Files
rocm-systems/tests/workloads/Axes1/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.kd000202048202048335544322560043241600x00x7ff18ec0428000017249839171366172491365515051724998673481817249986848227
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00220204820204832768256001224138880x00x7ff18ec23f8000017249992035347172499867348181724999216233617249992165533
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0052020482020484194304256001224143360x7ff191cc53800x7ff18ec23fc000017249992202162172499921623361724999249017617249992492374
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0082020482020484194304256001624150400x7ff191cc52000x7ff18ec2400000017249992529443172499924901761724999289081617249992893283
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00112020482020484194304256001624154880x7ff191cc50800x7ff18ec2404000017249992925242172499928908161724999328329617249993285693
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00142020482020484194304256001224159360x7ff18f697f000x7ff18ec2408000017249993318942172499932832961724999359209617249993594354
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00172020482020484194304256001224163840x7ff18f697d800x7ff18ec240c000017249993626764172499935920961724999389929617249993901626
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00202020482020484194304256001224170880x7ff18f697c000x7ff18ec2410000017249993945465172499938992961724999421961617249994222037
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00232020482020484194304256001624177920x7ff18f697a800x7ff18ec2414000017249994253437172499942196161724999462265617249994624857
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00262020482020484194304256001624184960x7ff18f6979000x7ff18ec2418000017249994656146172499946226561724999501801617249995020296
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00292020482020484194304256001624192000x7ff18f6977800x7ff18ec241c000017249995050875172499950180161724999533641617249995338617
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00322020482020484194304256001624199040x7ff18f6976000x7ff18ec2420000017249995371007172499953364161724999564169617249995643839
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00352020482020484194304256001224206080x7ff191cc54800x7ff18ec2424000017249995684388172499956416961724999594889617249995951081
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00382020482020484194304256001624213120x7ff191cc53000x7ff18ec2428000017249995984580172499959488961724999634009617249996342321
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00412020482020484194304256001624220160x7ff191cc51800x7ff18ec242c000017249996375400172499963400961724999673017617249996732560
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00442020482020484194304256001624227200x7ff191cc50000x7ff18ec2430000017249996765329172499967301761724999703129617249997033652
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00472020482020484194304256001224234240x7ff18f697e800x7ff18ec2434000017249997066421172499970312961724999733769617249997339894
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00502020482020484194304256001224241280x7ff18f697d000x7ff18ec2438000017249997378473172499973376961724999763897617249997641146
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00532020482020484194304256001624248320x7ff18f697b800x7ff18ec243c000017249997672505172499976389761724999803145617249998033625
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00562020482020484194304256001624255360x7ff18f697a000x7ff18ec2440000017249998065784172499980314561724999844745617249998450024
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00592020482020484194304256001224262400x7ff18f6978800x7ff18ec2444000017249998484223172499984474561724999875209617249998753776
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00622020482020484194304256001224269440x7ff18f6977000x7ff18ec2448000017249998785525172499987520961724999903097617249999032658
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00652020482020484194304256001224276480x7ff191cc55800x7ff18ec244c000017249999072127172499990309761724999930793617249999309711
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00682020482020484194304256001624286080x7ff191cc54000x7ff18ec2450000017249999342300172499993079361724999967481617249999676431
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00712020482020484194304256001624293120x7ff191cc52800x7ff18ec2454000017249999709210172499996748161725000004137617250000043121
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00742020482020484194304256001224300160x7ff191cc51000x7ff18ec2458000017250000075610172500000413761725000031833617250000320053
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077202048202048419430425600824309760x7ff18f697f800x7ff18ec245c000017250000352962172500003183361725000060041617250000602016
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00802020482020484194304256001224316800x7ff18f697e000x7ff18ec2460000017250000641455172500006004161725000087833617250000879978
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00832020482020484194304256001624326400x7ff18f697c800x7ff18ec2464000017250000911847172500008783361725000124137617250001243018
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00862020482020484194304256001224336000x7ff18f697b000x7ff18ec2468000017250001275378172500012413761725000160809617250001609689
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00892020482020484194304256001224345600x7ff18f6979800x7ff18ec246c000017250001641878172500016080961725000189081617250001892581
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092202048202048419430425600824355200x7ff18f6978000x7ff18ec2470000017250001924570172500018908161725000217017617250002171953
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00952020482020484194304256001224362240x7ff18f6976800x7ff18ec2474000017250002211702172500021701761725000245177617250002453386
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00982020482020484194304256001224371840x7ff191cc55000x7ff18ec2478000017250002485335172500024517761725000281929617250002821006
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001012020482020484194304256001224381440x7ff191cc53800x7ff18ec247c000017250002853395172500028192961725000319161617250003193166
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001042020482020484194304256001224391040x7ff191cc52000x7ff18ec2480000017250003225635172500031916161725000347001617250003471708
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107202048202048419430425600824403200x7ff191cc50800x7ff18ec2484000017250003504508172500034700161725000374841617250003750151
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001102020482020484194304256001224412800x7ff18f697f000x7ff18ec2488000017250003790240172500037484161725000402761617250004029204
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001132020482020484194304256001224422400x7ff18f697d800x7ff18ec248c000017250004060783172500040276161725000439337617250004395214
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001162020482020484194304256001224432000x7ff18f697c000x7ff18ec2490000017250004427603172500043933761725000476265617250004764364
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119202048202048419430425600824441600x7ff18f697a800x7ff18ec2494000017250004795883172500047626561725000504233517250005043946
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001222020482020484194304256001224453760x7ff18f6979000x7ff18ec2498000017250005076675172500050423351725000533785517250005339478
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001252020482020484194304256001224463360x7ff18f6977800x7ff18ec249c000017250005378017172500053378551725000561833517250005620071
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001282020482020484194304256001224475520x7ff18f6976000x7ff18ec24a0000017250005651960172500056183351725000598137517250005982891
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001312020482020484194304256001224485120x7ff191cc54800x7ff18ec24a4000017250006015180172500059813751725000635609517250006357801
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134202048202048419430425600824494720x7ff191cc53000x7ff18ec24a8000017250006390150172500063560951725000663641517250006638083
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001372020482020484194304256001224506880x7ff191cc51800x7ff18ec24ac000017250006670163172500066364151725000691529517250006916826
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001402020482020484194304256001224516480x7ff191cc50000x7ff18ec24b0000017250006956305172500069152951725000719209517250007193868
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001432020482020484194304256001224528640x7ff18f697e800x7ff18ec24b4000017250007225608172500071920951725000756025517250007561868
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001462020482020484194304256001224540800x7ff18f697d000x7ff18ec24b8000017250007593328172500075602551725000793033517250007931788
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149202048202048419430425600824552960x7ff18f697b800x7ff18ec24bc000017250007962958172500079303351725000821017517250008211931
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001522020482020484194304256001224567680x7ff18f697a000x7ff18ec24c0000017250008243900172500082101751725000849017517250008491643
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001552020482020484194304256001224577280x7ff18f6978800x7ff18ec24c4000017250008529862172500084901751725000876729517250008768846
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001582020482020484194304256001224589440x7ff18f6977000x7ff18ec24c8000017250008801015172500087672951725000913353517250009135316
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001612020482020484194304256001224601600x7ff191cc55800x7ff18ec24cc000017250009167525172500091335351725000949721517250009498826
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164202048202048419430425600824613760x7ff191cc54000x7ff18ec24d0000017250009530285172500094972151725000977449517250009776119
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001672020482020484194304256001224628480x7ff191cc52800x7ff18ec24d4000017250009807728172500097744951725001005609517250010057781
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001702020482020484194304256001224638080x7ff191cc51000x7ff18ec24d8000017250010101420172500100560951725001034985517250010351743
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001732020482020484194304256001224650240x7ff18f697f800x7ff18ec24dc000017250010383852172500103498551725001071913517250010720863
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001762020482020484194304256001224662400x7ff18f697e000x7ff18ec24e0000017250010753092172500107191351725001108569517250011087233
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179202048202048419430425600824674560x7ff18f697c800x7ff18ec24e4000017250011118952172500110856951725001136489517250011366506
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001822020482020484194304256001224689280x7ff18f697b000x7ff18ec24e8000017250011399495172500113648951725001165481517250011656398
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001852020482020484194304256001224701440x7ff18f6979800x7ff18ec24ec000017250011696437172500116548151725001193337517250011934980
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001882020482020484194304256001224716160x7ff18f6978000x7ff18ec24f0000017250011966369172500119333751725001230217517250012303850
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001912020482020484194304256001224728320x7ff18f6976800x7ff18ec24f4000017250012335749172500123021751725001267225517250012673930
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194202048202048419430425600824740480x7ff191cc55000x7ff18ec24f8000017250012706059172500126722551725001295177517250012953383
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001972020482020484194304256001224757760x7ff191cc53800x7ff18ec24fc000017250012985682172500129517751725001324617517250013247735
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002002020482020484194304256001224769920x7ff191cc52000x7ff18ec2500000017250013287404172500132461751725001352585517250013527607
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002032020482020484194304256001224784640x7ff191cc50800x7ff18ec2504000017250013559916172500135258551725001389449517250013896277
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002062020482020484194304256001224799360x7ff18f697f000x7ff18ec2508000017250013928766172500138944951725001425993517250014261747
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209202048202048419430425600824814080x7ff18f697d800x7ff18ec250c000017250014294877172500142599351725001454681517250014548540
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002122020482020484194304256001224831360x7ff18f697c000x7ff18ec2510000017250014579829172500145468151725001484553517250014847142
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002152020482020484194304256001224843520x7ff18f697a800x7ff18ec2514000017250014896760172500148455351725001512649517250015128384
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002182020482020484194304256001224858240x7ff18f6979000x7ff18ec2518000017250015159803172500151264951725001549065517250015492484
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002212020482020484194304256001224872960x7ff18f6977800x7ff18ec251c000017250015524194172500154906551725001585353517250015855125
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002242020482020484194304256001224887680x7ff18f6976000x7ff18ec2520000017250015886674172500158535351725001613273517250016134397
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002272020482020484194304256001224907520x7ff191cc54800x7ff18ec2524000017250016166106172500161327351725001643449517250016436389
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002302020482020484194304256001224919680x7ff191cc53000x7ff18ec2528000017250016474598172500164344951725001671785517250016719451
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002332020482020484194304256001224934400x7ff191cc51800x7ff18ec252c000017250016750651172500167178551725001708329517250017084962
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002362020482020484194304256001224949120x7ff191cc50000x7ff18ec2530000017250017116261172500170832951725001744601517250017447732
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002392020482020484194304256001224963840x7ff18f697e800x7ff18ec2534000017250017478501172500174460151725001772665517250017728224
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002422020482020484194304256001224983680x7ff18f697d000x7ff18ec2538000017250017759794172500177266551725001803625517250018037846
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002452020482020484194304256001224995840x7ff18f697b800x7ff18ec253c000017250018084125172500180362551725001831657517250018318209
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024820204820204841943042560012241013120x7ff18f697a000x7ff18ec2540000017250018349828172500183165751725001868729517250018688969
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025120204820204841943042560012241027840x7ff18f6978800x7ff18ec2544000017250018720298172500186872951725001905193517250019053609
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025420204820204841943042560012241042560x7ff18f6977000x7ff18ec2548000017250019085488172500190519351725001933241517250019333961
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025720204820204841943042560012241062400x7ff191cc55800x7ff18ec254c000017250019365160172500193324151725001964697517250019648723
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026020204820204841943042560012241077120x7ff191cc54000x7ff18ec2550000017250019688752172500196469751725001993449517250019936085
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026320204820204841943042560016241094400x7ff191cc52800x7ff18ec2554000017250019968774172500199344951725002029865517250020300345
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026620204820204841943042560016241111680x7ff191cc51000x7ff18ec2558000017250020331954172500202986551725002066393517250020665595
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002692020482020484194304256008241128960x7ff18f697f800x7ff18ec255c000017250020697724172500206639351725002094521517250020946938
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027220204820204841943042560012241151360x7ff18f697e000x7ff18ec2560000017250020979117172500209452151725002127113517250021272729
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027520204820204841943042560012241166080x7ff18f697c800x7ff18ec2564000017250021311788172500212711351725002154953517250021551161
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027820204820204841943042560016241183360x7ff18f697b000x7ff18ec2568000017250021582920172500215495351725002191449517250021916101
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028120204820204841943042560016241200640x7ff18f6979800x7ff18ec256c000017250021947220172500219144951725002228537517250022287171
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028420204820204841943042560012241217920x7ff18f6978000x7ff18ec2570000017250022319060172500222853751725002258009517250022581813
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028720204820204841943042560012241240320x7ff18f6976800x7ff18ec2574000017250022614103172500225800951725002291321517250022914864
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029020204820204841943042560012241255040x7ff191cc55000x7ff18ec2578000017250022954783172500229132151725002319161417250023193277
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029320204820204841943042560012241274880x7ff191cc53800x7ff18ec257c000017250023225146172500231916141725002355625417250023557967
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029620204820204841943042560012241292160x7ff191cc52000x7ff18ec2580000017250023589986172500235562541725002392185417250023923477
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029920204820204841943042560012241309440x7ff191cc50800x7ff18ec2584000017250023954797172500239218541725002420729417250024208840
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030220204820204841943042560012241334400x7ff18f697f000x7ff18ec2588000017250024241219172500242072941725002455161417250024553261
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030520204820204841943042560012241349120x7ff18f697d800x7ff18ec258c000017250024592319172500245516141725002483001417250024831703
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030820204820204841943042560012241368960x7ff18f697c000x7ff18ec2590000017250024863352172500248300141725002520153417250025203253
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031120204820204841943042560012241388800x7ff18f697a800x7ff18ec2594000017250025235412172500252015341725002556505417250025566733
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031420204820204841943042560012241408640x7ff18f6979000x7ff18ec2598000017250025597652172500255650541725002585529417250025856936
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031720204820204841943042560012241436160x7ff18f6977800x7ff18ec259c000017250025887595172500258552941725002621449417250026216556
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032020204820204841943042560012241453440x7ff18f6976000x7ff18ec25a0000017250026256775172500262144941725002650633417250026507828
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032320204820204841943042560012241475840x7ff191cc54800x7ff18ec25a4000017250026539807172500265063341725002687321417250026874788
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032620204820204841943042560012241495680x7ff191cc53000x7ff18ec25a8000017250026907227172500268732141725002724009417250027241838
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032920204820204841943042560012241515520x7ff191cc51800x7ff18ec25ac000017250027273827172500272400941725002753577417250027537420
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033220204820204841943042560012241543040x7ff191cc50000x7ff18ec25b0000017250027569779172500275357741725002790169417250027903350
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033520204820204841943042560012241562880x7ff18f697e800x7ff18ec25b4000017250027941739172500279016941725002818761417250028189313
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033820204820204841943042560012241587840x7ff18f697d000x7ff18ec25b8000017250028221292172500281876141725002855705417250028558593
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034120204820204841943042560012241610240x7ff18f697b800x7ff18ec25bc000017250028590722172500285570541725002892585417250028927573
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034420204820204841943042560012241632640x7ff18f697a000x7ff18ec25c0000017250028959012172500289258541725002923657417250029238184
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034720204820204841943042560012241665280x7ff18f6978800x7ff18ec25c4000017250029268973172500292365741725002963305417250029652533
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035020204820204841943042560012241685120x7ff18f6977000x7ff18ec25c8000017250029673472172500296330541725002993689417250029938475
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035320204820204841943042560012241712640x7ff191cc55800x7ff18ec25cc000017250029970014172500299368941725003031465417250030316675
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035620204820204841943042560012241737600x7ff191cc54000x7ff18ec25d0000017250030349674172500303146541725003068633417250030687945
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035920204820204841943042560012241762560x7ff191cc52800x7ff18ec25d4000017250030719524172500306863341725003100665417250031008336
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036220204820204841943042560012241797760x7ff191cc51000x7ff18ec25d8000017250031039776172500310066541725003142281417250031467844
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036520204820204841943042560012241822720x7ff18f697f800x7ff18ec25dc000017250031486953172500314228141725003177353417250031775126
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036820204820204841943042560012241855360x7ff18f697e000x7ff18ec25e0000017250031806945172500317735341725003214921417250032193484
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037120204820204841943042560012241885440x7ff18f697c800x7ff18ec25e4000017250032205894172500321492141725003255929417250032580324
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037420204820204841943042560012241915520x7ff18f697b000x7ff18ec25e8000017250032592394172500325592941725003292105417250032922615
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037720204820204841943042560012241958400x7ff18f6979800x7ff18ec25ec000017250032953794172500329210541725003339033417250033407822
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038020204820204841943042560012241985920x7ff18f6978000x7ff18ec25f0000017250033430201172500333903341725003372553417250033727103
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038320204820204841943042560012242023680x7ff18f6976800x7ff18ec25f4000017250033757882172500337255341725003412057417250034142802
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038620204820204841943042560012242058880x7ff191cc55000x7ff18ec25f8000017250034155271172500341205741725003452537417250034544491
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038920204820204841943042560012242094080x7ff191cc53800x7ff18ec25fc000017250034558791172500345253741725003490073417250034902381
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039220204820204841943042560012242144640x7ff191cc52000x7ff18ec2600000017250034934360172500349007341725003541881417250035436097
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039520204820204841943042560012242177280x7ff191cc50800x7ff18ec2604000017250035459876172500354188141725003577961417250035781328
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039820204820204841943042560012242220160x7ff18f697f000x7ff18ec2608000017250035812857172500357796141725003619529417250036212556
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040120204820204841943042560012242260480x7ff18f697d800x7ff18ec260c000017250036228766172500361952941725003661945417250036636225
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040420204820204841943042560012242300800x7ff18f697c000x7ff18ec2610000017250036652734172500366194541725003701945417250037036564
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040720204820204841943042560012242359040x7ff18f697a800x7ff18ec2614000017250037053704172500370194541725003759177417250037608549
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041020204820204841943042560012242394240x7ff18f6979000x7ff18ec2618000017250037632138172500375917741725003797017417250037971779
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041320204820204841943042560012242442240x7ff18f6977800x7ff18ec261c000017250038003048172500379701741725003841385417250038437536
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041620204820204841943042560012242487680x7ff18f6976000x7ff18ec2620000017250038449936172500384138541725003885817417250038899884
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041920204820204841943042560012242533120x7ff191cc54800x7ff18ec2624000017250038912234172500388581741725003930681417250039348802
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004222020482020484194304256008242555520x7ff191cc53000x7ff18ec2628000017250039360151172500393068141725003997225417250040014014
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042520204820204841943042560012242598400x7ff191cc51800x7ff18ec262c000017250040033743172500399722541725004041017417250040451192
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042820204820204841943042560012242656640x7ff191cc50000x7ff18ec2630000017250040463092172500404101741725004092153417250040939109
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043120204820204841943042560012242712320x7ff18f697e800x7ff18ec2634000017250040955688172500409215341725004141449317250041432345
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004342020482020484194304256008242732160x7ff18f697d000x7ff18ec2638000017250041446965172500414144931725004189865317250041915732
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004372020482020484194304256008242757120x7ff18f697b800x7ff18ec263c000017250041932422172500418986531725004263849317250042658702
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044020204820204841943042560012242807680x7ff18f697a000x7ff18ec2640000017250042680402172500426384931725004309993317250043116590
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044320204820204841943042560012242876160x7ff18f6978800x7ff18ec2644000017250043133570172500430999331725004363801317250043655575
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044620204820204841943042560012242942080x7ff18f6977000x7ff18ec2648000017250043673655172500436380131725004417433317250044190921
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004492020482020484194304256008242969600x7ff191cc55800x7ff18ec264c000017250044208160172500441743331725004470857317250044725657
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004522020482020484194304256008242999680x7ff191cc54000x7ff18ec2650000017250044742886172500447085731725004555465317250045571234
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004552020482020484194304256008243027200x7ff191cc52800x7ff18ec2654000017250045596103172500455546531725004618953317250046207366
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045820204820204841943042560012243054720x7ff191cc51000x7ff18ec2658000017250046224526172500461895331725004684553317250046887638
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046120204820204841943042560012243082240x7ff18f697f800x7ff18ec265c000017250046898758172500468455331725004752441317250047565400
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004642020482020484194304256008243109760x7ff18f697e000x7ff18ec2660000017250047576870172500475244131725004818857317250048229422
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004672020482020484194304256008243132160x7ff18f697c800x7ff18ec2664000017250048241772172500481885731725004927497317250049293424
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004702020482020484194304256008243159680x7ff18f697b000x7ff18ec2668000017250049316833172500492746461725005031704617250050366595
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047320204820204841943042560012243187200x7ff18f6979800x7ff18ec266c000017250050378434172500503170461725005142872417250051494854
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047620204820204841943042560012243214720x7ff18f6978000x7ff18ec2670000017250051508774172500514287241725005256552317250052630134
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004792020482020484194304256008243242240x7ff18f6976800x7ff18ec2674000017250052642423172500525655231725005367544217250053739184
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004822020482020484194304256008243264640x7ff191cc55000x7ff18ec2678000017250053751213172500536754421725005562152117250055669142
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004852020482020484194304256008243292160x7ff191cc53800x7ff18ec267c000017250055689131172500556215211725005752392017250057565091
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048820204820204841943042560012243319680x7ff191cc52000x7ff18ec2680000017250057576921172500575239201725005948087817250059554457
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049120204820204841943042560012243347200x7ff191cc50800x7ff18ec2684000017250059567397172500594808781725006146375717250061506085
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004942020482020484194304256008243374720x7ff18f697f000x7ff18ec2688000017250061518804172500614637571725006337159517250063418413
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049720204820204841943042560082400x7ff18f697d800x7ff18ec268c000017250063432183172500633715951725006696967317250067038855