Files
rocm-systems/tests/workloads/HBM/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.kd000170693170693335544322560043241600x00x7fb8f4804280524288547857261354343216704516970838167022076758511670466811059016704668215009
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00217069317069332768256001224138880x00x7fb8f4823f80409651987582956416704673421218167046681105901670467354607816704673550673
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051706931706934194304256001224143360x7fb8f77b33800x7fb8f4823fc052428810931927122446344016704673584352167046735460781670467391151616704673913831
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081706931706934194304256001624150400x7fb8f77b32000x7fb8f482400052428811514439128956943216704673949690167046739115161670467432495316704674327548
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111706931706934194304256001624154880x7fb8f77b30800x7fb8f482404052428811530497129140714016704674361017167046743249531670467472879116704674731135
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141706931706934194304256001224159360x7fb8f5183f000x7fb8f482408052428810825575121241839216704674763724167046747287911670467503566916704675037905
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171706931706934194304256001224163840x7fb8f5183d800x7fb8f48240c052428810838395121377890416704675069403167046750356691670467534206716704675344304
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201706931706934194304256001224170880x7fb8f5183c000x7fb8f482410052428811296377126521255616704675388603167046753420671670467564078616704675642905
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231706931706934194304256001624177920x7fb8f5183a800x7fb8f482414052428811640646130373673216704675674474167046756407861670467603470316704676036742
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261706931706934194304256001624184960x7fb8f51839000x7fb8f482418052428811440440128133504016704676068431167046760347031670467642558116704676427739
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291706931706934194304256001624192000x7fb8f51837800x7fb8f48241c052428810871404121749792416704676458948167046764255811670467674253916704676744618
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321706931706934194304256001624199040x7fb8f51836000x7fb8f482420052428811189485125316651616704676777327167046767425391670467704669716704677049008
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351706931706934194304256001224206080x7fb8f77b34800x7fb8f482424052428811166700125067515216704677088767167046770466971670467735917616704677361208
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381706931706934194304256001624213120x7fb8f77b33000x7fb8f482428052428811509982128908425616704677393497167046773591761670467775821316704677760465
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411706931706934194304256001624220160x7fb8f77b31800x7fb8f48242c052428811438429128108310016704677792874167046777582131670467814973116704678152522
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441706931706934194304256001624227200x7fb8f77b30000x7fb8f482430052428811357415127201033216704678184491167046781497311670467846044916704678462602
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471706931706934194304256001224234240x7fb8f5183e800x7fb8f482434052428811001757123224622416704678494261167046784604491670467876476816704678767022
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501706931706934194304256001224241280x7fb8f5183d000x7fb8f482438052428811204770125486064816704678805831167046787647681670467906668616704679068432
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531706931706934194304256001624248320x7fb8f5183b800x7fb8f48243c052428811469494128458184016704679101291167046790666861670467943020416704679431750
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561706931706934194304256001624255360x7fb8f5183a000x7fb8f482440052428811467338128429154816704679463179167046794302041670467980044216704679801948
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591706931706934194304256001224262400x7fb8f51838800x7fb8f482444052428811298924126547052416704679832867167046798004421670468007724016704680078799
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621706931706934194304256001224269440x7fb8f51837000x7fb8f482448052428810727525120156327216704680110608167046800772401670468035051816704680351930
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651706931706934194304256001224276480x7fb8f77b35800x7fb8f48244c052428810884436121900928816704680392049167046803505181670468062731716704680628991
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681706931706934194304256001624286080x7fb8f77b34000x7fb8f482450052428811487596128661784816704680661710167046806273171670468099179516704680993209
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711706931706934194304256001624293120x7fb8f77b32800x7fb8f482454052428811483037128609473216704681024158167046809917951670468135675316704681358337
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741706931706934194304256001224300160x7fb8f77b31000x7fb8f482458052428811082719124125655616704681390756167046813567531670468163083116704681632308
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077170693170693419430425600824309760x7fb8f5183f800x7fb8f48245c052428810818047121157678416704681663957167046816308311670468190746916704681909209
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801706931706934194304256001224316800x7fb8f5183e000x7fb8f482460052428810900029122078514016704681947128167046819074691670468219258816704682194389
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831706931706934194304256001624326400x7fb8f5183c800x7fb8f482464052428811407247127760114016704682225208167046821925881670468256426616704682565857
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861706931706934194304256001224336000x7fb8f5183b000x7fb8f482468052428811492238128709385616704682597006167046825642661670468293162316704682933045
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891706931706934194304256001224345600x7fb8f51839800x7fb8f48246c052428811063434123904565616704682965564167046829316231670468320842216704683210096
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092170693170693419430425600824355200x7fb8f51838000x7fb8f482470052428810677477119582193216704683242045167046832084221670468348986016704683491407
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951706931706934194304256001224362240x7fb8f51836800x7fb8f482474052428810934958122466869216704683530126167046834898601670468376537916704683767028
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981706931706934194304256001224371840x7fb8f77b35000x7fb8f482478052428811510150128909930416704683797827167046837653791670468413017616704684131896
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011706931706934194304256001224381440x7fb8f77b33800x7fb8f48247c052428811376846127414830416704684164415167046841301761670468449241416704684493944
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041706931706934194304256001224391040x7fb8f77b32000x7fb8f482480052428810551207118176376416704684525643167046844924141670468476841316704684770095
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107170693170693419430425600824403200x7fb8f77b30800x7fb8f48248405242889880605110661638416704684802064167046847684131670468504329116704685045006
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101706931706934194304256001224412800x7fb8f5183f000x7fb8f482488052428810987196123055089616704685084064167046850432911670468532777016704685329266
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131706931706934194304256001224422400x7fb8f5183d800x7fb8f48248c052428811390290127569398816704685360875167046853277701670468569144716704685693044
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161706931706934194304256001224432000x7fb8f5183c000x7fb8f482490052428811326765126857161616704685724603167046856914471670468605448516704686055943
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119170693170693419430425600824441600x7fb8f5183a800x7fb8f482494052428810922919122339770416704686096771167046860544851670468634392416704686345763
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221706931706934194304256001224453760x7fb8f51839000x7fb8f48249805242889917172111073764816704686377902167046863439241670468662344216704686624984
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251706931706934194304256001224463360x7fb8f51837800x7fb8f48249c052428810671820119528135216704686663083167046866234421670468690648016704686908125
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281706931706934194304256001224475520x7fb8f51836000x7fb8f4824a0052428811256752126073189216704686939573167046869064801670468726871816704687270283
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311706931706934194304256001224485120x7fb8f77b34800x7fb8f4824a4052428811265836126172247616704687301552167046872687181670468763031616704687631711
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134170693170693419430425600824494720x7fb8f77b33000x7fb8f4824a8052428810538715118026579616704687663510167046876303161670468790487516704687906432
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371706931706934194304256001224506880x7fb8f77b31800x7fb8f4824ac05242889081765101710691216704687938201167046879048751670468818711316704688188532
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401706931706934194304256001224516480x7fb8f77b30000x7fb8f4824b0052428810481317117390757216704688227761167046881871131670468846615116704688467733
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431706931706934194304256001224528640x7fb8f5183e800x7fb8f4824b4052428811323962126824461616704688499442167046884661511670468882982916704688831441
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461706931706934194304256001224540800x7fb8f5183d000x7fb8f4824b8052428811266375126182624416704688862690167046888298291670468919126716704689192709
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149170693170693419430425600824552960x7fb8f5183b800x7fb8f4824bc052428810679797119617514416704689223498167046891912671670468946870616704689470450
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521706931706934194304256001224567680x7fb8f5183a000x7fb8f4824c00524288753829384434270016704689503249167046894687061670468974518416704689746841
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551706931706934194304256001224577280x7fb8f51838800x7fb8f4824c4052428810540677118052828816704689785420167046897451841670469002262216704690024172
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581706931706934194304256001224589440x7fb8f51837000x7fb8f4824c8052428811284767126387328016704690054911167046900226221670469039510016704690396830
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611706931706934194304256001224601600x7fb8f77b35800x7fb8f4824cc052428811185675125282112816704690428449167046903951001670469075941816704690760938
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164170693170693419430425600824613760x7fb8f77b34000x7fb8f4824d0052428810135655113506659216704690793237167046907594181670469104085716704691042419
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671706931706934194304256001224628480x7fb8f77b32800x7fb8f4824d40524288623220269798836016704691074338167046910408571670469132869516704691330269
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701706931706934194304256001224638080x7fb8f77b31000x7fb8f4824d8052428810625084118990155216704691369458167046913286951670469160805316704691609740
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731706931706934194304256001224650240x7fb8f5183f800x7fb8f4824dc052428811311593126685408816704691642889167046916080531670469196885116704691970418
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761706931706934194304256001224662400x7fb8f5183e000x7fb8f4824e0052428811239019125875767616704692002297167046919688511670469232980916704692331356
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179170693170693419430425600824674560x7fb8f5183c800x7fb8f4824e405242889802508109789286416704692362155167046923298091670469260644816704692608017
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821706931706934194304256001224689280x7fb8f5183b000x7fb8f4824e80524288540810760569534016704692639516167046926064481670469289556616704692897088
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851706931706934194304256001224701440x7fb8f51839800x7fb8f4824ec052428810181096114029857216704692935377167046928955661670469317396416704693175509
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881706931706934194304256001224716160x7fb8f51838000x7fb8f4824f0052428811325686126843320016704693206788167046931739641670469353860216704693540257
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911706931706934194304256001224728320x7fb8f51836800x7fb8f4824f4052428811287941126422406016704693571986167046935386021670469390820016704693909674
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194170693170693419430425600824740480x7fb8f77b35000x7fb8f4824f805242889983545111816696416704693940673167046939082001670469419043816704694192265
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971706931706934194304256001224757760x7fb8f77b33800x7fb8f4824fc0524288462836251829674816704694225124167046941904381670469448499716704694486476
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001706931706934194304256001224769920x7fb8f77b32000x7fb8f482500052428810286288115214798816704694526134167046944849971670469476643516704694768046
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031706931706934194304256001224784640x7fb8f77b30800x7fb8f482504052428811191608125349007216704694799505167046947664351670469512771316704695129384
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061706931706934194304256001224799360x7fb8f5183f000x7fb8f482508052428811142052124790140016704695161103167046951277131670469548883116704695490493
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209170693170693419430425600824814080x7fb8f5183d800x7fb8f48250c05242889617402107724136816704695521892167046954888311670469576434916704695765914
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121706931706934194304256001224831360x7fb8f5183c000x7fb8f4825100524288415964946595160016704695798342167046957643491670469605986816704696061304
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151706931706934194304256001224843520x7fb8f5183a800x7fb8f482514052428810129716113442736416704696109702167046960598681670469634194616704696343535
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181706931706934194304256001224858240x7fb8f51839000x7fb8f482518052428811072233124005784016704696375033167046963419461670469670722416704696708893
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211706931706934194304256001224872960x7fb8f51837800x7fb8f48251c052428811202060125462503216704696741481167046967072241670469707122216704697072821
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241706931706934194304256001224887680x7fb8f51836000x7fb8f48252005242889377934105034562416704697103640167046970712221670469735026016704697351961
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271706931706934194304256001224907520x7fb8f77b34800x7fb8f4825240524288392810543987604016704697383110167046973502601670469765297816704697654521
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301706931706934194304256001224919680x7fb8f77b33000x7fb8f482528052428810085618112955524016704697693190167046976529781670469792945716704697931042
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331706931706934194304256001224934400x7fb8f77b31800x7fb8f48252c052428811189192125314619616704697964211167046979294571670469830225516704698304090
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361706931706934194304256001224949120x7fb8f77b30000x7fb8f482530052428811182301125238332016704698336609167046983022551670469866753216704698669028
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391706931706934194304256001224963840x7fb8f5183e800x7fb8f48253405242889337171104576840416704698700527167046986675321670469894417116704698945909
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421706931706934194304256001224983680x7fb8f5183d000x7fb8f4825380524288351350939346152416704698977928167046989441711670469925280916704699254369
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451706931706934194304256001224995840x7fb8f5183b800x7fb8f48253c05242889942998111354585616704699293558167046992528091670469954032716704699541949
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024817069317069341943042560012241013120x7fb8f5183a000x7fb8f482540052428811223557125700712816704699573038167046995403271670469990864516704699910407
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025117069317069341943042560012241027840x7fb8f51838800x7fb8f482544052428811079662124091383616704699942466167046999086451670470027584316704700277555
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025417069317069341943042560012241042560x7fb8f51837000x7fb8f4825480524288884936099104175216704700309424167047002758431670470055184216704700553566
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025717069317069341943042560012241062400x7fb8f77b35800x7fb8f48254c0524288328648036810217216704700584785167047005518421670470086448016704700866126
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026017069317069341943042560012241077120x7fb8f77b34000x7fb8f48255005242889690119108527443216704700905295167047008644801670470113919816704701140677
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026317069317069341943042560016241094400x7fb8f77b32800x7fb8f482554052428811094495124252933616704701172196167047011391981670470150431616704701505835
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026617069317069341943042560016241111680x7fb8f77b31000x7fb8f482558052428811122694124571194016704701537744167047015043161670470186831416704701869813
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691706931706934194304256008241128960x7fb8f5183f800x7fb8f48255c0524288821675592021552416704701900942167047018683141670470214895216704702150704
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027217069317069341943042560012241151360x7fb8f5183e000x7fb8f4825600524288299354733528680816704702182903167047021489521670470247311016704702474713
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027517069317069341943042560012241166080x7fb8f5183c800x7fb8f48256405242889693261108554309216704702513502167047024731101670470276094916704702762614
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027817069317069341943042560016241183360x7fb8f5183b000x7fb8f482568052428811053862123799078416704702793923167047027609491670470312206716704703123562
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028117069317069341943042560016241200640x7fb8f51839800x7fb8f48256c052428811214415125597923216704703155331167047031220671670470348414516704703485750
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028417069317069341943042560012241217920x7fb8f51838000x7fb8f4825700524288708612579364963616704703516449167047034841451670470376254316704703764231
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028717069317069341943042560012241240320x7fb8f51836800x7fb8f4825740524288293594932878744816704703795330167047037625431670470408814116704704089630
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029017069317069341943042560012241255040x7fb8f77b35000x7fb8f48257805242889338489104583652016704704128579167047040881411670470436430016704704365921
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029317069317069341943042560012241274880x7fb8f77b33800x7fb8f48257c052428810994540123135937616704704396900167047043643001670470472413716704704725729
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029617069317069341943042560012241292160x7fb8f77b32000x7fb8f482580052428811045927123708808016704704757148167047047241371670470508573516704705087337
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029917069317069341943042560012241309440x7fb8f77b30800x7fb8f4825840524288651271472948383616704705119136167047050857351670470536877416704705370348
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030217069317069341943042560012241334400x7fb8f5183f000x7fb8f4825880524288297454633304819616704705403747167047053687741670470571293216704705714467
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030517069317069341943042560012241349120x7fb8f5183d800x7fb8f48258c0524288858231096114925216704705753685167047057129321670470598989016704705991378
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030817069317069341943042560012241368960x7fb8f5183c000x7fb8f482590052428811018019123402085616704706023107167047059898901670470636764816704706369365
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031117069317069341943042560012241388800x7fb8f5183a800x7fb8f482594052428811025628123480690816704706400754167047063676481670470673308616704706734723
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031417069317069341943042560012241408640x7fb8f51839000x7fb8f4825980524288500943256101386016704706766232167047067330861670470702204416704707023764
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031717069317069341943042560012241436160x7fb8f51837800x7fb8f48259c0524288283929131797855216704707056933167047070220441670470737212216704707373732
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032017069317069341943042560012241453440x7fb8f51836000x7fb8f4825a00524288743543883278614816704707413001167047073721221670470764908116704707650663
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032317069317069341943042560012241475840x7fb8f77b34800x7fb8f4825a4052428810982737123005053216704707681562167047076490811670470801403816704708015611
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032617069317069341943042560012241495680x7fb8f77b33000x7fb8f4825a8052428810956731122713992016704708047080167047080140381670470837723616704708378919
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032917069317069341943042560012241515520x7fb8f77b31800x7fb8f4825ac0524288392304743940126016704708410278167047083772361670470867483516704708676479
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033217069317069341943042560012241543040x7fb8f77b30000x7fb8f4825b00524288283629131780795616704708708508167047086748351670470903819316704709039807
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033517069317069341943042560012241562880x7fb8f5183e800x7fb8f4825b40524288570125763855773616704709078666167047090381931670470932331116704709324808
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033817069317069341943042560012241587840x7fb8f5183d000x7fb8f4825b8052428810140239113566904416704709355667167047093233111670470968954916704709690966
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034117069317069341943042560012241610240x7fb8f5183b800x7fb8f4825bc052428810824181121227550816704709722475167047096895491670471005258716704710054264
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034417069317069341943042560012241632640x7fb8f5183a000x7fb8f4825c00524288376155642122338016704710091253167047100525871670471036906516704710370634
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034717069317069341943042560012241665280x7fb8f51838800x7fb8f4825c40524288288561332323270816704710401573167047103690651670471076058316704710783760
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035017069317069341943042560012241685120x7fb8f51837000x7fb8f4825c80524288381520642728752416704710803559167047107605831670471106618116704711067791
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035317069317069341943042560012241712640x7fb8f77b35800x7fb8f4825cc052428810040881112453412416704711098830167047110661811670471143305916704711434539
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035617069317069341943042560012241737600x7fb8f77b34000x7fb8f4825d0052428810429466116808713616704711467458167047114330591670471180489716704711806666
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035917069317069341943042560012241762560x7fb8f77b32800x7fb8f4825d40524288283085831701706016704711837335167047118048971670471212281516704712124446
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036217069317069341943042560012241797760x7fb8f77b31000x7fb8f4825d80524288292442532757342016704712156125167047121228151670471253817216704712558472
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036517069317069341943042560012241822720x7fb8f5183f800x7fb8f4825dc0524288309674634685181616704712579401167047125381721670471285705016704712858762
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036817069317069341943042560012241855360x7fb8f5183e000x7fb8f4825e00524288814948091269591616704712889591167047128570501670471323032816704713248829
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037117069317069341943042560012241885440x7fb8f5183c800x7fb8f4825e40524288786775488117851216704713263999167047132303281670471361160616704713630047
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037417069317069341943042560012241915520x7fb8f5183b000x7fb8f4825e80524288283392731733213616704713644746167047136116061670471395976416704713961386
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037717069317069341943042560012241958400x7fb8f51839800x7fb8f4825ec0524288290860132575166016704713993065167047139597641670471444024116704714466009
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038017069317069341943042560012241985920x7fb8f51838000x7fb8f4825f00524288287401432190424016704714486548167047144402411670471478903916704714790698
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038317069317069341943042560012242023680x7fb8f51836800x7fb8f4825f40524288718624380484941616704714821867167047147890391670471518791716704715231094
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038617069317069341943042560012242058880x7fb8f77b35000x7fb8f4825f80524288680120776169622016704715243024167047151879171670471560919516704715651460
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038917069317069341943042560012242094080x7fb8f77b33800x7fb8f4825fc0524288278624431203408816704715663470167047156091951670471600711216704716008868
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039217069317069341943042560012242144640x7fb8f77b32000x7fb8f4826000524288288982332357540816704716040977167047160071121670471652422916704716566610
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039517069317069341943042560012242177280x7fb8f77b30800x7fb8f4826040524288277542031076506816704716585879167047165242291670471690326716704716904949
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039817069317069341943042560012242220160x7fb8f5183f000x7fb8f4826080524288585632865589746016704716937168167047169032671670471732198516704717363984
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040117069317069341943042560012242260480x7fb8f5183d800x7fb8f48260c0524288528365359174008416704717376653167047173219851670471776582216704717783520
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040417069317069341943042560012242300800x7fb8f5183c000x7fb8f4826100524288280551531424316416704717798470167047177658221670471816502016704718209126
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040717069317069341943042560012242359040x7fb8f5183a800x7fb8f4826140524288292367032749652816704718222006167047181650201670471878181616704718800677
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041017069317069341943042560012242394240x7fb8f51839000x7fb8f4826180524288281029431467260816704718823416167047187818161670471916485416704719166495
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041317069317069341943042560012242442240x7fb8f51837800x7fb8f48261c0524288516634257857132416704719197394167047191648541670471959797116704719615200
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041617069317069341943042560012242487680x7fb8f51836000x7fb8f4826200524288337092937755479216704719630519167047195979711670472003108916704720049936
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041917069317069341943042560012242533120x7fb8f77b34800x7fb8f4826240524288277680231094773216704720064265167047200310891670472045732716704720474352
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221706931706934194304256008242555520x7fb8f77b33000x7fb8f4826280524288238058226659123616704720490571167047204573271670472109732316704721114951
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042517069317069341943042560012242598400x7fb8f77b31800x7fb8f48262c0524288272463030515380416704721138990167047210973231670472151124016704721527747
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042817069317069341943042560012242656640x7fb8f77b30000x7fb8f4826300524288323761836263237216704721544117167047215112401670472199875816704722015131
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043117069317069341943042560012242712320x7fb8f5183e800x7fb8f4826340524288386667443308626016704722033250167047219987581670472250963516704722529344
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341706931706934194304256008242732160x7fb8f5183d000x7fb8f4826380524288240659626950722816704722543404167047225096351670472299795216704723041757
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371706931706934194304256008242757120x7fb8f5183b800x7fb8f48263c0524288238454526706507616704723053777167047229979521670472377282716704723814472
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044017069317069341943042560012242807680x7fb8f5183a000x7fb8f4826400524288267993430010370816704723834011167047237728271670472424978516704724291906
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044317069317069341943042560012242876160x7fb8f51838800x7fb8f4826440524288337412637792815616704724303596167047242497851670472481410116704724856348
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044617069317069341943042560012242942080x7fb8f51837000x7fb8f4826480524288359761840289382816704724869037167047248141011670472537825816704725421349
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491706931706934194304256008242969600x7fb8f77b35800x7fb8f48264c0524288240879526979712016704725433319167047253782581670472593825516704725956492
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521706931706934194304256008242999680x7fb8f77b34000x7fb8f4826500524288239384126806586816704725974241167047259382551670472679521016704726840103
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551706931706934194304256008243027200x7fb8f77b32800x7fb8f4826540524288239246426792376416704726860062167047267952101670472746272616704727506231
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045817069317069341943042560012243054720x7fb8f77b31000x7fb8f4826580524288258819828987248416704727518450167047274627261670472815136216704728193048
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046117069317069341943042560012243082240x7fb8f5183f800x7fb8f48265c0524288259990929122435216704728205448167047281513621670472882575816704728869046
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641706931706934194304256008243109760x7fb8f5183e000x7fb8f4826600524288239088226777695216704728881155167047288257581670472949599416704729537764
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671706931706934194304256008243132160x7fb8f5183c800x7fb8f4826640524288240978926989188416704729549684167047294959941670473057694816704730626228
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701706931706934194304256008243159680x7fb8f5183b000x7fb8f4826680524288243225827244070816704730647067167047305767701670473165660416704731706633
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047317069317069341943042560012243187200x7fb8f51839800x7fb8f48266c0524288259368329046592416704731718932167047316566041670473277787616704732844905
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047617069317069341943042560012243214720x7fb8f51838000x7fb8f4826700524288259589429070338816704732856535167047327778761670473391242916704733978298
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791706931706934194304256008243242240x7fb8f51836800x7fb8f4826740524288243536527273644016704733991398167047339124291670473503098216704735098801
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821706931706934194304256008243264640x7fb8f77b35000x7fb8f4826780524288245603727499162416704735111351167047350309821670473698409016704737050797
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851706931706934194304256008243292160x7fb8f77b33800x7fb8f48267c0524288246052627562580816704737071616167047369840901670473890103816704738972034
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048817069317069341943042560012243319680x7fb8f77b32000x7fb8f4826800524288262692929423018816704738984374167047389010381670474089126616704740955539
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049117069317069341943042560012243347200x7fb8f77b30800x7fb8f4826840524288262836929433256816704740967218167047408912661670474286933416704742937234
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941706931706934194304256008243374720x7fb8f5183f000x7fb8f4826880524288244744827415266016704742950193167047428693341670474480708216704744875010
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049717069317069341943042560082400x7fb8f5183d800x7fb8f48268c0524288249859327981831216704744887110167047448070821670474841730016704748495341