Files
rocm-systems/tests/workloads/kernels/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.kd000890939890944335544322560083264640x00x7f8564a041804194304306539039252736812075750428536136120757506729999081207575067332566612075750673439498
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00289093989094432768256002424124800x00x7f8564a3510051219888255181612075750688487414120757506887992701207575068880535012075750688810875
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0048909398909444194304256002424129280x7f86705c79000x7f8564a35140655361641242096729612075750688875716120757506891671081207575068930534812075750689309763
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0068909398909444194304256003624136320x7f86705c78000x7f8564a35180655361444701854679212075750689380735120757506895888661207575068984438512075750689916651
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0088909398909444194304256002824140800x7f86705c77000x7f8564a351c0655361576182012786412075750689949462120757506901803831207575069043414212075750690505224
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00108909398909444194304256002424145280x7f86705c76000x7f8564a35200655361617782058063212075750690533076120757506907610211207575069090086012075750690905578
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00128909398909444194304256002424149760x7f86705c75000x7f8564a35240655361590202038385612075750690954499120757506911829391207575069131877812075750691323084
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00148909398909444194304256002424154240x7f86705c74000x7f8564a352801310722383823051069612075750691398875120757506915845371207575069171541612075750691719882
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00168909398909444194304256002824161280x7f86705c73000x7f8564a352c01310721941802475004812075750691768592120757506919958951207575069225237312075750692299228
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00188909398909444194304256002824168320x7f86705c7a000x7f8564a35300655361616002070213612075750692327761120757506925557321207575069281285112075750692857265
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00208909398909444194304256002424175360x7f86705c79000x7f8564a353401310722443683139096012075750692883634120757506931261291207575069325668912075750693260886
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00228909398909444194304256002424182400x7f86705c78000x7f8564a353801310722268262902690412075750693311840120757506935286871207575069366468712075750693669315
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00248909398909444194304256002424189440x7f86705c77000x7f8564a353c01310722393903063897612075750693731440120757506939397251207575069407044512075750694074718
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00268909398909444194304256002824199040x7f86705c76000x7f8564a354001310721779382276153612075750694128428120757506943408431207575069459172212075750694663202
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00288909398909444194304256002824206080x7f86705c75000x7f8564a35440655361595382033276012075750694692877120757506949176411207575069517107912075750695242298
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00308909398909444194304256002424213120x7f86705c74000x7f8564a354801310722189442798564812075750695270771120757506954985981207575069562835712075750695633034
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00328909398909444194304256002424220160x7f86705c73000x7f8564a354c01310722383083055424812075750695681063120757506959025961207575069603635512075750696040531
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00348909398909444194304256002424227200x7f86705c7a000x7f8564a355001310722369163041180812075750696103969120757506963057941207575069643555312075750696440204
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00368909398909444194304256002824236800x7f86705c79000x7f8564a355401310721873362402912012075750696488033120757506967041921207575069696403112075750697018018
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00388909398909444194304256002824243840x7f86705c78000x7f8564a35580655361575402016620812075750697046431120757506972797091207575069753922812075750697583339
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00408909398909444194304256002424250880x7f86705c77000x7f8564a355c01310722279802899968812075750697608265120757506978353861207575069796674612075750697970709
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00428909398909444194304256002424257920x7f86705c76000x7f8564a356001310722642263384677612075750698026623120757506982448241207575069837922412075750698383596
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00448909398909444194304256002424264960x7f86705c75000x7f8564a356401310722499543187789612075750698446703120757506986512221207575069878290212075750698787426
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00468909398909444194304256002824277120x7f86705c74000x7f8564a356801310721921762464500812075750698835866120757506990545811207575069930705912075750699378805
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00488909398909444194304256002824284160x7f86705c73000x7f8564a356c0655361522601956653612075750699406126120757506996321781207575069988417612075750699955988
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00508909398909444194304256002424291200x7f86705c7a000x7f8564a357001310722372463045076812075750699982497120757507002243351207575070036369412075750700368064
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00528909398909444194304256002424300800x7f86705c79000x7f8564a357401310722413283081896812075750700415733120757507006345731207575070076673212075750700771133
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00548909398909444194304256002424307840x7f86705c78000x7f8564a357801310722380643037288812075750700831846120757507010444911207575070117809012075750701182137
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00568909398909444194304256002824320000x7f86705c77000x7f8564a357c01310722004442545583212075750701232621120757507014560091207575070170944812075750701755262
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00588909398909444194304256002824329600x7f86705c76000x7f8564a35800655361631602090204012075750701783224120757507020097661207575070227312512075750702345098
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00608909398909444194304256002424339200x7f86705c75000x7f8564a358401310722295922935245612075750702373200120757507025984031207575070273136312075750702736095
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00628909398909444194304256002424348800x7f86705c74000x7f8564a358801310722322202991891212075750702783844120757507030008011207575070313888112075750703143352
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00648909398909444194304256002424358400x7f86705c73000x7f8564a358c01310722399543063706412075750703204956120757507034129591207575070354511912075750703549827
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00668909398909444194304256002824373120x7f86705c7a000x7f8564a359001310721904722429368812075750703598057120757507038180771207575070406991612075750704140966
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00688909398909444194304256002824382720x7f86705c79000x7f8564a35940655361601362052461612075750704169429120757507043932751207575070465215312075750704698061
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00708909398909444194304256002424392320x7f86705c78000x7f8564a359801310722400663071626412075750704724200120757507049492721207575070508239112075750705087094
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00728909398909444194304256002424401920x7f86705c77000x7f8564a359c01310722450043140207212075750705140794120757507053547101207575070548750912075750705491916
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00748909398909444194304256002424411520x7f86705c76000x7f8564a35a001310722283582935401612075750705550756120757507057625481207575070589518712075750705899955
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00768909398909444194304256002824426240x7f86705c75000x7f8564a35a401310721884382418412012075750705948485120757507061716661207575070642654512075750706498146
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00788909398909444194304256002824435840x7f86705c74000x7f8564a35a80655361535381958482412075750706524586120757507067534231207575070700622212075750707078615
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00808909398909444194304256002424445440x7f86705c73000x7f8564a35ac01310722359643002204812075750707109122120757507073505401207575070748542012075750707489749
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00828909398909444194304256002424457600x7f86705c7a000x7f8564a35b001310722355643027917612075750707538821120757507077578981207575070789389812075750707898309
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00848909398909444194304256002424467200x7f86705c79000x7f8564a35b401310722385943059412012075750707959061120757507081764561207575070830733612075750708311657
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00868909398909444194304256002824484480x7f86705c78000x7f8564a35b801310721874222413028812075750708362060120757507085799741207575070885037312075750708921530
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00888909398909444194304256002824494080x7f86705c77000x7f8564a35bc0655361583302037757612075750708949232120757507091791721207575070943453012075750709480629
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00908909398909444194304256002424503680x7f86705c76000x7f8564a35c001310722246822864926412075750709506307120757507097335691207575070986748812075750709871766
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00928909398909444194304256002424515840x7f86705c75000x7f8564a35c401310722413943097443212075750709922100120757507101506871207575071029116612075750710295554
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00948909398909444194304256002424525440x7f86705c74000x7f8564a35c801310722392623036387212075750710358150120757507105606051207575071069148412075750710696038
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00968909398909444194304256002824542720x7f86705c73000x7f8564a35cc01310722073962653058412075750710744147120757507109607631207575071122668212075750711298267
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00988909398909444194304256002824554880x7f86705c7a000x7f8564a35d00655361728622223214412075750711325398120757507115505201207575071180683912075750711878566
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001008909398909444194304256002424567040x7f86705c79000x7f8564a35d401310722395443074265612075750711904925120757507121397971207575071227131712075750712276044
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001028909398909444194304256002424581760x7f86705c78000x7f8564a35d801310722411343088941612075750712324685120757507125469951207575071269051512075750712694983
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001048909398909444194304256002424593920x7f86705c77000x7f8564a35dc01310722438323101553612075750712755065120757507129601131207575071309467312075750713099134
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001068909398909444194304256002824613760x7f86705c76000x7f8564a35e001310722330223012422412075750713147885120757507133673111207575071363947012075750713710039
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001088909398909444194304256002824625920x7f86705c75000x7f8564a35e40655361690142153336812075750713737460120757507139596281207575071421546712075750714287322
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001108909398909444194304256002424638080x7f86705c74000x7f8564a35e801310722386883053030412075750714316086120757507145473061207575071467610512075750714680603
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001128909398909444194304256002424652800x7f86705c73000x7f8564a35ec01310722364103033361612075750714728182120757507149466641207575071508554312075750715089964
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001148909398909444194304256002424664960x7f86705c7a000x7f8564a35f001310722385783050916812075750715150146120757507153557821207575071549114112075750715495858
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001168909398909444194304256002824684800x7f86705c79000x7f8564a35f401310722479383169330412075750715543327120757507157602601207575071602777812075750716100702
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001188909398909444194304256002824696960x7f86705c78000x7f8564a35f80655361573482021536012075750716129336120757507163560971207575071661513612075750716686972
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001208909398909444194304256002424709120x7f86705c77000x7f8564a35fc01310722403283081272812075750716714193120757507169512941207575071709017312075750717094660
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001228909398909444194304256002424723840x7f86705c76000x7f8564a360001310722336943007533612075750717145113120757507173592921207575071749817112075750717502858
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001248909398909444194304256002424736000x7f86705c75000x7f8564a360401310722350582998653612075750717565214120757507177608901207575071789320912075750717897963
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001268909398909444194304256002824758400x7f86705c74000x7f8564a360801310721912662452045612075750717944439120757507181666481207575071843608712075750718507836
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001288909398909444194304256002824770560x7f86705c73000x7f8564a360c0655361574802017448012075750718533183120757507187716051207575071902856412075750719101479
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001308909398909444194304256002424782720x7f86705c7a000x7f8564a361001310722416343090460812075750719129281120757507193631221207575071949192212075750719496453
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001328909398909444194304256002424800000x7f86705c79000x7f8564a361401310721879462402190412075750719546186120757507197620001207575071990584012075750719910433
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001348909398909444194304256002424812160x7f86705c78000x7f8564a361801310722408703049381612075750719970594120757507201927181207575072032615812075750720330493
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001368909398909444194304256002824834560x7f86705c77000x7f8564a361c01310721978602528831212075750720379544120757507205971961207575072086807512075750720940176
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001388909398909444194304256002824849280x7f86705c76000x7f8564a36200655361628102093719212075750720966886120757507211978331207575072145431212075750721501309
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001408909398909444194304256002424864000x7f86705c75000x7f8564a362401310722361243028857612075750721529482120757507217611911207575072189895012075750721903667
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001428909398909444194304256002424881280x7f86705c74000x7f8564a362801310722233762851241612075750721951826120757507221763891207575072232694812075750722331702
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001448909398909444194304256002424896000x7f86705c73000x7f8564a362c01310722403303083432012075750722415087120757507226011871207575072273606612075750722740582
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001468909398909444194304256002824920960x7f86705c7a000x7f8564a363001310722019162573188812075750722789143120757507230023051207575072327094312075750723343282
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001488909398909444194304256002824935680x7f86705c79000x7f8564a36340655361654782117618412075750723371455120757507235968621207575072384854112075750723920826
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001508909398909444194304256002424950400x7f86705c78000x7f8564a363801310722418103091514412075750723946704120757507241779791207575072431509812075750724319657
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001528909398909444194304256002424967680x7f86705c77000x7f8564a363c01310722458503135621612075750724368678120757507245845371207575072474197612075750724746911
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001548909398909444194304256002424982400x7f86705c76000x7f8564a364001310722377763042541612075750724810168120757507250106151207575072514165412075750725146453
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015689093989094441943042560028241007360x7f86705c75000x7f8564a364401310721891162398405612075750725196947120757507254170131207575072567781212075750725724558
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015889093989094441943042560028241022080x7f86705c74000x7f8564a36480655361585402026845612075750725751298120757507259734901207575072623412912075750726306029
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016089093989094441943042560024241036800x7f86705c73000x7f8564a364c01310722413043072553612075750726333520120757507265616471207575072670228712075750726706763
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016289093989094441943042560024241056640x7f86705c7a000x7f8564a365001310722437303094310412075750726753721120757507269814851207575072714692512075750727151500
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016489093989094441943042560024241071360x7f86705c79000x7f8564a365401310722453403119679212075750727212523120757507274184431207575072755572312075750727560780
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016689093989094441943042560028241098880x7f86705c78000x7f8564a365801310721745682231514412075750727609962120757507278258011207575072809284012075750728164623
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016889093989094441943042560028241113600x7f86705c77000x7f8564a365c0655361626042077345612075750728192194120757507284177981207575072867299712075750728745442
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017089093989094441943042560024241128320x7f86705c76000x7f8564a366001310722438683111920812075750728773604120757507289966761207575072913635512075750729140907
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017289093989094441943042560024241148160x7f86705c75000x7f8564a366401310722482143166891212075750729189968120757507294059541207575072958019312075750729585143
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017489093989094441943042560024241162880x7f86705c74000x7f8564a366801310722403763059139212075750729644403120757507298486711207575072998771112075750729992580
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017689093989094441943042560028241190400x7f86705c73000x7f8564a366c01310721916162451928012075750730042192120757507302595491207575073052034812075750730592425
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017889093989094441943042560028241207680x7f86705c7a000x7f8564a36700655361665822130600812075750730616559120757507308443471207575073110898512075750731181750
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018089093989094441943042560024241224960x7f86705c79000x7f8564a367401310722261942926432012075750731207818120757507314449841207575073158658312075750731591371
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018289093989094441943042560024241247360x7f86705c78000x7f8564a367801310722415283065579212075750731640903120757507318577821207575073204034112075750732044844
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018489093989094441943042560024241264640x7f86705c77000x7f8564a367c01310722351543014203212075750732109604120757507323147401207575073245393912075750732458803
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018689093989094441943042560020241279360x7f86705c76000x7f8564a368001310722429103104207212075750732506171120757507327204981207575073298641612075750733059429
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018889093989094441943042560028241296640x7f86705c75000x7f8564a36840655361561421996772012075750733086249120757507333161751207575073357665312075750733648334
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019089093989094441943042560024241313920x7f86705c74000x7f8564a368801310722399863085244812075750733674012120757507339000121207575073403825112075750734043087
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019289093989094441943042560024241336320x7f86705c73000x7f8564a368c01310722374663055977612075750734093621120757507343129701207575073450384912075750734549118
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019489093989094441943042560024241353600x7f86705c7a000x7f8564a369001310722443103130025612075750734584414120757507347988881207575073493888712075750734943641
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019689093989094441943042560020241368320x7f86705c79000x7f8564a369401310722476383150195212075750734991600120757507352241651207575073550784412075750735579593
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019889093989094441943042560028241385600x7f86705c78000x7f8564a36980655361637522095006412075750735605251120757507358358371207575073609823612075750736173567
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020089093989094441943042560024241402880x7f86705c77000x7f8564a369c01310722370643045288012075750736201629120757507364321531207575073657119312075750736575213
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020289093989094441943042560024241427840x7f86705c76000x7f8564a36a001310722253062922819212075750736624495120757507368567921207575073706735112075750737140764
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020489093989094441943042560024241447680x7f86705c75000x7f8564a36a401310722386903067969612075750737177773120757507373961501207575073753646912075750737540808
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020689093989094441943042560020241457280x7f86705c74000x7f8564a36a801310722445303101878412075750737587895120757507378060681207575073814398712075750738215682
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020889093989094441943042560028241477120x7f86705c73000x7f8564a36ac0655361652062116302412075750738243353120757507384697461207575073873054512075750738775132
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021089093989094441943042560024241496960x7f86705c7a000x7f8564a36b001310722567283272523212075750738799768120757507390364631207575073917358312075750739177660
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021289093989094441943042560024241521920x7f86705c79000x7f8564a36b401310722440723096960812075750739227603120757507394462221207575073967438112075750739719808
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021489093989094441943042560024241541760x7f86705c78000x7f8564a36b801310722370463021724812075750739758289120757507399719801207575074011053912075750740114221
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021689093989094441943042560020241556480x7f86705c77000x7f8564a36bc01310722322443010596812075750740164955120757507403902181207575074071917712075750740789415
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021889093989094441943042560028241576320x7f86705c76000x7f8564a36c00655361662602120248812075750740816576120757507410521361207575074131597512075750741387497
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022089093989094441943042560024241596160x7f86705c75000x7f8564a36c401310722388503056131212075750741415849120757507416444531207575074178589312075750741789764
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022289093989094441943042560024241623680x7f86705c74000x7f8564a36c801310722328422956016012075750741837233120757507420735721207575074231949112075750742390741
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022489093989094441943042560024241646080x7f86705c73000x7f8564a36cc01310722437923086878412075750742427590120757507426458901207575074278556912075750742789382
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022689093989094441943042560020241663360x7f86705c7a000x7f8564a36d001310722393503072133612075750742836500120757507430575681207575074343372712075750743505864
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022889093989094441943042560028241685760x7f86705c79000x7f8564a36d40655361727662203269612075750743533094120757507437609251207575074402428412075750744095640
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023089093989094441943042560024241708160x7f86705c78000x7f8564a36d801310722385883050311212075750744125435120757507443642831207575074450300212075750744506814
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023289093989094441943042560024241740800x7f86705c77000x7f8564a36dc01310722437743087302412075750744555695120757507447732411207575074505212012075750745123390
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023489093989094441943042560024241765760x7f86705c76000x7f8564a36e001310722401823081168812075750745161320120757507453813991207575074552299812075750745527411
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023689093989094441943042560020241777920x7f86705c75000x7f8564a36e401310722457703154172012075750745577474120757507457978771207575074622139612075750746292773
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023889093989094441943042560028241802880x7f86705c74000x7f8564a36e80655361652502105818412075750746319903120757507465463551207575074681323312075750746884493
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024089093989094441943042560024241827840x7f86705c73000x7f8564a36ec01310722522283206345612075750746912064120757507471420321207575074728187212075750747285889
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024289093989094441943042560024241863040x7f86705c7a000x7f8564a36f001310722376723046724812075750747335541120757507475527511207575074787018912075750747941948
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024489093989094441943042560024241893120x7f86705c79000x7f8564a36f401310722599423330903212075750747980299120757507482076281207575074836026812075750748363922
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024689093989094441943042560020241907840x7f86705c78000x7f8564a36f801310722407603067444812075750748411931120757507486287461207575074914762412075750749194145
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024889093989094441943042560028241937920x7f86705c77000x7f8564a36fc0655361572202009260812075750749227878120757507494567431207575074975402212075750749825138
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025089093989094441943042560024241968000x7f86705c76000x7f8564a370001310722395803047588812075750749855023120757507500882611207575075024346012075750750247903
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025289093989094441943042560024242010880x7f86705c75000x7f8564a370401310722352222994500812075750750295893120757507505205791207575075090633812075750750977740
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025489093989094441943042560024242046080x7f86705c74000x7f8564a370801310722378823048576812075750751022743120757507512455361207575075142265612075750751426654
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025689093989094441943042560020242060800x7f86705c73000x7f8564a370c01310722428063089343212075750751476086120757507516986551207575075231081212075750752382340
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025889093989094441943042560028242096000x7f86705c7a000x7f8564a37100655361661422129515212075750752414961120757507526428111207575075297593012075750753047396
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026089093989094441943042560024242131200x7f86705c79000x7f8564a371401310722287562945474412075750753085487120757507533136881207575075349192812075750753495419
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026289093989094441943042560024242181760x7f86705c78000x7f8564a371801310722362583031991212075750753545402120757507537632871207575075421944512075750754291288
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026489093989094441943042560024242222080x7f86705c77000x7f8564a371c01310722417963065480812075750754332695120757507545496841207575075474856312075750754792770
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026689093989094441943042560020242239360x7f86705c76000x7f8564a372001310722382843065255212075750754823918120757507550580021207575075576151912075750755832662
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026889093989094441943042560028242279680x7f86705c75000x7f8564a37240655361561882000944812075750755860113120757507560989581207575075647207612075750756542792
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027089093989094441943042560024242320000x7f86705c74000x7f8564a372801310722298562947986412075750756569973120757507567949551207575075699815412075750757069952
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027289093989094441943042560024242378240x7f86705c73000x7f8564a372c01310722388663065064812075750757096842120757507573231131207575075784903112075750757920252
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027489093989094441943042560024242423680x7f86705c7a000x7f8564a373001310722414583089869612075750757960417120757507581807101207575075840502912075750758475965
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027689093989094441943042560020242435840x7f86705c79000x7f8564a373401310722369063041226412075750758503316120757507587291881207575075952870412075750759599403
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027889093989094441943042560028242481280x7f86705c78000x7f8564a37380655361593362046908812075750759628858120757507598635831207575076028310212075750760355097
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028089093989094441943042560024242526720x7f86705c77000x7f8564a373c01310722462683133423212075750760381126120757507606162201207575076084213912075750760913235
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028289093989094441943042560024242592640x7f86705c76000x7f8564a374001310722378043047180812075750760939253120757507611715781207575076176965612075750761841720
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028489093989094441943042560024242648320x7f86705c75000x7f8564a374401310722373543039004812075750761877246120757507621085351207575076237637312075750762447927
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028689093989094441943042560020242663040x7f86705c74000x7f8564a374801310722392083057057612075750762474967120757507627072521207575076369364812075750763764974
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028889093989094441943042560028242718720x7f86705c73000x7f8564a374c0655361574862015949612075750763792405120757507640389271207575076455252512075750764623901
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029089093989094441943042560024242774400x7f86705c7a000x7f8564a375001310722396183075225612075750764653556120757507648901241207575076516292312075750765233744
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029289093989094441943042560012242799360x7f86705c79000x7f8564a375401310722366463008086412075750765260053120757507654944411207575076623363912075750766304594
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029489093989094441943042560024242865280x7f86705c78000x7f8564a375801310722386283076348012075750766341403120757507665645171207575076688131612075750766952308
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029689093989094441943042560020242880000x7f86705c77000x7f8564a375c01310722400243075832012075750766978767120757507672249951207575076839923012075750768471281
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029889093989094441943042560032242945920x7f86705c76000x7f8564a37600655361540961982448812075750768498191120757507687395491207575076934818712075750769420204
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030089093989094441943042560024243011840x7f86705c75000x7f8564a376401310722365923017581612075750769451943120757507696835451207575077000466412075750770075492
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030289093989094441943042560012243049600x7f86705c74000x7f8564a376801310722449623129837612075750770107612120757507703347431207575077121361912075750771284559
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030489093989094441943042560024243136000x7f86705c73000x7f8564a376c01310722410803043036812075750771324513120757507715494581207575077196033712075750772013324
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030689093989094441943042560020243148160x7f86705c7a000x7f8564a377001310722384963056460012075750772038771120757507722777751207575077382848912075750773900431
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030889093989094441943042560020243175680x7f86705c79000x7f8564a37740655361756102245789612075750773927381120757507741673681207575077496512512075750775037714
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031089093989094441943042560012243203200x7f86705c78000x7f8564a377801310722342062986688012075750775070565120757507752966441207575077571248212075750775782518
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031289093989094441943042560012243240960x7f86705c77000x7f8564a377c01310722403083057212012075750775808346120757507760452811207575077720495612075750777276575
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031489093989094441943042560012243288960x7f86705c76000x7f8564a378001310722501043202719212075750777314866120757507775428751207575077833007212075750778402027
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031689093989094441943042560020243301120x7f86705c75000x7f8564a378401310722429003110720812075750778434116120757507786631911207575078171981912075750781791686
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031889093989094441943042560020243328640x7f86705c74000x7f8564a37880655361628422082063212075750781823425120757507820586981207575078360333212075750783675187
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032089093989094441943042560012243356160x7f86705c73000x7f8564a378c01310722432643112904812075750783709681120757507839431701207575078473340712075750784805006
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032289093989094441943042560012243393920x7f86705c7a000x7f8564a379001310722477103160257612075750784830424120757507850761261207575078735947712075750787432199
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032489093989094441943042560012243441920x7f86705c79000x7f8564a379401310722306562947173612075750787476611120757507876989961207575078923515012075750789309418
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032689093989094441943042560020243454080x7f86705c78000x7f8564a379801310722408943065785612075750789339714120757507895783491207575079563736512075750795709121
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032889093989094441943042560020243481600x7f86705c77000x7f8564a379c0655361657442124271212075750795743365120757507959766311207575079902078112075750799083783
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033089093989094441943042560012243509120x7f86705c76000x7f8564a37a001310722302282947911212075750799109621120757507993490991207575080088781312075750800959158
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332890939890944419430425600122400x7f86705c75000x7f8564a37a401310722265922913469612075750800986218120757508012305321207575080575947712075750805833878