052428812177599155870495612073197639468741120731976396334621207319763976626212073197639770041
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00647479347479394194304256002424358400x7fe3e26d03000x7fe2d6a358c052428813462484172326301612073197639830594120731976399886611207319764011602012073197640120032
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00667479347479394194304256002824373120x7fe3e26d0a000x7fe2d6a3590052428812512802160160000812073197640174092120731976403337791207319764063089812073197640700089
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00687479347479394194304256002824382720x7fe3e26d09000x7fe2d6a3594052428813533162173218562812073197640725617120731976408996961207319764115153512073197641220386
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00707479347479394194304256002424392320x7fe3e26d08000x7fe2d6a3598052428812488852159856188812073197641243850120731976414252941207319764155569312073197641559045
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00727479347479394194304256002424401920x7fe3e26d07000x7fe2d6a359c052428811884379152118268812073197641608658120731976417814521207319764191649212073197641920277
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00747479347479394194304256002424411520x7fe3e26d06000x7fe2d6a35a0052428813400335171517820812073197641982021120731976421508911207319764227841012073197642282460
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00767479347479394194304256002824426240x7fe3e26d05000x7fe2d6a35a4052428814158642181227941612073197642333314120731976425059291207319764275568812073197642823014
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00787479347479394194304256002824435840x7fe3e26d04000x7fe2d6a35a8052428814115848180680325612073197642848782120731976430281671207319764328400512073197643353209
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00807479347479394194304256002424445440x7fe3e26d03000x7fe2d6a35ac052428812176907155854617212073197643381602120731976435563241207319764368816412073197643691949
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00827479347479394194304256002424457600x7fe3e26d0a000x7fe2d6a35b0052428811804041151095977212073197643741761120731976439035231207319764403776212073197644041809
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00847479347479394194304256002424467200x7fe3e26d09000x7fe2d6a35b4052428812819279164077872812073197644103403120731976442651211207319764439440012073197644398121
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00867479347479394194304256002824484480x7fe3e26d08000x7fe2d6a35b8052428813620372174339468012073197644449456120731976446105591207319764487055812073197644938986
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00887479347479394194304256002824494080x7fe3e26d07000x7fe2d6a35bc052428814233310182187684412073197644963702120731976451446371207319764539695612073197645467528
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00907479347479394194304256002424503680x7fe3e26d06000x7fe2d6a35c0052428812296472157397951612073197645489969120731976456710341207319764580303412073197645806778
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00927479347479394194304256002424515840x7fe3e26d05000x7fe2d6a35c4052428811563011148001848812073197645857683120731976460289531207319764616527212073197646169121
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00947479347479394194304256002424525440x7fe3e26d04000x7fe2d6a35c8052428812786714163678012812073197646232189120731976463910311207319764652143112073197646525353
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00967479347479394194304256002824542720x7fe3e26d03000x7fe2d6a35cc052428812997975166368315212073197646574485120731976467390301207319764699854812073197647068362
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00987479347479394194304256002824554880x7fe3e26d0a000x7fe2d6a35d0052428813072767167325694412073197647090744120731976472703871207319764752334612073197647591514
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001007479347479394194304256002424567040x7fe3e26d09000x7fe2d6a35d4052428813240905169476231212073197647613365120731976477971051207319764792510412073197647928881
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001027479347479394194304256002424581760x7fe3e26d08000x7fe2d6a35d8052428810393391133036380412073197647978083120731976481443031207319764828142212073197648285484
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001047479347479394194304256002424593920x7fe3e26d07000x7fe2d6a35dc052428812165310155723259212073197648345946120731976485043011207319764863566112073197648639431
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001067479347479394194304256002824613760x7fe3e26d06000x7fe2d6a35e0052428812200329156169246012073197648688232120731976488535801207319764911261912073197649157544
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001087479347479394194304256002824625920x7fe3e26d05000x7fe2d6a35e4052428813575928173770862412073197649179846120731976493678171207319764961901612073197649661711
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001107479347479394194304256002424638080x7fe3e26d04000x7fe2d6a35e8052428812991656166286903212073197649689032120731976498666951207319764999597512073197649999739
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001127479347479394194304256002424652800x7fe3e26d03000x7fe2d6a35ec05242889347798119653728012073197650049542120731976502188541207319765035773312073197650361531
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001147479347479394194304256002424664960x7fe3e26d0a000x7fe2d6a35f0052428812902877165162261612073197650424037120731976505817321207319765071181112073197650715629
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001167479347479394194304256002824684800x7fe3e26d09000x7fe2d6a35f4052428813336615170710570812073197650764530120731976509284501207319765119244912073197651263417
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001187479347479394194304256002824696960x7fe3e26d08000x7fe2d6a35f8052428813332193170651835212073197651286400120731976514638081207319765171804712073197651785708
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001207479347479394194304256002424709120x7fe3e26d07000x7fe2d6a35fc052428811936218152785050412073197651811115120731976519820451207319765211564512073197652119678
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001227479347479394194304256002424723840x7fe3e26d06000x7fe2d6a360005242888022050102683661212073197652169982120731976523324441207319765247180312073197652475720
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001247479347479394194304256002424736000x7fe3e26d05000x7fe2d6a3604052428811550985147850390412073197652536623120731976526908421207319765282492212073197652828655
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001267479347479394194304256002824758400x7fe3e26d04000x7fe2d6a3608052428812969609166013329612073197652878318120731976530497211207319765331371912073197653364371
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001287479347479394194304256002824770560x7fe3e26d03000x7fe2d6a360c052428813411485171670753612073197653387644120731976535676381207319765382219712073197653872886
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001307479347479394194304256002424782720x7fe3e26d0a000x7fe2d6a3610052428812595176161218109212073197653897842120731976540716361207319765420283512073197654206816
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001327479347479394194304256002424800000x7fe3e26d09000x7fe2d6a36140524288693193288718546812073197654256418120731976544257141207319765457083412073197654574710
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001347479347479394194304256002424812160x7fe3e26d08000x7fe2d6a3618052428811884893152125719212073197654635793120731976547927521207319765492539212073197654929038
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001367479347479394194304256002824834560x7fe3e26d07000x7fe2d6a361c052428811203591143402308812073197654978310120731976551437911207319765540651012073197655457129
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001387479347479394194304256002824849280x7fe3e26d06000x7fe2d6a3620052428813234978169411680812073197655479501120731976556565891207319765591322712073197655961126
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001407479347479394194304256002424864000x7fe3e26d05000x7fe2d6a3624052428811792877150949604012073197655987655120731976561665061207319765630042612073197656304434
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001427479347479394194304256002424881280x7fe3e26d04000x7fe2d6a36280524288527102667467270012073197656353174120731976565314641207319765668122412073197656684891
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001447479347479394194304256002424896000x7fe3e26d03000x7fe2d6a362c052428810756148137669422812073197656763717120731976569204231207319765705770212073197657061761
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001467479347479394194304256002824920960x7fe3e26d0a000x7fe2d6a3630052428811533426147628050812073197657112455120731976572834611207319765755018012073197657602035
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001487479347479394194304256002824935680x7fe3e26d09000x7fe2d6a3634052428813971451178833700412073197657625078120731976578034591207319765805577712073197658106692
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001507479347479394194304256002424950400x7fe3e26d08000x7fe2d6a3638052428812249143156786969212073197658131248120731976583080961207319765843993612073197658443799
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001527479347479394194304256002424967680x7fe3e26d07000x7fe2d6a363c0524288467833559875816412073197658492199120731976586509751207319765880841412073197658812193
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001547479347479394194304256002424982400x7fe3e26d06000x7fe2d6a3640052428810574531135346077212073197658873688120731976590346531207319765917209212073197659176150
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015674793474793941943042560028241007360x7fe3e26d05000x7fe2d6a3644052428811132774142497555612073197659225441120731976593949711207319765965673012073197659705934
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015874793474793941943042560028241022080x7fe3e26d04000x7fe2d6a3648052428812652006161940521612073197659728386120731976599018491207319766015960812073197660211313
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016074793474793941943042560024241036800x7fe3e26d03000x7fe2d6a364c052428811783419150826953212073197660238403120731976604117671207319766054488612073197660548860
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016274793474793941943042560024241056640x7fe3e26d0a000x7fe2d6a36500524288414373653030243212073197660598122120731976607653651207319766093080412073197660934727
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016474793474793941943042560024241071360x7fe3e26d09000x7fe2d6a3654052428812032592154008785612073197660996081120731976611608831207319766129480312073197661298934
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016674793474793941943042560028241098880x7fe3e26d08000x7fe2d6a3658052428810457763133858658012073197661340982120731976615114421207319766177144012073197661820032
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016874793474793941943042560028241113600x7fe3e26d07000x7fe2d6a365c052428814157464181218555212073197661844397120731976620227991207319766227591812073197662326844
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017074793474793941943042560024241128320x7fe3e26d06000x7fe2d6a3660052428810614211135863291612073197662354185120731976625279171207319766266727612073197662671284
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017274793474793941943042560024241148160x7fe3e26d05000x7fe2d6a36640524288355138345464612012073197662719403120731976628832751207319766305703412073197663061148
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017474793474793941943042560024241162880x7fe3e26d04000x7fe2d6a3668052428810367386132701544812073197663121811120731976632787931207319766341895312073197663422921
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017674793474793941943042560028241190400x7fe3e26d03000x7fe2d6a366c05242887844350100405723612073197663470769120731976636378321207319766390087112073197663949779
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017874793474793941943042560028241207680x7fe3e26d0a000x7fe2d6a3670052428813967361178781928412073197663971430120731976641591091207319766441478812073197664466490
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018074793474793941943042560024241224960x7fe3e26d09000x7fe2d6a3674052428811909891152446052412073197664490454120731976646688671207319766480262612073197664806451
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018274793474793941943042560024241247360x7fe3e26d08000x7fe2d6a36780524288367146246982937612073197664856264120731976650251851207319766520758512073197665211975
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018474793474793941943042560024241264640x7fe3e26d07000x7fe2d6a367c052428811520716147462473612073197665273178120731976654295041207319766556486312073197665568728
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018674793474793941943042560020241279360x7fe3e26d06000x7fe2d6a36800524288414242653020234412073197665616887120731976657803821207319766607862112073197666128197
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018874793474793941943042560028241296640x7fe3e26d05000x7fe2d6a3684052428812518770160240994012073197666151240120731976663283791207319766658453812073197666633436
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019074793474793941943042560024241313920x7fe3e26d04000x7fe2d6a3688052428811471812146846718812073197666655196120731976668283771207319766696373612073197666967697
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019274793474793941943042560024241336320x7fe3e26d03000x7fe2d6a368c0524288368229847143272412073197667022158120731976671862951207319766737813512073197667429265
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019474793474793941943042560024241353600x7fe3e26d0a000x7fe2d6a3690052428812371030158346654412073197667463088120731976676243731207319766775621312073197667759999
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019674793474793941943042560020241368320x7fe3e26d09000x7fe2d6a36940524288299185838299518412073197667807838120731976679749321207319766825973012073197668311514
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019874793474793941943042560028241385600x7fe3e26d08000x7fe2d6a3698052428812919876165373880412073197668328415120731976685122091207319766877060812073197668818807
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020074793474793941943042560024241402880x7fe3e26d07000x7fe2d6a369c052428811021326141070374412073197668846107120731976690214871207319766915796612073197669162255
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020274793474793941943042560024241427840x7fe3e26d06000x7fe2d6a36a00524288383931649143138812073197669211246120731976693773251207319766958740412073197669636115
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020474793474793941943042560024241447680x7fe3e26d05000x7fe2d6a36a4052428810897125139487696412073197669672803120731976698296431207319766996500312073197669968723
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020674793474793941943042560020241457280x7fe3e26d04000x7fe2d6a36a80524288254510432586163212073197670015731120731976701875621207319767049508012073197670519697
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020874793474793941943042560028241477120x7fe3e26d03000x7fe2d6a36ac052428812690051162425467612073197670567035120731976707254791207319767098227812073197671030105
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021074793474793941943042560024241496960x7fe3e26d0a000x7fe2d6a36b0052428810378914132845276412073197671056474120731976712305971207319767137011612073197671373924
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021274793474793941943042560024241521920x7fe3e26d09000x7fe2d6a36b40524288342899943893472812073197671422525120731976715883551207319767181603412073197671863364
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021474793474793941943042560024241541760x7fe3e26d08000x7fe2d6a36b8052428812100457154886628412073197671899110120731976720723531207319767220659212073197672210649
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021674793474793941943042560020241556480x7fe3e26d07000x7fe2d6a36bc0524288246334031532316012073197672258508120731976724262711207319767275699012073197672805294
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021874793474793941943042560028241576320x7fe3e26d06000x7fe2d6a36c0052428813245281169536295212073197672830120120731976730019491207319767326146712073197673310262
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022074793474793941943042560024241596160x7fe3e26d05000x7fe2d6a36c405242889880791126479461612073197673333756120731976735105861207319767365122612073197673655173
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022274793474793941943042560024241623680x7fe3e26d04000x7fe2d6a36c80524288329363242154966812073197673703413120731976738656251207319767410978412073197674158438
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022474793474793941943042560024241646080x7fe3e26d03000x7fe2d6a36cc052428810373304132781088412073197674196980120731976743576221207319767449618212073197674499943
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022674793474793941943042560020241663360x7fe3e26d0a000x7fe2d6a36d00524288237808530437145212073197674548523120731976747123651207319767508820412073197675141344
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022874793474793941943042560028241685760x7fe3e26d09000x7fe2d6a36d4052428813496109172745790812073197675166551120731976753493221207319767560564112073197675653757
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023074793474793941943042560024241708160x7fe3e26d08000x7fe2d6a36d8052428810266134131412026012073197675684624120731976758502801207319767598867912073197675992095
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023274793474793941943042560024241740800x7fe3e26d07000x7fe2d6a36dc0524288340808643609254812073197676041838120731976762113981207319767649123712073197676542278
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023474793474793941943042560024241765760x7fe3e26d06000x7fe2d6a36e005242888102750103708407612073197676576972120731976767344361207319767687779512073197676881247
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023674793474793941943042560020241777920x7fe3e26d05000x7fe2d6a36e40524288233996029948857212073197676932673120731976771062741207319767755347212073197677605032
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023874793474793941943042560028241802880x7fe3e26d04000x7fe2d6a36e8052428810359981132604574412073197677629768120731976778038711207319767806259012073197678114339
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024074793474793941943042560024241827840x7fe3e26d03000x7fe2d6a36ec0524288762146797545786012073197678135959120731976783121891207319767845170912073197678455382
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024274793474793941943042560024241863040x7fe3e26d0a000x7fe2d6a36f00524288356587345648457612073197678505886120731976786713881207319767898642612073197679036001
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024474793474793941943042560024241893120x7fe3e26d09000x7fe2d6a36f40524288364500746649213212073197679073190120731976792325051207319767938530512073197679388887
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024674793474793941943042560020241907840x7fe3e26d08000x7fe2d6a36f80524288230197829462534812073197679437667120731976795961841207319768011298212073197680161723
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024874793474793941943042560028241937920x7fe3e26d07000x7fe2d6a36fc0524288739500194654175212073197680188523120731976803686611207319768066657912073197680714780
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025074793474793941943042560024241968000x7fe3e26d06000x7fe2d6a37000524288316145740486472412073197680743874120731976809236981207319768107761812073197681081261
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025274793474793941943042560024242010880x7fe3e26d05000x7fe2d6a37040524288345759044258269212073197681131535120731976813088171207319768169409512073197681744694
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025474793474793941943042560024242046080x7fe3e26d04000x7fe2d6a37080524288329445542178900812073197681783126120731976819387341207319768211601312073197682119691
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025674793474793941943042560020242060800x7fe3e26d03000x7fe2d6a370c0524288234713730038425212073197682169614120731976823304131207319768294209012073197682990319
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025874793474793941943042560028242096000x7fe3e26d0a000x7fe2d6a37100524288454586758197405212073197683020294120731976832019291207319768353264812073197683580645
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026074793474793941943042560024242131200x7fe3e26d09000x7fe2d6a37140524288349807444777141612073197683617554120731976837755271207319768399200612073197684040380
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026274793474793941943042560024242181760x7fe3e26d08000x7fe2d6a37180524288412486352789662412073197684070145120731976842412851207319768469680312073197684743957
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026474793474793941943042560024242222080x7fe3e26d07000x7fe2d6a371c0524288312600040007358412073197684782298120731976849424021207319768514240112073197685193232
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026674793474793941943042560020242239360x7fe3e26d06000x7fe2d6a37200524288231299329601186012073197685211325120731976853979201207319768610047712073197686150731
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026874793474793941943042560028242279680x7fe3e26d05000x7fe2d6a37240524288345285644198824812073197686178953120731976863591961207319768673007412073197686777756
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027074793474793941943042560024242320000x7fe3e26d04000x7fe2d6a37280524288327053641862834412073197686804235120731976869804731207319768718447212073197687234475
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027274793474793941943042560024242378240x7fe3e26d03000x7fe2d6a372c0524288443937456831875212073197687269339120731976874329511207319768795870912073197688011909
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027474793474793941943042560024242423680x7fe3e26d0a000x7fe2d6a37300524288308039839448886812073197688054859120731976882167881207319768843966712073197688489176
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027674793474793941943042560020242435840x7fe3e26d09000x7fe2d6a37340524288229997529440680412073197688511628120731976886867061207319768948606312073197689540329
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027874793474793941943042560028242481280x7fe3e26d08000x7fe2d6a37380524288361058846215982812073197689567029120731976897563021207319769019982012073197690251420
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028074793474793941943042560024242526720x7fe3e26d07000x7fe2d6a373c0524288308401839478862812073197690281426120731976904591791207319769068589812073197690735400
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028274793474793941943042560024242592640x7fe3e26d06000x7fe2d6a37400524288447378157255166412073197690760737120731976909326171207319769153053412073197691582203
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028474793474793941943042560024242648320x7fe3e26d05000x7fe2d6a37440524288333028442636332412073197691617639120731976917854131207319769205469212073197692107359
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028674793474793941943042560020242663040x7fe3e26d04000x7fe2d6a37480524288230801029557797212073197692131394120731976923068511207319769329132712073197693360848
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028874793474793941943042560028242718720x7fe3e26d03000x7fe2d6a374c0524288338510343316795212073197693383500120731976935639661207319769407836412073197694147910
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029074793474793941943042560024242774400x7fe3e26d0a000x7fe2d6a37500524288338979743377726412073197694175101120731976943452421207319769461836112073197694686231
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029274793474793941943042560012242799360x7fe3e26d09000x7fe2d6a37540524288221671928384222412073197694710165120731976948817201207319769561979712073197695691068
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029474793474793941943042560024242865280x7fe3e26d08000x7fe2d6a37580524288329341642145879612073197695730351120731976958903561207319769623419512073197696305610
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029674793474793941943042560020242880000x7fe3e26d07000x7fe2d6a375c0524288230162829458104812073197696331438120731976965153131207319769768538912073197697755243
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029874793474793941943042560032242945920x7fe3e26d06000x7fe2d6a37600524288318655340781818812073197697785049120731976979629871207319769857162512073197698641109
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030074793474793941943042560024243011840x7fe3e26d05000x7fe2d6a37640524288331074142367842812073197698666506120731976988468241207319769916506212073197699237257
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030274793474793941943042560012243049600x7fe3e26d04000x7fe2d6a37680524288219587628112888012073197699262724120731976994425011207319770032105812073197700391291
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030474793474793941943042560024243136000x7fe3e26d03000x7fe2d6a376c0524288331881142482616012073197700430684120731977005879361207319770102377512073197701093306
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030674793474793941943042560020243148160x7fe3e26d0a000x7fe2d6a37700524288232678429787061212073197701122430120731977012981731207319770284568712073197702915602
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030874793474793941943042560020243175680x7fe3e26d09000x7fe2d6a37740524288228841029293746012073197702945337120731977031276061207319770392168312073197703992863
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031074793474793941943042560012243203200x7fe3e26d08000x7fe2d6a37780524288216859227757534012073197704016427120731977041959211207319770461096012073197704681643
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031274793474793941943042560012243240960x7fe3e26d07000x7fe2d6a377c0524288229389629361942812073197704702402120731977048863191207319770604503412073197706115187
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031474793474793941943042560012243288960x7fe3e26d06000x7fe2d6a37800524288223271628595126012073197706155782120731977063163931207319770710246912073197707171930
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031674793474793941943042560020243301120x7fe3e26d05000x7fe2d6a37840524288264340533824557212073197707202046120731977073783081207319771042709512073197710497169
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031874793474793941943042560020243328640x7fe3e26d04000x7fe2d6a37880524288231631029655571212073197710526283120731977107040541207319771224452812073197712314536
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032074793474793941943042560012243356160x7fe3e26d03000x7fe2d6a378c0524288231085529577587612073197712346926120731977125267671207319771331764312073197713387269
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032274793474793941943042560012243393920x7fe3e26d0a000x7fe2d6a37900524288251719432227280012073197713409500120731977135917221207319771587411312073197715943990
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032474793474793941943042560012243441920x7fe3e26d09000x7fe2d6a37940524288244237331273325612073197715986899120731977161544321207319771769026512073197717761527
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032674793474793941943042560020243454080x7fe3e26d08000x7fe2d6a37980524288286423836652396012073197717790982120731977179678641207319772402159912073197724095135
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032874793474793941943042560020243481600x7fe3e26d07000x7fe2d6a379c0524288303282238823061612073197724120011120731977242995181207319772734094512073197727411527
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033074793474793941943042560012243509120x7fe3e26d06000x7fe2d6a37a00524288225777528906197212073197727441994120731977276223841207319772916109712073197729230998
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332747934747939419430425600122400x7fe3e26d05000x7fe2d6a37a40524288258273733054366412073197729260974120731977294366161207319773396427712073197734034153