Files
rocm-systems/tests/workloads/Axes4/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.kd000219687219687335544322560043241600x00x7f2c5ee0428000017539642547842175389322253261753978956230517539789674205
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00221968721968732768256001224138880x00x7f2c5ee23f8000017539794859632175397895623051753979498422917539794988729
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0052196872196874194304256001224143360x7f2c61e2c3800x7f2c5ee23fc000017539795023528175397949842291753979534422917539795346589
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0082196872196874194304256001624150400x7f2c61e2c2000x7f2c5ee2400000017539795381879175397953442291753979574518917539795747589
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00112196872196874194304256001624154880x7f2c61e2c0800x7f2c5ee2404000017539795777878175397957451891753979613830917539796140369
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00142196872196874194304256001224159360x7f2c5f6cdf000x7f2c5ee2408000017539796172818175397961383091753979644199017539796444081
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00172196872196874194304256001224163840x7f2c5f6cdd800x7f2c5ee240c000017539796474580175397964419901753979674151017539796743564
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00202196872196874194304256001224170880x7f2c5f6cdc000x7f2c5ee2410000017539796786692175397967415101753979703751017539797039566
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00232196872196874194304256001624177920x7f2c5f6cda800x7f2c5ee2414000017539797069095175397970375101753979742087017539797422966
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00262196872196874194304256001624184960x7f2c5f6cd9000x7f2c5ee2418000017539797453875175397974208701753979780727117539797809216
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00292196872196874194304256001624192000x7f2c5f6cd7800x7f2c5ee241c000017539797838785175397978072711753979812007117539798122448
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00322196872196874194304256001624199040x7f2c5f6cd6000x7f2c5ee2420000017539798153057175397981200711753979842839117539798430370
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00352196872196874194304256001224206080x7f2c61e2c4800x7f2c5ee2424000017539798469349175397984283911753979872871117539798730913
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00382196872196874194304256001624213120x7f2c61e2c3000x7f2c5ee2428000017539798762712175397987287111753979910279217539799104133
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00412196872196874194304256001624220160x7f2c61e2c1800x7f2c5ee242c000017539799135122175397991027921753979946103217539799462534
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00442196872196874194304256001624227200x7f2c61e2c0000x7f2c5ee2430000017539799493383175397994610321753979973271217539799734057
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00472196872196874194304256001224234240x7f2c5f6cde800x7f2c5ee2434000017539799763796175397997327121753980000455217539800006010
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00502196872196874194304256001224241280x7f2c5f6cdd000x7f2c5ee2438000017539800043389175398000045521753980027479317539800276383
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00532196872196874194304256001624248320x7f2c5f6cdb800x7f2c5ee243c000017539800307302175398002747931753980063271317539800634124
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00562196872196874194304256001624255360x7f2c5f6cda000x7f2c5ee2440000017539800663653175398006327131753980099303317539800994525
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00592196872196874194304256001224262400x7f2c5f6cd8800x7f2c5ee2444000017539801024284175398009930331753980126855317539801270158
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00622196872196874194304256001224269440x7f2c5f6cd7000x7f2c5ee2448000017539801299937175398012685531753980153863417539801540071
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00652196872196874194304256001224276480x7f2c61e2c5800x7f2c5ee244c000017539801577760175398015386341753980181159417539801813094
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00682196872196874194304256001624286080x7f2c61e2c4000x7f2c5ee2450000017539801843983175398018115941753980218295417539802184775
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00712196872196874194304256001624293120x7f2c61e2c2800x7f2c5ee2454000017539802215564175398021829541753980254631417539802547865
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00742196872196874194304256001224300160x7f2c61e2c1000x7f2c5ee2458000017539802578574175398025463141753980281751517539802818868
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077219687219687419430425600824309760x7f2c5f6cdf800x7f2c5ee245c000017539802849607175398028175151753980309079517539803092331
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00802196872196874194304256001224316800x7f2c5f6cde000x7f2c5ee2460000017539803129210175398030907951753980336183517539803363204
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00832196872196874194304256001624326400x7f2c5f6cdc800x7f2c5ee2464000017539803394623175398033618351753980372695517539803728605
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00862196872196874194304256001224336000x7f2c5f6cdb000x7f2c5ee2468000017539803758304175398037269551753980408759617539804089026
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00892196872196874194304256001224345600x7f2c5f6cd9800x7f2c5ee246c000017539804118465175398040875961753980436647617539804367968
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092219687219687419430425600824355200x7f2c5f6cd8000x7f2c5ee2470000017539804397998175398043664761753980463927617539804640761
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00952196872196874194304256001224362240x7f2c5f6cd6800x7f2c5ee2474000017539804677740175398046392761753980491703617539804918594
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00982196872196874194304256001224371840x7f2c61e2c5000x7f2c5ee2478000017539804948494175398049170361753980527751717539805279075
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001012196872196874194304256001224381440x7f2c61e2c3800x7f2c5ee247c000017539805309964175398052775171753980563943717539805640846
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001042196872196874194304256001224391040x7f2c61e2c2000x7f2c5ee2480000017539805671575175398056394371753980591319717539805914669
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107219687219687419430425600824403200x7f2c61e2c0800x7f2c5ee2484000017539805945418175398059131971753980620599717539806207741
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001102196872196874194304256001224412800x7f2c5f6cdf000x7f2c5ee2488000017539806246370175398062059971753980648807717539806489614
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001132196872196874194304256001224422400x7f2c5f6cdd800x7f2c5ee248c000017539806519623175398064880771753980684855817539806849925
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001162196872196874194304256001224432000x7f2c5f6cdc000x7f2c5ee2490000017539806880304175398068485581753980721191817539807213456
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119219687219687419430425600824441600x7f2c5f6cda800x7f2c5ee2494000017539807243355175398072119181753980748167817539807483179
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001222196872196874194304256001224453760x7f2c5f6cd9000x7f2c5ee2498000017539807512868175398074816781753980775063817539807752242
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001252196872196874194304256001224463360x7f2c5f6cd7800x7f2c5ee249c000017539807789281175398077506381753980802167917539808023145
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001282196872196874194304256001224475520x7f2c5f6cd6000x7f2c5ee24a0000017539808053954175398080216791753980837831917539808379936
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001312196872196874194304256001224485120x7f2c61e2c4800x7f2c5ee24a4000017539808411565175398083783191753980873783917539808739297
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134219687219687419430425600824494720x7f2c61e2c3000x7f2c5ee24a8000017539808770176175398087378391753980901111917539809012640
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001372196872196874194304256001224506880x7f2c61e2c1800x7f2c5ee24ac000017539809043309175398090111191753980928232017539809283773
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001402196872196874194304256001224516480x7f2c61e2c0000x7f2c5ee24b0000017539809321652175398092823201753980956008017539809561496
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001432196872196874194304256001224528640x7f2c5f6cde800x7f2c5ee24b4000017539809592375175398095600801753980992136017539809922946
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001462196872196874194304256001224540800x7f2c5f6cdd000x7f2c5ee24b8000017539809953056175398099213601753981029192017539810293527
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149219687219687419430425600824552960x7f2c5f6cdb800x7f2c5ee24bc000017539810324246175398102919201753981056776117539810569300
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001522196872196874194304256001224567680x7f2c5f6cda000x7f2c5ee24c0000017539810599619175398105677611753981084232117539810843933
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001552196872196874194304256001224577280x7f2c5f6cd8800x7f2c5ee24c4000017539810881562175398108423211753981111704117539811118536
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001582196872196874194304256001224589440x7f2c5f6cd7000x7f2c5ee24c8000017539811150325175398111170411753981147624117539811477587
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001612196872196874194304256001224601600x7f2c61e2c5800x7f2c5ee24cc000017539811508086175398114762411753981183576217539811837147
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164219687219687419430425600824613760x7f2c61e2c4000x7f2c5ee24d0000017539811867147175398118357621753981211160217539812112960
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001672196872196874194304256001224628480x7f2c61e2c2800x7f2c5ee24d4000017539812144159175398121116021753981239144217539812392963
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001702196872196874194304256001224638080x7f2c61e2c1000x7f2c5ee24d8000017539812430762175398123914421753981266456217539812666176
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001732196872196874194304256001224650240x7f2c5f6cdf800x7f2c5ee24dc000017539812697145175398126645621753981303128217539813032827
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001762196872196874194304256001224662400x7f2c5f6cde000x7f2c5ee24e0000017539813062576175398130312821753981339048317539813392077
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179219687219687419430425600824674560x7f2c5f6cdc800x7f2c5ee24e4000017539813421997175398133904831753981366712317539813668750
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001822196872196874194304256001224689280x7f2c5f6cdb000x7f2c5ee24e8000017539813699340175398136671231753981394920317539813950743
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001852196872196874194304256001224701440x7f2c5f6cd9800x7f2c5ee24ec000017539813988642175398139492031753981423704317539814238936
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001882196872196874194304256001224716160x7f2c5f6cd8000x7f2c5ee24f0000017539814269435175398142370431753981459784417539814599156
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001912196872196874194304256001224728320x7f2c5f6cd6800x7f2c5ee24f4000017539814629826175398145978441753981495496417539814956457
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194219687219687419430425600824740480x7f2c61e2c5000x7f2c5ee24f8000017539814986147175398149549641753981523064417539815232180
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001972196872196874194304256001224757760x7f2c61e2c3800x7f2c5ee24fc000017539815262690175398152306441753981551560417539815517033
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002002196872196874194304256001224769920x7f2c61e2c2000x7f2c5ee2500000017539815554802175398155156041753981578760517539815789256
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002032196872196874194304256001224784640x7f2c61e2c0800x7f2c5ee2504000017539815818905175398157876051753981615208517539816153627
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002062196872196874194304256001224799360x7f2c5f6cdf000x7f2c5ee2508000017539816184476175398161520851753981650920517539816510588
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209219687219687419430425600824814080x7f2c5f6cdd800x7f2c5ee250c000017539816540627175398165092051753981678072517539816782331
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002122196872196874194304256001224831360x7f2c5f6cdc000x7f2c5ee2510000017539816812290175398167807251753981706872617539817070173
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002152196872196874194304256001224843520x7f2c5f6cda800x7f2c5ee2514000017539817118022175398170687261753981734008617539817341627
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002182196872196874194304256001224858240x7f2c5f6cd9000x7f2c5ee2518000017539817371136175398173400861753981770040617539817701907
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002212196872196874194304256001224872960x7f2c5f6cd7800x7f2c5ee251c000017539817732147175398177004061753981805960617539818061138
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002242196872196874194304256001224887680x7f2c5f6cd6000x7f2c5ee2520000017539818092447175398180596061753981834968717539818351271
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002272196872196874194304256001224907520x7f2c61e2c4800x7f2c5ee2524000017539818381770175398183496871753981864776717539818649353
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002302196872196874194304256001224919680x7f2c61e2c3000x7f2c5ee2528000017539818687192175398186477671753981892456717539818926146
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002332196872196874194304256001224934400x7f2c61e2c1800x7f2c5ee252c000017539818955995175398189245671753981928248717539819284147
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002362196872196874194304256001224949120x7f2c61e2c0000x7f2c5ee2530000017539819315276175398192824871753981963976817539819641258
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002392196872196874194304256001224963840x7f2c5f6cde800x7f2c5ee2534000017539819671377175398196397681753981991320817539819914681
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002422196872196874194304256001224983680x7f2c5f6cdd000x7f2c5ee2538000017539819944760175398199132081753982021640817539820217933
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002452196872196874194304256001224995840x7f2c5f6cdb800x7f2c5ee253c000017539820255462175398202164081753982048936817539820490916
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024821968721968741943042560012241013120x7f2c5f6cda000x7f2c5ee2540000017539820522195175398204893681753982084744817539820848837
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025121968721968741943042560012241027840x7f2c5f6cd8800x7f2c5ee2544000017539820879466175398208474481753982120792917539821209507
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025421968721968741943042560012241042560x7f2c5f6cd7000x7f2c5ee2548000017539821239357175398212079291753982148216917539821483580
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025721968721968741943042560012241062400x7f2c61e2c5800x7f2c5ee254c000017539821514140175398214821691753982180136917539821802832
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026021968721968741943042560012241077120x7f2c61e2c4000x7f2c5ee2550000017539821840291175398218013691753982207896917539822081925
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026321968721968741943042560016241094400x7f2c61e2c2800x7f2c5ee2554000017539822111534175398220789691753982244201017539822443456
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026621968721968741943042560016241111680x7f2c61e2c1000x7f2c5ee2558000017539822473595175398224420101753982280137017539822802857
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002692196872196874194304256008241128960x7f2c5f6cdf800x7f2c5ee255c000017539822833286175398228013701753982307385017539823075220
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027221968721968741943042560012241151360x7f2c5f6cde000x7f2c5ee2560000017539823105449175398230738501753982339241017539823393691
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027521968721968741943042560012241166080x7f2c5f6cdc800x7f2c5ee2564000017539823431270175398233924101753982367385117539823675374
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027821968721968741943042560016241183360x7f2c5f6cdb000x7f2c5ee2568000017539823705234175398236738511753982403033117539824031915
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028121968721968741943042560016241200640x7f2c5f6cd9800x7f2c5ee256c000017539824062164175398240303311753982438777117539824389096
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028421968721968741943042560012241217920x7f2c5f6cd8000x7f2c5ee2570000017539824419505175398243877711753982466217117539824663679
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028721968721968741943042560012241240320x7f2c5f6cd6800x7f2c5ee2574000017539824693628175398246621711753982499177217539824993321
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029021968721968741943042560012241255040x7f2c61e2c5000x7f2c5ee2578000017539825030660175398249917721753982527209217539825273603
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029321968721968741943042560012241274880x7f2c61e2c3800x7f2c5ee257c000017539825305093175398252720921753982563577217539825637474
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029621968721968741943042560012241292160x7f2c61e2c2000x7f2c5ee2580000017539825668583175398256357721753982599529217539825996765
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029921968721968741943042560012241309440x7f2c61e2c0800x7f2c5ee2584000017539826026784175398259952921753982628761317539826289158
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030221968721968741943042560012241334400x7f2c5f6cdf000x7f2c5ee2588000017539826320997175398262876131753982662185317539826623439
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030521968721968741943042560012241349120x7f2c5f6cdd800x7f2c5ee258c000017539826661948175398266218531753982689289317539826894422
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030821968721968741943042560012241368960x7f2c5f6cdc000x7f2c5ee2590000017539826924541175398268928931753982724921317539827250863
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031121968721968741943042560012241388800x7f2c5f6cda800x7f2c5ee2594000017539827280492175398272492131753982760697417539827608534
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031421968721968741943042560012241408640x7f2c5f6cd9000x7f2c5ee2598000017539827638253175398276069741753982789065417539827892176
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031721968721968741943042560012241436160x7f2c5f6cd7800x7f2c5ee259c000017539827921856175398278906541753982824201417539828243757
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032021968721968741943042560012241453440x7f2c5f6cd6000x7f2c5ee25a0000017539828281276175398282420141753982852025417539828521780
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032321968721968741943042560012241475840x7f2c61e2c4800x7f2c5ee25a4000017539828552409175398285202541753982888089517539828882521
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032621968721968741943042560012241495680x7f2c61e2c3000x7f2c5ee25a8000017539828913090175398288808951753982923897517539829240492
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032921968721968741943042560012241515520x7f2c61e2c1800x7f2c5ee25ac000017539829271421175398292389751753982952921517539829530714
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033221968721968741943042560012241543040x7f2c61e2c0000x7f2c5ee25b0000017539829560914175398295292151753982989049517539829891995
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033521968721968741943042560012241562880x7f2c5f6cde800x7f2c5ee25b4000017539829929474175398298904951753983017065617539830172478
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033821968721968741943042560012241587840x7f2c5f6cdd000x7f2c5ee25b8000017539830204627175398301706561753983053321617539830534759
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034121968721968741943042560012241610240x7f2c5f6cdb800x7f2c5ee25bc000017539830565108175398305332161753983089337617539830894899
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034421968721968741943042560012241632640x7f2c5f6cda000x7f2c5ee25c0000017539830925199175398308933761753983120041617539831201901
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034721968721968741943042560012241665280x7f2c5f6cd8800x7f2c5ee25c4000017539831232221175398312004161753983158585717539831631310
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035021968721968741943042560012241685120x7f2c5f6cd7000x7f2c5ee25c8000017539831649590175398315858571753983191033717539831911823
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035321968721968741943042560012241712640x7f2c61e2c5800x7f2c5ee25cc000017539831942482175398319103371753983226985717539832271544
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035621968721968741943042560012241737600x7f2c61e2c4000x7f2c5ee25d0000017539832302823175398322698571753983263129817539832632725
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035921968721968741943042560012241762560x7f2c61e2c2800x7f2c5ee25d4000017539832663264175398326312981753983294409817539832945657
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036221968721968741943042560012241797760x7f2c61e2c1000x7f2c5ee25d8000017539832976446175398329440981753983335337817539833371956
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036521968721968741943042560012241822720x7f2c5f6cdf800x7f2c5ee25dc000017539833393325175398333533781753983366489817539833666418
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036821968721968741943042560012241855360x7f2c5f6cde000x7f2c5ee25e0000017539833696467175398336648981753983403529917539834038079
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037121968721968741943042560012241885440x7f2c5f6cdc800x7f2c5ee25e4000017539834067308175398340352991753983441913917539834466168
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037421968721968741943042560012241915520x7f2c5f6cdb000x7f2c5ee25e8000017539834476297175398344191391753983480089917539834802429
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037721968721968741943042560012241958400x7f2c5f6cd9800x7f2c5ee25ec000017539834832218175398348008991753983526266017539835307296
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038021968721968741943042560012241985920x7f2c5f6cd8000x7f2c5ee25f0000017539835325006175398352626601753983561994017539835621558
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038321968721968741943042560012242023680x7f2c5f6cd6800x7f2c5ee25f4000017539835651767175398356199401753983600986017539836054307
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038621968721968741943042560012242058880x7f2c61e2c5000x7f2c5ee25f8000017539836066417175398360098601753983642554017539836466637
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038921968721968741943042560012242094080x7f2c61e2c3800x7f2c5ee25fc000017539836476946175398364255401753983681754117539836819048
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039221968721968741943042560012242144640x7f2c61e2c2000x7f2c5ee2600000017539836849357175398368175411753983732762117539837370864
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039521968721968741943042560012242177280x7f2c61e2c0800x7f2c5ee2604000017539837388773175398373276211753983770394117539837705475
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039821968721968741943042560012242220160x7f2c5f6cdf000x7f2c5ee2608000017539837736364175398377039411753983811642217539838142234
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040121968721968741943042560012242260480x7f2c5f6cdd800x7f2c5ee260c000017539838152634175398381164221753983854778217539838564913
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040421968721968741943042560012242300800x7f2c5f6cdc000x7f2c5ee2610000017539838579383175398385477821753983894714217539838964333
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040721968721968741943042560012242359040x7f2c5f6cda800x7f2c5ee2614000017539838978622175398389471421753983951674317539839533588
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041021968721968741943042560012242394240x7f2c5f6cd9000x7f2c5ee2618000017539839555818175398395167431753983988986317539839891409
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041321968721968741943042560012242442240x7f2c5f6cd7800x7f2c5ee261c000017539839921348175398398898631753984031914317539840337727
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041621968721968741943042560012242487680x7f2c5f6cd6000x7f2c5ee2620000017539840350707175398403191431753984075050417539840770356
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041921968721968741943042560012242533120x7f2c61e2c4800x7f2c5ee2624000017539840781976175398407505041753984117466417539841191986
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004222196872196874194304256008242555520x7f2c61e2c3000x7f2c5ee2628000017539841207655175398411746641753984181018517539841827319
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042521968721968741943042560012242598400x7f2c61e2c1800x7f2c5ee262c000017539841850169175398418101851753984222090517539842241709
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042821968721968741943042560012242656640x7f2c61e2c0000x7f2c5ee2630000017539842253158175398422209051753984270922517539842726616
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043121968721968741943042560012242712320x7f2c5f6cde800x7f2c5ee2634000017539842740586175398427092251753984319658617539843238223
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004342196872196874194304256008242732160x7f2c5f6cdd000x7f2c5ee2638000017539843249303175398431965861753984370202617539843743600
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004372196872196874194304256008242757120x7f2c5f6cdb800x7f2c5ee263c000017539843754160175398437020261753984446506717539844507001
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044021968721968741943042560012242807680x7f2c5f6cda000x7f2c5ee2640000017539844524950175398444650671753984493770717539844979939
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044321968721968741943042560012242876160x7f2c5f6cd8800x7f2c5ee2644000017539844990458175398449377071753984549546717539845537795
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044621968721968741943042560012242942080x7f2c5f6cd7000x7f2c5ee2648000017539845547944175398454954671753984605802817539846096570
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004492196872196874194304256008242969600x7f2c61e2c5800x7f2c5ee264c000017539846107400175398460580281753984662202817539846667036
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004522196872196874194304256008242999680x7f2c61e2c4000x7f2c5ee2650000017539846677845175398466220281753984749002917539847533553
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004552196872196874194304256008243027200x7f2c61e2c2800x7f2c5ee2654000017539847551143175398474900291753984814666917539848188157
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045821968721968741943042560012243054720x7f2c61e2c1000x7f2c5ee2658000017539848198386175398481466691753984881755017539848859329
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046121968721968741943042560012243082240x7f2c5f6cdf800x7f2c5ee265c000017539848869599175398488175501753984949163117539849532882
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004642196872196874194304256008243109760x7f2c5f6cde000x7f2c5ee2660000017539849543602175398494916311753985015051117539850194355
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004672196872196874194304256008243132160x7f2c5f6cdc800x7f2c5ee2664000017539850205595175398501505111753985123291217539851276447
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004702196872196874194304256008243159680x7f2c5f6cdb000x7f2c5ee2668000017539851294707175398512326601753985230130017539852354110
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047321968721968741943042560012243187200x7f2c5f6cd9800x7f2c5ee266c000017539852363730175398523013001753985340130017539853466352
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047621968721968741943042560012243214720x7f2c5f6cd8000x7f2c5ee2670000017539853476361175398534013001753985453122017539854602223
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004792196872196874194304256008243242240x7f2c5f6cd6800x7f2c5ee2674000017539854613582175398545312201753985564658017539855713034
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004822196872196874194304256008243264640x7f2c61e2c5000x7f2c5ee2678000017539855723444175398556465801753985759186117539857660884
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004852196872196874194304256008243292160x7f2c61e2c3800x7f2c5ee267c000017539857679314175398575918611753985951538117539859586145
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048821968721968741943042560012243319680x7f2c61e2c2000x7f2c5ee2680000017539859597864175398595153811753986150674217539861579113
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049121968721968741943042560012243347200x7f2c61e2c0800x7f2c5ee2684000017539861589563175398615067421753986347906317539863549623
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004942196872196874194304256008243374720x7f2c5f6cdf000x7f2c5ee2688000017539863560583175398634790631753986541298317539865480074
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049721968721968741943042560082400x7f2c5f6cdd800x7f2c5ee268c000017539865490633175398654129831753986902082417539869095251