Files
rocm-systems/tests/workloads/mixbench2/mi100/SQ_INST_LEVEL_VMEM.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

43 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_VMEMSQ_INST_LEVEL_VMEMSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000765125765130335544322560083264640x00x7f1f67204180104857611164777142923904012073467472462070120734677158064811207346771613128012073467716223251
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00276512576513032768256002424124800x00x7f1f6723510040961157251481785212073467730930413120734677312404511207346773124701112073467731258703
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0047651257651304194304256002424129280x7f20972e59000x7f1f6723514052428811904931152380558412073467731354080120734677315258891207346773165964912073467731663165
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0067651257651304194304256003624136320x7f20972e58000x7f1f6723518052428812792363163744827612073467731756979120734677319249281207346773217644712073467732222715
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0087651257651304194304256002824140800x7f20972e57000x7f1f672351c052428814131644180881066412073467732291332120734677324662051207346773271484412073467732758280
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00107651257651304194304256002424145280x7f20972e56000x7f1f6723520052428811177346143071495612073467732825345120734677329911631207346773312620212073467733129720
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00127651257651304194304256002424149760x7f20972e55000x7f1f6723524052428812606907161364887212073467733193849120734677333606011207346773349116112073467733494358
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00147651257651304194304256002424154240x7f20972e54000x7f1f6723528052428811828883151416516812073467733586088120734677337474791207346773388091912073467733884092
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00167651257651304194304256002824161280x7f20972e53000x7f1f672352c052428814250642182401388412073467733947660120734677341205981207346773436651712073467734409749
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00187651257651304194304256002824168320x7f20972e5a000x7f1f6723530052428813377886171233140812073467734432662120734677346202751207346773487259412073467734913595
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00207651257651304194304256002424175360x7f20972e59000x7f1f6723534052428811944871152889412412073467734937239120734677351324331207346773526475312073467735268194
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00227651257651304194304256002424182400x7f20972e58000x7f1f6723538052428812393409158618915212073467735328306120734677354917921207346773562507112073467735628354
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00247651257651304194304256002424189440x7f20972e57000x7f1f672353c052428812595801161222175612073467735697402120734677358586701207346773598890912073467735992150
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00267651257651304194304256002824199040x7f20972e56000x7f1f6723540052428813722627175645367212073467736052141120734677362140281207346773647002712073467736512487
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00287651257651304194304256002824206080x7f20972e55000x7f1f6723544052428813140875168200742412073467736539797120734677367153061207346773697082512073467737018116
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00307651257651304194304256002424213120x7f20972e54000x7f1f6723548052428812819847164093938012073467737042031120734677372273041207346773735546312073467737358849
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00327651257651304194304256002424220160x7f20972e53000x7f1f672354c052428812002575153627123212073467737416647120734677375775421207346773771082212073467737714130
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00347651257651304194304256002424227200x7f20972e5a000x7f1f6723550052428812934253165563439212073467737784360120734677379439401207346773807226012073467738075672
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00367651257651304194304256002824236800x7f20972e59000x7f1f6723554052428814273962182700866012073467738134281120734677382976991207346773854953812073467738591130
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00387651257651304194304256002824243840x7f20972e58000x7f1f6723558052428814260194182526862812073467738613631120734677387976971207346773904905612073467739091239
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00407651257651304194304256002424250880x7f20972e57000x7f1f672355c052428812590690161156337612073467739112659120734677393013741207346773943177412073467739435028
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00427651257651304194304256002424257920x7f20972e56000x7f1f6723560052428811256730144085162412073467739495671120734677396565731207346773979193212073467739795187
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00447651257651304194304256002424264960x7f20972e55000x7f1f6723564052428812478517159722699212073467739863815120734677400298511207346774016009012073467740163682
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00467651257651304194304256002824277120x7f20972e54000x7f1f6723568052428812727518162919332412073467740220197120734677403821691207346774063928812073467740680522
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00487651257651304194304256002824284160x7f20972e53000x7f1f672356c052428813020527166654681612073467740705188120734677408840871207346774114008612073467741182946
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00507651257651304194304256002424291200x7f20972e5a000x7f1f6723570052428813164330168497594412073467741209325120734677413863251207346774151464412073467741517808
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00527651257651304194304256002424300800x7f20972e59000x7f1f6723574052428812800208163833352012073467741576528120734677417399231207346774187000312073467741873329
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00547651257651304194304256002424307840x7f20972e58000x7f1f6723578052428812793405163745103212073467741943970120734677421085621207346774223832112073467742241684
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00567651257651304194304256002824320000x7f20972e57000x7f1f672357c052428811618586148722446412073467742299271120734677424589601207346774271527912073467742755569
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00587651257651304194304256002824329600x7f20972e56000x7f1f6723580052428813380870171275266812073467742779022120734677429594381207346774321559712073467743260818
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00607651257651304194304256002424339200x7f20972e55000x7f1f6723584052428812631798161683269612073467743283570120734677434703161207346774360023512073467743603464
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00627651257651304194304256002424348800x7f20972e54000x7f1f6723588052428811939594152822912412073467743661001120734677438208741207346774399703312073467744005782
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00647651257651304194304256002424358400x7f20972e53000x7f1f672358c052428812225704156495194812073467744071664120734677442346321207346774436615212073467744369568
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00667651257651304194304256002824373120x7f20972e5a000x7f1f6723590052428813391489171413396412073467744428127120734677445872711207346774484838912073467744889063
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00687651257651304194304256002824382720x7f20972e59000x7f1f6723594052428814263111182568164812073467744915553120734677450975081207346774535030712073467745392840
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00707651257651304194304256002424392320x7f20972e58000x7f1f6723598052428812362779158255062412073467745417796120734677455959061207346774572886512073467745732210
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00727651257651304194304256002424401920x7f20972e57000x7f1f672359c052428812077629154584292012073467745789958120734677459499841207346774612342412073467746127154
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00747651257651304194304256002424411520x7f20972e56000x7f1f67235a0052428811641155148997771212073467746193668120734677463586231207346774649206212073467746495639
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00767651257651304194304256002824426240x7f20972e55000x7f1f67235a4052428813451688172174962812073467746553316120734677467111011207346774696534012073467747013021
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00787651257651304194304256002824435840x7f20972e54000x7f1f67235a8052428814203952181803840812073467747040081120734677472189391207346774746853812073467747510615
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00807651257651304194304256002424445440x7f20972e53000x7f1f67235ac052428812872195164771099612073467747532326120734677477101361207346774783957612073467747843053
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00827651257651304194304256002424457600x7f20972e5a000x7f1f67235b0052428812291264157330655612073467747901101120734677480578151207346774819157412073467748195037
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00847651257651304194304256002424467200x7f20972e59000x7f1f67235b4052428811174749143038999612073467748267502120734677484278931207346774856229312073467748565606
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00867651257651304194304256002824484480x7f20972e58000x7f1f67235b8052428813921533178191597612073467748623474120734677487832521207346774904885012073467749089800
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00887651257651304194304256002824494080x7f20972e57000x7f1f67235bc052428814232490182178596412073467749115969120734677492933291207346774958084812073467749622901
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00907651257651304194304256002424503680x7f20972e56000x7f1f67235c0052428812276567157127948012073467749645443120734677498277271207346774995988612073467749963253
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00927651257651304194304256002424515840x7f20972e55000x7f1f67235c4052428811216693143566044012073467750031079120734677501941251207346775033316512073467750336617
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00947651257651304194304256002424525440x7f20972e54000x7f1f67235c8052428810978312140528550012073467750405956120734677505672441207346775070292312073467750706294
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00967651257651304194304256002824542720x7f20972e53000x7f1f67235cc052428813999164179189954812073467750763711120734677509230821207346775119076112073467751236189
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00987651257651304194304256002824554880x7f20972e5a000x7f1f67235d0052428813004315166452679612073467751264071120734677514421201207346775169779812073467751738502
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001007651257651304194304256002424567040x7f20972e59000x7f1f67235d4052428812614457161458749612073467751760223120734677519416371207346775207187712073467752075549
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001027651257651304194304256002424581760x7f20972e58000x7f1f67235d8052428810410984133254552812073467752135891120734677522977961207346775243827512073467752441709
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001047651257651304194304256002424593920x7f20972e57000x7f1f67235dc052428811853986151735010412073467752510587120734677526686741207346775280131312073467752804714
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001067651257651304194304256002824613760x7f20972e56000x7f1f67235e0052428812448644159344963612073467752863052120734677530270721207346775328963112073467753331613
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001087651257651304194304256002824625920x7f20972e55000x7f1f67235e4052428813193225168869268812073467753355147120734677535384301207346775379522912073467753836391
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001107651257651304194304256002424638080x7f20972e54000x7f1f67235e8052428812886389164938098012073467753858352120734677540414681207346775416962712073467754173437
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001127651257651304194304256002424652800x7f20972e53000x7f1f67235ec05242889556459122323148012073467754233780120734677543982661207346775453762612073467754540970
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001147651257651304194304256002424664960x7f20972e5a000x7f1f67235f0052428812716314162771410812073467754610470120734677547691451207346775489842412073467754901871
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001167651257651304194304256002824684800x7f20972e59000x7f1f67235f4052428813649718174712619612073467754957555120734677551235431207346775538610212073467755409685
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001187651257651304194304256002824696960x7f20972e58000x7f1f67235f8052428814123489180776834012073467755451783120734677556088211207346775585570012073467755877584
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001207651257651304194304256002424709120x7f20972e57000x7f1f67235fc052428812048398154214112012073467755920604120734677560825791207346775621505812073467756218518
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001227651257651304194304256002424723840x7f20972e56000x7f1f67236000524288780983399967070812073467756276646120734677564376171207346775657697612073467756580381
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001247651257651304194304256002424736000x7f20972e55000x7f1f6723604052428810436447133594128412073467756648537120734677568067351207346775694561512073467756949246
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001267651257651304194304256002824758400x7f20972e54000x7f1f6723608052428812324685157759845612073467757009598120734677571737741207346775743505312073467757458552
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001287651257651304194304256002824770560x7f20972e53000x7f1f672360c052428812758362163302362012073467757500831120734677576571321207346775791697012073467757938524
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001307651257651304194304256002424782720x7f20972e5a000x7f1f6723610052428812110279155000260812073467757983248120734677581464091207346775827824912073467758281612
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001327651257651304194304256002424800000x7f20972e59000x7f1f67236140524288741543394930500812073467758338418120734677584990481207346775864256712073467758646180
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001347651257651304194304256002424812160x7f20972e58000x7f1f6723618052428812786143163664300012073467758713996120734677588747261207346775900464512073467759008312
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001367651257651304194304256002824834560x7f20972e57000x7f1f672361c052428811282040144404041612073467759065940120734677592259241207346775948832312073467759511087
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001387651257651304194304256002824849280x7f20972e56000x7f1f6723620052428814176218181455565212073467759553977120734677597121621207346775997088112073467759993173
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001407651257651304194304256002424864000x7f20972e55000x7f1f6723624052428811339231145132166012073467760039459120734677601964801207346776033103912073467760334577
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001427651257651304194304256002424881280x7f20972e54000x7f1f67236280524288623131479742763612073467760392164120734677605500781207346776070095812073467760704565
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001447651257651304194304256002424896000x7f20972e53000x7f1f672362c052428810836144138699754812073467760790004120734677609494371207346776108575612073467761089540
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001467651257651304194304256002824920960x7f20972e5a000x7f1f6723630052428813189200168815940812073467761148289120734677613083151207346776157535412073467761596713
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001487651257651304194304256002824935680x7f20972e59000x7f1f6723634052428813663454174893556012073467761640624120734677617959931207346776205263212073467762075432
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001507651257651304194304256002424950400x7f20972e58000x7f1f6723638052428811790813150921265612073467762117801120734677622915111207346776242511012073467762428659
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001527651257651304194304256002424967680x7f20972e57000x7f1f672363c0524288480851461535565612073467762484222120734677626438291207346776280286812073467762806280
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001547651257651304194304256002424982400x7f20972e56000x7f1f6723640052428811238063143847361612073467762878585120734677630457471207346776318078712073467763184363
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015676512576513041943042560028241007360x7f20972e55000x7f1f6723644052428810882773139289692412073467763240638120734677634009461207346776366078412073467763682669
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015876512576513041943042560028241022080x7f20972e54000x7f1f6723648052428812386923158545449612073467763725649120734677638822231207346776414110212073467764164916
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016076512576513041943042560024241036800x7f20972e53000x7f1f672364c052428811321465144916013612073467764208396120734677643707011207346776450654112073467764510087
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016276512576513041943042560024241056640x7f20972e5a000x7f1f67236500524288428273854823541612073467764563015120734677647331001207346776489949912073467764903117
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016476512576513041943042560024241071360x7f20972e59000x7f1f6723654052428811799773151034377612073467764971755120734677651350181207346776526941712073467765273285
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016676512576513041943042560028241098880x7f20972e58000x7f1f672365805242889883222126492460812073467765328538120734677654886161207346776574973512073467765770770
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016876512576513041943042560028241113600x7f20972e57000x7f1f672365c052428812746033163146395612073467765813770120734677659697341207346776622749312073467766249219
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017076512576513041943042560024241128320x7f20972e56000x7f1f6723660052428811463111146731502012073467766292229120734677664519721207346776658509112073467766588580
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017276512576513041943042560024241148160x7f20972e55000x7f1f67236640524288370334047389320412073467766644914120734677668014101207346776697597012073467766979486
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017476512576513041943042560024241162880x7f20972e54000x7f1f6723668052428812476371159688194012073467767052131120734677672174081207346776734860812073467767352349
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017676512576513041943042560028241190400x7f20972e53000x7f1f672366c05242888648918110714263212073467767409746120734677675706871207346776782716612073467767848601
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017876512576513041943042560028241207680x7f20972e5a000x7f1f6723670052428812775435163522952412073467767897592120734677680746851207346776833420312073467768356325
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018076512576513041943042560024241224960x7f20972e59000x7f1f6723674052428810821550138517199212073467768398162120734677685553221207346776869388212073467768697489
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018276512576513041943042560024241247360x7f20972e58000x7f1f67236780524288372817147711359212073467768755517120734677689148411207346776909804012073467769101550
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018476512576513041943042560024241264640x7f20972e57000x7f1f672367c052428811752794150436972012073467769174736120734677693378791207346776947099812073467769474513
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018676512576513041943042560020241279360x7f20972e56000x7f1f67236800524288425680354471086012073467769530517120734677696901971207346776999083612073467770015618
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018876512576513041943042560028241296640x7f20972e55000x7f1f6723684052428812656051161993689612073467770068076120734677702301951207346777049275412073467770514205
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019076512576513041943042560024241313920x7f20972e54000x7f1f6723688052428812835249164298362012073467770562404120734677707242731207346777085451212073467770858134
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019276512576513041943042560024241336320x7f20972e53000x7f1f672368c0524288349569544747850412073467770913988120734677710823511207346777127355012073467771295827
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019476512576513041943042560024241353600x7f20972e5a000x7f1f6723690052428811494105147121069612073467771351330120734677715100291207346777164506812073467771648603
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019676512576513041943042560020241368320x7f20972e59000x7f1f67236940524288288215136885520012073467771702854120734677718625071207346777214490612073467772167307
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019876512576513041943042560028241385600x7f20972e58000x7f1f6723698052428813266149169801584812073467772210367120734677723701851207346777263018412073467772651146
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020076512576513041943042560024241402880x7f20972e57000x7f1f672369c052428811446539146520399612073467772693866120734677728516231207346777298666212073467772990196
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020276512576513041943042560024241427840x7f20972e56000x7f1f67236a00524288345090744190546812073467773049837120734677732097011207346777341946012073467773441856
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020476512576513041943042560024241447680x7f20972e55000x7f1f67236a4052428811195501143299029212073467773496778120734677736573791207346777379385912073467773797436
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020676512576513041943042560020241457280x7f20972e54000x7f1f67236a80524288257893033012669212073467773853450120734677740136981207346777432345612073467774344944
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020876512576513041943042560028241477120x7f20972e53000x7f1f67236ac052428813898958177904309212073467774388234120734677745480951207346777480185412073467774823303
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021076512576513041943042560024241496960x7f20972e5a000x7f1f67236b0052428811796659150990904812073467774865802120734677750301731207346777516473312073467775168454
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021276512576513041943042560024241521920x7f20972e59000x7f1f67236b40524288341099643654437612073467775227213120734677753896921207346777561721112073467775638929
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021476512576513041943042560024241541760x7f20972e58000x7f1f67236b8052428811163625142892596812073467775697918120734677758583291207346777599592912073467775999699
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021676512576513041943042560020241556480x7f20972e57000x7f1f67236bc0524288246062431500231212073467776056134120734677762157681207346777654472612073467776566492
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021876512576513041943042560028241576320x7f20972e56000x7f1f67236c0052428814182092181528802012073467776610805120734677767717651207346777702696412073467777048278
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022076512576513041943042560024241596160x7f20972e55000x7f1f67236c4052428810746725137553355612073467777091698120734677772514431207346777739064312073467777394241
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022276512576513041943042560024241623680x7f20972e54000x7f1f67236c80524288344926244162720412073467777450695120734677776088821207346777785496012073467777876096
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022476512576513041943042560024241646080x7f20972e53000x7f1f67236cc05242889936453127189053612073467777934354120734677780999191207346777824023912073467778243869
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022676512576513041943042560020241663360x7f20972e5a000x7f1f67236d00524288239011930578744812073467778299964120734677784603701207346777883780912073467778862760
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022876512576513041943042560028241685760x7f20972e59000x7f1f67236d4052428813295392170182175212073467778901291120734677790726871207346777933860612073467779360134
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023076512576513041943042560024241708160x7f20972e58000x7f1f67236d8052428810300058131837542412073467779400509120734677795589251207346777969588512073467779698322
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023276512576513041943042560024241740800x7f20972e57000x7f1f67236dc0524288335565942958738812073467779756020120734677799149241207346778022484312073467780249447
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023476512576513041943042560024241765760x7f20972e56000x7f1f67236e005242888385515107326893212073467780304559120734677804666021207346778060564212073467780608153
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023676512576513041943042560020241777920x7f20972e55000x7f1f67236e40524288233890129925354012073467780665650120734677808237211207346778127124012073467781294449
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023876512576513041943042560028241802880x7f20972e54000x7f1f67236e805242889451627120980057212073467781336908120734677814957191207346778175555812073467781775843
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024076512576513041943042560024241827840x7f20972e53000x7f1f67236ec05242887856352100558606012073467781817110120734677819734781207346778211299712073467782115975
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024276512576513041943042560024241863040x7f20972e5a000x7f1f67236f00524288344265644074073212073467782174324120734677823352371207346778265091612073467782670827
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024476512576513041943042560024241893120x7f20972e59000x7f1f67236f40524288369763747334688412073467782727121120734677828859551207346778303987412073467783042678
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024676512576513041943042560020241907840x7f20972e58000x7f1f67236f80524288232425729742205212073467783100094120734677832661141207346778378467212073467783805706
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024876512576513041943042560028241937920x7f20972e57000x7f1f67236fc05242887943928101679173212073467783849056120734677840073911207346778430643012073467784327906
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025076512576513041943042560024241968000x7f20972e56000x7f1f67237000524288347121844420967612073467784370916120734677845352301207346778468994912073467784692674
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025276512576513041943042560024242010880x7f20972e55000x7f1f67237040524288353280345216615612073467784748678120734677849072291207346778529298712073467785316243
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025476512576513041943042560024242046080x7f20972e54000x7f1f67237080524288343563643983717212073467785374902120734677855390671207346778571666612073467785719181
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025676512576513041943042560020242060800x7f20972e53000x7f1f672370c0524288235272330124450412073467785776728120734677859355451207346778654818312073467786571255
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025876512576513041943042560028242096000x7f20972e5a000x7f1f67237100524288447832157308294812073467786615237120734677867758631207346778710290212073467787125685
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026076512576513041943042560024242131200x7f20972e59000x7f1f67237140524288341264643678423612073467787172903120734677873336211207346778751234012073467787515219
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026276512576513041943042560024242181760x7f20972e58000x7f1f67237180524288332492142574094012073467787572776120734677877352201207346778819089812073467788213216
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026476512576513041943042560024242222080x7f20972e57000x7f1f672371c0524288323723541431972412073467788274731120734677884363371207346778863649712073467788658243
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026676512576513041943042560020242239360x7f20972e56000x7f1f67237200524288235653030176920012073467788705561120734677888649761207346778956817412073467789593181
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026876512576513041943042560028242279680x7f20972e55000x7f1f67237240524288350601244880988812073467789633846120734677897971331207346779017137212073467790192154
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027076512576513041943042560024242320000x7f20972e54000x7f1f67237280524288328985042117288812073467790242057120734677904072111207346779061105112073467790630729
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027276512576513041943042560024242378240x7f20972e53000x7f1f672372c0524288436493255871310012073467790674210120734677908326501207346779135904812073467791380803
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027476512576513041943042560024242423680x7f20972e5a000x7f1f67237300524288315056040324283212073467791438079120734677916000081207346779182368712073467791843383
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027676512576513041943042560020242435840x7f20972e59000x7f1f67237340524288229107429341384412073467791887725120734677920524861207346779285168412073467792872415
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027876512576513041943042560028242481280x7f20972e58000x7f1f67237380524288349566644752284012073467792917228120734677930817631207346779350304212073467793525739
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028076512576513041943042560024242526720x7f20972e57000x7f1f672373c0524288309377639586454412073467793566565120734677937304011207346779395696012073467793978871
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028276512576513041943042560024242592640x7f20972e56000x7f1f67237400524288468095359917635612073467794027702120734677941907191207346779478751812073467794810897
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028476512576513041943042560024242648320x7f20972e55000x7f1f67237440524288329205442131188812073467794863034120734677950302371207346779529887612073467795320104
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028676512576513041943042560020242663040x7f20972e54000x7f1f67237480524288235731630156631212073467795364737120734677955252751207346779651119212073467796531495
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028876512576513041943042560028242718720x7f20972e53000x7f1f672374c0524288318428340744848012073467796581287120734677967431911207346779725871012073467797281058
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029076512576513041943042560024242774400x7f20972e5a000x7f1f67237500524288339290643418387612073467797330159120734677974926291207346779776462812073467797784654
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029276512576513041943042560012242799360x7f20972e59000x7f1f67237540524288218948828020154812073467797834867120734677979972671207346779874046512073467798763733
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029476512576513041943042560024242865280x7f20972e58000x7f1f67237580524288332416742545072812073467798823565120734677989863841207346779930270312073467799323804
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029676512576513041943042560020242880000x7f20972e57000x7f1f672375c0524288229503629359040812073467799366864120734677995263831207346780069677912073467800718316
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029876512576513041943042560032242945920x7f20972e56000x7f1f67237600524288321081741083008812073467800766585120734678009287781207346780153981612073467801561843
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030076512576513041943042560024243011840x7f20972e55000x7f1f67237640524288332616142560215212073467801607909120734678017702161207346780208909512073467802110803
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030276512576513041943042560012243049600x7f20972e54000x7f1f67237680524288224788628763107612073467802164523120734678023367741207346780321485112073467803237447
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030476512576513041943042560024243136000x7f20972e53000x7f1f672376c0524288325787841707856812073467803297789120734678034593301207346780389100912073467803911540
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030676512576513041943042560020243148160x7f20972e5a000x7f1f67237700524288231459429619040812073467803960952120734678041290881207346780567852312073467805723126
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030876512576513041943042560020243175680x7f20972e59000x7f1f67237740524288227551229134399612073467805752581120734678059329231207346780673036012073467806771074
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031076512576513041943042560012243203200x7f20972e58000x7f1f67237780524288216719927747498012073467806794488120734678069745191207346780738923812073467807431071
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031276512576513041943042560012243240960x7f20972e57000x7f1f672377c0524288232111329725054812073467807460465120734678076412371207346780880123412073467808842744
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031476512576513041943042560012243288960x7f20972e56000x7f1f67237800524288225677428869790412073467808885383120734678090540331207346780983995012073467809882226
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031676512576513041943042560020243301120x7f20972e55000x7f1f67237840524288264413733839947612073467809911260120734678100924291207346781314314012073467813168302
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031876512576513041943042560020243328640x7f20972e54000x7f1f67237880524288231872929696510012073467813271705120734678134351391207346781497929412073467815021847
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032076512576513041943042560012243356160x7f20972e53000x7f1f672378c0524288219169528055151212073467815099982120734678152661731207346781605689112073467816099089
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032276512576513041943042560012243393920x7f20972e5a000x7f1f67237900524288252808032349043212073467816129015120734678163095301207346781859144312073467818633940
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032476512576513041943042560012243441920x7f20972e59000x7f1f67237940524288252969432377683612073467818706244120734678188685621207346782040407712073467820446548
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032676512576513041943042560020243454080x7f20972e58000x7f1f67237980524288292194137401674812073467820527970120734678206979961207346782675253712073467826798312
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032876512576513041943042560020243481600x7f20972e57000x7f1f672379c0524288311290039817786812073467826877790120734678270478961207346783008868712073467830133029
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033076512576513041943042560012243509120x7f20972e56000x7f1f67237a00524288246986031603866012073467830209562120734678303805261207346783192052112073467831964102
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332765125765130419430425600122400x7f20972e55000x7f1f67237a40524288255901832758070412073467832059049120734678322227601207346783674946612073467836795300