Files
rocm-systems/tests/workloads/Axes2/mi200/SQ_INST_LEVEL_LDS.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

38 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_LDSSQ_INST_LEVEL_LDSSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000208139208139335544322560043241600x00x7fbdd460428000017355253900417173545572388401735539687991317355396996993
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00220813920813932768256001224138880x00x7fbdd4623f8000017355402176137173553968799131735540230679717355402311693
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0052081392081394194304256001224143360x7fbdf30f63800x7fbdd4623fc000017355402345302173554023067971735540267655817355402679014
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0082081392081394194304256001624150400x7fbdf30f62000x7fbdd462400000017355402716183173554026765581735540308311817355403085393
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00112081392081394194304256001624154880x7fbdf30f60800x7fbdd462404000017355403118362173554030831181735540348119817355403483312
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00142081392081394194304256001224159360x7fbdf0ac9f000x7fbdd462408000017355403517392173554034811981735540378823917355403790524
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00172081392081394194304256001224163840x7fbdf0ac9d800x7fbdd46240c000017355403823184173554037882391735540409607917355404098396
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00202081392081394194304256001224170880x7fbdf0ac9c000x7fbdd462410000017355404143325173554040960791735540440087917355404403108
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00232081392081394194304256001624177920x7fbdf0ac9a800x7fbdd462414000017355404435087173554044008791735540480536017355404807718
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00262081392081394194304256001624184960x7fbdf0ac99000x7fbdd462418000017355404840777173554048053601735540520056017355405202937
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00292081392081394194304256001624192000x7fbdf0ac97800x7fbdd46241c000017355405234306173554052005601735540551992017355405522279
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00322081392081394194304256001624199040x7fbdf0ac96000x7fbdd462420000017355405554858173554055199201735540582424017355405826651
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00352081392081394194304256001224206080x7fbdf30f64800x7fbdd462424000017355405866650173554058242401735540612824117355406130853
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00382081392081394194304256001624213120x7fbdf30f63000x7fbdd462428000017355406163922173554061282411735540653288117355406535262
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00412081392081394194304256001624220160x7fbdf30f61800x7fbdd46242c000017355406568181173554065328811735540692568117355406927382
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00442081392081394194304256001624227200x7fbdf30f60000x7fbdd462430000017355406959511173554069256811735540720488217355407206764
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00472081392081394194304256001224234240x7fbdf0ac9e800x7fbdd462434000017355407238593173554072048821735540748152217355407483257
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00502081392081394194304256001224241280x7fbdf0ac9d000x7fbdd462438000017355407522896173554074815221735540775720217355407759100
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00532081392081394194304256001624248320x7fbdf0ac9b800x7fbdd46243c000017355407790509173554077572021735540812472217355408126310
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00562081392081394194304256001624255360x7fbdf0ac9a000x7fbdd462440000017355408157239173554081247221735540849080317355408492420
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00592081392081394194304256001224262400x7fbdf0ac98800x7fbdd462444000017355408523579173554084908031735540877480317355408776663
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00622081392081394194304256001224269440x7fbdf0ac97000x7fbdd462448000017355408807542173554087748031735540905176317355409053605
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00652081392081394194304256001224276480x7fbdf30f65800x7fbdd46244c000017355409091794173554090517631735540933640417355409338148
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00682081392081394194304256001624286080x7fbdf30f64000x7fbdd462450000017355409370037173554093364041735540970456417355409706368
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00712081392081394194304256001624293120x7fbdf30f62800x7fbdd462454000017355409737547173554097045641735541007384417355410080528
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00742081392081394194304256001224300160x7fbdf30f61000x7fbdd462458000017355410108607173554100738441735541036120417355410362971
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077208139208139419430425600824309760x7fbdf0ac9f800x7fbdd46245c000017355410394120173554103612041735541064024517355410641903
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00802081392081394194304256001224316800x7fbdf0ac9e000x7fbdd462460000017355410682192173554106402451735541091816517355410919956
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00832081392081394194304256001624326400x7fbdf0ac9c800x7fbdd462464000017355410950295173554109181651735541128280517355411284446
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00862081392081394194304256001224336000x7fbdf0ac9b000x7fbdd462468000017355411315845173554112828051735541164664617355411648297
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00892081392081394194304256001224345600x7fbdf0ac99800x7fbdd46246c000017355411679586173554116466461735541192952617355411931229
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092208139208139419430425600824355200x7fbdf0ac98000x7fbdd462470000017355411962408173554119295261735541220840617355412210252
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00952081392081394194304256001224362240x7fbdf0ac96800x7fbdd462474000017355412248241173554122084061735541248632617355412488015
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00982081392081394194304256001224371840x7fbdf30f65000x7fbdd462478000017355412518784173554124863261735541285384717355412855705
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001012081392081394194304256001224381440x7fbdf30f63800x7fbdd46247c000017355412886924173554128538471735541321880717355413220445
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001042081392081394194304256001224391040x7fbdf30f62000x7fbdd462480000017355413251404173554132188071735541349864717355413500328
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107208139208139419430425600824403200x7fbdf30f60800x7fbdd462484000017355413532317173554134986471735541378344817355413785220
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001102081392081394194304256001224412800x7fbdf0ac9f000x7fbdd462488000017355413822829173554137834481735541406792817355414069643
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001132081392081394194304256001224422400x7fbdf0ac9d800x7fbdd46248c000017355414100762173554140679281735541443816817355414439953
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001162081392081394194304256001224432000x7fbdf0ac9c000x7fbdd462490000017355414470542173554144381681735541480968817355414811313
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119208139208139419430425600824441600x7fbdf0ac9a800x7fbdd462494000017355414841763173554148096881735541508600917355415087746
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001222081392081394194304256001224453760x7fbdf0ac99000x7fbdd462498000017355415119095173554150860091735541536344917355415365139
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001252081392081394194304256001224463360x7fbdf0ac97800x7fbdd46249c000017355415402768173554153634491735541564792917355415649691
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001282081392081394194304256001224475520x7fbdf0ac96000x7fbdd4624a0000017355415680260173554156479291735541601609017355416017812
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001312081392081394194304256001224485120x7fbdf30f64800x7fbdd4624a4000017355416049291173554160160901735541638169017355416383402
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134208139208139419430425600824494720x7fbdf30f63000x7fbdd4624a8000017355416414061173554163816901735541665977017355416661505
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001372081392081394194304256001224506880x7fbdf30f61800x7fbdd4624ac000017355416692894173554166597701735541694201017355416943677
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001402081392081394194304256001224516480x7fbdf30f60000x7fbdd4624b0000017355416982186173554169420101735541722329117355417224860
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001432081392081394194304256001224528640x7fbdf0ac9e800x7fbdd4624b4000017355417255569173554172232911735541758937117355417590980
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001462081392081394194304256001224540800x7fbdf0ac9d000x7fbdd4624b8000017355417621569173554175893711735541796569117355417967300
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149208139208139419430425600824552960x7fbdf0ac9b800x7fbdd4624bc000017355417998279173554179656911735541826137217355418263332
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001522081392081394194304256001224567680x7fbdf0ac9a000x7fbdd4624c0000017355418295472173554182613721735541854425217355418545905
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001552081392081394194304256001224577280x7fbdf0ac98800x7fbdd4624c4000017355418584334173554185442521735541883033217355418831927
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001582081392081394194304256001224589440x7fbdf0ac97000x7fbdd4624c8000017355418863387173554188303321735541919321217355419194888
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001612081392081394194304256001224601600x7fbdf30f65800x7fbdd4624cc000017355419226067173554191932121735541955689317355419558608
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164208139208139419430425600824613760x7fbdf30f64000x7fbdd4624d0000017355419589707173554195568931735541983849317355419840101
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001672081392081394194304256001224628480x7fbdf30f62800x7fbdd4624d4000017355419872090173554198384931735542012153317355420123253
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001702081392081394194304256001224638080x7fbdf30f61000x7fbdd4624d8000017355420161762173554201215331735542040745417355420409086
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001732081392081394194304256001224650240x7fbdf0ac9f800x7fbdd4624dc000017355420440175173554204074541735542077929417355420780936
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001762081392081394194304256001224662400x7fbdf0ac9e000x7fbdd4624e0000017355420812245173554207792941735542114553417355421147286
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179208139208139419430425600824674560x7fbdf0ac9c800x7fbdd4624e4000017355421177816173554211455341735542142873417355421430409
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001822081392081394194304256001224689280x7fbdf0ac9b000x7fbdd4624e8000017355421460908173554214287341735542171865517355421720371
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001852081392081394194304256001224701440x7fbdf0ac99800x7fbdd4624ec000017355421757820173554217186551735542199849517355422000134
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001882081392081394194304256001224716160x7fbdf0ac98000x7fbdd4624f0000017355422030713173554219984951735542236937517355422371424
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001912081392081394194304256001224728320x7fbdf0ac96800x7fbdd4624f4000017355422402893173554223693751735542273849617355422740124
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194208139208139419430425600824740480x7fbdf30f65000x7fbdd4624f8000017355422770824173554227384961735542301545617355423017197
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001972081392081394194304256001224757760x7fbdf30f63800x7fbdd4624fc000017355423048906173554230154561735542330777617355423309459
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002002081392081394194304256001224769920x7fbdf30f62000x7fbdd462500000017355423348418173554233077761735542359225617355423593942
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002032081392081394194304256001224784640x7fbdf30f60800x7fbdd462504000017355423625151173554235922561735542396105717355423962722
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002062081392081394194304256001224799360x7fbdf0ac9f000x7fbdd462508000017355423994281173554239610571735542432857717355424330213
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209208139208139419430425600824814080x7fbdf0ac9d800x7fbdd46250c000017355424360652173554243285771735542460825717355424609855
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002122081392081394194304256001224831360x7fbdf0ac9c000x7fbdd462510000017355424640474173554246082571735542490649817355424908207
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002152081392081394194304256001224843520x7fbdf0ac9a800x7fbdd462514000017355424955386173554249064981735542518537817355425187080
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002182081392081394194304256001224858240x7fbdf0ac99000x7fbdd462518000017355425217849173554251853781735542556393817355425565640
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002212081392081394194304256001224872960x7fbdf0ac97800x7fbdd46251c000017355425596569173554255639381735542593305817355425934770
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002242081392081394194304256001224887680x7fbdf0ac96000x7fbdd462520000017355425965359173554259330581735542622329917355426225373
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002272081392081394194304256001224907520x7fbdf30f64800x7fbdd462524000017355426256502173554262232991735542653337917355426534994
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002302081392081394194304256001224919680x7fbdf30f63000x7fbdd462528000017355426573183173554265333791735542682185917355426823557
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002332081392081394194304256001224934400x7fbdf30f61800x7fbdd46252c000017355426855096173554268218591735542718938017355427191067
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002362081392081394194304256001224949120x7fbdf30f60000x7fbdd462530000017355427222546173554271893801735542755290017355427554778
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002392081392081394194304256001224963840x7fbdf0ac9e800x7fbdd462534000017355427585597173554275529001735542783002017355427831600
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002422081392081394194304256001224983680x7fbdf0ac9d000x7fbdd462538000017355427862989173554278300201735542814106017355428142752
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002452081392081394194304256001224995840x7fbdf0ac9b800x7fbdd46253c000017355428180761173554281410601735542842538117355428427005
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024820813920813941943042560012241013120x7fbdf0ac9a000x7fbdd462540000017355428457714173554284253811735542878954117355428791195
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025120813920813941943042560012241027840x7fbdf0ac98800x7fbdd462544000017355428822724173554287895411735542915658117355429158265
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025420813920813941943042560012241042560x7fbdf0ac97000x7fbdd462548000017355429188945173554291565811735542943562217355429437208
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025720813920813941943042560012241062400x7fbdf30f65800x7fbdd46254c000017355429468157173554294356221735542975130217355429752950
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026020813920813941943042560012241077120x7fbdf30f64000x7fbdd462550000017355429792219173554297513021735543003962217355430041272
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026320813920813941943042560016241094400x7fbdf30f62800x7fbdd462554000017355430072701173554300396221735543041082217355430412382
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026620813920813941943042560016241111680x7fbdf30f61000x7fbdd462558000017355430444111173554304108221735543077850317355430780153
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002692081392081394194304256008241128960x7fbdf0ac9f800x7fbdd46255c000017355430811122173554307785031735543105722317355431058955
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027220813920813941943042560012241151360x7fbdf0ac9e000x7fbdd462560000017355431089674173554310572231735543138522317355431386947
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027520813920813941943042560012241166080x7fbdf0ac9c800x7fbdd462564000017355431425596173554313852231735543167226417355431673909
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027820813920813941943042560016241183360x7fbdf0ac9b000x7fbdd462568000017355431704528173554316722641735543203690417355432038659
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028120813920813941943042560016241200640x7fbdf0ac99800x7fbdd46256c000017355432069869173554320369041735543240090417355432402770
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028420813920813941943042560012241217920x7fbdf0ac98000x7fbdd462570000017355432433259173554324009041735543268122517355432683043
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028720813920813941943042560012241240320x7fbdf0ac96800x7fbdd462574000017355432713452173554326812251735543301674517355433018434
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029020813920813941943042560012241255040x7fbdf30f65000x7fbdd462578000017355433056823173554330167451735543330026517355433301936
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029320813920813941943042560012241274880x7fbdf30f63800x7fbdd46257c000017355433333415173554333002651735543366538517355433667117
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029620813920813941943042560012241292160x7fbdf30f62000x7fbdd462580000017355433698316173554336653851735543403034617355434031977
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029920813920813941943042560012241309440x7fbdf30f60800x7fbdd462584000017355434063546173554340303461735543432538617355434327419
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030220813920813941943042560012241334400x7fbdf0ac9f000x7fbdd462588000017355434359488173554343253861735543466714617355434668890
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030520813920813941943042560012241349120x7fbdf0ac9d800x7fbdd46258c000017355434707219173554346671461735543495370717355434955383
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030820813920813941943042560012241368960x7fbdf0ac9c000x7fbdd462590000017355434986112173554349537071735543532330717355435324943
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031120813920813941943042560012241388800x7fbdf0ac9a800x7fbdd462594000017355435356282173554353233071735543569050717355435692103
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031420813920813941943042560012241408640x7fbdf0ac99000x7fbdd462598000017355435723392173554356905071735543598442717355435986175
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031720813920813941943042560012241436160x7fbdf0ac97800x7fbdd46259c000017355436016455173554359844271735543634490817355436346526
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032020813920813941943042560012241453440x7fbdf0ac96000x7fbdd4625a0000017355436385585173554363449081735543663226817355436633978
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032320813920813941943042560012241475840x7fbdf30f64800x7fbdd4625a4000017355436665388173554366322681735543699946817355437001279
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032620813920813941943042560012241495680x7fbdf30f63000x7fbdd4625a8000017355437031618173554369994681735543736426917355437365879
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032920813920813941943042560012241515520x7fbdf30f61800x7fbdd4625ac000017355437396688173554373642691735543765946917355437661181
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033220813920813941943042560012241543040x7fbdf30f60000x7fbdd4625b0000017355437692521173554376594691735543802698917355438028592
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033520813920813941943042560012241562880x7fbdf0ac9e800x7fbdd4625b4000017355438066971173554380269891735543832891017355438330684
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033820813920813941943042560012241587840x7fbdf0ac9d000x7fbdd4625b8000017355438361133173554383289101735543869883017355438700434
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034120813920813941943042560012241610240x7fbdf0ac9b800x7fbdd4625bc000017355438731663173554386988301735543906715017355439068784
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034420813920813941943042560012241632640x7fbdf0ac9a000x7fbdd4625c0000017355439100293173554390671501735543937963117355439381426
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034720813920813941943042560012241665280x7fbdf0ac98800x7fbdd4625c4000017355439411915173554393796311735543977403117355439819634
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035020813920813941943042560012241685120x7fbdf0ac97000x7fbdd4625c8000017355439838704173554397740311735544010395117355440105627
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035320813920813941943042560012241712640x7fbdf30f65800x7fbdd4625cc000017355440135866173554401039511735544047147117355440473257
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035620813920813941943042560012241737600x7fbdf30f64000x7fbdd4625d0000017355440504386173554404714711735544084155217355440843417
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035920813920813941943042560012241762560x7fbdf30f62800x7fbdd4625d4000017355440874266173554408415521735544116091217355441162599
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036220813920813941943042560012241797760x7fbdf30f61000x7fbdd4625d8000017355441193658173554411609121735544157643217355441595027
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036520813920813941943042560012241822720x7fbdf0ac9f800x7fbdd4625dc000017355441616697173554415764321735544189835317355441900169
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036820813920813941943042560012241855360x7fbdf0ac9e000x7fbdd4625e0000017355441931218173554418983531735544227643317355442299508
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037120813920813941943042560012241885440x7fbdf0ac9c800x7fbdd4625e4000017355442310858173554422764331735544267531317355442719887
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037420813920813941943042560012241915520x7fbdf0ac9b000x7fbdd4625e8000017355442731157173554426753131735544305851417355443060238
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037720813920813941943042560012241958400x7fbdf0ac99800x7fbdd4625ec000017355443091198173554430585141735544352827417355443574015
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038020813920813941943042560012241985920x7fbdf0ac98000x7fbdd4625f0000017355443593074173554435282741735544389403517355443895626
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038320813920813941943042560012242023680x7fbdf0ac96800x7fbdd4625f4000017355443926816173554438940351735544428699517355444306476
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038620813920813941943042560012242058880x7fbdf30f65000x7fbdd4625f8000017355444319265173554442869951735544468683517355444704195
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038920813920813941943042560012242094080x7fbdf30f63800x7fbdd4625fc000017355444719495173554446868351735544506155617355445063256
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039220813920813941943042560012242144640x7fbdf30f62000x7fbdd462600000017355445094505173554450615561735544557851617355445596432
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039520813920813941943042560012242177280x7fbdf30f60800x7fbdd462604000017355445619401173554455785161735544593579617355445937383
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039820813920813941943042560012242220160x7fbdf0ac9f000x7fbdd462608000017355445968382173554459357961735544636139717355446379351
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040120813920813941943042560012242260480x7fbdf0ac9d800x7fbdd46260c000017355446394141173554463613971735544679435717355446811760
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040420813920813941943042560012242300800x7fbdf0ac9c000x7fbdd462610000017355446826599173554467943571735544719803817355447240028
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040720813920813941943042560012242359040x7fbdf0ac9a800x7fbdd462614000017355447250608173554471980381735544779915817355447817183
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041020813920813941943042560012242394240x7fbdf0ac99000x7fbdd462618000017355447839543173554477991581735544817563817355448177344
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041320813920813941943042560012242442240x7fbdf0ac97800x7fbdd46261c000017355448207793173554481756381735544861275917355448630472
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041620813920813941943042560012242487680x7fbdf0ac96000x7fbdd462620000017355448645631173554486127591735544905419917355449073210
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041920813920813941943042560012242533120x7fbdf30f64800x7fbdd462624000017355449087230173554490541991735544948620017355449503439
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004222081392081394194304256008242555520x7fbdf30f63000x7fbdd462628000017355449518798173554494862001735545013068017355450149832
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042520813920813941943042560012242598400x7fbdf30f61800x7fbdd46262c000017355450172541173554501306801735545055356117355450570971
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042820813920813941943042560012242656640x7fbdf30f60000x7fbdd462630000017355450586580173554505535611735545105004117355451067727
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043120813920813941943042560012242712320x7fbdf0ac9e800x7fbdd462634000017355451081517173554510500411735545154652117355451564154
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004342081392081394194304256008242732160x7fbdf0ac9d000x7fbdd462638000017355451577904173554515465211735545203756217355452055201
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004372081392081394194304256008242757120x7fbdf0ac9b800x7fbdd46263c000017355452069881173554520375621735545278316317355452800462
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044020813920813941943042560012242807680x7fbdf0ac9a000x7fbdd462640000017355452824501173554527831631735545324044317355453259300
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044320813920813941943042560012242876160x7fbdf0ac98800x7fbdd462644000017355453272239173554532404431735545378684317355453804135
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044620813920813941943042560012242942080x7fbdf0ac97000x7fbdd462648000017355453820055173554537868431735545432764417355454345791
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004492081392081394194304256008242969600x7fbdf30f65800x7fbdd46264c000017355454360381173554543276441735545487260417355454890487
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004522081392081394194304256008242999680x7fbdf30f64000x7fbdd462650000017355454905546173554548726041735545572556517355455743454
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004552081392081394194304256008243027200x7fbdf30f62800x7fbdd462654000017355455766294173554557255651735545636444617355456382537
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045820813920813941943042560012243054720x7fbdf30f61000x7fbdd462658000017355456396897173554563644461735545701900617355457036250
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046120813920813941943042560012243082240x7fbdf0ac9f800x7fbdd46265c000017355457051320173554570190061735545767532717355457692693
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004642081392081394194304256008243109760x7fbdf0ac9e000x7fbdd462660000017355457707433173554576753271735545831612817355458334696
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004672081392081394194304256008243132160x7fbdf0ac9c800x7fbdd462664000017355458349116173554583161281735545938268817355459401638
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004702081392081394194304256008243159680x7fbdf0ac9b000x7fbdd462668000017355459422977173554593827591735546043444017355460457570
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047320813920813941943042560012243187200x7fbdf0ac99800x7fbdd46266c000017355460468800173554604344401735546152948117355461569341
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047620813920813941943042560012243214720x7fbdf0ac98000x7fbdd462670000017355461580840173554615294811735546263748217355462707271
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004792081392081394194304256008243242240x7fbdf0ac96800x7fbdd462674000017355462719510173554626374821735546375844317355463825571
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004822081392081394194304256008243264640x7fbdf30f65000x7fbdd462678000017355463836941173554637584431735546571156517355465779170
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004852081392081394194304256008243292160x7fbdf30f63800x7fbdd46267c000017355465797879173554657115651735546763572717355467710809
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048820813920813941943042560012243319680x7fbdf30f62000x7fbdd462680000017355467722378173554676357271735546963540917355469702126
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049120813920813941943042560012243347200x7fbdf30f60800x7fbdd462684000017355469713006173554696354091735547160821117355471680064
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004942081392081394194304256008243374720x7fbdf0ac9f000x7fbdd462688000017355471691723173554716082111735547354645317355473616443
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049720813920813941943042560082400x7fbdf0ac9d800x7fbdd46268c000017355473628272173554735464531735547716533717355477243437