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

48 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjGRBM_COUNTGRBM_GUI_ACTIVECPC_ME1_BUSY_FOR_PACKET_DECODESQ_CYCLESSQ_WAVESSQ_WAVE_CYCLESSQ_BUSY_CYCLESSQ_LEVEL_WAVESSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000137266137266335544322560043241600x00x7feb78404280388592388592865231087445242882456541793022814099890572815894714993359158940077186661589486524328615894865331336
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00213726613726632768256001224138880x00x7feb78423f8033345333452984626676851216885201699150676726015894870480071158948652432861589487061386115894870618498
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051372661372664194304256001224143360x7feb7b4793800x7feb78423fc016424316424313776131395265536757938801207030030490786415894870663287158948706138611589487099994215894871001980
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081372661372664194304256001624150400x7feb7b4792000x7feb78424000311012311012250322488104655362203695992380369088320503215894871046879158948709999421589487142122415894871423310
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111372661372664194304256001624154880x7feb7b4790800x7feb78424040308657308657241272469264655362266471032365877090831790415894871464329158948714212241589487183546515894871837401
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141372661372664194304256001224159360x7feb78e19f000x7feb7842408016514416514413187132116065536738316791213311029705833615894871879490158948718354651589487215898615894872160774
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171372661372664194304256001224163840x7feb78e19d800x7feb784240c016415616415614126131325665536842940411207559033890740415894872201913158948721589861589487247658715894872478577
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201372661372664194304256001224170880x7feb78e19c000x7feb78424100162777162777155831302224655361083043471202534043494028815894872531885158948724765871589487279962815894872801399
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231372661372664194304256001624177920x7feb78e19a800x7feb78424140311253311253249252490032655362297658492385878092079340015894872841388158948727996281589487322122915894873223300
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261372661372664194304256001624184960x7feb78e199000x7feb78424180308878308878228222471032655362196531232365388088033963215894873263099158948732212291589487363131015894873633251
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291372661372664194304256001624192000x7feb78e197800x7feb784241c0165629165629152901325040655361040840701223950041805906015894873674020158948736313101589487395419115894873956044
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321372661372664194304256001624199040x7feb78e196000x7feb7842420016521116521115379132169665536971315651217717039025564015894873996273158948739541911589487429019215894874292216
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351372661372664194304256001224206080x7feb7b4794800x7feb78424240163843163843158141310752655361017443771207913040870185215894874344475158948742901921589487462091315894874622899
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381372661372664194304256001624213120x7feb7b4793000x7feb78424280310776310776242382486216655362284794932378701091564529615894874665708158948746209131589487500987415894875011260
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411372661372664194304256001624220160x7feb7b4791800x7feb784242c0310121310121235392480976655362254298642371701090344785615894875053429158948750098741589487539099515894875392501
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441372661372664194304256001624227200x7feb7b4790000x7feb7842430016461116461114369131689665536972624911216912039077584015894875433341158948753909951589487569531615894875696725
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471372661372664194304256001224234240x7feb78e19e800x7feb7842434016361516361514432130892865536907234521204295036462270015894875738864158948756953161589487599003715894875991438
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501372661372664194304256001224241280x7feb78e19d000x7feb7842438016262216262214980130098465536929982131198071037371709615894876040277158948759900371589487628203815894876283532
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531372661372664194304256001624248320x7feb78e19b800x7feb784243c0310143310143255342481152655362269075722371715090935880815894876329571158948762820381589487667067915894876671963
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561372661372664194304256001624255360x7feb78e19a000x7feb78424400307688307688229932461512655362207675012354600088479970015894876713322158948766706791589487705036015894877051714
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591372661372664194304256001224262400x7feb78e198800x7feb78424440162931162931154791303456655361059068601201053042535016015894877093713158948770503601589487734428115894877345728
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621372661372664194304256001224269440x7feb78e197000x7feb7842448016304016304014889130432865536915418171199620036789718415894877387647158948773442811589487763884215894877640261
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651372661372664194304256001224276480x7feb7b4795800x7feb784244c0162639162639151651301120655361029051081198351041335038415894877688960158948776388421589487793884315894877940265
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681372661372664194304256001624286080x7feb7b4794000x7feb78424500308303308303242972466432655362225618822360744089197572415894877984934158948779388431589487833276415894878334386
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711372661372664194304256001624293120x7feb7b4792800x7feb78424540306683306683221492453472655362169776622344975086963908015894878376215158948783327641589487871308515894878714317
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741372661372664194304256001224300160x7feb7b4791000x7feb7842458016246816246814924129975265536996448501198914040030900815894878756406158948787130851589487900460615894879005961
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077137266137266419430425600824309760x7feb78e19f800x7feb784245c016194016194014512129552865536913931061193077036730096015894879046730158948790046061589487929740715894879298654
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801372661372664194304256001224316800x7feb78e19e000x7feb7842460016353216353215863130826465536998911151206086040129092815894879347753158948792974071589487959564815894879596948
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831372661372664194304256001624326400x7feb78e19c800x7feb78424640307096307096247482456776655362288467572352394091711906015894879637837158948795956481589487998140915894879982829
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861372661372664194304256001224336000x7feb78e19b000x7feb78424680305980305980226932447848655362201966212343359088251286015894880025518158948799814091589488036141015894880362761
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891372661372664194304256001224345600x7feb78e199800x7feb784246c016258216258215155130066465536969419531194801038948986415894880404620158948803614101589488065389115894880655174
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092137266137266419430425600824355200x7feb78e198000x7feb7842470016371616371615973130973665536828439741198348033310336815894880697523158948806538911589488094701215894880948348
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951372661372664194304256001224362240x7feb78e196800x7feb7842474016280016280014875130240865536936826401198944037645694415894880996287158948809470121589488124541315894881246691
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981372661372664194304256001224371840x7feb7b4795000x7feb78424780306180306180235372449448655362264453652341730090751218415894881290320158948812454131589488162269415894881624043
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011372661372664194304256001224381440x7feb7b4793800x7feb784247c0308092308092231782464744655362196325272361420088025910815894881665992158948816226941589488200269515894882003944
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041372661372664194304256001224391040x7feb7b4792000x7feb7842480016366616366615047130933665536962721631204557038681882015894882044433158948820026951589488231693615894882318247
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107137266137266419430425600824403200x7feb7b4790800x7feb7842484016353816353815399130831265536880358991201828035387170815894882360326158948823169361589488261245715894882613931
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101372661372664194304256001224412800x7feb78e19f000x7feb7842488016225116225114980129801665536986435121191865039629748415894882662410158948826124571589488290765815894882909044
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131372661372664194304256001224422400x7feb78e19d800x7feb784248c0307034307034248632456280655362293619552351032091917380415894882953143158948829076581589488329309915894883294496
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161372661372664194304256001224432000x7feb78e19c000x7feb78424900306502306502229472452024655362160360962342190086587405615894883334975158948832930991589488367406015894883675547
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119137266137266419430425600824441600x7feb78e19a800x7feb7842494016260816260814826130087265536904950761198929036370191215894883716176158948836740601589488396510115894883966351
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221372661372664194304256001224453760x7feb78e199000x7feb7842498016326916326915709130616065536926553801199974037234435215894884009340158948839651011589488426398215894884265344
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251372661372664194304256001224463360x7feb78e197800x7feb784249c016258016258014090130064865536875814091199027035205386815894884313413158948842639821589488456718215894884568487
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281372661372664194304256001224475520x7feb78e196000x7feb78424a00305362305362235202442904655362244315432333312089945450015894884614436158948845671821589488495902415894884960378
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311372661372664194304256001224485120x7feb7b4794800x7feb78424a40302917302917211692423344655362027843112312396081286732015894885002037158948849590241589488533934515894885340750
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134137266137266419430425600824494720x7feb7b4793000x7feb78424a8016234616234615203129877665536947112791194519038057388815894885382689158948853393451589488563150615894885632873
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371372661372664194304256001224506880x7feb7b4791800x7feb78424ac016301116301116470130409665536976708311195321039241432015894885676622158948856315061589488592862715894885929927
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401372661372664194304256001224516480x7feb7b4790000x7feb78424b0016114516114514969128916865536936206901188541037620719615894885978786158948859286271589488623294715894886234390
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431372661372664194304256001224528640x7feb78e19e800x7feb78424b40304850304850246112438808655362238478192332231089711967615894886276599158948862329471589488661502915894886616331
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461372661372664194304256001224540800x7feb78e19d000x7feb78424b80302423302423206802419392655362030067552306792081375727615894886658190158948866150291589488699855015894887000013
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149137266137266419430425600824552960x7feb78e19b800x7feb78424bc016278816278814575130231265536820634361197836032998008015894887040112158948869985501589488729199115894887293246
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521372661372664194304256001224567680x7feb78e19a000x7feb78424c0016328316328316135130627265536995249591202673039983501215894887334025158948872919911589488758991115894887591330
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551372661372664194304256001224577280x7feb78e198800x7feb78424c4016224616224614600129797665536959379391193002038548106015894887640108158948875899111589488789023215894887891663
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581372661372664194304256001224589440x7feb78e197000x7feb78424c80303061303061231602424496655362227613282317965089277596815894887935782158948878902321589488827375315894888275114
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611372661372664194304256001224601600x7feb7b4795800x7feb78424cc0301686301686215192413496655362094222382302873083941818015894888316143158948882737531589488865071515894888652106
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164137266137266419430425600824613760x7feb7b4794000x7feb78424d0016215016215014369129720865536863648771195547034718789615894888692585158948886507151589488894079515894888942169
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671372661372664194304256001224628480x7feb7b4792800x7feb78424d40168246168246161701345976655361047850551242695042087664015894888983108158948889407951589488924095615894889242253
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701372661372664194304256001224638080x7feb7b4791000x7feb78424d8016243216243214380129946465536914854711196261036766888015894889291492158948892409561589488953663715894889538076
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731372661372664194304256001224650240x7feb78e19f800x7feb78424dc0301282301282233832410264655362201836362306896088246530015894889582335158948895366371589488992511815894889926457
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761372661372664194304256001224662400x7feb78e19e000x7feb78424e00299164299164203492393320655362096866502287478084047715215894889968066158948899251181589489031216015894890313649
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179137266137266419430425600824674560x7feb78e19c800x7feb78424e4016256416256415378130052065536895895621197642036008256015894890354198158948903121601589489060848015894890609842
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821372661372664194304256001224689280x7feb78e19b000x7feb78424e80175815175815166231406528655361027234751301756041262757215894890650491158948906084801589489091168115894890912945
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851372661372664194304256001224701440x7feb78e199800x7feb78424ec016103416103415200128828065536869743781182175034963421615894890961014158948909116811589489120848215894891209839
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881372661372664194304256001224716160x7feb78e198000x7feb78424f00303338303338233972426712655362221233892324524089022809615894891250988158948912084821589489159312315894891594500
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911372661372664194304256001224728320x7feb78e196800x7feb78424f40302644302644240962421160655362201021382314929088213859615894891635379158948915931231589489197632415894891977682
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194137266137266419430425600824740480x7feb7b4795000x7feb78424f8016153016153015039129224865536881866581190820035447835615894892018061158948919763241589489226944515894892270775
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971372661372664194304256001224757760x7feb7b4793800x7feb78424fc0183282183282172051466264655361063364111358309042709392415894892313154158948922694451589489257488615894892576238
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001372661372664194304256001224769920x7feb7b4792000x7feb7842500016185516185515298129484865536971370841190867039027290815894892634847158948925748861589489293056715894892932010
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031372661372664194304256001224784640x7feb7b4790800x7feb78425040303302303302239352426424655362231932752321212089450237615894892973829158948929305671589489331472815894893316042
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061372661372664194304256001224799360x7feb78e19f000x7feb78425080302234302234235722417880655362197287072314332088064154415894893357881158948933147281589489369681015894893698183
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209137266137266419430425600824814080x7feb78e19d800x7feb784250c016272016272015713130176865536890594241194860035796772015894893738712158948936968101589489399185015894893993207
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121372661372664194304256001224831360x7feb78e19c000x7feb78425100191246191246182761529976655361203230521422635048302984415894894033916158948939918501589489431985115894894321429
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151372661372664194304256001224843520x7feb78e19a800x7feb7842514016103616103614348128829665536992349351186722039866460015894894369708158948943198511589489461793215894894619283
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181372661372664194304256001224858240x7feb78e199000x7feb78425180304518304518244322436152655362218107752327964088898238015894894663582158948946179321589489500433315894895005804
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211372661372664194304256001224872960x7feb78e197800x7feb784251c0300137300137224762401104655362109225882297489084541963215894895047913158948950043331589489538513515894895386515
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241372661372664194304256001224887680x7feb78e196000x7feb7842520016237616237615807129901665536956188331193111038419977615894895427185158948953851351589489567729515894895678659
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271372661372664194304256001224907520x7feb7b4794800x7feb78425240201226201226179701609816655361244272921502376049944877615894895719358158948956772951589489600049615894896001902
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301372661372664194304256001224919680x7feb7b4793000x7feb7842528016100616100614736128805665536918394771184029036908791615894896050921158948960004961589489630001715894896301375
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331372661372664194304256001224934400x7feb7b4791800x7feb784252c0302017302017224352416144655362092866922304993083888297215894896346684158948963000171589489668417815894896685676
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361372661372664194304256001224949120x7feb7b4790000x7feb78425300297506297506204322380056655362134202382276103085541469615894896726436158948966841781589489706482015894897066078
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391372661372664194304256001224963840x7feb78e19e800x7feb7842534016238516238515674129908865536989024651197237039734036815894897106477158948970648201589489735938015894897360791
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421372661372664194304256001224983680x7feb78e19d000x7feb78425380213039213039197731704320655361195693291581142048001969615894897402050158948973593801589489768594115894897687364
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451372661372664194304256001224995840x7feb78e19b800x7feb784253c016200416200414997129604065536912084011191673036656424015894897735483158948976859411589489798610215894897987347
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024813726613726641943042560012241013120x7feb78e19a000x7feb78425400300655300655237802405248655362139718062293311085762014015894898028216158948979861021589489837602315894898377439
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025113726613726641943042560012241027840x7feb78e198800x7feb78425440298622298622205132388984655362020827142279113081006246415894898419028158948983760231589489876818515894898769580
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025413726613726641943042560012241042560x7feb78e197000x7feb7842548016103616103615594128829665536979690081185517039361176815894898810299158948987681851589489906082515894899062113
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025713726613726641943042560012241062400x7feb7b4795800x7feb784254c0219497219497193721755984655361425320331646415057187442015894899102833158948990608251589489939042615894899391866
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026013726613726641943042560012241077120x7feb7b4794000x7feb7842550016045416045415262128364065536906364761181822036428091215894899440695158948993904261589489968418715894899685550
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026313726613726641943042560016241094400x7feb7b4792800x7feb78425540298528298528225992388232655362179751752283440087363396015894899729859158948996841871589490006434815894900065771
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026613726613726641943042560016241111680x7feb7b4791000x7feb78425580299119299119215722392960655362059862312281742082567886015894900107610158949000643481589490044371015894900445023
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691372661372664194304256008241128960x7feb78e19f800x7feb784255c0162017162017161411296144655361030383181192634041388384415894900485712158949004437101589490074163015894900742846
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027213726613726641943042560012241151360x7feb78e19e000x7feb78425600229945229945199411839568655361435902881725068057610664415894900783535158949007416301589490107651115894901077869
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027513726613726641943042560012241166080x7feb78e19c800x7feb7842564016172716172715296129382465536905903611183509036408850815894901125808158949010765111589490137523215894901376712
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027813726613726641943042560016241183360x7feb78e19b000x7feb78425680296613296613211372372912655362029947832268021081371133615894901420881158949013752321589490175587315894901757304
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028113726613726641943042560016241200640x7feb78e199800x7feb784256c0297599297599201192380800655361937561042270597077675860415894901798353158949017558731589490213523515894902136795
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028413726613726641943042560012241217920x7feb78e198000x7feb78425700163749163749160191310000655361043087401207315041897389215894902178064158949021352351589490243267515894902434059
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028713726613726641943042560012241240320x7feb78e196800x7feb78425740240824240824202541926600655361476044291814984059216599215894902474668158949024326751589490277987615894902781111
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029013726613726641943042560012241255040x7feb7b4795000x7feb7842578016170816170815751129367265536966968341189519038852138415894902828550158949027798761589490307155715894903072924
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029313726613726641943042560012241274880x7feb7b4793800x7feb784257c0297436297436206342379496655362029269222273349081343944815894903117373158949030715571589490345667815894903458006
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029613726613726641943042560012241292160x7feb7b4792000x7feb78425800297960297960216222383688655362126279752276068085224605615894903499265158949034566781589490383412015894903835687
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029913726613726641943042560012241309440x7feb7b4790800x7feb78425840169372169372163581354984655361077031521252635043255720015894903876706158949038341201589490414004015894904141491
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030213726613726641943042560012241334400x7feb78e19f000x7feb78425880258450258450214972067608655361834064411958596073536864415894904182980158949041400401589490449620215894904497753
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030513726613726641943042560012241349120x7feb78e19d800x7feb784258c016088616088615737128709665536978946851183825039330780815894904545821158949044962021589490479012215894904791526
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030813726613726641943042560012241368960x7feb78e19c000x7feb78425900296337296337196612370704655362027571472261138081277348015894904832675158949047901221589490517316415894905174467
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031113726613726641943042560012241388800x7feb78e19a800x7feb78425940295114295114207182360920655362050514452257287082194035615894905215827158949051731641589490555076515894905552109
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031413726613726641943042560012241408640x7feb78e199000x7feb78425980177864177864172451422920655361062570431313746042676911615894905593008158949055507651589490585604615894905857452
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031713726613726641943042560012241436160x7feb78e197800x7feb784259c0278458278458224102227672655362042759262123609081884708415894905897491158949058560461589490622372715894906225254
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032013726613726641943042560012241453440x7feb78e196000x7feb78425a0016085616085615692128685665536999017191184947040134206815894906274283158949062237271589490652708815894906528567
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032313726613726641943042560012241475840x7feb7b4794800x7feb78425a40295730295730219852365848655362086083912260396083617578415894906573836158949065270881589490691460915894906915949
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032613726613726641943042560012241495680x7feb7b4793000x7feb78425a80294388294388209942355112655361998211012246077080102511215894906958208158949069146091589490730501015894907306300
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032913726613726641943042560012241515520x7feb7b4791800x7feb78425ac0186736186736179351493896655361142667571384214045880804415894907347169158949073050101589490761957115894907620973
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033213726613726641943042560012241543040x7feb7b4790000x7feb78425b00299540299540234252396328655362068900312283853082931090015894907662622158949076195711589490800549215894908006744
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033513726613726641943042560012241562880x7feb78e19e800x7feb78425b40171763171763166541374112655361026314481264894041227512015894908054963158949080054921589490831285315894908314207
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033813726613726641943042560012241587840x7feb78e19d000x7feb78425b80297876297876209452383016655361894712752260691075962404015894908354996158949083128531589490869397415894908695369
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034113726613726641943042560012241610240x7feb78e19b800x7feb78425bc0297465297465211672379728655362017095122265397080857699215894908736778158949086939741589490907685515894909078110
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034413726613726641943042560012241632640x7feb78e19a000x7feb78425c00205919205919185841647360655361317023961536821052855695215894909118279158949090768551589490940277615894909404143
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034713726613726641943042560012241665280x7feb78e198800x7feb78425c40341127341127262432729024655362377884922610753095290680415894909444782158949094027761589490981237715894909831403
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035013726613726641943042560012241685120x7feb78e197000x7feb78425c80183756183756176941470056655361111151391360691044620476815894909862503158949098123771589491012693815894910128267
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035313726613726641943042560012241712640x7feb7b4795800x7feb78425cc0297075297075201572376608655361922838142256545077089472815894910170406158949101269381589491051269915894910514188
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035613726613726641943042560012241737600x7feb7b4794000x7feb78425d00297146297146209552377176655361935352882269942077588790015894910555907158949105126991589491089654115894910897880
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035913726613726641943042560012241762560x7feb7b4792800x7feb78425d40225480225480199761803848655361491489281691456059834408015894910938939158949108965411589491123398115894911235392
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036213726613726641943042560012241797760x7feb7b4791000x7feb78425d803810333810332824130482726553627292981429315730109347540815894911280421158949112339811589491167078315894911691432
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036513726613726641943042560012241822720x7feb78e19f800x7feb78425dc0211269211269188761690160655361369606611578707054959070815894911721391158949116707831589491200246415894912003815
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036813726613726641943042560012241855360x7feb78e19e000x7feb78425e00308462308462227662467704655361795584642345218071997956415894912044994158949120024641589491239366515894912414226
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037113726613726641943042560012241885440x7feb78e19c800x7feb78425e40310998310998212592487992655361887829632354999075688869615894912434925158949123936651589491279302615894912813367
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037413726613726641943042560012241915520x7feb78e19b000x7feb78425e80266633266633216322133072655361835973612021452073614126815894912835016158949127930261589491316070715894913162029
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037713726613726641943042560012241958400x7feb78e199800x7feb78425ec04615324615323235436922646553634268999135805470137251148815894913202498158949131607071589491364390915894913661118
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038013726613726641943042560012241985920x7feb78e198000x7feb78425f00244594244594207981956760655361470376461845434058990121215894913693897158949136439091589491400231015894914003670
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038313726613726641943042560012242023680x7feb78e196800x7feb78425f40334826334826230182678616655362135952652561043085615086815894914044549158949140023101589491442103115894914440470
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038613726613726641943042560012242058880x7feb7b4795000x7feb78425f80329712329712243322637704655362257868812529422090491574015894914465160158949144210311589491482839215894914870361
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038913726613726641943042560012242094080x7feb7b4793800x7feb78425fc0306022306022234842448184655362164558112341186086758075615894914881011158949148283921589491523879315894915240063
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039213726613726641943042560012242144640x7feb7b4792000x7feb784260005422345422343597743378806553640724422742269130163073960415894915281262158949152387931589491577639515894915818530
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039513726613726641943042560012242177280x7feb7b4790800x7feb78426040273982273982224142191864655361884868602079468075571780415894915837840158949157763951589491616551615894916166902
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039813726613726641943042560012242220160x7feb78e19f000x7feb78426080363612363612261252908904655362355892612790352094412934015894916212061158949161655161589491659831715894916639932
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040113726613726641943042560012242260480x7feb78e19d800x7feb784260c03652163652162879429217366553625462151628094630102025686015894916651211158949165983171589491704727915894917088872
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040413726613726641943042560012242300800x7feb78e19c000x7feb784261003462783462782563727702326553625133911426631820100711503615894917099802158949170472791589491747512015894917516922
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040713726613726641943042560012242359040x7feb78e19a800x7feb784261406241816241813989749934566553647265756748762150189238661615894917527722158949174751201589491808232215894918108059
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041013726613726641943042560012242394240x7feb78e199000x7feb78426180303406303406235162427256655362115131712319823084780287615894918132229158949180823221589491848168315894918483151
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041313726613726641943042560012242442240x7feb78e197800x7feb784261c03991483991482712631931926553627222782230824550109069519215894918523770158949184816831589491893880415894918984070
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041613726613726641943042560012242487680x7feb78e196000x7feb784262003915823915822817431326646553628343113130183830113549411615894918994419158949189388041589491940824615894919452669
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041913726613726641943042560012242533120x7feb7b4794800x7feb784262403875433875432864331003526553628578814329869990114491646815894919463189158949194082461589491986648715894919908509
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221372661372664194304256008242555520x7feb7b4793000x7feb784262807194447194444538957555606553654503654956340320218188570815894919919489158949198664871589492053800915894920579914
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042513726613726641943042560012242598400x7feb7b4791800x7feb784262c03652113652112752329216966553625981917427996890104103954415894920599783158949205380091589492098905015894921031024
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042813726613726641943042560012242656640x7feb7b4790000x7feb784263004692954692953164737543686553634807748336437970139409125615894921041934158949209890501589492150569215894921547632
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043113726613726641943042560012242712320x7feb78e19e800x7feb784263404709264709263176237674166553634986125536648180140122564015894921558712158949215056921589492202857315894922046671
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341372661372664194304256008242732160x7feb78e19d000x7feb784263804823124823123306038585046553635830131037492280143494594815894922071471158949220285731589492253049515894922575519
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371372661372664194304256008242757120x7feb78e19b800x7feb784263c08806038806035283970448326553667832395369248370271503660415894922586409158949225304951589492330857715894923353922
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044013726613726641943042560012242807680x7feb78e19a000x7feb784264004271784271782978834174326553631490702733009210126139020015894923372582158949233085771589492379545915894923837161
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044313726613726641943042560012242876160x7feb78e198800x7feb784264405499065499063600143992566553640623304942801630162671486815894923848091158949237954591589492436506015894924407078
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044613726613726641943042560012242942080x7feb78e197000x7feb784264805512985512983624344103926553641805457943046600167400374815894924417928158949243650601589492493738215894924979566
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491372661372664194304256008242969600x7feb7b4795800x7feb784264c05631475631473684545051846553642082155943940290168502875615894924990285158949249373821589492550458415894925546293
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521372661372664194304256008242999680x7feb7b4794000x7feb78426500104347410434746166883478006553681004925282253330324193934015894925557173158949255045841589492638794615894926431833
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551372661372664194304256008243027200x7feb7b4792800x7feb784265407232857232854501757862886553653803944256568290215389956815894926452523158949263879461589492706170815894927106478
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045813726613726641943042560012243054720x7feb7b4791000x7feb784265807249127249124520057993046553654708239956754870219007039615894927117498158949270617081589492774891015894927793203
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046113726613726641943042560012243082240x7feb78e19f800x7feb784265c07221727221724413957773846553654226742256640740217080919215894927803843158949277484971589492842993815894928476348
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641372661372664194304256008243109760x7feb78e19e000x7feb784266007272387272384556658179126553655881133256984420223698623615894928486937158949284299381589492910273915894929145063
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671372661372664194304256008243132160x7feb78e19c800x7feb78426640136598313659837703910927872655361061793463108137870424891503215894929156222158949291027391589493018738115894930231788
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701372661372664194304256008243159680x7feb78e19b000x7feb78426680137193113719317722710975456655361075311214108461240430298678815894930251378158949301873811589493126226415894931327184
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047313726613726641943042560012243187200x7feb78e199800x7feb784266c0137193513719357768810975488655361072700862108597910429254461215894931337924158949312622641589493238930615894932454339
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047613726613726641943042560012243214720x7feb78e198000x7feb78426700137241813724187797110979352655361077480868108471790431166380015894932465179158949323893061589493351010815894933573704
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791372661372664194304256008243242240x7feb78e196800x7feb78426740137542213754227780211003384655361086131642108858950434626876415894933584384158949335101081589493460963115894934681130
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821372661372664194304256008243264640x7feb7b4795000x7feb784267802663585266358514291221308688655362130157038211886660852236989615894934693419158949346096311589493658371515894936650116
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851372661372664194304256008243292160x7feb7b4793800x7feb784267c02667402266740214257421339224655362130094686212253590852211941615894936672405158949365837151589493851171915894938582392
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048813726613726641943042560012243319680x7feb7b4792000x7feb784268002673341267334114358221386736655362124937638212408550850149152015894938594612158949385117191589494050564315894940573618
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049113726613726641943042560012243347200x7feb7b4790800x7feb784268402668646266864614356521349176655362126765727212308400850880320415894940585548158949405056431589494249492815894942564113
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941372661372664194304256008243374720x7feb78e19f000x7feb784268802673755267375514317821390048655362131133856212632020852627716815894942575933158949424949281589494444229215894944513930
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049713726613726641943042560082400x7feb78e19d800x7feb784268c052560315256031273779420482566553642320234674192759001692983550415894944525220158949444422921589494806374015894948136289