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

43 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_VMEMSQ_INST_LEVEL_VMEMSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000896130896135335544322560083264640x00x7fd0e6a04180104857611113035142372307612075847189171067120758474367719041207584743709622312075847437209605
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00289613089613532768256002424124800x00x7fd0e6a3510040961069781369611212075847451790473120758474521084391207584745211499912075847452123532
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0048961308961354194304256002424129280x7fd216a7e9000x7fd0e6a3514052428811732531150174384012075847452175839120758474523989981207584745253307712075847452536279
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0068961308961354194304256003624136320x7fd216a7e8000x7fd0e6a3518052428813261562169742329212075847452603755120758474527778761207584745302907512075847453099706
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0088961308961354194304256002824140800x7fd216a7e7000x7fd0e6a351c052428813506013172870090412075847453137517120758474533293941207584745358059312075847453650740
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00108961308961354194304256002424145280x7fd216a7e6000x7fd0e6a3520052428810910835139655174812075847453678903120758474538690721207584745400747112075847454010629
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00128961308961354194304256002424149760x7fd216a7e5000x7fd0e6a3524052428811221602143620528812075847454062666120758474542367501207584745437307012075847454376309
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00148961308961354194304256002424154240x7fd216a7e4000x7fd0e6a3528052428812426791159066942812075847454451448120758474546218691207584745475290812075847454755614
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00168961308961354194304256002824161280x7fd216a7e3000x7fd0e6a352c052428814238844182256644012075847454806007120758474549834671207584745523738612075847455282232
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00188961308961354194304256002824168320x7fd216a7ea000x7fd0e6a3530052428814110483180614780812075847455311848120758474555020251207584745575530412075847455799163
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00208961308961354194304256002424175360x7fd216a7e9000x7fd0e6a3534052428811118541142307881212075847455823088120758474560154631207584745615258212075847456155726
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00228961308961354194304256002424182400x7fd216a7e8000x7fd0e6a3538052428813071668167322814812075847456205218120758474563882611207584745651674112075847456519682
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00248961308961354194304256002424189440x7fd216a7e7000x7fd0e6a353c052428812083863154658189212075847456584232120758474567557801207584745688745912075847456890091
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00268961308961354194304256002824199040x7fd216a7e6000x7fd0e6a3540052428814120979180742278812075847456939553120758474571199381207584745736713712075847457437668
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00288961308961354194304256002824206080x7fd216a7e5000x7fd0e6a3544052428814228841182126807612075847457465019120758474576474561207584745789753512075847457967092
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00308961308961354194304256002424213120x7fd216a7e4000x7fd0e6a3548052428812526162160346811612075847457994523120758474581799341207584745831081312075847458313797
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00328961308961354194304256002424220160x7fd216a7e3000x7fd0e6a354c052428812511934160161285612075847458363118120758474585415321207584745867257212075847458675529
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00348961308961354194304256002424227200x7fd216a7ea000x7fd0e6a3550052428812011830153730914812075847458737294120758474589036111207584745903673012075847459039856
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00368961308961354194304256002824236800x7fd216a7e9000x7fd0e6a3554052428814116529180686900812075847459088957120758474592655291207584745951272812075847459557107
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00388961308961354194304256002824243840x7fd216a7e8000x7fd0e6a3558052428813390088171398232812075847459581933120758474597748071207584746003048612075847460100627
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00408961308961354194304256002424250880x7fd216a7e7000x7fd0e6a355c052428812405895158805591212075847460126315120758474603199251207584746049288412075847460495992
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00428961308961354194304256002424257920x7fd216a7e6000x7fd0e6a3560052428811319776144883688412075847460545103120758474607120831207584746084856312075847460851533
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00448961308961354194304256002424264960x7fd216a7e5000x7fd0e6a3564052428812557591160730107212075847460913308120758474610868021207584746121752112075847461220869
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00468961308961354194304256002824277120x7fd216a7e4000x7fd0e6a3568052428813307819170339599212075847461267806120758474614464801207584746169911912075847461769419
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00488961308961354194304256002824284160x7fd216a7e3000x7fd0e6a356c052428813921376178194396812075847461792942120758474619760781207584746222567712075847462296398
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00508961308961354194304256002424291200x7fd216a7ea000x7fd0e6a3570052428811909327152426302412075847462324480120758474625085561207584746264087512075847462643723
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00528961308961354194304256002424300800x7fd216a7e9000x7fd0e6a3574052428812576131160973456412075847462692053120758474628642341207584746299527412075847462998322
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00548961308961354194304256002424307840x7fd216a7e8000x7fd0e6a3578052428811423184146218041212075847463062822120758474632275931207584746336327212075847463366166
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00568961308961354194304256002824320000x7fd216a7e7000x7fd0e6a357c052428814123847180795053212075847463416550120758474635943111207584746384359012075847463912181
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00588961308961354194304256002824329600x7fd216a7e6000x7fd0e6a3580052428814269449182643426812075847463937127120758474641351091207584746438854812075847464459228
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00608961308961354194304256002424339200x7fd216a7e5000x7fd0e6a3584052428812402921158758967212075847464486829120758474646682271207584746479878612075847464801814
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00628961308961354194304256002424348800x7fd216a7e4000x7fd0e6a3588052428811950198152967627612075847464852428120758474650235851207584746515814512075847465161573
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00648961308961354194304256002424358400x7fd216a7e3000x7fd0e6a358c052428811830261151417556012075847465223568120758474653922241207584746552550312075847465528334
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00668961308961354194304256002824373120x7fd216a7ea000x7fd0e6a3590052428814132265180887872012075847465576965120758474657520621207584746600422112075847466074880
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00688961308961354194304256002824382720x7fd216a7e9000x7fd0e6a3594052428813923855178211996812075847466098584120758474662843801207584746653637912075847466607199
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00708961308961354194304256002424392320x7fd216a7e8000x7fd0e6a3598052428812341583157965201212075847466632947120758474668226181207584746695429712075847466957260
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00728961308961354194304256002424401920x7fd216a7e7000x7fd0e6a359c052428810830085138624748812075847467010699120758474671875761207584746732645612075847467329321
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00748961308961354194304256002424411520x7fd216a7e6000x7fd0e6a35a0052428812136361155340030412075847467390435120758474675562151207584746768757412075847467690372
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00768961308961354194304256002824426240x7fd216a7e5000x7fd0e6a35a4052428813918303178154652812075847467738332120758474679118931207584746816197212075847468232690
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00788961308961354194304256002824435840x7fd216a7e4000x7fd0e6a35a8052428814256652182481289212075847468256925120758474684424511207584746869269012075847468762866
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00808961308961354194304256002424445440x7fd216a7e3000x7fd0e6a35ac052428812380571158466320412075847468789124120758474689677291207584746909828812075847469101355
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00828961308961354194304256002424457600x7fd216a7ea000x7fd0e6a35b0052428812211121156292679612075847469148582120758474693250071207584746945812712075847469460943
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00848961308961354194304256002424467200x7fd216a7e9000x7fd0e6a35b4052428812394432158639500812075847469520924120758474696880461207584746981924512075847469822004
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00868961308961354194304256002824484480x7fd216a7e8000x7fd0e6a35b8052428814159122181227358412075847469872708120758474700570041207584747032020312075847470390591
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00888961308961354194304256002824494080x7fd216a7e7000x7fd0e6a35bc052428814208102181858421212075847470415066120758474706003621207584747085172112075847470896080
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00908961308961354194304256002424503680x7fd216a7e6000x7fd0e6a35c0052428812990765166273535212075847470927088120758474711224401207584747125139912075847471254466
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00928961308961354194304256002424515840x7fd216a7e5000x7fd0e6a35c4052428811639044148961796412075847471302956120758474714806781207584747161603812075847471618883
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00948961308961354194304256002424525440x7fd216a7e4000x7fd0e6a35c8052428812324768157755945212075847471680288120758474718457971207584747197763612075847471980435
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00968961308961354194304256002824542720x7fd216a7e3000x7fd0e6a35cc052428812511239160140856412075847472032252120758474722107551207584747247395412075847472542139
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00988961308961354194304256002824554880x7fd216a7ea000x7fd0e6a35d0052428812992719166305796812075847472568649120758474727499531207584747299891212075847473069209
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001008961308961354194304256002424567040x7fd216a7e9000x7fd0e6a35d4052428812232564156583435612075847473094065120758474732792311207584747341203012075847473415062
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001028961308961354194304256002424581760x7fd216a7e8000x7fd0e6a35d8052428810808912138349634012075847473463241120758474736382691207584747377458912075847473777385
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001048961308961354194304256002424593920x7fd216a7e7000x7fd0e6a35dc052428811740658150283753212075847473837016120758474740008281207584747413378712075847474136923
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001068961308961354194304256002824613760x7fd216a7e6000x7fd0e6a35e0052428814221614182034422412075847474185043120758474743619461207584747462754512075847474671246
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001088961308961354194304256002824625920x7fd216a7e5000x7fd0e6a35e4052428814116723180685458012075847474695722120758474748805041207584747517218312075847475242257
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001108961308961354194304256002424638080x7fd216a7e4000x7fd0e6a35e8052428811816496151251933212075847475268546120758474754523421207584747558722112075847475589964
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001128961308961354194304256002424652800x7fd216a7e3000x7fd0e6a35ec05242888990755115085382812075847475642100120758474758056201207584747594786012075847475950624
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001148961308961354194304256002424664960x7fd216a7ea000x7fd0e6a35f0052428811385669145744856012075847476016676120758474761841791207584747631873812075847476321713
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001168961308961354194304256002824684800x7fd216a7e9000x7fd0e6a35f4052428812587832161129366012075847476369963120758474765459371207584747680625612075847476875873
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001188961308961354194304256002824696960x7fd216a7e8000x7fd0e6a35f8052428814107169180566175212075847476901792120758474770899351207584747734353412075847477414835
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001208961308961354194304256002424709120x7fd216a7e7000x7fd0e6a35fc052428813005004166452815212075847477439391120758474776260921207584747775569212075847477758544
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001228961308961354194304256002424723840x7fd216a7e6000x7fd0e6a36000524288771135198725013212075847477807214120758474779748911207584747811281012075847478116018
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001248961308961354194304256002424736000x7fd216a7e5000x7fd0e6a3604052428811871677151959366812075847478178544120758474783452891207584747847904912075847478481968
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001268961308961354194304256002824758400x7fd216a7e4000x7fd0e6a3608052428812294602157370207212075847478530809120758474787065681207584747897216712075847479043211
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001288961308961354194304256002824770560x7fd216a7e3000x7fd0e6a360c052428813790381176518707612075847479067947120758474792532861207584747950560512075847479575851
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001308961308961354194304256002424782720x7fd216a7ea000x7fd0e6a3610052428813113411167858272412075847479598413120758474797830431207584747991184312075847479914721
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001328961308961354194304256002424800000x7fd216a7e9000x7fd0e6a36140524288702245389884496012075847479962460120758474801440021207584748028736112075847480290710
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001348961308961354194304256002424812160x7fd216a7e8000x7fd0e6a3618052428811917372152553641612075847480350932120758474805164801207584748064880012075847480651580
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001368961308961354194304256002824834560x7fd216a7e7000x7fd0e6a361c052428813322838170521711212075847480699059120758474808726391207584748113535812075847481187977
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001388961308961354194304256002824849280x7fd216a7e6000x7fd0e6a3620052428814154295181170461612075847481212172120758474813963171207584748164735612075847481697945
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001408961308961354194304256002424864000x7fd216a7e5000x7fd0e6a3624052428813023829166705578812075847481724384120758474819035151207584748203327412075847482036584
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001428961308961354194304256002424881280x7fd216a7e4000x7fd0e6a36280524288551359470584900812075847482083762120758474822617531207584748241119212075847482414076
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001448961308961354194304256002424896000x7fd216a7e3000x7fd0e6a362c052428811665202149315337212075847482495337120758474826593511207584748279375112075847482796647
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001468961308961354194304256002824920960x7fd216a7ea000x7fd0e6a3630052428811994638153522430812075847482844225120758474830251101207584748329230912075847483344335
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001488961308961354194304256002824935680x7fd216a7e9000x7fd0e6a3634052428812873259164779132012075847483369912120758474835527881207584748380734712075847483857809
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001508961308961354194304256002424950400x7fd216a7e8000x7fd0e6a3638052428811147910142700160412075847483881543120758474840662261207584748420206512075847484205275
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001528961308961354194304256002424967680x7fd216a7e7000x7fd0e6a363c0524288465014859544956012075847484253805120758474844279841207584748458622312075847484589108
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001548961308961354194304256002424982400x7fd216a7e6000x7fd0e6a3640052428811602964148529566012075847484649490120758474848134221207584748494750212075847484950319
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015689613089613541943042560028241007360x7fd216a7e5000x7fd0e6a3644052428812214711156342743212075847484998389120758474851715011207584748543342012075847485485915
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015889613089613541943042560028241022080x7fd216a7e4000x7fd0e6a3648052428814112061180627813612075847485511061120758474856945391207584748594621812075847485970325
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016089613089613541943042560024241036800x7fd216a7e3000x7fd0e6a364c052428812365231158282132012075847486019997120758474861865371207584748631789612075847486321107
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016289613089613541943042560024241056640x7fd216a7ea000x7fd0e6a36500524288352011845061756012075847486382731120758474865471751207584748671261512075847486715400
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016489613089613541943042560024241071360x7fd216a7e9000x7fd0e6a3654052428812136916155351665612075847486781192120758474869463741207584748707901312075847487082382
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016689613089613541943042560028241098880x7fd216a7e8000x7fd0e6a3658052428810583105135459856012075847487130491120758474873079721207584748756781112075847487617065
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016889613089613541943042560028241113600x7fd216a7e7000x7fd0e6a365c052428813204569169012043612075847487644937120758474878223701207584748807564912075847488127023
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017089613089613541943042560024241128320x7fd216a7e6000x7fd0e6a3660052428812769405163439974412075847488156067120758474883354881207584748846588712075847488468798
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017289613089613541943042560024241148160x7fd216a7e5000x7fd0e6a36640524288368217647141985212075847488518100120758474886882861207584748886220612075847488865115
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017489613089613541943042560024241162880x7fd216a7e4000x7fd0e6a3668052428812900158165112038812075847488926549120758474890985251207584748922748412075847489230834
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017689613089613541943042560028241190400x7fd216a7e3000x7fd0e6a366c05242888231249105351291612075847489278513120758474894521231207584748970844212075847489758936
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017889613089613541943042560028241207680x7fd216a7ea000x7fd0e6a3670052428814080373180233268812075847489782880120758474899700411207584749021852012075847490271328
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018089613089613541943042560024241224960x7fd216a7e9000x7fd0e6a3674052428811922394152611814412075847490296585120758474904831591207584749061819812075847490621098
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018289613089613541943042560024241247360x7fd216a7e8000x7fd0e6a36780524288343000343907673212075847490668546120758474908415571207584749102395612075847491027263
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018489613089613541943042560024241264640x7fd216a7e7000x7fd0e6a367c052428811052850141470016412075847491092104120758474912599551207584749139691512075847491399835
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018689613089613541943042560020241279360x7fd216a7e6000x7fd0e6a36800524288406498252037206012075847491448085120758474916209141207584749188635312075847491936713
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018889613089613541943042560028241296640x7fd216a7e5000x7fd0e6a3684052428813993970179130277612075847491960918120758474921495521207584749240523112075847492456409
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019089613089613541943042560024241313920x7fd216a7e4000x7fd0e6a3688052428810452682133796678812075847492480173120758474926631501207584749280362912075847492806470
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019289613089613541943042560024241336320x7fd216a7e3000x7fd0e6a368c0524288356668745638362812075847492853878120758474930311481207584749322282712075847493273948
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019489613089613541943042560024241353600x7fd216a7ea000x7fd0e6a3690052428810919828139759796012075847493315896120758474934845861207584749362250612075847493625552
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019689613089613541943042560020241368320x7fd216a7e9000x7fd0e6a36940524288280562335901076412075847493674403120758474938500251207584749413562312075847494188638
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019889613089613541943042560028241385600x7fd216a7e8000x7fd0e6a3698052428812984292166194883212075847494214637120758474943999421207584749465466112075847494706651
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020089613089613541943042560024241402880x7fd216a7e7000x7fd0e6a369c052428810706156137030765212075847494734182120758474949157801207584749505514012075847495058325
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020289613089613541943042560024241427840x7fd216a7e6000x7fd0e6a36a00524288353335645203184412075847495107786120758474952812191207584749549241812075847495543186
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020489613089613541943042560024241447680x7fd216a7e5000x7fd0e6a36a4052428811052205141452270012075847495581527120758474957468171207584749588409612075847495887135
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020689613089613541943042560020241457280x7fd216a7e4000x7fd0e6a36a80524288253128132402614012075847495939212120758474961096951207584749641689412075847496467894
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020889613089613541943042560028241477120x7fd216a7e3000x7fd0e6a36ac052428813203268169006428012075847496495125120758474966759331207584749693625212075847496987780
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021089613089613541943042560024241496960x7fd216a7ea000x7fd0e6a36b0052428810770369137856197612075847497022545120758474972002511207584749733865012075847497341738
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021289613089613541943042560024241521920x7fd216a7e9000x7fd0e6a36b40524288330818742321888412075847497395919120758474975584891207584749778664812075847497837680
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021489613089613541943042560024241541760x7fd216a7e8000x7fd0e6a36b8052428811504049147252929212075847497874759120758474980484071207584749818328712075847498186739
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021689613089613541943042560020241556480x7fd216a7e7000x7fd0e6a36bc0524288245817631476743612075847498234437120758474984100061207584749874088412075847498792274
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021889613089613541943042560028241576320x7fd216a7e6000x7fd0e6a36c0052428813965277178756847612075847498816309120758474989973631207584749924888212075847499300038
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022089613089613541943042560024241596160x7fd216a7e5000x7fd0e6a36c4052428810261099131337100812075847499326958120758474995055211207584749964504012075847499648375
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022289613089613541943042560024241623680x7fd216a7e4000x7fd0e6a36c80524288321076441076338812075847499699280120758474998694571207584750011457612075847500171287
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022489613089613541943042560024241646080x7fd216a7e3000x7fd0e6a36cc05242889438787120798390812075847500206031120758475003750541207584750051969312075847500522419
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022689613089613541943042560020241663360x7fd216a7ea000x7fd0e6a36d00524288237362630381471212075847500571190120758475007428921207584750112065112075847501145968
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022889613089613541943042560028241685760x7fd216a7e9000x7fd0e6a36d4052428812840320164363925612075847501190281120758475013553701207584750161760912075847501668379
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023089613089613541943042560024241708160x7fd216a7e8000x7fd0e6a36d805242889196031117692408812075847501700699120758475018756881207584750202032712075847502023539
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023289613089613541943042560024241740800x7fd216a7e7000x7fd0e6a36dc0524288314677240261725212075847502076908120758475022526461207584750253360512075847502585554
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023489613089613541943042560024241765760x7fd216a7e6000x7fd0e6a36e005242887998375102376842012075847502624716120758475027884841207584750292992412075847502933130
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023689613089613541943042560020241777920x7fd216a7e5000x7fd0e6a36e40524288236780230290274412075847502981259120758475031616031207584750361024112075847503661934
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023889613089613541943042560028241802880x7fd216a7e4000x7fd0e6a36e8052428811244625143934374012075847503687542120758475038723201207584750413135912075847504182742
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024089613089613541943042560024241827840x7fd216a7e3000x7fd0e6a36ec0524288755016096621441612075847504210043120758475043948781207584750453455812075847504537411
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024289613089613541943042560024241863040x7fd216a7ea000x7fd0e6a36f00524288314184640215294412075847504585981120758475047603171207584750507535612075847505126396
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024489613089613541943042560024241893120x7fd216a7e9000x7fd0e6a36f40524288359279846005643212075847505173112120758475053435151207584750549743412075847505500341
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024689613089613541943042560020241907840x7fd216a7e8000x7fd0e6a36f80524288229813429431262012075847505550774120758475057217531207584750623951112075847506290249
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024889613089613541943042560028241937920x7fd216a7e7000x7fd0e6a36fc05242887815105100030793212075847506322869120758475064991901207584750679726912075847506848226
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025089613089613541943042560024241968000x7fd216a7e6000x7fd0e6a37000524288300761038501481612075847506872010120758475070751881207584750723022712075847507233291
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025289613089613541943042560024242010880x7fd216a7e5000x7fd0e6a37040524288345130344189390812075847507282312120758475074659061207584750785150512075847507903006
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025489613089613541943042560024242046080x7fd216a7e4000x7fd0e6a37080524288319271840884734412075847507942519120758475081110241207584750828750312075847508290837
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025689613089613541943042560020242060800x7fd216a7e3000x7fd0e6a370c0524288230954829558053612075847508338415120758475085110221207584750913486012075847509186882
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025889613089613541943042560028242096000x7fd216a7ea000x7fd0e6a37100524288397201550851688812075847509211608120758475094039791207584750972989812075847509780545
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026089613089613541943042560024242131200x7fd216a7e9000x7fd0e6a37140524288331983642475201212075847509809519120758475099924571207584751017277612075847510176431
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026289613089613541943042560024242181760x7fd216a7e8000x7fd0e6a37180524288340323943567107612075847510228768120758475104009351207584751085693312075847510907079
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026489613089613541943042560024242222080x7fd216a7e7000x7fd0e6a371c0524288321773841201940012075847510946512120758475111180521207584751131917112075847511371582
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026689613089613541943042560020242239360x7fd216a7e6000x7fd0e6a37200524288229207829300263612075847511396819120758475115846101207584751228812812075847512339711
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026889613089613541943042560028242279680x7fd216a7e5000x7fd0e6a37240524288348984944675361612075847512367092120758475125556471207584751292956512075847512981193
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027089613089613541943042560024242320000x7fd216a7e4000x7fd0e6a37280524288327668241927294012075847513012241120758475132052441207584751340748312075847513458971
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027289613089613541943042560024242378240x7fd216a7e3000x7fd0e6a372c0524288389896549909160812075847513483727120758475136660421207584751419276012075847514245082
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027489613089613541943042560024242423680x7fd216a7ea000x7fd0e6a37300524288307226139331923612075847514287331120758475144570791207584751468187812075847514731957
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027689613089613541943042560020242435840x7fd216a7e9000x7fd0e6a37340524288231036129578929212075847514757455120758475149388371207584751573771412075847515790124
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027889613089613541943042560028242481280x7fd216a7e8000x7fd0e6a37380524288352163745091785212075847515817865120758475159977131207584751644011212075847516492499
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028089613089613541943042560024242526720x7fd216a7e7000x7fd0e6a373c0524288318043040720478812075847516518778120758475167015511207584751692939012075847516981007
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028289613089613541943042560024242592640x7fd216a7e6000x7fd0e6a37400524288427640754747131612075847517013627120758475171935491207584751779050612075847517843249
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028489613089613541943042560024242648320x7fd216a7e5000x7fd0e6a37440524288324675041555380012075847517879948120758475180815451207584751835162412075847518404442
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028689613089613541943042560020242663040x7fd216a7e4000x7fd0e6a37480524288231051729549462812075847518432535120758475186125831207584751959817912075847519669744
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028889613089613541943042560028242718720x7fd216a7e3000x7fd0e6a374c0524288326862141826960012075847519704058120758475198840981207584752039769612075847520470211
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029089613089613541943042560024242774400x7fd216a7ea000x7fd0e6a37500524288326105641754612812075847520506008120758475206925751207584752099577412075847521043928
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029289613089613541943042560012242799360x7fd216a7e9000x7fd0e6a37540524288223634228623177212075847521075587120758475212508131207584752198985012075847522061509
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029489613089613541943042560024242865280x7fd216a7e8000x7fd0e6a37580524288317300040596938812075847522101804120758475222677691207584752258600812075847522656184
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029689613089613541943042560020242880000x7fd216a7e7000x7fd0e6a375c0524288231536329637368012075847522683495120758475228618471207584752403336212075847524105618
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029889613089613541943042560032242945920x7fd216a7e6000x7fd0e6a37600524288330322742270791612075847524137918120758475243168811207584752492711912075847524998136
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030089613089613541943042560024243011840x7fd216a7e5000x7fd0e6a37640524288327225841869682812075847525029585120758475252101581207584752552967712075847525601919
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030289613089613541943042560012243049600x7fd216a7e4000x7fd0e6a37680524288223022528528809612075847525627606120758475258141551207584752669287212075847526765241
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030489613089613541943042560024243136000x7fd216a7e3000x7fd0e6a376c0524288318883040834319612075847526805676120758475269719111207584752738454912075847527455684
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030689613089613541943042560020243148160x7fd216a7ea000x7fd0e6a37700524288230583929537751212075847527482443120758475276715881207584752922134212075847529292758
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030889613089613541943042560020243175680x7fd216a7e9000x7fd0e6a37740524288224991628803424812075847529325158120758475295091811207584753030693812075847530377814
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031089613089613541943042560012243203200x7fd216a7e8000x7fd0e6a37780524288220151528144266412075847530411457120758475305822971207584753099829512075847531069199
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031289613089613541943042560012243240960x7fd216a7e7000x7fd0e6a377c0524288222404728439116012075847531102521120758475312816541207584753244181012075847532513373
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031489613089613541943042560012243288960x7fd216a7e6000x7fd0e6a37800524288225230628819282812075847532559649120758475327270891207584753351348612075847533583933
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031689613089613541943042560020243301120x7fd216a7e5000x7fd0e6a37840524288261329533450068412075847533616874120758475337928451207584753684307312075847536915925
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031889613089613541943042560020243328640x7fd216a7e4000x7fd0e6a37880524288229116229351097212075847536949277120758475371358721207584753868034612075847538752799
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032089613089613541943042560012243356160x7fd216a7e3000x7fd0e6a378c0524288223369828608071612075847538788255120758475389712251207584753976098212075847539833547
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032289613089613541943042560012243393920x7fd216a7ea000x7fd0e6a37900524288249317331896784412075847539866148120758475400496201207584754233169212075847542403003
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032489613089613541943042560012243441920x7fd216a7e9000x7fd0e6a37940524288245042931363892412075847542449810120758475426195311207584754415536512075847544226071
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032689613089613541943042560020243454080x7fd216a7e8000x7fd0e6a37980524288285367436524025612075847544259032120758475444408041207584755049502012075847550566674
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032889613089613541943042560020243481600x7fd216a7e7000x7fd0e6a379c0524288301421038602103212075847550598884120758475507774191207584755381804712075847553892175
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033089613089613541943042560012243509120x7fd216a7e6000x7fd0e6a37a00524288240727930791394012075847553921569120758475541108461207584755565036012075847555726844
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332896130896135419430425600122400x7fd216a7e5000x7fd0e6a37a40524288258728933093747612075847555757431120758475559434791207584756046986212075847560544347