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

44 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjGRBM_COUNTGRBM_GUI_ACTIVESQ_WAVESSQ_IFETCHSQ_IFETCH_LEVELSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000169067169067335544322560043241600x00x7fc9f180428038105438105452428847185926850187666244016686012409410166853352666241668615944131616686159553545
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00216906716906732768256001224138880x00x7fc9f1823f8033513335135128192605968438016686164716134166861594413161668616484544616686164850159
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051690671690674194304256001224143360x7fc9f47573800x7fc9f1823fc0163951163951655369175041400011572134816686164888588166861648454461668616522000316686165222817
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081690671690674194304256001624150400x7fc9f47572000x7fc9f18240003100833100836553611141121698841900514016686165261276166861652200031668616563376116686165636313
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111690671690674194304256001624154880x7fc9f47570800x7fc9f1824040309152309152655369175041400141562825216686165672022166861656337611668616603983916686166042350
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141690671690674194304256001224159360x7fc9f2103f000x7fc9f18240801648221648226553610485761594071784376016686166098478166861660398391668616637279716686166375239
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171690671690674194304256001224163840x7fc9f2103d800x7fc9f18240c0163906163906655369830401478161655706416686166409467166861663727971668616669263516686166695048
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201690671690674194304256001224170880x7fc9f2103c000x7fc9f18241001622461622466553611141121637661824688416686166742936166861666926351668616700783416686167010237
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231690671690674194304256001624177920x7fc9f2103a800x7fc9f18241403079003079006553613107201952842191478416686167045306166861670078341668616741391116686167416254
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261690671690674194304256001624184960x7fc9f21039000x7fc9f18241803064243064246553611796481784821998093216686167449903166861674139111668616782814916686167830530
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291690671690674194304256001624192000x7fc9f21037800x7fc9f18241c01639561639566553612451841895982121541216686167864699166861678281491668616814158816686168143880
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321690671690674194304256001624199040x7fc9f21036000x7fc9f18242001642161642166553612451842018622262401616686168179769166861681415881668616845390616686168456409
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351690671690674194304256001224206080x7fc9f47574800x7fc9f18242401641691641696553612451841889012111032816686168499778166861684539061668616876910416686168771389
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381690671690674194304256001624213120x7fc9f47573000x7fc9f18242803078843078846553614417922161282418007616686168808218166861687691041668616917086216686169173236
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411690671690674194304256001624220160x7fc9f47571800x7fc9f18242c03079073079076553613107201981802217213616686169209064166861691708621668616957278016686169575212
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441690671690674194304256001624227200x7fc9f47570000x7fc9f18243001640041640046553613762562059472308493216686169610821166861695727801668616988829816686169890582
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471690671690674194304256001224234240x7fc9f2103e800x7fc9f18243401628711628716553614417922155902413936416686169926481166861698882981668617021245616686170214951
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501690671690674194304256001224241280x7fc9f2103d000x7fc9f18243801621461621466553613107201957932187554416686170256850166861702124561668617054381416686170545550
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531690671690674194304256001624248320x7fc9f2103b800x7fc9f18243c03087733087736553615728642349832632455216686170581839166861705438141668617092125216686170923038
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561690671690674194304256001624255360x7fc9f2103a000x7fc9f18244003057263057266553614417922095272346350816686170958746166861709212521668617129693016686171298695
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591690671690674194304256001224262400x7fc9f21038800x7fc9f18244401633381633386553615073282247802520444816686171334004166861712969301668617158220916686171583936
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621690671690674194304256001224269440x7fc9f21037000x7fc9f18244801625991625996553616384002447642742072016686171620104166861715822091668617186716716686171868846
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651690671690674194304256001224276480x7fc9f47575800x7fc9f18244c01624941624946553614417922214822484574016686171911635166861718671671668617215884616686172160617
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681690671690674194304256001624286080x7fc9f47574000x7fc9f18245003064133064136553617039362538452835988016686172196515166861721588461668617253276316686172534524
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711690671690674194304256001624293120x7fc9f47572800x7fc9f18245403065183065186553615728642329582616070816686172570643166861725327631668617290844116686172910252
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741690671690674194304256001224300160x7fc9f47571000x7fc9f18245801624281624286553616384002494612787748816686172945300166861729084411668617319836016686173200042
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077169067169067419430425600824309760x7fc9f2103f800x7fc9f18245c01627761627766553618350082735243065442016686173235881166861731983601668617348731816686173489092
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801690671690674194304256001224316800x7fc9f2103e000x7fc9f18246001624411624416553615073282249642511480816686173531111166861734873181668617377643716686173778313
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831690671690674194304256001624326400x7fc9f2103c800x7fc9f18246403059703059706553618350082915413257775216686173813572166861737764371668617415579516686174157780
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861690671690674194304256001224336000x7fc9f2103b000x7fc9f18246803085593085596553617039362479082785044016686174193209166861741557951668617453563316686174537328
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891690671690674194304256001224345600x7fc9f21039800x7fc9f18246c01628241628246553617694722645172965872016686174573066166861745356331668617482651116686174828228
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092169067169067419430425600824355200x7fc9f21038000x7fc9f18247001630591630596553620316163035853396101216686174863047166861748265111668617513162916686175133438
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951690671690674194304256001224362240x7fc9f21036800x7fc9f18247401624581624586553616384002455252758328816686175176206166861751316291668617542746816686175429178
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981690671690674194304256001224371840x7fc9f47575000x7fc9f18247803055893055896553619660802892243232648016686175463817166861754274681668617580842616686175810135
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011690671690674194304256001224381440x7fc9f47573800x7fc9f18247c03034703034706553618350082718683048351616686175845874166861758084261668617618074416686176182443
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041690671690674194304256001224391040x7fc9f47572000x7fc9f18248001623291623296553619005442824133163316016686176217352166861761807441668617646778216686176469584
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107169067169067419430425600824403200x7fc9f47570800x7fc9f18248401636281636286553622282243278543673172416686176505122166861764677821668617675722016686176759034
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101690671690674194304256001224412800x7fc9f2103f000x7fc9f18248801616721616726553617039362536352840582416686176801443166861767572201668617704633916686177048094
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131690671690674194304256001224422400x7fc9f2103d800x7fc9f18248c03056363056366553620971523108773478869216686177083903166861770463391668617742265716686177424432
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161690671690674194304256001224432000x7fc9f2103c000x7fc9f18249003022943022946553619660802837753176805616686177460351166861774226571668617780569516686177807469
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119169067169067419430425600824441600x7fc9f2103a800x7fc9f18249401621941621946553620316163009763380953616686177842868166861778056951668617809417316686178096040
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221690671690674194304256001224453760x7fc9f21039000x7fc9f18249801624101624106553624248323615364046454416686178131688166861780941731668617839177116686178393610
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251690671690674194304256001224463360x7fc9f21037800x7fc9f18249c01611161611166553618350082743503074784816686178435028166861783917711668617868521016686178686910
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281690671690674194304256001224475520x7fc9f21036000x7fc9f1824a003052983052986553622282243278653673192816686178723869166861786852101668617906152816686179063287
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311690671690674194304256001224485120x7fc9f47574800x7fc9f1824a403005913005916553620971523102723476188816686179099646166861790615281668617943624616686179437925
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134169067169067419430425600824494720x7fc9f47573000x7fc9f1824a801608641608646553621626883201223586374816686179473684166861794362461668617972456416686179726385
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371690671690674194304256001224506880x7fc9f47571800x7fc9f1824ac01617411617416553626214403865524330674416686179762224166861797245641668618001368316686180015606
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401690671690674194304256001224516480x7fc9f47570000x7fc9f1824b001607401607406553619660802928963278367216686180057984166861800136831668618030328116686180305066
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431690671690674194304256001224528640x7fc9f2103e800x7fc9f1824b403022333022336553623592963584664011521216686180342825166861803032811668618067847916686180680234
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461690671690674194304256001224540800x7fc9f2103d000x7fc9f1824b803016463016466553622282243361253766492416686180715293166861806784791668618105591716686181057641
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149169067169067419430425600824552960x7fc9f2103b800x7fc9f1824bc01617831617836553622937603445463852817616686181092240166861810559171668618134487516686181346662
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521690671690674194304256001224567680x7fc9f2103a000x7fc9f1824c001621771621776553627525124070484566320816686181382530166861813448751668618164183416686181643582
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551690671690674194304256001224577280x7fc9f21038800x7fc9f1824c401624831624836553620316163178543551513216686181686040166861816418341668618193719216686181938842
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581690671690674194304256001224589440x7fc9f21037000x7fc9f1824c803018173018176553624903683673734105909616686181974611166861819371921668618232167016686182323429
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611690671690674194304256001224601600x7fc9f47575800x7fc9f1824cc03006793006796553623592963602714035756816686182359468166861823216701668618270022816686182702107
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164169067169067419430425600824613760x7fc9f47574000x7fc9f1824d001628331628336553624248323777474229310816686182737345166861827002281668618298678616686182988497
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671690671690674194304256001224628480x7fc9f47572800x7fc9f1824d401686591686596553629491204444984983442816686183023966166861829867861668618327926516686183280967
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701690671690674194304256001224638080x7fc9f47571000x7fc9f1824d801625391625396553621626883402433812976816686183324346166861832792651668618357878316686183580588
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731690671690674194304256001224650240x7fc9f2103f800x7fc9f1824dc03001683001686553626214403881514345821616686183616596166861835787831668618396278116686183964555
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761690671690674194304256001224662400x7fc9f2103e000x7fc9f1824e002998302998306553624903683617834056556016686184000554166861839627811668618433813916686184339992
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179169067169067419430425600824674560x7fc9f2103c800x7fc9f1824e401626601626606553625559043834494291174016686184374881166861843381391668618462885716686184630583
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821690671690674194304256001224689280x7fc9f2103b000x7fc9f1824e801754441754446553631457284654235219875216686184665901166861846288571668618492629616686184928093
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851690671690674194304256001224701440x7fc9f21039800x7fc9f1824ec01601811601816553622282243413543823211616686184971171166861849262961668618521189416686185213593
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881690671690674194304256001224716160x7fc9f21038000x7fc9f1824f003003363003366553627525124058834547658816686185248282166861852118941668618558741216686185589181
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911690671690674194304256001224728320x7fc9f21036800x7fc9f1824f402994742994746553626214403888424354736816686185624880166861855874121668618595893016686185960719
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194169067169067419430425600824740480x7fc9f47575000x7fc9f1824f801610561610566553626869763978664464651216686185995227166861859589301668618625908816686186261309
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971690671690674194304256001224757760x7fc9f47573800x7fc9f1824fc01828901828906553633423365190505800288816686186296627166861862590881668618657156716686186573408
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001690671690674194304256001224769920x7fc9f47572000x7fc9f18250001615911615916553623592963570774001286416686186624826166861865715671668618686276516686186864509
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031690671690674194304256001224784640x7fc9f47570800x7fc9f18250402986182986186553628835844289044804226416686186900157166861868627651668618723876316686187240566
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061690671690674194304256001224799360x7fc9f2103f000x7fc9f18250803003383003386553626869764177814677462816686187275725166861872387631668618761604116686187617784
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209169067169067419430425600824814080x7fc9f2103d800x7fc9f18250c01633091633096553628180484156644650868016686187653132166861876160411668618790547916686187907324
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121690671690674194304256001224831360x7fc9f2103c000x7fc9f18251001920181920186553635389445366266007712416686187943403166861879054791668618821299816686188214854
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151690671690674194304256001224843520x7fc9f2103a800x7fc9f18251401609261609266553624248323638174084208016686188256732166861882129981668618850435616686188506114
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181690671690674194304256001224858240x7fc9f21039000x7fc9f18251802997902997906553630146564614555168060416686188540493166861885043561668618888243416686188884391
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211690671690674194304256001224872960x7fc9f21037800x7fc9f18251c02988122988126553628180484159864658375616686188919440166861888824341668618925635216686189258069
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241690671690674194304256001224887680x7fc9f21036000x7fc9f18252001623261623266553629491204430254959668016686189293778166861892563521668618954755016686189549409
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271690671690674194304256001224907520x7fc9f47574800x7fc9f18252402021422021426553637355525664596346453216686189585008166861895475501668618986338916686189865199
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301690671690674194304256001224919680x7fc9f47573000x7fc9f18252801618641618646553625559043867254329432416686189907578166861898633891668619016082716686190162729
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331690671690674194304256001224934400x7fc9f47571800x7fc9f18252c03003743003746553631457284807615385965216686190198808166861901608271668619054002516686190541866
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361690671690674194304256001224949120x7fc9f47570000x7fc9f18253003000083000086553629491204348124868177216686190577785166861905400251668619091410316686190915914
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391690671690674194304256001224963840x7fc9f2103e800x7fc9f18253401620291620296553630801924630585193731216686190951023166861909141031668619120674116686191208564
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421690671690674194304256001224983680x7fc9f2103d000x7fc9f18253802112282112286553639321605890476590040016686191243783166861912067411668619153714016686191538993
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451690671690674194304256001224995840x7fc9f2103b800x7fc9f18253c01612581612586553626214403903494372246016686191581012166861915371401668619183009816686191831934
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024816906716906741943042560012241013120x7fc9f2103a000x7fc9f18254003012253012256553632768004883395469557616686191865703166861918300981668619220929616686192211011
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025116906716906741943042560012241027840x7fc9f21038800x7fc9f18254402968502968506553630801924540255079336416686192246600166861922092961668619258225416686192584009
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025416906716906741943042560012241042560x7fc9f21037000x7fc9f18254801611111611116553632112644809345381176816686192618558166861925822541668619287169216686192873439
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025716906716906741943042560012241062400x7fc9f47575800x7fc9f18254c02195762195766553641287686196186930150016686192909238166861928716921668619319761016686193199418
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026016906716906741943042560012241077120x7fc9f47574000x7fc9f18255001606051606056553627525124116014607709616686193242477166861931976101668619348512916686193487019
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026316906716906741943042560016241094400x7fc9f47572800x7fc9f18255402988562988566553634078725059385671637616686193521968166861934851291668619386032716686193862086
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026616906716906741943042560016241111680x7fc9f47571000x7fc9f18255802970872970876553632112644782835361528816686193897305166861938603271668619423696516686194238984
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691690671690674194304256008241128960x7fc9f2103f800x7fc9f18255c01619961619966553632768005007985607696416686194275333166861942369651668619452864316686194530374
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027216906716906741943042560012241151360x7fc9f2103e000x7fc9f18256002299052299056553643253766470677255982816686194566203166861945286431668619485872116686194860473
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027516906716906741943042560012241166080x7fc9f2103c800x7fc9f18256401617781617786553628180484264714765516816686194903692166861948587211668619515248016686195154383
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027816906716906741943042560016241183360x7fc9f2103b000x7fc9f18256802956352956356553635389445371906021345616686195188872166861951524801668619552255816686195524211
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028116906716906741943042560016241200640x7fc9f21039800x7fc9f18256c02989722989726553634078725035685637850016686195559520166861955225581668619589727616686195899099
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028416906716906741943042560012241217920x7fc9f21038000x7fc9f18257001626611626616553634078725183155804517216686195934827166861958972761668619618943416686196191269
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028716906716906741943042560012241240320x7fc9f21036800x7fc9f18257402382872382876553645219846828407642179216686196227708166861961894341668619652799216686196529798
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029016906716906741943042560012241255040x7fc9f47575000x7fc9f18257801605871605876553630146564489425036328016686196572046166861965279921668619681535116686196817138
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029316906716906741943042560012241274880x7fc9f47573800x7fc9f18257c02984812984816553638010885741496427541216686196851997166861968153511668619719486916686197196656
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029616906716906741943042560012241292160x7fc9f47572000x7fc9f18258002981172981176553636700165636626306359216686197232044166861971948691668619756878716686197570573
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029916906716906741943042560012241309440x7fc9f47570800x7fc9f18258401693731693736553636700165436036080114816686197606702166861975687871668619786270516686197864543
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030216906716906741943042560012241334400x7fc9f2103f000x7fc9f18258802592472592476553649152007380488273562416686197899332166861978627051668619821214316686198214002
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030516906716906741943042560012241349120x7fc9f2103d800x7fc9f18258c01601751601756553631457284656895216045216686198257940166861982121431668619851406116686198515852
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030816906716906741943042560012241368960x7fc9f2103c000x7fc9f18259002974432974436553640632326023696737137216686198550461166861985140611668619888701916686198888779
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031116906716906741943042560012241388800x7fc9f2103a800x7fc9f18259402965912965916553639321605845456544197216686198924248166861988870191668619925917716686199261047
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031416906716906741943042560012241408640x7fc9f21039000x7fc9f18259801788911788916553639321605917016624756816686199295676166861992591771668619956445616686199566237
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031716906716906741943042560012241436160x7fc9f21037800x7fc9f18259c02795402795406553653084167968308938924816686199601406166861995644561668619992813416686199929935
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032016906716906741943042560012241453440x7fc9f21036000x7fc9f1825a001616761616766553633423364975065567825616686199972903166861999281341668620022557216686200227295
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032316906716906741943042560012241475840x7fc9f47574800x7fc9f1825a402959962959966553643253766504687288213616686200262734166862002255721668620060237016686200604113
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032616906716906741943042560012241495680x7fc9f47573000x7fc9f1825a802933362933366553641943046438447215791216686200639871166862006023701668620097404816686200975930
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032916906716906741943042560012241515520x7fc9f47571800x7fc9f1825ac01860461860466553641943046323827085852416686201011199166862009740481668620128092616686201282740
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033216906716906741943042560012241543040x7fc9f47570000x7fc9f1825b003004303004306553657016328566509596495616686201318379166862012809261668620165852416686201660337
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033516906716906741943042560012241562880x7fc9f2103e800x7fc9f1825b401709001709006553637355525550326215620016686201702446166862016585241668620195644316686201958338
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033816906716906741943042560012241587840x7fc9f2103d000x7fc9f1825b802980642980646553648496647798838727855216686201992816166862019564431668620234172016686202343435
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034116906716906741943042560012241610240x7fc9f2103b800x7fc9f1825bc02978322978326553647185927321788196624016686202379064166862023417201668620272395816686202725762
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034416906716906741943042560012241632640x7fc9f2103a000x7fc9f1825c002070722070726553647185927361228235203616686202760981166862027239581668620304219716686203044072
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034716906716906741943042560012241665280x7fc9f21038800x7fc9f1825c4033977033977065536648806498895211075363216686203079140166862030421971668620344363416686203489327
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035016906716906741943042560012241685120x7fc9f21037000x7fc9f1825c801839341839346553641287686364177134010016686203510526166862034436341668620377867316686203780507
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035316906716906741943042560012241712640x7fc9f47575800x7fc9f1825cc02965062965066553653739528347089351171216686203816456166862037786731668620415563116686204157245
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035616906716906741943042560012241737600x7fc9f47574000x7fc9f1825d002980812980816553652428808276269273317216686204192383166862041556311668620453930816686204541112
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035916906716906741943042560012241762560x7fc9f47572800x7fc9f1825d402252372252376553652428807862858808017216686204576011166862045393081668620487146716686204873241
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036216906716906741943042560012241797760x7fc9f47571000x7fc9f1825d80380596380596655367274496114945212875090416686204908350166862048714671668620530538416686205325336
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036516906716906741943042560012241822720x7fc9f2103f800x7fc9f1825dc02113032113036553649152007445058334626016686205350075166862053053841668620564538216686205647235
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036816906716906741943042560012241855360x7fc9f2103e000x7fc9f1825e00304548304548655366422528103533311596240416686205683264166862056453821668620603690016686206039232
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037116906716906741943042560012241885440x7fc9f2103c800x7fc9f1825e40312770312770655366291456102587311483097216686206073761166862060369001668620643161816686206479998
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037416906716906741943042560012241915520x7fc9f2103b000x7fc9f1825e8026570126570165536629145695409510684792016686206492427166862064316181668620682041616686206822136
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037716906716906741943042560012241958400x7fc9f21039800x7fc9f1825ec0461221461221655368847360133626714961002816686206858045166862068204161668620729929316686207345179
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038016906716906741943042560012241985920x7fc9f21038000x7fc9f1825f002432412432416553657016328626829653761616686207365068166862072992931668620767577116686207677488
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038316906716906741943042560012242023680x7fc9f21036800x7fc9f1825f40333259333259655367471104116117612986188016686207714667166862076757711668620808008916686208125553
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038616906716906741943042560012242058880x7fc9f47575000x7fc9f1825f80331653331653655367340032115546912943273616686208136263166862080800891668620851608716686208558569
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038916906716906741943042560012242094080x7fc9f47573800x7fc9f1825fc0306261306261655367340032112593112591011616686208570218166862085160871668620893592416686208937786
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039216906716906741943042560012242144640x7fc9f47572000x7fc9f18260005437045437046553610420224158936117808546016686208973815166862089359241668620946584116686209509257
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039516906716906741943042560012242177280x7fc9f47570800x7fc9f182604027254827254865536648806499969611187877216686209530026166862094658411668620985735916686209859235
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039816906716906741943042560012242220160x7fc9f2103f000x7fc9f1826080367785367785655368519680136659815297180016686209894094166862098573591668621028407716686210330420
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040116906716906741943042560012242260480x7fc9f2103d800x7fc9f18260c0364803364803655368388608131841614774186416686210342539166862102840771668621074551416686210790405
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040416906716906741943042560012242300800x7fc9f2103c000x7fc9f1826100347802347802655368388608129101014456692816686210802414166862107455141668621118167216686211223770
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040716906716906741943042560012242359040x7fc9f2103a800x7fc9f18261406243036243036553611993088184712320683716816686211236360166862111816721668621178966916686211831850
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041016906716906741943042560012242394240x7fc9f21039000x7fc9f1826180304471304471655367274496112934512649571616686211851070166862117896691668621220134716686212203088
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041316906716906741943042560012242442240x7fc9f21037800x7fc9f18261c0396881396881655369568256151336516950611616686212239907166862122013471668621264454416686212687352
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041616906716906741943042560012242487680x7fc9f21036000x7fc9f1826200390594390594655369437184151264316933598816686212698802166862126445441668621311222216686213154646
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041916906716906741943042560012242533120x7fc9f47574800x7fc9f1826240388467388467655369437184145982116358434016686213167226166862131122221668621357221916686213614671
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221690671690674194304256008242555520x7fc9f47573000x7fc9f18262807199857199856553616056320230442725809071216686213625311166862135722191668621424581516686214291059
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042516906716906741943042560012242598400x7fc9f47571800x7fc9f18262c0363510363510655368847360136790615322224416686214311758166862142458151668621469861316686214743244
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042816906716906741943042560012242656640x7fc9f47570000x7fc9f18263004678454678456553611665408179913720140738816686214754304166862146986131668621521909016686215261287
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043116906716906741943042560012242712320x7fc9f2103e800x7fc9f18263404702924702926553611468800181991020379438816686215272986166862152190901668621573748716686215780130
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341690671690674194304256008242732160x7fc9f2103d000x7fc9f18263804834274834276553614090240202104622643262416686215791059166862157374871668621625940416686216301712
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371690671690674194304256008242757120x7fc9f2103b800x7fc9f18263c08796028796026553619202048275864430911279616686216313442166862162594041668621703908016686217080976
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044016906716906741943042560012242807680x7fc9f2103a000x7fc9f18264004267414267416553610420224160365217963838016686217101576166862170390801668621752435716686217567020
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044316906716906741943042560012242876160x7fc9f21038800x7fc9f18264405478145478146553613762560217726624383474816686217579290166862175243571668621809603416686218119622
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044616906716906741943042560012242942080x7fc9f21037000x7fc9f18264805495725495726553613565952213806123950880816686218133901166862180960341668621865123116686218696323
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491690671690674194304256008242969600x7fc9f47575800x7fc9f18264c05632185632186553615466496222730324945875216686218708212166862186512311668621922370816686219265984
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521690671690674194304256008242999680x7fc9f47574000x7fc9f1826500104151310415136553622347776320970435950410016686219277143166862192237081668622010370316686220146285
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551690671690674194304256008243027200x7fc9f47572800x7fc9f18265407225577225576553620250624290624132565359616686220166244166862201037031668622077426016686220821442
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045816906716906741943042560012243054720x7fc9f47571000x7fc9f18265807227917227916553620447232294292532968720416686220833812166862207742601668622146913616686221512989
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046116906716906741943042560012243082240x7fc9f2103f800x7fc9f18265c07220617220616553619595264281930931568422016686221524969166862214691111668622216766716686222219896
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641690671690674194304256008243109760x7fc9f2103e000x7fc9f18266007246857246856553620381696292660332793366816686222233105166862221676671668622286766216686222914573
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671690671690674194304256008243132160x7fc9f2103c800x7fc9f1826640136983313698336553631522816451327250546278816686222927252166862228676621668622397853616686224026496
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701690671690674194304256008243159680x7fc9f2103b000x7fc9f1826680136903113690316553638993920558915262616959216686224046685166862239785361668622507213016686225137669
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047316906716906741943042560012243187200x7fc9f21039800x7fc9f18266c0137351113735116553639124992560709162800056016686225150449166862250721301668622621628316686226283471
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047616906716906741943042560012243214720x7fc9f21038000x7fc9f1826700136989313698936553638469632551019161714470016686226295331166862262162831668622735995716686227426813
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791690671690674194304256008243242240x7fc9f21036800x7fc9f1826740137533013753306553639059456559912562707638016686227439153166862273599571668622847899116686228545846
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821690671690674194304256008243264640x7fc9f47575000x7fc9f1826780266395526639556553660489728865085796903973616686228557025166862284789911668623044570016686230517760
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851690671690674194304256008243292160x7fc9f47573800x7fc9f18267c026696302669630655367726694411057256123834691216686230539490166862304457001668623238520916686232452656
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048816906716906741943042560012243319680x7fc9f47572000x7fc9f182680026703252670325655367739801611072561124032105216686232465106166862323852091668623437127816686234442770
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049116906716906741943042560012243347200x7fc9f47570800x7fc9f182684026697502669750655367621836810906222122138150416686234456080166862343712781668623636518716686236435254
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941690671690674194304256008243374720x7fc9f2103f000x7fc9f182688026737282673728655367733248011071993124009167216686236447754166862363651871668623830597716686238378739
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049716906716906741943042560082400x7fc9f2103d800x7fc9f18268c0525634352563436553612025856017191805192561248816686238391659166862383059771668624196131716686242032858