Comhaid
rocm-systems/tests/workloads/Axes4/mi200/SQ_INST_LEVEL_VMEM.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

41 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_VMEMSQ_INST_LEVEL_VMEMSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000219465219465335544322560043241600x00x7f435e404280524288549400261523364817538702437295175364121035891753885156276417538851655314
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00221946521946532768256001224138880x00x7f435e423f80409638020426304417538856858391175388515627641753885698645217538856991047
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0052194652194654194304256001224143360x7f436130f3800x7f435e423fc052428810652073119301383217538857025677175388569864521753885735525217538857357628
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0082194652194654194304256001624150400x7f436130f2000x7f435e42400052428811435156128072432417538857394017175388573552521753885775957317538857761958
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00112194652194654194304256001624154880x7f436130f0800x7f435e42404052428811498563128777471217538857795027175388577595731753885816357417538858165757
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00142194652194654194304256001224159360x7f435eb6df000x7f435e42408052428810703388119881976817538858198246175388581635741753885847941417538858481579
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00172194652194654194304256001224163840x7f435eb6dd800x7f435e4240c052428811005035123248702417538858513508175388584794141753885878741517538858789741
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00202194652194654194304256001224170880x7f435eb6dc000x7f435e42410052428811044993123696214417538858832460175388587874151753885909509517538859097174
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00232194652194654194304256001624177920x7f435eb6da800x7f435e42414052428811351528127134452017538859130243175388590950951753885948997617538859492213
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00262194652194654194304256001624184960x7f435eb6d9000x7f435e42418052428811548152129339537617538859523223175388594899761753885988613617538859888613
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00292194652194654194304256001624192000x7f435eb6d7800x7f435e4241c052428811040623123654009617538859920323175388598861361753886020885717538860211155
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00322194652194654194304256001624199040x7f435eb6d6000x7f435e42420052428811197142125403752817538860242884175388602088571753886051429717538860516457
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00352194652194654194304256001224206080x7f436130f4800x7f435e42424052428810899260122067078017538860557086175388605142971753886082101817538860823349
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00382194652194654194304256001624213120x7f436130f3000x7f435e42428052428811435854128083747617538860855499175388608210181753886121381817538861215959
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00412194652194654194304256001624220160x7f436130f1800x7f435e4242c052428811535132129191072817538861247819175388612138181753886160901917538861611149
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00442194652194654194304256001624227200x7f436130f0000x7f435e42430052428810835518121359029217538861643109175388616090191753886191734017538861919602
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00472194652194654194304256001224234240x7f435eb6de800x7f435e42434052428810789489120835386017538861952721175388619173401753886223830017538862240533
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00502194652194654194304256001224241280x7f435eb6dd000x7f435e42438052428811201830125463308417538862280762175388622383001753886255238117538862554815
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00532194652194654194304256001624248320x7f435eb6db800x7f435e4243c052428811611238130041405217538862586114175388625523811753886295046117538862952005
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00562194652194654194304256001624255360x7f435eb6da000x7f435e42440052428811340020127003320417538862984034175388629504611753886332342217538863324985
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00592194652194654194304256001224262400x7f435eb6d8800x7f435e42444052428810864430121674743217538863356875175388633234221753886360358217538863605428
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00622194652194654194304256001224269440x7f435eb6d7000x7f435e42448052428811076206124054275617538863637687175388636035821753886388214317538863883891
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00652194652194654194304256001224276480x7f436130f5800x7f435e4244c052428811093684124244412417538863923120175388638821431753886416390317538864165524
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00682194652194654194304256001624286080x7f436130f4000x7f435e42450052428811499255128784620417538864200003175388641639031753886454134417538864542924
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00712194652194654194304256001624293120x7f436130f2800x7f435e42454052428811457893128327203217538864575313175388645413441753886490918417538864910755
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00742194652194654194304256001224300160x7f436130f1000x7f435e42458052428811047015123723173617538864943154175388649091841753886518694517538865188758
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077219465219465419430425600824309760x7f435eb6df800x7f435e4245c052428810549398118151212017538865220737175388651869451753886546566517538865467390
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00802194652194654194304256001224316800x7f435eb6de000x7f435e42460052428811230236125771791217538865506899175388654656651753886574406617538865745763
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00832194652194654194304256001624326400x7f435eb6dc800x7f435e42464052428811522302129045152417538865776492175388657440661753886611574617538866117494
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00862194652194654194304256001224336000x7f435eb6db000x7f435e42468052428811528606129123155617538866150153175388661157461753886648662717538866488214
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00892194652194654194304256001224345600x7f435eb6d9800x7f435e4246c052428810795899120910936817538866520583175388664866271753886676806717538866769567
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092219465219465419430425600824355200x7f435eb6d8000x7f435e42470052428810380399116251243617538866802086175388667680671753886704486817538867046530
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00952194652194654194304256001224362240x7f435eb6d6800x7f435e42474052428810644931119218940817538867085289175388670448681753886732150817538867323143
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00982194652194654194304256001224371840x7f436130f5000x7f435e42478052428811542758129277948817538867356212175388673215081753886768534917538867686994
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001012194652194654194304256001224381440x7f436130f3800x7f435e4247c052428811364010127271373617538867719263175388676853491753886805142917538868053204
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001042194652194654194304256001224391040x7f436130f2000x7f435e42480052428810625273118994376017538868085854175388680514291753886832903017538868330677
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107219465219465419430425600824403200x7f436130f0800x7f435e42484052428810133917113502163217538868362496175388683290301753886860727017538868608750
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001102194652194654194304256001224412800x7f435eb6df000x7f435e42488052428810557599118239984817538868648119175388686072701753886889063017538868892473
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001132194652194654194304256001224422400x7f435eb6dd800x7f435e4248c052428811407851127766623617538868924772175388688906301753886925527117538869256994
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001162194652194654194304256001224432000x7f435eb6dc000x7f435e42490052428811332653126919313617538869289313175388692552711753886961895217538869620754
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119219465219465419430425600824441600x7f435eb6da800x7f435e42494052428810721686120078749217538869652314175388696189521753886989527217538869897097
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001222194652194654194304256001224453760x7f435eb6d9000x7f435e4249805242889675753108369116017538869929187175388698952721753887017463217538870176320
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001252194652194654194304256001224463360x7f435eb6d7800x7f435e4249c052428810419398116689065617538870216569175388701746321753887046391317538870465523
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001282194652194654194304256001224475520x7f435eb6d6000x7f435e424a0052428811484331128621676017538870497432175388704639131753887082935317538870830873
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001312194652194654194304256001224485120x7f436130f4800x7f435e424a4052428811402035127703649617538870863733175388708293531753887119431417538871196034
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134219465219465419430425600824494720x7f436130f3000x7f435e424a8052428810393752116408392817538871227423175388711943141753887147191417538871473637
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001372194652194654194304256001224506880x7f436130f1800x7f435e424ac05242889066181101539033217538871505936175388714719141753887175687517538871758440
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001402194652194654194304256001224516480x7f436130f0000x7f435e424b0052428810366829116106417217538871797979175388717568751753887203783517538872039472
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001432194652194654194304256001224528640x7f435eb6de800x7f435e424b4052428811239734125886870017538872070282175388720378351753887240183617538872403433
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001462194652194654194304256001224540800x7f435eb6dd000x7f435e424b8052428811300498126563086817538872435832175388724018361753887276823717538872770064
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149219465219465419430425600824552960x7f435eb6db800x7f435e424bc052428810521280117843724417538872802253175388727682371753887304647717538873048156
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001522194652194654194304256001224567680x7f435eb6da000x7f435e424c00524288771441686405087617538873079886175388730464771753887332471717538873326309
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001552194652194654194304256001224577280x7f435eb6d8800x7f435e424c4052428810613235118873408017538873364068175388733247171753887360855817538873610332
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001582194652194654194304256001224589440x7f435eb6d7000x7f435e424c8052428811346084127074048817538873643111175388736085581753887397207817538873973583
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001612194652194654194304256001224601600x7f436130f5800x7f435e424cc052428811129257124644717617538874005172175388739720781753887434215917538874343863
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164219465219465419430425600824613760x7f436130f4000x7f435e424d0052428810090707113007061217538874375792175388743421591753887462919917538874630906
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001672194652194654194304256001224628480x7f436130f2800x7f435e424d40524288601994967423655217538874662865175388746291991753887491032017538874911949
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001702194652194654194304256001224638080x7f436130f1000x7f435e424d8052428810326761115647304017538874951308175388749103201753887518776017538875189391
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001732194652194654194304256001224650240x7f435eb6df800x7f435e424dc052428811367946127315828817538875222051175388751877601753887555128117538875552872
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001762194652194654194304256001224662400x7f435eb6de000x7f435e424e0052428811252514126024602017538875584141175388755512811753887591304117538875914683
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179219465219465419430425600824674560x7f435eb6dc800x7f435e424e405242889818339109963129217538875946302175388759130411753887619112217538876192776
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001822194652194654194304256001224689280x7f435eb6db000x7f435e424e80524288604616467715340817538876225225175388761911221753887647864217538876480338
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001852194652194654194304256001224701440x7f435eb6d9800x7f435e424ec052428810030930112350807217538876519667175388764786421753887675704317538876758791
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001882194652194654194304256001224716160x7f435eb6d8000x7f435e424f0052428811349372127111888417538876792420175388767570431753887712392317538877125482
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001912194652194654194304256001224728320x7f435eb6d6800x7f435e424f4052428811080449124097740417538877158861175388771239231753887749128417538877492922
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194219465219465419430425600824740480x7f436130f5000x7f435e424f805242889751840109215812017538877524172175388774912841753887777848417538877780175
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001972194652194654194304256001224757760x7f436130f3800x7f435e424fc0524288449841450376966817538877811944175388777784841753887806936517538878070987
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002002194652194654194304256001224769920x7f436130f2000x7f435e42500052428810262836114939148417538878112046175388780693651753887835464517538878356290
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002032194652194654194304256001224784640x7f436130f0800x7f435e42504052428811326665126857580017538878387699175388783546451753887872072617538878722401
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002062194652194654194304256001224799360x7f435eb6df000x7f435e42508052428811281611126351902017538878754050175388787207261753887908888617538879090641
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209219465219465419430425600824814080x7f435eb6dd800x7f435e4250c05242889438261105708222017538879122021175388790888861753887936952717538879371294
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002122194652194654194304256001224831360x7f435eb6dc000x7f435e425100524288385208243138958817538879403173175388793695271753887966824717538879669767
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002152194652194654194304256001224843520x7f435eb6da800x7f435e42514052428810561108118281584017538879721625175388796682471753887995176817538879953509
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002182194652194654194304256001224858240x7f435eb6d9000x7f435e42518052428811286332126405562817538879994038175388799517681753888031880817538880320410
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002212194652194654194304256001224872960x7f435eb6d7800x7f435e4251c052428811145032124825252817538880354839175388803188081753888069048917538880692321
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002242194652194654194304256001224887680x7f435eb6d6000x7f435e4252005242889524816106673419617538880724450175388806904891753888097032917538880972043
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002272194652194654194304256001224907520x7f436130f4800x7f435e425240524288361100740441685617538881003763175388809703291753888127465017538881276246
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002302194652194654194304256001224919680x7f436130f3000x7f435e4252805242889845506110265120017538881315815175388812746501753888155209017538881553649
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002332194652194654194304256001224934400x7f436130f1800x7f435e4252c052428811194735125376566417538881585428175388815520901753888192153117538881923069
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002362194652194654194304256001224949120x7f436130f0000x7f435e42530052428811193831125368917217538881955758175388819215311753888229017117538882292040
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002392194652194654194304256001224963840x7f435eb6de800x7f435e4253405242889022738101050054417538882323949175388822901711753888257593217538882577462
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002422194652194654194304256001224983680x7f435eb6dd000x7f435e425380524288348022538973924817538882609462175388825759321753888288489217538882886444
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002452194652194654194304256001224995840x7f435eb6db800x7f435e4253c052428810050550112562841217538882925683175388828848921753888316265317538883164247
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024821946521946541943042560012241013120x7f435eb6da000x7f435e42540052428811098761124304196017538883195387175388831626531753888352969317538883531288
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025121946521946541943042560012241027840x7f435eb6d8800x7f435e42544052428811167576125078385617538883562737175388835296931753888389209417538883893649
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025421946521946541943042560012241042560x7f435eb6d7000x7f435e425480524288869226597344572817538883924768175388838920941753888417001417538884171681
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025721946521946541943042560012241062400x7f436130f5800x7f435e4254c0524288324118336301176817538884202171175388841700141753888448521517538884486883
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026021946521946541943042560012241077120x7f436130f4000x7f435e4255005242889738795109080610817538884525822175388844852151753888476345517538884765166
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026321946521946541943042560016241094400x7f436130f2800x7f435e42554052428811227362125745227217538884796075175388847634551753888512745617538885129047
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026621946521946541943042560016241111680x7f436130f1000x7f435e42558052428811092740124235402817538885160816175388851274561753888549113617538885492848
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002692194652194654194304256008241128960x7f435eb6df800x7f435e4255c0524288796597289215354417538885523707175388854911361753888577049717538885772250
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027221946521946541943042560012241151360x7f435eb6de000x7f435e425600524288299485433537926017538885803050175388857704971753888609017717538886091862
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027521946521946541943042560012241166080x7f435eb6dc800x7f435e42564052428810045198112492632417538886130651175388860901771753888637673817538886378235
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027821946521946541943042560016241183360x7f435eb6db000x7f435e42568052428811084020124137978017538886409344175388863767381753888674137817538886742956
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028121946521946541943042560016241200640x7f435eb6d9800x7f435e4256c052428811131197124666597217538886774425175388867413781753888710489917538887106456
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028421946521946541943042560012241217920x7f435eb6d8000x7f435e425700524288675987075709782817538887137286175388871048991753888738665917538887388379
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028721946521946541943042560012241240320x7f435eb6d6800x7f435e425740524288293369132858942817538887419518175388873866591753888771706017538887718681
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029021946521946541943042560012241255040x7f436130f5000x7f435e4257805242889518791106599591217538887757620175388877170601753888799882017538888000393
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029321946521946541943042560012241274880x7f436130f3800x7f435e4257c052428811024897123477028817538888031573175388879988201753888836298117538888364534
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029621946521946541943042560012241292160x7f436130f2000x7f435e42580052428811151357124894875617538888396743175388883629811753888872810117538888729715
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029921946521946541943042560012241309440x7f436130f0800x7f435e425840524288642276871933611617538888761664175388887281011753888901322217538889014708
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030221946521946541943042560012241334400x7f435eb6df000x7f435e425880524288291320532623021217538889046767175388890132221753888935626217538889357989
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030521946521946541943042560012241349120x7f435eb6dd800x7f435e4258c0524288839541394033085617538889396358175388893562621753888964442317538889646042
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030821946521946541943042560012241368960x7f435eb6dc000x7f435e42590052428810953707122674295617538889678281175388896444231753889000858317538890010042
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031121946521946541943042560012241388800x7f435eb6da800x7f435e42594052428811080508124093754017538890042211175388900085831753889038650417538890388153
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031421946521946541943042560012241408640x7f435eb6d9000x7f435e425980524288484928454306914017538890420602175388903865041753889067818517538890679845
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031721946521946541943042560012241436160x7f435eb6d7800x7f435e4259c0524288284181131830993617538890712104175388906781851753889103242517538891034086
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032021946521946541943042560012241453440x7f435eb6d6000x7f435e425a00524288704969478953374417538891073585175388910324251753889131898617538891320799
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032321946521946541943042560012241475840x7f436130f4800x7f435e425a4052428811015995123376946817538891352568175388913189861753889168650617538891688119
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032621946521946541943042560012241495680x7f436130f3000x7f435e425a8052428810833174121329171617538891720108175388916865061753889204874717538892050470
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032921946521946541943042560012241515520x7f436130f1800x7f435e425ac0524288382753542858518017538892082259175388920487471753889234778717538892349482
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033221946521946541943042560012241543040x7f436130f0000x7f435e425b00524288287363632184926017538892381231175388923477871753889271242817538892713893
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033521946521946541943042560012241562880x7f435eb6de800x7f435e425b40524288562427762995896017538892753642175388927124281753889300122817538893002865
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033821946521946541943042560012241587840x7f435eb6dd000x7f435e425b8052428810478906117361848017538893035135175388930012281753889337002917538893371896
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034121946521946541943042560012241610240x7f435eb6db800x7f435e425bc052428810803704120997686017538893403785175388933700291753889373770917538893739466
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034421946521946541943042560012241632640x7f435eb6da000x7f435e425c00524288348698639050899217538893770646175388937377091753889404587017538894047519
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034721946521946541943042560012241665280x7f435eb6d8800x7f435e425c40524288282227431608848417538894086628175388940458701753889444923017538894473188
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035021946521946541943042560012241685120x7f435eb6d7000x7f435e425c80524288399025144677212417538894493477175388944492301753889476027117538894761890
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035321946521946541943042560012241712640x7f436130f5800x7f435e425cc05242889983994111820082417538894793379175388947602711753889512891117538895130521
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035621946521946541943042560012241737600x7f436130f4000x7f435e425d0052428810388480116351527617538895164510175388951289111753889550011217538895501741
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035921946521946541943042560012241762560x7f436130f2800x7f435e425d40524288285684331990836417538895532980175388955001121753889581995317538895821413
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036221946521946541943042560012241797760x7f436130f1000x7f435e425d80524288285745831992883217538895853452175388958199531753889623595317538896257382
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036521946521946541943042560012241822720x7f435eb6df800x7f435e425dc0524288320710435909625617538896276831175388962359531753889655867417538896560244
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036821946521946541943042560012241855360x7f435eb6de000x7f435e425e00524288836055893636363217538896590943175388965586741753889693387417538896953094
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037121946521946541943042560012241885440x7f435eb6dc800x7f435e425e40524288755342584595113217538896966534175388969338741753889732027517538897337534
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037421946521946541943042560012241915520x7f435eb6db000x7f435e425e80524288279600831323986817538897353514175388973202751753889767147517538897673035
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037721946521946541943042560012241958400x7f435eb6d9800x7f435e425ec0524288283092931698641217538897704535175388976714751753889814187617538898161433
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038021946521946541943042560012241985920x7f435eb6d8000x7f435e425f00524288280659331434587217538898183072175388981418761753889849659717538898498204
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038321946521946541943042560012242023680x7f435eb6d6800x7f435e425f40524288683889176591729617538898529334175388984965971753889889739717538898920754
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038621946521946541943042560012242058880x7f436130f5000x7f435e425f80524288614665968835386817538898933003175388988973971753889930331817538899320993
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038921946521946541943042560012242094080x7f436130f3800x7f435e425fc0524288285375631963500017538899336583175388993033181753889968123917538899682784
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039221946521946541943042560012242144640x7f436130f2000x7f435e426000524288289369432400469217538899715243175388996812391753890020027917538900219980
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039521946521946541943042560012242177280x7f436130f0800x7f435e426040524288277603931090406817538900241760175389002002791753890056284017538900564532
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039821946521946541943042560012242220160x7f435eb6df000x7f435e426080524288618526969274149617538900596931175389005628401753890097916117538900996521
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040121946521946541943042560012242260480x7f435eb6dd800x7f435e4260c0524288530182459377724817538901013570175389009791611753890139900117538901416720
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040421946521946541943042560012242300800x7f435eb6dc000x7f435e426100524288274059530691832817538901431639175389013990011753890180188217538901819680
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040721946521946541943042560012242359040x7f435eb6da800x7f435e426140524288291971732701861217538901835119175389018018821753890237788317538902399295
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041021946521946541943042560012242394240x7f435eb6d9000x7f435e426180524288272784530549876017538902418774175389023778831753890276620317538902767985
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041321946521946541943042560012242442240x7f435eb6d7800x7f435e4261c0524288524847458778324417538902801174175389027662031753890320124417538903243613
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041621946521946541943042560012242487680x7f435eb6d6000x7f435e426200524288316633735456013217538903255483175389032012441753890366124517538903703431
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041921946521946541943042560012242533120x7f436130f4800x7f435e426240524288276281530931880817538903715081175389036612451753890411308617538904155390
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004222194652194654194304256008242555520x7f436130f3000x7f435e426280524288236824726517926017538904167859175389041130861753890478124717538904825242
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042521946521946541943042560012242598400x7f436130f1800x7f435e4262c0524288272694430533277617538904844672175389047812471753890522316717538905265071
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042821946521946541943042560012242656640x7f436130f0000x7f435e426300524288320954935943147617538905276691175389052231671753890573692817538905754289
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043121946521946541943042560012242712320x7f435eb6de800x7f435e426340524288378792842422624017538905770118175389057369281753890622428917538906271115
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004342194652194654194304256008242732160x7f435eb6dd000x7f435e426380524288239254226798374017538906283165175389062242891753890674573017538906789982
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004372194652194654194304256008242757120x7f435eb6db800x7f435e4263c0524288238345326693056417538906801642175389067457301753890752285117538907565152
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044021946521946541943042560012242807680x7f435eb6da000x7f435e426400524288264690529638902817538907584192175389075228511753890800093217538908042800
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044321946521946541943042560012242876160x7f435eb6d8800x7f435e426440524288352568039487534417538908054110175389080009321753890856445317538908606446
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044621946521946541943042560012242942080x7f435eb6d7000x7f435e426480524288357583540049712817538908618595175389085644531753890913373317538909176561
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004492194652194654194304256008242969600x7f436130f5800x7f435e4264c0524288239252426790878417538909188531175389091337331753890969853417538909740827
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004522194652194654194304256008242999680x7f436130f4000x7f435e426500524288240165726895153617538909752687175389096985341753891057309617538910618024
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004552194652194654194304256008243027200x7f436130f2800x7f435e426540524288238373326699803617538910638264175389105730961753891124189717538911285897
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045821946521946541943042560012243054720x7f436130f1000x7f435e426580524288258307828926223617538911297497175389112418971753891192173817538911963920
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046121946521946541943042560012243082240x7f435eb6df800x7f435e4265c0524288259544129067292417538911975410175389119217381753891259677917538912638862
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004642194652194654194304256008243109760x7f435eb6de000x7f435e426600524288238772326744036817538912650832175389125967791753891326750017538913309695
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004672194652194654194304256008243132160x7f435eb6dc800x7f435e426640524288239563726833021617538913322085175389132673761753891435201717538914404927
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004702194652194654194304256008243159680x7f435eb6db000x7f435e426680524288244579927393378817538914425307175389143520171753891543601817538915485260
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047321946521946541943042560012243187200x7f435eb6d9800x7f435e4266c0524288258018328898481617538915496579175389154360181753891655905917538916626551
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047621946521946541943042560012243214720x7f435eb6d8000x7f435e426700524288259143929024831217538916639410175389165590591753891769410117538917758802
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004792194652194654194304256008243242240x7f435eb6d6800x7f435e426740524288242426927143788417538917770561175389176941011753891880514217538918877773
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004822194652194654194304256008243264640x7f436130f5000x7f435e426780524288247196227685149617538918890553175389188051421753892076850517538920836543
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004852194652194654194304256008243292160x7f436130f3800x7f435e4267c0524288244564627391308817538920856332175389207685051753892269522717538922765813
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048821946521946541943042560012243319680x7f436130f2000x7f435e426800524288262522829396343617538922778973175389226952271753892468115017538924746662
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049121946521946541943042560012243347200x7f436130f0800x7f435e426840524288262396829385689217538924759792175389246811501753892666947317538926740451
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004942194652194654194304256008243374720x7f435eb6df000x7f435e426880524288246229527582137617538926753411175389266694731753892860643517538928673032
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049721946521946541943042560082400x7f435eb6dd800x7f435e4268c0524288246560727610983217538928684832175389286064351753893222484017538932304279