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

48 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjGRBM_COUNTGRBM_GUI_ACTIVECPC_ME1_BUSY_FOR_PACKET_DECODESQ_CYCLESSQ_WAVESSQ_WAVE_CYCLESSQ_BUSY_CYCLESSQ_LEVEL_WAVESSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000175379175379335544322560043241600x00x7fce3f804280380644380644866630451605242882382451772959012096923346016792691334909167919831739701679283449053716792834600426
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00217537917537932768256001224138880x00x7fce3f823f8033369333692985326696051216614791641950665913616792839726115167928344905371679283986075616792839865120
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051753791753794194304256001224143360x7fcf4a0c63800x7fce3f823fc016895316895315194135163265536948173241245795038100038416792839908649167928398607561679284025691516792840259288
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081753791753794194304256001624150400x7fcf4a0c62000x7fce3f824000319429319429243542555440655362332882072451793093488236016792840305987167928402569151679284069003316792840692284
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111753791753794194304256001624154880x7fcf4a0c60800x7fce3f824040319876319876239072559016655362359011592455981094533581216792840733953167928406900331679284111563216792841117571
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141753791753794194304256001224159360x7fcf401c3f000x7fce3f82408017274817274815999138199265536990981891276923039811566816792841158950167928411156321679284145435016792841456360
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171753791753794194304256001224163840x7fcf401c3d800x7fce3f8240c016984616984615344135877665536956214911252978038421130416792841497389167928414543501679284178170916792841783830
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201753791753794194304256001224170880x7fcf401c3c000x7fce3f824100169702169702163891357624655361091555391257096043835512416792841837408167928417817091679284210682816792842108780
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231753791753794194304256001624177920x7fcf401c3a800x7fce3f824140319682319682249812557464655362370362672452329094987717216792842150018167928421068281679284254234616792842544326
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261753791753794194304256001624184960x7fcf401c39000x7fce3f824180317314317314238722538520655362329822172435182093365858816792842585005167928425423461679284296410516792842966153
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291753791753794194304256001624192000x7fcf401c37800x7fce3f8241c0167206167206150601337656655361079488871238392043352598416792843006082167928429641051679284328698416792843289053
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321753791753794194304256001624199040x7fcf401c36000x7fce3f824200168081168081155041344656655361056172771239895042419752416792843328591167928432869841679284361130316792843613503
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351753791753794194304256001224206080x7fcf4a0c64800x7fce3f824240168194168194161321345560655361104064951242867044335410416792843666801167928436113031679284393898116792843941112
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381753791753794194304256001624213120x7fcf4a0c63000x7fce3f824280317394317394245502539160655362371550142435280095034980816792843983141167928439389811679284435322016792844355249
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411753791753794194304256001624220160x7fcf4a0c61800x7fce3f8242c0317416317416247972539336655362302643812426582092278900016792844396058167928443532201679284477033816792844772566
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441753791753794194304256001624227200x7fcf4a0c60000x7fce3f824300166282166282157371330264655361045046221226278041974714016792844813395167928447703381679284510169716792845103656
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471753791753794194304256001224234240x7fcf401c3e800x7fce3f824340168038168038155171344312655361115129171243154044778296816792845144405167928451016971679284542537616792845427386
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501753791753794194304256001224241280x7fcf401c3d000x7fce3f824380166605166605164001332848655361105140501229244044377798416792845476434167928454253761679284574969516792845751895
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531753791753794194304256001624248320x7fcf401c3b800x7fce3f8243c0315832315832245672526664655362341646062420848093839021216792845793444167928457496951679284616441316792846166712
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561753791753794194304256001624255360x7fcf401c3a000x7fce3f824400314767314767239572518144655362271681162411625091040799616792846207911167928461644131679284659145216792846593399
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591753791753794194304256001224262400x7fcf401c38800x7fce3f824440168785168785157131350288655361109924951247054044570444416792846633478167928465914521679284691417016792846916409
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621753791753794194304256001224269440x7fcf401c37000x7fce3f824480167940167940146521343528655361095770081241608044002896416792846956528167928469141701679284725624916792847257708
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651753791753794194304256001224276480x7fcf4a0c65800x7fce3f8244c0166697166697157791333584655361100617161231074044197796016792847306637167928472562491679284755912816792847560759
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681753791753794194304256001624286080x7fcf4a0c64000x7fce3f824500319841319841244402558736655362368150752459750094899260016792847606327167928475591281679284795448716792847955796
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711753791753794194304256001624293120x7fcf4a0c62800x7fce3f824540314496314496234322515976655362298236862410723092102496416792847998435167928479544871679284834232516792848343894
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741753791753794194304256001224300160x7fcf4a0c61000x7fce3f824580166832166832157721334664655361096256251233269044023853216792848387102167928483423251679284864296416792848644364
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077175379175379419430425600824309760x7fcf401c3f800x7fce3f8245c0168643168643147081349152655361060230201246751042581680016792848686633167928486429641679284894296316792848944565
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801753791753794194304256001224316800x7fcf401c3e000x7fce3f824600166196166196162221329576655361129119051225470045335994816792848993563167928489429631679284924392216792849245465
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831753791753794194304256001624326400x7fcf401c3c800x7fce3f824640314215314215246122513728655362322053492406232093055715216792849287104167928492439221679284963736116792849639013
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861753791753794194304256001224336000x7fcf401c3b000x7fce3f824680313140313140232272505128655362271700802398851091041152816792849682222167928496373611679285002311916792850024691
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891753791753794194304256001224345600x7fcf401c39800x7fce3f8246c0166425166425155701331408655361076778871227474043243870816792850065470167928500231191679285033319816792850334991
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092175379175379419430425600824355200x7fcf401c38000x7fce3f824700169115169115160721352928655361002989261247637040291842416792850376640167928503331981679285063655716792850638102
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951753791753794194304256001224362240x7fcf401c36800x7fce3f824740165829165829154581326640655361058241071224631042502443616792850686020167928506365571679285093943616792850940902
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981753791753794194304256001224371840x7fcf4a0c65000x7fce3f824780313266313266247962506136655362322131102399764093058667216792850987151167928509394361679285133751416792851338950
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011753791753794194304256001224381440x7fcf4a0c63800x7fce3f8247c0312976312976249502503816655362273602002395518091117178016792851381248167928513375141679285172359316792851725098
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041753791753794194304256001224391040x7fcf4a0c62000x7fce3f824800167475167475157091339808655361006266351236940040423020816792851766126167928517235931679285202695216792852028368
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107175379175379419430425600824403200x7fcf4a0c60800x7fce3f824840169643169643156151357152655361007530101255043040473063216792852069757167928520269521679285232487116792852326219
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101753791753794194304256001224412800x7fcf401c3f000x7fce3f824880168059168059155631344480655361089619181242153043757492816792852374977167928523248711679285262919016792852630639
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131753791753794194304256001224422400x7fcf401c3d800x7fce3f8248c0314481314481250582515856655362340078232412456093776075616792852671358167928526291901679285301558816792853017107
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161753791753794194304256001224432000x7fcf401c3c000x7fce3f824900312068312068229442496552655362272217472391867091061986016792853059096167928530155881679285339974716792853401325
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119175379175379419430425600824441600x7fcf401c3a800x7fce3f824940169121169121152941352976655361074133871249941043137976016792853441874167928533997471679285369478616792853696346
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221753791753794194304256001224453760x7fcf401c39000x7fce3f824980170513170513164971364112655361024118181256688041137078016792853737854167928536947861679285399446516792853995916
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251753791753794194304256001224463360x7fcf401c37800x7fce3f8249c0166790166790153371334328655361088024871229269043692978416792854044965167928539944651679285431014316792854311796
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281753791753794194304256001224475520x7fcf401c36000x7fce3f824a00309952309952255222479624655362309542712375957092554755616792854353285167928543101431679285469606216792854697404
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311753791753794194304256001224485120x7fcf4a0c64800x7fce3f824a40304008304008217512432072655362187699202330678087681186816792854740703167928546960621679285507670116792855078142
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134175379175379419430425600824494720x7fcf4a0c63000x7fce3f824a8016594616594615211132757665536997655971223525040079269216792855119821167928550767011679285537286016792855374433
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371753791753794194304256001224506880x7fcf4a0c61800x7fce3f824ac0167910167910171011343288655361010216521239554040581939616792855416412167928553728601679285567093816792855672433
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401753791753794194304256001224516480x7fcf4a0c60000x7fce3f824b00167000167000156551336008655361009134181225021040538080416792855721512167928556709381679285597589716792855977334
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431753791753794194304256001224528640x7fcf401c3e800x7fce3f824b40308360308360245802466888655362291463922364573091831539216792856019083167928559758971679285636693616792856368352
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461753791753794194304256001224540800x7fcf401c3d000x7fce3f824b80305326305326230032442616655362209660122336744088559468416792856409950167928563669361679285675605416792856757479
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149175379175379419430425600824552960x7fcf401c3b800x7fce3f824bc016747616747615322133981665536976112051235958039216715616792856797968167928567560541679285705525316792857056850
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521753791753794194304256001224567680x7fcf401c3a000x7fce3f824c00169937169937168881359504655361053395531254081042308253616792857098119167928570552531679285735541216792857356800
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551753791753794194304256001224577280x7fcf401c38800x7fce3f824c40168254168254163471346040655361008851311230405040525966016792857405509167928573554121679285765413116792857655531
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581753791753794194304256001224589440x7fcf401c37000x7fce3f824c80306169306169248632449360655362259964922344113090572030816792857701580167928576541311679285804229016792858043879
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611753791753794194304256001224601600x7fcf4a0c65800x7fce3f824cc0306630306630236732453048655362203003262344096088292928016792858093407167928580422901679285843332816792858435006
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164175379175379419430425600824613760x7fcf4a0c64000x7fce3f824d00170627170627164921365024655361022902791255202041088541616792858477365167928584333281679285873444716792858735887
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671753791753794194304256001224628480x7fcf4a0c62800x7fce3f824d40173068173068168221384552655361052390761280034042269414016792858776986167928587344471679285904452616792859046157
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701753791753794194304256001224638080x7fcf4a0c61000x7fce3f824d80167087167087163881336704655361023329401226282041105484016792859095786167928590445261679285934644516792859347838
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731753791753794194304256001224650240x7fcf401c3f800x7fce3f824dc0304928304928243342439432655362221876672333491089048711616792859392316167928593464451679285973220416792859733736
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761753791753794194304256001224662400x7fcf401c3e000x7fce3f824e00306957306957239772455664655362195386232347655087989053616792859774764167928597322041679286011588216792860117314
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179175379175379419430425600824674560x7fcf401c3c800x7fce3f824e4016861616861615685134893665536974714381243952039161628816792860157732167928601158821679286041140116792860412864
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821753791753794194304256001224689280x7fcf401c3b000x7fce3f824e80176886176886167491415096655361121540641311652045034860816792860455073167928604114011679286071636016792860717835
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851753791753794194304256001224701440x7fcf401c39800x7fce3f824ec0167346167346160131338776655361006287211230038040424117216792860766733167928607163601679286101955916792861020925
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881753791753794194304256001224716160x7fcf401c38000x7fce3f824f00303483303483235012427872655362202921542316766088289967216792861062304167928610195591679286140499716792861406453
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911753791753794194304256001224728320x7fcf401c36800x7fce3f824f40303480303480235792427848655362223490392319885089112933216792861448272167928614049971679286178499616792861786331
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194175379175379419430425600824740480x7fcf4a0c65000x7fce3f824f8016824216824215525134594465536988365451240470039706981216792861827510167928617849961679286208307516792862087332
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971753791753794194304256001224757760x7fcf4a0c63800x7fce3f824fc0182736182736172511461896655361083436291357734043512067616792862127401167928620830751679286239731416792862398742
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001753791753794194304256001224769920x7fcf4a0c62000x7fce3f825000166216166216162811329736655361023703691223191041120324416792862460530167928623973141679286269939316792862700883
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031753791753794194304256001224784640x7fcf4a0c60800x7fce3f825040305080305080251242440648655362159804512328490086565868416792862746631167928626993931679286309251116792863094000
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061753791753794194304256001224799360x7fcf401c3f000x7fce3f825080305546305546243852444376655362209331392339698088546532416792863136379167928630925111679286348275016792863484228
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209175379175379419430425600824814080x7fcf401c3d800x7fce3f8250c016830816830815395134647265536991327171244091039826734416792863525017167928634827501679286378338916792863784728
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121753791753794194304256001224831360x7fcf401c3c000x7fce3f825100192876192876186011543016655361108386771429368044509692816792863825607167928637833891679286409746816792864099049
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151753791753794194304256001224843520x7fcf401c3a800x7fce3f825140167176167176152941337416655361042411511232996041869226016792864147257167928640974681679286439650716792864398079
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181753791753794194304256001224858240x7fcf401c39000x7fce3f825180302402302402226752419224655362140675692315723085801343616792864443418167928643965071679286478274516792864784167
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211753791753794194304256001224872960x7fcf401c37800x7fce3f8251c0304465304465245872435728655362233600302330002089517070016792864826196167928647827451679286516738416792865168905
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241753791753794194304256001224887680x7fcf401c36000x7fce3f825200168817168817155181350544655361001226641247832040221764016792865209574167928651673841679286546850316792865469955
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271753791753794194304256001224907520x7fcf4a0c64800x7fce3f825240202029202029181941616240655361175372281499468047189400416792865511514167928654685031679286579426116792865795675
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301753791753794194304256001224919680x7fcf4a0c63000x7fce3f825280168303168303159571346432655361038740951240900041722398416792865844894167928657942611679286610162016792866103135
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331753791753794194304256001224934400x7fcf4a0c61800x7fce3f8252c0306052306052243472448424655362261413792342010090629735216792866145844167928661016201679286649025916792866491683
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361753791753794194304256001224949120x7fcf4a0c60000x7fce3f825300301441301441227462411536655362152760672303240086283705616792866535872167928664902591679286687729716792866878651
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391753791753794194304256001224963840x7fcf401c3e800x7fce3f825340168408168408163091347272655361019858311244569040966721616792866919240167928668772971679286717777616792867179252
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421753791753794194304256001224983680x7fcf401c3d000x7fce3f825380210184210184189011681480655361362052491576007054656169616792867220500167928671777761679286750753516792867509061
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451753791753794194304256001224995840x7fcf401c3b800x7fce3f8253c016815316815315559134523265536997526521242641040073452816792867557860167928675075351679286780977416792867811422
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024817537917537941943042560012241013120x7fcf401c3a000x7fce3f825400304350304350249782434808655362149533692328241086155149616792867852531167928678097741679286820049316792868201960
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025117537917537941943042560012241027840x7fcf401c38800x7fce3f825440306499306499237852452000655362205591732348126088396844816792868243868167928682004931679286858609116792868587687
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025417537917537941943042560012241042560x7fcf401c37000x7fce3f825480168120168120155591344968655361020935811243804041010489216792868628826167928685860911679286888641016792868887758
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025717537917537941943042560012241062400x7fcf4a0c65800x7fce3f8254c0219347219347192991754784655361362750991642713054684778416792868928767167928688864101679286921856916792869220058
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026017537917537941943042560012241077120x7fcf4a0c64000x7fce3f825500167096167096162321336776655361006630011233514040438454016792869269176167928692185691679286952160816792869523088
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026317537917537941943042560016241094400x7fcf4a0c62800x7fce3f825540301461301461230332411696655362199058242302501088136001216792869569407167928695216081679286991120616792869912536
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026617537917537941943042560016241111680x7fcf4a0c61000x7fce3f825580301238301238224982409912655362172457702303649087071483216792869953845167928699112061679287031024516792870311693
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691753791753794194304256008241128960x7fcf401c3f800x7fce3f8255c0170412170412160331363304655361034018591260389041533533616792870353012167928703102451679287061968416792870621124
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027217537917537941943042560012241151360x7fcf401c3e000x7fce3f825600228675228675200251829408655361526626631724149061239294416792870661982167928706196841679287095920316792870960813
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027517537917537941943042560012241166080x7fcf401c3c800x7fce3f825640168115168115168521344928655361017843051236751040886139616792871008671167928709592031679287126464116792871265963
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027817537917537941943042560016241183360x7fcf401c3b000x7fce3f825680298104298104222512384840655362052643922275367082279907616792871307532167928712646411679287165088016792871652241
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028117537917537941943042560016241200640x7fcf401c39800x7fce3f8256c0302864302864231192422920655362149837082313930086167306416792871693790167928716508801679287203359916792872035079
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028417537917537941943042560012241217920x7fcf401c38000x7fce3f825700170727170727158761365824655361060699611263742042601320416792872075638167928720335991679287233567816792872337040
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028717537917537941943042560012241240320x7fcf401c36800x7fce3f825740238277238277200901906224655361632736581802522065483790016792872377928167928723356781679287268559616792872686999
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029017537917537941943042560012241255040x7fcf4a0c65000x7fce3f825780168360168360164661346888655361017731001240656040882238016792872735177167928726855961679287298879516792872990369
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029317537917537941943042560012241274880x7fcf4a0c63800x7fce3f8257c0301139301139218912409120655362077800552301131083285569216792873033028167928729887951679287337695416792873378267
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029617537917537941943042560012241292160x7fcf4a0c62000x7fce3f825800300792300792224772406344655362134225982298839085542443616792873420415167928733769541679287376191216792873763455
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029917537917537941943042560012241309440x7fcf4a0c60800x7fce3f825840172715172715164841381728655361073597391279338043118983216792873805653167928737619121679287406623116792874067575
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030217537917537941943042560012241334400x7fcf401c3f000x7fce3f825880258582258582211582068664655361721627491957131069040109216792874110024167928740662311679287442479016792874426184
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030517537917537941943042560012241349120x7fcf401c3d800x7fce3f8258c0168175168175163971345408655361012972721240261040692033216792874475742167928744247901679287473022916792874731564
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030817537917537941943042560012241368960x7fcf401c3c000x7fce3f825900299640299640213252397128655362093837942294200083928205216792874772933167928747302291679287511694716792875118382
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031117537917537941943042560012241388800x7fcf401c3a800x7fce3f825940301231301231231812409856655362124804762305774085166264416792875159811167928751169471679287550094616792875502400
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031417537917537941943042560012241408640x7fcf401c39000x7fce3f825980178572178572171011428584655361036148781320071041619669216792875543139167928755009461679287580974516792875811290
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031717537917537941943042560012241436160x7fcf401c37800x7fce3f8259c0281121281121226592248976655361791630482131379071840225216792875852459167928758097451679287618190316792876183249
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032017537917537941943042560012241453440x7fcf401c36000x7fce3f825a00168100168100168401344808655361025879871234755041208176016792876231817167928761819031679287649150216792876493079
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032317537917537941943042560012241475840x7fcf4a0c64800x7fce3f825a40301317301317229482410544655362097135882302387084059164816792876539058167928764915021679287688334116792876884817
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032617537917537941943042560012241495680x7fcf4a0c63000x7fce3f825a80303192303192246832425544655362150266162313058086184841216792876926945167928768833411679287726893916792877270455
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032917537917537941943042560012241515520x7fcf4a0c61800x7fce3f825ac0187445187445186491499568655361064052061376994042736731216792877311643167928772689391679287759245816792877594034
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033217537917537941943042560012241543040x7fcf4a0c60000x7fce3f825b00300214300214237392401720655362006184772286537080422204416792877635103167928775924581679287797901716792877980422
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033517537917537941943042560012241562880x7fcf401c3e800x7fce3f825b40173049173049169891384400655361036573131278119041637380016792878029281167928779790171679287829101616792878292753
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033817537917537941943042560012241587840x7fcf401c3d000x7fce3f825b80302390302390225832419128655362001508392309446080234648416792878334071167928782910161679287868093416792878682350
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034117537917537941943042560012241610240x7fcf401c3b800x7fce3f825bc0303057303057228672424464655362091122942319447083818810016792878723959167928786809341679287906685316792879068108
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034417537917537941943042560012241632640x7fcf401c3a000x7fce3f825c00206533206533186541652272655361257009581537662050455764016792879109227167928790668531679287939053216792879392018
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034717537917537941943042560012241665280x7fcf401c38800x7fce3f825c40341459341459262522731680655362312489232613191092675322816792879433467167928793905321679287980077016792879846674
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035017537917537941943042560012241685120x7fcf401c37000x7fce3f825c80184310184310182121474488655361232987961367102049493529616792879865433167928798007701679288014332916792880144714
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035317537917537941943042560012241712640x7fcf4a0c65800x7fce3f825cc0302003302003220002416032655362008814182310773080527634816792880186553167928801433291679288053196816792880533372
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035617537917537941943042560012241737600x7fcf4a0c64000x7fce3f825d00303498303498222982427992655362063870702323427082730210816792880575791167928805319681679288092268616792880924070
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035917537917537941943042560012241762560x7fcf4a0c62800x7fce3f825d40225491225491194971803936655361339801591695018053767596816792880968448167928809226861679288126604516792881267519
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036217537917537941943042560012241797760x7fcf4a0c61000x7fce3f825d803812683812682747230501526553626033578329374180104310152416792881308887167928812660451679288170028316792881719884
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036517537917537941943042560012241822720x7fcf401c3f800x7fce3f825dc0211337211337190611690704655361256225341580936050424630016792881750834167928817002831679288203804216792882039444
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036817537917537941943042560012241855360x7fcf401c3e000x7fce3f825e00307553307553249152460432655362041530982350385081838864816792882087913167928820380421679288245596016792882477671
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037117537917537941943042560012241885440x7fcf401c3c800x7fce3f825e40311655311655238932493248655361948897022376677078132657616792882499420167928824559601679288285931916792882879728
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037417537917537941943042560012241915520x7fcf401c3b000x7fce3f825e80267485267485216742139888655361630428792029450065394154016792882901567167928828593191679288322443816792883225747
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037717537917537941943042560012241958400x7fcf401c39800x7fce3f825ec04623834623833169336990726553632705635435845390130998492816792883266836167928832244381679288370955616792883730171
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038017537917537941943042560012241985920x7fcf401c38000x7fce3f825f00243299243299206621946400655361690259301841316067784687616792883759910167928837095561679288406443516792884065791
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038317537917537941943042560012242023680x7fcf401c36800x7fce3f825f40335723335723239902685792655362060492182564367082597062016792884106310167928840644351679288447627316792884493757
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038617537917537941943042560012242058880x7fcf4a0c65000x7fce3f825f80331041331041230522648336655362084702572524982083564175616792884519057167928844762731679288488587216792884903265
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038917537917537941943042560012242094080x7fcf4a0c63800x7fce3f825fc0306711306711237112453696655362090137822344942083781264016792884927704167928848858721679288528507016792885286383
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039217537917537941943042560012242144640x7fcf4a0c62000x7fce3f8260005426415426413602643411366553640634661442258680162715340416792885327881167928852850701679288582778816792885846425
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039517537917537941943042560012242177280x7fcf4a0c60800x7fce3f826040271773271773222192174192655361916445902068246076833602416792885879944167928858277881679288620746716792886209014
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039817537917537941943042560012242220160x7fcf401c3f000x7fce3f826080364357364357268442914864655362427016602795062097259239616792886251332167928862074671679288664426516792886686869
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040117537917537941943042560012242260480x7fcf401c3d800x7fce3f8260c03657613657612938529260966553625312942128100480101427689216792886697748167928866442651679288709626416792887138214
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040417537917537941943042560012242300800x7fcf401c3c000x7fce3f826100346692346692254832773544655362474996272666126099176960016792887149754167928870962641679288752986216792887571731
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040717537917537941943042560012242359040x7fcf401c3a800x7fce3f8261406242326242324016949938646553646651653848759070186782917616792887582800167928875298621679288813642016792888178402
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041017537917537941943042560012242394240x7fcf401c39000x7fce3f826180304516304516234812436136655361962151392323234078663101216792888205081167928881364201679288855545816792888556890
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041317537917537941943042560012242442240x7fcf401c37800x7fce3f8261c03990743990742738431926006553627338508430814550109532373216792888598038167928885554581679288900969716792889052984
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041617537917537941943042560012242487680x7fcf401c36000x7fce3f8262003919683919682787731357526553627989421630219340112135249616792889064094167928890096971679288948009516792889522119
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041917537917537941943042560012242533120x7fcf4a0c64800x7fce3f8262403882083882082800631056726553628012173429896670112225349216792889534119167928894800951679288993913316792889957106
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221753791753794194304256008242555520x7fcf4a0c63000x7fce3f8262807185687185684502257485526553653340563256327380213536316816792889982145167928899391331679289060233116792890648274
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042517537917537941943042560012242598400x7fcf4a0c61800x7fce3f8262c03658763658762810129270166553625731979728041840103103897616792890668373167928906023311679289105832916792891101850
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042817537917537941943042560012242656640x7fcf4a0c60000x7fce3f8263004686524686523196937492246553635022911136409610140269815616792891113739167928910583291679289158264716792891624333
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043117537917537941943042560012242712320x7fcf401c3e800x7fce3f8263404728504728503198237828086553634612877636734450138629384016792891636103167928915826471679289210648516792892150327
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341753791753794194304256008242732160x7fcf401c3d000x7fce3f8263804853984853983440238831926553634244736237514060137153031616792892161516167928921064851679289262536316792892667311
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371753791753794194304256008242757120x7fcf401c3b800x7fce3f8263c08802348802345309870418806553668702950569356480274985862816792892678930167928926253631679289340248016792893444656
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044017537917537941943042560012242807680x7fcf401c3a000x7fce3f8264004271564271562985834172566553630004694233044770120195925616792893465106167928934024801679289388855916792893906642
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044317537917537941943042560012242876160x7fcf401c38800x7fce3f8264405493345493343610343946806553640915281942875840163839911616792893931001167928938885591679289444775716792894492853
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044617537917537941943042560012242942080x7fcf401c37000x7fce3f8264805510125510123626344081046553641255301242995220165199433216792894504163167928944477571679289502615516792895072195
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491753791753794194304256008242969600x7fcf4a0c65800x7fce3f8264c05634725634723620745077846553641633702043953020166709061216792895084005167928950261551679289559703216792895639987
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521753791753794194304256008242999680x7fcf4a0c64000x7fce3f826500104226810422686243183381526553679966365782189230320039592816792895651107167928955970321679289648518916792896532659
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551753791753794194304256008243027200x7fcf4a0c62800x7fce3f8265407220027220024487557760246553653986330156622510216119348016792896552539167928964849321679289715932916792897208678
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045817537917537941943042560012243054720x7fcf4a0c61000x7fce3f8265807242087242084589357936726553655817061656722000223442372816792897220718167928971593291679289787612516792897920086
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046117537917537941943042560012243082240x7fcf401c3f800x7fce3f8265c07227027227024443257816246553654633399756598220218707838016792897931105167928978761251679289858652216792898632793
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641753791753794194304256008243109760x7fcf401c3e000x7fce3f8266007272877272874529858183046553654349054356967440217570438016792898644643167928985865221679289928331916792899328901
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671753791753794194304256008243132160x7fcf401c3c800x7fce3f826640136888813688887738410951112655361060573322108147960424403542016792899340771167928992833191679290038907416792900435027
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701753791753794194304256008243159680x7fcf401c3b000x7fce3f826680137112413711247776410969000655361073826064108425530429704608816792900455116167929003890741679290149083016792901556101
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047317537917537941943042560012243187200x7fcf401c39800x7fce3f8266c0137325613732567754810986056655361075277290108622400430285074016792901568691167929014908301679290263626516792902706585
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047617537917537941943042560012243214720x7fcf401c38000x7fce3f826700137069513706957746510965568655361071497348108435100428772980016792902719195167929026362651679290378714016792903852809
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791753791753794194304256008243242240x7fcf401c36800x7fce3f826740137791213779127685311023304655361074148799108808190429833729216792903864509167929037871401679290491081516792904983954
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821753791753794194304256008243264640x7fcf4a0c65000x7fce3f8267802661612266161214283621292904655362128465729211836170851560473616792904995333167929049108151679290687752716792906949282
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851753791753794194304256008243292160x7fcf4a0c63800x7fce3f8267c02669004266900414299621352040655362127225666212259670851064381616792906969461167929068775271679290881495916792908882491
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048817537917537941943042560012243319680x7fcf4a0c62000x7fce3f8268002668964266896414333521351720655362134640821212371510854030382416792908894691167929088149591679291080167116792910873258
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049117537917537941943042560012243347200x7fcf4a0c60800x7fce3f8268402670820267082014336321366568655362117835991212299440847308514016792910886248167929108016711679291279894316792912865576
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941753791753794194304256008243374720x7fcf401c3f000x7fce3f8268802673572267357214357921388584655362120013542212590210848179582016792912877856167929127989431679291473925416792914809795
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049717537917537941943042560082400x7fcf401c3d800x7fce3f8268c052578365257836274170420626966553642325409424192579901693190517616792914822314167929147392541679291837235916792918444090