Files
rocm-systems/tests/workloads/L2/mi200/SQ_INST_LEVEL_LDS.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

38 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_LDSSQ_INST_LEVEL_LDSSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000177005177005335544322560043241600x00x7ff270c0428000016811153277662168104438498771681130149894216811301584321
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00217700517700532768256001224138880x00x7ff270c23f8000016811306763779168113014989421681130689107716811306895955
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051770051770054194304256001224143360x7ff273ce53800x7ff270c23fc000016811306930984168113068910771681130725747616811307260064
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081770051770054194304256001624150400x7ff273ce52000x7ff270c2400000016811307296493168113072574761681130765907416811307661491
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111770051770054194304256001624154880x7ff273ce50800x7ff270c2404000016811307695540168113076590741681130805651216811308059099
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141770051770054194304256001224159360x7ff27164df000x7ff270c2408000016811308091058168113080565121681130836147116811308364060
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171770051770054194304256001224163840x7ff27164dd800x7ff270c240c000016811308396329168113083614711681130866355016811308665910
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201770051770054194304256001224170880x7ff27164dc000x7ff270c2410000016811308710329168113086635501681130895906816811308961401
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231770051770054194304256001624177920x7ff27164da800x7ff270c2414000016811308993680168113089590681681130934674716811309349209
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261770051770054194304256001624184960x7ff27164d9000x7ff270c2418000016811309381468168113093467471681130974226516811309744637
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291770051770054194304256001624192000x7ff27164d7800x7ff270c241c000016811309775466168113097422651681131005682416811310059167
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321770051770054194304256001624199040x7ff27164d6000x7ff270c2420000016811310102276168113100568241681131039858216811310401126
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351770051770054194304256001224206080x7ff273ce54800x7ff270c2424000016811310441355168113103985821681131069986116811310701657
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381770051770054194304256001624213120x7ff273ce53000x7ff270c2428000016811310734816168113106998611681131106097916811311062706
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411770051770054194304256001624220160x7ff273ce51800x7ff270c242c000016811311095295168113110609791681131142033816811311422185
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441770051770054194304256001624227200x7ff273ce50000x7ff270c2430000016811311454594168113114203381681131169377616811311695536
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471770051770054194304256001224234240x7ff27164de800x7ff270c2434000016811311727585168113116937761681131196705516811311968857
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501770051770054194304256001224241280x7ff27164dd000x7ff270c2438000016811312007846168113119670551681131224817416811312249999
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531770051770054194304256001624248320x7ff27164db800x7ff270c243c000016811312281498168113122481741681131261153216811312613287
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561770051770054194304256001624255360x7ff27164da000x7ff270c2440000016811312645886168113126115321681131296977116811312971506
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591770051770054194304256001224262400x7ff27164d8800x7ff270c2444000016811313003065168113129697711681131324913016811313251018
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621770051770054194304256001224269440x7ff27164d7000x7ff270c2448000016811313282897168113132491301681131352048916811313522319
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651770051770054194304256001224276480x7ff273ce55800x7ff270c244c000016811313561638168113135204891681131380320716811313804960
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681770051770054194304256001624286080x7ff273ce54000x7ff270c2450000016811313838409168113138032071681131417808616811314179919
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711770051770054194304256001624293120x7ff273ce52800x7ff270c2454000016811314211828168113141780861681131454560416811314547537
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741770051770054194304256001224300160x7ff273ce51000x7ff270c2458000016811314580016168113145456041681131481840316811314820199
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077177005177005419430425600824309760x7ff27164df800x7ff270c245c000016811314852188168113148184031681131509216216811315093960
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801770051770054194304256001224316800x7ff27164de000x7ff270c2460000016811315131879168113150921621681131536656016811315368431
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831770051770054194304256001624326400x7ff27164dc800x7ff270c2464000016811315399990168113153665601681131572655916811315728330
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861770051770054194304256001224336000x7ff27164db000x7ff270c2468000016811315759329168113157265591681131608863716811316090429
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891770051770054194304256001224345600x7ff27164d9800x7ff270c246c000016811316120828168113160886371681131636815616811316370050
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092177005177005419430425600824355200x7ff27164d8000x7ff270c2470000016811316401209168113163681561681131663903516811316640732
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951770051770054194304256001224362240x7ff27164d6800x7ff270c2474000016811316680691168113166390351681131691311416811316914863
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981770051770054194304256001224371840x7ff273ce55000x7ff270c2478000016811316945562168113169131141681131727359216811317275302
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011770051770054194304256001224381440x7ff273ce53800x7ff270c247c000016811317306241168113172735921681131763759116811317639231
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041770051770054194304256001224391040x7ff273ce52000x7ff270c2480000016811317669910168113176375911681131791198916811317913712
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107177005177005419430425600824403200x7ff273ce50800x7ff270c2484000016811317944971168113179119891681131820382816811318206163
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101770051770054194304256001224412800x7ff27164df000x7ff270c2488000016811318245392168113182038281681131848366716811318485394
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131770051770054194304256001224422400x7ff27164dd800x7ff270c248c000016811318515723168113184836671681131884670516811318848513
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161770051770054194304256001224432000x7ff27164dc000x7ff270c2490000016811318879552168113188467051681131921294416811319214642
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119177005177005419430425600824441600x7ff27164da800x7ff270c2494000016811319245561168113192129441681131948766316811319489453
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221770051770054194304256001224453760x7ff27164d9000x7ff270c2498000016811319519492168113194876631681131976222116811319764014
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251770051770054194304256001224463360x7ff27164d7800x7ff270c249c000016811319801443168113197622211681132003582016811320037586
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281770051770054194304256001224475520x7ff27164d6000x7ff270c24a0000016811320067755168113200358201681132039693916811320398795
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311770051770054194304256001224485120x7ff273ce54800x7ff270c24a4000016811320429924168113203969391681132075917716811320760983
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134177005177005419430425600824494720x7ff273ce53000x7ff270c24a8000016811320792012168113207591771681132103261616811321034415
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371770051770054194304256001224506880x7ff273ce51800x7ff270c24ac000016811321065644168113210326161681132130621516811321308026
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401770051770054194304256001224516480x7ff273ce50000x7ff270c24b0000016811321346285168113213062151681132157901316811321580808
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431770051770054194304256001224528640x7ff27164de800x7ff270c24b4000016811321611047168113215790131681132193981216811321941576
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461770051770054194304256001224540800x7ff27164dd000x7ff270c24b8000016811321972716168113219398121681132231197016811322313945
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149177005177005419430425600824552960x7ff27164db800x7ff270c24bc000016811322344194168113223119701681132259228916811322594016
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521770051770054194304256001224567680x7ff27164da000x7ff270c24c0000016811322625035168113225922891681132286940816811322871297
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551770051770054194304256001224577280x7ff27164d8800x7ff270c24c4000016811322909356168113228694081681132315084716811323152599
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581770051770054194304256001224589440x7ff27164d7000x7ff270c24c8000016811323182958168113231508471681132351020516811323511928
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611770051770054194304256001224601600x7ff273ce55800x7ff270c24cc000016811323542497168113235102051681132387660316811323878536
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164177005177005419430425600824613760x7ff273ce54000x7ff270c24d0000016811323910355168113238766031681132415212216811324153967
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671770051770054194304256001224628480x7ff273ce52800x7ff270c24d4000016811324185327168113241521221681132443388116811324435589
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701770051770054194304256001224638080x7ff273ce51000x7ff270c24d8000016811324474417168113244338811681132470764016811324709360
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731770051770054194304256001224650240x7ff27164df800x7ff270c24dc000016811324740219168113247076401681132507467816811325076429
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761770051770054194304256001224662400x7ff27164de000x7ff270c24e0000016811325107328168113250746781681132543819716811325439867
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179177005177005419430425600824674560x7ff27164dc800x7ff270c24e4000016811325470156168113254381971681132571451516811325716249
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821770051770054194304256001224689280x7ff27164db000x7ff270c24e8000016811325747308168113257145151681132599931416811326001140
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851770051770054194304256001224701440x7ff27164d9800x7ff270c24ec000016811326039179168113259993141681132627899316811326280721
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881770051770054194304256001224716160x7ff27164d8000x7ff270c24f0000016811326311510168113262789931681132664411116811326645910
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911770051770054194304256001224728320x7ff27164d6800x7ff270c24f4000016811326677529168113266441111681132701227016811327014018
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194177005177005419430425600824740480x7ff273ce55000x7ff270c24f8000016811327044268168113270122701681132728794916811327289590
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971770051770054194304256001224757760x7ff273ce53800x7ff270c24fc000016811327320479168113272879491681132757738716811327579161
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001770051770054194304256001224769920x7ff273ce52000x7ff270c2500000016811327617230168113275773871681132785818616811327859832
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031770051770054194304256001224784640x7ff273ce50800x7ff270c2504000016811327890891168113278581861681132822234416811328224131
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061770051770054194304256001224799360x7ff27164df000x7ff270c2508000016811328256250168113282223441681132858426316811328585930
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209177005177005419430425600824814080x7ff27164dd800x7ff270c250c000016811328616309168113285842631681132886250216811328864491
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121770051770054194304256001224831360x7ff27164dc000x7ff270c2510000016811328895790168113288625021681132915802016811329159722
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151770051770054194304256001224843520x7ff27164da800x7ff270c2514000016811329208450168113291580201681132943737916811329439203
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181770051770054194304256001224858240x7ff27164d9000x7ff270c2518000016811329469822168113294373791681132980281816811329804592
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211770051770054194304256001224872960x7ff27164d7800x7ff270c251c000016811329835401168113298028181681133016393616811330165891
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241770051770054194304256001224887680x7ff27164d6000x7ff270c2520000016811330197700168113301639361681133044185516811330443452
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271770051770054194304256001224907520x7ff273ce54800x7ff270c2524000016811330474511168113304418551681133074313316811330744793
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301770051770054194304256001224919680x7ff273ce53000x7ff270c2528000016811330783651168113307431331681133102265216811331024474
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331770051770054194304256001224934400x7ff273ce51800x7ff270c252c000016811331056163168113310226521681133138393116811331385773
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361770051770054194304256001224949120x7ff273ce50000x7ff270c2530000016811331417742168113313839311681133174392916811331745721
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391770051770054194304256001224963840x7ff27164de800x7ff270c2534000016811331776250168113317439291681133201880816811332020603
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421770051770054194304256001224983680x7ff27164dd000x7ff270c2538000016811332051312168113320188081681133232488716811332326593
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451770051770054194304256001224995840x7ff27164db800x7ff270c253c000016811332364372168113323248871681133259800516811332599705
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024817700517700541943042560012241013120x7ff27164da000x7ff270c2540000016811332630624168113325980051681133295800416811332959784
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025117700517700541943042560012241027840x7ff27164d8800x7ff270c2544000016811332990633168113329580041681133332200216811333323662
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025417700517700541943042560012241042560x7ff27164d7000x7ff270c2548000016811333354391168113333220021681133359736116811333599094
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025717700517700541943042560012241062400x7ff273ce55800x7ff270c254c000016811333628853168113335973611681133390968016811333911484
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026017700517700541943042560012241077120x7ff273ce54000x7ff270c2550000016811333949743168113339096801681133419671816811334198755
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026317700517700541943042560016241094400x7ff273ce52800x7ff270c2554000016811334229904168113341967181681133456199716811334563714
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026617700517700541943042560016241111680x7ff273ce51000x7ff270c2558000016811334595303168113345619971681133492071516811334922402
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691770051770054194304256008241128960x7ff27164df800x7ff270c255c000016811334953041168113349207151681133519687416811335198874
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027217700517700541943042560012241151360x7ff27164de000x7ff270c2560000016811335230013168113351968741681133551495316811335516664
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027517700517700541943042560012241166080x7ff27164dc800x7ff270c2564000016811335554953168113355149531681133579383116811335795495
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027817700517700541943042560016241183360x7ff27164db000x7ff270c2568000016811335826604168113357938311681133616583016811336167484
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028117700517700541943042560016241200640x7ff27164d9800x7ff270c256c000016811336197973168113361658301681133652598816811336527732
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028417700517700541943042560012241217920x7ff27164d8000x7ff270c2570000016811336558331168113365259881681133680214716811336803994
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028717700517700541943042560012241240320x7ff27164d6800x7ff270c2574000016811336835333168113368021471681133713334616811337135083
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029017700517700541943042560012241255040x7ff273ce55000x7ff270c2578000016811337172742168113371333461681133741702416811337418624
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029317700517700541943042560012241274880x7ff273ce53800x7ff270c257c000016811337449774168113374170241681133777766316811337779383
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029617700517700541943042560012241292160x7ff273ce52000x7ff270c2580000016811337810352168113377776631681133814358116811338145372
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029917700517700541943042560012241309440x7ff273ce50800x7ff270c2584000016811338176641168113381435811681133842902016811338430833
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030217700517700541943042560012241334400x7ff27164df000x7ff270c2588000016811338461892168113384290201681133876805916811338769802
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030517700517700541943042560012241349120x7ff27164dd800x7ff270c258c000016811338808511168113387680591681133904693716811339048674
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030817700517700541943042560012241368960x7ff27164dc000x7ff270c2590000016811339079003168113390469371681133940885616811339410662
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031117700517700541943042560012241388800x7ff27164da800x7ff270c2594000016811339441511168113394088561681133977061416811339772311
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031417700517700541943042560012241408640x7ff27164d9000x7ff270c2598000016811339802120168113397706141681134005861316811340060322
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031717700517700541943042560012241436160x7ff27164d7800x7ff270c259c000016811340090661168113400586131681134041493116811340416761
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032017700517700541943042560012241453440x7ff27164d6000x7ff270c25a0000016811340455600168113404149311681134069749016811340699132
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032317700517700541943042560012241475840x7ff273ce54800x7ff270c25a4000016811340730851168113406974901681134106020916811341061881
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032617700517700541943042560012241495680x7ff273ce53000x7ff270c25a8000016811341092790168113410602091681134141908716811341420810
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032917700517700541943042560012241515520x7ff273ce51800x7ff270c25ac000016811341451499168113414190871681134171076616811341712491
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033217700517700541943042560012241543040x7ff273ce50000x7ff270c25b0000016811341743600168113417107661681134207092416811342072629
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033517700517700541943042560012241562880x7ff27164de800x7ff270c25b4000016811342111868168113420709241681134236452316811342366220
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033817700517700541943042560012241587840x7ff27164dd000x7ff270c25b8000016811342396739168113423645231681134272884116811342730569
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034117700517700541943042560012241610240x7ff27164db800x7ff270c25bc000016811342761028168113427288411681134309108016811343092818
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034417700517700541943042560012241632640x7ff27164da000x7ff270c25c0000016811343122917168113430910801681134340179816811343403548
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034717700517700541943042560012241665280x7ff27164d8800x7ff270c25c4000016811343434677168113434017981681134379459716811343819035
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035017700517700541943042560012241685120x7ff27164d7000x7ff270c25c8000016811343837724168113437945971681134410099516811344102766
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035317700517700541943042560012241712640x7ff273ce55800x7ff270c25cc000016811344133735168113441009951681134446611416811344467865
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035617700517700541943042560012241737600x7ff273ce54000x7ff270c25d0000016811344499314168113444661141681134483603216811344837753
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035917700517700541943042560012241762560x7ff273ce52800x7ff270c25d4000016811344868242168113448360321681134515635116811345158063
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036217700517700541943042560012241797760x7ff273ce51000x7ff270c25d8000016811345189622168113451563511681134557170916811345589730
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036517700517700541943042560012241822720x7ff27164df800x7ff270c25dc000016811345612119168113455717091681134589218816811345894130
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036817700517700541943042560012241855360x7ff27164de000x7ff270c25e0000016811345923979168113458921881681134626594616811346269668
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037117700517700541943042560012241885440x7ff27164dc800x7ff270c25e4000016811346299198168113462659461681134664722416811346692685
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037417700517700541943042560012241915520x7ff27164db000x7ff270c25e8000016811346703225168113466472241681134702834316811347030075
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037717700517700541943042560012241958400x7ff27164d9800x7ff270c25ec000016811347060424168113470283431681134749378116811347539299
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038017700517700541943042560012241985920x7ff27164d8000x7ff270c25f0000016811347558348168113474937811681134786049916811347862219
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038317700517700541943042560012242023680x7ff27164d6800x7ff270c25f4000016811347893038168113478604991681134825009716811348295555
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038617700517700541943042560012242058880x7ff273ce55000x7ff270c25f8000016811348306085168113482500971681134867121516811348712962
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038917700517700541943042560012242094080x7ff273ce53800x7ff270c25fc000016811348723512168113486712151681134906817416811349071931
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039217700517700541943042560012242144640x7ff273ce52000x7ff270c2600000016811349101720168113490681741681134958417116811349603734
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039517700517700541943042560012242177280x7ff273ce50800x7ff270c2604000016811349624694168113495841711681134993825016811349940014
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039817700517700541943042560012242220160x7ff27164df000x7ff270c2608000016811349971163168113499382501681135035840816811350381070
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040117700517700541943042560012242260480x7ff27164dd800x7ff270c260c000016811350391830168113503584081681135079648616811350814217
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040417700517700541943042560012242300800x7ff27164dc000x7ff270c2610000016811350828836168113507964861681135119632416811351238224
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040717700517700541943042560012242359040x7ff27164da800x7ff270c2614000016811351248853168113511963241681135179200216811351834045
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041017700517700541943042560012242394240x7ff27164d9000x7ff270c2618000016811351852965168113517920021681135219520016811352196974
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041317700517700541943042560012242442240x7ff27164d7800x7ff270c261c000016811352227393168113521952001681135262671816811352669149
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041617700517700541943042560012242487680x7ff27164d6000x7ff270c2620000016811352679349168113526267181681135308207616811353123915
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041917700517700541943042560012242533120x7ff273ce54800x7ff270c2624000016811353135115168113530820761681135353055416811353548572
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221770051770054194304256008242555520x7ff273ce53000x7ff270c2628000016811353563542168113535305541681135416751116811354211741
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042517700517700541943042560012242598400x7ff273ce51800x7ff270c262c000016811354231031168113541675111681135460735016811354625549
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042817700517700541943042560012242656640x7ff273ce50000x7ff270c2630000016811354639928168113546073501681135509182716811355109523
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043117700517700541943042560012242712320x7ff27164de800x7ff270c2634000016811355123503168113550918271681135558094516811355599128
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341770051770054194304256008242732160x7ff27164dd000x7ff270c2638000016811355612968168113555809451681135606702316811356084103
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371770051770054194304256008242757120x7ff27164db800x7ff270c263c000016811356099513168113560670231681135680926016811356827500
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044017700517700541943042560012242807680x7ff27164da000x7ff270c2640000016811356849579168113568092601681135726173816811357279636
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044317700517700541943042560012242876160x7ff27164d8800x7ff270c2644000016811357294565168113572617381681135779597616811357813909
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044617700517700541943042560012242942080x7ff27164d7000x7ff270c2648000016811357828199168113577959761681135833085316811358349772
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491770051770054194304256008242969600x7ff273ce55800x7ff270c264c000016811358363362168113583308531681135886989116811358911965
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521770051770054194304256008242999680x7ff273ce54000x7ff270c2650000016811358922715168113588698911681135973884716811359757348
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551770051770054194304256008243027200x7ff273ce52800x7ff270c2654000016811359778858168113597388471681136037660416811360394209
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045817700517700541943042560012243054720x7ff273ce51000x7ff270c2658000016811360409498168113603766041681136102508216811361068628
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046117700517700541943042560012243082240x7ff27164df800x7ff270c265c000016811361079597168113610250821681136170091916811361744017
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641770051770054194304256008243109760x7ff27164de000x7ff270c2660000016811361755416168113617009191681136236155616811362408296
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671770051770054194304256008243132160x7ff27164dc800x7ff270c2664000016811362419635168113623615561681136345003116811363495112
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701770051770054194304256008243159680x7ff27164db000x7ff270c2668000016811363513851168113634499551681136451619016811364564359
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047317700517700541943042560012243187200x7ff27164d9800x7ff270c266c000016811364574858168113645161901681136561474416811365680594
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047617700517700541943042560012243214720x7ff27164d8000x7ff270c2670000016811365691973168113656147441681136672561916811366794959
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791770051770054194304256008243242240x7ff27164d6800x7ff270c2674000016811366805939168113667256191681136782433416811367891775
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821770051770054194304256008243264640x7ff273ce55000x7ff270c2678000016811367903174168113678243341681136977440516811369841814
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851770051770054194304256008243292160x7ff273ce53800x7ff270c267c000016811369860913168113697744051681137169087616811371763194
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048817700517700541943042560012243319680x7ff273ce52000x7ff270c2680000016811371775064168113716908761681137369086716811373758522
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049117700517700541943042560012243347200x7ff273ce50800x7ff270c2684000016811373769092168113736908671681137566813816811375747250
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941770051770054194304256008243374720x7ff27164df000x7ff270c2688000016811375758750168113756681381681137761597016811377684640
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049717700517700541943042560082400x7ff27164dd800x7ff270c268c000016811377696510168113776159701681138124139316811381314347