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

46 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjGRBM_COUNTGRBM_GUI_ACTIVESQ_WAVESSQ_IFETCHSQ_IFETCH_LEVELSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000873972873977335544322560083264640x00x7f8ee3a04180509817509817524288629145679238210151586812075419862902974120754201084853491207542010881206712075420108922310
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00287397287397732768256002424124800x00x7f8ee3a35100287252872551281928564110647212075420123341778120754201236571111207542012366335112075420123671170
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0048739728739774194304256002424129280x7f9013d2a9000x7f8ee3a35140222139222139655369175041407271795278812075420123735800120754201239607901207542012409630912075420124100558
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0068739728739774194304256003624136320x7f9013d2a8000x7f8ee3a351803900173900176553612451841820012324710012075420124173584120754201243575881207542012460638612075420124677841
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0088739728739774194304256002824140800x7f9013d2a7000x7f8ee3a351c0393131393131655369830401356181732337212075420124709730120754201249031851207542012515262412075420125224046
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00108739728739774194304256002424145280x7f9013d2a6000x7f8ee3a352002126092126096553610485761574192013851612075420125245135120754201254499021207542012557998112075420125583354
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00128739728739774194304256002424149760x7f9013d2a5000x7f8ee3a35240222355222355655369830401490241904956812075420125637394120754201258204601207542012595598012075420125959432
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00148739728739774194304256002424154240x7f9013d2a4000x7f8ee3a352802181692181696553610485761472191881194812075420126048227120754201262270181207542012636109812075420126364856
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00168739728739774194304256002824161280x7f9013d2a3000x7f8ee3a352c03989073989076553615728642270142899808412075420126418265120754201266039761207542012685757512075420126900301
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00188739728739774194304256002824168320x7f9013d2aa000x7f8ee3a353003898813898816553611796481586222040424012075420126936268120754201271294141207542012737773212075420127447217
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00208739728739774194304256002424175360x7f9013d2a9000x7f8ee3a353402114192114196553611141121602312052842812075420127474969120754201276663711207542012779469012075420127798200
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00228739728739774194304256002424182400x7f9013d2a8000x7f8ee3a353802165132165136553611141121595402036416012075420127850317120754201280340491207542012816636812075420128170001
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00248739728739774194304256002424189440x7f9013d2a7000x7f8ee3a353c02118912118916553611796481684362155282812075420128236344120754201284134071207542012854220712075420128545699
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00268739728739774194304256002824199040x7f9013d2a6000x7f8ee3a354003978973978976553618350082602193331839612075420128596483120754201287812451207542012903548412075420129106782
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00288739728739774194304256002824206080x7f9013d2a5000x7f8ee3a354403897873897876553613107201787022285786812075420129133111120754201293324431207542012958044112075420129648078
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00308739728739774194304256002424213120x7f9013d2a4000x7f8ee3a354802099212099216553612451841825562341459212075420129673876120754201298626801207542012999099912075420129994411
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00328739728739774194304256002424220160x7f9013d2a3000x7f8ee3a354c02186672186676553613107201822802339805612075420130046408120754201302356381207542013036891712075420130372484
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00348739728739774194304256002424227200x7f9013d2aa000x7f8ee3a355002122812122816553613107201793402300152012075420130436703120754201306042761207542013073371512075420130737302
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00368739728739774194304256002824236800x7f9013d2a9000x7f8ee3a355404534994534996553620971522877553684128812075420130789519120754201309698741207542013126011312075420131328831
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00388739728739774194304256002824243840x7f9013d2a8000x7f8ee3a355804014894014896553614417921942012498260412075420131350201120754201315449111207542013180043012075420131868284
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00408739728739774194304256002424250880x7f9013d2a7000x7f8ee3a355c02111632111636553613762561913092441283212075420131886979120754201320887491207542013221834812075420132222001
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00428739728739774194304256002424257920x7f9013d2a6000x7f8ee3a356002131372131376553615073282154882758697612075420132270311120754201324585071207542013258682612075420132590456
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00448739728739774194304256002424264960x7f9013d2a5000x7f8ee3a356402197072197076553614417922096592677685612075420132656258120754201328250651207542013295978412075420132963339
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00468739728739774194304256002824277120x7f9013d2a4000x7f8ee3a356804018814018816553623592963240244156549612075420133013362120754201332025031207542013345930212075420133528579
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00488739728739774194304256002824284160x7f9013d2a3000x7f8ee3a356c03880913880916553615728642096502695762012075420133554017120754201337487401207542013399641912075420134065197
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00508739728739774194304256002424291200x7f9013d2aa000x7f8ee3a357002169612169616553615073282039082614144012075420134092537120754201342898581207542013442265712075420134426087
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00528739728739774194304256002424300800x7f9013d2a9000x7f8ee3a357402167712167716553617039362353783012736812075420134477493120754201346597761207542013479273512075420134796396
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00548739728739774194304256002424307840x7f9013d2a8000x7f8ee3a357802132332132336553615728642125832720833212075420134859673120754201350343341207542013516457312075420135168297
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00568739728739774194304256002824320000x7f9013d2a7000x7f8ee3a357c03950593950596553626214403608314611601212075420135219231120754201354044121207542013565785112075420135725993
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00588739728739774194304256002824329600x7f9013d2a6000x7f8ee3a358003954173954176553617039362303942940405212075420135753204120754201359384891207542013619096812075420136261869
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00608739728739774194304256002424339200x7f9013d2a5000x7f8ee3a358402144032144036553616384002270842904403612075420136293017120754201364831261207542013661240612075420136615997
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00628739728739774194304256002424348800x7f9013d2a4000x7f8ee3a358802161132161136553619005442775573538818812075420136670589120754201368501651207542013698232412075420136985925
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00648739728739774194304256002424358400x7f9013d2a3000x7f8ee3a358c02098432098436553617039362326982978572412075420137057658120754201372308031207542013735944212075420137363096
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00668739728739774194304256002824373120x7f9013d2aa000x7f8ee3a359004083374083376553628835843989195109357612075420137415713120754201376042411207542013786535912075420137908229
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00688739728739774194304256002824382720x7f9013d2a9000x7f8ee3a359403969313969316553618350082436813117066812075420137936281120754201381312781207542013838567712075420138428135
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00708739728739774194304256002424392320x7f9013d2a8000x7f8ee3a359802180732180736553617694722579373303120812075420138458892120754201386482361207542013878151512075420138784998
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00728739728739774194304256002424401920x7f9013d2a7000x7f8ee3a359c02184512184516553620971523092323942470412075420138840141120754201390069541207542013914151312075420139145368
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00748739728739774194304256002424411520x7f9013d2a6000x7f8ee3a35a002205852205856553618350082512993217563612075420139211912120754201393835921207542013951911112075420139522709
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00768739728739774194304256002824426240x7f9013d2a5000x7f8ee3a35a404087874087876553631457284337945538835612075420139568244120754201397503101207542014001302912075420140062803
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00788739728739774194304256002824435840x7f9013d2a4000x7f8ee3a35a803876653876656553619660802616603339747212075420140088901120754201402789471207542014052662612075420140567240
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00808739728739774194304256002424445440x7f9013d2a3000x7f8ee3a35ac02154592154596553619005442575763295687612075420140600121120754201407835851207542014091574412075420140919445
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00828739728739774194304256002424457600x7f9013d2aa000x7f8ee3a35b002196732196736553622937603121373997428412075420140972714120754201411551031207542014129046212075420141294422
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00848739728739774194304256002424467200x7f9013d2a9000x7f8ee3a35b402155792155796553619660802718203484938012075420141357960120754201415280611207542014166070012075420141664199
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00868739728739774194304256002824484480x7f9013d2a8000x7f8ee3a35b804034414034416553634078724613725897161212075420141711407120754201418923791207542014215093812075420142193052
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00888739728739774194304256002824494080x7f9013d2a7000x7f8ee3a35bc03953633953636553620971522854533648332812075420142224751120754201424056571207542014265925512075420142700625
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00908739728739774194304256002424503680x7f9013d2a6000x7f8ee3a35c002127212127216553620316162780173561442812075420142732464120754201429093341207542014303957312075420143043402
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00928739728739774194304256002424515840x7f9013d2a5000x7f8ee3a35c402175712175716553624903683419394358559612075420143094728120754201432730121207542014340757212075420143411266
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00948739728739774194304256002424525440x7f9013d2a4000x7f8ee3a35c802150972150976553620971522971013800046812075420143474764120754201436426101207542014377461012075420143778078
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00968739728739774194304256002824542720x7f9013d2a3000x7f8ee3a35cc04083474083476553636700164933686319286812075420143829934120754201440101281207542014427252712075420144342507
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00988739728739774194304256002824554880x7f9013d2aa000x7f8ee3a35d003866573866576553622282242985943819106412075420144367223120754201445646861207542014481236412075420144879845
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001008739728739774194304256002424567040x7f9013d2a9000x7f8ee3a35d402173552173556553621626883144354019374012075420144899221120754201450971631207542014523076212075420145234605
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001028739728739774194304256002424581760x7f9013d2a8000x7f8ee3a35d802224012224016553626869763775764823428412075420145288054120754201454634011207542014560084012075420145604442
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001048739728739774194304256002424593920x7f9013d2a7000x7f8ee3a35dc02148832148836553622282243060013915992412075420145669242120754201458355591207542014596755912075420145971093
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001068739728739774194304256002824613760x7f9013d2a6000x7f8ee3a35e004048254048256553639321605689487279782412075420146021577120754201462136371207542014647427612075420146541684
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001088739728739774194304256002824625920x7f9013d2a5000x7f8ee3a35e403885153885156553623592963088503958295612075420146565197120754201467525151207542014700195312075420147044278
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001108739728739774194304256002424638080x7f9013d2a4000x7f8ee3a35e802226332226336553622937603608144619394412075420147076838120754201472598721207542014739667112075420147400259
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001128739728739774194304256002424652800x7f9013d2a3000x7f8ee3a35ec02332592332596553628835844474825717190812075420147454720120754201476339501207542014777890912075420147782520
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001148739728739774194304256002424664960x7f9013d2aa000x7f8ee3a35f002154412154416553623592963432054398691212075420147847811120754201480206681207542014815282812075420148156845
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001168739728739774194304256002824684800x7f9013d2a9000x7f8ee3a35f404050674050676553641943045626417211045212075420148208732120754201483891461207542014864978512075420148718018
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001188739728739774194304256002824696960x7f9013d2a8000x7f8ee3a35f803913533913536553624903683313144228364812075420148740921120754201489267441207542014917762212075420149247633
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001208739728739774194304256002424709120x7f9013d2a7000x7f8ee3a35fc02157632157636553624248323301864232864412075420149275755120754201494598611207542014959234012075420149595950
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001228739728739774194304256002424723840x7f9013d2a6000x7f8ee3a360002264652264656553630801924803496174250012075420149642977120754201498228991207542014996353812075420149966989
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001248739728739774194304256002424736000x7f9013d2a5000x7f8ee3a360402155712155716553624903683678904716162812075420150037851120754201502048171207542015033761712075420150341335
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001268739728739774194304256002824758400x7f9013d2a4000x7f8ee3a360804075694075696553644564485888597532886412075420150392360120754201505718551207542015083473412075420150877682
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001288739728739774194304256002824770560x7f9013d2a3000x7f8ee3a360c03868753868756553626214403565204552758812075420150895846120754201511022531207542015135137112075420151393480
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001308739728739774194304256002424782720x7f9013d2aa000x7f8ee3a361002139452139456553625559043673154701910012075420151411574120754201516032101207542015173457012075420151738181
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001328739728739774194304256002424800000x7f9013d2a9000x7f8ee3a361402316592316596553632768004947566323138412075420151790789120754201519678481207542015211200812075420152115923
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001348739728739774194304256002424812160x7f9013d2a8000x7f8ee3a361802172652172656553626214404126255281221212075420152181836120754201523531261207542015248672612075420152490489
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001368739728739774194304256002824834560x7f9013d2a7000x7f8ee3a361c04050514050516553647185926313558074773212075420152535062120754201527182451207542015298032312075420153048176
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001388739728739774194304256002824849280x7f9013d2a6000x7f8ee3a362004021454021456553627525123624594635178412075420153073453120754201532625621207542015352096012075420153588189
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001408739728739774194304256002424864000x7f9013d2a5000x7f8ee3a362402749872749876553626869763982185096734412075420153611883120754201538011191207542015397199812075420153975549
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001428739728739774194304256002424881280x7f9013d2a4000x7f8ee3a362802445052445056553634734085288816757155612075420154028948120754201542151971207542015436687612075420154370764
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001448739728739774194304256002424896000x7f9013d2a3000x7f8ee3a362c02191312191316553627525124020645149187212075420154448638120754201546167951207542015475183412075420154755439
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001468739728739774194304256002824920960x7f9013d2aa000x7f8ee3a363004065214065216553649807366536118349018012075420154807285120754201549868731207542015524975212075420155298538
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001488739728739774194304256002824935680x7f9013d2a9000x7f8ee3a363403876353876356553628835843905494995807212075420155324136120754201555119901207542015576190912075420155809608
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001508739728739774194304256002424950400x7f9013d2a8000x7f8ee3a363802162892162896553628180483836344909798812075420155837379120754201560222281207542015615358712075420156157194
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001528739728739774194304256002424967680x7f9013d2a7000x7f8ee3a363c02529792529796553636700165655887247880412075420156211414120754201563897461207542015654846512075420156552058
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001548739728739774194304256002424982400x7f9013d2a6000x7f8ee3a364002137452137456553628835844176215357094412075420156616016120754201567828641207542015691438312075420156918268
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015687397287397741943042560028241007360x7f9013d2a5000x7f8ee3a364404079074079076553651773446814998727278812075420156969824120754201571527821207542015741742112075420157467148
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015887397287397741943042560028241022080x7f9013d2a4000x7f8ee3a364803930733930736553630146564421755662217612075420157491053120754201576777401207542015793101812075420157952861
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016087397287397741943042560024241036800x7f9013d2a3000x7f8ee3a364c02156112156116553629491204408025643884012075420157998776120754201581754971207542015830845612075420158312389
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016287397287397741943042560024241056640x7f9013d2aa000x7f8ee3a365002649212649216553638666245887167559259212075420158364987120754201585428551207542015870861412075420158712302
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016487397287397741943042560024241071360x7f9013d2a9000x7f8ee3a365402213792213796553630146564330175544879612075420158776782120754201589425331207542015907933212075420159083482
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016687397287397741943042560028241098880x7f9013d2a8000x7f8ee3a365804050894050896553654394887654439808864812075420159139466120754201593122911207542015957405012075420159622624
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016887397287397741943042560028241113600x7f9013d2a7000x7f8ee3a365c03882513882516553631457284150375294856012075420159649203120754201598342091207542016008444712075420160134686
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017087397287397741943042560024241128320x7f9013d2a6000x7f8ee3a366002208652208656553630801924543425815162812075420160159482120754201603478061207542016048412512075420160487712
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017287397287397741943042560024241148160x7f9013d2a5000x7f8ee3a366402752272752276553640632325602877188970812075420160538737120754201607159641207542016088988312075420160893696
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017487397287397741943042560024241162880x7f9013d2a4000x7f8ee3a366802183292183296553631457284359115579788012075420160957735120754201611287621207542016126316112075420161267060
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017687397287397741943042560028241190400x7f9013d2a3000x7f8ee3a366c04025154025156553657016327562579710612812075420161321261120754201614959601207542016175659912075420161807785
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017887397287397741943042560028241207680x7f9013d2aa000x7f8ee3a367003936333936336553632768004265375452090012075420161830617120754201620245981207542016227819612075420162327691
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018087397287397741943042560024241224960x7f9013d2a9000x7f8ee3a367402218112218116553632112645166336625174012075420162355222120754201625412351207542016267851412075420162682240
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018287397287397741943042560024241247360x7f9013d2a8000x7f8ee3a367802881292881296553642598405736707329461612075420162737543120754201629093931207542016309131212075420163095198
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018487397287397741943042560024241264640x7f9013d2a7000x7f8ee3a367c02184992184996553632768004515115781239612075420163159207120754201633362711207542016347083012075420163474593
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018687397287397741943042560020241279360x7f9013d2a6000x7f8ee3a3680040924140924165536773324897545412478078012075420163526710120754201637106691207542016397578812075420164029183
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018887397287397741943042560028241296640x7f9013d2a5000x7f8ee3a368403908193908196553634078724520595777606412075420164055813120754201642538661207542016450618512075420164553618
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019087397287397741943042560024241313920x7f9013d2a4000x7f8ee3a368802202492202496553633423364910336283338812075420164570940120754201647666641207542016490282312075420164906584
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019287397287397741943042560024241336320x7f9013d2a3000x7f8ee3a368c03025473025476553644564486648948474713612075420164960765120754201651370621207542016532906112075420165377219
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019487397287397741943042560024241353600x7f9013d2aa000x7f8ee3a369002243212243216553635389445164716605767212075420165417794120754201655834601207542016572233912075420165726037
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019687397287397741943042560020241368320x7f9013d2a9000x7f8ee3a36940434971434971655368978432112886014471745212075420165771682120754201659516181207542016623481612075420166285336
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019887397287397741943042560028241385600x7f9013d2a8000x7f8ee3a369803950253950256553636700164883886254346412075420166305394120754201664965751207542016675177412075420166798570
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020087397287397741943042560024241402880x7f9013d2a7000x7f8ee3a369c02239072239076553636044805273076748736412075420166826021120754201670111321207542016714921212075420167153480
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020287397287397741943042560024241427840x7f9013d2a6000x7f8ee3a36a003328413328416553648496647446579558694012075420167207170120754201673829711207542016759448912075420167641887
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020487397287397741943042560024241447680x7f9013d2a5000x7f8ee3a36a402234672234676553638010886046257736159612075420167680058120754201678456881207542016798408812075420167987720
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020687397287397741943042560020241457280x7f9013d2a4000x7f8ee3a36a804715934715936553614548992182711723384994012075420168041160120754201682244061207542016853144512075420168579700
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020887397287397741943042560028241477120x7f9013d2a3000x7f8ee3a36ac04018274018276553639321605178996638022412075420168603905120754201687901631207542016905000212075420169078838
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021087397287397741943042560024241496960x7f9013d2aa000x7f8ee3a36b002145292145296553638666245472297006556012075420169124823120754201692904811207542016942296012075420169426745
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021287397287397741943042560024241521920x7f9013d2a9000x7f8ee3a36b4035745135745165536524288078083910009844812075420169478150120754201696535191207542016988183812075420169929429
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021487397287397741943042560024241541760x7f9013d2a8000x7f8ee3a36b802176492176496553640632325985817673100812075420169967600120754201701415171207542017027575612075420170279930
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021687397287397741943042560020241556480x7f9013d2a7000x7f8ee3a36bc05030915030916553610027008126035916128904412075420170323421120754201705125551207542017084183312075420170889253
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021887397287397741943042560028241576320x7f9013d2a6000x7f8ee3a36c004008814008816553641943046264668011415212075420170912967120754201711173521207542017137671012075420171424958
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022087397287397741943042560024241596160x7f9013d2a5000x7f8ee3a36c402243792243796553641287685814687452262412075420171447871120754201716351711207542017177469112075420171781982
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022287397287397741943042560024241623680x7f9013d2a4000x7f8ee3a36c803818573818576553656360967782649956621612075420171829921120754201720124481207542017225708712075420172304833
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022487397287397741943042560024241646080x7f9013d2a3000x7f8ee3a36cc02256832256836553645875207101329096119612075420172345609120754201725158061207542017265580612075420172659082
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022687397287397741943042560020241663360x7f9013d2aa000x7f8ee3a36d005746655746656553611075584139378417832088412075420172705989120754201728865241207542017326348312075420173313428
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022887397287397741943042560028241685760x7f9013d2a9000x7f8ee3a36d404073954073956553647185926178617898582012075420173341981120754201735268421207542017378860012075420173836239
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023087397287397741943042560024241708160x7f9013d2a8000x7f8ee3a36d802216572216576553646530567037839015860412075420173858881120754201740564391207542017419355812075420174196920
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023287397287397741943042560024241740800x7f9013d2a7000x7f8ee3a36dc043621943621965536642252893539112074376412075420174243376120754201744255571207542017470651612075420174753674
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023487397287397741943042560024241765760x7f9013d2a6000x7f8ee3a36e0022541722541765536511180881422110417560412075420174791525120754201749578751207542017509835412075420175102302
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023687397287397741943042560020241777920x7f9013d2a5000x7f8ee3a36e406434756434756553615007744188247124087607212075420175154229120754201753343531207542017575867112075420175805669
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023887397287397741943042560028241802880x7f9013d2a4000x7f8ee3a36e8040880140880165536524288078135610020301612075420175829544120754201760276301207542017629066912075420176338890
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024087397287397741943042560024241827840x7f9013d2a3000x7f8ee3a36ec022637922637965536517734486726011097410012075420176363666120754201765533881207542017669450712075420176697868
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024287397287397741943042560024241863040x7f9013d2aa000x7f8ee3a36f00487697487697655367208960100633612902836412075420176751056120754201769266661207542017724170512075420177291200
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024487397287397741943042560024241893120x7f9013d2a9000x7f8ee3a36f4024186724186765536616038486834211123342412075420177329582120754201774999431207542017765162312075420177655006
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024687397287397741943042560020241907840x7f9013d2a8000x7f8ee3a36f807852577852576553617104896214702327469606012075420177709628120754201778831421207542017840153912075420178452018
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024887397287397741943042560028241937920x7f9013d2a7000x7f8ee3a36fc045617145617165536629145686150011009649212075420178476293120754201786661781207542017896377712075420179022107
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025087397287397741943042560024241968000x7f9013d2a6000x7f8ee3a3700024839324839365536622592095665112238636412075420179106564120754201793484151207542017950441412075420179507790
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025287397287397741943042560024242010880x7f9013d2a5000x7f8ee3a37040593699593699655368781824128184516437666812075420179563784120754201797629731207542018014937112075420180198834
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025487397287397741943042560024242046080x7f9013d2a4000x7f8ee3a37080279537279537655367208960107452113748334012075420180271559120754201805002501207542018067704912075420180680529
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025687397287397741943042560020242060800x7f9013d2a3000x7f8ee3a370c09254199254196553619202048239478330808545212075420180732326120754201809215281207542018153416512075420181583117
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025887397287397741943042560028242096000x7f9013d2aa000x7f8ee3a37100501089501089655367340032103334113221197212075420181607953120754201818039241207542018213192212075420182180587
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026087397287397741943042560024242131200x7f9013d2a9000x7f8ee3a37140283299283299655367274496111196314222803612075420182207627120754201823996011207542018257928012075420182582734
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026287397287397741943042560024242181760x7f9013d2a8000x7f8ee3a371806974256974256553610354688147109818829412412075420182635773120754201828149591207542018327015712075420183317891
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026487397287397741943042560024242222080x7f9013d2a7000x7f8ee3a371c0315075315075655368257536125927416122991612075420183357925120754201835296761207542018373063512075420183777745
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026687397287397741943042560020242239360x7f9013d2a6000x7f8ee3a37200106720110672016553621299200266905434170834812075420183800698120754201839904741207542018469575112075420184749551
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026887397287397741943042560028242279680x7f9013d2a5000x7f8ee3a37240567235567235655368388608110416014043296812075420184775359120754201849883891207542018536166812075420185411532
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027087397287397741943042560024242320000x7f9013d2a4000x7f8ee3a37280318041318041655368323072120397715423334412075420185436969120754201856304661207542018583270512075420185880723
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027287397287397741943042560024242378240x7f9013d2a3000x7f8ee3a372c08046758046756553611927552165926621101814812075420185904598120754201861018241207542018662854212075420186678566
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027487397287397741943042560024242423680x7f9013d2aa000x7f8ee3a37300350609350609655369306112142669718244896412075420186715004120754201868898211207542018711462012075420187162516
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027687397287397741943042560020242435840x7f9013d2a9000x7f8ee3a37340120678712067876553629163520365264646752505212075420187187141120754201873782981207542018817733512075420188245418
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027887397287397741943042560028242481280x7f9013d2a8000x7f8ee3a37380637945637945655369437184129494416568301212075420188273150120754201884634131207542018888421112075420188951861
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028087397287397741943042560024242526720x7f9013d2a7000x7f8ee3a373c0353019353019655369371648141109318063901212075420188980715120754201891725301207542018939924912075420189466968
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028287397287397741943042560024242592640x7f9013d2a6000x7f8ee3a374009091859091856553613500416188936024252938012075420189520798120754201897482081207542019034516512075420190412826
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028487397287397741943042560024242648320x7f9013d2a5000x7f8ee3a374404197474197476553611403264182018423297718012075420190460204120754201906392431207542019091092212075420190978067
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028687397287397741943042560020242663040x7f9013d2a4000x7f8ee3a37480149008114900816553633357824417473253456762012075420191044921120754201912720411207542019225939612075420192329438
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028887397287397741943042560028242718720x7f9013d2a3000x7f8ee3a374c08032678032676553611534336162219520875286012075420192389039120754201926161941207542019315075212075420193219262
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029087397287397741943042560024242774400x7f9013d2aa000x7f8ee3a375004236654236656553611534336178341122823534012075420193280055120754201935072301207542019378098912075420193848592
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029287397287397741943042560012242799360x7f9013d2a9000x7f8ee3a37540112664311266436553619267584242908931115096012075420193903724120754201941398681207542019487858412075420194948105
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029487397287397741943042560024242865280x7f9013d2a8000x7f8ee3a375804885454885456553613500416209073926760684412075420195028404120754201952552221207542019557122112075420195639520
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029687397287397741943042560020242880000x7f9013d2a7000x7f8ee3a375c0176893917689396553637552128469569260163171612075420195699491120754201959267391207542019709857412075420197168401
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029887397287397741943042560032242945920x7f9013d2a6000x7f8ee3a376009215699215696553613631488186226823928830412075420197230006120754201974571321207542019806833012075420198138264
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030087397287397741943042560024243011840x7f9013d2a5000x7f8ee3a376404932754932756553613631488209887726860643612075420198174792120754201983750481207542019869536712075420198763165
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030287397287397741943042560012243049600x7f9013d2a4000x7f8ee3a37680133794513379456553621692416273176734982922012075420198798721120754201989793651207542019985840112075420199928621
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030487397287397741943042560024243136000x7f9013d2a3000x7f8ee3a376c06330516330516553617694720271803534798637212075420199975769120754202001560001207542020056783812075420200636997
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030687397287397741943042560020243148160x7f9013d2aa000x7f8ee3a37700233319323331936553657475072719558092086984012075420200663807120754202008543971207542020240479012075420202475514
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030887397287397741943042560020243175680x7f9013d2a9000x7f8ee3a37740120264312026436553619660800247279531663976012075420202503095120754202026963081207542020349374512075420203562735
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031087397287397741943042560012243203200x7f9013d2a8000x7f8ee3a377806747376747376553620381696257074532894254412075420203595245120754202037833441207542020422142212075420204292681
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031287397287397741943042560012243240960x7f9013d2a7000x7f8ee3a377c0175978717597876553628704768360858746236414012075420204323368120754202045140601207542020567309512075420205742015
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031487397287397741943042560012243288960x7f9013d2a6000x7f8ee3a37800120083312008336553636634624463041259295786412075420205788461120754202059588541207542020674621012075420206815760
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031687397287397741943042560020243301120x7f9013d2a5000x7f8ee3a37840458534745853476553610584064013244661169492565212075420206848111120754202070470091207542021010027512075420210170255
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031887397287397741943042560020243328640x7f9013d2a4000x7f8ee3a37880232334523233456553638535168483420261832917212075420210197655120754202103943531207542021193594612075420212013871
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032087397287397741943042560012243356160x7f9013d2a3000x7f8ee3a378c0120547512054756553639124992491414062887480012075420212036543120754202122313051207542021302058112075420213088799
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032287397287397741943042560012243393920x7f9013d2aa000x7f8ee3a37900344373734437376553655771136700704089676233612075420213118684120754202133066601207542021558889012075420215657713
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032487397287397741943042560012243441920x7f9013d2a9000x7f8ee3a379402323771232377165536725483529112347116623962412075420215701795120754202158727281207542021740872112075420217478617
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032687397287397741943042560020243454080x7f9013d2a8000x7f8ee3a37980908728990872896553621069824026341361337267088012075420217509184120754202176989601207542022375333212075420223822627
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032887397287397741943042560020243481600x7f9013d2a7000x7f8ee3a379c04575907457590765536762839049553807122374504812075420223852773120754202240493311207542022709619712075420227168315
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033087397287397741943042560012243509120x7f9013d2a6000x7f8ee3a37a002327129232712965536773980169697090124132601612075420227196888120754202273941161207542022893266912075420229007623
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332873972873977419430425600122400x7f9013d2a5000x7f8ee3a37a40681369968136996553611082137613884239177762765612075420229033301120754202292281871207542023375584712075420233827220