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

43 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_SMEMSQ_INST_LEVEL_SMEMSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000936496936501335544322560083264640x00x7f17e84041804194304312266639890417612076630480743351120766307183905151207663071871435412076630718822006
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00293649693650132768256002424124800x00x7f17e843510051221524275425612076630733442442120766307337498981207663073375645812076630733761836
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0049364969365014194304256002424129280x7f18f40309000x7f17e8435140655361468061877572012076630733826656120766307340455771207663073417901712076630734183330
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0069364969365014194304256003624136320x7f18f40308000x7f17e8435180655361668002136355212076630734250836120766307344244561207663073467645512076630734744404
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0089364969365014194304256002824140800x7f18f40307000x7f17e84351c0655361453121868756812076630734769059120766307349562941207663073520989312076630735278627
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00109364969365014194304256002424145280x7f18f40306000x7f17e8435200655361509661940276012076630735302752120766307354882921207663073562109212076630735624911
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00129364969365014194304256002424149760x7f18f40305000x7f17e8435240655361432901843244812076630735674393120766307358527711207663073598653012076630735990331
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00149364969365014194304256002424154240x7f18f40304000x7f17e84352801310722273902916081612076630736069599120766307362399691207663073637244912076630736376349
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00169364969365014194304256002824161280x7f18f40303000x7f17e84352c01310721890482423631212076630736425691120766307365948481207663073685932712076630736901155
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00189364969365014194304256002824168320x7f18f4030a000x7f17e8435300655361482681904093612076630736924379120766307371294061207663073738252512076630737423557
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00209364969365014194304256002424175360x7f18f40309000x7f17e84353401310722254942883525612076630737447872120766307376362841207663073776924412076630737772967
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00229364969365014194304256002424182400x7f18f40308000x7f17e84353801310722249702882681612076630737822008120766307379870031207663073812220312076630738126284
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00249364969365014194304256002424189440x7f18f40307000x7f17e84353c01310722269202912480012076630738189021120766307383583621207663073849196112076630738495431
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00269364969365014194304256002824199040x7f18f40306000x7f17e84354001310721888842413382412076630738544602120766307387078001207663073896700012076630739033422
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00289364969365014194304256002824206080x7f18f40305000x7f17e8435440655361453541867360012076630739060312120766307392455591207663073950299812076630739569298
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00309364969365014194304256002424213120x7f18f40304000x7f17e84354801310722252062887275212076630739595898120766307397721171207663073990491612076630739908349
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00329364969365014194304256002424220160x7f18f40303000x7f17e84354c01310722195602825888812076630739957340120766307401322751207663074026059512076630740264552
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00349364969365014194304256002424227200x7f18f4030a000x7f17e84355001310722640563382516812076630740326287120766307404913141207663074066747312076630740671338
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00369364969365014194304256002824236800x7f18f40309000x7f17e84355401310721802482301280012076630740719638120766307408893931207663074114475212076630741211082
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00389364969365014194304256002824243840x7f18f40308000x7f17e8435580655361521081935800012076630741236900120766307414223511207663074168027012076630741747320
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00409364969365014194304256002424250880x7f18f40307000x7f17e84355c01310722405723074516012076630741770152120766307419524291207663074208538812076630742089256
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00429364969365014194304256002424257920x7f18f40306000x7f17e84356001310722279262910226412076630742137025120766307423151471207663074244538712076630742449195
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00449364969365014194304256002424264960x7f18f40305000x7f17e84356401310722380443058615212076630742511051120766307426751461207663074280890612076630742812662
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00469364969365014194304256002824277120x7f18f40304000x7f17e84356801310722140862745455212076630742860410120766307430391451207663074329962412076630743365810
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00489364969365014194304256002824284160x7f18f40303000x7f17e84356c0655361518921929660012076630743392941120766307435727431207663074382666212076630743893562
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00509364969365014194304256002424291200x7f18f4030a000x7f17e84357001310722270842906302412076630743916916120766307440967411207663074422970012076630744233504
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00529364969365014194304256002424300800x7f18f40309000x7f17e84357401310722291022937985612076630744284449120766307444487401207663074457881912076630744582634
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00549364969365014194304256002424307840x7f18f40308000x7f17e84357801310722236602858979212076630744643166120766307448042581207663074493385812076630744937734
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00569364969365014194304256002824320000x7f18f40307000x7f17e84357c01310721887562413558412076630744985393120766307451727371207663074543513612076630745501092
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00589364969365014194304256002824329600x7f18f40306000x7f17e8435800655361490721905228812076630745525418120766307457039351207663074596073412076630746027231
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00609364969365014194304256002424339200x7f18f40305000x7f17e84358401310722212922829420812076630746054892120766307462324131207663074636873312076630746372603
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00629364969365014194304256002424348800x7f18f40304000x7f17e84358801310722247102866473612076630746420783120766307465831321207663074671833112076630746721993
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00649364969365014194304256002424358400x7f18f40303000x7f17e84358c01310722219942840058412076630746783147120766307469461711207663074707673012076630747081081
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00669364969365014194304256002824373120x7f18f4030a000x7f17e84359001310722175002782110412076630747129852120766307473032891207663074756392812076630747631135
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00689364969365014194304256002824382720x7f18f40309000x7f17e8435940655361458021853303212076630747657163120766307478340071207663074808712712076630748154638
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00709364969365014194304256002424392320x7f18f40308000x7f17e84359801310722274662911269612076630748178493120766307483642461207663074850120512076630748504940
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00729364969365014194304256002424401920x7f18f40307000x7f17e84359c01310722287662916378412076630748553921120766307487176841207663074885432412076630748858297
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00749364969365014194304256002424411520x7f18f40306000x7f17e8435a001310722179962792689612076630748919220120766307490866431207663074921896212076630749222755
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00769364969365014194304256002824426240x7f18f40305000x7f17e8435a401310721831002341393612076630749271796120766307494439221207663074970376112076630749770233
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00789364969365014194304256002824435840x7f18f40304000x7f17e8435a80655361526761942981612076630749794378120766307499725601207663075023255912076630750330926
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00809364969365014194304256002424445440x7f18f40303000x7f17e8435ac01310722236802869784812076630750354861120766307505480781207663075068471712076630750688662
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00829364969365014194304256002424457600x7f18f4030a000x7f17e8435b001310722260802915892812076630750736942120766307509066361207663075104375612076630751048231
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00849364969365014194304256002424467200x7f18f40309000x7f17e8435b401310722258302899775212076630751108353120766307512771951207663075141111412076630751415093
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00869364969365014194304256002824484480x7f18f40308000x7f17e8435b801310721807562313533612076630751465056120766307516227941207663075189255312076630751963002
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00889364969365014194304256002824494080x7f18f40307000x7f17e8435bc0655361494401911473612076630751989592120766307521701521207663075242647112076630752493219
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00909364969365014194304256002424503680x7f18f40306000x7f17e8435c001310722622663362372812076630752519848120766307526991101207663075282806912076630752832029
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00929364969365014194304256002424515840x7f18f40305000x7f17e8435c401310722271862906040812076630752881821120766307530520691207663075318838812076630753191978
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00949364969365014194304256002424525440x7f18f40304000x7f17e8435c801310722305422947086412076630753253212120766307534168671207663075355110712076630753554743
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00969364969365014194304256002824542720x7f18f40303000x7f17e8435cc01310721777782287304812076630753602021120766307537731861207663075403750512076630754103965
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00989364969365014194304256002824554880x7f18f4030a000x7f17e8435d00655361731922215451212076630754130945120766307543091841207663075456518312076630754631786
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001009364969365014194304256002424567040x7f18f40309000x7f17e8435d401310722275322925213612076630754654709120766307548317421207663075496566212076630754969194
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001029364969365014194304256002424581760x7f18f40308000x7f17e8435d801310722292342940926412076630755019708120766307551933411207663075533446012076630755338551
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001049364969365014194304256002424593920x7f18f40307000x7f17e8435dc01310722282602918364812076630755399925120766307555614991207663075569941912076630755703179
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001069364969365014194304256002824613760x7f18f40306000x7f17e8435e001310722252542876494412076630755751660120766307559195781207663075617829712076630756245338
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001089364969365014194304256002824625920x7f18f40305000x7f17e8435e40655361492421906306412076630756272358120766307564486961207663075670837512076630756774753
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001109364969365014194304256002424638080x7f18f40304000x7f17e8435e801310722271562901428812076630756799128120766307569798941207663075711381412076630757118462
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001129364969365014194304256002424652800x7f18f40303000x7f17e8435ec01310722277822890747212076630757168094120766307573312531207663075747029312076630757474214
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001149364969365014194304256002424664960x7f18f4030a000x7f17e8435f001310722271022902286412076630757534035120766307576938121207663075782917112076630757832911
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001169364969365014194304256002824684800x7f18f40309000x7f17e8435f401310722270882908934412076630757880630120766307580538101207663075831125012076630758378676
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001189364969365014194304256002824696960x7f18f40308000x7f17e8435f80655361477041886103212076630758405416120766307585794091207663075883332812076630758899234
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001209364969365014194304256002424709120x7f18f40307000x7f17e8435fc01310722251162889450412076630758925974120766307591149271207663075924740612076630759251199
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001229364969365014194304256002424723840x7f18f40306000x7f17e84360001310722263562893896812076630759300401120766307594630851207663075960212512076630759606019
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001249364969365014194304256002424736000x7f18f40305000x7f17e84360401310722254642889199212076630759666862120766307598270841207663075995812412076630759961801
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001269364969365014194304256002824758400x7f18f40304000x7f17e84360801310721760882257359212076630760013808120766307601774831207663076044612212076630760512545
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001289364969365014194304256002824770560x7f18f40303000x7f17e84360c0655361462001863813612076630760536089120766307607200411207663076097604012076630761018497
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001309364969365014194304256002424782720x7f18f4030a000x7f17e84361001310722644403355372812076630761040888120766307612222791207663076135267912076630761356676
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001329364969365014194304256002424800000x7f18f40309000x7f17e84361401310721972142531325612076630761405857120766307615745981207663076172147712076630761725392
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001349364969365014194304256002424812160x7f18f40308000x7f17e84361801310722254822882561612076630761785584120766307619430761207663076207811612076630762082105
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001369364969365014194304256002824834560x7f18f40307000x7f17e84361c01310721804782315152812076630762129794120766307623009951207663076257011412076630762591432
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001389364969365014194304256002824849280x7f18f40306000x7f17e8436200655361800782306624012076630762634322120766307627928331207663076309027212076630763113874
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001409364969365014194304256002424864000x7f18f40305000x7f17e84362401310722331842957432012076630763158197120766307633198711207663076345411112076630763458125
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001429364969365014194304256002424881280x7f18f40304000x7f17e84362801310721991902560328812076630763506124120766307636731501207663076382515012076630763829095
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001449364969365014194304256002424896000x7f18f40303000x7f17e84362c01310722306562961590412076630763911097120766307640718691207663076420610812076630764210123
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001469364969365014194304256002824920960x7f18f4030a000x7f17e84363001310721836042342632812076630764258634120766307644269071207663076469778612076630764722096
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001489364969365014194304256002824935680x7f18f40309000x7f17e8436340655361441561843417612076630764763383120766307649253061207663076518034512076630765204984
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001509364969365014194304256002424950400x7f18f40308000x7f17e84363801310722185122790995212076630765247433120766307654083441207663076554226312076630765545828
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001529364969365014194304256002424967680x7f18f40307000x7f17e84363c01310722307222947935212076630765596031120766307657656231207663076592354212076630765927498
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001549364969365014194304256002424982400x7f18f40306000x7f17e84364001310722231862852260812076630765987219120766307661585811207663076629234112076630766296665
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015693649693650141943042560028241007360x7f18f40305000x7f17e84364401310721826482333948012076630766345836120766307665166601207663076678161912076630766829576
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015893649693650141943042560028241022080x7f18f40304000x7f17e8436480655361869022386955212076630766854182120766307670355381207663076728817712076630767338382
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016093649693650141943042560024241036800x7f18f40303000x7f17e84364c01310722285002914781612076630767365653120766307675408161207663076767569612076630767679337
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016293649693650141943042560024241056640x7f18f4030a000x7f17e84365001310722181062797276012076630767728779120766307678956951207663076806193412076630768065795
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016493649693650141943042560024241071360x7f18f40309000x7f17e84365401310722259082872932012076630768128412120766307682908931207663076842129312076630768425354
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016693649693650141943042560028241098880x7f18f40308000x7f17e84365801310721800442304318412076630768473734120766307686406521207663076890705112076630768931195
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016893649693650141943042560028241113600x7f18f40307000x7f17e84365c0655361511321941986412076630768976980120766307691614501207663076942112912076630769468905
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017093649693650141943042560024241128320x7f18f40306000x7f17e84366001310722652903384231212076630769492760120766307696705681207663076980784812076630769811863
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017293649693650141943042560024241148160x7f18f40305000x7f17e84366401310722231242875220012076630769861646120766307700312071207663077020448612076630770208471
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017493649693650141943042560024241162880x7f18f40304000x7f17e84366801310722257562900396012076630770269695120766307704307261207663077056208512076630770566086
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017693649693650141943042560028241190400x7f18f40303000x7f17e84366c01310721789902285218412076630770615679120766307707776041207663077104272312076630771091424
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017893649693650141943042560028241207680x7f18f4030a000x7f17e8436700655361448141852488012076630771118253120766307712947231207663077155408212076630771600681
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018093649693650141943042560024241224960x7f18f40309000x7f17e84367401310722277442919279212076630771625737120766307718057611207663077194144012076630771945592
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018293649693650141943042560024241247360x7f18f40308000x7f17e84367801310722270822899427212076630771994333120766307721684791207663077235071912076630772354974
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018493649693650141943042560024241264640x7f18f40307000x7f17e84367c01310722263902905512012076630772416588120766307725795181207663077272031712076630772723990
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018693649693650141943042560020241279360x7f18f40306000x7f17e84368001310722239162859380812076630772770507120766307729361571207663077320335612076630773250399
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018893649693650141943042560028241296640x7f18f40305000x7f17e8436840655361514721940072012076630773273172120766307734513551207663077371007412076630773756300
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019093649693650141943042560024241313920x7f18f40304000x7f17e84368801310722574563273817612076630773781838120766307739553531207663077409759212076630774101833
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019293649693650141943042560024241336320x7f18f40303000x7f17e84368c01310722355042991517612076630774150303120766307743222321207663077451327112076630774561378
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019493649693650141943042560024241353600x7f18f4030a000x7f17e84369001310722567443277063212076630774598196120766307747588701207663077489934912076630774903304
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019693649693650141943042560020241368320x7f18f40309000x7f17e84369401310722218142852486412076630774952726120766307751236691207663077540654812076630775455772
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019893649693650141943042560028241385600x7f18f40308000x7f17e8436980655361531981962116812076630775479025120766307756599871207663077591790612076630775964748
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020093649693650141943042560024241402880x7f18f40307000x7f17e84369c01310722465343150327212076630775991037120766307761793451207663077631358412076630776317915
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020293649693650141943042560024241427840x7f18f40306000x7f17e8436a001310722194182823272012076630776366896120766307765382241207663077674958312076630776771990
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020493649693650141943042560024241447680x7f18f40305000x7f17e8436a401310722206662820692812076630776825820120766307769879821207663077712686112076630777130848
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020693649693650141943042560020241457280x7f18f40304000x7f17e8436a801310722209142836416012076630777180931120766307773462211207663077765341912076630777700587
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020893649693650141943042560028241477120x7f18f40303000x7f17e8436ac0655361445441839847212076630777724111120766307779007791207663077816093812076630778209855
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021093649693650141943042560024241496960x7f18f4030a000x7f17e8436b001310722158422768613612076630778236775120766307784126171207663077854829612076630778552051
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021293649693650141943042560024241521920x7f18f40309000x7f17e8436b401310722256462910232012076630778600181120766307787663751207663077899421512076630779043365
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021493649693650141943042560024241541760x7f18f40308000x7f17e8436b801310722287222908582412076630779077990120766307792471741207663077938317312076630779387625
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021693649693650141943042560020241556480x7f18f40307000x7f17e8436bc01310722256662894410412076630779437468120766307796102121207663077993933112076630779987521
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021893649693650141943042560028241576320x7f18f40306000x7f17e8436c00655361431901828843212076630780015714120766307801950101207663078045788912076630780506937
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022093649693650141943042560024241596160x7f18f40305000x7f17e8436c401310722283082926373612076630780533056120766307807129281207663078084860812076630780852781
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022293649693650141943042560024241623680x7f18f40304000x7f17e8436c801310722298662943367212076630780901071120766307810735671207663078131836612076630781368059
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022493649693650141943042560024241646080x7f18f40303000x7f17e8436cc01310722232062880425612076630781410769120766307815755631207663078171252312076630781719633
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022693649693650141943042560020241663360x7f18f4030a000x7f17e8436d001310722288402925577612076630781762894120766307819315611207663078230804012076630782355576
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022893649693650141943042560028241685760x7f18f40309000x7f17e8436d40655361492381898373612076630782381955120766307825598791207663078282579912076630782872948
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023093649693650141943042560024241708160x7f18f40308000x7f17e8436d801310722305362950602412076630782898456120766307830774781207663078322003712076630783223300
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023293649693650141943042560024241740800x7f18f40307000x7f17e8436dc01310722294522921996012076630783272983120766307834469171207663078375619612076630783801987
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023493649693650141943042560024241765760x7f18f40306000x7f17e8436e001310722305222954532812076630783837322120766307840017951207663078414195512076630784145506
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023693649693650141943042560020241777920x7f18f40305000x7f17e8436e401310722091182691603212076630784193916120766307843670741207663078479251312076630784840148
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023893649693650141943042560028241802880x7f18f40304000x7f17e8436e80655361541621978117612076630784863591120766307850525121207663078531619212076630785364583
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024093649693650141943042560024241827840x7f18f40303000x7f17e8436ec01310722252882862639212076630785392425120766307855681911207663078570707112076630785710817
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024293649693650141943042560024241863040x7f18f4030a000x7f17e8436f001310722253122882412812076630785759147120766307859251501207663078624050912076630786288993
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024493649693650141943042560024241893120x7f18f40309000x7f17e8436f401310722276162890884012076630786330530120766307864917091207663078664418812076630786647249
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024693649693650141943042560020241907840x7f18f40308000x7f17e8436f801310722256822877774412076630786695389120766307868632281207663078738018612076630787429053
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024893649693650141943042560028241937920x7f18f40307000x7f17e8436fc0655361523681958921612076630787462896120766307876326651207663078793170512076630787978586
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025093649693650141943042560024241968000x7f18f40306000x7f17e84370001310722235202854580812076630788015083120766307881837041207663078833874412076630788342282
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025293649693650141943042560024242010880x7f18f40305000x7f17e84370401310722258322900195212076630788397264120766307885584231207663078894434212076630788965792
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025493649693650141943042560024242046080x7f18f40304000x7f17e84370801310722249642878414412076630789036884120766307892045011207663078938034112076630789383810
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025693649693650141943042560020242060800x7f18f40303000x7f17e84370c01310722289802911108012076630789433773120766307896061001207663079021729812076630790265530
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025893649693650141943042560028242096000x7f18f4030a000x7f17e8437100655361457501871554412076630790299653120766307904734581207663079080049712076630790847332
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026093649693650141943042560024242131200x7f18f40309000x7f17e84371401310722440683134213612076630790884271120766307910566561207663079123489612076630791238570
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026293649693650141943042560024242181760x7f18f40308000x7f17e84371801310722463123121164012076630791291749120766307914555351207663079191201412076630791958108
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026493649693650141943042560024242222080x7f18f40307000x7f17e84371c01310722283502918155212076630791998343120766307921672131207663079236705312076630792414186
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026693649693650141943042560020242239360x7f18f40306000x7f17e84372001310722215662888223212076630792444613120766307926152121207663079331953012076630793367139
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026893649693650141943042560028242279680x7f18f40305000x7f17e8437240655361475561886144012076630793390973120766307935776091207663079397728812076630794025494
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027093649693650141943042560024242320000x7f18f40304000x7f17e84372801310722260962899941612076630794057984120766307942376081207663079444000712076630794487543
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027293649693650141943042560024242378240x7f18f40303000x7f17e84372c01310722433703087500012076630794513702120766307946884861207663079521536512076630795261944
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027493649693650141943042560024242423680x7f18f4030a000x7f17e84373001310722327222953739212076630795298512120766307954608041207663079568480412076630795732198
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027693649693650141943042560020242435840x7f18f40309000x7f17e84373401310722261822906834412076630795757796120766307959310431207663079673040112076630796781650
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027893649693650141943042560028242481280x7f18f40308000x7f17e8437380655361523441948852012076630796807899120766307969859201207663079740719912076630797455855
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028093649693650141943042560024242526720x7f18f40307000x7f17e84373c01310722281822919210412076630797479599120766307976596781207663079788815812076630797935176
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028293649693650141943042560024242592640x7f18f40306000x7f17e84374001310722259262897102412076630797961756120766307981404771207663079873775512076630798785869
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028493649693650141943042560024242648320x7f18f40305000x7f17e84374401310722249622878478412076630798826785120766307989889551207663079925855412076630799308010
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028693649693650141943042560020242663040x7f18f40304000x7f17e84374801310722307242930373612076630799331574120766307995167931207663080050207112076630800568915
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028893649693650141943042560028242718720x7f18f40303000x7f17e84374c0655361475821885427212076630800600514120766308007790301207663080131198812076630801378822
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029093649693650141943042560024242774400x7f18f4030a000x7f17e84375001310722264882918960812076630801406563120766308015875081207663080185854712076630801924547
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029293649693650141943042560012242799360x7f18f40309000x7f17e84375401310722180742763420812076630801950315120766308021355061207663080287454412076630802942130
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029493649693650141943042560024242865280x7f18f40308000x7f17e84375801310722191062813818412076630802981232120766308031577431207663080347406312076630803541054
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029693649693650141943042560020242880000x7f18f40307000x7f17e84375c01310722245382885430412076630803564638120766308037459021207663080491757912076630804987584
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029893649693650141943042560032242945920x7f18f40306000x7f17e8437600655361475241877442412076630805023241120766308052057381207663080581533612076630805883811
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030093649693650141943042560024243011840x7f18f40305000x7f17e84376401310722260122884227212076630805911944120766308060972551207663080641629512076630806484218
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030293649693650141943042560012243049600x7f18f40304000x7f17e84376801310722256102906924812076630806512471120766308066865341207663080756525112076630807631983
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030493649693650141943042560024243136000x7f18f40303000x7f17e84376c01310722545583285060012076630807668531120766308078346911207663080824685012076630808315845
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030693649693650141943042560020243148160x7f18f4030a000x7f17e84377001310722266462918347212076630808347384120766308085287691207663081007644512076630810144407
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030893649693650141943042560020243175680x7f18f40309000x7f17e8437740655361462641873903212076630810174753120766308103548441207663081114988212076630811216802
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031093649693650141943042560012243203200x7f18f40308000x7f17e84377801310722622063352260012076630811243782120766308114274811207663081184252012076630811908639
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031293649693650141943042560012243240960x7f18f40307000x7f17e84377c01310722259322877513612076630811933695120766308121218791207663081328011612076630813348357
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031493649693650141943042560012243288960x7f18f40306000x7f17e84378001310722120862730544812076630813389683120766308135492351207663081433451312076630814401756
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031693649693650141943042560020243301120x7f18f40305000x7f17e84378401310722781983569860012076630814433465120766308146106721207663081766122412076630817728875
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031893649693650141943042560020243328640x7f18f40304000x7f17e8437880655361477281899383212076630817759983120766308179297031207663081947017912076630819538611
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032093649693650141943042560012243356160x7f18f40303000x7f17e84378c01310722306242945231212076630819562395120766308197517781207663082054137612076630820609142
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032293649693650141943042560012243393920x7f18f4030a000x7f17e84379001310722251762923160812076630820639719120766308208258561207663082310648912076630823175005
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032493649693650141943042560012243441920x7f18f40309000x7f17e84379401310722260422880154412076630823218656120766308233834491207663082491816412076630824984611
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032693649693650141943042560020243454080x7f18f40308000x7f17e84379801310722294402939909612076630825019356120766308252034441207663083125702712076630831327209
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032893649693650141943042560020243481600x7f18f40307000x7f17e84379c0655361532381969610412076630831358758120766308315397471207663083457925812076630834649489
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033093649693650141943042560012243509120x7f18f40306000x7f17e8437a001310722236282840112812076630834684204120766308348506181207663083638997312076630836458544
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332936496936501419430425600122400x7f18f40305000x7f17e8437a401310722257722878838412076630836488380120766308366706131207663084119764012076630841270295