Moving workloads to old

Signed-off-by: Jose Santos <josantos@login1.hpcfund>


[ROCm/rocprofiler-compute commit: 989e29cf81]
This commit is contained in:
Jose Santos
2024-02-20 11:01:23 -06:00
committato da Karl W. Schulz
parent 6ac883e20e
commit 79c75edc48
9701 ha cambiato i file con 4016 aggiunte e 0 eliminazioni
@@ -0,0 +1,168 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,grd,Workgroup_Size,LDS_Per_Workgroup,scr,vgpr,SGPR,fbar,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"__amd_rocclr_fillBuffer.kd",0,0,0,930064,930069,33554432,256,0,0,8,32,6464,0x0,0x7fc924204180,501625,501625,524288,6291456,791363,101379224,12076511629552996,12076511873640060,12076511873962459,12076511874072021
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,930064,930069,32768,256,0,0,24,24,12480,0x0,0x7fc924235100,28353,28353,512,8192,8985,1155340,12076511888619511,12076511888937326,12076511888943886,12076511888951659
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,930064,930069,4194304,256,0,0,24,24,12928,0x7fca2f751900,0x7fc924235140,214915,214915,65536,917504,139932,17898568,12076511889024354,12076511889248365,12076511889378924,12076511889383012
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,930064,930069,4194304,256,0,0,36,24,13632,0x7fca2f751800,0x7fc924235180,395129,395129,65536,1245184,187764,24126632,12076511889454855,12076511889648043,12076511889900362,12076511889970525
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,930064,930069,4194304,256,0,0,28,24,14080,0x7fca2f751700,0x7fc9242351c0,394163,394163,65536,983040,136843,17530748,12076511890016450,12076511890190761,12076511890441481,12076511890512944
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,930064,930069,4194304,256,0,0,24,24,14528,0x7fca2f751600,0x7fc924235200,224953,224953,65536,1048576,161417,20651260,12076511890543120,12076511890729320,12076511890867879,12076511890871450
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,930064,930069,4194304,256,0,0,24,24,14976,0x7fca2f751500,0x7fc924235240,219883,219883,65536,983040,148081,18955680,12076511890925862,12076511891112998,12076511891247078,12076511891250816
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,930064,930069,4194304,256,0,0,24,24,15424,0x7fca2f751400,0x7fc924235280,218281,218281,65536,1048576,146679,18771468,12076511891333450,12076511891507717,12076511891641796,12076511891645079
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,930064,930069,4194304,256,0,0,28,24,16128,0x7fca2f751300,0x7fc9242352c0,407163,407163,65536,1572864,230007,29426828,12076511891699921,12076511891872996,12076511892132515,12076511892177309
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,930064,930069,4194304,256,0,0,28,24,16832,0x7fca2f751a00,0x7fc924235300,408841,408841,65536,1179648,158554,20265040,12076511892202747,12076511892399554,12076511892660993,12076511892702727
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,930064,930069,4194304,256,0,0,24,24,17536,0x7fca2f751900,0x7fc924235340,218443,218443,65536,1114112,161435,20666692,12076511892737542,12076511892913792,12076511893046912,12076511893050474
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,930064,930069,4194304,256,0,0,24,24,18240,0x7fca2f751800,0x7fc924235380,221425,221425,65536,1114112,156380,20042720,12076511893101348,12076511893284831,12076511893420990,12076511893424319
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,930064,930069,4194304,256,0,0,24,24,18944,0x7fca2f751700,0x7fc9242353c0,216971,216971,65536,1179648,164746,21076988,12076511893492636,12076511893661309,12076511893793309,12076511893796892
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,930064,930069,4194304,256,0,0,28,24,19904,0x7fca2f751600,0x7fc924235400,407969,407969,65536,1835008,255078,32648428,12076511893850391,12076511894026428,12076511894287227,12076511894357064
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,930064,930069,4194304,256,0,0,28,24,20608,0x7fca2f751500,0x7fc924235440,400515,400515,65536,1310720,178314,22809868,12076511894386819,12076511894574106,12076511894829305,12076511894897379
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,930064,930069,4194304,256,0,0,24,24,21312,0x7fca2f751400,0x7fc924235480,214529,214529,65536,1245184,175469,22446300,12076511894925291,12076511895117144,12076511895248984,12076511895252780
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,930064,930069,4194304,256,0,0,24,24,22016,0x7fca2f751300,0x7fc9242354c0,228443,228443,65536,1310720,183393,23483288,12076511895306129,12076511895481943,12076511895622103,12076511895625644
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,930064,930069,4194304,256,0,0,24,24,22720,0x7fca2f751a00,0x7fc924235500,212545,212545,65536,1310720,180330,23094592,12076511895693300,12076511895863062,12076511895993621,12076511895997115
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,930064,930069,4194304,256,0,0,28,24,23680,0x7fca2f751900,0x7fc924235540,402323,402323,65536,2097152,315221,40321040,12076511896052017,12076511896228820,12076511896485780,12076511896554371
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,930064,930069,4194304,256,0,0,28,24,24384,0x7fca2f751800,0x7fc924235580,402137,402137,65536,1441792,196188,25215192,12076511896580740,12076511896765619,12076511897023058,12076511897093123
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,930064,930069,4194304,256,0,0,24,24,25088,0x7fca2f751700,0x7fc9242355c0,214459,214459,65536,1376256,189903,24366844,12076511897118090,12076511897314897,12076511897445616,12076511897449086
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,930064,930069,4194304,256,0,0,24,24,25792,0x7fca2f751600,0x7fc924235600,213489,213489,65536,1507328,211954,27040156,12076511897503667,12076511897671695,12076511897802895,12076511897806370
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,930064,930069,4194304,256,0,0,24,24,26496,0x7fca2f751500,0x7fc924235640,217707,217707,65536,1441792,211624,27116764,12076511897873004,12076511898048014,12076511898180814,12076511898184754
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,930064,930069,4194304,256,0,0,28,24,27712,0x7fca2f751400,0x7fc924235680,391313,391313,65536,2359296,324312,41593648,12076511898232613,12076511898413933,12076511898665132,12076511898733505
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,930064,930069,4194304,256,0,0,28,24,28416,0x7fca2f751300,0x7fc9242356c0,407515,407515,65536,1572864,209927,26902472,12076511898761347,12076511898946251,12076511899206250,12076511899274792
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,930064,930069,4194304,256,0,0,24,24,29120,0x7fca2f751a00,0x7fc924235700,210249,210249,65536,1507328,207874,26606196,12076511899301962,12076511899492969,12076511899621769,12076511899625534
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,930064,930069,4194304,256,0,0,24,24,30080,0x7fca2f751900,0x7fc924235740,223187,223187,65536,1703936,235765,30251584,12076511899679174,12076511899847528,12076511899984647,12076511899988139
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,930064,930069,4194304,256,0,0,24,24,30784,0x7fca2f751800,0x7fc924235780,213337,213337,65536,1572864,215134,27578720,12076511900056145,12076511900222247,12076511900353606,12076511900357025
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,930064,930069,4194304,256,0,0,28,24,32000,0x7fca2f751700,0x7fc9242357c0,399979,399979,65536,2621440,369765,47301416,12076511900410374,12076511900578245,12076511900834084,12076511900901998
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,930064,930069,4194304,256,0,0,28,24,32960,0x7fca2f751600,0x7fc924235800,399761,399761,65536,1703936,231171,29615256,12076511900929039,12076511901116004,12076511901371523,12076511901440991
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,930064,930069,4194304,256,0,0,24,24,33920,0x7fca2f751500,0x7fc924235840,215987,215987,65536,1638400,229448,29354540,12076511901465827,12076511901650402,12076511901782241,12076511901785782
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,930064,930069,4194304,256,0,0,24,24,34880,0x7fca2f751400,0x7fc924235880,211777,211777,65536,1900544,269121,34406164,12076511901838020,12076511902013280,12076511902143680,12076511902147565
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,930064,930069,4194304,256,0,0,24,24,35840,0x7fca2f751300,0x7fc9242358c0,220899,220899,65536,1703936,228758,29330840,12076511902214981,12076511902383839,12076511902517119,12076511902520739
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,930064,930069,4194304,256,0,0,28,24,37312,0x7fca2f751a00,0x7fc924235900,399281,399281,65536,2883584,387449,49510472,12076511902574509,12076511902751518,12076511903008797,12076511903078166
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,930064,930069,4194304,256,0,0,28,24,38272,0x7fca2f751900,0x7fc924235940,398979,398979,65536,1835008,243929,31209696,12076511903105197,12076511903294556,12076511903549435,12076511903618011
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,930064,930069,4194304,256,0,0,24,24,39232,0x7fca2f751800,0x7fc924235980,217769,217769,65536,1769472,258399,33089216,12076511903646494,12076511903835514,12076511903969914,12076511903973512
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,930064,930069,4194304,256,0,0,24,24,40192,0x7fca2f751700,0x7fc9242359c0,224219,224219,65536,2097152,303544,38989148,12076511904035036,12076511904206873,12076511904344632,12076511904348249
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,930064,930069,4194304,256,0,0,24,24,41152,0x7fca2f751600,0x7fc924235a00,216753,216753,65536,1835008,254074,32467216,12076511904412989,12076511904576791,12076511904710871,12076511904714029
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,930064,930069,4194304,256,0,0,28,24,42624,0x7fca2f751500,0x7fc924235a40,408491,408491,65536,3145728,432511,55278432,12076511904766918,12076511904938550,12076511905201109,12076511905271396
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,930064,930069,4194304,256,0,0,28,24,43584,0x7fca2f751400,0x7fc924235a80,398857,398857,65536,1966080,262806,33632440,12076511905296563,12076511905484468,12076511905740147,12076511905807734
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,930064,930069,4194304,256,0,0,24,24,44544,0x7fca2f751300,0x7fc924235ac0,286747,286747,65536,1900544,261316,33522712,12076511905831949,12076511906025266,12076511906204306,12076511906208138
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,930064,930069,4194304,256,0,0,24,24,45760,0x7fca2f751a00,0x7fc924235b00,227329,227329,65536,2293760,308417,39638124,12076511906262089,12076511906438705,12076511906578545,12076511906582074
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,930064,930069,4194304,256,0,0,24,24,46720,0x7fca2f751900,0x7fc924235b40,215867,215867,65536,1966080,270023,34543308,12076511906646875,12076511906812304,12076511906945263,12076511906948846
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,930064,930069,4194304,256,0,0,28,24,48448,0x7fca2f751800,0x7fc924235b80,409825,409825,65536,3407872,462030,59205132,12076511907007425,12076511907177902,12076511907441742,12076511907511072
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,930064,930069,4194304,256,0,0,28,24,49408,0x7fca2f751700,0x7fc924235bc0,401483,401483,65536,2097152,278549,35578596,12076511907539595,12076511907722381,12076511907980460,12076511908047580
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,930064,930069,4194304,256,0,0,24,24,50368,0x7fca2f751600,0x7fc924235c00,210585,210585,65536,2031616,285951,36567104,12076511908075532,12076511908262059,12076511908391018,12076511908394756
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,930064,930069,4194304,256,0,0,24,24,51584,0x7fca2f751500,0x7fc924235c40,223627,223627,65536,2490368,349329,44598892,12076511908446612,12076511908618537,12076511908757097,12076511908760667
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,930064,930069,4194304,256,0,0,24,24,52544,0x7fca2f751400,0x7fc924235c80,216289,216289,65536,2097152,290541,37131692,12076511908827100,12076511908994536,12076511909127016,12076511909130975
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,930064,930069,4194304,256,0,0,28,24,54272,0x7fca2f751300,0x7fc924235cc0,416907,416907,65536,3670016,488244,62467976,12076511909184104,12076511909367655,12076511909636934,12076511909703851
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,930064,930069,4194304,256,0,0,28,24,55488,0x7fca2f751a00,0x7fc924235d00,403089,403089,65536,2228224,298418,38285100,12076511909731803,12076511909914373,12076511910173092,12076511910242703
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,930064,930069,4194304,256,0,0,24,24,56704,0x7fca2f751900,0x7fc924235d40,218979,218979,65536,2162688,309702,39589660,12076511910270575,12076511910453251,12076511910587811,12076511910591262
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,930064,930069,4194304,256,0,0,24,24,58176,0x7fca2f751800,0x7fc924235d80,231753,231753,65536,2686976,388230,49683460,12076511910646695,12076511910809410,12076511910952929,12076511910956671
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,930064,930069,4194304,256,0,0,24,24,59392,0x7fca2f751700,0x7fc924235dc0,220643,220643,65536,2228224,324455,41538656,12076511911028535,12076511911192608,12076511911328288,12076511911332080
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,930064,930069,4194304,256,0,0,28,24,61376,0x7fca2f751600,0x7fc924235e00,412609,412609,65536,3932160,519403,66408384,12076511911386070,12076511911558847,12076511911824286,12076511911891670
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,930064,930069,4194304,256,0,0,28,24,62592,0x7fca2f751500,0x7fc924235e40,400643,400643,65536,2359296,328434,42024304,12076511911918871,12076511912111165,12076511912368444,12076511912435522
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,930064,930069,4194304,256,0,0,24,24,63808,0x7fca2f751400,0x7fc924235e80,211377,211377,65536,2293760,320544,41035888,12076511912460719,12076511912643003,12076511912772603,12076511912776316
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,930064,930069,4194304,256,0,0,24,24,65280,0x7fca2f751300,0x7fc924235ec0,221523,221523,65536,2883584,420092,53683000,12076511912829034,12076511913005402,12076511913143162,12076511913146715
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,930064,930069,4194304,256,0,0,24,24,66496,0x7fca2f751a00,0x7fc924235f00,216569,216569,65536,2359296,327023,41842148,12076511913216826,12076511913384281,12076511913517240,12076511913520871
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,930064,930069,4194304,256,0,0,28,24,68480,0x7fca2f751900,0x7fc924235f40,409011,409011,65536,4194304,597281,76594840,12076511913571986,12076511913744920,12076511914009559,12076511914076755
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,930064,930069,4194304,256,0,0,28,24,69696,0x7fca2f751800,0x7fc924235f80,401265,401265,65536,2490368,328494,41973448,12076511914108775,12076511914287958,12076511914545557,12076511914586533
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,930064,930069,4194304,256,0,0,24,24,70912,0x7fca2f751700,0x7fc924235fc0,216323,216323,65536,2424832,336930,43132840,12076511914618433,12076511914795956,12076511914929075,12076511914932697
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,930064,930069,4194304,256,0,0,24,24,72384,0x7fca2f751600,0x7fc924236000,225233,225233,65536,3080192,492289,63022112,12076511914986247,12076511915167795,12076511915307474,12076511915311372
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,930064,930069,4194304,256,0,0,24,24,73600,0x7fca2f751500,0x7fc924236040,226195,226195,65536,2490368,379413,48573264,12076511915377434,12076511915541393,12076511915681393,12076511915685147
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,930064,930069,4194304,256,0,0,28,24,75840,0x7fca2f751400,0x7fc924236080,409569,409569,65536,4456448,588726,75217880,12076511915737995,12076511915909872,12076511916174351,12076511916242804
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,930064,930069,4194304,256,0,0,28,24,77056,0x7fca2f751300,0x7fc9242360c0,397867,397867,65536,2621440,348743,44602924,12076511916267891,12076511916455310,12076511916711149,12076511916778360
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,930064,930069,4194304,256,0,0,24,24,78272,0x7fca2f751a00,0x7fc924236100,212241,212241,65536,2555904,378392,48366064,12076511916805401,12076511916986508,12076511917116748,12076511917120667
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,930064,930069,4194304,256,0,0,24,24,80000,0x7fca2f751900,0x7fc924236140,231443,231443,65536,3276800,451179,57802376,12076511917178495,12076511917344587,12076511917488747,12076511917492489
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,930064,930069,4194304,256,0,0,24,24,81216,0x7fca2f751800,0x7fc924236180,218057,218057,65536,2621440,371758,47504748,12076511917559233,12076511917725706,12076511917859785,12076511917863429
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,930064,930069,4194304,256,0,0,28,24,83456,0x7fca2f751700,0x7fc9242361c0,420315,420315,65536,4718592,625771,80053288,12076511917916287,12076511918096264,12076511918368424,12076511918436565
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,930064,930069,4194304,256,0,0,28,24,84928,0x7fca2f751600,0x7fc924236200,402433,402433,65536,2752512,361304,46192032,12076511918465509,12076511918646023,12076511918904262,12076511918971530
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,930064,930069,4194304,256,0,0,24,24,86400,0x7fca2f751500,0x7fc924236240,225723,225723,65536,2686976,437108,56026900,12076511918998029,12076511919191141,12076511919330660,12076511919334635
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,930064,930069,4194304,256,0,0,24,24,88128,0x7fca2f751400,0x7fc924236280,241321,241321,65536,3473408,565919,72576752,12076511919389467,12076511919553859,12076511919704099,12076511919707699
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,930064,930069,4194304,256,0,0,24,24,89600,0x7fca2f751300,0x7fc9242362c0,220363,220363,65536,2752512,410661,52599332,12076511919790784,12076511919954818,12076511920090978,12076511920095461
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,930064,930069,4194304,256,0,0,28,24,92096,0x7fca2f751a00,0x7fc924236300,418153,418153,65536,4980736,696325,89348908,12076511920149722,12076511920324577,12076511920595136,12076511920644372
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,930064,930069,4194304,256,0,0,28,24,93568,0x7fca2f751900,0x7fc924236340,402755,402755,65536,2883584,402521,51417348,12076511920673536,12076511920850975,12076511921110174,12076511921159640
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,930064,930069,4194304,256,0,0,24,24,95040,0x7fca2f751800,0x7fc924236380,214289,214289,65536,2818048,399571,51181284,12076511921186851,12076511921369533,12076511921501213,12076511921504992
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,930064,930069,4194304,256,0,0,24,24,96768,0x7fca2f751700,0x7fc9242363c0,256115,256115,65536,3670016,560285,71675928,12076511921557841,12076511921722332,12076511921881051,12076511921884839
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,930064,930069,4194304,256,0,0,24,24,98240,0x7fca2f751600,0x7fc924236400,226265,226265,65536,2883584,408569,52243256,12076511921952375,12076511922123290,12076511922262970,12076511922267110
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,930064,930069,4194304,256,0,0,28,24,100736,0x7fca2f751500,0x7fc924236440,413747,413747,65536,5177344,687052,88025392,12076511922320990,12076511922487449,12076511922755928,12076511922804820
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,930064,930069,4194304,256,0,0,28,24,102208,0x7fca2f751400,0x7fc924236480,398081,398081,65536,3014656,415416,53193000,12076511922831530,12076511923015127,12076511923271607,12076511923323094
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,930064,930069,4194304,256,0,0,24,24,103680,0x7fca2f751300,0x7fc9242364c0,222539,222539,65536,2949120,478928,61249356,12076511923350325,12076511923538966,12076511923676885,12076511923680660
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,930064,930069,4194304,256,0,0,24,24,105664,0x7fca2f751a00,0x7fc924236500,262593,262593,65536,3866624,543605,69595000,12076511923736043,12076511923898004,12076511924062644,12076511924066507
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,930064,930069,4194304,256,0,0,24,24,107136,0x7fca2f751900,0x7fc924236540,223795,223795,65536,3014656,455697,58262024,12076511924133812,12076511924298643,12076511924436882,12076511924440773
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,930064,930069,4194304,256,0,0,28,24,109888,0x7fca2f751800,0x7fc924236580,412209,412209,65536,5439488,716896,91691208,12076511924494824,12076511924659922,12076511924926801,12076511924948628
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,930064,930069,4194304,256,0,0,28,24,111360,0x7fca2f751700,0x7fc9242365c0,403699,403699,65536,3145728,450971,57650148,12076511924994974,12076511925164880,12076511925425359,12076511925473554
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,930064,930069,4194304,256,0,0,24,24,112832,0x7fca2f751600,0x7fc924236600,224801,224801,65536,3080192,495442,63423164,12076511925498902,12076511925684718,12076511925823278,12076511925827062
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,930064,930069,4194304,256,0,0,24,24,114816,0x7fca2f751500,0x7fc924236640,276835,276835,65536,4063232,568762,72684956,12076511925879870,12076511926053517,12076511926227436,12076511926231464
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,930064,930069,4194304,256,0,0,24,24,116288,0x7fca2f751400,0x7fc924236680,226881,226881,65536,3145728,467020,59818232,12076511926299030,12076511926464555,12076511926604715,12076511926608596
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,930064,930069,4194304,256,0,0,28,24,119040,0x7fca2f751300,0x7fc9242366c0,406683,406683,65536,5701632,806922,103299876,12076511926661895,12076511926832074,12076511927095753,12076511927146216
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,930064,930069,4194304,256,0,0,28,24,120768,0x7fca2f751a00,0x7fc924236700,406433,406433,65536,3276800,437380,55872072,12076511927175871,12076511927356712,12076511927618631,12076511927668197
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,930064,930069,4194304,256,0,0,24,24,122496,0x7fca2f751900,0x7fc924236740,228755,228755,65536,3211264,460325,58884540,12076511927695407,12076511927874471,12076511928016230,12076511928020182
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,930064,930069,4194304,256,0,0,24,24,124736,0x7fca2f751800,0x7fc924236780,289169,289169,65536,4259840,581188,74298136,12076511928074332,12076511928246629,12076511928429509,12076511928433621
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,930064,930069,4194304,256,0,0,24,24,126464,0x7fca2f751700,0x7fc9242367c0,227115,227115,65536,3276800,505912,64725060,12076511928499112,12076511928663268,12076511928803267,12076511928807256
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,930064,930069,4194304,256,0,0,20,24,127936,0x7fca2f751600,0x7fc924236800,410673,410673,65536,7733248,975275,124837252,12076511928862118,12076511929034146,12076511929300706,12076511929349484
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,930064,930069,4194304,256,0,0,28,24,129664,0x7fca2f751500,0x7fc924236840,398331,398331,65536,3407872,457792,58617684,12076511929378378,12076511929559745,12076511929816864,12076511929866285
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,930064,930069,4194304,256,0,0,24,24,131392,0x7fca2f751400,0x7fc924236880,225841,225841,65536,3342336,480358,61506388,12076511929890641,12076511930083743,12076511930223422,12076511930227277
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,930064,930069,4194304,256,0,0,24,24,133632,0x7fca2f751300,0x7fc9242368c0,301395,301395,65536,4456448,637852,81949632,12076511930282259,12076511930449022,12076511930640701,12076511930688024
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,930064,930069,4194304,256,0,0,24,24,135360,0x7fca2f751a00,0x7fc924236900,220737,220737,65536,3538944,574538,73514252,12076511930729371,12076511930894780,12076511931030780,12076511931034739
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,930064,930069,4194304,256,0,0,20,24,136832,0x7fca2f751900,0x7fc924236940,435139,435139,65536,8978432,1128256,144640484,12076511931088339,12076511931256539,12076511931540218,12076511931586986
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,930064,930069,4194304,256,0,0,28,24,138560,0x7fca2f751800,0x7fc924236980,396241,396241,65536,3670016,502907,64221436,12076511931612935,12076511931792537,12076511932049016,12076511932070746
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,930064,930069,4194304,256,0,0,24,24,140288,0x7fca2f751700,0x7fc9242369c0,220683,220683,65536,3604480,548357,70137088,12076511932125167,12076511932292215,12076511932428535,12076511932432299
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,930064,930069,4194304,256,0,0,24,24,142784,0x7fca2f751600,0x7fc924236a00,330929,330929,65536,4849664,756734,96932892,12076511932486099,12076511932653654,12076511932863893,12076511932911730
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,930064,930069,4194304,256,0,0,24,24,144768,0x7fca2f751500,0x7fc924236a40,231883,231883,65536,3801088,634788,81172200,12076511932953278,12076511933124212,12076511933268372,12076511933272291
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,930064,930069,4194304,256,0,0,20,24,145728,0x7fca2f751400,0x7fc924236a80,470385,470385,65536,14548992,1827450,233846504,12076511933326141,12076511933504531,12076511933811570,12076511933858592
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,930064,930069,4194304,256,0,0,28,24,147712,0x7fca2f751300,0x7fc924236ac0,409011,409011,65536,3932160,517874,66533164,12076511933887846,12076511934061329,12076511934326608,12076511934374231
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,930064,930069,4194304,256,0,0,24,24,149696,0x7fca2f751a00,0x7fc924236b00,223657,223657,65536,3866624,563998,72189852,12076511934403395,12076511934585967,12076511934724367,12076511934728099
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,930064,930069,4194304,256,0,0,24,24,152192,0x7fca2f751900,0x7fc924236b40,356411,356411,65536,5242880,770082,98788036,12076511934781138,12076511934946606,12076511935174765,12076511935225434
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,930064,930069,4194304,256,0,0,24,24,154176,0x7fca2f751800,0x7fc924236b80,222401,222401,65536,4063232,622486,79775516,12076511935268094,12076511935435724,12076511935573484,12076511935577269
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,930064,930069,4194304,256,0,0,20,24,155648,0x7fca2f751700,0x7fc924236bc0,502523,502523,65536,10027008,1260314,161428400,12076511935627783,12076511935807403,12076511936137002,12076511936165222
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,930064,930069,4194304,256,0,0,28,24,157632,0x7fca2f751600,0x7fc924236c00,404241,404241,65536,4194304,554570,71021236,12076511936213362,12076511936380095,12076511936641055,12076511936693585
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,930064,930069,4194304,256,0,0,24,24,159616,0x7fca2f751500,0x7fc924236c40,214435,214435,65536,4128768,574408,73434388,12076511936715967,12076511936901373,12076511937034492,12076511937038316
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,930064,930069,4194304,256,0,0,24,24,162368,0x7fca2f751400,0x7fc924236c80,431513,431513,65536,5636096,780436,99873568,12076511937093219,12076511937271132,12076511937549051,12076511937596485
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,930064,930069,4194304,256,0,0,24,24,164608,0x7fca2f751300,0x7fc924236cc0,223707,223707,65536,4587520,658096,84300796,12076511937634145,12076511937800090,12076511937937690,12076511937941126
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,930064,930069,4194304,256,0,0,20,24,166336,0x7fca2f751a00,0x7fc924236d00,572249,572249,65536,11075584,1390692,177990324,12076511937993183,12076511938171609,12076511938547608,12076511938595793
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,930064,930069,4194304,256,0,0,28,24,168576,0x7fca2f751900,0x7fc924236d40,400499,400499,65536,4718592,644940,82542628,12076511938620409,12076511938811127,12076511939070486,12076511939120580
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,930064,930069,4194304,256,0,0,24,24,170816,0x7fca2f751800,0x7fc924236d80,219817,219817,65536,4653056,730814,93608432,12076511939144023,12076511939337686,12076511939474485,12076511939478065
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,930064,930069,4194304,256,0,0,24,24,174080,0x7fca2f751700,0x7fc924236dc0,438059,438059,65536,6422528,911676,116615924,12076511939534369,12076511939696244,12076511939976084,12076511940024721
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,930064,930069,4194304,256,0,0,24,24,176576,0x7fca2f751600,0x7fc924236e00,226697,226697,65536,5111808,822125,105295488,12076511940066098,12076511940235283,12076511940376722,12076511940380173
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,930064,930069,4194304,256,0,0,20,24,177792,0x7fca2f751500,0x7fc924236e40,644371,644371,65536,15007744,1885121,241036332,12076511940434013,12076511940600562,12076511941023920,12076511941071419
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,930064,930069,4194304,256,0,0,28,24,180288,0x7fca2f751400,0x7fc924236e80,415625,415625,65536,5242880,723513,92529184,12076511941097848,12076511941291920,12076511941562799,12076511941610491
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,930064,930069,4194304,256,0,0,24,24,182784,0x7fca2f751300,0x7fc924236ec0,226347,226347,65536,5177344,837217,107044760,12076511941640758,12076511941817838,12076511941958318,12076511941961955
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,930064,930069,4194304,256,0,0,24,24,186304,0x7fca2f751a00,0x7fc924236f00,487145,487145,65536,7208960,1038969,132954000,12076511942025774,12076511942189677,12076511942505356,12076511942551652
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,930064,930069,4194304,256,0,0,24,24,189312,0x7fca2f751900,0x7fc924236f40,244347,244347,65536,6160384,919610,117851268,12076511942588781,12076511942754635,12076511942907275,12076511942910770
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,930064,930069,4194304,256,0,0,20,24,190784,0x7fca2f751800,0x7fc924236f80,783393,783393,65536,17104896,2147380,274723160,12076511942963177,12076511943145514,12076511943662473,12076511943711880
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,930064,930069,4194304,256,0,0,28,24,193792,0x7fca2f751700,0x7fc924236fc0,453939,453939,65536,6291456,838704,107318240,12076511943743128,12076511943928712,12076511944224391,12076511944273364
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,930064,930069,4194304,256,0,0,24,24,196800,0x7fca2f751600,0x7fc924237000,246497,246497,65536,6225920,930537,119161908,12076511944306987,12076511944479590,12076511944634950,12076511944638363
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,930064,930069,4194304,256,0,0,24,24,201088,0x7fca2f751500,0x7fc924237040,592803,592803,65536,8781824,1258002,160492552,12076511944693806,12076511944877029,12076511945262308,12076511945309502
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,930064,930069,4194304,256,0,0,24,24,204608,0x7fca2f751400,0x7fc924237080,278393,278393,65536,7208960,1068025,136737860,12076511945355698,12076511945523427,12076511945700706,12076511945704056
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,930064,930069,4194304,256,0,0,20,24,206080,0x7fca2f751300,0x7fc9242370c0,925627,925627,65536,19202048,2413930,309449300,12076511945756593,12076511945931586,12076511946542464,12076511946592348
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,930064,930069,4194304,256,0,0,28,24,209600,0x7fca2f751a00,0x7fc924237100,499953,499953,65536,7340032,1042709,133734804,12076511946623356,12076511946809183,12076511947137662,12076511947186784
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,930064,930069,4194304,256,0,0,24,24,213120,0x7fca2f751900,0x7fc924237140,283635,283635,65536,7274496,1073972,137482588,12076511947218843,12076511947409021,12076511947587901,12076511947591426
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,930064,930069,4194304,256,0,0,24,24,218176,0x7fca2f751800,0x7fc924237180,697849,697849,65536,10354688,1479623,190320272,12076511947643854,12076511947817180,12076511948273659,12076511948321214
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,930064,930069,4194304,256,0,0,24,24,222208,0x7fca2f751700,0x7fc9242371c0,366731,366731,65536,8257536,1194526,152993784,12076511948363783,12076511948532218,12076511948767577,12076511948814732
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,930064,930069,4194304,256,0,0,20,24,223936,0x7fca2f751600,0x7fc924237200,1074881,1074881,65536,21299200,2670862,341680532,12076511948842794,12076511949038296,12076511949747894,12076511949800516
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,930064,930069,4194304,256,0,0,28,24,227968,0x7fca2f751500,0x7fc924237240,565907,565907,65536,8388608,1199958,153494464,12076511949832185,12076511950037973,12076511950409812,12076511950459481
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,930064,930069,4194304,256,0,0,24,24,232000,0x7fca2f751400,0x7fc924237280,317777,317777,65536,8323072,1262083,161524352,12076511950485390,12076511950668691,12076511950872051,12076511950919667
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,930064,930069,4194304,256,0,0,24,24,237824,0x7fca2f751300,0x7fc9242372c0,801691,801691,65536,11927552,1637757,208842428,12076511950948100,12076511951133170,12076511951658129,12076511951708214
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,930064,930069,4194304,256,0,0,24,24,242368,0x7fca2f751a00,0x7fc924237300,349633,349633,65536,9306112,1431268,183218216,12076511951749301,12076511951915728,12076511952140847,12076511952189489
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,930064,930069,4194304,256,0,0,20,24,243584,0x7fca2f751900,0x7fc924237340,1207459,1207459,65536,29163520,3650139,467426916,12076511952219866,12076511952400686,12076511953199884,12076511953268116
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,930064,930069,4194304,256,0,0,28,24,248128,0x7fca2f751800,0x7fc924237380,671633,671633,65536,9437184,1317261,168392776,12076511953297030,12076511953480523,12076511953924522,12076511953992293
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,930064,930069,4194304,256,0,0,24,24,252672,0x7fca2f751700,0x7fc9242373c0,354315,354315,65536,9371648,1410177,180572968,12076511954018451,12076511954226281,12076511954453800,12076511954523301
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,930064,930069,4194304,256,0,0,24,24,259264,0x7fca2f751600,0x7fc924237400,910129,910129,65536,13500416,1962408,250402000,12076511954557334,12076511954726919,12076511955325957,12076511955396034
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,930064,930069,4194304,256,0,0,24,24,264832,0x7fca2f751500,0x7fc924237440,417587,417587,65536,11403264,1738015,222515428,12076511955443763,12076511955611237,12076511955879876,12076511955948001
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,930064,930069,4194304,256,0,0,20,24,266304,0x7fca2f751400,0x7fc924237480,1486641,1486641,65536,33357824,4179073,534645340,12076511955978818,12076511956168035,12076511957152352,12076511957222602
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,930064,930069,4194304,256,0,0,28,24,271872,0x7fca2f751300,0x7fc9242374c0,778755,778755,65536,11534336,1602986,204658396,12076511957255102,12076511957436511,12076511957951710,12076511958023101
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,930064,930069,4194304,256,0,0,24,24,277440,0x7fca2f751a00,0x7fc924237500,421577,421577,65536,11534336,1691806,216538116,12076511958055892,12076511958240029,12076511958512668,12076511958581379
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,930064,930069,4194304,256,0,0,12,24,279936,0x7fca2f751900,0x7fc924237540,1126115,1126115,65536,19267584,2426553,310501124,12076511958612547,12076511958796187,12076511959535065,12076511959604733
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,930064,930069,4194304,256,0,0,24,24,286528,0x7fca2f751800,0x7fc924237580,488993,488993,65536,13500416,2120242,271554024,12076511959645268,12076511959811544,12076511960128823,12076511960199409
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,930064,930069,4194304,256,0,0,20,24,288000,0x7fca2f751700,0x7fc9242375c0,1769259,1769259,65536,37552128,4685733,601539424,12076511960228563,12076511960409302,12076511961581299,12076511961650398
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,930064,930069,4194304,256,0,0,32,24,294592,0x7fca2f751600,0x7fc924237600,922025,922025,65536,13631488,1876067,240866692,12076511961685653,12076511961856178,12076511962467856,12076511962538400
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,930064,930069,4194304,256,0,0,24,24,301184,0x7fca2f751500,0x7fc924237640,494651,494651,65536,13631488,2150490,275254876,12076511962572152,12076511962761455,12076511963082254,12076511963150288
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,930064,930069,4194304,256,0,0,12,24,304960,0x7fca2f751400,0x7fc924237680,1336529,1336529,65536,21692416,2744730,351517752,12076511963183089,12076511963364653,12076511964243051,12076511964311538
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,930064,930069,4194304,256,0,0,24,24,313600,0x7fca2f751300,0x7fc9242376c0,628915,628915,65536,17694720,2732233,349748404,12076511964358425,12076511964525450,12076511964935369,12076511965009797
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,930064,930069,4194304,256,0,0,20,24,314816,0x7fca2f751a00,0x7fc924237700,2331993,2331993,65536,57475072,7196580,920856128,12076511965034543,12076511965224808,12076511966772163,12076511966841624
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,930064,930069,4194304,256,0,0,20,24,317568,0x7fca2f751900,0x7fc924237740,1201707,1201707,65536,19660800,2468542,315845476,12076511966874175,12076511967057922,12076511967853440,12076511967923116
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,930064,930069,4194304,256,0,0,12,24,320320,0x7fca2f751800,0x7fc924237780,639713,639713,65536,20381696,2569368,328948860,12076511967950948,12076511968139039,12076511968553118,12076511968620794
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,930064,930069,4194304,256,0,0,12,24,324096,0x7fca2f751700,0x7fc9242377c0,1757275,1757275,65536,28704768,3611254,462516792,12076511968649247,12076511968827997,12076511969986713,12076511970056434
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,930064,930069,4194304,256,0,0,12,24,328896,0x7fca2f751600,0x7fc924237800,1199305,1199305,65536,36634624,4670974,597989840,12076511970098522,12076511970267193,12076511971053910,12076511971122327
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,930064,930069,4194304,256,0,0,20,24,330112,0x7fca2f751500,0x7fc924237840,4584587,4584587,65536,105840640,13245157,1694951680,12076511971155789,12076511971342389,12076511974393100,12076511974463552
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,930064,930069,4194304,256,0,0,20,24,332864,0x7fca2f751400,0x7fc924237880,2324257,2324257,65536,38535168,4833917,618273068,12076511974498156,12076511974677739,12076511976219495,12076511976287715
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,930064,930069,4194304,256,0,0,12,24,335616,0x7fca2f751300,0x7fc9242378c0,1204803,1204803,65536,39124992,4912544,628724484,12076511976320436,12076511976494854,12076511977284291,12076511977352967
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,930064,930069,4194304,256,0,0,12,24,339392,0x7fca2f751a00,0x7fc924237900,3442921,3442921,65536,55771136,7008728,896749468,12076511977385778,12076511977565891,12076511979848124,12076511979917307
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,930064,930069,4194304,256,0,0,12,24,344192,0x7fca2f751900,0x7fc924237940,2323203,2323203,65536,72548352,9116143,1166622420,12076511979964344,12076511980139483,12076511981674998,12076511981745076
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,930064,930069,4194304,256,0,0,20,24,345408,0x7fca2f751800,0x7fc924237980,9088465,9088465,65536,210698240,26349453,3372603416,12076511981779300,12076511981959157,12076511988015459,12076511988084058
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,930064,930069,4194304,256,0,0,20,24,348160,0x7fca2f751700,0x7fc9242379c0,4571627,4571627,65536,76283904,9555771,1222719012,12076511988118041,12076511988304738,12076511991346489,12076511991416486
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,930064,930069,4194304,256,0,0,12,24,350912,0x7fca2f751600,0x7fc924237a00,2329897,2329897,65536,77398016,9708865,1242502468,12076511991448165,12076511991636248,12076511993176244,12076511993247773
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,930064,930069,4194304,256,0,0,12,24,0,0x7fca2f751500,0x7fc924237a40,6812827,6812827,65536,110821376,13891448,1777823056,12076511993277087,12076511993464403,12076511997993349,12076511998064773
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid grd Workgroup_Size LDS_Per_Workgroup scr vgpr SGPR fbar sig obj GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 __amd_rocclr_fillBuffer.kd 0 0 0 930064 930069 33554432 256 0 0 8 32 6464 0x0 0x7fc924204180 501625 501625 524288 6291456 791363 101379224 12076511629552996 12076511873640060 12076511873962459 12076511874072021
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 930064 930069 32768 256 0 0 24 24 12480 0x0 0x7fc924235100 28353 28353 512 8192 8985 1155340 12076511888619511 12076511888937326 12076511888943886 12076511888951659
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 4 930064 930069 4194304 256 0 0 24 24 12928 0x7fca2f751900 0x7fc924235140 214915 214915 65536 917504 139932 17898568 12076511889024354 12076511889248365 12076511889378924 12076511889383012
5 3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 6 930064 930069 4194304 256 0 0 36 24 13632 0x7fca2f751800 0x7fc924235180 395129 395129 65536 1245184 187764 24126632 12076511889454855 12076511889648043 12076511889900362 12076511889970525
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 8 930064 930069 4194304 256 0 0 28 24 14080 0x7fca2f751700 0x7fc9242351c0 394163 394163 65536 983040 136843 17530748 12076511890016450 12076511890190761 12076511890441481 12076511890512944
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 10 930064 930069 4194304 256 0 0 24 24 14528 0x7fca2f751600 0x7fc924235200 224953 224953 65536 1048576 161417 20651260 12076511890543120 12076511890729320 12076511890867879 12076511890871450
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 12 930064 930069 4194304 256 0 0 24 24 14976 0x7fca2f751500 0x7fc924235240 219883 219883 65536 983040 148081 18955680 12076511890925862 12076511891112998 12076511891247078 12076511891250816
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 14 930064 930069 4194304 256 0 0 24 24 15424 0x7fca2f751400 0x7fc924235280 218281 218281 65536 1048576 146679 18771468 12076511891333450 12076511891507717 12076511891641796 12076511891645079
10 8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 16 930064 930069 4194304 256 0 0 28 24 16128 0x7fca2f751300 0x7fc9242352c0 407163 407163 65536 1572864 230007 29426828 12076511891699921 12076511891872996 12076511892132515 12076511892177309
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 18 930064 930069 4194304 256 0 0 28 24 16832 0x7fca2f751a00 0x7fc924235300 408841 408841 65536 1179648 158554 20265040 12076511892202747 12076511892399554 12076511892660993 12076511892702727
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 20 930064 930069 4194304 256 0 0 24 24 17536 0x7fca2f751900 0x7fc924235340 218443 218443 65536 1114112 161435 20666692 12076511892737542 12076511892913792 12076511893046912 12076511893050474
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 22 930064 930069 4194304 256 0 0 24 24 18240 0x7fca2f751800 0x7fc924235380 221425 221425 65536 1114112 156380 20042720 12076511893101348 12076511893284831 12076511893420990 12076511893424319
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 24 930064 930069 4194304 256 0 0 24 24 18944 0x7fca2f751700 0x7fc9242353c0 216971 216971 65536 1179648 164746 21076988 12076511893492636 12076511893661309 12076511893793309 12076511893796892
15 13 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 26 930064 930069 4194304 256 0 0 28 24 19904 0x7fca2f751600 0x7fc924235400 407969 407969 65536 1835008 255078 32648428 12076511893850391 12076511894026428 12076511894287227 12076511894357064
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 28 930064 930069 4194304 256 0 0 28 24 20608 0x7fca2f751500 0x7fc924235440 400515 400515 65536 1310720 178314 22809868 12076511894386819 12076511894574106 12076511894829305 12076511894897379
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 30 930064 930069 4194304 256 0 0 24 24 21312 0x7fca2f751400 0x7fc924235480 214529 214529 65536 1245184 175469 22446300 12076511894925291 12076511895117144 12076511895248984 12076511895252780
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 32 930064 930069 4194304 256 0 0 24 24 22016 0x7fca2f751300 0x7fc9242354c0 228443 228443 65536 1310720 183393 23483288 12076511895306129 12076511895481943 12076511895622103 12076511895625644
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 34 930064 930069 4194304 256 0 0 24 24 22720 0x7fca2f751a00 0x7fc924235500 212545 212545 65536 1310720 180330 23094592 12076511895693300 12076511895863062 12076511895993621 12076511895997115
20 18 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 36 930064 930069 4194304 256 0 0 28 24 23680 0x7fca2f751900 0x7fc924235540 402323 402323 65536 2097152 315221 40321040 12076511896052017 12076511896228820 12076511896485780 12076511896554371
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 38 930064 930069 4194304 256 0 0 28 24 24384 0x7fca2f751800 0x7fc924235580 402137 402137 65536 1441792 196188 25215192 12076511896580740 12076511896765619 12076511897023058 12076511897093123
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 40 930064 930069 4194304 256 0 0 24 24 25088 0x7fca2f751700 0x7fc9242355c0 214459 214459 65536 1376256 189903 24366844 12076511897118090 12076511897314897 12076511897445616 12076511897449086
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 42 930064 930069 4194304 256 0 0 24 24 25792 0x7fca2f751600 0x7fc924235600 213489 213489 65536 1507328 211954 27040156 12076511897503667 12076511897671695 12076511897802895 12076511897806370
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 44 930064 930069 4194304 256 0 0 24 24 26496 0x7fca2f751500 0x7fc924235640 217707 217707 65536 1441792 211624 27116764 12076511897873004 12076511898048014 12076511898180814 12076511898184754
25 23 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 46 930064 930069 4194304 256 0 0 28 24 27712 0x7fca2f751400 0x7fc924235680 391313 391313 65536 2359296 324312 41593648 12076511898232613 12076511898413933 12076511898665132 12076511898733505
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 48 930064 930069 4194304 256 0 0 28 24 28416 0x7fca2f751300 0x7fc9242356c0 407515 407515 65536 1572864 209927 26902472 12076511898761347 12076511898946251 12076511899206250 12076511899274792
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 50 930064 930069 4194304 256 0 0 24 24 29120 0x7fca2f751a00 0x7fc924235700 210249 210249 65536 1507328 207874 26606196 12076511899301962 12076511899492969 12076511899621769 12076511899625534
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 52 930064 930069 4194304 256 0 0 24 24 30080 0x7fca2f751900 0x7fc924235740 223187 223187 65536 1703936 235765 30251584 12076511899679174 12076511899847528 12076511899984647 12076511899988139
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 54 930064 930069 4194304 256 0 0 24 24 30784 0x7fca2f751800 0x7fc924235780 213337 213337 65536 1572864 215134 27578720 12076511900056145 12076511900222247 12076511900353606 12076511900357025
30 28 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 56 930064 930069 4194304 256 0 0 28 24 32000 0x7fca2f751700 0x7fc9242357c0 399979 399979 65536 2621440 369765 47301416 12076511900410374 12076511900578245 12076511900834084 12076511900901998
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 58 930064 930069 4194304 256 0 0 28 24 32960 0x7fca2f751600 0x7fc924235800 399761 399761 65536 1703936 231171 29615256 12076511900929039 12076511901116004 12076511901371523 12076511901440991
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 60 930064 930069 4194304 256 0 0 24 24 33920 0x7fca2f751500 0x7fc924235840 215987 215987 65536 1638400 229448 29354540 12076511901465827 12076511901650402 12076511901782241 12076511901785782
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 62 930064 930069 4194304 256 0 0 24 24 34880 0x7fca2f751400 0x7fc924235880 211777 211777 65536 1900544 269121 34406164 12076511901838020 12076511902013280 12076511902143680 12076511902147565
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 64 930064 930069 4194304 256 0 0 24 24 35840 0x7fca2f751300 0x7fc9242358c0 220899 220899 65536 1703936 228758 29330840 12076511902214981 12076511902383839 12076511902517119 12076511902520739
35 33 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 66 930064 930069 4194304 256 0 0 28 24 37312 0x7fca2f751a00 0x7fc924235900 399281 399281 65536 2883584 387449 49510472 12076511902574509 12076511902751518 12076511903008797 12076511903078166
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 68 930064 930069 4194304 256 0 0 28 24 38272 0x7fca2f751900 0x7fc924235940 398979 398979 65536 1835008 243929 31209696 12076511903105197 12076511903294556 12076511903549435 12076511903618011
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 70 930064 930069 4194304 256 0 0 24 24 39232 0x7fca2f751800 0x7fc924235980 217769 217769 65536 1769472 258399 33089216 12076511903646494 12076511903835514 12076511903969914 12076511903973512
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 72 930064 930069 4194304 256 0 0 24 24 40192 0x7fca2f751700 0x7fc9242359c0 224219 224219 65536 2097152 303544 38989148 12076511904035036 12076511904206873 12076511904344632 12076511904348249
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 74 930064 930069 4194304 256 0 0 24 24 41152 0x7fca2f751600 0x7fc924235a00 216753 216753 65536 1835008 254074 32467216 12076511904412989 12076511904576791 12076511904710871 12076511904714029
40 38 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 76 930064 930069 4194304 256 0 0 28 24 42624 0x7fca2f751500 0x7fc924235a40 408491 408491 65536 3145728 432511 55278432 12076511904766918 12076511904938550 12076511905201109 12076511905271396
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 78 930064 930069 4194304 256 0 0 28 24 43584 0x7fca2f751400 0x7fc924235a80 398857 398857 65536 1966080 262806 33632440 12076511905296563 12076511905484468 12076511905740147 12076511905807734
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 80 930064 930069 4194304 256 0 0 24 24 44544 0x7fca2f751300 0x7fc924235ac0 286747 286747 65536 1900544 261316 33522712 12076511905831949 12076511906025266 12076511906204306 12076511906208138
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 82 930064 930069 4194304 256 0 0 24 24 45760 0x7fca2f751a00 0x7fc924235b00 227329 227329 65536 2293760 308417 39638124 12076511906262089 12076511906438705 12076511906578545 12076511906582074
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 84 930064 930069 4194304 256 0 0 24 24 46720 0x7fca2f751900 0x7fc924235b40 215867 215867 65536 1966080 270023 34543308 12076511906646875 12076511906812304 12076511906945263 12076511906948846
45 43 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 86 930064 930069 4194304 256 0 0 28 24 48448 0x7fca2f751800 0x7fc924235b80 409825 409825 65536 3407872 462030 59205132 12076511907007425 12076511907177902 12076511907441742 12076511907511072
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 88 930064 930069 4194304 256 0 0 28 24 49408 0x7fca2f751700 0x7fc924235bc0 401483 401483 65536 2097152 278549 35578596 12076511907539595 12076511907722381 12076511907980460 12076511908047580
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 90 930064 930069 4194304 256 0 0 24 24 50368 0x7fca2f751600 0x7fc924235c00 210585 210585 65536 2031616 285951 36567104 12076511908075532 12076511908262059 12076511908391018 12076511908394756
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 92 930064 930069 4194304 256 0 0 24 24 51584 0x7fca2f751500 0x7fc924235c40 223627 223627 65536 2490368 349329 44598892 12076511908446612 12076511908618537 12076511908757097 12076511908760667
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 94 930064 930069 4194304 256 0 0 24 24 52544 0x7fca2f751400 0x7fc924235c80 216289 216289 65536 2097152 290541 37131692 12076511908827100 12076511908994536 12076511909127016 12076511909130975
50 48 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 96 930064 930069 4194304 256 0 0 28 24 54272 0x7fca2f751300 0x7fc924235cc0 416907 416907 65536 3670016 488244 62467976 12076511909184104 12076511909367655 12076511909636934 12076511909703851
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 98 930064 930069 4194304 256 0 0 28 24 55488 0x7fca2f751a00 0x7fc924235d00 403089 403089 65536 2228224 298418 38285100 12076511909731803 12076511909914373 12076511910173092 12076511910242703
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 100 930064 930069 4194304 256 0 0 24 24 56704 0x7fca2f751900 0x7fc924235d40 218979 218979 65536 2162688 309702 39589660 12076511910270575 12076511910453251 12076511910587811 12076511910591262
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 102 930064 930069 4194304 256 0 0 24 24 58176 0x7fca2f751800 0x7fc924235d80 231753 231753 65536 2686976 388230 49683460 12076511910646695 12076511910809410 12076511910952929 12076511910956671
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 104 930064 930069 4194304 256 0 0 24 24 59392 0x7fca2f751700 0x7fc924235dc0 220643 220643 65536 2228224 324455 41538656 12076511911028535 12076511911192608 12076511911328288 12076511911332080
55 53 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 106 930064 930069 4194304 256 0 0 28 24 61376 0x7fca2f751600 0x7fc924235e00 412609 412609 65536 3932160 519403 66408384 12076511911386070 12076511911558847 12076511911824286 12076511911891670
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 108 930064 930069 4194304 256 0 0 28 24 62592 0x7fca2f751500 0x7fc924235e40 400643 400643 65536 2359296 328434 42024304 12076511911918871 12076511912111165 12076511912368444 12076511912435522
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 110 930064 930069 4194304 256 0 0 24 24 63808 0x7fca2f751400 0x7fc924235e80 211377 211377 65536 2293760 320544 41035888 12076511912460719 12076511912643003 12076511912772603 12076511912776316
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 112 930064 930069 4194304 256 0 0 24 24 65280 0x7fca2f751300 0x7fc924235ec0 221523 221523 65536 2883584 420092 53683000 12076511912829034 12076511913005402 12076511913143162 12076511913146715
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 114 930064 930069 4194304 256 0 0 24 24 66496 0x7fca2f751a00 0x7fc924235f00 216569 216569 65536 2359296 327023 41842148 12076511913216826 12076511913384281 12076511913517240 12076511913520871
60 58 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 116 930064 930069 4194304 256 0 0 28 24 68480 0x7fca2f751900 0x7fc924235f40 409011 409011 65536 4194304 597281 76594840 12076511913571986 12076511913744920 12076511914009559 12076511914076755
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 118 930064 930069 4194304 256 0 0 28 24 69696 0x7fca2f751800 0x7fc924235f80 401265 401265 65536 2490368 328494 41973448 12076511914108775 12076511914287958 12076511914545557 12076511914586533
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 120 930064 930069 4194304 256 0 0 24 24 70912 0x7fca2f751700 0x7fc924235fc0 216323 216323 65536 2424832 336930 43132840 12076511914618433 12076511914795956 12076511914929075 12076511914932697
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 122 930064 930069 4194304 256 0 0 24 24 72384 0x7fca2f751600 0x7fc924236000 225233 225233 65536 3080192 492289 63022112 12076511914986247 12076511915167795 12076511915307474 12076511915311372
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 124 930064 930069 4194304 256 0 0 24 24 73600 0x7fca2f751500 0x7fc924236040 226195 226195 65536 2490368 379413 48573264 12076511915377434 12076511915541393 12076511915681393 12076511915685147
65 63 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 126 930064 930069 4194304 256 0 0 28 24 75840 0x7fca2f751400 0x7fc924236080 409569 409569 65536 4456448 588726 75217880 12076511915737995 12076511915909872 12076511916174351 12076511916242804
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 128 930064 930069 4194304 256 0 0 28 24 77056 0x7fca2f751300 0x7fc9242360c0 397867 397867 65536 2621440 348743 44602924 12076511916267891 12076511916455310 12076511916711149 12076511916778360
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 130 930064 930069 4194304 256 0 0 24 24 78272 0x7fca2f751a00 0x7fc924236100 212241 212241 65536 2555904 378392 48366064 12076511916805401 12076511916986508 12076511917116748 12076511917120667
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 132 930064 930069 4194304 256 0 0 24 24 80000 0x7fca2f751900 0x7fc924236140 231443 231443 65536 3276800 451179 57802376 12076511917178495 12076511917344587 12076511917488747 12076511917492489
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 134 930064 930069 4194304 256 0 0 24 24 81216 0x7fca2f751800 0x7fc924236180 218057 218057 65536 2621440 371758 47504748 12076511917559233 12076511917725706 12076511917859785 12076511917863429
70 68 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 136 930064 930069 4194304 256 0 0 28 24 83456 0x7fca2f751700 0x7fc9242361c0 420315 420315 65536 4718592 625771 80053288 12076511917916287 12076511918096264 12076511918368424 12076511918436565
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 138 930064 930069 4194304 256 0 0 28 24 84928 0x7fca2f751600 0x7fc924236200 402433 402433 65536 2752512 361304 46192032 12076511918465509 12076511918646023 12076511918904262 12076511918971530
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 140 930064 930069 4194304 256 0 0 24 24 86400 0x7fca2f751500 0x7fc924236240 225723 225723 65536 2686976 437108 56026900 12076511918998029 12076511919191141 12076511919330660 12076511919334635
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 142 930064 930069 4194304 256 0 0 24 24 88128 0x7fca2f751400 0x7fc924236280 241321 241321 65536 3473408 565919 72576752 12076511919389467 12076511919553859 12076511919704099 12076511919707699
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 144 930064 930069 4194304 256 0 0 24 24 89600 0x7fca2f751300 0x7fc9242362c0 220363 220363 65536 2752512 410661 52599332 12076511919790784 12076511919954818 12076511920090978 12076511920095461
75 73 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 146 930064 930069 4194304 256 0 0 28 24 92096 0x7fca2f751a00 0x7fc924236300 418153 418153 65536 4980736 696325 89348908 12076511920149722 12076511920324577 12076511920595136 12076511920644372
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 148 930064 930069 4194304 256 0 0 28 24 93568 0x7fca2f751900 0x7fc924236340 402755 402755 65536 2883584 402521 51417348 12076511920673536 12076511920850975 12076511921110174 12076511921159640
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 150 930064 930069 4194304 256 0 0 24 24 95040 0x7fca2f751800 0x7fc924236380 214289 214289 65536 2818048 399571 51181284 12076511921186851 12076511921369533 12076511921501213 12076511921504992
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 152 930064 930069 4194304 256 0 0 24 24 96768 0x7fca2f751700 0x7fc9242363c0 256115 256115 65536 3670016 560285 71675928 12076511921557841 12076511921722332 12076511921881051 12076511921884839
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 154 930064 930069 4194304 256 0 0 24 24 98240 0x7fca2f751600 0x7fc924236400 226265 226265 65536 2883584 408569 52243256 12076511921952375 12076511922123290 12076511922262970 12076511922267110
80 78 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 156 930064 930069 4194304 256 0 0 28 24 100736 0x7fca2f751500 0x7fc924236440 413747 413747 65536 5177344 687052 88025392 12076511922320990 12076511922487449 12076511922755928 12076511922804820
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 158 930064 930069 4194304 256 0 0 28 24 102208 0x7fca2f751400 0x7fc924236480 398081 398081 65536 3014656 415416 53193000 12076511922831530 12076511923015127 12076511923271607 12076511923323094
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 160 930064 930069 4194304 256 0 0 24 24 103680 0x7fca2f751300 0x7fc9242364c0 222539 222539 65536 2949120 478928 61249356 12076511923350325 12076511923538966 12076511923676885 12076511923680660
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 162 930064 930069 4194304 256 0 0 24 24 105664 0x7fca2f751a00 0x7fc924236500 262593 262593 65536 3866624 543605 69595000 12076511923736043 12076511923898004 12076511924062644 12076511924066507
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 164 930064 930069 4194304 256 0 0 24 24 107136 0x7fca2f751900 0x7fc924236540 223795 223795 65536 3014656 455697 58262024 12076511924133812 12076511924298643 12076511924436882 12076511924440773
85 83 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 166 930064 930069 4194304 256 0 0 28 24 109888 0x7fca2f751800 0x7fc924236580 412209 412209 65536 5439488 716896 91691208 12076511924494824 12076511924659922 12076511924926801 12076511924948628
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 168 930064 930069 4194304 256 0 0 28 24 111360 0x7fca2f751700 0x7fc9242365c0 403699 403699 65536 3145728 450971 57650148 12076511924994974 12076511925164880 12076511925425359 12076511925473554
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 170 930064 930069 4194304 256 0 0 24 24 112832 0x7fca2f751600 0x7fc924236600 224801 224801 65536 3080192 495442 63423164 12076511925498902 12076511925684718 12076511925823278 12076511925827062
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 172 930064 930069 4194304 256 0 0 24 24 114816 0x7fca2f751500 0x7fc924236640 276835 276835 65536 4063232 568762 72684956 12076511925879870 12076511926053517 12076511926227436 12076511926231464
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 174 930064 930069 4194304 256 0 0 24 24 116288 0x7fca2f751400 0x7fc924236680 226881 226881 65536 3145728 467020 59818232 12076511926299030 12076511926464555 12076511926604715 12076511926608596
90 88 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 176 930064 930069 4194304 256 0 0 28 24 119040 0x7fca2f751300 0x7fc9242366c0 406683 406683 65536 5701632 806922 103299876 12076511926661895 12076511926832074 12076511927095753 12076511927146216
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 178 930064 930069 4194304 256 0 0 28 24 120768 0x7fca2f751a00 0x7fc924236700 406433 406433 65536 3276800 437380 55872072 12076511927175871 12076511927356712 12076511927618631 12076511927668197
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 180 930064 930069 4194304 256 0 0 24 24 122496 0x7fca2f751900 0x7fc924236740 228755 228755 65536 3211264 460325 58884540 12076511927695407 12076511927874471 12076511928016230 12076511928020182
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 182 930064 930069 4194304 256 0 0 24 24 124736 0x7fca2f751800 0x7fc924236780 289169 289169 65536 4259840 581188 74298136 12076511928074332 12076511928246629 12076511928429509 12076511928433621
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 184 930064 930069 4194304 256 0 0 24 24 126464 0x7fca2f751700 0x7fc9242367c0 227115 227115 65536 3276800 505912 64725060 12076511928499112 12076511928663268 12076511928803267 12076511928807256
95 93 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 186 930064 930069 4194304 256 0 0 20 24 127936 0x7fca2f751600 0x7fc924236800 410673 410673 65536 7733248 975275 124837252 12076511928862118 12076511929034146 12076511929300706 12076511929349484
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 188 930064 930069 4194304 256 0 0 28 24 129664 0x7fca2f751500 0x7fc924236840 398331 398331 65536 3407872 457792 58617684 12076511929378378 12076511929559745 12076511929816864 12076511929866285
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 190 930064 930069 4194304 256 0 0 24 24 131392 0x7fca2f751400 0x7fc924236880 225841 225841 65536 3342336 480358 61506388 12076511929890641 12076511930083743 12076511930223422 12076511930227277
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 192 930064 930069 4194304 256 0 0 24 24 133632 0x7fca2f751300 0x7fc9242368c0 301395 301395 65536 4456448 637852 81949632 12076511930282259 12076511930449022 12076511930640701 12076511930688024
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 194 930064 930069 4194304 256 0 0 24 24 135360 0x7fca2f751a00 0x7fc924236900 220737 220737 65536 3538944 574538 73514252 12076511930729371 12076511930894780 12076511931030780 12076511931034739
100 98 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 196 930064 930069 4194304 256 0 0 20 24 136832 0x7fca2f751900 0x7fc924236940 435139 435139 65536 8978432 1128256 144640484 12076511931088339 12076511931256539 12076511931540218 12076511931586986
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 198 930064 930069 4194304 256 0 0 28 24 138560 0x7fca2f751800 0x7fc924236980 396241 396241 65536 3670016 502907 64221436 12076511931612935 12076511931792537 12076511932049016 12076511932070746
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 200 930064 930069 4194304 256 0 0 24 24 140288 0x7fca2f751700 0x7fc9242369c0 220683 220683 65536 3604480 548357 70137088 12076511932125167 12076511932292215 12076511932428535 12076511932432299
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 202 930064 930069 4194304 256 0 0 24 24 142784 0x7fca2f751600 0x7fc924236a00 330929 330929 65536 4849664 756734 96932892 12076511932486099 12076511932653654 12076511932863893 12076511932911730
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 204 930064 930069 4194304 256 0 0 24 24 144768 0x7fca2f751500 0x7fc924236a40 231883 231883 65536 3801088 634788 81172200 12076511932953278 12076511933124212 12076511933268372 12076511933272291
105 103 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 206 930064 930069 4194304 256 0 0 20 24 145728 0x7fca2f751400 0x7fc924236a80 470385 470385 65536 14548992 1827450 233846504 12076511933326141 12076511933504531 12076511933811570 12076511933858592
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 208 930064 930069 4194304 256 0 0 28 24 147712 0x7fca2f751300 0x7fc924236ac0 409011 409011 65536 3932160 517874 66533164 12076511933887846 12076511934061329 12076511934326608 12076511934374231
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 210 930064 930069 4194304 256 0 0 24 24 149696 0x7fca2f751a00 0x7fc924236b00 223657 223657 65536 3866624 563998 72189852 12076511934403395 12076511934585967 12076511934724367 12076511934728099
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 212 930064 930069 4194304 256 0 0 24 24 152192 0x7fca2f751900 0x7fc924236b40 356411 356411 65536 5242880 770082 98788036 12076511934781138 12076511934946606 12076511935174765 12076511935225434
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 214 930064 930069 4194304 256 0 0 24 24 154176 0x7fca2f751800 0x7fc924236b80 222401 222401 65536 4063232 622486 79775516 12076511935268094 12076511935435724 12076511935573484 12076511935577269
110 108 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 216 930064 930069 4194304 256 0 0 20 24 155648 0x7fca2f751700 0x7fc924236bc0 502523 502523 65536 10027008 1260314 161428400 12076511935627783 12076511935807403 12076511936137002 12076511936165222
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 218 930064 930069 4194304 256 0 0 28 24 157632 0x7fca2f751600 0x7fc924236c00 404241 404241 65536 4194304 554570 71021236 12076511936213362 12076511936380095 12076511936641055 12076511936693585
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 220 930064 930069 4194304 256 0 0 24 24 159616 0x7fca2f751500 0x7fc924236c40 214435 214435 65536 4128768 574408 73434388 12076511936715967 12076511936901373 12076511937034492 12076511937038316
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 222 930064 930069 4194304 256 0 0 24 24 162368 0x7fca2f751400 0x7fc924236c80 431513 431513 65536 5636096 780436 99873568 12076511937093219 12076511937271132 12076511937549051 12076511937596485
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 224 930064 930069 4194304 256 0 0 24 24 164608 0x7fca2f751300 0x7fc924236cc0 223707 223707 65536 4587520 658096 84300796 12076511937634145 12076511937800090 12076511937937690 12076511937941126
115 113 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 226 930064 930069 4194304 256 0 0 20 24 166336 0x7fca2f751a00 0x7fc924236d00 572249 572249 65536 11075584 1390692 177990324 12076511937993183 12076511938171609 12076511938547608 12076511938595793
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 228 930064 930069 4194304 256 0 0 28 24 168576 0x7fca2f751900 0x7fc924236d40 400499 400499 65536 4718592 644940 82542628 12076511938620409 12076511938811127 12076511939070486 12076511939120580
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 230 930064 930069 4194304 256 0 0 24 24 170816 0x7fca2f751800 0x7fc924236d80 219817 219817 65536 4653056 730814 93608432 12076511939144023 12076511939337686 12076511939474485 12076511939478065
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 232 930064 930069 4194304 256 0 0 24 24 174080 0x7fca2f751700 0x7fc924236dc0 438059 438059 65536 6422528 911676 116615924 12076511939534369 12076511939696244 12076511939976084 12076511940024721
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 234 930064 930069 4194304 256 0 0 24 24 176576 0x7fca2f751600 0x7fc924236e00 226697 226697 65536 5111808 822125 105295488 12076511940066098 12076511940235283 12076511940376722 12076511940380173
120 118 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 236 930064 930069 4194304 256 0 0 20 24 177792 0x7fca2f751500 0x7fc924236e40 644371 644371 65536 15007744 1885121 241036332 12076511940434013 12076511940600562 12076511941023920 12076511941071419
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 238 930064 930069 4194304 256 0 0 28 24 180288 0x7fca2f751400 0x7fc924236e80 415625 415625 65536 5242880 723513 92529184 12076511941097848 12076511941291920 12076511941562799 12076511941610491
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 240 930064 930069 4194304 256 0 0 24 24 182784 0x7fca2f751300 0x7fc924236ec0 226347 226347 65536 5177344 837217 107044760 12076511941640758 12076511941817838 12076511941958318 12076511941961955
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 242 930064 930069 4194304 256 0 0 24 24 186304 0x7fca2f751a00 0x7fc924236f00 487145 487145 65536 7208960 1038969 132954000 12076511942025774 12076511942189677 12076511942505356 12076511942551652
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 244 930064 930069 4194304 256 0 0 24 24 189312 0x7fca2f751900 0x7fc924236f40 244347 244347 65536 6160384 919610 117851268 12076511942588781 12076511942754635 12076511942907275 12076511942910770
125 123 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 246 930064 930069 4194304 256 0 0 20 24 190784 0x7fca2f751800 0x7fc924236f80 783393 783393 65536 17104896 2147380 274723160 12076511942963177 12076511943145514 12076511943662473 12076511943711880
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 248 930064 930069 4194304 256 0 0 28 24 193792 0x7fca2f751700 0x7fc924236fc0 453939 453939 65536 6291456 838704 107318240 12076511943743128 12076511943928712 12076511944224391 12076511944273364
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 250 930064 930069 4194304 256 0 0 24 24 196800 0x7fca2f751600 0x7fc924237000 246497 246497 65536 6225920 930537 119161908 12076511944306987 12076511944479590 12076511944634950 12076511944638363
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 252 930064 930069 4194304 256 0 0 24 24 201088 0x7fca2f751500 0x7fc924237040 592803 592803 65536 8781824 1258002 160492552 12076511944693806 12076511944877029 12076511945262308 12076511945309502
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 254 930064 930069 4194304 256 0 0 24 24 204608 0x7fca2f751400 0x7fc924237080 278393 278393 65536 7208960 1068025 136737860 12076511945355698 12076511945523427 12076511945700706 12076511945704056
130 128 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 256 930064 930069 4194304 256 0 0 20 24 206080 0x7fca2f751300 0x7fc9242370c0 925627 925627 65536 19202048 2413930 309449300 12076511945756593 12076511945931586 12076511946542464 12076511946592348
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 258 930064 930069 4194304 256 0 0 28 24 209600 0x7fca2f751a00 0x7fc924237100 499953 499953 65536 7340032 1042709 133734804 12076511946623356 12076511946809183 12076511947137662 12076511947186784
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 260 930064 930069 4194304 256 0 0 24 24 213120 0x7fca2f751900 0x7fc924237140 283635 283635 65536 7274496 1073972 137482588 12076511947218843 12076511947409021 12076511947587901 12076511947591426
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 262 930064 930069 4194304 256 0 0 24 24 218176 0x7fca2f751800 0x7fc924237180 697849 697849 65536 10354688 1479623 190320272 12076511947643854 12076511947817180 12076511948273659 12076511948321214
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 264 930064 930069 4194304 256 0 0 24 24 222208 0x7fca2f751700 0x7fc9242371c0 366731 366731 65536 8257536 1194526 152993784 12076511948363783 12076511948532218 12076511948767577 12076511948814732
135 133 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 266 930064 930069 4194304 256 0 0 20 24 223936 0x7fca2f751600 0x7fc924237200 1074881 1074881 65536 21299200 2670862 341680532 12076511948842794 12076511949038296 12076511949747894 12076511949800516
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 268 930064 930069 4194304 256 0 0 28 24 227968 0x7fca2f751500 0x7fc924237240 565907 565907 65536 8388608 1199958 153494464 12076511949832185 12076511950037973 12076511950409812 12076511950459481
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 270 930064 930069 4194304 256 0 0 24 24 232000 0x7fca2f751400 0x7fc924237280 317777 317777 65536 8323072 1262083 161524352 12076511950485390 12076511950668691 12076511950872051 12076511950919667
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 272 930064 930069 4194304 256 0 0 24 24 237824 0x7fca2f751300 0x7fc9242372c0 801691 801691 65536 11927552 1637757 208842428 12076511950948100 12076511951133170 12076511951658129 12076511951708214
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 274 930064 930069 4194304 256 0 0 24 24 242368 0x7fca2f751a00 0x7fc924237300 349633 349633 65536 9306112 1431268 183218216 12076511951749301 12076511951915728 12076511952140847 12076511952189489
140 138 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 276 930064 930069 4194304 256 0 0 20 24 243584 0x7fca2f751900 0x7fc924237340 1207459 1207459 65536 29163520 3650139 467426916 12076511952219866 12076511952400686 12076511953199884 12076511953268116
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 278 930064 930069 4194304 256 0 0 28 24 248128 0x7fca2f751800 0x7fc924237380 671633 671633 65536 9437184 1317261 168392776 12076511953297030 12076511953480523 12076511953924522 12076511953992293
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 280 930064 930069 4194304 256 0 0 24 24 252672 0x7fca2f751700 0x7fc9242373c0 354315 354315 65536 9371648 1410177 180572968 12076511954018451 12076511954226281 12076511954453800 12076511954523301
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 282 930064 930069 4194304 256 0 0 24 24 259264 0x7fca2f751600 0x7fc924237400 910129 910129 65536 13500416 1962408 250402000 12076511954557334 12076511954726919 12076511955325957 12076511955396034
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 284 930064 930069 4194304 256 0 0 24 24 264832 0x7fca2f751500 0x7fc924237440 417587 417587 65536 11403264 1738015 222515428 12076511955443763 12076511955611237 12076511955879876 12076511955948001
145 143 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 286 930064 930069 4194304 256 0 0 20 24 266304 0x7fca2f751400 0x7fc924237480 1486641 1486641 65536 33357824 4179073 534645340 12076511955978818 12076511956168035 12076511957152352 12076511957222602
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 288 930064 930069 4194304 256 0 0 28 24 271872 0x7fca2f751300 0x7fc9242374c0 778755 778755 65536 11534336 1602986 204658396 12076511957255102 12076511957436511 12076511957951710 12076511958023101
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 290 930064 930069 4194304 256 0 0 24 24 277440 0x7fca2f751a00 0x7fc924237500 421577 421577 65536 11534336 1691806 216538116 12076511958055892 12076511958240029 12076511958512668 12076511958581379
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 292 930064 930069 4194304 256 0 0 12 24 279936 0x7fca2f751900 0x7fc924237540 1126115 1126115 65536 19267584 2426553 310501124 12076511958612547 12076511958796187 12076511959535065 12076511959604733
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 294 930064 930069 4194304 256 0 0 24 24 286528 0x7fca2f751800 0x7fc924237580 488993 488993 65536 13500416 2120242 271554024 12076511959645268 12076511959811544 12076511960128823 12076511960199409
150 148 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 296 930064 930069 4194304 256 0 0 20 24 288000 0x7fca2f751700 0x7fc9242375c0 1769259 1769259 65536 37552128 4685733 601539424 12076511960228563 12076511960409302 12076511961581299 12076511961650398
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 298 930064 930069 4194304 256 0 0 32 24 294592 0x7fca2f751600 0x7fc924237600 922025 922025 65536 13631488 1876067 240866692 12076511961685653 12076511961856178 12076511962467856 12076511962538400
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 300 930064 930069 4194304 256 0 0 24 24 301184 0x7fca2f751500 0x7fc924237640 494651 494651 65536 13631488 2150490 275254876 12076511962572152 12076511962761455 12076511963082254 12076511963150288
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 302 930064 930069 4194304 256 0 0 12 24 304960 0x7fca2f751400 0x7fc924237680 1336529 1336529 65536 21692416 2744730 351517752 12076511963183089 12076511963364653 12076511964243051 12076511964311538
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 304 930064 930069 4194304 256 0 0 24 24 313600 0x7fca2f751300 0x7fc9242376c0 628915 628915 65536 17694720 2732233 349748404 12076511964358425 12076511964525450 12076511964935369 12076511965009797
155 153 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 306 930064 930069 4194304 256 0 0 20 24 314816 0x7fca2f751a00 0x7fc924237700 2331993 2331993 65536 57475072 7196580 920856128 12076511965034543 12076511965224808 12076511966772163 12076511966841624
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 308 930064 930069 4194304 256 0 0 20 24 317568 0x7fca2f751900 0x7fc924237740 1201707 1201707 65536 19660800 2468542 315845476 12076511966874175 12076511967057922 12076511967853440 12076511967923116
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 310 930064 930069 4194304 256 0 0 12 24 320320 0x7fca2f751800 0x7fc924237780 639713 639713 65536 20381696 2569368 328948860 12076511967950948 12076511968139039 12076511968553118 12076511968620794
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 312 930064 930069 4194304 256 0 0 12 24 324096 0x7fca2f751700 0x7fc9242377c0 1757275 1757275 65536 28704768 3611254 462516792 12076511968649247 12076511968827997 12076511969986713 12076511970056434
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 314 930064 930069 4194304 256 0 0 12 24 328896 0x7fca2f751600 0x7fc924237800 1199305 1199305 65536 36634624 4670974 597989840 12076511970098522 12076511970267193 12076511971053910 12076511971122327
160 158 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 316 930064 930069 4194304 256 0 0 20 24 330112 0x7fca2f751500 0x7fc924237840 4584587 4584587 65536 105840640 13245157 1694951680 12076511971155789 12076511971342389 12076511974393100 12076511974463552
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 318 930064 930069 4194304 256 0 0 20 24 332864 0x7fca2f751400 0x7fc924237880 2324257 2324257 65536 38535168 4833917 618273068 12076511974498156 12076511974677739 12076511976219495 12076511976287715
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 320 930064 930069 4194304 256 0 0 12 24 335616 0x7fca2f751300 0x7fc9242378c0 1204803 1204803 65536 39124992 4912544 628724484 12076511976320436 12076511976494854 12076511977284291 12076511977352967
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 322 930064 930069 4194304 256 0 0 12 24 339392 0x7fca2f751a00 0x7fc924237900 3442921 3442921 65536 55771136 7008728 896749468 12076511977385778 12076511977565891 12076511979848124 12076511979917307
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 324 930064 930069 4194304 256 0 0 12 24 344192 0x7fca2f751900 0x7fc924237940 2323203 2323203 65536 72548352 9116143 1166622420 12076511979964344 12076511980139483 12076511981674998 12076511981745076
165 163 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 326 930064 930069 4194304 256 0 0 20 24 345408 0x7fca2f751800 0x7fc924237980 9088465 9088465 65536 210698240 26349453 3372603416 12076511981779300 12076511981959157 12076511988015459 12076511988084058
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 328 930064 930069 4194304 256 0 0 20 24 348160 0x7fca2f751700 0x7fc9242379c0 4571627 4571627 65536 76283904 9555771 1222719012 12076511988118041 12076511988304738 12076511991346489 12076511991416486
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 330 930064 930069 4194304 256 0 0 12 24 350912 0x7fca2f751600 0x7fc924237a00 2329897 2329897 65536 77398016 9708865 1242502468 12076511991448165 12076511991636248 12076511993176244 12076511993247773
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 332 930064 930069 4194304 256 0 0 12 24 0 0x7fca2f751500 0x7fc924237a40 6812827 6812827 65536 110821376 13891448 1777823056 12076511993277087 12076511993464403 12076511997993349 12076511998064773
@@ -0,0 +1,168 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,grd,Workgroup_Size,LDS_Per_Workgroup,scr,vgpr,SGPR,fbar,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"__amd_rocclr_fillBuffer.kd",0,0,0,931859,931864,33554432,256,0,0,8,32,6464,0x0,0x7fa2f4604180,0,0,0,12076538010346649,12076538250264836,12076538250588515,12076538250679036
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,931859,931864,32768,256,0,0,24,24,12480,0x0,0x7fa2f4635100,0,0,0,12076538265124998,12076538265420263,12076538265426823,12076538265432269
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,931859,931864,4194304,256,0,0,24,24,12928,0x7fa40034b900,0x7fa2f4635140,0,0,0,12076538265550439,12076538265717702,12076538265859462,12076538265863321
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,931859,931864,4194304,256,0,0,36,24,13632,0x7fa40034b800,0x7fa2f4635180,0,0,0,12076538265960702,12076538266141701,12076538266393860,12076538266436517
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,931859,931864,4194304,256,0,0,28,24,14080,0x7fa40034b700,0x7fa2f46351c0,0,0,0,12076538266503442,12076538266670019,12076538266926658,12076538266967535
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,931859,931864,4194304,256,0,0,24,24,14528,0x7fa40034b600,0x7fa2f4635200,0,0,0,12076538267047314,12076538267222337,12076538267360257,12076538267364083
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,931859,931864,4194304,256,0,0,24,24,14976,0x7fa40034b500,0x7fa2f4635240,0,0,0,12076538267415248,12076538267602176,12076538267739935,12076538267743599
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,931859,931864,4194304,256,0,0,24,24,15424,0x7fa40034b400,0x7fa2f4635280,0,0,0,12076538267827625,12076538267995454,12076538268126494,12076538268130448
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,931859,931864,4194304,256,0,0,28,24,16128,0x7fa40034b300,0x7fa2f46352c0,0,0,0,12076538268181353,12076538268362973,12076538268622332,12076538268663349
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,931859,931864,4194304,256,0,0,28,24,16832,0x7fa40034ba00,0x7fa2f4635300,0,0,0,12076538268686803,12076538268868572,12076538269127131,12076538269166916
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,931859,931864,4194304,256,0,0,24,24,17536,0x7fa40034b900,0x7fa2f4635340,0,0,0,12076538269192474,12076538269382810,12076538269514169,12076538269517819
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,931859,931864,4194304,256,0,0,24,24,18240,0x7fa40034b800,0x7fa2f4635380,0,0,0,12076538269567952,12076538269753208,12076538269891448,12076538269895021
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,931859,931864,4194304,256,0,0,24,24,18944,0x7fa40034b700,0x7fa2f46353c0,0,0,0,12076538269962386,12076538270134807,12076538270265047,12076538270268876
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,931859,931864,4194304,256,0,0,28,24,19904,0x7fa40034b600,0x7fa2f4635400,0,0,0,12076538270321033,12076538270498326,12076538270757205,12076538270797219
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,931859,931864,4194304,256,0,0,28,24,20608,0x7fa40034b500,0x7fa2f4635440,0,0,0,12076538270822295,12076538271003764,12076538271258963,12076538271299673
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,931859,931864,4194304,256,0,0,24,24,21312,0x7fa40034b400,0x7fa2f4635480,0,0,0,12076538271323718,12076538271506323,12076538271641682,12076538271644946
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,931859,931864,4194304,256,0,0,24,24,22016,0x7fa40034b300,0x7fa2f46354c0,0,0,0,12076538271694187,12076538271869041,12076538272006321,12076538272009935
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,931859,931864,4194304,256,0,0,24,24,22720,0x7fa40034ba00,0x7fa2f4635500,0,0,0,12076538272074865,12076538272239600,12076538272378160,12076538272381756
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,931859,931864,4194304,256,0,0,28,24,23680,0x7fa40034b900,0x7fa2f4635540,0,0,0,12076538272431419,12076538272607279,12076538272864878,12076538272904719
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,931859,931864,4194304,256,0,0,28,24,24384,0x7fa40034b800,0x7fa2f4635580,0,0,0,12076538272928944,12076538273125837,12076538273384556,12076538273423935
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,931859,931864,4194304,256,0,0,24,24,25088,0x7fa40034b700,0x7fa2f46355c0,0,0,0,12076538273449142,12076538273631755,12076538273765195,12076538273768696
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,931859,931864,4194304,256,0,0,24,24,25792,0x7fa40034b600,0x7fa2f4635600,0,0,0,12076538273818950,12076538273995914,12076538274130634,12076538274134256
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,931859,931864,4194304,256,0,0,24,24,26496,0x7fa40034b500,0x7fa2f4635640,0,0,0,12076538274197914,12076538274360873,12076538274497192,12076538274500668
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,931859,931864,4194304,256,0,0,28,24,27712,0x7fa40034b400,0x7fa2f4635680,0,0,0,12076538274549949,12076538274723752,12076538274982151,12076538275023490
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,931859,931864,4194304,256,0,0,28,24,28416,0x7fa40034b300,0x7fa2f46356c0,0,0,0,12076538275049008,12076538275232710,12076538275489029,12076538275529341
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,931859,931864,4194304,256,0,0,24,24,29120,0x7fa40034ba00,0x7fa2f4635700,0,0,0,12076538275553195,12076538275731108,12076538275862628,12076538275866108
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,931859,931864,4194304,256,0,0,24,24,30080,0x7fa40034b900,0x7fa2f4635740,0,0,0,12076538275918645,12076538276101667,12076538276236066,12076538276239823
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,931859,931864,4194304,256,0,0,24,24,30784,0x7fa40034b800,0x7fa2f4635780,0,0,0,12076538276302399,12076538276461986,12076538276595585,12076538276599061
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,931859,931864,4194304,256,0,0,28,24,32000,0x7fa40034b700,0x7fa2f46357c0,0,0,0,12076538276648433,12076538276830304,12076538277089983,12076538277131201
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,931859,931864,4194304,256,0,0,28,24,32960,0x7fa40034b600,0x7fa2f4635800,0,0,0,12076538277155907,12076538277346463,12076538277601182,12076538277641831
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,931859,931864,4194304,256,0,0,24,24,33920,0x7fa40034b500,0x7fa2f4635840,0,0,0,12076538277666126,12076538277845821,12076538277978780,12076538277982244
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,931859,931864,4194304,256,0,0,24,24,34880,0x7fa40034b400,0x7fa2f4635880,0,0,0,12076538278033499,12076538278212860,12076538278351579,12076538278355388
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,931859,931864,4194304,256,0,0,24,24,35840,0x7fa40034b300,0x7fa2f46358c0,0,0,0,12076538278416802,12076538278577018,12076538278708218,12076538278711821
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,931859,931864,4194304,256,0,0,28,24,37312,0x7fa40034ba00,0x7fa2f4635900,0,0,0,12076538278762766,12076538278934137,12076538279198616,12076538279240554
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,931859,931864,4194304,256,0,0,28,24,38272,0x7fa40034b900,0x7fa2f4635940,0,0,0,12076538279264248,12076538279444855,12076538279698935,12076538279739202
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,931859,931864,4194304,256,0,0,24,24,39232,0x7fa40034b800,0x7fa2f4635980,0,0,0,12076538279762585,12076538279945174,12076538280084373,12076538280088041
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,931859,931864,4194304,256,0,0,24,24,40192,0x7fa40034b700,0x7fa2f46359c0,0,0,0,12076538280141701,12076538280315893,12076538280458612,12076538280462397
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,931859,931864,4194304,256,0,0,24,24,41152,0x7fa40034b600,0x7fa2f4635a00,0,0,0,12076538280526396,12076538280686451,12076538280820051,12076538280823779
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,931859,931864,4194304,256,0,0,28,24,42624,0x7fa40034b500,0x7fa2f4635a40,0,0,0,12076538280872360,12076538281071570,12076538281335089,12076538281376478
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,931859,931864,4194304,256,0,0,28,24,43584,0x7fa40034b400,0x7fa2f4635a80,0,0,0,12076538281400713,12076538281579888,12076538281838927,12076538281879283
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,931859,931864,4194304,256,0,0,24,24,44544,0x7fa40034b300,0x7fa2f4635ac0,0,0,0,12076538281903658,12076538282089486,12076538282225486,12076538282229745
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,931859,931864,4194304,256,0,0,24,24,45760,0x7fa40034ba00,0x7fa2f4635b00,0,0,0,12076538282280930,12076538282456365,12076538282599245,12076538282602869
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,931859,931864,4194304,256,0,0,24,24,46720,0x7fa40034b900,0x7fa2f4635b40,0,0,0,12076538282664774,12076538282824844,12076538282958763,12076538282962498
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,931859,931864,4194304,256,0,0,28,24,48448,0x7fa40034b800,0x7fa2f4635b80,0,0,0,12076538283015717,12076538283195403,12076538283462442,12076538283504646
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,931859,931864,4194304,256,0,0,28,24,49408,0x7fa40034b700,0x7fa2f4635bc0,0,0,0,12076538283527729,12076538283708841,12076538283965800,12076538284014134
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,931859,931864,4194304,256,0,0,24,24,50368,0x7fa40034b600,0x7fa2f4635c00,0,0,0,12076538284041825,12076538284220519,12076538284351399,12076538284354617
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,931859,931864,4194304,256,0,0,24,24,51584,0x7fa40034b500,0x7fa2f4635c40,0,0,0,12076538284404630,12076538284576838,12076538284721317,12076538284724986
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,931859,931864,4194304,256,0,0,24,24,52544,0x7fa40034b400,0x7fa2f4635c80,0,0,0,12076538284788504,12076538284946757,12076538285078756,12076538285082792
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,931859,931864,4194304,256,0,0,28,24,54272,0x7fa40034b300,0x7fa2f4635cc0,0,0,0,12076538285134277,12076538285323235,12076538285594115,12076538285633847
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,931859,931864,4194304,256,0,0,28,24,55488,0x7fa40034ba00,0x7fa2f4635d00,0,0,0,12076538285658733,12076538285836514,12076538286089953,12076538286133226
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,931859,931864,4194304,256,0,0,24,24,56704,0x7fa40034b900,0x7fa2f4635d40,0,0,0,12076538286157070,12076538286337632,12076538286472352,12076538286476033
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,931859,931864,4194304,256,0,0,24,24,58176,0x7fa40034b800,0x7fa2f4635d80,0,0,0,12076538286527118,12076538286698751,12076538286843550,12076538286847264
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,931859,931864,4194304,256,0,0,24,24,59392,0x7fa40034b700,0x7fa2f4635dc0,0,0,0,12076538286910832,12076538287074909,12076538287204189,12076538287208195
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,931859,931864,4194304,256,0,0,28,24,61376,0x7fa40034b600,0x7fa2f4635e00,0,0,0,12076538287259000,12076538287433628,12076538287741307,12076538287781942
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,931859,931864,4194304,256,0,0,28,24,62592,0x7fa40034b500,0x7fa2f4635e40,0,0,0,12076538287805366,12076538287982106,12076538288240826,12076538288280840
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,931859,931864,4194304,256,0,0,24,24,63808,0x7fa40034b400,0x7fa2f4635e80,0,0,0,12076538288305366,12076538288484665,12076538288620024,12076538288623738
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,931859,931864,4194304,256,0,0,24,24,65280,0x7fa40034b300,0x7fa2f4635ec0,0,0,0,12076538288674002,12076538288847703,12076538288987863,12076538288991592
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,931859,931864,4194304,256,0,0,24,24,66496,0x7fa40034ba00,0x7fa2f4635f00,0,0,0,12076538289053768,12076538289222262,12076538289359702,12076538289363504
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,931859,931864,4194304,256,0,0,28,24,68480,0x7fa40034b900,0x7fa2f4635f40,0,0,0,12076538289415261,12076538289587541,12076538289857940,12076538289898439
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,931859,931864,4194304,256,0,0,28,24,69696,0x7fa40034b800,0x7fa2f4635f80,0,0,0,12076538289925299,12076538290113299,12076538290368978,12076538290410211
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,931859,931864,4194304,256,0,0,24,24,70912,0x7fa40034b700,0x7fa2f4635fc0,0,0,0,12076538290438885,12076538290616977,12076538290752177,12076538290756025
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,931859,931864,4194304,256,0,0,24,24,72384,0x7fa40034b600,0x7fa2f4636000,0,0,0,12076538290805326,12076538290979696,12076538291116816,12076538291120813
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,931859,931864,4194304,256,0,0,24,24,73600,0x7fa40034b500,0x7fa2f4636040,0,0,0,12076538291183640,12076538291346575,12076538291480334,12076538291484129
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,931859,931864,4194304,256,0,0,28,24,75840,0x7fa40034b400,0x7fa2f4636080,0,0,0,12076538291533441,12076538291708494,12076538291980013,12076538291998676
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,931859,931864,4194304,256,0,0,28,24,77056,0x7fa40034b300,0x7fa2f46360c0,0,0,0,12076538292048429,12076538292223532,12076538292486411,12076538292505348
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,931859,931864,4194304,256,0,0,24,24,78272,0x7fa40034ba00,0x7fa2f4636100,0,0,0,12076538292552045,12076538292712490,12076538292847530,12076538292851392
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,931859,931864,4194304,256,0,0,24,24,80000,0x7fa40034b900,0x7fa2f4636140,0,0,0,12076538292899131,12076538293086569,12076538293231528,12076538293235537
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,931859,931864,4194304,256,0,0,24,24,81216,0x7fa40034b800,0x7fa2f4636180,0,0,0,12076538293300678,12076538293458568,12076538293592007,12076538293595777
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,931859,931864,4194304,256,0,0,28,24,83456,0x7fa40034b700,0x7fa2f46361c0,0,0,0,12076538293645509,12076538293820166,12076538294090406,12076538294109973
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,931859,931864,4194304,256,0,0,28,24,84928,0x7fa40034b600,0x7fa2f4636200,0,0,0,12076538294160978,12076538294322405,12076538294582404,12076538294602179
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,931859,931864,4194304,256,0,0,24,24,86400,0x7fa40034b500,0x7fa2f4636240,0,0,0,12076538294647884,12076538294813923,12076538294955203,12076538294958933
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,931859,931864,4194304,256,0,0,24,24,88128,0x7fa40034b400,0x7fa2f4636280,0,0,0,12076538295010779,12076538295191362,12076538295343361,12076538295347365
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,931859,931864,4194304,256,0,0,24,24,89600,0x7fa40034b300,0x7fa2f46362c0,0,0,0,12076538295430049,12076538295591520,12076538295723840,12076538295727713
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,931859,931864,4194304,256,0,0,28,24,92096,0x7fa40034ba00,0x7fa2f4636300,0,0,0,12076538295779309,12076538295951999,12076538296223198,12076538296241969
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,931859,931864,4194304,256,0,0,28,24,93568,0x7fa40034b900,0x7fa2f4636340,0,0,0,12076538296286853,12076538296449278,12076538296710717,12076538296729827
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,931859,931864,4194304,256,0,0,24,24,95040,0x7fa40034b800,0x7fa2f4636380,0,0,0,12076538296776694,12076538296943036,12076538297081915,12076538297085979
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,931859,931864,4194304,256,0,0,24,24,96768,0x7fa40034b700,0x7fa2f46363c0,0,0,0,12076538297136984,12076538297309435,12076538297468314,12076538297472147
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,931859,931864,4194304,256,0,0,24,24,98240,0x7fa40034b600,0x7fa2f4636400,0,0,0,12076538297535004,12076538297694233,12076538297823993,12076538297827769
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,931859,931864,4194304,256,0,0,28,24,100736,0x7fa40034b500,0x7fa2f4636440,0,0,0,12076538297878343,12076538298069112,12076538298338551,12076538298358055
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,931859,931864,4194304,256,0,0,28,24,102208,0x7fa40034b400,0x7fa2f4636480,0,0,0,12076538298403710,12076538298565110,12076538298825749,12076538298843418
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,931859,931864,4194304,256,0,0,24,24,103680,0x7fa40034b300,0x7fa2f46364c0,0,0,0,12076538298888953,12076538299059189,12076538299194388,12076538299198589
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,931859,931864,4194304,256,0,0,24,24,105664,0x7fa40034ba00,0x7fa2f4636500,0,0,0,12076538299249153,12076538299423507,12076538299590387,12076538299594265
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,931859,931864,4194304,256,0,0,24,24,107136,0x7fa40034b900,0x7fa2f4636540,0,0,0,12076538299660578,12076538299821746,12076538299957586,12076538299961388
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,931859,931864,4194304,256,0,0,28,24,109888,0x7fa40034b800,0x7fa2f4636580,0,0,0,12076538300016150,12076538300195665,12076538300463664,12076538300482337
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,931859,931864,4194304,256,0,0,28,24,111360,0x7fa40034b700,0x7fa2f46365c0,0,0,0,12076538300529394,12076538300692623,12076538300947982,12076538300966097
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,931859,931864,4194304,256,0,0,24,24,112832,0x7fa40034b600,0x7fa2f4636600,0,0,0,12076538301020357,12076538301191981,12076538301331181,12076538301335193
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,931859,931864,4194304,256,0,0,24,24,114816,0x7fa40034b500,0x7fa2f4636640,0,0,0,12076538301389484,12076538301559500,12076538301734060,12076538301737812
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,931859,931864,4194304,256,0,0,24,24,116288,0x7fa40034b400,0x7fa2f4636680,0,0,0,12076538301806650,12076538301967339,12076538302102538,12076538302106408
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,931859,931864,4194304,256,0,0,28,24,119040,0x7fa40034b300,0x7fa2f46366c0,0,0,0,12076538302158464,12076538302333097,12076538302594537,12076538302614222
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,931859,931864,4194304,256,0,0,28,24,120768,0x7fa40034ba00,0x7fa2f4636700,0,0,0,12076538302659496,12076538302820616,12076538303082695,12076538303101859
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,931859,931864,4194304,256,0,0,24,24,122496,0x7fa40034b900,0x7fa2f4636740,0,0,0,12076538303152844,12076538303314374,12076538303449574,12076538303453533
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,931859,931864,4194304,256,0,0,24,24,124736,0x7fa40034b800,0x7fa2f4636780,0,0,0,12076538303504458,12076538303676933,12076538303859812,12076538303863777
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,931859,931864,4194304,256,0,0,24,24,126464,0x7fa40034b700,0x7fa2f46367c0,0,0,0,12076538303927916,12076538304092611,12076538304232611,12076538304236720
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,931859,931864,4194304,256,0,0,20,24,127936,0x7fa40034b600,0x7fa2f4636800,0,0,0,12076538304285912,12076538304460290,12076538304727329,12076538304745176
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,931859,931864,4194304,256,0,0,28,24,129664,0x7fa40034b500,0x7fa2f4636840,0,0,0,12076538304791302,12076538304962849,12076538305223488,12076538305241449
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,931859,931864,4194304,256,0,0,24,24,131392,0x7fa40034b400,0x7fa2f4636880,0,0,0,12076538305289428,12076538305455967,12076538305590206,12076538305594145
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,931859,931864,4194304,256,0,0,24,24,133632,0x7fa40034b300,0x7fa2f46368c0,0,0,0,12076538305642515,12076538305815166,12076538306009085,12076538306027491
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,931859,931864,4194304,256,0,0,24,24,135360,0x7fa40034ba00,0x7fa2f4636900,0,0,0,12076538306089126,12076538306255164,12076538306389724,12076538306393903
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,931859,931864,4194304,256,0,0,20,24,136832,0x7fa40034b900,0x7fa2f4636940,0,0,0,12076538306440449,12076538306619163,12076538306903642,12076538306922176
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,931859,931864,4194304,256,0,0,28,24,138560,0x7fa40034b800,0x7fa2f4636980,0,0,0,12076538306967320,12076538307137881,12076538307402680,12076538307421364
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,931859,931864,4194304,256,0,0,24,24,140288,0x7fa40034b700,0x7fa2f46369c0,0,0,0,12076538307466298,12076538307628599,12076538307763639,12076538307767478
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,931859,931864,4194304,256,0,0,24,24,142784,0x7fa40034b600,0x7fa2f4636a00,0,0,0,12076538307815868,12076538307991798,12076538308203477,12076538308221863
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,931859,931864,4194304,256,0,0,24,24,144768,0x7fa40034b500,0x7fa2f4636a40,0,0,0,12076538308281424,12076538308442037,12076538308583316,12076538308587173
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,931859,931864,4194304,256,0,0,20,24,145728,0x7fa40034b400,0x7fa2f4636a80,0,0,0,12076538308634040,12076538308814035,12076538309122034,12076538309140472
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,931859,931864,4194304,256,0,0,28,24,147712,0x7fa40034b300,0x7fa2f4636ac0,0,0,0,12076538309185446,12076538309354674,12076538309615953,12076538309633489
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,931859,931864,4194304,256,0,0,24,24,149696,0x7fa40034ba00,0x7fa2f4636b00,0,0,0,12076538309684584,12076538309848112,12076538309984751,12076538309988800
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,931859,931864,4194304,256,0,0,24,24,152192,0x7fa40034b900,0x7fa2f4636b40,0,0,0,12076538310041007,12076538310219631,12076538310449070,12076538310468302
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,931859,931864,4194304,256,0,0,24,24,154176,0x7fa40034b800,0x7fa2f4636b80,0,0,0,12076538310526861,12076538310687149,12076538310822189,12076538310826238
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,931859,931864,4194304,256,0,0,20,24,155648,0x7fa40034b700,0x7fa2f4636bc0,0,0,0,12076538310876351,12076538311054348,12076538311385707,12076538311404563
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,931859,931864,4194304,256,0,0,28,24,157632,0x7fa40034b600,0x7fa2f4636c00,0,0,0,12076538311451220,12076538311611146,12076538311871305,12076538311889555
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,931859,931864,4194304,256,0,0,24,24,159616,0x7fa40034b500,0x7fa2f4636c40,0,0,0,12076538311938657,12076538312120424,12076538312256104,12076538312260035
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,931859,931864,4194304,256,0,0,24,24,162368,0x7fa40034b400,0x7fa2f4636c80,0,0,0,12076538312310549,12076538312482983,12076538312729062,12076538312748062
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,931859,931864,4194304,256,0,0,24,24,164608,0x7fa40034b300,0x7fa2f4636cc0,0,0,0,12076538312812252,12076538312980261,12076538313120261,12076538313124523
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,931859,931864,4194304,256,0,0,20,24,166336,0x7fa40034ba00,0x7fa2f4636d00,0,0,0,12076538313176930,12076538313353227,12076538313729707,12076538313750848
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,931859,931864,4194304,256,0,0,28,24,168576,0x7fa40034b900,0x7fa2f4636d40,0,0,0,12076538313792455,12076538313955145,12076538314218185,12076538314236752
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,931859,931864,4194304,256,0,0,24,24,170816,0x7fa40034b800,0x7fa2f4636d80,0,0,0,12076538314285512,12076538314448264,12076538314588104,12076538314590850
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,931859,931864,4194304,256,0,0,24,24,174080,0x7fa40034b700,0x7fa2f4636dc0,0,0,0,12076538314641765,12076538314812903,12076538315093383,12076538315112150
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,931859,931864,4194304,256,0,0,24,24,176576,0x7fa40034b600,0x7fa2f4636e00,0,0,0,12076538315172773,12076538315335942,12076538315474822,12076538315477530
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,931859,931864,4194304,256,0,0,20,24,177792,0x7fa40034b500,0x7fa2f4636e40,0,0,0,12076538315528514,12076538315701062,12076538316126501,12076538316144380
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,931859,931864,4194304,256,0,0,28,24,180288,0x7fa40034b400,0x7fa2f4636e80,0,0,0,12076538316192089,12076538316356420,12076538316622020,12076538316638429
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,931859,931864,4194304,256,0,0,24,24,182784,0x7fa40034b300,0x7fa2f4636ec0,0,0,0,12076538316693481,12076538316856739,12076538316997219,12076538317005341
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,931859,931864,4194304,256,0,0,24,24,186304,0x7fa40034ba00,0x7fa2f4636f00,0,0,0,12076538317050956,12076538317237059,12076538317581058,12076538317597713
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,931859,931864,4194304,256,0,0,24,24,189312,0x7fa40034b900,0x7fa2f4636f40,0,0,0,12076538317659358,12076538317820737,12076538317974177,12076538317976969
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,931859,931864,4194304,256,0,0,20,24,190784,0x7fa40034b800,0x7fa2f4636f80,0,0,0,12076538318028685,12076538318208097,12076538318726816,12076538318744907
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,931859,931864,4194304,256,0,0,28,24,193792,0x7fa40034b700,0x7fa2f4636fc0,0,0,0,12076538318793668,12076538318954175,12076538319256415,12076538319274292
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,931859,931864,4194304,256,0,0,24,24,196800,0x7fa40034b600,0x7fa2f4637000,0,0,0,12076538319317222,12076538319487614,12076538319641854,12076538319644621
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,931859,931864,4194304,256,0,0,24,24,201088,0x7fa40034b500,0x7fa2f4637040,0,0,0,12076538319693752,12076538319866653,12076538320280093,12076538320297806
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,931859,931864,4194304,256,0,0,24,24,204608,0x7fa40034b400,0x7fa2f4637080,0,0,0,12076538320359150,12076538320522812,12076538320699772,12076538320702559
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,931859,931864,4194304,256,0,0,20,24,206080,0x7fa40034b300,0x7fa2f46370c0,0,0,0,12076538320752762,12076538320925851,12076538321537210,12076538321554533
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,931859,931864,4194304,256,0,0,28,24,209600,0x7fa40034ba00,0x7fa2f4637100,0,0,0,12076538321600870,12076538321765850,12076538322094489,12076538322113674
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,931859,931864,4194304,256,0,0,24,24,213120,0x7fa40034b900,0x7fa2f4637140,0,0,0,12076538322168125,12076538322332088,12076538322512728,12076538322515551
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,931859,931864,4194304,256,0,0,24,24,218176,0x7fa40034b800,0x7fa2f4637180,0,0,0,12076538322564031,12076538322749528,12076538323206167,12076538323225171
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,931859,931864,4194304,256,0,0,24,24,222208,0x7fa40034b700,0x7fa2f46371c0,0,0,0,12076538323294119,12076538323459606,12076538323659606,12076538323676441
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,931859,931864,4194304,256,0,0,20,24,223936,0x7fa40034b600,0x7fa2f4637200,0,0,0,12076538323722246,12076538323887925,12076538324599284,12076538324618383
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,931859,931864,4194304,256,0,0,28,24,227968,0x7fa40034b500,0x7fa2f4637240,0,0,0,12076538324664839,12076538324829364,12076538325204083,12076538325221424
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,931859,931864,4194304,256,0,0,24,24,232000,0x7fa40034b400,0x7fa2f4637280,0,0,0,12076538325275214,12076538325441842,12076538325682482,12076538325699343
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,931859,931864,4194304,256,0,0,24,24,237824,0x7fa40034b300,0x7fa2f46372c0,0,0,0,12076538325757542,12076538325922961,12076538326451120,12076538326468534
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,931859,931864,4194304,256,0,0,24,24,242368,0x7fa40034ba00,0x7fa2f4637300,0,0,0,12076538326530019,12076538326693040,12076538326918159,12076538326935202
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,931859,931864,4194304,256,0,0,20,24,243584,0x7fa40034b900,0x7fa2f4637340,0,0,0,12076538326984504,12076538327153359,12076538327955437,12076538327973834
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,931859,931864,4194304,256,0,0,28,24,248128,0x7fa40034b800,0x7fa2f4637380,0,0,0,12076538328027684,12076538328207917,12076538328628556,12076538328647848
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,931859,931864,4194304,256,0,0,24,24,252672,0x7fa40034b700,0x7fa2f46373c0,0,0,0,12076538328692020,12076538328863115,12076538329125035,12076538329143530
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,931859,931864,4194304,256,0,0,24,24,259264,0x7fa40034b600,0x7fa2f4637400,0,0,0,12076538329189726,12076538329355595,12076538329955593,12076538329973764
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,931859,931864,4194304,256,0,0,24,24,264832,0x7fa40034b500,0x7fa2f4637440,0,0,0,12076538330045388,12076538330211593,12076538330482152,12076538330501796
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,931859,931864,4194304,256,0,0,20,24,266304,0x7fa40034b400,0x7fa2f4637480,0,0,0,12076538330556148,12076538330720392,12076538331708070,12076538331752092
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,931859,931864,4194304,256,0,0,28,24,271872,0x7fa40034b300,0x7fa2f46374c0,0,0,0,12076538331780545,12076538331966949,12076538332484228,12076538332526022
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,931859,931864,4194304,256,0,0,24,24,277440,0x7fa40034ba00,0x7fa2f4637500,0,0,0,12076538332550908,12076538332737508,12076538333011267,12076538333050297
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,931859,931864,4194304,256,0,0,12,24,279936,0x7fa40034b900,0x7fa2f4637540,0,0,0,12076538333073661,12076538333255907,12076538333996065,12076538334036712
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,931859,931864,4194304,256,0,0,24,24,286528,0x7fa40034b800,0x7fa2f4637580,0,0,0,12076538334073029,12076538334237345,12076538334555904,12076538334596413
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,931859,931864,4194304,256,0,0,20,24,288000,0x7fa40034b700,0x7fa2f46375c0,0,0,0,12076538334619095,12076538334798944,12076538335974941,12076538336019169
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,931859,931864,4194304,256,0,0,32,24,294592,0x7fa40034b600,0x7fa2f4637600,0,0,0,12076538336046280,12076538336232861,12076538336845020,12076538336884559
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,931859,931864,4194304,256,0,0,24,24,301184,0x7fa40034b500,0x7fa2f4637640,0,0,0,12076538336912291,12076538337093819,12076538337414939,12076538337455802
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,931859,931864,4194304,256,0,0,12,24,304960,0x7fa40034b400,0x7fa2f4637680,0,0,0,12076538337480037,12076538337660538,12076538338539256,12076538338579402
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,931859,931864,4194304,256,0,0,24,24,313600,0x7fa40034b300,0x7fa2f46376c0,0,0,0,12076538338616751,12076538338781816,12076538339192695,12076538339235312
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,931859,931864,4194304,256,0,0,20,24,314816,0x7fa40034ba00,0x7fa2f4637700,0,0,0,12076538339265117,12076538339448694,12076538341000691,12076538341041472
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,931859,931864,4194304,256,0,0,20,24,317568,0x7fa40034b900,0x7fa2f4637740,0,0,0,12076538341066618,12076538341254771,12076538342051729,12076538342092236
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,931859,931864,4194304,256,0,0,12,24,320320,0x7fa40034b800,0x7fa2f4637780,0,0,0,12076538342117583,12076538342307249,12076538342723568,12076538342763605
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,931859,931864,4194304,256,0,0,12,24,324096,0x7fa40034b700,0x7fa2f46377c0,0,0,0,12076538342787009,12076538342971087,12076538344131565,12076538344172766
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,931859,931864,4194304,256,0,0,12,24,328896,0x7fa40034b600,0x7fa2f4637800,0,0,0,12076538344217479,12076538344382925,12076538345169483,12076538345210076
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,931859,931864,4194304,256,0,0,20,24,330112,0x7fa40034b500,0x7fa2f4637840,0,0,0,12076538345238739,12076538345421003,12076538348475237,12076538348518239
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,931859,931864,4194304,256,0,0,20,24,332864,0x7fa40034b400,0x7fa2f4637880,0,0,0,12076538348598749,12076538348764196,12076538350308833,12076538350351239
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,931859,931864,4194304,256,0,0,12,24,335616,0x7fa40034b300,0x7fa2f46378c0,0,0,0,12076538350427210,12076538350592992,12076538351383071,12076538351426509
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,931859,931864,4194304,256,0,0,12,24,339392,0x7fa40034ba00,0x7fa2f4637900,0,0,0,12076538351498493,12076538351664830,12076538353948826,12076538353990007
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,931859,931864,4194304,256,0,0,12,24,344192,0x7fa40034b900,0x7fa2f4637940,0,0,0,12076538354071429,12076538354240185,12076538355776982,12076538355818419
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,931859,931864,4194304,256,0,0,20,24,345408,0x7fa40034b800,0x7fa2f4637980,0,0,0,12076538355902134,12076538356061142,12076538362120009,12076538362164774
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,931859,931864,4194304,256,0,0,20,24,348160,0x7fa40034b700,0x7fa2f46379c0,0,0,0,12076538362238771,12076538362404649,12076538365447683,12076538365491401
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,931859,931864,4194304,256,0,0,12,24,350912,0x7fa40034b600,0x7fa2f4637a00,0,0,0,12076538365562283,12076538365725122,12076538367265439,12076538367306237
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,931859,931864,4194304,256,0,0,12,24,0,0x7fa40034b500,0x7fa2f4637a40,0,0,0,12076538367374494,12076538367541119,12076538372069110,12076538372116815
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid grd Workgroup_Size LDS_Per_Workgroup scr vgpr SGPR fbar sig obj SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 __amd_rocclr_fillBuffer.kd 0 0 0 931859 931864 33554432 256 0 0 8 32 6464 0x0 0x7fa2f4604180 0 0 0 12076538010346649 12076538250264836 12076538250588515 12076538250679036
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 931859 931864 32768 256 0 0 24 24 12480 0x0 0x7fa2f4635100 0 0 0 12076538265124998 12076538265420263 12076538265426823 12076538265432269
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 4 931859 931864 4194304 256 0 0 24 24 12928 0x7fa40034b900 0x7fa2f4635140 0 0 0 12076538265550439 12076538265717702 12076538265859462 12076538265863321
5 3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 6 931859 931864 4194304 256 0 0 36 24 13632 0x7fa40034b800 0x7fa2f4635180 0 0 0 12076538265960702 12076538266141701 12076538266393860 12076538266436517
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 8 931859 931864 4194304 256 0 0 28 24 14080 0x7fa40034b700 0x7fa2f46351c0 0 0 0 12076538266503442 12076538266670019 12076538266926658 12076538266967535
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 10 931859 931864 4194304 256 0 0 24 24 14528 0x7fa40034b600 0x7fa2f4635200 0 0 0 12076538267047314 12076538267222337 12076538267360257 12076538267364083
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 12 931859 931864 4194304 256 0 0 24 24 14976 0x7fa40034b500 0x7fa2f4635240 0 0 0 12076538267415248 12076538267602176 12076538267739935 12076538267743599
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 14 931859 931864 4194304 256 0 0 24 24 15424 0x7fa40034b400 0x7fa2f4635280 0 0 0 12076538267827625 12076538267995454 12076538268126494 12076538268130448
10 8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 16 931859 931864 4194304 256 0 0 28 24 16128 0x7fa40034b300 0x7fa2f46352c0 0 0 0 12076538268181353 12076538268362973 12076538268622332 12076538268663349
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 18 931859 931864 4194304 256 0 0 28 24 16832 0x7fa40034ba00 0x7fa2f4635300 0 0 0 12076538268686803 12076538268868572 12076538269127131 12076538269166916
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 20 931859 931864 4194304 256 0 0 24 24 17536 0x7fa40034b900 0x7fa2f4635340 0 0 0 12076538269192474 12076538269382810 12076538269514169 12076538269517819
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 22 931859 931864 4194304 256 0 0 24 24 18240 0x7fa40034b800 0x7fa2f4635380 0 0 0 12076538269567952 12076538269753208 12076538269891448 12076538269895021
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 24 931859 931864 4194304 256 0 0 24 24 18944 0x7fa40034b700 0x7fa2f46353c0 0 0 0 12076538269962386 12076538270134807 12076538270265047 12076538270268876
15 13 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 26 931859 931864 4194304 256 0 0 28 24 19904 0x7fa40034b600 0x7fa2f4635400 0 0 0 12076538270321033 12076538270498326 12076538270757205 12076538270797219
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 28 931859 931864 4194304 256 0 0 28 24 20608 0x7fa40034b500 0x7fa2f4635440 0 0 0 12076538270822295 12076538271003764 12076538271258963 12076538271299673
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 30 931859 931864 4194304 256 0 0 24 24 21312 0x7fa40034b400 0x7fa2f4635480 0 0 0 12076538271323718 12076538271506323 12076538271641682 12076538271644946
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 32 931859 931864 4194304 256 0 0 24 24 22016 0x7fa40034b300 0x7fa2f46354c0 0 0 0 12076538271694187 12076538271869041 12076538272006321 12076538272009935
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 34 931859 931864 4194304 256 0 0 24 24 22720 0x7fa40034ba00 0x7fa2f4635500 0 0 0 12076538272074865 12076538272239600 12076538272378160 12076538272381756
20 18 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 36 931859 931864 4194304 256 0 0 28 24 23680 0x7fa40034b900 0x7fa2f4635540 0 0 0 12076538272431419 12076538272607279 12076538272864878 12076538272904719
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 38 931859 931864 4194304 256 0 0 28 24 24384 0x7fa40034b800 0x7fa2f4635580 0 0 0 12076538272928944 12076538273125837 12076538273384556 12076538273423935
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 40 931859 931864 4194304 256 0 0 24 24 25088 0x7fa40034b700 0x7fa2f46355c0 0 0 0 12076538273449142 12076538273631755 12076538273765195 12076538273768696
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 42 931859 931864 4194304 256 0 0 24 24 25792 0x7fa40034b600 0x7fa2f4635600 0 0 0 12076538273818950 12076538273995914 12076538274130634 12076538274134256
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 44 931859 931864 4194304 256 0 0 24 24 26496 0x7fa40034b500 0x7fa2f4635640 0 0 0 12076538274197914 12076538274360873 12076538274497192 12076538274500668
25 23 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 46 931859 931864 4194304 256 0 0 28 24 27712 0x7fa40034b400 0x7fa2f4635680 0 0 0 12076538274549949 12076538274723752 12076538274982151 12076538275023490
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 48 931859 931864 4194304 256 0 0 28 24 28416 0x7fa40034b300 0x7fa2f46356c0 0 0 0 12076538275049008 12076538275232710 12076538275489029 12076538275529341
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 50 931859 931864 4194304 256 0 0 24 24 29120 0x7fa40034ba00 0x7fa2f4635700 0 0 0 12076538275553195 12076538275731108 12076538275862628 12076538275866108
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 52 931859 931864 4194304 256 0 0 24 24 30080 0x7fa40034b900 0x7fa2f4635740 0 0 0 12076538275918645 12076538276101667 12076538276236066 12076538276239823
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 54 931859 931864 4194304 256 0 0 24 24 30784 0x7fa40034b800 0x7fa2f4635780 0 0 0 12076538276302399 12076538276461986 12076538276595585 12076538276599061
30 28 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 56 931859 931864 4194304 256 0 0 28 24 32000 0x7fa40034b700 0x7fa2f46357c0 0 0 0 12076538276648433 12076538276830304 12076538277089983 12076538277131201
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 58 931859 931864 4194304 256 0 0 28 24 32960 0x7fa40034b600 0x7fa2f4635800 0 0 0 12076538277155907 12076538277346463 12076538277601182 12076538277641831
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 60 931859 931864 4194304 256 0 0 24 24 33920 0x7fa40034b500 0x7fa2f4635840 0 0 0 12076538277666126 12076538277845821 12076538277978780 12076538277982244
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 62 931859 931864 4194304 256 0 0 24 24 34880 0x7fa40034b400 0x7fa2f4635880 0 0 0 12076538278033499 12076538278212860 12076538278351579 12076538278355388
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 64 931859 931864 4194304 256 0 0 24 24 35840 0x7fa40034b300 0x7fa2f46358c0 0 0 0 12076538278416802 12076538278577018 12076538278708218 12076538278711821
35 33 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 66 931859 931864 4194304 256 0 0 28 24 37312 0x7fa40034ba00 0x7fa2f4635900 0 0 0 12076538278762766 12076538278934137 12076538279198616 12076538279240554
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 68 931859 931864 4194304 256 0 0 28 24 38272 0x7fa40034b900 0x7fa2f4635940 0 0 0 12076538279264248 12076538279444855 12076538279698935 12076538279739202
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 70 931859 931864 4194304 256 0 0 24 24 39232 0x7fa40034b800 0x7fa2f4635980 0 0 0 12076538279762585 12076538279945174 12076538280084373 12076538280088041
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 72 931859 931864 4194304 256 0 0 24 24 40192 0x7fa40034b700 0x7fa2f46359c0 0 0 0 12076538280141701 12076538280315893 12076538280458612 12076538280462397
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 74 931859 931864 4194304 256 0 0 24 24 41152 0x7fa40034b600 0x7fa2f4635a00 0 0 0 12076538280526396 12076538280686451 12076538280820051 12076538280823779
40 38 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 76 931859 931864 4194304 256 0 0 28 24 42624 0x7fa40034b500 0x7fa2f4635a40 0 0 0 12076538280872360 12076538281071570 12076538281335089 12076538281376478
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 78 931859 931864 4194304 256 0 0 28 24 43584 0x7fa40034b400 0x7fa2f4635a80 0 0 0 12076538281400713 12076538281579888 12076538281838927 12076538281879283
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 80 931859 931864 4194304 256 0 0 24 24 44544 0x7fa40034b300 0x7fa2f4635ac0 0 0 0 12076538281903658 12076538282089486 12076538282225486 12076538282229745
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 82 931859 931864 4194304 256 0 0 24 24 45760 0x7fa40034ba00 0x7fa2f4635b00 0 0 0 12076538282280930 12076538282456365 12076538282599245 12076538282602869
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 84 931859 931864 4194304 256 0 0 24 24 46720 0x7fa40034b900 0x7fa2f4635b40 0 0 0 12076538282664774 12076538282824844 12076538282958763 12076538282962498
45 43 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 86 931859 931864 4194304 256 0 0 28 24 48448 0x7fa40034b800 0x7fa2f4635b80 0 0 0 12076538283015717 12076538283195403 12076538283462442 12076538283504646
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 88 931859 931864 4194304 256 0 0 28 24 49408 0x7fa40034b700 0x7fa2f4635bc0 0 0 0 12076538283527729 12076538283708841 12076538283965800 12076538284014134
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 90 931859 931864 4194304 256 0 0 24 24 50368 0x7fa40034b600 0x7fa2f4635c00 0 0 0 12076538284041825 12076538284220519 12076538284351399 12076538284354617
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 92 931859 931864 4194304 256 0 0 24 24 51584 0x7fa40034b500 0x7fa2f4635c40 0 0 0 12076538284404630 12076538284576838 12076538284721317 12076538284724986
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 94 931859 931864 4194304 256 0 0 24 24 52544 0x7fa40034b400 0x7fa2f4635c80 0 0 0 12076538284788504 12076538284946757 12076538285078756 12076538285082792
50 48 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 96 931859 931864 4194304 256 0 0 28 24 54272 0x7fa40034b300 0x7fa2f4635cc0 0 0 0 12076538285134277 12076538285323235 12076538285594115 12076538285633847
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 98 931859 931864 4194304 256 0 0 28 24 55488 0x7fa40034ba00 0x7fa2f4635d00 0 0 0 12076538285658733 12076538285836514 12076538286089953 12076538286133226
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 100 931859 931864 4194304 256 0 0 24 24 56704 0x7fa40034b900 0x7fa2f4635d40 0 0 0 12076538286157070 12076538286337632 12076538286472352 12076538286476033
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 102 931859 931864 4194304 256 0 0 24 24 58176 0x7fa40034b800 0x7fa2f4635d80 0 0 0 12076538286527118 12076538286698751 12076538286843550 12076538286847264
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 104 931859 931864 4194304 256 0 0 24 24 59392 0x7fa40034b700 0x7fa2f4635dc0 0 0 0 12076538286910832 12076538287074909 12076538287204189 12076538287208195
55 53 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 106 931859 931864 4194304 256 0 0 28 24 61376 0x7fa40034b600 0x7fa2f4635e00 0 0 0 12076538287259000 12076538287433628 12076538287741307 12076538287781942
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 108 931859 931864 4194304 256 0 0 28 24 62592 0x7fa40034b500 0x7fa2f4635e40 0 0 0 12076538287805366 12076538287982106 12076538288240826 12076538288280840
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 110 931859 931864 4194304 256 0 0 24 24 63808 0x7fa40034b400 0x7fa2f4635e80 0 0 0 12076538288305366 12076538288484665 12076538288620024 12076538288623738
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 112 931859 931864 4194304 256 0 0 24 24 65280 0x7fa40034b300 0x7fa2f4635ec0 0 0 0 12076538288674002 12076538288847703 12076538288987863 12076538288991592
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 114 931859 931864 4194304 256 0 0 24 24 66496 0x7fa40034ba00 0x7fa2f4635f00 0 0 0 12076538289053768 12076538289222262 12076538289359702 12076538289363504
60 58 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 116 931859 931864 4194304 256 0 0 28 24 68480 0x7fa40034b900 0x7fa2f4635f40 0 0 0 12076538289415261 12076538289587541 12076538289857940 12076538289898439
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 118 931859 931864 4194304 256 0 0 28 24 69696 0x7fa40034b800 0x7fa2f4635f80 0 0 0 12076538289925299 12076538290113299 12076538290368978 12076538290410211
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 120 931859 931864 4194304 256 0 0 24 24 70912 0x7fa40034b700 0x7fa2f4635fc0 0 0 0 12076538290438885 12076538290616977 12076538290752177 12076538290756025
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 122 931859 931864 4194304 256 0 0 24 24 72384 0x7fa40034b600 0x7fa2f4636000 0 0 0 12076538290805326 12076538290979696 12076538291116816 12076538291120813
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 124 931859 931864 4194304 256 0 0 24 24 73600 0x7fa40034b500 0x7fa2f4636040 0 0 0 12076538291183640 12076538291346575 12076538291480334 12076538291484129
65 63 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 126 931859 931864 4194304 256 0 0 28 24 75840 0x7fa40034b400 0x7fa2f4636080 0 0 0 12076538291533441 12076538291708494 12076538291980013 12076538291998676
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 128 931859 931864 4194304 256 0 0 28 24 77056 0x7fa40034b300 0x7fa2f46360c0 0 0 0 12076538292048429 12076538292223532 12076538292486411 12076538292505348
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 130 931859 931864 4194304 256 0 0 24 24 78272 0x7fa40034ba00 0x7fa2f4636100 0 0 0 12076538292552045 12076538292712490 12076538292847530 12076538292851392
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 132 931859 931864 4194304 256 0 0 24 24 80000 0x7fa40034b900 0x7fa2f4636140 0 0 0 12076538292899131 12076538293086569 12076538293231528 12076538293235537
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 134 931859 931864 4194304 256 0 0 24 24 81216 0x7fa40034b800 0x7fa2f4636180 0 0 0 12076538293300678 12076538293458568 12076538293592007 12076538293595777
70 68 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 136 931859 931864 4194304 256 0 0 28 24 83456 0x7fa40034b700 0x7fa2f46361c0 0 0 0 12076538293645509 12076538293820166 12076538294090406 12076538294109973
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 138 931859 931864 4194304 256 0 0 28 24 84928 0x7fa40034b600 0x7fa2f4636200 0 0 0 12076538294160978 12076538294322405 12076538294582404 12076538294602179
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 140 931859 931864 4194304 256 0 0 24 24 86400 0x7fa40034b500 0x7fa2f4636240 0 0 0 12076538294647884 12076538294813923 12076538294955203 12076538294958933
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 142 931859 931864 4194304 256 0 0 24 24 88128 0x7fa40034b400 0x7fa2f4636280 0 0 0 12076538295010779 12076538295191362 12076538295343361 12076538295347365
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 144 931859 931864 4194304 256 0 0 24 24 89600 0x7fa40034b300 0x7fa2f46362c0 0 0 0 12076538295430049 12076538295591520 12076538295723840 12076538295727713
75 73 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 146 931859 931864 4194304 256 0 0 28 24 92096 0x7fa40034ba00 0x7fa2f4636300 0 0 0 12076538295779309 12076538295951999 12076538296223198 12076538296241969
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 148 931859 931864 4194304 256 0 0 28 24 93568 0x7fa40034b900 0x7fa2f4636340 0 0 0 12076538296286853 12076538296449278 12076538296710717 12076538296729827
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 150 931859 931864 4194304 256 0 0 24 24 95040 0x7fa40034b800 0x7fa2f4636380 0 0 0 12076538296776694 12076538296943036 12076538297081915 12076538297085979
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 152 931859 931864 4194304 256 0 0 24 24 96768 0x7fa40034b700 0x7fa2f46363c0 0 0 0 12076538297136984 12076538297309435 12076538297468314 12076538297472147
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 154 931859 931864 4194304 256 0 0 24 24 98240 0x7fa40034b600 0x7fa2f4636400 0 0 0 12076538297535004 12076538297694233 12076538297823993 12076538297827769
80 78 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 156 931859 931864 4194304 256 0 0 28 24 100736 0x7fa40034b500 0x7fa2f4636440 0 0 0 12076538297878343 12076538298069112 12076538298338551 12076538298358055
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 158 931859 931864 4194304 256 0 0 28 24 102208 0x7fa40034b400 0x7fa2f4636480 0 0 0 12076538298403710 12076538298565110 12076538298825749 12076538298843418
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 160 931859 931864 4194304 256 0 0 24 24 103680 0x7fa40034b300 0x7fa2f46364c0 0 0 0 12076538298888953 12076538299059189 12076538299194388 12076538299198589
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 162 931859 931864 4194304 256 0 0 24 24 105664 0x7fa40034ba00 0x7fa2f4636500 0 0 0 12076538299249153 12076538299423507 12076538299590387 12076538299594265
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 164 931859 931864 4194304 256 0 0 24 24 107136 0x7fa40034b900 0x7fa2f4636540 0 0 0 12076538299660578 12076538299821746 12076538299957586 12076538299961388
85 83 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 166 931859 931864 4194304 256 0 0 28 24 109888 0x7fa40034b800 0x7fa2f4636580 0 0 0 12076538300016150 12076538300195665 12076538300463664 12076538300482337
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 168 931859 931864 4194304 256 0 0 28 24 111360 0x7fa40034b700 0x7fa2f46365c0 0 0 0 12076538300529394 12076538300692623 12076538300947982 12076538300966097
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 170 931859 931864 4194304 256 0 0 24 24 112832 0x7fa40034b600 0x7fa2f4636600 0 0 0 12076538301020357 12076538301191981 12076538301331181 12076538301335193
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 172 931859 931864 4194304 256 0 0 24 24 114816 0x7fa40034b500 0x7fa2f4636640 0 0 0 12076538301389484 12076538301559500 12076538301734060 12076538301737812
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 174 931859 931864 4194304 256 0 0 24 24 116288 0x7fa40034b400 0x7fa2f4636680 0 0 0 12076538301806650 12076538301967339 12076538302102538 12076538302106408
90 88 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 176 931859 931864 4194304 256 0 0 28 24 119040 0x7fa40034b300 0x7fa2f46366c0 0 0 0 12076538302158464 12076538302333097 12076538302594537 12076538302614222
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 178 931859 931864 4194304 256 0 0 28 24 120768 0x7fa40034ba00 0x7fa2f4636700 0 0 0 12076538302659496 12076538302820616 12076538303082695 12076538303101859
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 180 931859 931864 4194304 256 0 0 24 24 122496 0x7fa40034b900 0x7fa2f4636740 0 0 0 12076538303152844 12076538303314374 12076538303449574 12076538303453533
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 182 931859 931864 4194304 256 0 0 24 24 124736 0x7fa40034b800 0x7fa2f4636780 0 0 0 12076538303504458 12076538303676933 12076538303859812 12076538303863777
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 184 931859 931864 4194304 256 0 0 24 24 126464 0x7fa40034b700 0x7fa2f46367c0 0 0 0 12076538303927916 12076538304092611 12076538304232611 12076538304236720
95 93 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 186 931859 931864 4194304 256 0 0 20 24 127936 0x7fa40034b600 0x7fa2f4636800 0 0 0 12076538304285912 12076538304460290 12076538304727329 12076538304745176
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 188 931859 931864 4194304 256 0 0 28 24 129664 0x7fa40034b500 0x7fa2f4636840 0 0 0 12076538304791302 12076538304962849 12076538305223488 12076538305241449
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 190 931859 931864 4194304 256 0 0 24 24 131392 0x7fa40034b400 0x7fa2f4636880 0 0 0 12076538305289428 12076538305455967 12076538305590206 12076538305594145
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 192 931859 931864 4194304 256 0 0 24 24 133632 0x7fa40034b300 0x7fa2f46368c0 0 0 0 12076538305642515 12076538305815166 12076538306009085 12076538306027491
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 194 931859 931864 4194304 256 0 0 24 24 135360 0x7fa40034ba00 0x7fa2f4636900 0 0 0 12076538306089126 12076538306255164 12076538306389724 12076538306393903
100 98 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 196 931859 931864 4194304 256 0 0 20 24 136832 0x7fa40034b900 0x7fa2f4636940 0 0 0 12076538306440449 12076538306619163 12076538306903642 12076538306922176
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 198 931859 931864 4194304 256 0 0 28 24 138560 0x7fa40034b800 0x7fa2f4636980 0 0 0 12076538306967320 12076538307137881 12076538307402680 12076538307421364
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 200 931859 931864 4194304 256 0 0 24 24 140288 0x7fa40034b700 0x7fa2f46369c0 0 0 0 12076538307466298 12076538307628599 12076538307763639 12076538307767478
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 202 931859 931864 4194304 256 0 0 24 24 142784 0x7fa40034b600 0x7fa2f4636a00 0 0 0 12076538307815868 12076538307991798 12076538308203477 12076538308221863
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 204 931859 931864 4194304 256 0 0 24 24 144768 0x7fa40034b500 0x7fa2f4636a40 0 0 0 12076538308281424 12076538308442037 12076538308583316 12076538308587173
105 103 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 206 931859 931864 4194304 256 0 0 20 24 145728 0x7fa40034b400 0x7fa2f4636a80 0 0 0 12076538308634040 12076538308814035 12076538309122034 12076538309140472
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 208 931859 931864 4194304 256 0 0 28 24 147712 0x7fa40034b300 0x7fa2f4636ac0 0 0 0 12076538309185446 12076538309354674 12076538309615953 12076538309633489
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 210 931859 931864 4194304 256 0 0 24 24 149696 0x7fa40034ba00 0x7fa2f4636b00 0 0 0 12076538309684584 12076538309848112 12076538309984751 12076538309988800
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 212 931859 931864 4194304 256 0 0 24 24 152192 0x7fa40034b900 0x7fa2f4636b40 0 0 0 12076538310041007 12076538310219631 12076538310449070 12076538310468302
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 214 931859 931864 4194304 256 0 0 24 24 154176 0x7fa40034b800 0x7fa2f4636b80 0 0 0 12076538310526861 12076538310687149 12076538310822189 12076538310826238
110 108 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 216 931859 931864 4194304 256 0 0 20 24 155648 0x7fa40034b700 0x7fa2f4636bc0 0 0 0 12076538310876351 12076538311054348 12076538311385707 12076538311404563
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 218 931859 931864 4194304 256 0 0 28 24 157632 0x7fa40034b600 0x7fa2f4636c00 0 0 0 12076538311451220 12076538311611146 12076538311871305 12076538311889555
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 220 931859 931864 4194304 256 0 0 24 24 159616 0x7fa40034b500 0x7fa2f4636c40 0 0 0 12076538311938657 12076538312120424 12076538312256104 12076538312260035
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 222 931859 931864 4194304 256 0 0 24 24 162368 0x7fa40034b400 0x7fa2f4636c80 0 0 0 12076538312310549 12076538312482983 12076538312729062 12076538312748062
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 224 931859 931864 4194304 256 0 0 24 24 164608 0x7fa40034b300 0x7fa2f4636cc0 0 0 0 12076538312812252 12076538312980261 12076538313120261 12076538313124523
115 113 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 226 931859 931864 4194304 256 0 0 20 24 166336 0x7fa40034ba00 0x7fa2f4636d00 0 0 0 12076538313176930 12076538313353227 12076538313729707 12076538313750848
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 228 931859 931864 4194304 256 0 0 28 24 168576 0x7fa40034b900 0x7fa2f4636d40 0 0 0 12076538313792455 12076538313955145 12076538314218185 12076538314236752
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 230 931859 931864 4194304 256 0 0 24 24 170816 0x7fa40034b800 0x7fa2f4636d80 0 0 0 12076538314285512 12076538314448264 12076538314588104 12076538314590850
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 232 931859 931864 4194304 256 0 0 24 24 174080 0x7fa40034b700 0x7fa2f4636dc0 0 0 0 12076538314641765 12076538314812903 12076538315093383 12076538315112150
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 234 931859 931864 4194304 256 0 0 24 24 176576 0x7fa40034b600 0x7fa2f4636e00 0 0 0 12076538315172773 12076538315335942 12076538315474822 12076538315477530
120 118 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 236 931859 931864 4194304 256 0 0 20 24 177792 0x7fa40034b500 0x7fa2f4636e40 0 0 0 12076538315528514 12076538315701062 12076538316126501 12076538316144380
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 238 931859 931864 4194304 256 0 0 28 24 180288 0x7fa40034b400 0x7fa2f4636e80 0 0 0 12076538316192089 12076538316356420 12076538316622020 12076538316638429
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 240 931859 931864 4194304 256 0 0 24 24 182784 0x7fa40034b300 0x7fa2f4636ec0 0 0 0 12076538316693481 12076538316856739 12076538316997219 12076538317005341
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 242 931859 931864 4194304 256 0 0 24 24 186304 0x7fa40034ba00 0x7fa2f4636f00 0 0 0 12076538317050956 12076538317237059 12076538317581058 12076538317597713
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 244 931859 931864 4194304 256 0 0 24 24 189312 0x7fa40034b900 0x7fa2f4636f40 0 0 0 12076538317659358 12076538317820737 12076538317974177 12076538317976969
125 123 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 246 931859 931864 4194304 256 0 0 20 24 190784 0x7fa40034b800 0x7fa2f4636f80 0 0 0 12076538318028685 12076538318208097 12076538318726816 12076538318744907
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 248 931859 931864 4194304 256 0 0 28 24 193792 0x7fa40034b700 0x7fa2f4636fc0 0 0 0 12076538318793668 12076538318954175 12076538319256415 12076538319274292
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 250 931859 931864 4194304 256 0 0 24 24 196800 0x7fa40034b600 0x7fa2f4637000 0 0 0 12076538319317222 12076538319487614 12076538319641854 12076538319644621
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 252 931859 931864 4194304 256 0 0 24 24 201088 0x7fa40034b500 0x7fa2f4637040 0 0 0 12076538319693752 12076538319866653 12076538320280093 12076538320297806
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 254 931859 931864 4194304 256 0 0 24 24 204608 0x7fa40034b400 0x7fa2f4637080 0 0 0 12076538320359150 12076538320522812 12076538320699772 12076538320702559
130 128 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 256 931859 931864 4194304 256 0 0 20 24 206080 0x7fa40034b300 0x7fa2f46370c0 0 0 0 12076538320752762 12076538320925851 12076538321537210 12076538321554533
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 258 931859 931864 4194304 256 0 0 28 24 209600 0x7fa40034ba00 0x7fa2f4637100 0 0 0 12076538321600870 12076538321765850 12076538322094489 12076538322113674
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 260 931859 931864 4194304 256 0 0 24 24 213120 0x7fa40034b900 0x7fa2f4637140 0 0 0 12076538322168125 12076538322332088 12076538322512728 12076538322515551
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 262 931859 931864 4194304 256 0 0 24 24 218176 0x7fa40034b800 0x7fa2f4637180 0 0 0 12076538322564031 12076538322749528 12076538323206167 12076538323225171
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 264 931859 931864 4194304 256 0 0 24 24 222208 0x7fa40034b700 0x7fa2f46371c0 0 0 0 12076538323294119 12076538323459606 12076538323659606 12076538323676441
135 133 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 266 931859 931864 4194304 256 0 0 20 24 223936 0x7fa40034b600 0x7fa2f4637200 0 0 0 12076538323722246 12076538323887925 12076538324599284 12076538324618383
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 268 931859 931864 4194304 256 0 0 28 24 227968 0x7fa40034b500 0x7fa2f4637240 0 0 0 12076538324664839 12076538324829364 12076538325204083 12076538325221424
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 270 931859 931864 4194304 256 0 0 24 24 232000 0x7fa40034b400 0x7fa2f4637280 0 0 0 12076538325275214 12076538325441842 12076538325682482 12076538325699343
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 272 931859 931864 4194304 256 0 0 24 24 237824 0x7fa40034b300 0x7fa2f46372c0 0 0 0 12076538325757542 12076538325922961 12076538326451120 12076538326468534
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 274 931859 931864 4194304 256 0 0 24 24 242368 0x7fa40034ba00 0x7fa2f4637300 0 0 0 12076538326530019 12076538326693040 12076538326918159 12076538326935202
140 138 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 276 931859 931864 4194304 256 0 0 20 24 243584 0x7fa40034b900 0x7fa2f4637340 0 0 0 12076538326984504 12076538327153359 12076538327955437 12076538327973834
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 278 931859 931864 4194304 256 0 0 28 24 248128 0x7fa40034b800 0x7fa2f4637380 0 0 0 12076538328027684 12076538328207917 12076538328628556 12076538328647848
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 280 931859 931864 4194304 256 0 0 24 24 252672 0x7fa40034b700 0x7fa2f46373c0 0 0 0 12076538328692020 12076538328863115 12076538329125035 12076538329143530
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 282 931859 931864 4194304 256 0 0 24 24 259264 0x7fa40034b600 0x7fa2f4637400 0 0 0 12076538329189726 12076538329355595 12076538329955593 12076538329973764
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 284 931859 931864 4194304 256 0 0 24 24 264832 0x7fa40034b500 0x7fa2f4637440 0 0 0 12076538330045388 12076538330211593 12076538330482152 12076538330501796
145 143 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 286 931859 931864 4194304 256 0 0 20 24 266304 0x7fa40034b400 0x7fa2f4637480 0 0 0 12076538330556148 12076538330720392 12076538331708070 12076538331752092
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 288 931859 931864 4194304 256 0 0 28 24 271872 0x7fa40034b300 0x7fa2f46374c0 0 0 0 12076538331780545 12076538331966949 12076538332484228 12076538332526022
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 290 931859 931864 4194304 256 0 0 24 24 277440 0x7fa40034ba00 0x7fa2f4637500 0 0 0 12076538332550908 12076538332737508 12076538333011267 12076538333050297
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 292 931859 931864 4194304 256 0 0 12 24 279936 0x7fa40034b900 0x7fa2f4637540 0 0 0 12076538333073661 12076538333255907 12076538333996065 12076538334036712
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 294 931859 931864 4194304 256 0 0 24 24 286528 0x7fa40034b800 0x7fa2f4637580 0 0 0 12076538334073029 12076538334237345 12076538334555904 12076538334596413
150 148 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 296 931859 931864 4194304 256 0 0 20 24 288000 0x7fa40034b700 0x7fa2f46375c0 0 0 0 12076538334619095 12076538334798944 12076538335974941 12076538336019169
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 298 931859 931864 4194304 256 0 0 32 24 294592 0x7fa40034b600 0x7fa2f4637600 0 0 0 12076538336046280 12076538336232861 12076538336845020 12076538336884559
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 300 931859 931864 4194304 256 0 0 24 24 301184 0x7fa40034b500 0x7fa2f4637640 0 0 0 12076538336912291 12076538337093819 12076538337414939 12076538337455802
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 302 931859 931864 4194304 256 0 0 12 24 304960 0x7fa40034b400 0x7fa2f4637680 0 0 0 12076538337480037 12076538337660538 12076538338539256 12076538338579402
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 304 931859 931864 4194304 256 0 0 24 24 313600 0x7fa40034b300 0x7fa2f46376c0 0 0 0 12076538338616751 12076538338781816 12076538339192695 12076538339235312
155 153 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 306 931859 931864 4194304 256 0 0 20 24 314816 0x7fa40034ba00 0x7fa2f4637700 0 0 0 12076538339265117 12076538339448694 12076538341000691 12076538341041472
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 308 931859 931864 4194304 256 0 0 20 24 317568 0x7fa40034b900 0x7fa2f4637740 0 0 0 12076538341066618 12076538341254771 12076538342051729 12076538342092236
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 310 931859 931864 4194304 256 0 0 12 24 320320 0x7fa40034b800 0x7fa2f4637780 0 0 0 12076538342117583 12076538342307249 12076538342723568 12076538342763605
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 312 931859 931864 4194304 256 0 0 12 24 324096 0x7fa40034b700 0x7fa2f46377c0 0 0 0 12076538342787009 12076538342971087 12076538344131565 12076538344172766
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 314 931859 931864 4194304 256 0 0 12 24 328896 0x7fa40034b600 0x7fa2f4637800 0 0 0 12076538344217479 12076538344382925 12076538345169483 12076538345210076
160 158 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 316 931859 931864 4194304 256 0 0 20 24 330112 0x7fa40034b500 0x7fa2f4637840 0 0 0 12076538345238739 12076538345421003 12076538348475237 12076538348518239
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 318 931859 931864 4194304 256 0 0 20 24 332864 0x7fa40034b400 0x7fa2f4637880 0 0 0 12076538348598749 12076538348764196 12076538350308833 12076538350351239
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 320 931859 931864 4194304 256 0 0 12 24 335616 0x7fa40034b300 0x7fa2f46378c0 0 0 0 12076538350427210 12076538350592992 12076538351383071 12076538351426509
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 322 931859 931864 4194304 256 0 0 12 24 339392 0x7fa40034ba00 0x7fa2f4637900 0 0 0 12076538351498493 12076538351664830 12076538353948826 12076538353990007
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 324 931859 931864 4194304 256 0 0 12 24 344192 0x7fa40034b900 0x7fa2f4637940 0 0 0 12076538354071429 12076538354240185 12076538355776982 12076538355818419
165 163 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 326 931859 931864 4194304 256 0 0 20 24 345408 0x7fa40034b800 0x7fa2f4637980 0 0 0 12076538355902134 12076538356061142 12076538362120009 12076538362164774
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 328 931859 931864 4194304 256 0 0 20 24 348160 0x7fa40034b700 0x7fa2f46379c0 0 0 0 12076538362238771 12076538362404649 12076538365447683 12076538365491401
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 330 931859 931864 4194304 256 0 0 12 24 350912 0x7fa40034b600 0x7fa2f4637a00 0 0 0 12076538365562283 12076538365725122 12076538367265439 12076538367306237
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 332 931859 931864 4194304 256 0 0 12 24 0 0x7fa40034b500 0x7fa2f4637a40 0 0 0 12076538367374494 12076538367541119 12076538372069110 12076538372116815
@@ -0,0 +1,168 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,grd,Workgroup_Size,LDS_Per_Workgroup,scr,vgpr,SGPR,fbar,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"__amd_rocclr_fillBuffer.kd",0,0,0,931481,931486,33554432,256,0,0,8,32,6464,0x0,0x7f07d2e04180,4194304,3256368,416675080,12076535482203595,12076535726603916,12076535726928235,12076535727038578
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,931481,931486,32768,256,0,0,24,24,12480,0x0,0x7f07d2e35100,512,23210,2955744,12076535741499958,12076535741800904,12076535741806984,12076535741811928
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,931481,931486,4194304,256,0,0,24,24,12928,0x7f0902d9c900,0x7f07d2e35140,65536,175692,22419328,12076535741871739,12076535742100583,12076535742237702,12076535742241807
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,931481,931486,4194304,256,0,0,36,24,13632,0x7f0902d9c800,0x7f07d2e35180,65536,164476,20977744,12076535742309664,12076535742486342,12076535742738181,12076535742807600
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,931481,931486,4194304,256,0,0,28,24,14080,0x7f0902d9c700,0x7f07d2e351c0,65536,180104,22944384,12076535742840461,12076535743032420,12076535743287779,12076535743355419
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,931481,931486,4194304,256,0,0,24,24,14528,0x7f0902d9c600,0x7f07d2e35200,65536,186150,23822168,12076535743380976,12076535743566498,12076535743704738,12076535743708085
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,931481,931486,4194304,256,0,0,24,24,14976,0x7f0902d9c500,0x7f07d2e35240,65536,202920,25964704,12076535743757837,12076535743929217,12076535744068416,12076535744072142
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,931481,931486,4194304,256,0,0,24,24,15424,0x7f0902d9c400,0x7f07d2e35280,131072,248294,31713160,12076535744153914,12076535744326175,12076535744456095,12076535744459463
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,931481,931486,4194304,256,0,0,28,24,16128,0x7f0902d9c300,0x7f07d2e352c0,131072,234156,29960616,12076535744506951,12076535744681534,12076535744938493,12076535744980792
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,931481,931486,4194304,256,0,0,28,24,16832,0x7f0902d9ca00,0x7f07d2e35300,65536,178214,22731216,12076535745014104,12076535745195452,12076535745448892,12076535745491362
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,931481,931486,4194304,256,0,0,24,24,17536,0x7f0902d9c900,0x7f07d2e35340,131072,251778,32084984,12076535745515838,12076535745705051,12076535745836410,12076535745839920
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,931481,931486,4194304,256,0,0,24,24,18240,0x7f0902d9c800,0x7f07d2e35380,131072,246028,31596872,12076535745888080,12076535746060570,12076535746193529,12076535746197185
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,931481,931486,4194304,256,0,0,24,24,18944,0x7f0902d9c700,0x7f07d2e353c0,131072,273886,34936256,12076535746260092,12076535746425688,12076535746557368,12076535746560791
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,931481,931486,4194304,256,0,0,28,24,19904,0x7f0902d9c600,0x7f07d2e35400,131072,204134,26153584,12076535746610524,12076535746781207,12076535747031766,12076535747100595
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,931481,931486,4194304,256,0,0,28,24,20608,0x7f0902d9c500,0x7f07d2e35440,65536,170504,21882928,12076535747128638,12076535747313365,12076535747568565,12076535747637744
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,931481,931486,4194304,256,0,0,24,24,21312,0x7f0902d9c400,0x7f07d2e35480,131072,249316,31831128,12076535747666298,12076535747844244,12076535747978963,12076535747982426
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,931481,931486,4194304,256,0,0,24,24,22016,0x7f0902d9c300,0x7f07d2e354c0,131072,245638,31443464,12076535748034513,12076535748211282,12076535748345202,12076535748348607
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,931481,931486,4194304,256,0,0,24,24,22720,0x7f0902d9ca00,0x7f07d2e35500,131072,280486,35867256,12076535748408689,12076535748570961,12076535748702321,12076535748705841
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,931481,931486,4194304,256,0,0,28,24,23680,0x7f0902d9c900,0x7f07d2e35540,131072,214098,27402864,12076535748755544,12076535748917360,12076535749174479,12076535749242960
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,931481,931486,4194304,256,0,0,28,24,24384,0x7f0902d9c800,0x7f07d2e35580,65536,183512,23474984,12076535749279118,12076535749462958,12076535749715277,12076535749783957
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,931481,931486,4194304,256,0,0,24,24,25088,0x7f0902d9c700,0x7f07d2e355c0,131072,254032,32614920,12076535749814223,12076535749995436,12076535750127276,12076535750130992
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,931481,931486,4194304,256,0,0,24,24,25792,0x7f0902d9c600,0x7f07d2e35600,131072,251624,32070864,12076535750184021,12076535750352555,12076535750482955,12076535750486604
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,931481,931486,4194304,256,0,0,24,24,26496,0x7f0902d9c500,0x7f07d2e35640,131072,244262,31359992,12076535750547497,12076535750709354,12076535750840554,12076535750843848
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,931481,931486,4194304,256,0,0,28,24,27712,0x7f0902d9c400,0x7f07d2e35680,131072,207754,26606728,12076535750892499,12076535751061353,12076535751318472,12076535751387640
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,931481,931486,4194304,256,0,0,28,24,28416,0x7f0902d9c300,0x7f07d2e356c0,65536,164360,20931088,12076535751415181,12076535751593511,12076535751848870,12076535751916353
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,931481,931486,4194304,256,0,0,24,24,29120,0x7f0902d9ca00,0x7f07d2e35700,131072,246736,31616176,12076535751941921,12076535752124709,12076535752255749,12076535752259461
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,931481,931486,4194304,256,0,0,24,24,30080,0x7f0902d9c900,0x7f07d2e35740,131072,247826,31848216,12076535752310176,12076535752473988,12076535752606788,12076535752610204
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,931481,931486,4194304,256,0,0,24,24,30784,0x7f0902d9c800,0x7f07d2e35780,131072,243760,31426976,12076535752670346,12076535752830627,12076535752964226,12076535752967719
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,931481,931486,4194304,256,0,0,28,24,32000,0x7f0902d9c700,0x7f07d2e357c0,131072,212792,27189448,12076535753022020,12076535753204386,12076535753463425,12076535753530947
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,931481,931486,4194304,256,0,0,28,24,32960,0x7f0902d9c600,0x7f07d2e35800,65536,174558,22325168,12076535753555212,12076535753734144,12076535753985023,12076535754054691
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,931481,931486,4194304,256,0,0,24,24,33920,0x7f0902d9c500,0x7f07d2e35840,131072,245656,31490712,12076535754082643,12076535754259902,12076535754394942,12076535754398460
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,931481,931486,4194304,256,0,0,24,24,34880,0x7f0902d9c400,0x7f07d2e35880,131072,246270,31481920,12076535754446980,12076535754608701,12076535754743260,12076535754746718
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,931481,931486,4194304,256,0,0,24,24,35840,0x7f0902d9c300,0x7f07d2e358c0,131072,253010,32386096,12076535754808172,12076535754969820,12076535755099099,12076535755102971
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,931481,931486,4194304,256,0,0,28,24,37312,0x7f0902d9ca00,0x7f07d2e35900,131072,207218,26665656,12076535755152102,12076535755319418,12076535755579898,12076535755647163
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,931481,931486,4194304,256,0,0,28,24,38272,0x7f0902d9c900,0x7f07d2e35940,65536,197618,25337616,12076535755669585,12076535755850137,12076535756103576,12076535756171318
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,931481,931486,4194304,256,0,0,24,24,39232,0x7f0902d9c800,0x7f07d2e35980,131072,251210,32286040,12076535756198038,12076535756378135,12076535756507094,12076535756510429
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,931481,931486,4194304,256,0,0,24,24,40192,0x7f0902d9c700,0x7f07d2e359c0,131072,254124,32474144,12076535756559220,12076535756725334,12076535756857333,12076535756860710
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,931481,931486,4194304,256,0,0,24,24,41152,0x7f0902d9c600,0x7f07d2e35a00,131072,259718,33164160,12076535756921513,12076535757086773,12076535757219252,12076535757222784
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,931481,931486,4194304,256,0,0,28,24,42624,0x7f0902d9c500,0x7f07d2e35a40,131072,212662,27174112,12076535757271565,12076535757441811,12076535757697330,12076535757763439
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,931481,931486,4194304,256,0,0,28,24,43584,0x7f0902d9c400,0x7f07d2e35a80,65536,192520,24657048,12076535757787324,12076535757967890,12076535758226129,12076535758293045
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,931481,931486,4194304,256,0,0,24,24,44544,0x7f0902d9c300,0x7f07d2e35ac0,131072,244208,31190864,12076535758317170,12076535758497168,12076535758625007,12076535758628338
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,931481,931486,4194304,256,0,0,24,24,45760,0x7f0902d9ca00,0x7f07d2e35b00,131072,245870,31585864,12076535758676478,12076535758845007,12076535758977006,12076535758980343
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,931481,931486,4194304,256,0,0,24,24,46720,0x7f0902d9c900,0x7f07d2e35b40,131072,249294,31931304,12076535759043641,12076535759202605,12076535759333165,12076535759336766
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,931481,931486,4194304,256,0,0,28,24,48448,0x7f0902d9c800,0x7f07d2e35b80,131072,206218,26319328,12076535759378744,12076535759550444,12076535759810443,12076535759877041
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,931481,931486,4194304,256,0,0,28,24,49408,0x7f0902d9c700,0x7f07d2e35bc0,65536,170500,21823672,12076535759900815,12076535760083882,12076535760337642,12076535760406656
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,931481,931486,4194304,256,0,0,24,24,50368,0x7f0902d9c600,0x7f07d2e35c00,131072,251582,32259376,12076535760434698,12076535760609641,12076535760740040,12076535760743443
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,931481,931486,4194304,256,0,0,24,24,51584,0x7f0902d9c500,0x7f07d2e35c40,131072,249270,31893144,12076535760792654,12076535760961480,12076535761102919,12076535761106789
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,931481,931486,4194304,256,0,0,24,24,52544,0x7f0902d9c400,0x7f07d2e35c80,131072,246976,31581480,12076535761169635,12076535761331718,12076535761464518,12076535761468201
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,931481,931486,4194304,256,0,0,28,24,54272,0x7f0902d9c300,0x7f07d2e35cc0,131072,216190,27664520,12076535761516901,12076535761683397,12076535761944676,12076535762016901
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,931481,931486,4194304,256,0,0,28,24,55488,0x7f0902d9ca00,0x7f07d2e35d00,65536,179178,22953424,12076535762042028,12076535762222275,12076535762478274,12076535762546216
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,931481,931486,4194304,256,0,0,24,24,56704,0x7f0902d9c900,0x7f07d2e35d40,131072,268848,34302832,12076535762572715,12076535762746754,12076535762876353,12076535762879887
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,931481,931486,4194304,256,0,0,24,24,58176,0x7f0902d9c800,0x7f07d2e35d80,131072,254066,32505440,12076535762930821,12076535763098272,12076535763242112,12076535763245797
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,931481,931486,4194304,256,0,0,24,24,59392,0x7f0902d9c700,0x7f07d2e35dc0,131072,254464,32498544,12076535763306641,12076535763466111,12076535763638591,12076535763642585
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,931481,931486,4194304,256,0,0,28,24,61376,0x7f0902d9c600,0x7f07d2e35e00,131072,247400,31932200,12076535763691106,12076535763856670,12076535764116989,12076535764185105
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,931481,931486,4194304,256,0,0,28,24,62592,0x7f0902d9c500,0x7f07d2e35e40,65536,174752,22359536,12076535764212716,12076535764387548,12076535764645627,12076535764713207
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,931481,931486,4194304,256,0,0,24,24,63808,0x7f0902d9c400,0x7f07d2e35e80,131072,254116,32560624,12076535764738193,12076535764917946,12076535765047226,12076535765050965
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,931481,931486,4194304,256,0,0,24,24,65280,0x7f0902d9c300,0x7f07d2e35ec0,131072,265428,34130688,12076535765101499,12076535765272665,12076535765409145,12076535765412748
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,931481,931486,4194304,256,0,0,24,24,66496,0x7f0902d9ca00,0x7f07d2e35f00,131072,251760,32130976,12076535765472980,12076535765631704,12076535765765143,12076535765768740
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,931481,931486,4194304,256,0,0,28,24,68480,0x7f0902d9c900,0x7f07d2e35f40,131072,266630,34210168,12076535765818683,12076535765976183,12076535766243062,12076535766292695
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,931481,931486,4194304,256,0,0,28,24,69696,0x7f0902d9c800,0x7f07d2e35f80,65536,176114,22519856,12076535766317060,12076535766495861,12076535766750900,12076535766797213
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,931481,931486,4194304,256,0,0,24,24,70912,0x7f0902d9c700,0x7f07d2e35fc0,131072,253938,32301352,12076535766824304,12076535766997299,12076535767130259,12076535767134280
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,931481,931486,4194304,256,0,0,24,24,72384,0x7f0902d9c600,0x7f07d2e36000,131072,244926,31439056,12076535767183742,12076535767352178,12076535767492978,12076535767496554
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,931481,931486,4194304,256,0,0,24,24,73600,0x7f0902d9c500,0x7f07d2e36040,131072,250200,31967768,12076535767557167,12076535767713297,12076535767852976,12076535767856544
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,931481,931486,4194304,256,0,0,28,24,75840,0x7f0902d9c400,0x7f07d2e36080,131072,209460,26566632,12076535767905485,12076535768076656,12076535768348655,12076535768398963
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,931481,931486,4194304,256,0,0,28,24,77056,0x7f0902d9c300,0x7f07d2e360c0,65536,172708,22036104,12076535768424510,12076535768606094,12076535768902413,12076535768924801
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,931481,931486,4194304,256,0,0,24,24,78272,0x7f0902d9ca00,0x7f07d2e36100,131072,248806,31816208,12076535768968202,12076535769133932,12076535769267212,12076535769270795
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,931481,931486,4194304,256,0,0,24,24,80000,0x7f0902d9c900,0x7f07d2e36140,131072,211576,27173496,12076535769319635,12076535769488011,12076535769632650,12076535769636184
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,931481,931486,4194304,256,0,0,24,24,81216,0x7f0902d9c800,0x7f07d2e36180,131072,248248,31743616,12076535769699171,12076535769855210,12076535769987529,12076535769991145
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,931481,931486,4194304,256,0,0,28,24,83456,0x7f0902d9c700,0x7f07d2e361c0,131072,205308,26396368,12076535770040116,12076535770206568,12076535770475528,12076535770525308
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,931481,931486,4194304,256,0,0,28,24,84928,0x7f0902d9c600,0x7f07d2e36200,65536,200150,25714536,12076535770550705,12076535770727367,12076535770977606,12076535770999831
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,931481,931486,4194304,256,0,0,24,24,86400,0x7f0902d9c500,0x7f07d2e36240,131072,259024,33237672,12076535771048461,12076535771211365,12076535771350085,12076535771353869
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,931481,931486,4194304,256,0,0,24,24,88128,0x7f0902d9c400,0x7f07d2e36280,131072,210488,26816104,12076535771397080,12076535771568644,12076535771719363,12076535771722996
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,931481,931486,4194304,256,0,0,24,24,89600,0x7f0902d9c300,0x7f07d2e362c0,131072,255326,32596984,12076535771799488,12076535771958243,12076535772095522,12076535772099486
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,931481,931486,4194304,256,0,0,28,24,92096,0x7f0902d9ca00,0x7f07d2e36300,131072,221646,28316016,12076535772149519,12076535772317761,12076535772584800,12076535772634592
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,931481,931486,4194304,256,0,0,28,24,93568,0x7f0902d9c900,0x7f07d2e36340,65536,180556,23015328,12076535772661191,12076535772834880,12076535773090079,12076535773141284
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,931481,931486,4194304,256,0,0,24,24,95040,0x7f0902d9c800,0x7f07d2e36380,131072,252764,32496864,12076535773169266,12076535773343038,12076535773482077,12076535773485645
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,931481,931486,4194304,256,0,0,24,24,96768,0x7f0902d9c700,0x7f07d2e363c0,131072,256718,32642296,12076535773533604,12076535773698877,12076535773856956,12076535773860472
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,931481,931486,4194304,256,0,0,24,24,98240,0x7f0902d9c600,0x7f07d2e36400,131072,247928,31648152,12076535773921786,12076535774087355,12076535774223355,12076535774227054
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,931481,931486,4194304,256,0,0,28,24,100736,0x7f0902d9c500,0x7f07d2e36440,131072,200730,25616384,12076535774278299,12076535774467034,12076535774735353,12076535774760516
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,931481,931486,4194304,256,0,0,28,24,102208,0x7f0902d9c400,0x7f07d2e36480,65536,181872,23237848,12076535774807073,12076535774966072,12076535775221432,12076535775249375
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,931481,931486,4194304,256,0,0,24,24,103680,0x7f0902d9c300,0x7f07d2e364c0,131072,250040,32105496,12076535775294149,12076535775478071,12076535775611510,12076535775614986
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,931481,931486,4194304,256,0,0,24,24,105664,0x7f0902d9ca00,0x7f07d2e36500,131072,250352,32093352,12076535775662674,12076535775855989,12076535776022869,12076535776026661
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,931481,931486,4194304,256,0,0,24,24,107136,0x7f0902d9c900,0x7f07d2e36540,131072,247916,31487336,12076535776093175,12076535776259988,12076535776395988,12076535776399645
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,931481,931486,4194304,256,0,0,28,24,109888,0x7f0902d9c800,0x7f07d2e36580,131072,212990,27290152,12076535776443316,12076535776618707,12076535776887346,12076535776912188
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,931481,931486,4194304,256,0,0,28,24,111360,0x7f0902d9c700,0x7f07d2e365c0,65536,174340,22404208,12076535776956621,12076535777127665,12076535777385584,12076535777413762
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,931481,931486,4194304,256,0,0,24,24,112832,0x7f0902d9c600,0x7f07d2e36600,131072,240372,30868120,12076535777458324,12076535777621584,12076535777751823,12076535777755708
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,931481,931486,4194304,256,0,0,24,24,114816,0x7f0902d9c500,0x7f07d2e36640,131072,248806,31678168,12076535777807083,12076535777967342,12076535778141422,12076535778145182
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,931481,931486,4194304,256,0,0,24,24,116288,0x7f0902d9c400,0x7f07d2e36680,131072,250278,31894328,12076535778211245,12076535778376461,12076535778512141,12076535778515781
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,931481,931486,4194304,256,0,0,28,24,119040,0x7f0902d9c300,0x7f07d2e366c0,131072,196654,25180536,12076535778565193,12076535778736140,12076535778999819,12076535779026311
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,931481,931486,4194304,256,0,0,28,24,120768,0x7f0902d9ca00,0x7f07d2e36700,65536,172424,22133856,12076535779069071,12076535779229738,12076535779492617,12076535779516673
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,931481,931486,4194304,256,0,0,24,24,122496,0x7f0902d9c900,0x7f07d2e36740,131072,249560,32080976,12076535779560214,12076535779722856,12076535779864296,12076535779868117
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,931481,931486,4194304,256,0,0,24,24,124736,0x7f0902d9c800,0x7f07d2e36780,131072,258696,32879344,12076535779922268,12076535780094055,12076535780277735,12076535780281726
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,931481,931486,4194304,256,0,0,24,24,126464,0x7f0902d9c700,0x7f07d2e367c0,131072,252498,32055280,12076535780342159,12076535780502374,12076535780641413,12076535780645062
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,931481,931486,4194304,256,0,0,20,24,127936,0x7f0902d9c600,0x7f07d2e36800,131072,246148,31514552,12076535780696878,12076535780860293,12076535781126532,12076535781155682
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,931481,931486,4194304,256,0,0,28,24,129664,0x7f0902d9c500,0x7f07d2e36840,65536,177902,22769528,12076535781197109,12076535781359011,12076535781613090,12076535781637819
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,931481,931486,4194304,256,0,0,24,24,131392,0x7f0902d9c400,0x7f07d2e36880,131072,252396,32364072,12076535781680769,12076535781840289,12076535781974849,12076535781978553
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,931481,931486,4194304,256,0,0,24,24,133632,0x7f0902d9c300,0x7f07d2e368c0,131072,254792,32535312,12076535782034837,12076535782212608,12076535782404927,12076535782433028
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,931481,931486,4194304,256,0,0,24,24,135360,0x7f0902d9ca00,0x7f07d2e36900,131072,248366,31793552,12076535782487429,12076535782652287,12076535782791486,12076535782795262
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,931481,931486,4194304,256,0,0,20,24,136832,0x7f0902d9c900,0x7f07d2e36940,131072,244972,31322200,12076535782845636,12076535783029085,12076535783313564,12076535783340496
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,931481,931486,4194304,256,0,0,28,24,138560,0x7f0902d9c800,0x7f07d2e36980,65536,190124,24376528,12076535783377775,12076535783553244,12076535783810363,12076535783831048
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,931481,931486,4194304,256,0,0,24,24,140288,0x7f0902d9c700,0x7f07d2e369c0,131072,241170,31060528,12076535783875952,12076535784043482,12076535784178202,12076535784181981
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,931481,931486,4194304,256,0,0,24,24,142784,0x7f0902d9c600,0x7f07d2e36a00,131072,247828,31622776,12076535784230381,12076535784402681,12076535784614040,12076535784638470
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,931481,931486,4194304,256,0,0,24,24,144768,0x7f0902d9c500,0x7f07d2e36a40,131072,234952,29939672,12076535784701257,12076535784864279,12076535785001879,12076535785006485
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,931481,931486,4194304,256,0,0,20,24,145728,0x7f0902d9c400,0x7f07d2e36a80,131072,254604,32747768,12076535785055386,12076535785229718,12076535785538357,12076535785564312
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,931481,931486,4194304,256,0,0,28,24,147712,0x7f0902d9c300,0x7f07d2e36ac0,65536,175756,22480392,12076535785607042,12076535785767476,12076535786026835,12076535786052110
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,931481,931486,4194304,256,0,0,24,24,149696,0x7f0902d9ca00,0x7f07d2e36b00,131072,250858,32293176,12076535786103586,12076535786269555,12076535786408594,12076535786412410
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,931481,931486,4194304,256,0,0,24,24,152192,0x7f0902d9c900,0x7f07d2e36b40,131072,253218,32269856,12076535786461531,12076535786623473,12076535786852113,12076535786876423
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,931481,931486,4194304,256,0,0,24,24,154176,0x7f0902d9c800,0x7f07d2e36b80,131072,254168,32385920,12076535786933600,12076535787109072,12076535787244751,12076535787248535
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,931481,931486,4194304,256,0,0,20,24,155648,0x7f0902d9c700,0x7f07d2e36bc0,131072,249452,32103096,12076535787297787,12076535787476110,12076535787806189,12076535787826761
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,931481,931486,4194304,256,0,0,28,24,157632,0x7f0902d9c600,0x7f07d2e36c00,65536,187108,23981928,12076535787871374,12076535788040429,12076535788304268,12076535788331029
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,931481,931486,4194304,256,0,0,24,24,159616,0x7f0902d9c500,0x7f07d2e36c40,131072,247350,31619328,12076535788375071,12076535788538027,12076535788682346,12076535788686220
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,931481,931486,4194304,256,0,0,24,24,162368,0x7f0902d9c400,0x7f07d2e36c80,131072,246700,31634104,12076535788737034,12076535788899306,12076535789146505,12076535789174738
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,931481,931486,4194304,256,0,0,24,24,164608,0x7f0902d9c300,0x7f07d2e36cc0,131072,247578,31620440,12076535789226074,12076535789392264,12076535789533864,12076535789537593
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,931481,931486,4194304,256,0,0,20,24,166336,0x7f0902d9ca00,0x7f07d2e36d00,131072,253398,32529688,12076535789585973,12076535789761345,12076535790138145,12076535790168056
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,931481,931486,4194304,256,0,0,28,24,168576,0x7f0902d9c900,0x7f07d2e36d40,65536,174194,22274640,12076535790209373,12076535790373823,12076535790637982,12076535790660943
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,931481,931486,4194304,256,0,0,24,24,170816,0x7f0902d9c800,0x7f07d2e36d80,131072,244474,31260976,12076535790709183,12076535790870302,12076535791007422,12076535791010253
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,931481,931486,4194304,256,0,0,24,24,174080,0x7f0902d9c700,0x7f07d2e36dc0,131072,245246,31511792,12076535791060015,12076535791230141,12076535791511261,12076535791535720
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,931481,931486,4194304,256,0,0,24,24,176576,0x7f0902d9c600,0x7f07d2e36e00,131072,272202,34692688,12076535791586184,12076535791745820,12076535791885980,12076535791888607
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,931481,931486,4194304,256,0,0,20,24,177792,0x7f0902d9c500,0x7f07d2e36e40,131072,248248,31698312,12076535791939060,12076535792115099,12076535792542138,12076535792568141
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,931481,931486,4194304,256,0,0,28,24,180288,0x7f0902d9c400,0x7f07d2e36e80,65536,186592,23892056,12076535792610319,12076535792768058,12076535793030937,12076535793055427
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,931481,931486,4194304,256,0,0,24,24,182784,0x7f0902d9c300,0x7f07d2e36ec0,131072,250486,31912200,12076535793104528,12076535793269817,12076535793407256,12076535793410157
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,931481,931486,4194304,256,0,0,24,24,186304,0x7f0902d9ca00,0x7f07d2e36f00,131072,268634,34525448,12076535793458437,12076535793626456,12076535793943095,12076535793966161
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,931481,931486,4194304,256,0,0,24,24,189312,0x7f0902d9c900,0x7f07d2e36f40,131072,252822,32410752,12076535794030641,12076535794191895,12076535794345014,12076535794347881
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,931481,931486,4194304,256,0,0,20,24,190784,0x7f0902d9c800,0x7f07d2e36f80,131072,247220,31441808,12076535794395910,12076535794573494,12076535795093653,12076535795117893
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,931481,931486,4194304,256,0,0,28,24,193792,0x7f0902d9c700,0x7f07d2e36fc0,65536,173626,22178136,12076535795170702,12076535795334932,12076535795633171,12076535795656455
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,931481,931486,4194304,256,0,0,24,24,196800,0x7f0902d9c600,0x7f07d2e37000,131072,246780,31460328,12076535795709153,12076535795872051,12076535796026771,12076535796029710
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,931481,931486,4194304,256,0,0,24,24,201088,0x7f0902d9c500,0x7f07d2e37040,131072,229086,29217376,12076535796081105,12076535796263410,12076535796650129,12076535796675861
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,931481,931486,4194304,256,0,0,24,24,204608,0x7f0902d9c400,0x7f07d2e37080,131072,255960,32676656,12076535796731535,12076535796893489,12076535797070928,12076535797073922
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,931481,931486,4194304,256,0,0,20,24,206080,0x7f0902d9c300,0x7f07d2e370c0,131072,244194,31503320,12076535797124085,12076535797292048,12076535797916046,12076535797939592
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,931481,931486,4194304,256,0,0,28,24,209600,0x7f0902d9ca00,0x7f07d2e37100,65536,184072,23645432,12076535797983404,12076535798147726,12076535798477485,12076535798502169
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,931481,931486,4194304,256,0,0,24,24,213120,0x7f0902d9c900,0x7f07d2e37140,131072,271282,34743344,12076535798545679,12076535798701325,12076535798880524,12076535798883448
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,931481,931486,4194304,256,0,0,24,24,218176,0x7f0902d9c800,0x7f07d2e37180,131072,242470,31230944,12076535798932739,12076535799103244,12076535799580843,12076535799609268
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,931481,931486,4194304,256,0,0,24,24,222208,0x7f0902d9c700,0x7f07d2e371c0,131072,247232,31706144,12076535799664541,12076535799827402,12076535800027882,12076535800053374
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,931481,931486,4194304,256,0,0,20,24,223936,0x7f0902d9c600,0x7f07d2e37200,131072,240382,30902936,12076535800093789,12076535800253801,12076535800959240,12076535800985197
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,931481,931486,4194304,256,0,0,28,24,227968,0x7f0902d9c500,0x7f07d2e37240,65536,172664,22120216,12076535801034138,12076535801192679,12076535801566758,12076535801592497
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,931481,931486,4194304,256,0,0,24,24,232000,0x7f0902d9c400,0x7f07d2e37280,131072,247830,31758136,12076535801642821,12076535801803398,12076535802007237,12076535802032135
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,931481,931486,4194304,256,0,0,24,24,237824,0x7f0902d9c300,0x7f07d2e372c0,131072,276044,35376792,12076535802077709,12076535802235397,12076535802780196,12076535802805994
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,931481,931486,4194304,256,0,0,24,24,242368,0x7f0902d9ca00,0x7f07d2e37300,131072,245004,31416496,12076535802860706,12076535803030115,12076535803254435,12076535803281779
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,931481,931486,4194304,256,0,0,20,24,243584,0x7f0902d9c900,0x7f07d2e37340,131072,248152,31499344,12076535803322906,12076535803482434,12076535804284032,12076535804311384
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,931481,931486,4194304,256,0,0,28,24,248128,0x7f0902d9c800,0x7f07d2e37380,65536,192356,24555984,12076535804358011,12076535804533792,12076535804979551,12076535805009192
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,931481,931486,4194304,256,0,0,24,24,252672,0x7f0902d9c700,0x7f07d2e373c0,131072,265446,33991336,12076535805056100,12076535805216030,12076535805478430,12076535805504694
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,931481,931486,4194304,256,0,0,24,24,259264,0x7f0902d9c600,0x7f07d2e37400,131072,228180,29320592,12076535805552934,12076535805714269,12076535806325468,12076535806355006
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,931481,931486,4194304,256,0,0,24,24,264832,0x7f0902d9c500,0x7f07d2e37440,131072,251198,32153504,12076535806411711,12076535806572827,12076535806842587,12076535806863562
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,931481,931486,4194304,256,0,0,20,24,266304,0x7f0902d9c400,0x7f07d2e37480,131072,252746,32146208,12076535806908185,12076535807075066,12076535808063704,12076535808133644
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,931481,931486,4194304,256,0,0,28,24,271872,0x7f0902d9c300,0x7f07d2e374c0,65536,173106,22358800,12076535808164101,12076535808346743,12076535808864982,12076535808933211
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,931481,931486,4194304,256,0,0,24,24,277440,0x7f0902d9ca00,0x7f07d2e37500,131072,244800,31286192,12076535808962646,12076535809147702,12076535809422261,12076535809491410
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,931481,931486,4194304,256,0,0,12,24,279936,0x7f0902d9c900,0x7f07d2e37540,131072,259600,33280864,12076535809521185,12076535809694100,12076535810434739,12076535810503583
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,931481,931486,4194304,256,0,0,24,24,286528,0x7f0902d9c800,0x7f07d2e37580,131072,244426,31258648,12076535810545681,12076535810708018,12076535811025938,12076535811094492
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,931481,931486,4194304,256,0,0,20,24,288000,0x7f0902d9c700,0x7f07d2e375c0,131072,245632,31453320,12076535811124578,12076535811302737,12076535812477934,12076535812546192
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,931481,931486,4194304,256,0,0,32,24,294592,0x7f0902d9c600,0x7f07d2e37600,65536,170046,21731288,12076535812577931,12076535812749934,12076535813363852,12076535813431970
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,931481,931486,4194304,256,0,0,24,24,301184,0x7f0902d9c500,0x7f07d2e37640,131072,248710,31768864,12076535813463899,12076535813636972,12076535813957451,12076535814025394
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,931481,931486,4194304,256,0,0,12,24,304960,0x7f0902d9c400,0x7f07d2e37680,131072,248358,31669136,12076535814056531,12076535814229450,12076535815109929,12076535815178519
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,931481,931486,4194304,256,0,0,24,24,313600,0x7f0902d9c300,0x7f07d2e376c0,131072,252416,32524368,12076535815221809,12076535815383688,12076535815818087,12076535815885494
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,931481,931486,4194304,256,0,0,20,24,314816,0x7f0902d9ca00,0x7f07d2e37700,131072,264090,33538024,12076535815916171,12076535816107206,12076535817660643,12076535817730826
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,931481,931486,4194304,256,0,0,20,24,317568,0x7f0902d9c900,0x7f07d2e37740,65536,177406,22597216,12076535817763046,12076535817945122,12076535818744001,12076535818812649
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,931481,931486,4194304,256,0,0,12,24,320320,0x7f0902d9c800,0x7f07d2e37780,131072,250710,31869752,12076535818840731,12076535819030880,12076535819469919,12076535819536936
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,931481,931486,4194304,256,0,0,12,24,324096,0x7f0902d9c700,0x7f07d2e377c0,131072,255298,32584632,12076535819563996,12076535819740798,12076535820901276,12076535820969440
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,931481,931486,4194304,256,0,0,12,24,328896,0x7f0902d9c600,0x7f07d2e37800,131072,248216,31699144,12076535821012781,12076535821174555,12076535821961113,12076535822030574
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,931481,931486,4194304,256,0,0,20,24,330112,0x7f0902d9c500,0x7f07d2e37840,131072,232208,29890112,12076535822062013,12076535822234553,12076535825293266,12076535825360979
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,931481,931486,4194304,256,0,0,20,24,332864,0x7f0902d9c400,0x7f07d2e37880,65536,205980,26381080,12076535825392768,12076535825570225,12076535827119822,12076535827188138
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,931481,931486,4194304,256,0,0,12,24,335616,0x7f0902d9c300,0x7f07d2e378c0,131072,253968,32336872,12076535827218074,12076535827399021,12076535828189900,12076535828258429
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,931481,931486,4194304,256,0,0,12,24,339392,0x7f0902d9ca00,0x7f07d2e37900,131072,245034,31582216,12076535828289777,12076535828475019,12076535830759654,12076535830828349
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,931481,931486,4194304,256,0,0,12,24,344192,0x7f0902d9c900,0x7f07d2e37940,131072,246990,31470576,12076535830872331,12076535831043013,12076535832580130,12076535832649998
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,931481,931486,4194304,256,0,0,20,24,345408,0x7f0902d9c800,0x7f07d2e37980,131072,248498,31682120,12076535832681005,12076535832863169,12076535838926356,12076535838998787
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,931481,931486,4194304,256,0,0,20,24,348160,0x7f0902d9c700,0x7f07d2e379c0,65536,164836,21120504,12076535839030656,12076535839214835,12076535842261389,12076535842334422
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,931481,931486,4194304,256,0,0,12,24,350912,0x7f0902d9c600,0x7f07d2e37a00,131072,269178,34623672,12076535842363666,12076535842546668,12076535844087145,12076535844155389
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,931481,931486,4194304,256,0,0,12,24,0,0x7f0902d9c500,0x7f07d2e37a40,131072,229584,29528560,12076535844185946,12076535844363944,12076535848893694,12076535848961960
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid grd Workgroup_Size LDS_Per_Workgroup scr vgpr SGPR fbar sig obj SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 __amd_rocclr_fillBuffer.kd 0 0 0 931481 931486 33554432 256 0 0 8 32 6464 0x0 0x7f07d2e04180 4194304 3256368 416675080 12076535482203595 12076535726603916 12076535726928235 12076535727038578
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 931481 931486 32768 256 0 0 24 24 12480 0x0 0x7f07d2e35100 512 23210 2955744 12076535741499958 12076535741800904 12076535741806984 12076535741811928
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 4 931481 931486 4194304 256 0 0 24 24 12928 0x7f0902d9c900 0x7f07d2e35140 65536 175692 22419328 12076535741871739 12076535742100583 12076535742237702 12076535742241807
5 3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 6 931481 931486 4194304 256 0 0 36 24 13632 0x7f0902d9c800 0x7f07d2e35180 65536 164476 20977744 12076535742309664 12076535742486342 12076535742738181 12076535742807600
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 8 931481 931486 4194304 256 0 0 28 24 14080 0x7f0902d9c700 0x7f07d2e351c0 65536 180104 22944384 12076535742840461 12076535743032420 12076535743287779 12076535743355419
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 10 931481 931486 4194304 256 0 0 24 24 14528 0x7f0902d9c600 0x7f07d2e35200 65536 186150 23822168 12076535743380976 12076535743566498 12076535743704738 12076535743708085
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 12 931481 931486 4194304 256 0 0 24 24 14976 0x7f0902d9c500 0x7f07d2e35240 65536 202920 25964704 12076535743757837 12076535743929217 12076535744068416 12076535744072142
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 14 931481 931486 4194304 256 0 0 24 24 15424 0x7f0902d9c400 0x7f07d2e35280 131072 248294 31713160 12076535744153914 12076535744326175 12076535744456095 12076535744459463
10 8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 16 931481 931486 4194304 256 0 0 28 24 16128 0x7f0902d9c300 0x7f07d2e352c0 131072 234156 29960616 12076535744506951 12076535744681534 12076535744938493 12076535744980792
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 18 931481 931486 4194304 256 0 0 28 24 16832 0x7f0902d9ca00 0x7f07d2e35300 65536 178214 22731216 12076535745014104 12076535745195452 12076535745448892 12076535745491362
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 20 931481 931486 4194304 256 0 0 24 24 17536 0x7f0902d9c900 0x7f07d2e35340 131072 251778 32084984 12076535745515838 12076535745705051 12076535745836410 12076535745839920
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 22 931481 931486 4194304 256 0 0 24 24 18240 0x7f0902d9c800 0x7f07d2e35380 131072 246028 31596872 12076535745888080 12076535746060570 12076535746193529 12076535746197185
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 24 931481 931486 4194304 256 0 0 24 24 18944 0x7f0902d9c700 0x7f07d2e353c0 131072 273886 34936256 12076535746260092 12076535746425688 12076535746557368 12076535746560791
15 13 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 26 931481 931486 4194304 256 0 0 28 24 19904 0x7f0902d9c600 0x7f07d2e35400 131072 204134 26153584 12076535746610524 12076535746781207 12076535747031766 12076535747100595
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 28 931481 931486 4194304 256 0 0 28 24 20608 0x7f0902d9c500 0x7f07d2e35440 65536 170504 21882928 12076535747128638 12076535747313365 12076535747568565 12076535747637744
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 30 931481 931486 4194304 256 0 0 24 24 21312 0x7f0902d9c400 0x7f07d2e35480 131072 249316 31831128 12076535747666298 12076535747844244 12076535747978963 12076535747982426
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 32 931481 931486 4194304 256 0 0 24 24 22016 0x7f0902d9c300 0x7f07d2e354c0 131072 245638 31443464 12076535748034513 12076535748211282 12076535748345202 12076535748348607
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 34 931481 931486 4194304 256 0 0 24 24 22720 0x7f0902d9ca00 0x7f07d2e35500 131072 280486 35867256 12076535748408689 12076535748570961 12076535748702321 12076535748705841
20 18 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 36 931481 931486 4194304 256 0 0 28 24 23680 0x7f0902d9c900 0x7f07d2e35540 131072 214098 27402864 12076535748755544 12076535748917360 12076535749174479 12076535749242960
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 38 931481 931486 4194304 256 0 0 28 24 24384 0x7f0902d9c800 0x7f07d2e35580 65536 183512 23474984 12076535749279118 12076535749462958 12076535749715277 12076535749783957
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 40 931481 931486 4194304 256 0 0 24 24 25088 0x7f0902d9c700 0x7f07d2e355c0 131072 254032 32614920 12076535749814223 12076535749995436 12076535750127276 12076535750130992
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 42 931481 931486 4194304 256 0 0 24 24 25792 0x7f0902d9c600 0x7f07d2e35600 131072 251624 32070864 12076535750184021 12076535750352555 12076535750482955 12076535750486604
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 44 931481 931486 4194304 256 0 0 24 24 26496 0x7f0902d9c500 0x7f07d2e35640 131072 244262 31359992 12076535750547497 12076535750709354 12076535750840554 12076535750843848
25 23 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 46 931481 931486 4194304 256 0 0 28 24 27712 0x7f0902d9c400 0x7f07d2e35680 131072 207754 26606728 12076535750892499 12076535751061353 12076535751318472 12076535751387640
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 48 931481 931486 4194304 256 0 0 28 24 28416 0x7f0902d9c300 0x7f07d2e356c0 65536 164360 20931088 12076535751415181 12076535751593511 12076535751848870 12076535751916353
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 50 931481 931486 4194304 256 0 0 24 24 29120 0x7f0902d9ca00 0x7f07d2e35700 131072 246736 31616176 12076535751941921 12076535752124709 12076535752255749 12076535752259461
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 52 931481 931486 4194304 256 0 0 24 24 30080 0x7f0902d9c900 0x7f07d2e35740 131072 247826 31848216 12076535752310176 12076535752473988 12076535752606788 12076535752610204
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 54 931481 931486 4194304 256 0 0 24 24 30784 0x7f0902d9c800 0x7f07d2e35780 131072 243760 31426976 12076535752670346 12076535752830627 12076535752964226 12076535752967719
30 28 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 56 931481 931486 4194304 256 0 0 28 24 32000 0x7f0902d9c700 0x7f07d2e357c0 131072 212792 27189448 12076535753022020 12076535753204386 12076535753463425 12076535753530947
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 58 931481 931486 4194304 256 0 0 28 24 32960 0x7f0902d9c600 0x7f07d2e35800 65536 174558 22325168 12076535753555212 12076535753734144 12076535753985023 12076535754054691
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 60 931481 931486 4194304 256 0 0 24 24 33920 0x7f0902d9c500 0x7f07d2e35840 131072 245656 31490712 12076535754082643 12076535754259902 12076535754394942 12076535754398460
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 62 931481 931486 4194304 256 0 0 24 24 34880 0x7f0902d9c400 0x7f07d2e35880 131072 246270 31481920 12076535754446980 12076535754608701 12076535754743260 12076535754746718
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 64 931481 931486 4194304 256 0 0 24 24 35840 0x7f0902d9c300 0x7f07d2e358c0 131072 253010 32386096 12076535754808172 12076535754969820 12076535755099099 12076535755102971
35 33 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 66 931481 931486 4194304 256 0 0 28 24 37312 0x7f0902d9ca00 0x7f07d2e35900 131072 207218 26665656 12076535755152102 12076535755319418 12076535755579898 12076535755647163
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 68 931481 931486 4194304 256 0 0 28 24 38272 0x7f0902d9c900 0x7f07d2e35940 65536 197618 25337616 12076535755669585 12076535755850137 12076535756103576 12076535756171318
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 70 931481 931486 4194304 256 0 0 24 24 39232 0x7f0902d9c800 0x7f07d2e35980 131072 251210 32286040 12076535756198038 12076535756378135 12076535756507094 12076535756510429
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 72 931481 931486 4194304 256 0 0 24 24 40192 0x7f0902d9c700 0x7f07d2e359c0 131072 254124 32474144 12076535756559220 12076535756725334 12076535756857333 12076535756860710
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 74 931481 931486 4194304 256 0 0 24 24 41152 0x7f0902d9c600 0x7f07d2e35a00 131072 259718 33164160 12076535756921513 12076535757086773 12076535757219252 12076535757222784
40 38 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 76 931481 931486 4194304 256 0 0 28 24 42624 0x7f0902d9c500 0x7f07d2e35a40 131072 212662 27174112 12076535757271565 12076535757441811 12076535757697330 12076535757763439
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 78 931481 931486 4194304 256 0 0 28 24 43584 0x7f0902d9c400 0x7f07d2e35a80 65536 192520 24657048 12076535757787324 12076535757967890 12076535758226129 12076535758293045
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 80 931481 931486 4194304 256 0 0 24 24 44544 0x7f0902d9c300 0x7f07d2e35ac0 131072 244208 31190864 12076535758317170 12076535758497168 12076535758625007 12076535758628338
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 82 931481 931486 4194304 256 0 0 24 24 45760 0x7f0902d9ca00 0x7f07d2e35b00 131072 245870 31585864 12076535758676478 12076535758845007 12076535758977006 12076535758980343
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 84 931481 931486 4194304 256 0 0 24 24 46720 0x7f0902d9c900 0x7f07d2e35b40 131072 249294 31931304 12076535759043641 12076535759202605 12076535759333165 12076535759336766
45 43 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 86 931481 931486 4194304 256 0 0 28 24 48448 0x7f0902d9c800 0x7f07d2e35b80 131072 206218 26319328 12076535759378744 12076535759550444 12076535759810443 12076535759877041
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 88 931481 931486 4194304 256 0 0 28 24 49408 0x7f0902d9c700 0x7f07d2e35bc0 65536 170500 21823672 12076535759900815 12076535760083882 12076535760337642 12076535760406656
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 90 931481 931486 4194304 256 0 0 24 24 50368 0x7f0902d9c600 0x7f07d2e35c00 131072 251582 32259376 12076535760434698 12076535760609641 12076535760740040 12076535760743443
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 92 931481 931486 4194304 256 0 0 24 24 51584 0x7f0902d9c500 0x7f07d2e35c40 131072 249270 31893144 12076535760792654 12076535760961480 12076535761102919 12076535761106789
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 94 931481 931486 4194304 256 0 0 24 24 52544 0x7f0902d9c400 0x7f07d2e35c80 131072 246976 31581480 12076535761169635 12076535761331718 12076535761464518 12076535761468201
50 48 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 96 931481 931486 4194304 256 0 0 28 24 54272 0x7f0902d9c300 0x7f07d2e35cc0 131072 216190 27664520 12076535761516901 12076535761683397 12076535761944676 12076535762016901
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 98 931481 931486 4194304 256 0 0 28 24 55488 0x7f0902d9ca00 0x7f07d2e35d00 65536 179178 22953424 12076535762042028 12076535762222275 12076535762478274 12076535762546216
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 100 931481 931486 4194304 256 0 0 24 24 56704 0x7f0902d9c900 0x7f07d2e35d40 131072 268848 34302832 12076535762572715 12076535762746754 12076535762876353 12076535762879887
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 102 931481 931486 4194304 256 0 0 24 24 58176 0x7f0902d9c800 0x7f07d2e35d80 131072 254066 32505440 12076535762930821 12076535763098272 12076535763242112 12076535763245797
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 104 931481 931486 4194304 256 0 0 24 24 59392 0x7f0902d9c700 0x7f07d2e35dc0 131072 254464 32498544 12076535763306641 12076535763466111 12076535763638591 12076535763642585
55 53 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 106 931481 931486 4194304 256 0 0 28 24 61376 0x7f0902d9c600 0x7f07d2e35e00 131072 247400 31932200 12076535763691106 12076535763856670 12076535764116989 12076535764185105
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 108 931481 931486 4194304 256 0 0 28 24 62592 0x7f0902d9c500 0x7f07d2e35e40 65536 174752 22359536 12076535764212716 12076535764387548 12076535764645627 12076535764713207
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 110 931481 931486 4194304 256 0 0 24 24 63808 0x7f0902d9c400 0x7f07d2e35e80 131072 254116 32560624 12076535764738193 12076535764917946 12076535765047226 12076535765050965
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 112 931481 931486 4194304 256 0 0 24 24 65280 0x7f0902d9c300 0x7f07d2e35ec0 131072 265428 34130688 12076535765101499 12076535765272665 12076535765409145 12076535765412748
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 114 931481 931486 4194304 256 0 0 24 24 66496 0x7f0902d9ca00 0x7f07d2e35f00 131072 251760 32130976 12076535765472980 12076535765631704 12076535765765143 12076535765768740
60 58 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 116 931481 931486 4194304 256 0 0 28 24 68480 0x7f0902d9c900 0x7f07d2e35f40 131072 266630 34210168 12076535765818683 12076535765976183 12076535766243062 12076535766292695
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 118 931481 931486 4194304 256 0 0 28 24 69696 0x7f0902d9c800 0x7f07d2e35f80 65536 176114 22519856 12076535766317060 12076535766495861 12076535766750900 12076535766797213
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 120 931481 931486 4194304 256 0 0 24 24 70912 0x7f0902d9c700 0x7f07d2e35fc0 131072 253938 32301352 12076535766824304 12076535766997299 12076535767130259 12076535767134280
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 122 931481 931486 4194304 256 0 0 24 24 72384 0x7f0902d9c600 0x7f07d2e36000 131072 244926 31439056 12076535767183742 12076535767352178 12076535767492978 12076535767496554
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 124 931481 931486 4194304 256 0 0 24 24 73600 0x7f0902d9c500 0x7f07d2e36040 131072 250200 31967768 12076535767557167 12076535767713297 12076535767852976 12076535767856544
65 63 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 126 931481 931486 4194304 256 0 0 28 24 75840 0x7f0902d9c400 0x7f07d2e36080 131072 209460 26566632 12076535767905485 12076535768076656 12076535768348655 12076535768398963
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 128 931481 931486 4194304 256 0 0 28 24 77056 0x7f0902d9c300 0x7f07d2e360c0 65536 172708 22036104 12076535768424510 12076535768606094 12076535768902413 12076535768924801
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 130 931481 931486 4194304 256 0 0 24 24 78272 0x7f0902d9ca00 0x7f07d2e36100 131072 248806 31816208 12076535768968202 12076535769133932 12076535769267212 12076535769270795
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 132 931481 931486 4194304 256 0 0 24 24 80000 0x7f0902d9c900 0x7f07d2e36140 131072 211576 27173496 12076535769319635 12076535769488011 12076535769632650 12076535769636184
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 134 931481 931486 4194304 256 0 0 24 24 81216 0x7f0902d9c800 0x7f07d2e36180 131072 248248 31743616 12076535769699171 12076535769855210 12076535769987529 12076535769991145
70 68 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 136 931481 931486 4194304 256 0 0 28 24 83456 0x7f0902d9c700 0x7f07d2e361c0 131072 205308 26396368 12076535770040116 12076535770206568 12076535770475528 12076535770525308
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 138 931481 931486 4194304 256 0 0 28 24 84928 0x7f0902d9c600 0x7f07d2e36200 65536 200150 25714536 12076535770550705 12076535770727367 12076535770977606 12076535770999831
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 140 931481 931486 4194304 256 0 0 24 24 86400 0x7f0902d9c500 0x7f07d2e36240 131072 259024 33237672 12076535771048461 12076535771211365 12076535771350085 12076535771353869
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 142 931481 931486 4194304 256 0 0 24 24 88128 0x7f0902d9c400 0x7f07d2e36280 131072 210488 26816104 12076535771397080 12076535771568644 12076535771719363 12076535771722996
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 144 931481 931486 4194304 256 0 0 24 24 89600 0x7f0902d9c300 0x7f07d2e362c0 131072 255326 32596984 12076535771799488 12076535771958243 12076535772095522 12076535772099486
75 73 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 146 931481 931486 4194304 256 0 0 28 24 92096 0x7f0902d9ca00 0x7f07d2e36300 131072 221646 28316016 12076535772149519 12076535772317761 12076535772584800 12076535772634592
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 148 931481 931486 4194304 256 0 0 28 24 93568 0x7f0902d9c900 0x7f07d2e36340 65536 180556 23015328 12076535772661191 12076535772834880 12076535773090079 12076535773141284
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 150 931481 931486 4194304 256 0 0 24 24 95040 0x7f0902d9c800 0x7f07d2e36380 131072 252764 32496864 12076535773169266 12076535773343038 12076535773482077 12076535773485645
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 152 931481 931486 4194304 256 0 0 24 24 96768 0x7f0902d9c700 0x7f07d2e363c0 131072 256718 32642296 12076535773533604 12076535773698877 12076535773856956 12076535773860472
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 154 931481 931486 4194304 256 0 0 24 24 98240 0x7f0902d9c600 0x7f07d2e36400 131072 247928 31648152 12076535773921786 12076535774087355 12076535774223355 12076535774227054
80 78 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 156 931481 931486 4194304 256 0 0 28 24 100736 0x7f0902d9c500 0x7f07d2e36440 131072 200730 25616384 12076535774278299 12076535774467034 12076535774735353 12076535774760516
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 158 931481 931486 4194304 256 0 0 28 24 102208 0x7f0902d9c400 0x7f07d2e36480 65536 181872 23237848 12076535774807073 12076535774966072 12076535775221432 12076535775249375
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 160 931481 931486 4194304 256 0 0 24 24 103680 0x7f0902d9c300 0x7f07d2e364c0 131072 250040 32105496 12076535775294149 12076535775478071 12076535775611510 12076535775614986
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 162 931481 931486 4194304 256 0 0 24 24 105664 0x7f0902d9ca00 0x7f07d2e36500 131072 250352 32093352 12076535775662674 12076535775855989 12076535776022869 12076535776026661
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 164 931481 931486 4194304 256 0 0 24 24 107136 0x7f0902d9c900 0x7f07d2e36540 131072 247916 31487336 12076535776093175 12076535776259988 12076535776395988 12076535776399645
85 83 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 166 931481 931486 4194304 256 0 0 28 24 109888 0x7f0902d9c800 0x7f07d2e36580 131072 212990 27290152 12076535776443316 12076535776618707 12076535776887346 12076535776912188
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 168 931481 931486 4194304 256 0 0 28 24 111360 0x7f0902d9c700 0x7f07d2e365c0 65536 174340 22404208 12076535776956621 12076535777127665 12076535777385584 12076535777413762
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 170 931481 931486 4194304 256 0 0 24 24 112832 0x7f0902d9c600 0x7f07d2e36600 131072 240372 30868120 12076535777458324 12076535777621584 12076535777751823 12076535777755708
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 172 931481 931486 4194304 256 0 0 24 24 114816 0x7f0902d9c500 0x7f07d2e36640 131072 248806 31678168 12076535777807083 12076535777967342 12076535778141422 12076535778145182
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 174 931481 931486 4194304 256 0 0 24 24 116288 0x7f0902d9c400 0x7f07d2e36680 131072 250278 31894328 12076535778211245 12076535778376461 12076535778512141 12076535778515781
90 88 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 176 931481 931486 4194304 256 0 0 28 24 119040 0x7f0902d9c300 0x7f07d2e366c0 131072 196654 25180536 12076535778565193 12076535778736140 12076535778999819 12076535779026311
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 178 931481 931486 4194304 256 0 0 28 24 120768 0x7f0902d9ca00 0x7f07d2e36700 65536 172424 22133856 12076535779069071 12076535779229738 12076535779492617 12076535779516673
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 180 931481 931486 4194304 256 0 0 24 24 122496 0x7f0902d9c900 0x7f07d2e36740 131072 249560 32080976 12076535779560214 12076535779722856 12076535779864296 12076535779868117
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 182 931481 931486 4194304 256 0 0 24 24 124736 0x7f0902d9c800 0x7f07d2e36780 131072 258696 32879344 12076535779922268 12076535780094055 12076535780277735 12076535780281726
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 184 931481 931486 4194304 256 0 0 24 24 126464 0x7f0902d9c700 0x7f07d2e367c0 131072 252498 32055280 12076535780342159 12076535780502374 12076535780641413 12076535780645062
95 93 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 186 931481 931486 4194304 256 0 0 20 24 127936 0x7f0902d9c600 0x7f07d2e36800 131072 246148 31514552 12076535780696878 12076535780860293 12076535781126532 12076535781155682
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 188 931481 931486 4194304 256 0 0 28 24 129664 0x7f0902d9c500 0x7f07d2e36840 65536 177902 22769528 12076535781197109 12076535781359011 12076535781613090 12076535781637819
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 190 931481 931486 4194304 256 0 0 24 24 131392 0x7f0902d9c400 0x7f07d2e36880 131072 252396 32364072 12076535781680769 12076535781840289 12076535781974849 12076535781978553
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 192 931481 931486 4194304 256 0 0 24 24 133632 0x7f0902d9c300 0x7f07d2e368c0 131072 254792 32535312 12076535782034837 12076535782212608 12076535782404927 12076535782433028
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 194 931481 931486 4194304 256 0 0 24 24 135360 0x7f0902d9ca00 0x7f07d2e36900 131072 248366 31793552 12076535782487429 12076535782652287 12076535782791486 12076535782795262
100 98 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 196 931481 931486 4194304 256 0 0 20 24 136832 0x7f0902d9c900 0x7f07d2e36940 131072 244972 31322200 12076535782845636 12076535783029085 12076535783313564 12076535783340496
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 198 931481 931486 4194304 256 0 0 28 24 138560 0x7f0902d9c800 0x7f07d2e36980 65536 190124 24376528 12076535783377775 12076535783553244 12076535783810363 12076535783831048
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 200 931481 931486 4194304 256 0 0 24 24 140288 0x7f0902d9c700 0x7f07d2e369c0 131072 241170 31060528 12076535783875952 12076535784043482 12076535784178202 12076535784181981
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 202 931481 931486 4194304 256 0 0 24 24 142784 0x7f0902d9c600 0x7f07d2e36a00 131072 247828 31622776 12076535784230381 12076535784402681 12076535784614040 12076535784638470
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 204 931481 931486 4194304 256 0 0 24 24 144768 0x7f0902d9c500 0x7f07d2e36a40 131072 234952 29939672 12076535784701257 12076535784864279 12076535785001879 12076535785006485
105 103 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 206 931481 931486 4194304 256 0 0 20 24 145728 0x7f0902d9c400 0x7f07d2e36a80 131072 254604 32747768 12076535785055386 12076535785229718 12076535785538357 12076535785564312
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 208 931481 931486 4194304 256 0 0 28 24 147712 0x7f0902d9c300 0x7f07d2e36ac0 65536 175756 22480392 12076535785607042 12076535785767476 12076535786026835 12076535786052110
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 210 931481 931486 4194304 256 0 0 24 24 149696 0x7f0902d9ca00 0x7f07d2e36b00 131072 250858 32293176 12076535786103586 12076535786269555 12076535786408594 12076535786412410
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 212 931481 931486 4194304 256 0 0 24 24 152192 0x7f0902d9c900 0x7f07d2e36b40 131072 253218 32269856 12076535786461531 12076535786623473 12076535786852113 12076535786876423
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 214 931481 931486 4194304 256 0 0 24 24 154176 0x7f0902d9c800 0x7f07d2e36b80 131072 254168 32385920 12076535786933600 12076535787109072 12076535787244751 12076535787248535
110 108 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 216 931481 931486 4194304 256 0 0 20 24 155648 0x7f0902d9c700 0x7f07d2e36bc0 131072 249452 32103096 12076535787297787 12076535787476110 12076535787806189 12076535787826761
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 218 931481 931486 4194304 256 0 0 28 24 157632 0x7f0902d9c600 0x7f07d2e36c00 65536 187108 23981928 12076535787871374 12076535788040429 12076535788304268 12076535788331029
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 220 931481 931486 4194304 256 0 0 24 24 159616 0x7f0902d9c500 0x7f07d2e36c40 131072 247350 31619328 12076535788375071 12076535788538027 12076535788682346 12076535788686220
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 222 931481 931486 4194304 256 0 0 24 24 162368 0x7f0902d9c400 0x7f07d2e36c80 131072 246700 31634104 12076535788737034 12076535788899306 12076535789146505 12076535789174738
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 224 931481 931486 4194304 256 0 0 24 24 164608 0x7f0902d9c300 0x7f07d2e36cc0 131072 247578 31620440 12076535789226074 12076535789392264 12076535789533864 12076535789537593
115 113 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 226 931481 931486 4194304 256 0 0 20 24 166336 0x7f0902d9ca00 0x7f07d2e36d00 131072 253398 32529688 12076535789585973 12076535789761345 12076535790138145 12076535790168056
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 228 931481 931486 4194304 256 0 0 28 24 168576 0x7f0902d9c900 0x7f07d2e36d40 65536 174194 22274640 12076535790209373 12076535790373823 12076535790637982 12076535790660943
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 230 931481 931486 4194304 256 0 0 24 24 170816 0x7f0902d9c800 0x7f07d2e36d80 131072 244474 31260976 12076535790709183 12076535790870302 12076535791007422 12076535791010253
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 232 931481 931486 4194304 256 0 0 24 24 174080 0x7f0902d9c700 0x7f07d2e36dc0 131072 245246 31511792 12076535791060015 12076535791230141 12076535791511261 12076535791535720
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 234 931481 931486 4194304 256 0 0 24 24 176576 0x7f0902d9c600 0x7f07d2e36e00 131072 272202 34692688 12076535791586184 12076535791745820 12076535791885980 12076535791888607
120 118 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 236 931481 931486 4194304 256 0 0 20 24 177792 0x7f0902d9c500 0x7f07d2e36e40 131072 248248 31698312 12076535791939060 12076535792115099 12076535792542138 12076535792568141
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 238 931481 931486 4194304 256 0 0 28 24 180288 0x7f0902d9c400 0x7f07d2e36e80 65536 186592 23892056 12076535792610319 12076535792768058 12076535793030937 12076535793055427
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 240 931481 931486 4194304 256 0 0 24 24 182784 0x7f0902d9c300 0x7f07d2e36ec0 131072 250486 31912200 12076535793104528 12076535793269817 12076535793407256 12076535793410157
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 242 931481 931486 4194304 256 0 0 24 24 186304 0x7f0902d9ca00 0x7f07d2e36f00 131072 268634 34525448 12076535793458437 12076535793626456 12076535793943095 12076535793966161
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 244 931481 931486 4194304 256 0 0 24 24 189312 0x7f0902d9c900 0x7f07d2e36f40 131072 252822 32410752 12076535794030641 12076535794191895 12076535794345014 12076535794347881
125 123 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 246 931481 931486 4194304 256 0 0 20 24 190784 0x7f0902d9c800 0x7f07d2e36f80 131072 247220 31441808 12076535794395910 12076535794573494 12076535795093653 12076535795117893
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 248 931481 931486 4194304 256 0 0 28 24 193792 0x7f0902d9c700 0x7f07d2e36fc0 65536 173626 22178136 12076535795170702 12076535795334932 12076535795633171 12076535795656455
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 250 931481 931486 4194304 256 0 0 24 24 196800 0x7f0902d9c600 0x7f07d2e37000 131072 246780 31460328 12076535795709153 12076535795872051 12076535796026771 12076535796029710
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 252 931481 931486 4194304 256 0 0 24 24 201088 0x7f0902d9c500 0x7f07d2e37040 131072 229086 29217376 12076535796081105 12076535796263410 12076535796650129 12076535796675861
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 254 931481 931486 4194304 256 0 0 24 24 204608 0x7f0902d9c400 0x7f07d2e37080 131072 255960 32676656 12076535796731535 12076535796893489 12076535797070928 12076535797073922
130 128 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 256 931481 931486 4194304 256 0 0 20 24 206080 0x7f0902d9c300 0x7f07d2e370c0 131072 244194 31503320 12076535797124085 12076535797292048 12076535797916046 12076535797939592
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 258 931481 931486 4194304 256 0 0 28 24 209600 0x7f0902d9ca00 0x7f07d2e37100 65536 184072 23645432 12076535797983404 12076535798147726 12076535798477485 12076535798502169
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 260 931481 931486 4194304 256 0 0 24 24 213120 0x7f0902d9c900 0x7f07d2e37140 131072 271282 34743344 12076535798545679 12076535798701325 12076535798880524 12076535798883448
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 262 931481 931486 4194304 256 0 0 24 24 218176 0x7f0902d9c800 0x7f07d2e37180 131072 242470 31230944 12076535798932739 12076535799103244 12076535799580843 12076535799609268
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 264 931481 931486 4194304 256 0 0 24 24 222208 0x7f0902d9c700 0x7f07d2e371c0 131072 247232 31706144 12076535799664541 12076535799827402 12076535800027882 12076535800053374
135 133 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 266 931481 931486 4194304 256 0 0 20 24 223936 0x7f0902d9c600 0x7f07d2e37200 131072 240382 30902936 12076535800093789 12076535800253801 12076535800959240 12076535800985197
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 268 931481 931486 4194304 256 0 0 28 24 227968 0x7f0902d9c500 0x7f07d2e37240 65536 172664 22120216 12076535801034138 12076535801192679 12076535801566758 12076535801592497
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 270 931481 931486 4194304 256 0 0 24 24 232000 0x7f0902d9c400 0x7f07d2e37280 131072 247830 31758136 12076535801642821 12076535801803398 12076535802007237 12076535802032135
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 272 931481 931486 4194304 256 0 0 24 24 237824 0x7f0902d9c300 0x7f07d2e372c0 131072 276044 35376792 12076535802077709 12076535802235397 12076535802780196 12076535802805994
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 274 931481 931486 4194304 256 0 0 24 24 242368 0x7f0902d9ca00 0x7f07d2e37300 131072 245004 31416496 12076535802860706 12076535803030115 12076535803254435 12076535803281779
140 138 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 276 931481 931486 4194304 256 0 0 20 24 243584 0x7f0902d9c900 0x7f07d2e37340 131072 248152 31499344 12076535803322906 12076535803482434 12076535804284032 12076535804311384
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 278 931481 931486 4194304 256 0 0 28 24 248128 0x7f0902d9c800 0x7f07d2e37380 65536 192356 24555984 12076535804358011 12076535804533792 12076535804979551 12076535805009192
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 280 931481 931486 4194304 256 0 0 24 24 252672 0x7f0902d9c700 0x7f07d2e373c0 131072 265446 33991336 12076535805056100 12076535805216030 12076535805478430 12076535805504694
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 282 931481 931486 4194304 256 0 0 24 24 259264 0x7f0902d9c600 0x7f07d2e37400 131072 228180 29320592 12076535805552934 12076535805714269 12076535806325468 12076535806355006
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 284 931481 931486 4194304 256 0 0 24 24 264832 0x7f0902d9c500 0x7f07d2e37440 131072 251198 32153504 12076535806411711 12076535806572827 12076535806842587 12076535806863562
145 143 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 286 931481 931486 4194304 256 0 0 20 24 266304 0x7f0902d9c400 0x7f07d2e37480 131072 252746 32146208 12076535806908185 12076535807075066 12076535808063704 12076535808133644
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 288 931481 931486 4194304 256 0 0 28 24 271872 0x7f0902d9c300 0x7f07d2e374c0 65536 173106 22358800 12076535808164101 12076535808346743 12076535808864982 12076535808933211
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 290 931481 931486 4194304 256 0 0 24 24 277440 0x7f0902d9ca00 0x7f07d2e37500 131072 244800 31286192 12076535808962646 12076535809147702 12076535809422261 12076535809491410
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 292 931481 931486 4194304 256 0 0 12 24 279936 0x7f0902d9c900 0x7f07d2e37540 131072 259600 33280864 12076535809521185 12076535809694100 12076535810434739 12076535810503583
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 294 931481 931486 4194304 256 0 0 24 24 286528 0x7f0902d9c800 0x7f07d2e37580 131072 244426 31258648 12076535810545681 12076535810708018 12076535811025938 12076535811094492
150 148 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 296 931481 931486 4194304 256 0 0 20 24 288000 0x7f0902d9c700 0x7f07d2e375c0 131072 245632 31453320 12076535811124578 12076535811302737 12076535812477934 12076535812546192
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 298 931481 931486 4194304 256 0 0 32 24 294592 0x7f0902d9c600 0x7f07d2e37600 65536 170046 21731288 12076535812577931 12076535812749934 12076535813363852 12076535813431970
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 300 931481 931486 4194304 256 0 0 24 24 301184 0x7f0902d9c500 0x7f07d2e37640 131072 248710 31768864 12076535813463899 12076535813636972 12076535813957451 12076535814025394
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 302 931481 931486 4194304 256 0 0 12 24 304960 0x7f0902d9c400 0x7f07d2e37680 131072 248358 31669136 12076535814056531 12076535814229450 12076535815109929 12076535815178519
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 304 931481 931486 4194304 256 0 0 24 24 313600 0x7f0902d9c300 0x7f07d2e376c0 131072 252416 32524368 12076535815221809 12076535815383688 12076535815818087 12076535815885494
155 153 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 306 931481 931486 4194304 256 0 0 20 24 314816 0x7f0902d9ca00 0x7f07d2e37700 131072 264090 33538024 12076535815916171 12076535816107206 12076535817660643 12076535817730826
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 308 931481 931486 4194304 256 0 0 20 24 317568 0x7f0902d9c900 0x7f07d2e37740 65536 177406 22597216 12076535817763046 12076535817945122 12076535818744001 12076535818812649
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 310 931481 931486 4194304 256 0 0 12 24 320320 0x7f0902d9c800 0x7f07d2e37780 131072 250710 31869752 12076535818840731 12076535819030880 12076535819469919 12076535819536936
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 312 931481 931486 4194304 256 0 0 12 24 324096 0x7f0902d9c700 0x7f07d2e377c0 131072 255298 32584632 12076535819563996 12076535819740798 12076535820901276 12076535820969440
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 314 931481 931486 4194304 256 0 0 12 24 328896 0x7f0902d9c600 0x7f07d2e37800 131072 248216 31699144 12076535821012781 12076535821174555 12076535821961113 12076535822030574
160 158 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 316 931481 931486 4194304 256 0 0 20 24 330112 0x7f0902d9c500 0x7f07d2e37840 131072 232208 29890112 12076535822062013 12076535822234553 12076535825293266 12076535825360979
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 318 931481 931486 4194304 256 0 0 20 24 332864 0x7f0902d9c400 0x7f07d2e37880 65536 205980 26381080 12076535825392768 12076535825570225 12076535827119822 12076535827188138
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 320 931481 931486 4194304 256 0 0 12 24 335616 0x7f0902d9c300 0x7f07d2e378c0 131072 253968 32336872 12076535827218074 12076535827399021 12076535828189900 12076535828258429
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 322 931481 931486 4194304 256 0 0 12 24 339392 0x7f0902d9ca00 0x7f07d2e37900 131072 245034 31582216 12076535828289777 12076535828475019 12076535830759654 12076535830828349
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 324 931481 931486 4194304 256 0 0 12 24 344192 0x7f0902d9c900 0x7f07d2e37940 131072 246990 31470576 12076535830872331 12076535831043013 12076535832580130 12076535832649998
165 163 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 326 931481 931486 4194304 256 0 0 20 24 345408 0x7f0902d9c800 0x7f07d2e37980 131072 248498 31682120 12076535832681005 12076535832863169 12076535838926356 12076535838998787
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 328 931481 931486 4194304 256 0 0 20 24 348160 0x7f0902d9c700 0x7f07d2e379c0 65536 164836 21120504 12076535839030656 12076535839214835 12076535842261389 12076535842334422
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 330 931481 931486 4194304 256 0 0 12 24 350912 0x7f0902d9c600 0x7f07d2e37a00 131072 269178 34623672 12076535842363666 12076535842546668 12076535844087145 12076535844155389
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 332 931481 931486 4194304 256 0 0 12 24 0 0x7f0902d9c500 0x7f07d2e37a40 131072 229584 29528560 12076535844185946 12076535844363944 12076535848893694 12076535848961960
@@ -0,0 +1,168 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,grd,Workgroup_Size,LDS_Per_Workgroup,scr,vgpr,SGPR,fbar,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"__amd_rocclr_fillBuffer.kd",0,0,0,931671,931676,33554432,256,0,0,8,32,6464,0x0,0x7f8101a04180,1048576,10991950,1406583256,12076536745644699,12076536990667420,12076536990991419,12076536991092712
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,931671,931676,32768,256,0,0,24,24,12480,0x0,0x7f8101a35100,4096,109855,14068084,12076537005633911,12076537005965694,12076537005972254,12076537005977540
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,931671,931676,4194304,256,0,0,24,24,12928,0x7f820d595900,0x7f8101a35140,524288,10827501,1385924644,12076537006052800,12076537006288733,12076537006426653,12076537006431615
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,931671,931676,4194304,256,0,0,36,24,13632,0x7f820d595800,0x7f8101a35180,524288,13152373,1683491304,12076537006499130,12076537006707452,12076537006957211,12076537007029086
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,931671,931676,4194304,256,0,0,28,24,14080,0x7f820d595700,0x7f8101a351c0,524288,14200061,1817639572,12076537007068339,12076537007304890,12076537007556409,12076537007625185
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,931671,931676,4194304,256,0,0,24,24,14528,0x7f820d595600,0x7f8101a35200,524288,11407226,1460160184,12076537007643849,12076537007878488,12076537008015288,12076537008020710
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,931671,931676,4194304,256,0,0,24,24,14976,0x7f820d595500,0x7f8101a35240,524288,10073682,1289371852,12076537008063009,12076537008302007,12076537008442327,12076537008446913
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,931671,931676,4194304,256,0,0,24,24,15424,0x7f820d595400,0x7f8101a35280,524288,12069674,1544916740,12076537008531060,12076537008737366,12076537008870326,12076537008875250
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,931671,931676,4194304,256,0,0,28,24,16128,0x7f820d595300,0x7f8101a352c0,524288,13834162,1770759264,12076537008926375,12076537009160245,12076537009417524,12076537009487819
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,931671,931676,4194304,256,0,0,28,24,16832,0x7f820d595a00,0x7f8101a35300,524288,13752043,1760197408,12076537009510792,12076537009741683,12076537009996242,12076537010065825
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,931671,931676,4194304,256,0,0,24,24,17536,0x7f820d595900,0x7f8101a35340,524288,12622999,1615692540,12076537010086012,12076537010327921,12076537010457841,12076537010462452
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,931671,931676,4194304,256,0,0,24,24,18240,0x7f820d595800,0x7f8101a35380,524288,10876400,1392226256,12076537010508829,12076537010736720,12076537010874480,12076537010879248
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,931671,931676,4194304,256,0,0,24,24,18944,0x7f820d595700,0x7f8101a353c0,524288,12430221,1591034056,12076537010943457,12076537011160559,12076537011290959,12076537011296013
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,931671,931676,4194304,256,0,0,28,24,19904,0x7f820d595600,0x7f8101a35400,524288,13681979,1751246956,12076537011345395,12076537011564078,12076537011819117,12076537011888365
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,931671,931676,4194304,256,0,0,28,24,20608,0x7f820d595500,0x7f8101a35440,524288,13735217,1758153172,12076537011910246,12076537012149516,12076537012402155,12076537012472131
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,931671,931676,4194304,256,0,0,24,24,21312,0x7f820d595400,0x7f8101a35480,524288,12508963,1601114468,12076537012493200,12076537012722794,12076537012853194,12076537012857968
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,931671,931676,4194304,256,0,0,24,24,22016,0x7f820d595300,0x7f8101a354c0,524288,11865378,1518770176,12076537012902471,12076537013134313,12076537013267113,12076537013272179
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,931671,931676,4194304,256,0,0,24,24,22720,0x7f820d595a00,0x7f8101a35500,524288,12904609,1651830556,12076537013335076,12076537013544232,12076537013673032,12076537013677733
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,931671,931676,4194304,256,0,0,28,24,23680,0x7f820d595900,0x7f8101a35540,524288,13326940,1705836624,12076537013729960,12076537013951431,12076537014209830,12076537014281426
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,931671,931676,4194304,256,0,0,28,24,24384,0x7f820d595800,0x7f8101a35580,524288,14016563,1794089300,12076537014304209,12076537014539109,12076537014792068,12076537014861345
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,931671,931676,4194304,256,0,0,24,24,25088,0x7f820d595700,0x7f8101a355c0,524288,12453533,1594103040,12076537014885710,12076537015130147,12076537015260227,12076537015265096
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,931671,931676,4194304,256,0,0,24,24,25792,0x7f820d595600,0x7f8101a35600,524288,11823515,1513438712,12076537015309529,12076537015531426,12076537015664866,12076537015669879
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,931671,931676,4194304,256,0,0,24,24,26496,0x7f820d595500,0x7f8101a35640,524288,13009055,1665205064,12076537015731223,12076537015938625,12076537016067425,12076537016072638
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,931671,931676,4194304,256,0,0,28,24,27712,0x7f820d595400,0x7f8101a35680,524288,13728992,1757293256,12076537016114786,12076537016346784,12076537016605503,12076537016674478
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,931671,931676,4194304,256,0,0,28,24,28416,0x7f820d595300,0x7f8101a356c0,524288,14176355,1814547952,12076537016694795,12076537016926142,12076537017178621,12076537017249808
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,931671,931676,4194304,256,0,0,24,24,29120,0x7f820d595a00,0x7f8101a35700,524288,12000157,1535962068,12076537017277078,12076537017506300,12076537017638300,12076537017643230
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,931671,931676,4194304,256,0,0,24,24,30080,0x7f820d595900,0x7f8101a35740,524288,12107321,1549687848,12076537017694325,12076537017909179,12076537018042459,12076537018047962
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,931671,931676,4194304,256,0,0,24,24,30784,0x7f820d595800,0x7f8101a35780,524288,12002481,1536392300,12076537018108966,12076537018322778,12076537018454458,12076537018459318
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,931671,931676,4194304,256,0,0,28,24,32000,0x7f820d595700,0x7f8101a357c0,524288,13300232,1702375832,12076537018508780,12076537018739257,12076537018997816,12076537019066878
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,931671,931676,4194304,256,0,0,28,24,32960,0x7f820d595600,0x7f8101a35800,524288,13638264,1745713280,12076537019087336,12076537019321495,12076537019573494,12076537019642609
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,931671,931676,4194304,256,0,0,24,24,33920,0x7f820d595500,0x7f8101a35840,524288,13304502,1702977096,12076537019662025,12076537019890133,12076537020017013,12076537020022014
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,931671,931676,4194304,256,0,0,24,24,34880,0x7f820d595400,0x7f8101a35880,524288,10787214,1380726760,12076537020071917,12076537020290452,12076537020428692,12076537020433440
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,931671,931676,4194304,256,0,0,24,24,35840,0x7f820d595300,0x7f8101a358c0,524288,12889254,1649864640,12076537020496016,12076537020704211,12076537020832211,12076537020837030
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,931671,931676,4194304,256,0,0,28,24,37312,0x7f820d595a00,0x7f8101a35900,524288,14166125,1813262800,12076537020886603,12076537021114290,12076537021365649,12076537021436746
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,931671,931676,4194304,256,0,0,28,24,38272,0x7f820d595900,0x7f8101a35940,524288,13076060,1673655584,12076537021456433,12076537021685648,12076537021941807,12076537022021484
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,931671,931676,4194304,256,0,0,24,24,39232,0x7f820d595800,0x7f8101a35980,524288,11865526,1518783952,12076537022040339,12076537022271406,12076537022404206,12076537022409155
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,931671,931676,4194304,256,0,0,24,24,40192,0x7f820d595700,0x7f8101a359c0,524288,11035340,1412490616,12076537022460260,12076537022681805,12076537022817965,12076537022822684
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,931671,931676,4194304,256,0,0,24,24,41152,0x7f820d595600,0x7f8101a35a00,524288,12250772,1568128872,12076537022883507,12076537023098604,12076537023229644,12076537023234680
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,931671,931676,4194304,256,0,0,28,24,42624,0x7f820d595500,0x7f8101a35a40,524288,14123077,1807746404,12076537023285405,12076537023503243,12076537023767242,12076537023836349
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,931671,931676,4194304,256,0,0,28,24,43584,0x7f820d595400,0x7f8101a35a80,524288,14205139,1818274976,12076537023855705,12076537024097161,12076537024347880,12076537024419033
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,931671,931676,4194304,256,0,0,24,24,44544,0x7f820d595300,0x7f8101a35ac0,524288,13116252,1678894716,12076537024439401,12076537024669959,12076537024797799,12076537024802647
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,931671,931676,4194304,256,0,0,24,24,45760,0x7f820d595a00,0x7f8101a35b00,524288,11853180,1517189460,12076537024853451,12076537025072838,12076537025205638,12076537025210866
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,931671,931676,4194304,256,0,0,24,24,46720,0x7f820d595900,0x7f8101a35b40,524288,13137811,1681585836,12076537025271329,12076537025476517,12076537025605317,12076537025610339
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,931671,931676,4194304,256,0,0,28,24,48448,0x7f820d595800,0x7f8101a35b80,524288,12530281,1603873608,12076537025658579,12076537025871876,12076537026131715,12076537026201729
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,931671,931676,4194304,256,0,0,28,24,49408,0x7f820d595700,0x7f8101a35bc0,524288,13561484,1735844340,12076537026223290,12076537026451714,12076537026704673,12076537026773864
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,931671,931676,4194304,256,0,0,24,24,50368,0x7f820d595600,0x7f8101a35c00,524288,12885465,1649371200,12076537026791927,12076537027039073,12076537027168512,12076537027173407
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,931671,931676,4194304,256,0,0,24,24,51584,0x7f820d595500,0x7f8101a35c40,524288,11421633,1461977256,12076537027219823,12076537027449631,12076537027586111,12076537027590893
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,931671,931676,4194304,256,0,0,24,24,52544,0x7f820d595400,0x7f8101a35c80,524288,13346675,1708389748,12076537027651616,12076537027857790,12076537027984990,12076537027989876
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,931671,931676,4194304,256,0,0,28,24,54272,0x7f820d595300,0x7f8101a35cc0,524288,13057516,1671339108,12076537028034488,12076537028255549,12076537028516828,12076537028587297
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,931671,931676,4194304,256,0,0,28,24,55488,0x7f820d595a00,0x7f8101a35d00,524288,13927985,1782757888,12076537028607324,12076537028832987,12076537029088027,12076537029159882
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,931671,931676,4194304,256,0,0,24,24,56704,0x7f820d595900,0x7f8101a35d40,524288,12262502,1569588808,12076537029177505,12076537029407386,12076537029538905,12076537029543746
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,931671,931676,4194304,256,0,0,24,24,58176,0x7f820d595800,0x7f8101a35d80,524288,10766993,1378140040,12076537029593639,12076537029804824,12076537029942264,12076537029946976
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,931671,931676,4194304,256,0,0,24,24,59392,0x7f820d595700,0x7f8101a35dc0,524288,12460249,1594860708,12076537030013901,12076537030222583,12076537030354103,12076537030358852
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,931671,931676,4194304,256,0,0,28,24,61376,0x7f820d595600,0x7f8101a35e00,524288,11574719,1481596380,12076537030410188,12076537030622742,12076537030887701,12076537030957105
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,931671,931676,4194304,256,0,0,28,24,62592,0x7f820d595500,0x7f8101a35e40,524288,13925416,1782478724,12076537030975910,12076537031224660,12076537031476820,12076537031547303
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,931671,931676,4194304,256,0,0,24,24,63808,0x7f820d595400,0x7f8101a35e80,524288,12431998,1591308920,12076537031572119,12076537031803059,12076537031934258,12076537031938991
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,931671,931676,4194304,256,0,0,24,24,65280,0x7f820d595300,0x7f8101a35ec0,524288,9470204,1212098968,12076537031989325,12076537032219377,12076537032358897,12076537032363822
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,931671,931676,4194304,256,0,0,24,24,66496,0x7f820d595a00,0x7f8101a35f00,524288,12349368,1580712168,12076537032426879,12076537032628016,12076537032758736,12076537032763665
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,931671,931676,4194304,256,0,0,28,24,68480,0x7f820d595900,0x7f8101a35f40,524288,12205000,1562224976,12076537032815241,12076537033036495,12076537033296494,12076537033360916
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,931671,931676,4194304,256,0,0,28,24,69696,0x7f820d595800,0x7f8101a35f80,524288,13408863,1716267348,12076537033385843,12076537033618733,12076537033870893,12076537033921619
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,931671,931676,4194304,256,0,0,24,24,70912,0x7f820d595700,0x7f8101a35fc0,524288,12132337,1552850360,12076537033946045,12076537034142572,12076537034274731,12076537034278894
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,931671,931676,4194304,256,0,0,24,24,72384,0x7f820d595600,0x7f8101a36000,524288,7901381,1011288268,12076537034329157,12076537034505611,12076537034641930,12076537034646157
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,931671,931676,4194304,256,0,0,24,24,73600,0x7f820d595500,0x7f8101a36040,524288,12435176,1591638924,12076537034709455,12076537034874250,12076537035005769,12076537035010294
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,931671,931676,4194304,256,0,0,28,24,75840,0x7f820d595400,0x7f8101a36080,524288,11989327,1534618116,12076537035058224,12076537035244649,12076537035505128,12076537035555829
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,931671,931676,4194304,256,0,0,28,24,77056,0x7f820d595300,0x7f8101a360c0,524288,13007964,1664985512,12076537035580395,12076537035763687,12076537036016166,12076537036066599
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,931671,931676,4194304,256,0,0,24,24,78272,0x7f820d595a00,0x7f8101a36100,524288,12590944,1611595548,12076537036090484,12076537036275206,12076537036405285,12076537036409497
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,931671,931676,4194304,256,0,0,24,24,80000,0x7f820d595900,0x7f8101a36140,524288,6841792,875700556,12076537036459260,12076537036637924,12076537036781604,12076537036785737
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,931671,931676,4194304,256,0,0,24,24,81216,0x7f820d595800,0x7f8101a36180,524288,12856824,1645714428,12076537036845238,12076537037008323,12076537037137603,12076537037141679
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,931671,931676,4194304,256,0,0,28,24,83456,0x7f820d595700,0x7f8101a361c0,524288,14168224,1813459176,12076537037192263,12076537037371682,12076537037633922,12076537037684839
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,931671,931676,4194304,256,0,0,28,24,84928,0x7f820d595600,0x7f8101a36200,524288,13053157,1670735760,12076537037708343,12076537037894561,12076537038146720,12076537038197783
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,931671,931676,4194304,256,0,0,24,24,86400,0x7f820d595500,0x7f8101a36240,524288,12189637,1560184936,12076537038225816,12076537038412319,12076537038544319,12076537038548426
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,931671,931676,4194304,256,0,0,24,24,88128,0x7f820d595400,0x7f8101a36280,524288,5375163,688039676,12076537038598669,12076537038799518,12076537038948318,12076537038952187
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,931671,931676,4194304,256,0,0,24,24,89600,0x7f820d595300,0x7f8101a362c0,524288,11182771,1431435040,12076537039037556,12076537039212477,12076537039347517,12076537039351359
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,931671,931676,4194304,256,0,0,28,24,92096,0x7f820d595a00,0x7f8101a36300,524288,13300122,1702427236,12076537039400491,12076537039579356,12076537039846715,12076537039894359
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,931671,931676,4194304,256,0,0,28,24,93568,0x7f820d595900,0x7f8101a36340,524288,13163914,1685019488,12076537039921009,12076537040128154,12076537040381434,12076537040431689
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,931671,931676,4194304,256,0,0,24,24,95040,0x7f820d595800,0x7f8101a36380,524288,12123514,1551890952,12076537040463378,12076537040635353,12076537040768632,12076537040772483
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,931671,931676,4194304,256,0,0,24,24,96768,0x7f820d595700,0x7f8101a363c0,524288,5155730,659888928,12076537040831563,12076537041005752,12076537041163511,12076537041167297
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,931671,931676,4194304,256,0,0,24,24,98240,0x7f820d595600,0x7f8101a36400,524288,12479243,1597274524,12076537041231577,12076537041411351,12076537041542710,12076537041546623
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,931671,931676,4194304,256,0,0,28,24,100736,0x7f820d595500,0x7f8101a36440,524288,12244800,1567268248,12076537041595894,12076537041770229,12076537042034709,12076537042083481
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,931671,931676,4194304,256,0,0,28,24,102208,0x7f820d595400,0x7f8101a36480,524288,13934187,1783508536,12076537042119869,12076537042298068,12076537042558227,12076537042605563
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,931671,931676,4194304,256,0,0,24,24,103680,0x7f820d595300,0x7f8101a364c0,524288,12662941,1620890016,12076537042632433,12076537042807026,12076537042936946,12076537042940806
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,931671,931676,4194304,256,0,0,24,24,105664,0x7f820d595a00,0x7f8101a36500,524288,3674071,470163008,12076537042990539,12076537043175185,12076537043341265,12076537043344998
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,931671,931676,4194304,256,0,0,24,24,107136,0x7f820d595900,0x7f8101a36540,524288,12560686,1607734028,12076537043408476,12076537043582544,12076537043712304,12076537043716369
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,931671,931676,4194304,256,0,0,28,24,109888,0x7f820d595800,0x7f8101a36580,524288,9566527,1224514548,12076537043764689,12076537043945583,12076537044210062,12076537044257936
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,931671,931676,4194304,256,0,0,28,24,111360,0x7f820d595700,0x7f8101a365c0,524288,13574083,1737513344,12076537044278074,12076537044476302,12076537044772141,12076537044821575
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,931671,931676,4194304,256,0,0,24,24,112832,0x7f820d595600,0x7f8101a36600,524288,12941392,1656450752,12076537044855778,12076537045040460,12076537045169900,12076537045173840
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,931671,931676,4194304,256,0,0,24,24,114816,0x7f820d595500,0x7f8101a36640,524288,3796563,485895600,12076537045223322,12076537045396139,12076537045570698,12076537045574545
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,931671,931676,4194304,256,0,0,24,24,116288,0x7f820d595400,0x7f8101a36680,524288,12860157,1646126936,12076537045635398,12076537045807978,12076537045937737,12076537045941628
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,931671,931676,4194304,256,0,0,28,24,119040,0x7f820d595300,0x7f8101a366c0,524288,8808066,1127415140,12076537045989026,12076537046175977,12076537046433256,12076537046481262
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,931671,931676,4194304,256,0,0,28,24,120768,0x7f820d595a00,0x7f8101a36700,524288,13987492,1790319144,12076537046500828,12076537046692455,12076537046942054,12076537046989237
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,931671,931676,4194304,256,0,0,24,24,122496,0x7f820d595900,0x7f8101a36740,524288,11869746,1519364556,12076537047022769,12076537047207974,12076537047342053,12076537047346090
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,931671,931676,4194304,256,0,0,24,24,124736,0x7f820d595800,0x7f8101a36780,524288,3676041,470439040,12076537047393098,12076537047567173,12076537047749892,12076537047756043
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,931671,931676,4194304,256,0,0,24,24,126464,0x7f820d595700,0x7f8101a367c0,524288,10235098,1310068808,12076537047813851,12076537047982851,12076537048123491,12076537048127554
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,931671,931676,4194304,256,0,0,20,24,127936,0x7f820d595600,0x7f8101a36800,524288,4059035,519533928,12076537048176345,12076537048357410,12076537048622049,12076537048670624
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,931671,931676,4194304,256,0,0,28,24,129664,0x7f820d595500,0x7f8101a36840,524288,13498901,1727885208,12076537048695220,12076537048874049,12076537049139168,12076537049189900
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,931671,931676,4194304,256,0,0,24,24,131392,0x7f820d595400,0x7f8101a36880,524288,12079436,1546157672,12076537049216259,12076537049402687,12076537049535967,12076537049539531
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,931671,931676,4194304,256,0,0,24,24,133632,0x7f820d595300,0x7f8101a368c0,524288,3668964,469562380,12076537049587670,12076537049753246,12076537049945406,12076537049993976
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,931671,931676,4194304,256,0,0,24,24,135360,0x7f820d595a00,0x7f8101a36900,524288,11740357,1502702696,12076537050040563,12076537050217085,12076537050350524,12076537050354486
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,931671,931676,4194304,256,0,0,20,24,136832,0x7f820d595900,0x7f8101a36940,524288,2910339,372538880,12076537050396424,12076537050582364,12076537050867643,12076537050915129
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,931671,931676,4194304,256,0,0,28,24,138560,0x7f820d595800,0x7f8101a36980,524288,13871266,1775489480,12076537050935136,12076537051129562,12076537051378361,12076537051428144
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,931671,931676,4194304,256,0,0,24,24,140288,0x7f820d595700,0x7f8101a369c0,524288,10902850,1395507584,12076537051457759,12076537051625241,12076537051762360,12076537051766473
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,931671,931676,4194304,256,0,0,24,24,142784,0x7f820d595600,0x7f8101a36a00,524288,3339333,427373264,12076537051814793,12076537051985240,12076537052195639,12076537052218053
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,931671,931676,4194304,256,0,0,24,24,144768,0x7f820d595500,0x7f8101a36a40,524288,10729796,1373365204,12076537052275480,12076537052451318,12076537052590998,12076537052595194
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,931671,931676,4194304,256,0,0,20,24,145728,0x7f820d595400,0x7f8101a36a80,524288,2567397,328588288,12076537052639166,12076537052819637,12076537053126196,12076537053177948
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,931671,931676,4194304,256,0,0,28,24,147712,0x7f820d595300,0x7f8101a36ac0,524288,14087651,1803179864,12076537053202885,12076537053384092,12076537053643292,12076537053696333
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,931671,931676,4194304,256,0,0,24,24,149696,0x7f820d595a00,0x7f8101a36b00,524288,10511919,1345492040,12076537053718624,12076537053899770,12076537054037370,12076537054040803
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,931671,931676,4194304,256,0,0,24,24,152192,0x7f820d595900,0x7f8101a36b40,524288,3448993,441336096,12076537054089083,12076537054261369,12076537054489689,12076537054537557
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,931671,931676,4194304,256,0,0,24,24,154176,0x7f820d595800,0x7f8101a36b80,524288,10589795,1355519852,12076537054581259,12076537054753528,12076537054891288,12076537054894872
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,931671,931676,4194304,256,0,0,20,24,155648,0x7f820d595700,0x7f8101a36bc0,524288,2471787,316445520,12076537054943132,12076537055120887,12076537055450487,12076537055499136
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,931671,931676,4194304,256,0,0,28,24,157632,0x7f820d595600,0x7f8101a36c00,524288,13426249,1718562836,12076537055526437,12076537055705366,12076537055968566,12076537056018392
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,931671,931676,4194304,256,0,0,24,24,159616,0x7f820d595500,0x7f8101a36c40,524288,11301734,1446524700,12076537056044290,12076537056225205,12076537056361045,12076537056364305
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,931671,931676,4194304,256,0,0,24,24,162368,0x7f820d595400,0x7f8101a36c80,524288,3490789,446777020,12076537056412325,12076537056586164,12076537056832884,12076537056880816
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,931671,931676,4194304,256,0,0,24,24,164608,0x7f820d595300,0x7f8101a36cc0,524288,9570521,1225124668,12076537056925479,12076537057104403,12076537057245683,12076537057249001
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,931671,931676,4194304,256,0,0,20,24,166336,0x7f820d595a00,0x7f8101a36d00,524288,2372318,303598848,12076537057292863,12076537057474002,12076537057850002,12076537057897387
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,931671,931676,4194304,256,0,0,28,24,168576,0x7f820d595900,0x7f8101a36d40,524288,12464562,1595428592,12076537057924538,12076537058100241,12076537058359600,12076537058408197
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,931671,931676,4194304,256,0,0,24,24,170816,0x7f820d595800,0x7f8101a36d80,524288,9076426,1161746084,12076537058435909,12076537058613520,12076537058755280,12076537058759080
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,931671,931676,4194304,256,0,0,24,24,174080,0x7f820d595700,0x7f8101a36dc0,524288,3338560,427183016,12076537058808111,12076537058983759,12076537059264079,12076537059312970
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,931671,931676,4194304,256,0,0,24,24,176576,0x7f820d595600,0x7f8101a36e00,524288,8169712,1045803212,12076537059355399,12076537059529038,12076537059671278,12076537059674934
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,931671,931676,4194304,256,0,0,20,24,177792,0x7f820d595500,0x7f8101a36e40,524288,2353641,301277372,12076537059723634,12076537059899597,12076537060325676,12076537060373934
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,931671,931676,4194304,256,0,0,28,24,180288,0x7f820d595400,0x7f8101a36e80,524288,9843291,1259866916,12076537060400633,12076537060580716,12076537060843115,12076537060890996
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,931671,931676,4194304,256,0,0,24,24,182784,0x7f820d595300,0x7f8101a36ec0,524288,7934379,1015561276,12076537060915010,12076537061103275,12076537061240074,12076537061243822
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,931671,931676,4194304,256,0,0,24,24,186304,0x7f820d595a00,0x7f8101a36f00,524288,3414394,436994796,12076537061294446,12076537061460554,12076537061776073,12076537061824292
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,931671,931676,4194304,256,0,0,24,24,189312,0x7f820d595900,0x7f8101a36f40,524288,3243029,414936448,12076537061869295,12076537062045513,12076537062197832,12076537062201594
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,931671,931676,4194304,256,0,0,20,24,190784,0x7f820d595800,0x7f8101a36f80,524288,2304386,294994940,12076537062243211,12076537062434952,12076537062953191,12076537063004657
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,931671,931676,4194304,256,0,0,28,24,193792,0x7f820d595700,0x7f8101a36fc0,524288,8029014,1027723944,12076537063034483,12076537063201990,12076537063501669,12076537063552536
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,931671,931676,4194304,256,0,0,24,24,196800,0x7f820d595600,0x7f8101a37000,524288,3230460,413418080,12076537063581490,12076537063771589,12076537063926469,12076537063929728
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,931671,931676,4194304,256,0,0,24,24,201088,0x7f820d595500,0x7f8101a37040,524288,3290249,421097372,12076537063977818,12076537064150948,12076537064537347,12076537064585017
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,931671,931676,4194304,256,0,0,24,24,204608,0x7f820d595400,0x7f8101a37080,524288,3561632,455977932,12076537064625312,12076537064796387,12076537064973826,12076537064977427
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,931671,931676,4194304,256,0,0,20,24,206080,0x7f820d595300,0x7f8101a370c0,524288,2321065,297025088,12076537065030806,12076537065194146,12076537065806784,12076537065857855
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,931671,931676,4194304,256,0,0,28,24,209600,0x7f820d595a00,0x7f8101a37100,524288,4092771,523943812,12076537065882991,12076537066076064,12076537066432383,12076537066481665
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,931671,931676,4194304,256,0,0,24,24,213120,0x7f820d595900,0x7f8101a37140,524288,3283078,420290284,12076537066509306,12076537066689983,12076537066868542,12076537066871941
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,931671,931676,4194304,256,0,0,24,24,218176,0x7f820d595800,0x7f8101a37180,524288,4011228,513419724,12076537066914841,12076537067101342,12076537067558141,12076537067607730
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,931671,931676,4194304,256,0,0,24,24,222208,0x7f820d595700,0x7f8101a371c0,524288,3086405,395051364,12076537067650379,12076537067823100,12076537068023100,12076537068072735
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,931671,931676,4194304,256,0,0,20,24,223936,0x7f820d595600,0x7f8101a37200,524288,2343631,299877004,12076537068103281,12076537068292219,12076537069004378,12076537069051906
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,931671,931676,4194304,256,0,0,28,24,227968,0x7f820d595500,0x7f8101a37240,524288,3513231,449720508,12076537069071342,12076537069256377,12076537069655256,12076537069702486
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,931671,931676,4194304,256,0,0,24,24,232000,0x7f820d595400,0x7f8101a37280,524288,3288966,421048972,12076537069724427,12076537069905016,12076537070108855,12076537070158925
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,931671,931676,4194304,256,0,0,24,24,237824,0x7f820d595300,0x7f8101a372c0,524288,4361274,558258120,12076537070178301,12076537070361495,12076537070888534,12076537070938746
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,931671,931676,4194304,256,0,0,24,24,242368,0x7f820d595a00,0x7f8101a37300,524288,3190851,408410816,12076537070978430,12076537071152693,12076537071411572,12076537071460717
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,931671,931676,4194304,256,0,0,20,24,243584,0x7f820d595900,0x7f8101a37340,524288,2332685,298669936,12076537071479061,12076537071664052,12076537072466290,12076537072515609
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,931671,931676,4194304,256,0,0,28,24,248128,0x7f820d595800,0x7f8101a37380,524288,3450545,441725456,12076537072538942,12076537072728690,12076537073149329,12076537073198138
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,931671,931676,4194304,256,0,0,24,24,252672,0x7f820d595700,0x7f8101a373c0,524288,3108461,397911152,12076537073223355,12076537073405808,12076537073632368,12076537073680135
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,931671,931676,4194304,256,0,0,24,24,259264,0x7f820d595600,0x7f8101a37400,524288,4492613,575010916,12076537073712776,12076537073885327,12076537074483886,12076537074534885
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,931671,931676,4194304,256,0,0,24,24,264832,0x7f820d595500,0x7f8101a37440,524288,3287085,420713856,12076537074580450,12076537074754125,12076537075024845,12076537075073777
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,931671,931676,4194304,256,0,0,20,24,266304,0x7f820d595400,0x7f8101a37480,524288,2305984,295182096,12076537075098513,12076537075280044,12076537076267402,12076537076316098
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,931671,931676,4194304,256,0,0,28,24,271872,0x7f820d595300,0x7f8101a374c0,524288,3310118,423677572,12076537076341966,12076537076532521,12076537077049320,12076537077097722
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,931671,931676,4194304,256,0,0,24,24,277440,0x7f820d595a00,0x7f8101a37500,524288,3398156,434965224,12076537077131816,12076537077303880,12076537077609159,12076537077657343
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,931671,931676,4194304,256,0,0,12,24,279936,0x7f820d595900,0x7f8101a37540,524288,2198801,281447692,12076537077691807,12076537077862919,12076537078601637,12076537078653045
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,931671,931676,4194304,256,0,0,24,24,286528,0x7f820d595800,0x7f8101a37580,524288,3281334,420013156,12076537078700173,12076537078873476,12076537079190916,12076537079240929
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,931671,931676,4194304,256,0,0,20,24,288000,0x7f820d595700,0x7f8101a375c0,524288,2281062,291946364,12076537079265945,12076537079453635,12076537080625473,12076537080673754
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,931671,931676,4194304,256,0,0,32,24,294592,0x7f820d595600,0x7f8101a37600,524288,3277654,419536336,12076537080699312,12076537080887392,12076537081498751,12076537081548972
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,931671,931676,4194304,256,0,0,24,24,301184,0x7f820d595500,0x7f8101a37640,524288,3326426,425791936,12076537081574089,12076537081763710,12076537082082270,12076537082132197
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,931671,931676,4194304,256,0,0,12,24,304960,0x7f820d595400,0x7f8101a37680,524288,2233117,285918628,12076537082162814,12076537082338749,12076537083218107,12076537083267408
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,931671,931676,4194304,256,0,0,24,24,313600,0x7f820d595300,0x7f8101a376c0,524288,3280601,419928344,12076537083314145,12076537083483706,12076537083893146,12076537083941402
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,931671,931676,4194304,256,0,0,20,24,314816,0x7f820d595a00,0x7f8101a37700,524288,2350440,300841592,12076537083965417,12076537084163225,12076537085714582,12076537085766818
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,931671,931676,4194304,256,0,0,20,24,317568,0x7f820d595900,0x7f8101a37740,524288,2288263,292945500,12076537085793077,12076537085975381,12076537086772339,12076537086822922
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,931671,931676,4194304,256,0,0,12,24,320320,0x7f820d595800,0x7f8101a37780,524288,2153711,275738376,12076537086848490,12076537087037299,12076537087452018,12076537087502296
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,931671,931676,4194304,256,0,0,12,24,324096,0x7f820d595700,0x7f8101a377c0,524288,2318144,296740524,12076537087526932,12076537087715057,12076537088875215,12076537088925383
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,931671,931676,4194304,256,0,0,12,24,328896,0x7f820d595600,0x7f8101a37800,524288,2241716,286894612,12076537088968353,12076537089144654,12076537089930413,12076537089982199
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,931671,931676,4194304,256,0,0,20,24,330112,0x7f820d595500,0x7f8101a37840,524288,2614237,334529596,12076537090021382,12076537090194092,12076537093247366,12076537093298057
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,931671,931676,4194304,256,0,0,20,24,332864,0x7f820d595400,0x7f8101a37880,524288,2310959,295677252,12076537093323414,12076537093509765,12076537095054242,12076537095104016
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,931671,931676,4194304,256,0,0,12,24,335616,0x7f820d595300,0x7f8101a378c0,524288,2319139,296774904,12076537095135775,12076537095308321,12076537096098399,12076537096147156
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,931671,931676,4194304,256,0,0,12,24,339392,0x7f820d595a00,0x7f8101a37900,524288,2470513,316064060,12076537096178144,12076537096345119,12076537098626394,12076537098675920
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,931671,931676,4194304,256,0,0,12,24,344192,0x7f820d595900,0x7f8101a37940,524288,2391560,306139512,12076537098723479,12076537098895353,12076537100430390,12076537100481950
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,931671,931676,4194304,256,0,0,20,24,345408,0x7f820d595800,0x7f8101a37980,524288,2951383,377816276,12076537100509471,12076537100688150,12076537106746537,12076537106797798
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,931671,931676,4194304,256,0,0,20,24,348160,0x7f820d595700,0x7f8101a379c0,524288,3477571,445081448,12076537106823726,12076537107010536,12076537110055009,12076537110109799
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,931671,931676,4194304,256,0,0,12,24,350912,0x7f820d595600,0x7f8101a37a00,524288,2506449,320772408,12076537110133613,12076537110323169,12076537111862366,12076537111911390
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,931671,931676,4194304,256,0,0,12,24,0,0x7f820d595500,0x7f8101a37a40,524288,2530108,323915568,12076537111936436,12076537112128066,12076537116655897,12076537116710397
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid grd Workgroup_Size LDS_Per_Workgroup scr vgpr SGPR fbar sig obj SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 __amd_rocclr_fillBuffer.kd 0 0 0 931671 931676 33554432 256 0 0 8 32 6464 0x0 0x7f8101a04180 1048576 10991950 1406583256 12076536745644699 12076536990667420 12076536990991419 12076536991092712
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 931671 931676 32768 256 0 0 24 24 12480 0x0 0x7f8101a35100 4096 109855 14068084 12076537005633911 12076537005965694 12076537005972254 12076537005977540
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 4 931671 931676 4194304 256 0 0 24 24 12928 0x7f820d595900 0x7f8101a35140 524288 10827501 1385924644 12076537006052800 12076537006288733 12076537006426653 12076537006431615
5 3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 6 931671 931676 4194304 256 0 0 36 24 13632 0x7f820d595800 0x7f8101a35180 524288 13152373 1683491304 12076537006499130 12076537006707452 12076537006957211 12076537007029086
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 8 931671 931676 4194304 256 0 0 28 24 14080 0x7f820d595700 0x7f8101a351c0 524288 14200061 1817639572 12076537007068339 12076537007304890 12076537007556409 12076537007625185
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 10 931671 931676 4194304 256 0 0 24 24 14528 0x7f820d595600 0x7f8101a35200 524288 11407226 1460160184 12076537007643849 12076537007878488 12076537008015288 12076537008020710
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 12 931671 931676 4194304 256 0 0 24 24 14976 0x7f820d595500 0x7f8101a35240 524288 10073682 1289371852 12076537008063009 12076537008302007 12076537008442327 12076537008446913
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 14 931671 931676 4194304 256 0 0 24 24 15424 0x7f820d595400 0x7f8101a35280 524288 12069674 1544916740 12076537008531060 12076537008737366 12076537008870326 12076537008875250
10 8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 16 931671 931676 4194304 256 0 0 28 24 16128 0x7f820d595300 0x7f8101a352c0 524288 13834162 1770759264 12076537008926375 12076537009160245 12076537009417524 12076537009487819
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 18 931671 931676 4194304 256 0 0 28 24 16832 0x7f820d595a00 0x7f8101a35300 524288 13752043 1760197408 12076537009510792 12076537009741683 12076537009996242 12076537010065825
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 20 931671 931676 4194304 256 0 0 24 24 17536 0x7f820d595900 0x7f8101a35340 524288 12622999 1615692540 12076537010086012 12076537010327921 12076537010457841 12076537010462452
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 22 931671 931676 4194304 256 0 0 24 24 18240 0x7f820d595800 0x7f8101a35380 524288 10876400 1392226256 12076537010508829 12076537010736720 12076537010874480 12076537010879248
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 24 931671 931676 4194304 256 0 0 24 24 18944 0x7f820d595700 0x7f8101a353c0 524288 12430221 1591034056 12076537010943457 12076537011160559 12076537011290959 12076537011296013
15 13 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 26 931671 931676 4194304 256 0 0 28 24 19904 0x7f820d595600 0x7f8101a35400 524288 13681979 1751246956 12076537011345395 12076537011564078 12076537011819117 12076537011888365
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 28 931671 931676 4194304 256 0 0 28 24 20608 0x7f820d595500 0x7f8101a35440 524288 13735217 1758153172 12076537011910246 12076537012149516 12076537012402155 12076537012472131
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 30 931671 931676 4194304 256 0 0 24 24 21312 0x7f820d595400 0x7f8101a35480 524288 12508963 1601114468 12076537012493200 12076537012722794 12076537012853194 12076537012857968
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 32 931671 931676 4194304 256 0 0 24 24 22016 0x7f820d595300 0x7f8101a354c0 524288 11865378 1518770176 12076537012902471 12076537013134313 12076537013267113 12076537013272179
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 34 931671 931676 4194304 256 0 0 24 24 22720 0x7f820d595a00 0x7f8101a35500 524288 12904609 1651830556 12076537013335076 12076537013544232 12076537013673032 12076537013677733
20 18 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 36 931671 931676 4194304 256 0 0 28 24 23680 0x7f820d595900 0x7f8101a35540 524288 13326940 1705836624 12076537013729960 12076537013951431 12076537014209830 12076537014281426
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 38 931671 931676 4194304 256 0 0 28 24 24384 0x7f820d595800 0x7f8101a35580 524288 14016563 1794089300 12076537014304209 12076537014539109 12076537014792068 12076537014861345
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 40 931671 931676 4194304 256 0 0 24 24 25088 0x7f820d595700 0x7f8101a355c0 524288 12453533 1594103040 12076537014885710 12076537015130147 12076537015260227 12076537015265096
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 42 931671 931676 4194304 256 0 0 24 24 25792 0x7f820d595600 0x7f8101a35600 524288 11823515 1513438712 12076537015309529 12076537015531426 12076537015664866 12076537015669879
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 44 931671 931676 4194304 256 0 0 24 24 26496 0x7f820d595500 0x7f8101a35640 524288 13009055 1665205064 12076537015731223 12076537015938625 12076537016067425 12076537016072638
25 23 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 46 931671 931676 4194304 256 0 0 28 24 27712 0x7f820d595400 0x7f8101a35680 524288 13728992 1757293256 12076537016114786 12076537016346784 12076537016605503 12076537016674478
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 48 931671 931676 4194304 256 0 0 28 24 28416 0x7f820d595300 0x7f8101a356c0 524288 14176355 1814547952 12076537016694795 12076537016926142 12076537017178621 12076537017249808
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 50 931671 931676 4194304 256 0 0 24 24 29120 0x7f820d595a00 0x7f8101a35700 524288 12000157 1535962068 12076537017277078 12076537017506300 12076537017638300 12076537017643230
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 52 931671 931676 4194304 256 0 0 24 24 30080 0x7f820d595900 0x7f8101a35740 524288 12107321 1549687848 12076537017694325 12076537017909179 12076537018042459 12076537018047962
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 54 931671 931676 4194304 256 0 0 24 24 30784 0x7f820d595800 0x7f8101a35780 524288 12002481 1536392300 12076537018108966 12076537018322778 12076537018454458 12076537018459318
30 28 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 56 931671 931676 4194304 256 0 0 28 24 32000 0x7f820d595700 0x7f8101a357c0 524288 13300232 1702375832 12076537018508780 12076537018739257 12076537018997816 12076537019066878
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 58 931671 931676 4194304 256 0 0 28 24 32960 0x7f820d595600 0x7f8101a35800 524288 13638264 1745713280 12076537019087336 12076537019321495 12076537019573494 12076537019642609
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 60 931671 931676 4194304 256 0 0 24 24 33920 0x7f820d595500 0x7f8101a35840 524288 13304502 1702977096 12076537019662025 12076537019890133 12076537020017013 12076537020022014
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 62 931671 931676 4194304 256 0 0 24 24 34880 0x7f820d595400 0x7f8101a35880 524288 10787214 1380726760 12076537020071917 12076537020290452 12076537020428692 12076537020433440
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 64 931671 931676 4194304 256 0 0 24 24 35840 0x7f820d595300 0x7f8101a358c0 524288 12889254 1649864640 12076537020496016 12076537020704211 12076537020832211 12076537020837030
35 33 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 66 931671 931676 4194304 256 0 0 28 24 37312 0x7f820d595a00 0x7f8101a35900 524288 14166125 1813262800 12076537020886603 12076537021114290 12076537021365649 12076537021436746
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 68 931671 931676 4194304 256 0 0 28 24 38272 0x7f820d595900 0x7f8101a35940 524288 13076060 1673655584 12076537021456433 12076537021685648 12076537021941807 12076537022021484
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 70 931671 931676 4194304 256 0 0 24 24 39232 0x7f820d595800 0x7f8101a35980 524288 11865526 1518783952 12076537022040339 12076537022271406 12076537022404206 12076537022409155
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 72 931671 931676 4194304 256 0 0 24 24 40192 0x7f820d595700 0x7f8101a359c0 524288 11035340 1412490616 12076537022460260 12076537022681805 12076537022817965 12076537022822684
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 74 931671 931676 4194304 256 0 0 24 24 41152 0x7f820d595600 0x7f8101a35a00 524288 12250772 1568128872 12076537022883507 12076537023098604 12076537023229644 12076537023234680
40 38 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 76 931671 931676 4194304 256 0 0 28 24 42624 0x7f820d595500 0x7f8101a35a40 524288 14123077 1807746404 12076537023285405 12076537023503243 12076537023767242 12076537023836349
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 78 931671 931676 4194304 256 0 0 28 24 43584 0x7f820d595400 0x7f8101a35a80 524288 14205139 1818274976 12076537023855705 12076537024097161 12076537024347880 12076537024419033
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 80 931671 931676 4194304 256 0 0 24 24 44544 0x7f820d595300 0x7f8101a35ac0 524288 13116252 1678894716 12076537024439401 12076537024669959 12076537024797799 12076537024802647
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 82 931671 931676 4194304 256 0 0 24 24 45760 0x7f820d595a00 0x7f8101a35b00 524288 11853180 1517189460 12076537024853451 12076537025072838 12076537025205638 12076537025210866
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 84 931671 931676 4194304 256 0 0 24 24 46720 0x7f820d595900 0x7f8101a35b40 524288 13137811 1681585836 12076537025271329 12076537025476517 12076537025605317 12076537025610339
45 43 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 86 931671 931676 4194304 256 0 0 28 24 48448 0x7f820d595800 0x7f8101a35b80 524288 12530281 1603873608 12076537025658579 12076537025871876 12076537026131715 12076537026201729
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 88 931671 931676 4194304 256 0 0 28 24 49408 0x7f820d595700 0x7f8101a35bc0 524288 13561484 1735844340 12076537026223290 12076537026451714 12076537026704673 12076537026773864
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 90 931671 931676 4194304 256 0 0 24 24 50368 0x7f820d595600 0x7f8101a35c00 524288 12885465 1649371200 12076537026791927 12076537027039073 12076537027168512 12076537027173407
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 92 931671 931676 4194304 256 0 0 24 24 51584 0x7f820d595500 0x7f8101a35c40 524288 11421633 1461977256 12076537027219823 12076537027449631 12076537027586111 12076537027590893
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 94 931671 931676 4194304 256 0 0 24 24 52544 0x7f820d595400 0x7f8101a35c80 524288 13346675 1708389748 12076537027651616 12076537027857790 12076537027984990 12076537027989876
50 48 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 96 931671 931676 4194304 256 0 0 28 24 54272 0x7f820d595300 0x7f8101a35cc0 524288 13057516 1671339108 12076537028034488 12076537028255549 12076537028516828 12076537028587297
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 98 931671 931676 4194304 256 0 0 28 24 55488 0x7f820d595a00 0x7f8101a35d00 524288 13927985 1782757888 12076537028607324 12076537028832987 12076537029088027 12076537029159882
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 100 931671 931676 4194304 256 0 0 24 24 56704 0x7f820d595900 0x7f8101a35d40 524288 12262502 1569588808 12076537029177505 12076537029407386 12076537029538905 12076537029543746
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 102 931671 931676 4194304 256 0 0 24 24 58176 0x7f820d595800 0x7f8101a35d80 524288 10766993 1378140040 12076537029593639 12076537029804824 12076537029942264 12076537029946976
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 104 931671 931676 4194304 256 0 0 24 24 59392 0x7f820d595700 0x7f8101a35dc0 524288 12460249 1594860708 12076537030013901 12076537030222583 12076537030354103 12076537030358852
55 53 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 106 931671 931676 4194304 256 0 0 28 24 61376 0x7f820d595600 0x7f8101a35e00 524288 11574719 1481596380 12076537030410188 12076537030622742 12076537030887701 12076537030957105
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 108 931671 931676 4194304 256 0 0 28 24 62592 0x7f820d595500 0x7f8101a35e40 524288 13925416 1782478724 12076537030975910 12076537031224660 12076537031476820 12076537031547303
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 110 931671 931676 4194304 256 0 0 24 24 63808 0x7f820d595400 0x7f8101a35e80 524288 12431998 1591308920 12076537031572119 12076537031803059 12076537031934258 12076537031938991
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 112 931671 931676 4194304 256 0 0 24 24 65280 0x7f820d595300 0x7f8101a35ec0 524288 9470204 1212098968 12076537031989325 12076537032219377 12076537032358897 12076537032363822
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 114 931671 931676 4194304 256 0 0 24 24 66496 0x7f820d595a00 0x7f8101a35f00 524288 12349368 1580712168 12076537032426879 12076537032628016 12076537032758736 12076537032763665
60 58 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 116 931671 931676 4194304 256 0 0 28 24 68480 0x7f820d595900 0x7f8101a35f40 524288 12205000 1562224976 12076537032815241 12076537033036495 12076537033296494 12076537033360916
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 118 931671 931676 4194304 256 0 0 28 24 69696 0x7f820d595800 0x7f8101a35f80 524288 13408863 1716267348 12076537033385843 12076537033618733 12076537033870893 12076537033921619
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 120 931671 931676 4194304 256 0 0 24 24 70912 0x7f820d595700 0x7f8101a35fc0 524288 12132337 1552850360 12076537033946045 12076537034142572 12076537034274731 12076537034278894
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 122 931671 931676 4194304 256 0 0 24 24 72384 0x7f820d595600 0x7f8101a36000 524288 7901381 1011288268 12076537034329157 12076537034505611 12076537034641930 12076537034646157
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 124 931671 931676 4194304 256 0 0 24 24 73600 0x7f820d595500 0x7f8101a36040 524288 12435176 1591638924 12076537034709455 12076537034874250 12076537035005769 12076537035010294
65 63 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 126 931671 931676 4194304 256 0 0 28 24 75840 0x7f820d595400 0x7f8101a36080 524288 11989327 1534618116 12076537035058224 12076537035244649 12076537035505128 12076537035555829
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 128 931671 931676 4194304 256 0 0 28 24 77056 0x7f820d595300 0x7f8101a360c0 524288 13007964 1664985512 12076537035580395 12076537035763687 12076537036016166 12076537036066599
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 130 931671 931676 4194304 256 0 0 24 24 78272 0x7f820d595a00 0x7f8101a36100 524288 12590944 1611595548 12076537036090484 12076537036275206 12076537036405285 12076537036409497
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 132 931671 931676 4194304 256 0 0 24 24 80000 0x7f820d595900 0x7f8101a36140 524288 6841792 875700556 12076537036459260 12076537036637924 12076537036781604 12076537036785737
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 134 931671 931676 4194304 256 0 0 24 24 81216 0x7f820d595800 0x7f8101a36180 524288 12856824 1645714428 12076537036845238 12076537037008323 12076537037137603 12076537037141679
70 68 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 136 931671 931676 4194304 256 0 0 28 24 83456 0x7f820d595700 0x7f8101a361c0 524288 14168224 1813459176 12076537037192263 12076537037371682 12076537037633922 12076537037684839
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 138 931671 931676 4194304 256 0 0 28 24 84928 0x7f820d595600 0x7f8101a36200 524288 13053157 1670735760 12076537037708343 12076537037894561 12076537038146720 12076537038197783
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 140 931671 931676 4194304 256 0 0 24 24 86400 0x7f820d595500 0x7f8101a36240 524288 12189637 1560184936 12076537038225816 12076537038412319 12076537038544319 12076537038548426
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 142 931671 931676 4194304 256 0 0 24 24 88128 0x7f820d595400 0x7f8101a36280 524288 5375163 688039676 12076537038598669 12076537038799518 12076537038948318 12076537038952187
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 144 931671 931676 4194304 256 0 0 24 24 89600 0x7f820d595300 0x7f8101a362c0 524288 11182771 1431435040 12076537039037556 12076537039212477 12076537039347517 12076537039351359
75 73 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 146 931671 931676 4194304 256 0 0 28 24 92096 0x7f820d595a00 0x7f8101a36300 524288 13300122 1702427236 12076537039400491 12076537039579356 12076537039846715 12076537039894359
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 148 931671 931676 4194304 256 0 0 28 24 93568 0x7f820d595900 0x7f8101a36340 524288 13163914 1685019488 12076537039921009 12076537040128154 12076537040381434 12076537040431689
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 150 931671 931676 4194304 256 0 0 24 24 95040 0x7f820d595800 0x7f8101a36380 524288 12123514 1551890952 12076537040463378 12076537040635353 12076537040768632 12076537040772483
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 152 931671 931676 4194304 256 0 0 24 24 96768 0x7f820d595700 0x7f8101a363c0 524288 5155730 659888928 12076537040831563 12076537041005752 12076537041163511 12076537041167297
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 154 931671 931676 4194304 256 0 0 24 24 98240 0x7f820d595600 0x7f8101a36400 524288 12479243 1597274524 12076537041231577 12076537041411351 12076537041542710 12076537041546623
80 78 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 156 931671 931676 4194304 256 0 0 28 24 100736 0x7f820d595500 0x7f8101a36440 524288 12244800 1567268248 12076537041595894 12076537041770229 12076537042034709 12076537042083481
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 158 931671 931676 4194304 256 0 0 28 24 102208 0x7f820d595400 0x7f8101a36480 524288 13934187 1783508536 12076537042119869 12076537042298068 12076537042558227 12076537042605563
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 160 931671 931676 4194304 256 0 0 24 24 103680 0x7f820d595300 0x7f8101a364c0 524288 12662941 1620890016 12076537042632433 12076537042807026 12076537042936946 12076537042940806
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 162 931671 931676 4194304 256 0 0 24 24 105664 0x7f820d595a00 0x7f8101a36500 524288 3674071 470163008 12076537042990539 12076537043175185 12076537043341265 12076537043344998
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 164 931671 931676 4194304 256 0 0 24 24 107136 0x7f820d595900 0x7f8101a36540 524288 12560686 1607734028 12076537043408476 12076537043582544 12076537043712304 12076537043716369
85 83 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 166 931671 931676 4194304 256 0 0 28 24 109888 0x7f820d595800 0x7f8101a36580 524288 9566527 1224514548 12076537043764689 12076537043945583 12076537044210062 12076537044257936
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 168 931671 931676 4194304 256 0 0 28 24 111360 0x7f820d595700 0x7f8101a365c0 524288 13574083 1737513344 12076537044278074 12076537044476302 12076537044772141 12076537044821575
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 170 931671 931676 4194304 256 0 0 24 24 112832 0x7f820d595600 0x7f8101a36600 524288 12941392 1656450752 12076537044855778 12076537045040460 12076537045169900 12076537045173840
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 172 931671 931676 4194304 256 0 0 24 24 114816 0x7f820d595500 0x7f8101a36640 524288 3796563 485895600 12076537045223322 12076537045396139 12076537045570698 12076537045574545
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 174 931671 931676 4194304 256 0 0 24 24 116288 0x7f820d595400 0x7f8101a36680 524288 12860157 1646126936 12076537045635398 12076537045807978 12076537045937737 12076537045941628
90 88 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 176 931671 931676 4194304 256 0 0 28 24 119040 0x7f820d595300 0x7f8101a366c0 524288 8808066 1127415140 12076537045989026 12076537046175977 12076537046433256 12076537046481262
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 178 931671 931676 4194304 256 0 0 28 24 120768 0x7f820d595a00 0x7f8101a36700 524288 13987492 1790319144 12076537046500828 12076537046692455 12076537046942054 12076537046989237
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 180 931671 931676 4194304 256 0 0 24 24 122496 0x7f820d595900 0x7f8101a36740 524288 11869746 1519364556 12076537047022769 12076537047207974 12076537047342053 12076537047346090
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 182 931671 931676 4194304 256 0 0 24 24 124736 0x7f820d595800 0x7f8101a36780 524288 3676041 470439040 12076537047393098 12076537047567173 12076537047749892 12076537047756043
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 184 931671 931676 4194304 256 0 0 24 24 126464 0x7f820d595700 0x7f8101a367c0 524288 10235098 1310068808 12076537047813851 12076537047982851 12076537048123491 12076537048127554
95 93 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 186 931671 931676 4194304 256 0 0 20 24 127936 0x7f820d595600 0x7f8101a36800 524288 4059035 519533928 12076537048176345 12076537048357410 12076537048622049 12076537048670624
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 188 931671 931676 4194304 256 0 0 28 24 129664 0x7f820d595500 0x7f8101a36840 524288 13498901 1727885208 12076537048695220 12076537048874049 12076537049139168 12076537049189900
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 190 931671 931676 4194304 256 0 0 24 24 131392 0x7f820d595400 0x7f8101a36880 524288 12079436 1546157672 12076537049216259 12076537049402687 12076537049535967 12076537049539531
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 192 931671 931676 4194304 256 0 0 24 24 133632 0x7f820d595300 0x7f8101a368c0 524288 3668964 469562380 12076537049587670 12076537049753246 12076537049945406 12076537049993976
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 194 931671 931676 4194304 256 0 0 24 24 135360 0x7f820d595a00 0x7f8101a36900 524288 11740357 1502702696 12076537050040563 12076537050217085 12076537050350524 12076537050354486
100 98 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 196 931671 931676 4194304 256 0 0 20 24 136832 0x7f820d595900 0x7f8101a36940 524288 2910339 372538880 12076537050396424 12076537050582364 12076537050867643 12076537050915129
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 198 931671 931676 4194304 256 0 0 28 24 138560 0x7f820d595800 0x7f8101a36980 524288 13871266 1775489480 12076537050935136 12076537051129562 12076537051378361 12076537051428144
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 200 931671 931676 4194304 256 0 0 24 24 140288 0x7f820d595700 0x7f8101a369c0 524288 10902850 1395507584 12076537051457759 12076537051625241 12076537051762360 12076537051766473
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 202 931671 931676 4194304 256 0 0 24 24 142784 0x7f820d595600 0x7f8101a36a00 524288 3339333 427373264 12076537051814793 12076537051985240 12076537052195639 12076537052218053
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 204 931671 931676 4194304 256 0 0 24 24 144768 0x7f820d595500 0x7f8101a36a40 524288 10729796 1373365204 12076537052275480 12076537052451318 12076537052590998 12076537052595194
105 103 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 206 931671 931676 4194304 256 0 0 20 24 145728 0x7f820d595400 0x7f8101a36a80 524288 2567397 328588288 12076537052639166 12076537052819637 12076537053126196 12076537053177948
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 208 931671 931676 4194304 256 0 0 28 24 147712 0x7f820d595300 0x7f8101a36ac0 524288 14087651 1803179864 12076537053202885 12076537053384092 12076537053643292 12076537053696333
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 210 931671 931676 4194304 256 0 0 24 24 149696 0x7f820d595a00 0x7f8101a36b00 524288 10511919 1345492040 12076537053718624 12076537053899770 12076537054037370 12076537054040803
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 212 931671 931676 4194304 256 0 0 24 24 152192 0x7f820d595900 0x7f8101a36b40 524288 3448993 441336096 12076537054089083 12076537054261369 12076537054489689 12076537054537557
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 214 931671 931676 4194304 256 0 0 24 24 154176 0x7f820d595800 0x7f8101a36b80 524288 10589795 1355519852 12076537054581259 12076537054753528 12076537054891288 12076537054894872
110 108 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 216 931671 931676 4194304 256 0 0 20 24 155648 0x7f820d595700 0x7f8101a36bc0 524288 2471787 316445520 12076537054943132 12076537055120887 12076537055450487 12076537055499136
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 218 931671 931676 4194304 256 0 0 28 24 157632 0x7f820d595600 0x7f8101a36c00 524288 13426249 1718562836 12076537055526437 12076537055705366 12076537055968566 12076537056018392
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 220 931671 931676 4194304 256 0 0 24 24 159616 0x7f820d595500 0x7f8101a36c40 524288 11301734 1446524700 12076537056044290 12076537056225205 12076537056361045 12076537056364305
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 222 931671 931676 4194304 256 0 0 24 24 162368 0x7f820d595400 0x7f8101a36c80 524288 3490789 446777020 12076537056412325 12076537056586164 12076537056832884 12076537056880816
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 224 931671 931676 4194304 256 0 0 24 24 164608 0x7f820d595300 0x7f8101a36cc0 524288 9570521 1225124668 12076537056925479 12076537057104403 12076537057245683 12076537057249001
115 113 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 226 931671 931676 4194304 256 0 0 20 24 166336 0x7f820d595a00 0x7f8101a36d00 524288 2372318 303598848 12076537057292863 12076537057474002 12076537057850002 12076537057897387
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 228 931671 931676 4194304 256 0 0 28 24 168576 0x7f820d595900 0x7f8101a36d40 524288 12464562 1595428592 12076537057924538 12076537058100241 12076537058359600 12076537058408197
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 230 931671 931676 4194304 256 0 0 24 24 170816 0x7f820d595800 0x7f8101a36d80 524288 9076426 1161746084 12076537058435909 12076537058613520 12076537058755280 12076537058759080
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 232 931671 931676 4194304 256 0 0 24 24 174080 0x7f820d595700 0x7f8101a36dc0 524288 3338560 427183016 12076537058808111 12076537058983759 12076537059264079 12076537059312970
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 234 931671 931676 4194304 256 0 0 24 24 176576 0x7f820d595600 0x7f8101a36e00 524288 8169712 1045803212 12076537059355399 12076537059529038 12076537059671278 12076537059674934
120 118 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 236 931671 931676 4194304 256 0 0 20 24 177792 0x7f820d595500 0x7f8101a36e40 524288 2353641 301277372 12076537059723634 12076537059899597 12076537060325676 12076537060373934
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 238 931671 931676 4194304 256 0 0 28 24 180288 0x7f820d595400 0x7f8101a36e80 524288 9843291 1259866916 12076537060400633 12076537060580716 12076537060843115 12076537060890996
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 240 931671 931676 4194304 256 0 0 24 24 182784 0x7f820d595300 0x7f8101a36ec0 524288 7934379 1015561276 12076537060915010 12076537061103275 12076537061240074 12076537061243822
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 242 931671 931676 4194304 256 0 0 24 24 186304 0x7f820d595a00 0x7f8101a36f00 524288 3414394 436994796 12076537061294446 12076537061460554 12076537061776073 12076537061824292
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 244 931671 931676 4194304 256 0 0 24 24 189312 0x7f820d595900 0x7f8101a36f40 524288 3243029 414936448 12076537061869295 12076537062045513 12076537062197832 12076537062201594
125 123 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 246 931671 931676 4194304 256 0 0 20 24 190784 0x7f820d595800 0x7f8101a36f80 524288 2304386 294994940 12076537062243211 12076537062434952 12076537062953191 12076537063004657
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 248 931671 931676 4194304 256 0 0 28 24 193792 0x7f820d595700 0x7f8101a36fc0 524288 8029014 1027723944 12076537063034483 12076537063201990 12076537063501669 12076537063552536
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 250 931671 931676 4194304 256 0 0 24 24 196800 0x7f820d595600 0x7f8101a37000 524288 3230460 413418080 12076537063581490 12076537063771589 12076537063926469 12076537063929728
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 252 931671 931676 4194304 256 0 0 24 24 201088 0x7f820d595500 0x7f8101a37040 524288 3290249 421097372 12076537063977818 12076537064150948 12076537064537347 12076537064585017
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 254 931671 931676 4194304 256 0 0 24 24 204608 0x7f820d595400 0x7f8101a37080 524288 3561632 455977932 12076537064625312 12076537064796387 12076537064973826 12076537064977427
130 128 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 256 931671 931676 4194304 256 0 0 20 24 206080 0x7f820d595300 0x7f8101a370c0 524288 2321065 297025088 12076537065030806 12076537065194146 12076537065806784 12076537065857855
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 258 931671 931676 4194304 256 0 0 28 24 209600 0x7f820d595a00 0x7f8101a37100 524288 4092771 523943812 12076537065882991 12076537066076064 12076537066432383 12076537066481665
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 260 931671 931676 4194304 256 0 0 24 24 213120 0x7f820d595900 0x7f8101a37140 524288 3283078 420290284 12076537066509306 12076537066689983 12076537066868542 12076537066871941
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 262 931671 931676 4194304 256 0 0 24 24 218176 0x7f820d595800 0x7f8101a37180 524288 4011228 513419724 12076537066914841 12076537067101342 12076537067558141 12076537067607730
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 264 931671 931676 4194304 256 0 0 24 24 222208 0x7f820d595700 0x7f8101a371c0 524288 3086405 395051364 12076537067650379 12076537067823100 12076537068023100 12076537068072735
135 133 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 266 931671 931676 4194304 256 0 0 20 24 223936 0x7f820d595600 0x7f8101a37200 524288 2343631 299877004 12076537068103281 12076537068292219 12076537069004378 12076537069051906
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 268 931671 931676 4194304 256 0 0 28 24 227968 0x7f820d595500 0x7f8101a37240 524288 3513231 449720508 12076537069071342 12076537069256377 12076537069655256 12076537069702486
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 270 931671 931676 4194304 256 0 0 24 24 232000 0x7f820d595400 0x7f8101a37280 524288 3288966 421048972 12076537069724427 12076537069905016 12076537070108855 12076537070158925
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 272 931671 931676 4194304 256 0 0 24 24 237824 0x7f820d595300 0x7f8101a372c0 524288 4361274 558258120 12076537070178301 12076537070361495 12076537070888534 12076537070938746
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 274 931671 931676 4194304 256 0 0 24 24 242368 0x7f820d595a00 0x7f8101a37300 524288 3190851 408410816 12076537070978430 12076537071152693 12076537071411572 12076537071460717
140 138 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 276 931671 931676 4194304 256 0 0 20 24 243584 0x7f820d595900 0x7f8101a37340 524288 2332685 298669936 12076537071479061 12076537071664052 12076537072466290 12076537072515609
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 278 931671 931676 4194304 256 0 0 28 24 248128 0x7f820d595800 0x7f8101a37380 524288 3450545 441725456 12076537072538942 12076537072728690 12076537073149329 12076537073198138
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 280 931671 931676 4194304 256 0 0 24 24 252672 0x7f820d595700 0x7f8101a373c0 524288 3108461 397911152 12076537073223355 12076537073405808 12076537073632368 12076537073680135
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 282 931671 931676 4194304 256 0 0 24 24 259264 0x7f820d595600 0x7f8101a37400 524288 4492613 575010916 12076537073712776 12076537073885327 12076537074483886 12076537074534885
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 284 931671 931676 4194304 256 0 0 24 24 264832 0x7f820d595500 0x7f8101a37440 524288 3287085 420713856 12076537074580450 12076537074754125 12076537075024845 12076537075073777
145 143 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 286 931671 931676 4194304 256 0 0 20 24 266304 0x7f820d595400 0x7f8101a37480 524288 2305984 295182096 12076537075098513 12076537075280044 12076537076267402 12076537076316098
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 288 931671 931676 4194304 256 0 0 28 24 271872 0x7f820d595300 0x7f8101a374c0 524288 3310118 423677572 12076537076341966 12076537076532521 12076537077049320 12076537077097722
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 290 931671 931676 4194304 256 0 0 24 24 277440 0x7f820d595a00 0x7f8101a37500 524288 3398156 434965224 12076537077131816 12076537077303880 12076537077609159 12076537077657343
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 292 931671 931676 4194304 256 0 0 12 24 279936 0x7f820d595900 0x7f8101a37540 524288 2198801 281447692 12076537077691807 12076537077862919 12076537078601637 12076537078653045
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 294 931671 931676 4194304 256 0 0 24 24 286528 0x7f820d595800 0x7f8101a37580 524288 3281334 420013156 12076537078700173 12076537078873476 12076537079190916 12076537079240929
150 148 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 296 931671 931676 4194304 256 0 0 20 24 288000 0x7f820d595700 0x7f8101a375c0 524288 2281062 291946364 12076537079265945 12076537079453635 12076537080625473 12076537080673754
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 298 931671 931676 4194304 256 0 0 32 24 294592 0x7f820d595600 0x7f8101a37600 524288 3277654 419536336 12076537080699312 12076537080887392 12076537081498751 12076537081548972
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 300 931671 931676 4194304 256 0 0 24 24 301184 0x7f820d595500 0x7f8101a37640 524288 3326426 425791936 12076537081574089 12076537081763710 12076537082082270 12076537082132197
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 302 931671 931676 4194304 256 0 0 12 24 304960 0x7f820d595400 0x7f8101a37680 524288 2233117 285918628 12076537082162814 12076537082338749 12076537083218107 12076537083267408
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 304 931671 931676 4194304 256 0 0 24 24 313600 0x7f820d595300 0x7f8101a376c0 524288 3280601 419928344 12076537083314145 12076537083483706 12076537083893146 12076537083941402
155 153 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 306 931671 931676 4194304 256 0 0 20 24 314816 0x7f820d595a00 0x7f8101a37700 524288 2350440 300841592 12076537083965417 12076537084163225 12076537085714582 12076537085766818
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 308 931671 931676 4194304 256 0 0 20 24 317568 0x7f820d595900 0x7f8101a37740 524288 2288263 292945500 12076537085793077 12076537085975381 12076537086772339 12076537086822922
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 310 931671 931676 4194304 256 0 0 12 24 320320 0x7f820d595800 0x7f8101a37780 524288 2153711 275738376 12076537086848490 12076537087037299 12076537087452018 12076537087502296
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 312 931671 931676 4194304 256 0 0 12 24 324096 0x7f820d595700 0x7f8101a377c0 524288 2318144 296740524 12076537087526932 12076537087715057 12076537088875215 12076537088925383
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 314 931671 931676 4194304 256 0 0 12 24 328896 0x7f820d595600 0x7f8101a37800 524288 2241716 286894612 12076537088968353 12076537089144654 12076537089930413 12076537089982199
160 158 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 316 931671 931676 4194304 256 0 0 20 24 330112 0x7f820d595500 0x7f8101a37840 524288 2614237 334529596 12076537090021382 12076537090194092 12076537093247366 12076537093298057
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 318 931671 931676 4194304 256 0 0 20 24 332864 0x7f820d595400 0x7f8101a37880 524288 2310959 295677252 12076537093323414 12076537093509765 12076537095054242 12076537095104016
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 320 931671 931676 4194304 256 0 0 12 24 335616 0x7f820d595300 0x7f8101a378c0 524288 2319139 296774904 12076537095135775 12076537095308321 12076537096098399 12076537096147156
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 322 931671 931676 4194304 256 0 0 12 24 339392 0x7f820d595a00 0x7f8101a37900 524288 2470513 316064060 12076537096178144 12076537096345119 12076537098626394 12076537098675920
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 324 931671 931676 4194304 256 0 0 12 24 344192 0x7f820d595900 0x7f8101a37940 524288 2391560 306139512 12076537098723479 12076537098895353 12076537100430390 12076537100481950
165 163 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 326 931671 931676 4194304 256 0 0 20 24 345408 0x7f820d595800 0x7f8101a37980 524288 2951383 377816276 12076537100509471 12076537100688150 12076537106746537 12076537106797798
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 328 931671 931676 4194304 256 0 0 20 24 348160 0x7f820d595700 0x7f8101a379c0 524288 3477571 445081448 12076537106823726 12076537107010536 12076537110055009 12076537110109799
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 330 931671 931676 4194304 256 0 0 12 24 350912 0x7f820d595600 0x7f8101a37a00 524288 2506449 320772408 12076537110133613 12076537110323169 12076537111862366 12076537111911390
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 332 931671 931676 4194304 256 0 0 12 24 0 0x7f820d595500 0x7f8101a37a40 524288 2530108 323915568 12076537111936436 12076537112128066 12076537116655897 12076537116710397
@@ -0,0 +1,168 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,grd,Workgroup_Size,LDS_Per_Workgroup,scr,vgpr,SGPR,fbar,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"__amd_rocclr_fillBuffer.kd",0,0,0,932047,932054,33554432,256,0,0,8,32,6464,0x0,0x7f4318204180,502027,502027,17663,4016224,524288,373010853,3812072,0,1506849280,12076539256161927,12076539500209550,12076539500532269,12076539500642792
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,932047,932054,32768,256,0,0,24,24,12480,0x0,0x7f4318235100,28337,28337,21039,226704,512,1125690,76367,0,4517036,12076539515082191,12076539515408737,12076539515415137,12076539515423846
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,932047,932054,4194304,256,0,0,24,24,12928,0x7f4423eba900,0x7f4318235140,214085,214085,21876,1712688,65536,145056154,1546601,0,582037424,12076539515493015,12076539515729376,12076539515859296,12076539515863073
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,932047,932054,4194304,256,0,0,36,24,13632,0x7f4423eba800,0x7f4318235180,384636,384636,29429,3077096,65536,257748821,2910007,0,1032814660,12076539515940978,12076539516139775,12076539516384574,12076539516454523
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,932047,932054,4194304,256,0,0,28,24,14080,0x7f4423eba700,0x7f43182351c0,402492,402492,29357,3219944,65536,279692821,3037066,0,1120588996,12076539516489238,12076539516696253,12076539516951772,12076539517020887
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,932047,932054,4194304,256,0,0,24,24,14528,0x7f4423eba600,0x7f4318235200,212317,212317,22764,1698544,65536,155474951,1531408,0,623720392,12076539517046294,12076539517254331,12076539517383931,12076539517387499
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,932047,932054,4194304,256,0,0,24,24,14976,0x7f4423eba500,0x7f4318235240,211901,211901,22389,1695216,65536,142732486,1522500,0,572750716,12076539517445937,12076539517643130,12076539517771769,12076539517775330
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,932047,932054,4194304,256,0,0,24,24,15424,0x7f4423eba400,0x7f4318235280,215869,215869,19266,1726960,65536,159152180,1562834,0,638425092,12076539517864656,12076539518050328,12076539518182328,12076539518185914
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,932047,932054,4194304,256,0,0,28,24,16128,0x7f4423eba300,0x7f43182352c0,392132,392132,32200,3137064,65536,337425059,2961038,0,1351517408,12076539518245044,12076539518450007,12076539518699126,12076539518741016
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,932047,932054,4194304,256,0,0,28,24,16832,0x7f4423ebaa00,0x7f4318235300,397317,397317,28490,3178544,65536,314230850,3009046,0,1258740612,12076539518777825,12076539518966805,12076539519220404,12076539519289907
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,932047,932054,4194304,256,0,0,24,24,17536,0x7f4423eba900,0x7f4318235340,208428,208428,23475,1667432,65536,168392411,1499567,0,675389732,12076539519317439,12076539519521523,12076539519648243,12076539519651680
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,932047,932054,4194304,256,0,0,24,24,18240,0x7f4423eba800,0x7f4318235380,218181,218181,22368,1745456,65536,148176463,1578162,0,594517888,12076539519709708,12076539519900562,12076539520034162,12076539520037909
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,932047,932054,4194304,256,0,0,24,24,18944,0x7f4423eba700,0x7f43182353c0,211493,211493,23293,1691952,65536,159187710,1520072,0,638568648,12076539520111125,12076539520295281,12076539520423920,12076539520427443
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,932047,932054,4194304,256,0,0,28,24,19904,0x7f4423eba600,0x7f4318235400,392900,392900,22533,3143208,65536,323568499,2957821,0,1296089812,12076539520488988,12076539520679279,12076539520930638,12076539520997003
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,932047,932054,4194304,256,0,0,28,24,20608,0x7f4423eba500,0x7f4318235440,388044,388044,27421,3104360,65536,315968977,2925187,0,1265693716,12076539521029143,12076539521233997,12076539521480877,12076539521549430
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,932047,932054,4194304,256,0,0,24,24,21312,0x7f4423eba400,0x7f4318235480,212861,212861,25994,1702896,65536,160543700,1517346,0,643992048,12076539521571471,12076539521771916,12076539521900715,12076539521904220
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,932047,932054,4194304,256,0,0,24,24,22016,0x7f4423eba300,0x7f43182354c0,215373,215373,21749,1722992,65536,152440532,1553500,0,611571948,12076539521955896,12076539522157834,12076539522289674,12076539522293064
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,932047,932054,4194304,256,0,0,24,24,22720,0x7f4423ebaa00,0x7f4318235500,208701,208701,17514,1669616,65536,165297552,1495890,0,663012708,12076539522363775,12076539522541833,12076539522669193,12076539522672720
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,932047,932054,4194304,256,0,0,28,24,23680,0x7f4423eba900,0x7f4318235540,399460,399460,33571,3195688,65536,364799220,3028168,0,1461014924,12076539522730978,12076539522919912,12076539523175591,12076539523242860
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,932047,932054,4194304,256,0,0,28,24,24384,0x7f4423eba800,0x7f4318235580,397604,397604,29669,3180840,65536,328803190,2990824,0,1317029904,12076539523267366,12076539523465670,12076539523718309,12076539523785009
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,932047,932054,4194304,256,0,0,24,24,25088,0x7f4423eba700,0x7f43182355c0,210581,210581,23874,1684656,65536,161468109,1515980,0,647690564,12076539523809915,12076539524007748,12076539524136228,12076539524139869
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,932047,932054,4194304,256,0,0,24,24,25792,0x7f4423eba600,0x7f4318235600,218085,218085,23334,1744688,65536,160499877,1576869,0,643821736,12076539524202566,12076539524399107,12076539524532706,12076539524536006
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,932047,932054,4194304,256,0,0,24,24,26496,0x7f4423eba500,0x7f4318235640,209717,209717,22643,1677744,65536,159537471,1511311,0,639967800,12076539524607639,12076539524781825,12076539524909345,12076539524912676
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,932047,932054,4194304,256,0,0,28,24,27712,0x7f4423eba400,0x7f4318235680,389613,389613,33391,3116912,65536,315783764,2960375,0,1264951208,12076539524969692,12076539525170144,12076539525420223,12076539525488207
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,932047,932054,4194304,256,0,0,28,24,28416,0x7f4423eba300,0x7f43182356c0,394892,394892,30346,3159144,65536,335876840,2992166,0,1345325376,12076539525512733,12076539525711262,12076539525963741,12076539526030456
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,932047,932054,4194304,256,0,0,24,24,29120,0x7f4423ebaa00,0x7f4318235700,209245,209245,20208,1673968,65536,164075248,1511213,0,658119196,12076539526053679,12076539526253820,12076539526381820,12076539526385386
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,932047,932054,4194304,256,0,0,24,24,30080,0x7f4423eba900,0x7f4318235740,218381,218381,26547,1747056,65536,161860757,1576635,0,649255836,12076539526445337,12076539526628859,12076539526762779,12076539526766174
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,932047,932054,4194304,256,0,0,24,24,30784,0x7f4423eba800,0x7f4318235780,210437,210437,22470,1683504,65536,160228275,1521869,0,642750380,12076539526836936,12076539527008378,12076539527137497,12076539527140951
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,932047,932054,4194304,256,0,0,28,24,32000,0x7f4423eba700,0x7f43182357c0,449005,449005,15250,3592048,65536,298339799,2970249,0,1195174808,12076539527196735,12076539527397656,12076539527686456,12076539527752980
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,932047,932054,4194304,256,0,0,28,24,32960,0x7f4423eba600,0x7f4318235800,396132,396132,28667,3169064,65536,300122611,2992825,0,1202309044,12076539527775251,12076539527971575,12076539528223894,12076539528293094
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,932047,932054,4194304,256,0,0,24,24,33920,0x7f4423eba500,0x7f4318235840,208044,208044,22029,1664360,65536,165662590,1501017,0,664472032,12076539528317059,12076539528514453,12076539528642132,12076539528645540
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,932047,932054,4194304,256,0,0,24,24,34880,0x7f4423eba400,0x7f4318235880,213420,213420,25970,1707368,65536,158450111,1535263,0,635627332,12076539528704590,12076539528890771,12076539529021331,12076539529024856
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,932047,932054,4194304,256,0,0,24,24,35840,0x7f4423eba300,0x7f43182358c0,214341,214341,22778,1714736,65536,158503640,1555723,0,635840568,12076539529095136,12076539529269170,12076539529400690,12076539529404191
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,932047,932054,4194304,256,0,0,28,24,37312,0x7f4423ebaa00,0x7f4318235900,393501,393501,27294,3148016,65536,292135368,2959063,0,1170360636,12076539529461838,12076539529646769,12076539529899088,12076539529966156
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,932047,932054,4194304,256,0,0,28,24,38272,0x7f4423eba900,0x7f4318235940,395740,395740,29857,3165928,65536,318956410,2991481,0,1277643520,12076539529988839,12076539530193007,12076539530446286,12076539530514006
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,932047,932054,4194304,256,0,0,24,24,39232,0x7f4423eba800,0x7f4318235980,210892,210892,24694,1687144,65536,161933161,1514602,0,649554832,12076539530537108,12076539530742285,12076539530870925,12076539530874506
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,932047,932054,4194304,256,0,0,24,24,40192,0x7f4423eba700,0x7f43182359c0,218149,218149,25502,1745200,65536,167197763,1572574,0,670637260,12076539530932795,12076539531121004,12076539531255563,12076539531259282
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,932047,932054,4194304,256,0,0,24,24,41152,0x7f4423eba600,0x7f4318235a00,213669,213669,24950,1709360,65536,158758103,1534953,0,636856296,12076539531331696,12076539531503563,12076539531633642,12076539531637205
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,932047,932054,4194304,256,0,0,28,24,42624,0x7f4423eba500,0x7f4318235a40,387493,387493,27375,3099952,65536,288078618,2915784,0,1154135460,12076539531694331,12076539531880841,12076539532129960,12076539532199771
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,932047,932054,4194304,256,0,0,28,24,43584,0x7f4423eba400,0x7f4318235a80,388805,388805,28163,3110448,65536,257785117,2922396,0,1032958956,12076539532223926,12076539532421639,12076539532669799,12076539532736670
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,932047,932054,4194304,256,0,0,24,24,44544,0x7f4423eba300,0x7f4318235ac0,212876,212876,25302,1703016,65536,163427144,1518417,0,655547712,12076539532759983,12076539532952998,12076539533082117,12076539533085900
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,932047,932054,4194304,256,0,0,24,24,45760,0x7f4423ebaa00,0x7f4318235b00,214476,214476,25502,1715816,65536,162024480,1539520,0,649921084,12076539533145601,12076539533339236,12076539533470916,12076539533474523
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,932047,932054,4194304,256,0,0,24,24,46720,0x7f4423eba900,0x7f4318235b40,210084,210084,21001,1680680,65536,163816612,1516465,0,657097232,12076539533546456,12076539533717475,12076539533846275,12076539533849971
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,932047,932054,4194304,256,0,0,28,24,48448,0x7f4423eba800,0x7f4318235b80,409333,409333,33833,3274672,65536,309768922,3060020,0,1240895608,12076539533909772,12076539534100834,12076539534361633,12076539534429709
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,932047,932054,4194304,256,0,0,28,24,49408,0x7f4423eba700,0x7f4318235bc0,449285,449285,15102,3594288,65536,332564316,2962689,0,1332073724,12076539534453423,12076539534647712,12076539534936831,12076539535010980
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,932047,932054,4194304,256,0,0,24,24,50368,0x7f4423eba600,0x7f4318235c00,214037,214037,25667,1712304,65536,161217224,1538544,0,646712252,12076539535035356,12076539535231230,12076539535361469,12076539535365169
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,932047,932054,4194304,256,0,0,24,24,51584,0x7f4423eba500,0x7f4318235c40,215093,215093,25716,1720752,65536,158219899,1544277,0,634702480,12076539535425041,12076539535606269,12076539535739068,12076539535743002
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,932047,932054,4194304,256,0,0,24,24,52544,0x7f4423eba400,0x7f4318235c80,214317,214317,21854,1714544,65536,161781270,1545844,0,648942668,12076539535813954,12076539535983707,12076539536114907,12076539536118671
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,932047,932054,4194304,256,0,0,28,24,54272,0x7f4423eba300,0x7f4318235cc0,410324,410324,33047,3282600,65536,339523520,3107522,0,1359914564,12076539536169826,12076539536369466,12076539536633625,12076539536700433
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,932047,932054,4194304,256,0,0,28,24,55488,0x7f4423ebaa00,0x7f4318235d00,392629,392629,30177,3141040,65536,316266298,2969078,0,1266883720,12076539536724368,12076539536919704,12076539537171863,12076539537239776
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,932047,932054,4194304,256,0,0,24,24,56704,0x7f4423eba900,0x7f4318235d40,213741,213741,20559,1709936,65536,160614774,1544044,0,644290392,12076539537266155,12076539537460822,12076539537592502,12076539537596009
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,932047,932054,4194304,256,0,0,24,24,58176,0x7f4423eba800,0x7f4318235d80,224884,224884,27629,1799080,65536,178813063,1622518,0,717122716,12076539537654087,12076539537838741,12076539537977460,12076539537981045
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,932047,932054,4194304,256,0,0,24,24,59392,0x7f4423eba700,0x7f4318235dc0,212324,212324,24327,1698600,65536,159376433,1529213,0,639328396,12076539538051386,12076539538224340,12076539538355219,12076539538358728
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,932047,932054,4194304,256,0,0,28,24,61376,0x7f4423eba600,0x7f4318235e00,405484,405484,33823,3243880,65536,316935047,3073762,0,1269554680,12076539538417687,12076539538602098,12076539538863217,12076539538928908
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,932047,932054,4194304,256,0,0,28,24,62592,0x7f4423eba500,0x7f4318235e40,394789,394789,23300,3158320,65536,290527648,2973188,0,1163929528,12076539538951560,12076539539151697,12076539539405776,12076539539472740
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,932047,932054,4194304,256,0,0,24,24,63808,0x7f4423eba400,0x7f4318235e80,217668,217668,24042,1741352,65536,166154705,1572065,0,666468924,12076539539491395,12076539539698095,12076539539831374,12076539539834904
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,932047,932054,4194304,256,0,0,24,24,65280,0x7f4423eba300,0x7f4318235ec0,218605,218605,27048,1748848,65536,182181831,1583724,0,730568756,12076539539893232,12076539540086093,12076539540221613,12076539540225270
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,932047,932054,4194304,256,0,0,24,24,66496,0x7f4423ebaa00,0x7f4318235f00,213317,213317,25345,1706544,65536,157655889,1537173,0,632441556,12076539540299027,12076539540471692,12076539540602412,12076539540605988
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,932047,932054,4194304,256,0,0,28,24,68480,0x7f4423eba900,0x7f4318235f40,404109,404109,32279,3232880,65536,292745969,3056493,0,1172827892,12076539540655169,12076539540847371,12076539541108810,12076539541176629
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,932047,932054,4194304,256,0,0,28,24,69696,0x7f4423eba800,0x7f4318235f80,386989,386989,28700,3095920,65536,312968802,2923908,0,1253693336,12076539541200684,12076539541400649,12076539541648968,12076539541715602
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,932047,932054,4194304,256,0,0,24,24,70912,0x7f4423eba700,0x7f4318235fc0,210908,210908,24817,1687272,65536,161522256,1518926,0,647957384,12076539541738444,12076539541931527,12076539542061127,12076539542064902
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,932047,932054,4194304,256,0,0,24,24,72384,0x7f4423eba600,0x7f4318236000,225629,225629,28226,1805040,65536,184569635,1633291,0,740148196,12076539542115265,12076539542314886,12076539542453925,12076539542457562
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,932047,932054,4194304,256,0,0,24,24,73600,0x7f4423eba500,0x7f4318236040,212597,212597,25805,1700784,65536,161704193,1531454,0,648642700,12076539542528103,12076539542701604,12076539542831844,12076539542835565
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,932047,932054,4194304,256,0,0,28,24,75840,0x7f4423eba400,0x7f4318236080,405725,405725,37301,3245808,65536,317268621,3072402,0,1270891056,12076539542886590,12076539543086563,12076539543348322,12076539543414582
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,932047,932054,4194304,256,0,0,28,24,77056,0x7f4423eba300,0x7f43182360c0,402196,402196,29450,3217576,65536,277427634,3017926,0,1111527848,12076539543433878,12076539543631841,12076539543889280,12076539543956530
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,932047,932054,4194304,256,0,0,24,24,78272,0x7f4423ebaa00,0x7f4318236100,212149,212149,26028,1697200,65536,167169679,1521350,0,670528196,12076539543980795,12076539544182559,12076539544312159,12076539544316009
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,932047,932054,4194304,256,0,0,24,24,80000,0x7f4423eba900,0x7f4318236140,232541,232541,26099,1860336,65536,201096862,1689339,0,806253228,12076539544367785,12076539544565758,12076539544710238,12076539544713929
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,932047,932054,4194304,256,0,0,24,24,81216,0x7f4423eba800,0x7f4318236180,219516,219516,23605,1756136,65536,165799056,1582560,0,665053064,12076539544785632,12076539544956317,12076539545091036,12076539545095138
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,932047,932054,4194304,256,0,0,28,24,83456,0x7f4423eba700,0x7f43182361c0,414972,414972,30784,3319784,65536,319219982,3097550,0,1278700860,12076539545151022,12076539545344955,12076539545611355,12076539545678413
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,932047,932054,4194304,256,0,0,28,24,84928,0x7f4423eba600,0x7f4318236200,393308,393308,33782,3146472,65536,326389601,2963130,0,1307374880,12076539545703400,12076539545898074,12076539546150713,12076539546192159
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,932047,932054,4194304,256,0,0,24,24,86400,0x7f4423eba500,0x7f4318236240,210901,210901,26428,1687216,65536,159867269,1511839,0,641322452,12076539546229278,12076539546414392,12076539546543831,12076539546547520
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,932047,932054,4194304,256,0,0,24,24,88128,0x7f4423eba400,0x7f4318236280,240757,240757,28236,1926064,65536,211812374,1760878,0,849109668,12076539546605939,12076539546789111,12076539546939030,12076539546942585
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,932047,932054,4194304,256,0,0,24,24,89600,0x7f4423eba300,0x7f43182362c0,212141,212141,25544,1697136,65536,160031469,1523145,0,641969516,12076539547036279,12076539547208789,12076539547339509,12076539547343180
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,932047,932054,4194304,256,0,0,28,24,92096,0x7f4423ebaa00,0x7f4318236300,408236,408236,32430,3265896,65536,291600969,3023547,0,1168222160,12076539547402110,12076539547585428,12076539547848147,12076539547915525
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,932047,932054,4194304,256,0,0,28,24,93568,0x7f4423eba900,0x7f4318236340,391564,391564,31768,3132520,65536,329929306,2951494,0,1321549252,12076539547940451,12076539548139506,12076539548391665,12076539548460829
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,932047,932054,4194304,256,0,0,24,24,95040,0x7f4423eba800,0x7f4318236380,220932,220932,27239,1767464,65536,170692455,1596627,0,684601716,12076539548483731,12076539548682384,12076539548818224,12076539548821931
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,932047,932054,4194304,256,0,0,24,24,96768,0x7f4423eba700,0x7f43182363c0,252132,252132,28039,2017064,65536,219135315,1848924,0,878405476,12076539548879017,12076539549060463,12076539549218222,12076539549222115
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,932047,932054,4194304,256,0,0,24,24,98240,0x7f4423eba600,0x7f4318236400,217908,217908,26726,1743272,65536,161732542,1565425,0,648762004,12076539549293428,12076539549464781,12076539549598381,12076539549602122
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,932047,932054,4194304,256,0,0,28,24,100736,0x7f4423eba500,0x7f4318236440,410508,410508,35220,3284072,65536,324406985,3094544,0,1299446960,12076539549659258,12076539549841100,12076539550106059,12076539550176250
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,932047,932054,4194304,256,0,0,28,24,102208,0x7f4423eba400,0x7f4318236480,400476,400476,29633,3203816,65536,258771257,3009523,0,1036904296,12076539550200855,12076539550395178,12076539550652617,12076539550719741
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,932047,932054,4194304,256,0,0,24,24,103680,0x7f4423eba300,0x7f43182364c0,220597,220597,25705,1764784,65536,169493389,1591755,0,679862632,12076539550743385,12076539550936456,12076539551072616,12076539551076524
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,932047,932054,4194304,256,0,0,24,24,105664,0x7f4423ebaa00,0x7f4318236500,266717,266717,29492,2133744,65536,236403157,1963801,0,947460520,12076539551134903,12076539551330055,12076539551497095,12076539551500804
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,932047,932054,4194304,256,0,0,24,24,107136,0x7f4423eba900,0x7f4318236540,220516,220516,27298,1764136,65536,165012275,1586662,0,661875912,12076539551570724,12076539551742214,12076539551878373,12076539551882003
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,932047,932054,4194304,256,0,0,28,24,109888,0x7f4423eba800,0x7f4318236580,404381,404381,38320,3235056,65536,315768659,3036582,0,1264902140,12076539551932647,12076539552131172,12076539552392131,12076539552443096
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,932047,932054,4194304,256,0,0,28,24,111360,0x7f4423eba700,0x7f43182365c0,397124,397124,26136,3177000,65536,259676647,2956125,0,1040523852,12076539552467832,12076539552660611,12076539552916290,12076539552938358
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,932047,932054,4194304,256,0,0,24,24,112832,0x7f4423eba600,0x7f4318236600,217381,217381,23631,1739056,65536,167844787,1568447,0,673256672,12076539552992238,12076539553167969,12076539553301568,12076539553305541
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,932047,932054,4194304,256,0,0,24,24,114816,0x7f4423eba500,0x7f4318236640,275765,275765,29612,2206128,65536,245890555,2042546,0,985409772,12076539553364370,12076539553548608,12076539553722687,12076539553726474
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,932047,932054,4194304,256,0,0,24,24,116288,0x7f4423eba400,0x7f4318236680,219277,219277,24997,1754224,65536,172741132,1583926,0,692837616,12076539553796905,12076539553970366,12076539554105566,12076539554109326
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,932047,932054,4194304,256,0,0,28,24,119040,0x7f4423eba300,0x7f43182366c0,397924,397924,38664,3183400,65536,335150662,2995908,0,1342474532,12076539554166292,12076539554359645,12076539554617084,12076539554665741
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,932047,932054,4194304,256,0,0,28,24,120768,0x7f4423ebaa00,0x7f4318236700,451429,451429,19078,3611440,65536,265901707,2923095,0,1065425080,12076539554688834,12076539554884123,12076539555174202,12076539555223699
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,932047,932054,4194304,256,0,0,24,24,122496,0x7f4423eba900,0x7f4318236740,222077,222077,27234,1776624,65536,169508774,1599073,0,679907308,12076539555248014,12076539555445561,12076539555581881,12076539555585642
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,932047,932054,4194304,256,0,0,24,24,124736,0x7f4423eba800,0x7f4318236780,289532,289532,30316,2316264,65536,258844184,2153967,0,1037246008,12076539555645313,12076539555828760,12076539556012119,12076539556016073
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,932047,932054,4194304,256,0,0,24,24,126464,0x7f4423eba700,0x7f43182367c0,218221,218221,22984,1745776,65536,165781438,1559706,0,664998292,12076539556101341,12076539556276438,12076539556408918,12076539556412790
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,932047,932054,4194304,256,0,0,20,24,127936,0x7f4423eba600,0x7f4318236800,408589,408589,35900,3268720,65536,377033478,3099857,0,1509953888,12076539556473523,12076539556654677,12076539556919636,12076539556968063
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,932047,932054,4194304,256,0,0,28,24,129664,0x7f4423eba500,0x7f4318236840,389164,389164,34775,3113320,65536,315336088,2919102,0,1263165704,12076539556989643,12076539557196915,12076539557446994,12076539557496837
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,932047,932054,4194304,256,0,0,24,24,131392,0x7f4423eba400,0x7f4318236880,214700,214700,20603,1717608,65536,166865449,1551116,0,669317244,12076539557530940,12076539557722353,12076539557854993,12076539557858880
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,932047,932054,4194304,256,0,0,24,24,133632,0x7f4423eba300,0x7f43182368c0,302381,302381,32196,2419056,65536,272099268,2251294,0,1090241708,12076539557916808,12076539558107792,12076539558299311,12076539558348942
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,932047,932054,4194304,256,0,0,24,24,135360,0x7f4423ebaa00,0x7f4318236900,221972,221972,25312,1775784,65536,171171967,1604347,0,686563316,12076539558387053,12076539558563630,12076539558700910,12076539558704623
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,932047,932054,4194304,256,0,0,20,24,136832,0x7f4423eba900,0x7f4318236940,436981,436981,41608,3495856,65536,403803421,3313333,0,1617035172,12076539558762150,12076539558948909,12076539559232588,12076539559281286
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,932047,932054,4194304,256,0,0,28,24,138560,0x7f4423eba800,0x7f4318236980,387732,387732,33051,3101864,65536,336168336,2924330,0,1346515816,12076539559305892,12076539559499787,12076539559750506,12076539559799290
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,932047,932054,4194304,256,0,0,24,24,140288,0x7f4423eba700,0x7f43182369c0,227357,227357,27174,1818864,65536,173238101,1633646,0,694839224,12076539559817203,12076539560014986,12076539560154825,12076539560159139
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,932047,932054,4194304,256,0,0,24,24,142784,0x7f4423eba600,0x7f4318236a00,330132,330132,33365,2641064,65536,297166738,2474091,0,1190521024,12076539560215955,12076539560411304,12076539560621863,12076539560644171
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,932047,932054,4194304,256,0,0,24,24,144768,0x7f4423eba500,0x7f4318236a40,213357,213357,26864,1706864,65536,163963370,1537735,0,657724816,12076539560710896,12076539560883463,12076539561015142,12076539561019059
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,932047,932054,4194304,256,0,0,20,24,145728,0x7f4423eba400,0x7f4318236a80,472652,472652,42088,3781224,65536,435175208,3605903,0,1742521028,12076539561068801,12076539561260741,12076539561569380,12076539561591313
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,932047,932054,4194304,256,0,0,28,24,147712,0x7f4423eba300,0x7f4318236ac0,391572,391572,31869,3132584,65536,312644928,2938508,0,1252403528,12076539561643220,12076539561811139,12076539562063779,12076539562086093
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,932047,932054,4194304,256,0,0,24,24,149696,0x7f4423ebaa00,0x7f4318236b00,213901,213901,25989,1711216,65536,163129910,1538185,0,654384080,12076539562138731,12076539562310978,12076539562442977,12076539562446905
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,932047,932054,4194304,256,0,0,24,24,152192,0x7f4423eba900,0x7f4318236b40,358245,358245,36987,2865968,65536,326658037,2689677,0,1308478340,12076539562504502,12076539562690656,12076539562918976,12076539562939872
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,932047,932054,4194304,256,0,0,24,24,154176,0x7f4423eba800,0x7f4318236b80,217597,217597,27104,1740784,65536,171228040,1572096,0,686808540,12076539563009271,12076539563184751,12076539563319471,12076539563326871
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,932047,932054,4194304,256,0,0,20,24,155648,0x7f4423eba700,0x7f4318236bc0,506516,506516,44667,4052136,65536,472333292,3881050,0,1891153688,12076539563374320,12076539563594829,12076539563925388,12076539563945552
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,932047,932054,4194304,256,0,0,28,24,157632,0x7f4423eba600,0x7f4318236c00,394044,394044,34711,3152360,65536,338460257,2965566,0,1355667104,12076539564004963,12076539564177387,12076539564432107,12076539564482531
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,932047,932054,4194304,256,0,0,24,24,159616,0x7f4423eba500,0x7f4318236c40,218148,218148,27459,1745192,65536,161402768,1567003,0,647476664,12076539564507167,12076539564704106,12076539564838666,12076539564841719
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,932047,932054,4194304,256,0,0,24,24,162368,0x7f4423eba400,0x7f4318236c80,382685,382685,37057,3061488,65536,352418579,2893804,0,1411522080,12076539564899647,12076539565090345,12076539565335464,12076539565385200
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,932047,932054,4194304,256,0,0,24,24,164608,0x7f4423eba300,0x7f4318236cc0,222684,222684,28213,1781480,65536,174659076,1610928,0,700515228,12076539565419614,12076539565624744,12076539565762343,12076539565765327
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,932047,932054,4194304,256,0,0,20,24,166336,0x7f4423ebaa00,0x7f4318236d00,575277,575277,49017,4602224,65536,542085357,4423425,0,2170161148,12076539565822624,12076539566006663,12076539566383142,12076539566438009
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,932047,932054,4194304,256,0,0,28,24,168576,0x7f4423eba900,0x7f4318236d40,411333,411333,32773,3290672,65536,294082965,3109407,0,1178149968,12076539566462494,12076539566681861,12076539566948100,12076539566995155
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,932047,932054,4194304,256,0,0,24,24,170816,0x7f4423eba800,0x7f4318236d80,220189,220189,27563,1761520,65536,180631894,1591688,0,724389492,12076539567017396,12076539567219779,12076539567356579,12076539567359663
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,932047,932054,4194304,256,0,0,24,24,174080,0x7f4423eba700,0x7f4318236dc0,434277,434277,40134,3474224,65536,400605027,3308028,0,1604265284,12076539567418563,12076539567603778,12076539567883458,12076539567931457
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,932047,932054,4194304,256,0,0,24,24,176576,0x7f4423eba600,0x7f4318236e00,221860,221860,26317,1774888,65536,183990518,1582528,0,737848128,12076539567966682,12076539568154497,12076539568290657,12076539568293951
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,932047,932054,4194304,256,0,0,20,24,177792,0x7f4423eba500,0x7f4318236e40,681069,681069,15834,5448560,65536,613770776,5015320,0,2456901536,12076539568355185,12076539568539936,12076539568988895,12076539569036933
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,932047,932054,4194304,256,0,0,28,24,180288,0x7f4423eba400,0x7f4318236e80,406237,406237,38275,3249904,65536,337896445,3059312,0,1353414276,12076539569061068,12076539569257854,12076539569520734,12076539569567560
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,932047,932054,4194304,256,0,0,24,24,182784,0x7f4423eba300,0x7f4318236ec0,221404,221404,25492,1771240,65536,187699303,1605385,0,752685080,12076539569590152,12076539569784413,12076539569922173,12076539569925175
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,932047,932054,4194304,256,0,0,24,24,186304,0x7f4423ebaa00,0x7f4318236f00,488172,488172,43321,3905384,65536,456128425,3738992,0,1826365740,12076539569983995,12076539570178812,12076539570494491,12076539570543575
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,932047,932054,4194304,256,0,0,24,24,189312,0x7f4423eba900,0x7f4318236f40,242548,242548,26894,1940392,65536,215380939,1778368,0,863419016,12076539570578210,12076539570761850,12076539570914330,12076539570917401
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,932047,932054,4194304,256,0,0,20,24,190784,0x7f4423eba800,0x7f4318236f80,785316,785316,60413,6282536,65536,750386555,6116830,0,3003366548,12076539570975639,12076539571166329,12076539571685208,12076539571735092
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,932047,932054,4194304,256,0,0,28,24,193792,0x7f4423eba700,0x7f4318236fc0,462404,462404,41294,3699240,65536,389065757,3519488,0,1558101460,12076539571759537,12076539571953047,12076539572255927,12076539572305873
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,932047,932054,4194304,256,0,0,24,24,196800,0x7f4423eba600,0x7f4318237000,246205,246205,27832,1969648,65536,217456841,1805195,0,871712088,12076539572330299,12076539572526006,12076539572680085,12076539572683225
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,932047,932054,4194304,256,0,0,24,24,201088,0x7f4423eba500,0x7f4318237040,592757,592757,47125,4742064,65536,560846135,4582835,0,2245236168,12076539572743437,12076539572924405,12076539573310804,12076539573360074
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,932047,932054,4194304,256,0,0,24,24,204608,0x7f4423eba400,0x7f4318237080,279484,279484,30869,2235880,65536,250652439,2064728,0,1004506820,12076539573394529,12076539573578803,12076539573755123,12076539573758245
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,932047,932054,4194304,256,0,0,20,24,206080,0x7f4423eba300,0x7f43182370c0,925917,925917,69064,7407344,65536,888877037,7236333,0,3557328232,12076539573814099,12076539574003442,12076539574617360,12076539574667527
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,932047,932054,4194304,256,0,0,28,24,209600,0x7f4423ebaa00,0x7f4318237100,502348,502348,44590,4018792,65536,439118559,3825833,0,1758313140,12076539574691411,12076539574889200,12076539575217519,12076539575267342
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,932047,932054,4194304,256,0,0,24,24,213120,0x7f4423eba900,0x7f4318237140,282684,282684,28726,2261480,65536,252689238,2099931,0,1012641916,12076539575291597,12076539575486478,12076539575666158,12076539575669320
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,932047,932054,4194304,256,0,0,24,24,218176,0x7f4423eba800,0x7f4318237180,699004,699004,55608,5592040,65536,664823353,5420629,0,2661141680,12076539575728059,12076539575911117,12076539576367436,12076539576418283
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,932047,932054,4194304,256,0,0,24,24,222208,0x7f4423eba700,0x7f43182371c0,313445,313445,31630,2507568,65536,282905871,2340290,0,1133508000,12076539576455062,12076539576633835,12076539576834315,12076539576883679
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,932047,932054,4194304,256,0,0,20,24,223936,0x7f4423eba600,0x7f4318237200,1067005,1067005,77826,8536048,65536,1028681435,8360329,0,4116546560,12076539576907864,12076539577105034,12076539577811112,12076539577880232
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,932047,932054,4194304,256,0,0,28,24,227968,0x7f4423eba500,0x7f4318237240,567516,567516,47066,4540136,65536,533040219,4369038,0,2134004644,12076539577903656,12076539578103591,12076539578476871,12076539578544288
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,932047,932054,4194304,256,0,0,24,24,232000,0x7f4423eba400,0x7f4318237280,318932,318932,33166,2551464,65536,289021482,2378929,0,1157974008,12076539578567581,12076539578762630,12076539578965509,12076539579033618
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,932047,932054,4194304,256,0,0,24,24,237824,0x7f4423eba300,0x7f43182372c0,803653,803653,60431,6429232,65536,770151333,6265288,0,3082454928,12076539579062081,12076539579256069,12076539579783427,12076539579850538
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,932047,932054,4194304,256,0,0,24,24,242368,0x7f4423ebaa00,0x7f4318237300,349972,349972,35373,2799784,65536,319600579,2626228,0,1280294176,12076539579885503,12076539580069506,12076539580293186,12076539580362299
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,932047,932054,4194304,256,0,0,20,24,243584,0x7f4423eba900,0x7f4318237340,1209261,1209261,86183,9674096,65536,1168697018,9490305,0,4676608676,12076539580385312,12076539580581025,12076539581381983,12076539581449672
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,932047,932054,4194304,256,0,0,28,24,248128,0x7f4423eba800,0x7f4318237380,640132,640132,53668,5121064,65536,599660316,4940574,0,2400485004,12076539581479718,12076539581674782,12076539582097341,12076539582165464
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,932047,932054,4194304,256,0,0,24,24,252672,0x7f4423eba700,0x7f43182373c0,353644,353644,35173,2829160,65536,322966437,2656731,0,1293749792,12076539582196702,12076539582390140,12076539582616860,12076539582683527
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,932047,932054,4194304,256,0,0,24,24,259264,0x7f4423eba600,0x7f4318237400,913252,913252,68136,7306024,65536,874047575,7108852,0,3498042204,12076539582706029,12076539582904859,12076539583502618,12076539583572010
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,932047,932054,4194304,256,0,0,24,24,264832,0x7f4423eba500,0x7f4318237440,465477,465477,15623,3723824,65536,385617966,3174831,0,1544356816,12076539583607025,12076539583792857,12076539584094456,12076539584164873
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,932047,932054,4194304,256,0,0,20,24,266304,0x7f4423eba400,0x7f4318237480,1489852,1489852,102328,11918824,65536,1447143697,11738272,0,5790395304,12076539584187906,12076539584384375,12076539585372853,12076539585441117
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,932047,932054,4194304,256,0,0,28,24,271872,0x7f4423eba300,0x7f43182374c0,776861,776861,59692,6214896,65536,741678364,6048016,0,2968545520,12076539585470481,12076539585667252,12076539586182131,12076539586250302
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,932047,932054,4194304,256,0,0,24,24,277440,0x7f4423ebaa00,0x7f4318237500,424052,424052,40753,3392424,65536,390940143,3216035,0,1565656504,12076539586281059,12076539586473970,12076539586747249,12076539586814421
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,932047,932054,4194304,256,0,0,12,24,279936,0x7f4423eba900,0x7f4318237540,1127588,1127588,79764,9020712,65536,1089666359,8846401,0,4360489876,12076539586837584,12076539587040369,12076539587780047,12076539587849266
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,932047,932054,4194304,256,0,0,24,24,286528,0x7f4423eba800,0x7f4318237580,491236,491236,44858,3929896,65536,456921999,3756820,0,1829591628,12076539587884682,12076539588075886,12076539588394445,12076539588463619
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,932047,932054,4194304,256,0,0,20,24,288000,0x7f4423eba700,0x7f43182375c0,1768581,1768581,117542,14148656,65536,1724447322,13979919,0,6899609844,12076539588480260,12076539588686124,12076539589862441,12076539589930097
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,932047,932054,4194304,256,0,0,32,24,294592,0x7f4423eba600,0x7f4318237600,921053,921053,66297,7368432,65536,804876492,7196129,0,3221370360,12076539589960724,12076539590164040,12076539590776999,12076539590846932
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,932047,932054,4194304,256,0,0,24,24,301184,0x7f4423eba500,0x7f4318237640,492644,492644,42992,3941160,65536,461031505,3771720,0,1846012960,12076539590876347,12076539591075558,12076539591395397,12076539591462808
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,932047,932054,4194304,256,0,0,12,24,304960,0x7f4423eba400,0x7f4318237680,1337396,1337396,92333,10699176,65536,1299277386,10528946,0,5198938588,12076539591485901,12076539591683877,12076539592563714,12076539592632033
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,932047,932054,4194304,256,0,0,24,24,313600,0x7f4423eba300,0x7f43182376c0,633333,633333,54072,5066672,65536,596476135,4888805,0,2387800312,12076539592676495,12076539592851394,12076539593264353,12076539593334429
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,932047,932054,4194304,256,0,0,20,24,314816,0x7f4423ebaa00,0x7f4318237700,2333356,2333356,79878,18666856,65536,2284896529,18494385,0,9141407988,12076539593365377,12076539593559872,12076539595112668,12076539595180623
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,932047,932054,4194304,256,0,0,20,24,317568,0x7f4423eba900,0x7f4318237740,1201356,1201356,84410,9610856,65536,1163784346,9436414,0,4656960640,12076539595208676,12076539595416667,12076539596213945,12076539596281711
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,932047,932054,4194304,256,0,0,12,24,320320,0x7f4423eba800,0x7f4318237780,640204,640204,49910,5121640,65536,609787230,4957036,0,2440985580,12076539596312980,12076539596508024,12076539596923863,12076539596991732
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,932047,932054,4194304,256,0,0,12,24,324096,0x7f4423eba700,0x7f43182377c0,1758908,1758908,118155,14071272,65536,1714603939,13898946,0,6860241008,12076539597015316,12076539597221622,12076539598381619,12076539598451678
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,932047,932054,4194304,256,0,0,12,24,328896,0x7f4423eba600,0x7f4318237800,1198893,1198893,83313,9591152,65536,1162202950,9418965,0,4650639276,12076539598497092,12076539598670739,12076539599457617,12076539599525425
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,932047,932054,4194304,256,0,0,20,24,330112,0x7f4423eba500,0x7f4318237840,4584605,4584605,282315,36676848,65536,4514668689,36504958,0,18060495812,12076539599556202,12076539599751536,12076539602807688,12076539602875888
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,932047,932054,4194304,256,0,0,20,24,332864,0x7f4423eba400,0x7f4318237880,2323717,2323717,149516,18589744,65536,2276271710,18426457,0,9106912448,12076539602907176,12076539603104647,12076539604650083,12076539604718685
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,932047,932054,4194304,256,0,0,12,24,335616,0x7f4423eba300,0x7f43182378c0,1203644,1203644,84669,9629160,65536,1165498254,9459635,0,4663816016,12076539604744233,12076539604944162,12076539605734400,12076539605803483
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,932047,932054,4194304,256,0,0,12,24,339392,0x7f4423ebaa00,0x7f4318237900,3442909,3442909,215169,27543280,65536,3384776709,27373869,0,13540931208,12076539605831495,12076539606036160,12076539608318234,12076539608386899
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,932047,932054,4194304,256,0,0,12,24,344192,0x7f4423eba900,0x7f4318237940,2326380,2326380,152550,18611048,65536,2276299888,18421771,0,9107028724,12076539608431972,12076539608608793,12076539610145269,12076539610213496
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,932047,932054,4194304,256,0,0,20,24,345408,0x7f4423eba800,0x7f4318237980,9087740,9087740,473479,72701928,65536,8978154106,72527985,0,35914436988,12076539610248151,12076539610438708,12076539616501253,12076539616571974
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,932047,932054,4194304,256,0,0,20,24,348160,0x7f4423eba700,0x7f43182379c0,4574484,4574484,283331,36595880,65536,4501040258,36416888,0,18005984112,12076539616598613,12076539616799652,12076539619846204,12076539619916605
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,932047,932054,4194304,256,0,0,12,24,350912,0x7f4423eba600,0x7f4318237a00,2330213,2330213,150793,18641712,65536,2281449272,18463936,0,9127621428,12076539619943846,12076539620150203,12076539621690679,12076539621760165
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,932047,932054,4194304,256,0,0,12,24,0,0x7f4423eba500,0x7f4318237a40,6816229,6816229,412766,54529840,65536,6723941280,54336435,0,26897589764,12076539621793717,12076539621986528,12076539626515797,12076539626589217
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid grd Workgroup_Size LDS_Per_Workgroup scr vgpr SGPR fbar sig obj GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 __amd_rocclr_fillBuffer.kd 0 0 0 932047 932054 33554432 256 0 0 8 32 6464 0x0 0x7f4318204180 502027 502027 17663 4016224 524288 373010853 3812072 0 1506849280 12076539256161927 12076539500209550 12076539500532269 12076539500642792
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 932047 932054 32768 256 0 0 24 24 12480 0x0 0x7f4318235100 28337 28337 21039 226704 512 1125690 76367 0 4517036 12076539515082191 12076539515408737 12076539515415137 12076539515423846
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 4 932047 932054 4194304 256 0 0 24 24 12928 0x7f4423eba900 0x7f4318235140 214085 214085 21876 1712688 65536 145056154 1546601 0 582037424 12076539515493015 12076539515729376 12076539515859296 12076539515863073
5 3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 6 932047 932054 4194304 256 0 0 36 24 13632 0x7f4423eba800 0x7f4318235180 384636 384636 29429 3077096 65536 257748821 2910007 0 1032814660 12076539515940978 12076539516139775 12076539516384574 12076539516454523
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 8 932047 932054 4194304 256 0 0 28 24 14080 0x7f4423eba700 0x7f43182351c0 402492 402492 29357 3219944 65536 279692821 3037066 0 1120588996 12076539516489238 12076539516696253 12076539516951772 12076539517020887
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 10 932047 932054 4194304 256 0 0 24 24 14528 0x7f4423eba600 0x7f4318235200 212317 212317 22764 1698544 65536 155474951 1531408 0 623720392 12076539517046294 12076539517254331 12076539517383931 12076539517387499
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 12 932047 932054 4194304 256 0 0 24 24 14976 0x7f4423eba500 0x7f4318235240 211901 211901 22389 1695216 65536 142732486 1522500 0 572750716 12076539517445937 12076539517643130 12076539517771769 12076539517775330
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 14 932047 932054 4194304 256 0 0 24 24 15424 0x7f4423eba400 0x7f4318235280 215869 215869 19266 1726960 65536 159152180 1562834 0 638425092 12076539517864656 12076539518050328 12076539518182328 12076539518185914
10 8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 16 932047 932054 4194304 256 0 0 28 24 16128 0x7f4423eba300 0x7f43182352c0 392132 392132 32200 3137064 65536 337425059 2961038 0 1351517408 12076539518245044 12076539518450007 12076539518699126 12076539518741016
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 18 932047 932054 4194304 256 0 0 28 24 16832 0x7f4423ebaa00 0x7f4318235300 397317 397317 28490 3178544 65536 314230850 3009046 0 1258740612 12076539518777825 12076539518966805 12076539519220404 12076539519289907
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 20 932047 932054 4194304 256 0 0 24 24 17536 0x7f4423eba900 0x7f4318235340 208428 208428 23475 1667432 65536 168392411 1499567 0 675389732 12076539519317439 12076539519521523 12076539519648243 12076539519651680
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 22 932047 932054 4194304 256 0 0 24 24 18240 0x7f4423eba800 0x7f4318235380 218181 218181 22368 1745456 65536 148176463 1578162 0 594517888 12076539519709708 12076539519900562 12076539520034162 12076539520037909
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 24 932047 932054 4194304 256 0 0 24 24 18944 0x7f4423eba700 0x7f43182353c0 211493 211493 23293 1691952 65536 159187710 1520072 0 638568648 12076539520111125 12076539520295281 12076539520423920 12076539520427443
15 13 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 26 932047 932054 4194304 256 0 0 28 24 19904 0x7f4423eba600 0x7f4318235400 392900 392900 22533 3143208 65536 323568499 2957821 0 1296089812 12076539520488988 12076539520679279 12076539520930638 12076539520997003
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 28 932047 932054 4194304 256 0 0 28 24 20608 0x7f4423eba500 0x7f4318235440 388044 388044 27421 3104360 65536 315968977 2925187 0 1265693716 12076539521029143 12076539521233997 12076539521480877 12076539521549430
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 30 932047 932054 4194304 256 0 0 24 24 21312 0x7f4423eba400 0x7f4318235480 212861 212861 25994 1702896 65536 160543700 1517346 0 643992048 12076539521571471 12076539521771916 12076539521900715 12076539521904220
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 32 932047 932054 4194304 256 0 0 24 24 22016 0x7f4423eba300 0x7f43182354c0 215373 215373 21749 1722992 65536 152440532 1553500 0 611571948 12076539521955896 12076539522157834 12076539522289674 12076539522293064
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 34 932047 932054 4194304 256 0 0 24 24 22720 0x7f4423ebaa00 0x7f4318235500 208701 208701 17514 1669616 65536 165297552 1495890 0 663012708 12076539522363775 12076539522541833 12076539522669193 12076539522672720
20 18 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 36 932047 932054 4194304 256 0 0 28 24 23680 0x7f4423eba900 0x7f4318235540 399460 399460 33571 3195688 65536 364799220 3028168 0 1461014924 12076539522730978 12076539522919912 12076539523175591 12076539523242860
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 38 932047 932054 4194304 256 0 0 28 24 24384 0x7f4423eba800 0x7f4318235580 397604 397604 29669 3180840 65536 328803190 2990824 0 1317029904 12076539523267366 12076539523465670 12076539523718309 12076539523785009
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 40 932047 932054 4194304 256 0 0 24 24 25088 0x7f4423eba700 0x7f43182355c0 210581 210581 23874 1684656 65536 161468109 1515980 0 647690564 12076539523809915 12076539524007748 12076539524136228 12076539524139869
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 42 932047 932054 4194304 256 0 0 24 24 25792 0x7f4423eba600 0x7f4318235600 218085 218085 23334 1744688 65536 160499877 1576869 0 643821736 12076539524202566 12076539524399107 12076539524532706 12076539524536006
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 44 932047 932054 4194304 256 0 0 24 24 26496 0x7f4423eba500 0x7f4318235640 209717 209717 22643 1677744 65536 159537471 1511311 0 639967800 12076539524607639 12076539524781825 12076539524909345 12076539524912676
25 23 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 46 932047 932054 4194304 256 0 0 28 24 27712 0x7f4423eba400 0x7f4318235680 389613 389613 33391 3116912 65536 315783764 2960375 0 1264951208 12076539524969692 12076539525170144 12076539525420223 12076539525488207
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 48 932047 932054 4194304 256 0 0 28 24 28416 0x7f4423eba300 0x7f43182356c0 394892 394892 30346 3159144 65536 335876840 2992166 0 1345325376 12076539525512733 12076539525711262 12076539525963741 12076539526030456
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 50 932047 932054 4194304 256 0 0 24 24 29120 0x7f4423ebaa00 0x7f4318235700 209245 209245 20208 1673968 65536 164075248 1511213 0 658119196 12076539526053679 12076539526253820 12076539526381820 12076539526385386
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 52 932047 932054 4194304 256 0 0 24 24 30080 0x7f4423eba900 0x7f4318235740 218381 218381 26547 1747056 65536 161860757 1576635 0 649255836 12076539526445337 12076539526628859 12076539526762779 12076539526766174
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 54 932047 932054 4194304 256 0 0 24 24 30784 0x7f4423eba800 0x7f4318235780 210437 210437 22470 1683504 65536 160228275 1521869 0 642750380 12076539526836936 12076539527008378 12076539527137497 12076539527140951
30 28 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 56 932047 932054 4194304 256 0 0 28 24 32000 0x7f4423eba700 0x7f43182357c0 449005 449005 15250 3592048 65536 298339799 2970249 0 1195174808 12076539527196735 12076539527397656 12076539527686456 12076539527752980
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 58 932047 932054 4194304 256 0 0 28 24 32960 0x7f4423eba600 0x7f4318235800 396132 396132 28667 3169064 65536 300122611 2992825 0 1202309044 12076539527775251 12076539527971575 12076539528223894 12076539528293094
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 60 932047 932054 4194304 256 0 0 24 24 33920 0x7f4423eba500 0x7f4318235840 208044 208044 22029 1664360 65536 165662590 1501017 0 664472032 12076539528317059 12076539528514453 12076539528642132 12076539528645540
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 62 932047 932054 4194304 256 0 0 24 24 34880 0x7f4423eba400 0x7f4318235880 213420 213420 25970 1707368 65536 158450111 1535263 0 635627332 12076539528704590 12076539528890771 12076539529021331 12076539529024856
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 64 932047 932054 4194304 256 0 0 24 24 35840 0x7f4423eba300 0x7f43182358c0 214341 214341 22778 1714736 65536 158503640 1555723 0 635840568 12076539529095136 12076539529269170 12076539529400690 12076539529404191
35 33 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 66 932047 932054 4194304 256 0 0 28 24 37312 0x7f4423ebaa00 0x7f4318235900 393501 393501 27294 3148016 65536 292135368 2959063 0 1170360636 12076539529461838 12076539529646769 12076539529899088 12076539529966156
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 68 932047 932054 4194304 256 0 0 28 24 38272 0x7f4423eba900 0x7f4318235940 395740 395740 29857 3165928 65536 318956410 2991481 0 1277643520 12076539529988839 12076539530193007 12076539530446286 12076539530514006
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 70 932047 932054 4194304 256 0 0 24 24 39232 0x7f4423eba800 0x7f4318235980 210892 210892 24694 1687144 65536 161933161 1514602 0 649554832 12076539530537108 12076539530742285 12076539530870925 12076539530874506
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 72 932047 932054 4194304 256 0 0 24 24 40192 0x7f4423eba700 0x7f43182359c0 218149 218149 25502 1745200 65536 167197763 1572574 0 670637260 12076539530932795 12076539531121004 12076539531255563 12076539531259282
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 74 932047 932054 4194304 256 0 0 24 24 41152 0x7f4423eba600 0x7f4318235a00 213669 213669 24950 1709360 65536 158758103 1534953 0 636856296 12076539531331696 12076539531503563 12076539531633642 12076539531637205
40 38 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 76 932047 932054 4194304 256 0 0 28 24 42624 0x7f4423eba500 0x7f4318235a40 387493 387493 27375 3099952 65536 288078618 2915784 0 1154135460 12076539531694331 12076539531880841 12076539532129960 12076539532199771
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 78 932047 932054 4194304 256 0 0 28 24 43584 0x7f4423eba400 0x7f4318235a80 388805 388805 28163 3110448 65536 257785117 2922396 0 1032958956 12076539532223926 12076539532421639 12076539532669799 12076539532736670
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 80 932047 932054 4194304 256 0 0 24 24 44544 0x7f4423eba300 0x7f4318235ac0 212876 212876 25302 1703016 65536 163427144 1518417 0 655547712 12076539532759983 12076539532952998 12076539533082117 12076539533085900
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 82 932047 932054 4194304 256 0 0 24 24 45760 0x7f4423ebaa00 0x7f4318235b00 214476 214476 25502 1715816 65536 162024480 1539520 0 649921084 12076539533145601 12076539533339236 12076539533470916 12076539533474523
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 84 932047 932054 4194304 256 0 0 24 24 46720 0x7f4423eba900 0x7f4318235b40 210084 210084 21001 1680680 65536 163816612 1516465 0 657097232 12076539533546456 12076539533717475 12076539533846275 12076539533849971
45 43 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 86 932047 932054 4194304 256 0 0 28 24 48448 0x7f4423eba800 0x7f4318235b80 409333 409333 33833 3274672 65536 309768922 3060020 0 1240895608 12076539533909772 12076539534100834 12076539534361633 12076539534429709
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 88 932047 932054 4194304 256 0 0 28 24 49408 0x7f4423eba700 0x7f4318235bc0 449285 449285 15102 3594288 65536 332564316 2962689 0 1332073724 12076539534453423 12076539534647712 12076539534936831 12076539535010980
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 90 932047 932054 4194304 256 0 0 24 24 50368 0x7f4423eba600 0x7f4318235c00 214037 214037 25667 1712304 65536 161217224 1538544 0 646712252 12076539535035356 12076539535231230 12076539535361469 12076539535365169
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 92 932047 932054 4194304 256 0 0 24 24 51584 0x7f4423eba500 0x7f4318235c40 215093 215093 25716 1720752 65536 158219899 1544277 0 634702480 12076539535425041 12076539535606269 12076539535739068 12076539535743002
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 94 932047 932054 4194304 256 0 0 24 24 52544 0x7f4423eba400 0x7f4318235c80 214317 214317 21854 1714544 65536 161781270 1545844 0 648942668 12076539535813954 12076539535983707 12076539536114907 12076539536118671
50 48 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 96 932047 932054 4194304 256 0 0 28 24 54272 0x7f4423eba300 0x7f4318235cc0 410324 410324 33047 3282600 65536 339523520 3107522 0 1359914564 12076539536169826 12076539536369466 12076539536633625 12076539536700433
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 98 932047 932054 4194304 256 0 0 28 24 55488 0x7f4423ebaa00 0x7f4318235d00 392629 392629 30177 3141040 65536 316266298 2969078 0 1266883720 12076539536724368 12076539536919704 12076539537171863 12076539537239776
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 100 932047 932054 4194304 256 0 0 24 24 56704 0x7f4423eba900 0x7f4318235d40 213741 213741 20559 1709936 65536 160614774 1544044 0 644290392 12076539537266155 12076539537460822 12076539537592502 12076539537596009
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 102 932047 932054 4194304 256 0 0 24 24 58176 0x7f4423eba800 0x7f4318235d80 224884 224884 27629 1799080 65536 178813063 1622518 0 717122716 12076539537654087 12076539537838741 12076539537977460 12076539537981045
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 104 932047 932054 4194304 256 0 0 24 24 59392 0x7f4423eba700 0x7f4318235dc0 212324 212324 24327 1698600 65536 159376433 1529213 0 639328396 12076539538051386 12076539538224340 12076539538355219 12076539538358728
55 53 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 106 932047 932054 4194304 256 0 0 28 24 61376 0x7f4423eba600 0x7f4318235e00 405484 405484 33823 3243880 65536 316935047 3073762 0 1269554680 12076539538417687 12076539538602098 12076539538863217 12076539538928908
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 108 932047 932054 4194304 256 0 0 28 24 62592 0x7f4423eba500 0x7f4318235e40 394789 394789 23300 3158320 65536 290527648 2973188 0 1163929528 12076539538951560 12076539539151697 12076539539405776 12076539539472740
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 110 932047 932054 4194304 256 0 0 24 24 63808 0x7f4423eba400 0x7f4318235e80 217668 217668 24042 1741352 65536 166154705 1572065 0 666468924 12076539539491395 12076539539698095 12076539539831374 12076539539834904
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 112 932047 932054 4194304 256 0 0 24 24 65280 0x7f4423eba300 0x7f4318235ec0 218605 218605 27048 1748848 65536 182181831 1583724 0 730568756 12076539539893232 12076539540086093 12076539540221613 12076539540225270
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 114 932047 932054 4194304 256 0 0 24 24 66496 0x7f4423ebaa00 0x7f4318235f00 213317 213317 25345 1706544 65536 157655889 1537173 0 632441556 12076539540299027 12076539540471692 12076539540602412 12076539540605988
60 58 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 116 932047 932054 4194304 256 0 0 28 24 68480 0x7f4423eba900 0x7f4318235f40 404109 404109 32279 3232880 65536 292745969 3056493 0 1172827892 12076539540655169 12076539540847371 12076539541108810 12076539541176629
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 118 932047 932054 4194304 256 0 0 28 24 69696 0x7f4423eba800 0x7f4318235f80 386989 386989 28700 3095920 65536 312968802 2923908 0 1253693336 12076539541200684 12076539541400649 12076539541648968 12076539541715602
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 120 932047 932054 4194304 256 0 0 24 24 70912 0x7f4423eba700 0x7f4318235fc0 210908 210908 24817 1687272 65536 161522256 1518926 0 647957384 12076539541738444 12076539541931527 12076539542061127 12076539542064902
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 122 932047 932054 4194304 256 0 0 24 24 72384 0x7f4423eba600 0x7f4318236000 225629 225629 28226 1805040 65536 184569635 1633291 0 740148196 12076539542115265 12076539542314886 12076539542453925 12076539542457562
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 124 932047 932054 4194304 256 0 0 24 24 73600 0x7f4423eba500 0x7f4318236040 212597 212597 25805 1700784 65536 161704193 1531454 0 648642700 12076539542528103 12076539542701604 12076539542831844 12076539542835565
65 63 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 126 932047 932054 4194304 256 0 0 28 24 75840 0x7f4423eba400 0x7f4318236080 405725 405725 37301 3245808 65536 317268621 3072402 0 1270891056 12076539542886590 12076539543086563 12076539543348322 12076539543414582
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 128 932047 932054 4194304 256 0 0 28 24 77056 0x7f4423eba300 0x7f43182360c0 402196 402196 29450 3217576 65536 277427634 3017926 0 1111527848 12076539543433878 12076539543631841 12076539543889280 12076539543956530
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 130 932047 932054 4194304 256 0 0 24 24 78272 0x7f4423ebaa00 0x7f4318236100 212149 212149 26028 1697200 65536 167169679 1521350 0 670528196 12076539543980795 12076539544182559 12076539544312159 12076539544316009
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 132 932047 932054 4194304 256 0 0 24 24 80000 0x7f4423eba900 0x7f4318236140 232541 232541 26099 1860336 65536 201096862 1689339 0 806253228 12076539544367785 12076539544565758 12076539544710238 12076539544713929
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 134 932047 932054 4194304 256 0 0 24 24 81216 0x7f4423eba800 0x7f4318236180 219516 219516 23605 1756136 65536 165799056 1582560 0 665053064 12076539544785632 12076539544956317 12076539545091036 12076539545095138
70 68 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 136 932047 932054 4194304 256 0 0 28 24 83456 0x7f4423eba700 0x7f43182361c0 414972 414972 30784 3319784 65536 319219982 3097550 0 1278700860 12076539545151022 12076539545344955 12076539545611355 12076539545678413
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 138 932047 932054 4194304 256 0 0 28 24 84928 0x7f4423eba600 0x7f4318236200 393308 393308 33782 3146472 65536 326389601 2963130 0 1307374880 12076539545703400 12076539545898074 12076539546150713 12076539546192159
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 140 932047 932054 4194304 256 0 0 24 24 86400 0x7f4423eba500 0x7f4318236240 210901 210901 26428 1687216 65536 159867269 1511839 0 641322452 12076539546229278 12076539546414392 12076539546543831 12076539546547520
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 142 932047 932054 4194304 256 0 0 24 24 88128 0x7f4423eba400 0x7f4318236280 240757 240757 28236 1926064 65536 211812374 1760878 0 849109668 12076539546605939 12076539546789111 12076539546939030 12076539546942585
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 144 932047 932054 4194304 256 0 0 24 24 89600 0x7f4423eba300 0x7f43182362c0 212141 212141 25544 1697136 65536 160031469 1523145 0 641969516 12076539547036279 12076539547208789 12076539547339509 12076539547343180
75 73 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 146 932047 932054 4194304 256 0 0 28 24 92096 0x7f4423ebaa00 0x7f4318236300 408236 408236 32430 3265896 65536 291600969 3023547 0 1168222160 12076539547402110 12076539547585428 12076539547848147 12076539547915525
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 148 932047 932054 4194304 256 0 0 28 24 93568 0x7f4423eba900 0x7f4318236340 391564 391564 31768 3132520 65536 329929306 2951494 0 1321549252 12076539547940451 12076539548139506 12076539548391665 12076539548460829
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 150 932047 932054 4194304 256 0 0 24 24 95040 0x7f4423eba800 0x7f4318236380 220932 220932 27239 1767464 65536 170692455 1596627 0 684601716 12076539548483731 12076539548682384 12076539548818224 12076539548821931
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 152 932047 932054 4194304 256 0 0 24 24 96768 0x7f4423eba700 0x7f43182363c0 252132 252132 28039 2017064 65536 219135315 1848924 0 878405476 12076539548879017 12076539549060463 12076539549218222 12076539549222115
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 154 932047 932054 4194304 256 0 0 24 24 98240 0x7f4423eba600 0x7f4318236400 217908 217908 26726 1743272 65536 161732542 1565425 0 648762004 12076539549293428 12076539549464781 12076539549598381 12076539549602122
80 78 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 156 932047 932054 4194304 256 0 0 28 24 100736 0x7f4423eba500 0x7f4318236440 410508 410508 35220 3284072 65536 324406985 3094544 0 1299446960 12076539549659258 12076539549841100 12076539550106059 12076539550176250
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 158 932047 932054 4194304 256 0 0 28 24 102208 0x7f4423eba400 0x7f4318236480 400476 400476 29633 3203816 65536 258771257 3009523 0 1036904296 12076539550200855 12076539550395178 12076539550652617 12076539550719741
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 160 932047 932054 4194304 256 0 0 24 24 103680 0x7f4423eba300 0x7f43182364c0 220597 220597 25705 1764784 65536 169493389 1591755 0 679862632 12076539550743385 12076539550936456 12076539551072616 12076539551076524
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 162 932047 932054 4194304 256 0 0 24 24 105664 0x7f4423ebaa00 0x7f4318236500 266717 266717 29492 2133744 65536 236403157 1963801 0 947460520 12076539551134903 12076539551330055 12076539551497095 12076539551500804
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 164 932047 932054 4194304 256 0 0 24 24 107136 0x7f4423eba900 0x7f4318236540 220516 220516 27298 1764136 65536 165012275 1586662 0 661875912 12076539551570724 12076539551742214 12076539551878373 12076539551882003
85 83 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 166 932047 932054 4194304 256 0 0 28 24 109888 0x7f4423eba800 0x7f4318236580 404381 404381 38320 3235056 65536 315768659 3036582 0 1264902140 12076539551932647 12076539552131172 12076539552392131 12076539552443096
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 168 932047 932054 4194304 256 0 0 28 24 111360 0x7f4423eba700 0x7f43182365c0 397124 397124 26136 3177000 65536 259676647 2956125 0 1040523852 12076539552467832 12076539552660611 12076539552916290 12076539552938358
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 170 932047 932054 4194304 256 0 0 24 24 112832 0x7f4423eba600 0x7f4318236600 217381 217381 23631 1739056 65536 167844787 1568447 0 673256672 12076539552992238 12076539553167969 12076539553301568 12076539553305541
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 172 932047 932054 4194304 256 0 0 24 24 114816 0x7f4423eba500 0x7f4318236640 275765 275765 29612 2206128 65536 245890555 2042546 0 985409772 12076539553364370 12076539553548608 12076539553722687 12076539553726474
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 174 932047 932054 4194304 256 0 0 24 24 116288 0x7f4423eba400 0x7f4318236680 219277 219277 24997 1754224 65536 172741132 1583926 0 692837616 12076539553796905 12076539553970366 12076539554105566 12076539554109326
90 88 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 176 932047 932054 4194304 256 0 0 28 24 119040 0x7f4423eba300 0x7f43182366c0 397924 397924 38664 3183400 65536 335150662 2995908 0 1342474532 12076539554166292 12076539554359645 12076539554617084 12076539554665741
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 178 932047 932054 4194304 256 0 0 28 24 120768 0x7f4423ebaa00 0x7f4318236700 451429 451429 19078 3611440 65536 265901707 2923095 0 1065425080 12076539554688834 12076539554884123 12076539555174202 12076539555223699
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 180 932047 932054 4194304 256 0 0 24 24 122496 0x7f4423eba900 0x7f4318236740 222077 222077 27234 1776624 65536 169508774 1599073 0 679907308 12076539555248014 12076539555445561 12076539555581881 12076539555585642
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 182 932047 932054 4194304 256 0 0 24 24 124736 0x7f4423eba800 0x7f4318236780 289532 289532 30316 2316264 65536 258844184 2153967 0 1037246008 12076539555645313 12076539555828760 12076539556012119 12076539556016073
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 184 932047 932054 4194304 256 0 0 24 24 126464 0x7f4423eba700 0x7f43182367c0 218221 218221 22984 1745776 65536 165781438 1559706 0 664998292 12076539556101341 12076539556276438 12076539556408918 12076539556412790
95 93 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 186 932047 932054 4194304 256 0 0 20 24 127936 0x7f4423eba600 0x7f4318236800 408589 408589 35900 3268720 65536 377033478 3099857 0 1509953888 12076539556473523 12076539556654677 12076539556919636 12076539556968063
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 188 932047 932054 4194304 256 0 0 28 24 129664 0x7f4423eba500 0x7f4318236840 389164 389164 34775 3113320 65536 315336088 2919102 0 1263165704 12076539556989643 12076539557196915 12076539557446994 12076539557496837
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 190 932047 932054 4194304 256 0 0 24 24 131392 0x7f4423eba400 0x7f4318236880 214700 214700 20603 1717608 65536 166865449 1551116 0 669317244 12076539557530940 12076539557722353 12076539557854993 12076539557858880
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 192 932047 932054 4194304 256 0 0 24 24 133632 0x7f4423eba300 0x7f43182368c0 302381 302381 32196 2419056 65536 272099268 2251294 0 1090241708 12076539557916808 12076539558107792 12076539558299311 12076539558348942
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 194 932047 932054 4194304 256 0 0 24 24 135360 0x7f4423ebaa00 0x7f4318236900 221972 221972 25312 1775784 65536 171171967 1604347 0 686563316 12076539558387053 12076539558563630 12076539558700910 12076539558704623
100 98 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 196 932047 932054 4194304 256 0 0 20 24 136832 0x7f4423eba900 0x7f4318236940 436981 436981 41608 3495856 65536 403803421 3313333 0 1617035172 12076539558762150 12076539558948909 12076539559232588 12076539559281286
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 198 932047 932054 4194304 256 0 0 28 24 138560 0x7f4423eba800 0x7f4318236980 387732 387732 33051 3101864 65536 336168336 2924330 0 1346515816 12076539559305892 12076539559499787 12076539559750506 12076539559799290
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 200 932047 932054 4194304 256 0 0 24 24 140288 0x7f4423eba700 0x7f43182369c0 227357 227357 27174 1818864 65536 173238101 1633646 0 694839224 12076539559817203 12076539560014986 12076539560154825 12076539560159139
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 202 932047 932054 4194304 256 0 0 24 24 142784 0x7f4423eba600 0x7f4318236a00 330132 330132 33365 2641064 65536 297166738 2474091 0 1190521024 12076539560215955 12076539560411304 12076539560621863 12076539560644171
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 204 932047 932054 4194304 256 0 0 24 24 144768 0x7f4423eba500 0x7f4318236a40 213357 213357 26864 1706864 65536 163963370 1537735 0 657724816 12076539560710896 12076539560883463 12076539561015142 12076539561019059
105 103 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 206 932047 932054 4194304 256 0 0 20 24 145728 0x7f4423eba400 0x7f4318236a80 472652 472652 42088 3781224 65536 435175208 3605903 0 1742521028 12076539561068801 12076539561260741 12076539561569380 12076539561591313
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 208 932047 932054 4194304 256 0 0 28 24 147712 0x7f4423eba300 0x7f4318236ac0 391572 391572 31869 3132584 65536 312644928 2938508 0 1252403528 12076539561643220 12076539561811139 12076539562063779 12076539562086093
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 210 932047 932054 4194304 256 0 0 24 24 149696 0x7f4423ebaa00 0x7f4318236b00 213901 213901 25989 1711216 65536 163129910 1538185 0 654384080 12076539562138731 12076539562310978 12076539562442977 12076539562446905
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 212 932047 932054 4194304 256 0 0 24 24 152192 0x7f4423eba900 0x7f4318236b40 358245 358245 36987 2865968 65536 326658037 2689677 0 1308478340 12076539562504502 12076539562690656 12076539562918976 12076539562939872
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 214 932047 932054 4194304 256 0 0 24 24 154176 0x7f4423eba800 0x7f4318236b80 217597 217597 27104 1740784 65536 171228040 1572096 0 686808540 12076539563009271 12076539563184751 12076539563319471 12076539563326871
110 108 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 216 932047 932054 4194304 256 0 0 20 24 155648 0x7f4423eba700 0x7f4318236bc0 506516 506516 44667 4052136 65536 472333292 3881050 0 1891153688 12076539563374320 12076539563594829 12076539563925388 12076539563945552
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 218 932047 932054 4194304 256 0 0 28 24 157632 0x7f4423eba600 0x7f4318236c00 394044 394044 34711 3152360 65536 338460257 2965566 0 1355667104 12076539564004963 12076539564177387 12076539564432107 12076539564482531
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 220 932047 932054 4194304 256 0 0 24 24 159616 0x7f4423eba500 0x7f4318236c40 218148 218148 27459 1745192 65536 161402768 1567003 0 647476664 12076539564507167 12076539564704106 12076539564838666 12076539564841719
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 222 932047 932054 4194304 256 0 0 24 24 162368 0x7f4423eba400 0x7f4318236c80 382685 382685 37057 3061488 65536 352418579 2893804 0 1411522080 12076539564899647 12076539565090345 12076539565335464 12076539565385200
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 224 932047 932054 4194304 256 0 0 24 24 164608 0x7f4423eba300 0x7f4318236cc0 222684 222684 28213 1781480 65536 174659076 1610928 0 700515228 12076539565419614 12076539565624744 12076539565762343 12076539565765327
115 113 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 226 932047 932054 4194304 256 0 0 20 24 166336 0x7f4423ebaa00 0x7f4318236d00 575277 575277 49017 4602224 65536 542085357 4423425 0 2170161148 12076539565822624 12076539566006663 12076539566383142 12076539566438009
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 228 932047 932054 4194304 256 0 0 28 24 168576 0x7f4423eba900 0x7f4318236d40 411333 411333 32773 3290672 65536 294082965 3109407 0 1178149968 12076539566462494 12076539566681861 12076539566948100 12076539566995155
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 230 932047 932054 4194304 256 0 0 24 24 170816 0x7f4423eba800 0x7f4318236d80 220189 220189 27563 1761520 65536 180631894 1591688 0 724389492 12076539567017396 12076539567219779 12076539567356579 12076539567359663
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 232 932047 932054 4194304 256 0 0 24 24 174080 0x7f4423eba700 0x7f4318236dc0 434277 434277 40134 3474224 65536 400605027 3308028 0 1604265284 12076539567418563 12076539567603778 12076539567883458 12076539567931457
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 234 932047 932054 4194304 256 0 0 24 24 176576 0x7f4423eba600 0x7f4318236e00 221860 221860 26317 1774888 65536 183990518 1582528 0 737848128 12076539567966682 12076539568154497 12076539568290657 12076539568293951
120 118 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 236 932047 932054 4194304 256 0 0 20 24 177792 0x7f4423eba500 0x7f4318236e40 681069 681069 15834 5448560 65536 613770776 5015320 0 2456901536 12076539568355185 12076539568539936 12076539568988895 12076539569036933
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 238 932047 932054 4194304 256 0 0 28 24 180288 0x7f4423eba400 0x7f4318236e80 406237 406237 38275 3249904 65536 337896445 3059312 0 1353414276 12076539569061068 12076539569257854 12076539569520734 12076539569567560
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 240 932047 932054 4194304 256 0 0 24 24 182784 0x7f4423eba300 0x7f4318236ec0 221404 221404 25492 1771240 65536 187699303 1605385 0 752685080 12076539569590152 12076539569784413 12076539569922173 12076539569925175
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 242 932047 932054 4194304 256 0 0 24 24 186304 0x7f4423ebaa00 0x7f4318236f00 488172 488172 43321 3905384 65536 456128425 3738992 0 1826365740 12076539569983995 12076539570178812 12076539570494491 12076539570543575
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 244 932047 932054 4194304 256 0 0 24 24 189312 0x7f4423eba900 0x7f4318236f40 242548 242548 26894 1940392 65536 215380939 1778368 0 863419016 12076539570578210 12076539570761850 12076539570914330 12076539570917401
125 123 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 246 932047 932054 4194304 256 0 0 20 24 190784 0x7f4423eba800 0x7f4318236f80 785316 785316 60413 6282536 65536 750386555 6116830 0 3003366548 12076539570975639 12076539571166329 12076539571685208 12076539571735092
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 248 932047 932054 4194304 256 0 0 28 24 193792 0x7f4423eba700 0x7f4318236fc0 462404 462404 41294 3699240 65536 389065757 3519488 0 1558101460 12076539571759537 12076539571953047 12076539572255927 12076539572305873
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 250 932047 932054 4194304 256 0 0 24 24 196800 0x7f4423eba600 0x7f4318237000 246205 246205 27832 1969648 65536 217456841 1805195 0 871712088 12076539572330299 12076539572526006 12076539572680085 12076539572683225
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 252 932047 932054 4194304 256 0 0 24 24 201088 0x7f4423eba500 0x7f4318237040 592757 592757 47125 4742064 65536 560846135 4582835 0 2245236168 12076539572743437 12076539572924405 12076539573310804 12076539573360074
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 254 932047 932054 4194304 256 0 0 24 24 204608 0x7f4423eba400 0x7f4318237080 279484 279484 30869 2235880 65536 250652439 2064728 0 1004506820 12076539573394529 12076539573578803 12076539573755123 12076539573758245
130 128 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 256 932047 932054 4194304 256 0 0 20 24 206080 0x7f4423eba300 0x7f43182370c0 925917 925917 69064 7407344 65536 888877037 7236333 0 3557328232 12076539573814099 12076539574003442 12076539574617360 12076539574667527
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 258 932047 932054 4194304 256 0 0 28 24 209600 0x7f4423ebaa00 0x7f4318237100 502348 502348 44590 4018792 65536 439118559 3825833 0 1758313140 12076539574691411 12076539574889200 12076539575217519 12076539575267342
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 260 932047 932054 4194304 256 0 0 24 24 213120 0x7f4423eba900 0x7f4318237140 282684 282684 28726 2261480 65536 252689238 2099931 0 1012641916 12076539575291597 12076539575486478 12076539575666158 12076539575669320
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 262 932047 932054 4194304 256 0 0 24 24 218176 0x7f4423eba800 0x7f4318237180 699004 699004 55608 5592040 65536 664823353 5420629 0 2661141680 12076539575728059 12076539575911117 12076539576367436 12076539576418283
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 264 932047 932054 4194304 256 0 0 24 24 222208 0x7f4423eba700 0x7f43182371c0 313445 313445 31630 2507568 65536 282905871 2340290 0 1133508000 12076539576455062 12076539576633835 12076539576834315 12076539576883679
135 133 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 266 932047 932054 4194304 256 0 0 20 24 223936 0x7f4423eba600 0x7f4318237200 1067005 1067005 77826 8536048 65536 1028681435 8360329 0 4116546560 12076539576907864 12076539577105034 12076539577811112 12076539577880232
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 268 932047 932054 4194304 256 0 0 28 24 227968 0x7f4423eba500 0x7f4318237240 567516 567516 47066 4540136 65536 533040219 4369038 0 2134004644 12076539577903656 12076539578103591 12076539578476871 12076539578544288
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 270 932047 932054 4194304 256 0 0 24 24 232000 0x7f4423eba400 0x7f4318237280 318932 318932 33166 2551464 65536 289021482 2378929 0 1157974008 12076539578567581 12076539578762630 12076539578965509 12076539579033618
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 272 932047 932054 4194304 256 0 0 24 24 237824 0x7f4423eba300 0x7f43182372c0 803653 803653 60431 6429232 65536 770151333 6265288 0 3082454928 12076539579062081 12076539579256069 12076539579783427 12076539579850538
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 274 932047 932054 4194304 256 0 0 24 24 242368 0x7f4423ebaa00 0x7f4318237300 349972 349972 35373 2799784 65536 319600579 2626228 0 1280294176 12076539579885503 12076539580069506 12076539580293186 12076539580362299
140 138 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 276 932047 932054 4194304 256 0 0 20 24 243584 0x7f4423eba900 0x7f4318237340 1209261 1209261 86183 9674096 65536 1168697018 9490305 0 4676608676 12076539580385312 12076539580581025 12076539581381983 12076539581449672
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 278 932047 932054 4194304 256 0 0 28 24 248128 0x7f4423eba800 0x7f4318237380 640132 640132 53668 5121064 65536 599660316 4940574 0 2400485004 12076539581479718 12076539581674782 12076539582097341 12076539582165464
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 280 932047 932054 4194304 256 0 0 24 24 252672 0x7f4423eba700 0x7f43182373c0 353644 353644 35173 2829160 65536 322966437 2656731 0 1293749792 12076539582196702 12076539582390140 12076539582616860 12076539582683527
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 282 932047 932054 4194304 256 0 0 24 24 259264 0x7f4423eba600 0x7f4318237400 913252 913252 68136 7306024 65536 874047575 7108852 0 3498042204 12076539582706029 12076539582904859 12076539583502618 12076539583572010
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 284 932047 932054 4194304 256 0 0 24 24 264832 0x7f4423eba500 0x7f4318237440 465477 465477 15623 3723824 65536 385617966 3174831 0 1544356816 12076539583607025 12076539583792857 12076539584094456 12076539584164873
145 143 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 286 932047 932054 4194304 256 0 0 20 24 266304 0x7f4423eba400 0x7f4318237480 1489852 1489852 102328 11918824 65536 1447143697 11738272 0 5790395304 12076539584187906 12076539584384375 12076539585372853 12076539585441117
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 288 932047 932054 4194304 256 0 0 28 24 271872 0x7f4423eba300 0x7f43182374c0 776861 776861 59692 6214896 65536 741678364 6048016 0 2968545520 12076539585470481 12076539585667252 12076539586182131 12076539586250302
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 290 932047 932054 4194304 256 0 0 24 24 277440 0x7f4423ebaa00 0x7f4318237500 424052 424052 40753 3392424 65536 390940143 3216035 0 1565656504 12076539586281059 12076539586473970 12076539586747249 12076539586814421
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 292 932047 932054 4194304 256 0 0 12 24 279936 0x7f4423eba900 0x7f4318237540 1127588 1127588 79764 9020712 65536 1089666359 8846401 0 4360489876 12076539586837584 12076539587040369 12076539587780047 12076539587849266
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 294 932047 932054 4194304 256 0 0 24 24 286528 0x7f4423eba800 0x7f4318237580 491236 491236 44858 3929896 65536 456921999 3756820 0 1829591628 12076539587884682 12076539588075886 12076539588394445 12076539588463619
150 148 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 296 932047 932054 4194304 256 0 0 20 24 288000 0x7f4423eba700 0x7f43182375c0 1768581 1768581 117542 14148656 65536 1724447322 13979919 0 6899609844 12076539588480260 12076539588686124 12076539589862441 12076539589930097
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 298 932047 932054 4194304 256 0 0 32 24 294592 0x7f4423eba600 0x7f4318237600 921053 921053 66297 7368432 65536 804876492 7196129 0 3221370360 12076539589960724 12076539590164040 12076539590776999 12076539590846932
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 300 932047 932054 4194304 256 0 0 24 24 301184 0x7f4423eba500 0x7f4318237640 492644 492644 42992 3941160 65536 461031505 3771720 0 1846012960 12076539590876347 12076539591075558 12076539591395397 12076539591462808
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 302 932047 932054 4194304 256 0 0 12 24 304960 0x7f4423eba400 0x7f4318237680 1337396 1337396 92333 10699176 65536 1299277386 10528946 0 5198938588 12076539591485901 12076539591683877 12076539592563714 12076539592632033
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 304 932047 932054 4194304 256 0 0 24 24 313600 0x7f4423eba300 0x7f43182376c0 633333 633333 54072 5066672 65536 596476135 4888805 0 2387800312 12076539592676495 12076539592851394 12076539593264353 12076539593334429
155 153 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 306 932047 932054 4194304 256 0 0 20 24 314816 0x7f4423ebaa00 0x7f4318237700 2333356 2333356 79878 18666856 65536 2284896529 18494385 0 9141407988 12076539593365377 12076539593559872 12076539595112668 12076539595180623
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 308 932047 932054 4194304 256 0 0 20 24 317568 0x7f4423eba900 0x7f4318237740 1201356 1201356 84410 9610856 65536 1163784346 9436414 0 4656960640 12076539595208676 12076539595416667 12076539596213945 12076539596281711
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 310 932047 932054 4194304 256 0 0 12 24 320320 0x7f4423eba800 0x7f4318237780 640204 640204 49910 5121640 65536 609787230 4957036 0 2440985580 12076539596312980 12076539596508024 12076539596923863 12076539596991732
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 312 932047 932054 4194304 256 0 0 12 24 324096 0x7f4423eba700 0x7f43182377c0 1758908 1758908 118155 14071272 65536 1714603939 13898946 0 6860241008 12076539597015316 12076539597221622 12076539598381619 12076539598451678
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 314 932047 932054 4194304 256 0 0 12 24 328896 0x7f4423eba600 0x7f4318237800 1198893 1198893 83313 9591152 65536 1162202950 9418965 0 4650639276 12076539598497092 12076539598670739 12076539599457617 12076539599525425
160 158 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 316 932047 932054 4194304 256 0 0 20 24 330112 0x7f4423eba500 0x7f4318237840 4584605 4584605 282315 36676848 65536 4514668689 36504958 0 18060495812 12076539599556202 12076539599751536 12076539602807688 12076539602875888
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 318 932047 932054 4194304 256 0 0 20 24 332864 0x7f4423eba400 0x7f4318237880 2323717 2323717 149516 18589744 65536 2276271710 18426457 0 9106912448 12076539602907176 12076539603104647 12076539604650083 12076539604718685
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 320 932047 932054 4194304 256 0 0 12 24 335616 0x7f4423eba300 0x7f43182378c0 1203644 1203644 84669 9629160 65536 1165498254 9459635 0 4663816016 12076539604744233 12076539604944162 12076539605734400 12076539605803483
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 322 932047 932054 4194304 256 0 0 12 24 339392 0x7f4423ebaa00 0x7f4318237900 3442909 3442909 215169 27543280 65536 3384776709 27373869 0 13540931208 12076539605831495 12076539606036160 12076539608318234 12076539608386899
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 324 932047 932054 4194304 256 0 0 12 24 344192 0x7f4423eba900 0x7f4318237940 2326380 2326380 152550 18611048 65536 2276299888 18421771 0 9107028724 12076539608431972 12076539608608793 12076539610145269 12076539610213496
165 163 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 326 932047 932054 4194304 256 0 0 20 24 345408 0x7f4423eba800 0x7f4318237980 9087740 9087740 473479 72701928 65536 8978154106 72527985 0 35914436988 12076539610248151 12076539610438708 12076539616501253 12076539616571974
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 328 932047 932054 4194304 256 0 0 20 24 348160 0x7f4423eba700 0x7f43182379c0 4574484 4574484 283331 36595880 65536 4501040258 36416888 0 18005984112 12076539616598613 12076539616799652 12076539619846204 12076539619916605
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 330 932047 932054 4194304 256 0 0 12 24 350912 0x7f4423eba600 0x7f4318237a00 2330213 2330213 150793 18641712 65536 2281449272 18463936 0 9127621428 12076539619943846 12076539620150203 12076539621690679 12076539621760165
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 332 932047 932054 4194304 256 0 0 12 24 0 0x7f4423eba500 0x7f4318237a40 6816229 6816229 412766 54529840 65536 6723941280 54336435 0 26897589764 12076539621793717 12076539621986528 12076539626515797 12076539626589217
@@ -0,0 +1,5 @@
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,5 @@
pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
@@ -0,0 +1,21 @@
pmc: SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_SH_FIFO_BUSY_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum
pmc: SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_INSTS SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_SH_FIFO_CMD_BUSY_sum TA_SH_FIFO_ADDR_BUSY_sum TD_COALESCABLE_WAVEFRONT_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum
pmc: SQ_ACTIVE_INST_ANY SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_INSTS_VALU SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_SH_FIFO_DATA_BUSY_sum TA_SH_FIFO_DATA_SFIFO_BUSY_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum
pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_SH_FIFO_DATA_TFIFO_BUSY_sum TA_SQ_TA_CMD_CYCLES_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum
pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES SQ_WAVES_EQ_64 SQ_WAVES_LT_64 TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_SP_TA_ADDR_CYCLES_sum TA_SP_TA_DATA_CYCLES_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_STALL_sum
pmc: SQ_WAVES_LT_48 SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_SH_FIFO_ADDR_STARVED_WHILE_BUSY_CYCLES_sum TA_SH_FIFO_CMD_STARVED_WHILE_BUSY_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_IO_CREDIT_STALL_sum TCC_EA_WRREQ_GMI_CREDIT_STALL_sum TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum
pmc: SQ_WAVES_SAVED SQ_INSTS_SMEM_NORM SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_SH_FIFO_DATA_STARVED_WHILE_BUSY_CYCLES_sum TA_TA_SH_FIFO_STARVED_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_ATOMIC_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum
pmc: SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_BUFFER_WAVEFRONTS_sum TA_BUFFER_READ_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_EA_RDREQ_IO_CREDIT_STALL_sum TCC_EA_RDREQ_GMI_CREDIT_STALL_sum TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum TCC_TAG_STALL_sum
pmc: SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum
pmc: TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum TA_BUFFER_TOTAL_CYCLES_sum TA_BUFFER_COALESCABLE_WAVEFRONTS_sum TCC_EA_RDREQ_DRAM_sum TCC_EA_WRREQ_DRAM_sum TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum
pmc: TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TCC_EA_ATOMIC_LEVEL_sum
pmc: TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31]
pmc: TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31]
pmc: TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31]
pmc: TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31]
pmc: TA_FLAT_COALESCEABLE_WAVEFRONTS_sum TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31]
pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31]
gpu:
range:
kernel:
@@ -0,0 +1,168 @@
Dispatch_ID,Kernel_Name,GPU_ID
0,__amd_rocclr_fillBuffer.kd,0
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0
1 Dispatch_ID Kernel_Name GPU_ID
2 0 __amd_rocclr_fillBuffer.kd 0
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0
5 3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0
10 8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0
15 13 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0
20 18 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0
25 23 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0
30 28 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0
35 33 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0
40 38 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0
45 43 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0
50 48 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0
55 53 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0
60 58 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0
65 63 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0
70 68 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0
75 73 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0
80 78 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0
85 83 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0
90 88 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0
95 93 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0
100 98 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0
105 103 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0
110 108 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0
115 113 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0
120 118 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0
125 123 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0
130 128 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0
135 133 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0
140 138 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0
145 143 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0
150 148 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0
155 153 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0
160 158 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0
165 163 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0
File diff soppresso perché una o più righe sono troppo lunghe
@@ -0,0 +1,11 @@
Kernel_Name,Count,Sum(ns),Mean(ns),Median(ns),Pct
"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,6057561.0,6057561.0,6057561.0,9.181885909300709
"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",1,4526211.0,4526211.0,4526211.0,6.860707305039414
"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,3055501.0,3055501.0,3055501.0,4.63144516047865
"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",1,3044781.0,3044781.0,3044781.0,4.615196076573808
"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",1,2280946.0,2280946.0,2280946.0,3.457395796307426
"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,1550707.0,1550707.0,1550707.0,2.3505194174279005
"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",1,1544150.0,1544150.0,1544150.0,2.340580495490955
"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",1,1539510.0,1539510.0,1539510.0,2.333547309920202
"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",1,1535670.0,1535670.0,1535670.0,2.3277267425513037
"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,1173590.0,1173590.0,1173590.0,1.778895744392209
1 Kernel_Name Count Sum(ns) Mean(ns) Median(ns) Pct
2 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 1 6057561.0 6057561.0 6057561.0 9.181885909300709
3 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 1 4526211.0 4526211.0 4526211.0 6.860707305039414
4 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 1 3055501.0 3055501.0 3055501.0 4.63144516047865
5 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 1 3044781.0 3044781.0 3044781.0 4.615196076573808
6 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 1 2280946.0 2280946.0 2280946.0 3.457395796307426
7 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 1 1550707.0 1550707.0 1550707.0 2.3505194174279005
8 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 1 1544150.0 1544150.0 1544150.0 2.340580495490955
9 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 1 1539510.0 1539510.0 1539510.0 2.333547309920202
10 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 1 1535670.0 1535670.0 1535670.0 2.3277267425513037
11 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 1 1173590.0 1173590.0 1173590.0 1.778895744392209
@@ -0,0 +1,9 @@
Metric,Count,Unit
VALU - Vector,,Instr per wave
VMEM,,Instr per wave
LDS_Per_Workgroup,0.0,Instr per wave
VALU - MFMA,,Instr per wave
SALU,46.862275449101794,Instr per wave
SMEM,1.8083832335329342,Instr per wave
Branch,21.97005988023952,Instr per wave
GDS,0.0,Instr per wave
1 Metric Count Unit
2 VALU - Vector Instr per wave
3 VMEM Instr per wave
4 LDS_Per_Workgroup 0.0 Instr per wave
5 VALU - MFMA Instr per wave
6 SALU 46.862275449101794 Instr per wave
7 SMEM 1.8083832335329342 Instr per wave
8 Branch 21.97005988023952 Instr per wave
9 GDS 0.0 Instr per wave
@@ -0,0 +1,16 @@
Metric,Count,Unit
INT-32,,Instr per wave
INT-64,,Instr per wave
F16-ADD,,Instr per wave
F16-Mult,,Instr per wave
F16-FMA,,Instr per wave
F16-Trans,,Instr per wave
F32-ADD,,Instr per wave
F32-Mult,,Instr per wave
F32-FMA,,Instr per wave
F32-Trans,,Instr per wave
F64-ADD,,Instr per wave
F64-Mult,,Instr per wave
F64-FMA,,Instr per wave
F64-Trans,,Instr per wave
Conversion,,Instr per wave
1 Metric Count Unit
2 INT-32 Instr per wave
3 INT-64 Instr per wave
4 F16-ADD Instr per wave
5 F16-Mult Instr per wave
6 F16-FMA Instr per wave
7 F16-Trans Instr per wave
8 F32-ADD Instr per wave
9 F32-Mult Instr per wave
10 F32-FMA Instr per wave
11 F32-Trans Instr per wave
12 F64-ADD Instr per wave
13 F64-Mult Instr per wave
14 F64-FMA Instr per wave
15 F64-Trans Instr per wave
16 Conversion Instr per wave
@@ -0,0 +1,9 @@
Type,Count
Buffer Instr,0.0
Buffer Read,0.0
Buffer Write,0.0
Buffer Atomic,0.0
Flat Instr,7.9640718562874255
Flat Read,7.952095808383233
Flat Write,0.011976047904191617
Flat Atomic,0.0
1 Type Count
2 Buffer Instr 0.0
3 Buffer Read 0.0
4 Buffer Write 0.0
5 Buffer Atomic 0.0
6 Flat Instr 7.9640718562874255
7 Flat Read 7.952095808383233
8 Flat Write 0.011976047904191617
9 Flat Atomic 0.0
@@ -0,0 +1,6 @@
Type,Count
MFMA-I8,
MFMA-F16,
MFMA-BF16,
MFMA-F32,
MFMA-F64,
1 Type Count
2 MFMA-I8
3 MFMA-F16
4 MFMA-BF16
5 MFMA-F32
6 MFMA-F64
@@ -0,0 +1,26 @@
Info
dev01p3
vesuvius
AMD EPYC 7542 32-Core Processor
""
4.18.0-240.15.1.el8_3.x86_64
4.2.0-21
Thu Sep 22 11:34:46 2022 (CDT)
gfx908
8
120
4
64
40
1024
16
""
1502
1200
300
1200
32
mi100
48
1228.8
SQ|LDS_Per_Workgroup|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF
1 Info
2 dev01p3
3 vesuvius
4 AMD EPYC 7542 32-Core Processor
5
6 4.18.0-240.15.1.el8_3.x86_64
7 4.2.0-21
8 Thu Sep 22 11:34:46 2022 (CDT)
9 gfx908
10 8
11 120
12 4
13 64
14 40
15 1024
16 16
17
18 1502
19 1200
20 300
21 1200
22 32
23 mi100
24 48
25 1228.8
26 SQ|LDS_Per_Workgroup|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF
@@ -0,0 +1,7 @@
Metric,Value
valu_flops_pop,
mfma_flops_bf16_pop,
mfma_flops_f16_pop,
mfma_flops_f32_pop,
mfma_flops_f64_pop,
mfma_flops_i8_pop,
1 Metric Value
2 valu_flops_pop
3 mfma_flops_bf16_pop
4 mfma_flops_f16_pop
5 mfma_flops_f32_pop
6 mfma_flops_f64_pop
7 mfma_flops_i8_pop
@@ -0,0 +1,8 @@
Metric,Avg,Min,Max,Unit
IPC (Avg),0.5967010982293053,0.033265912609182026,1.433747633495388,Instr/cycle
IPC (Issue),0.8437287060051507,0.5168776263701953,0.9995913989478523,Instr/cycle
SALU Util,2.1142315362209505,0.029171794521172342,23.298857478812526,Pct
VALU Util,59.27505815065561,0.8605679383745841,99.09113890249397,Pct
VALU Active Threads,63.96805399754944,63.73180122585954,64.0,Threads
MFMA Util,,,,Pct
MFMA Instr Cycles,,,,Cycles/instr
1 Metric Avg Min Max Unit
2 IPC (Avg) 0.5967010982293053 0.033265912609182026 1.433747633495388 Instr/cycle
3 IPC (Issue) 0.8437287060051507 0.5168776263701953 0.9995913989478523 Instr/cycle
4 SALU Util 2.1142315362209505 0.029171794521172342 23.298857478812526 Pct
5 VALU Util 59.27505815065561 0.8605679383745841 99.09113890249397 Pct
6 VALU Active Threads 63.96805399754944 63.73180122585954 64.0 Threads
7 MFMA Util Pct
8 MFMA Instr Cycles Cycles/instr
@@ -0,0 +1,7 @@
Metric,Avg,Min,Max,Unit
FLOPs (Total),,,,Ops per wave
INT8 OPs,,,,Ops per wave
F16 OPs,,,,Ops per wave
BF16 OPs,,,,Ops per wave
F32 OPs,,,,Ops per wave
F64 OPs,,,,Ops per wave
1 Metric Avg Min Max Unit
2 FLOPs (Total) Ops per wave
3 INT8 OPs Ops per wave
4 F16 OPs Ops per wave
5 BF16 OPs Ops per wave
6 F32 OPs Ops per wave
7 F64 OPs Ops per wave
@@ -0,0 +1,5 @@
Metric,Value
Utilization,0.0
Access Rate,0.0
Bandwith (Pct-of-Peak),0.0
Bank Conflict Rate,
1 Metric Value
2 Utilization 0.0
3 Access Rate 0.0
4 Bandwith (Pct-of-Peak) 0.0
5 Bank Conflict Rate
@@ -0,0 +1,12 @@
Metric,Avg,Min,Max,Unit
Wave Cycles,33701.426573519224,2837.008590698242,547911.8947753906,Cycles/wave
LDS_Per_Workgroup Instrs,0.0,0.0,0.0,Instr per wave
Bandwidth,0.0,0.0,0.0,Bytes per wave
Bank Conficts/Access,,,,Conflicts/access
Dispatch_ID Accesses,0.0,0.0,0.0,Cycles per wave
Atomic Cycles,0.0,0.0,0.0,Cycles per wave
Bank Conflict,0.0,0.0,0.0,Cycles per wave
Addr Conflict,0.0,0.0,0.0,Cycles per wave
Unaligned Stall,0.0,0.0,0.0,Cycles per wave
Mem Violations,0.0,0.0,0.0, per wave
LDS_Per_Workgroup Latency,,,,Cycles
1 Metric Avg Min Max Unit
2 Wave Cycles 33701.426573519224 2837.008590698242 547911.8947753906 Cycles/wave
3 LDS_Per_Workgroup Instrs 0.0 0.0 0.0 Instr per wave
4 Bandwidth 0.0 0.0 0.0 Bytes per wave
5 Bank Conficts/Access Conflicts/access
6 Dispatch_ID Accesses 0.0 0.0 0.0 Cycles per wave
7 Atomic Cycles 0.0 0.0 0.0 Cycles per wave
8 Bank Conflict 0.0 0.0 0.0 Cycles per wave
9 Addr Conflict 0.0 0.0 0.0 Cycles per wave
10 Unaligned Stall 0.0 0.0 0.0 Cycles per wave
11 Mem Violations 0.0 0.0 0.0 per wave
12 LDS_Per_Workgroup Latency Cycles
@@ -0,0 +1,3 @@
Metric,Value
Bandwidth,30.55821701704327
Cache Hit,99.52066831123885
1 Metric Value
2 Bandwidth 30.55821701704327
3 Cache Hit 99.52066831123885
@@ -0,0 +1,6 @@
L1I Metric,Mean,Min,Max,Unit
Req,162.66467065868264,12.0,3215.0,Req per wave
Hits,162.4759195293495,11.996292114257812,3214.9818725585938,Hits per wave
Misses - Non Duplicated,0.001965551319236527,0.00018310546875,0.09375,Misses per wave
Misses - Duplicated,0.29370532920974457,0.00411224365234375,2.935546875,Misses per wave
Cache Hit,99.52066831123885,81.06689453125,99.99930279529585,Pct
1 L1I Metric Mean Min Max Unit
2 Req 162.66467065868264 12.0 3215.0 Req per wave
3 Hits 162.4759195293495 11.996292114257812 3214.9818725585938 Hits per wave
4 Misses - Non Duplicated 0.001965551319236527 0.00018310546875 0.09375 Misses per wave
5 Misses - Duplicated 0.29370532920974457 0.00411224365234375 2.935546875 Misses per wave
6 Cache Hit 99.52066831123885 81.06689453125 99.99930279529585 Pct
@@ -0,0 +1,3 @@
Metric,Value
Bandwidth,0.9329371880256379
Cache Hit,98.0273830676507
1 Metric Value
2 Bandwidth 0.9329371880256379
3 Cache Hit 98.0273830676507
@@ -0,0 +1,13 @@
Metric,Mean,Min,Max,Unit
Req,1.8083832335329342,1.0,8.0,Req per wave
Hits,1.779911395318494,0.0,7.991540908813477,Req per wave
Misses - Non Duplicated,0.0012866722609468563,0.000274658203125,0.09375,Req per wave
Misses- Duplicated,0.027185165953493403,0.008184432983398438,0.90625,Req per wave
Cache Hit,98.0273830676507,0.0,99.89426136016846,Pct
Read Req (Total),1.8083832335329342,1.0,8.0,Req per wave
Atomic Req,0.0,0.0,0.0,Req per wave
Read Req (1 DWord),0.5988023952095808,0.0,4.0,Req per wave
Read Req (2 DWord),1.0,0.0,2.0,Req per wave
Read Req (4 DWord),0.20958083832335328,0.0,3.0,Req per wave
Read Req (8 DWord),0.0,0.0,0.0,Req per wave
Read Req (16 DWord),0.0,0.0,0.0,Req per wave
1 Metric Mean Min Max Unit
2 Req 1.8083832335329342 1.0 8.0 Req per wave
3 Hits 1.779911395318494 0.0 7.991540908813477 Req per wave
4 Misses - Non Duplicated 0.0012866722609468563 0.000274658203125 0.09375 Req per wave
5 Misses- Duplicated 0.027185165953493403 0.008184432983398438 0.90625 Req per wave
6 Cache Hit 98.0273830676507 0.0 99.89426136016846 Pct
7 Read Req (Total) 1.8083832335329342 1.0 8.0 Req per wave
8 Atomic Req 0.0 0.0 0.0 Req per wave
9 Read Req (1 DWord) 0.5988023952095808 0.0 4.0 Req per wave
10 Read Req (2 DWord) 1.0 0.0 2.0 Req per wave
11 Read Req (4 DWord) 0.20958083832335328 0.0 3.0 Req per wave
12 Read Req (8 DWord) 0.0 0.0 0.0 Req per wave
13 Read Req (16 DWord) 0.0 0.0 0.0 Req per wave
@@ -0,0 +1,5 @@
Metric,Mean,Min,Max,Unit
Read Req,0.0012866722609468563,0.000274658203125,0.09375,Req per wave
Write Req,0.0,0.0,0.0,Req per wave
Atomic Req,0.0,0.0,0.0,Req per wave
Stall,0.0,0.0,0.0,Cycles per wave
1 Metric Mean Min Max Unit
2 Read Req 0.0012866722609468563 0.000274658203125 0.09375 Req per wave
3 Write Req 0.0 0.0 0.0 Req per wave
4 Atomic Req 0.0 0.0 0.0 Req per wave
5 Stall 0.0 0.0 0.0 Cycles per wave
@@ -0,0 +1,17 @@
Metric,Avg,Min,Max,Unit
TA Busy,58.29573892312343,2.2585320486354257,93.29102881278597,Pct
TC2TA Addr Stall,44.612169977074934,0.09191929673616535,79.31252478238704,Pct
TC2TA Data Stall,0.3722098529633452,0.0,62.15904544487864,Pct
TD2TA Addr Stall,0.0,0.0,0.0,Pct
Total Instructions,7.9640718562874255,2.0,8.0,Instr per wave
Flat Instr,7.9640718562874255,2.0,8.0,Instr per wave
Flat Read Instr,7.952095808383233,0.0,8.0,Instr per wave
Flat Write Instr,0.011976047904191617,0.0,2.0,Instr per wave
Flat Atomic Instr,0.0,0.0,0.0,Instr per wave
Buffer Instr,0.0,0.0,0.0,Instr per wave
Buffer Read Instr,0.0,0.0,0.0,Instr per wave
Buffer Write Instr,0.0,0.0,0.0,Instr per wave
Buffer Atomic Instr,0.0,0.0,0.0,Instr per wave
Buffer Total Cylces,0.0,0.0,0.0,Cycles per wave
Buffer Coalesced Read,0.0,0.0,0.0,Cycles per wave
Buffer Coalesced Write,0.0,0.0,0.0,Cycles per wave
1 Metric Avg Min Max Unit
2 TA Busy 58.29573892312343 2.2585320486354257 93.29102881278597 Pct
3 TC2TA Addr Stall 44.612169977074934 0.09191929673616535 79.31252478238704 Pct
4 TC2TA Data Stall 0.3722098529633452 0.0 62.15904544487864 Pct
5 TD2TA Addr Stall 0.0 0.0 0.0 Pct
6 Total Instructions 7.9640718562874255 2.0 8.0 Instr per wave
7 Flat Instr 7.9640718562874255 2.0 8.0 Instr per wave
8 Flat Read Instr 7.952095808383233 0.0 8.0 Instr per wave
9 Flat Write Instr 0.011976047904191617 0.0 2.0 Instr per wave
10 Flat Atomic Instr 0.0 0.0 0.0 Instr per wave
11 Buffer Instr 0.0 0.0 0.0 Instr per wave
12 Buffer Read Instr 0.0 0.0 0.0 Instr per wave
13 Buffer Write Instr 0.0 0.0 0.0 Instr per wave
14 Buffer Atomic Instr 0.0 0.0 0.0 Instr per wave
15 Buffer Total Cylces 0.0 0.0 0.0 Cycles per wave
16 Buffer Coalesced Read 0.0 0.0 0.0 Cycles per wave
17 Buffer Coalesced Write 0.0 0.0 0.0 Cycles per wave
@@ -0,0 +1,8 @@
Metric,Avg,Min,Max,Unit
TD Busy,74.55442326384481,15.435907651344314,93.80582451117056,Pct
TC2TD Stall,64.63842236054707,13.180191438603288,89.64189063455353,Pct
SPI2TD Stall,,,,Pct
Coalescable Instr,4.802395209580839,0.0,8.0,Instr per wave
Load Instr,7.952095808383233,0.0,8.0,Instr per wave
Store Instr,0.011976047904191617,0.0,2.0,Instr per wave
Atomic Instr,0.0,0.0,0.0,Instr per wave
1 Metric Avg Min Max Unit
2 TD Busy 74.55442326384481 15.435907651344314 93.80582451117056 Pct
3 TC2TD Stall 64.63842236054707 13.180191438603288 89.64189063455353 Pct
4 SPI2TD Stall Pct
5 Coalescable Instr 4.802395209580839 0.0 8.0 Instr per wave
6 Load Instr 7.952095808383233 0.0 8.0 Instr per wave
7 Store Instr 0.011976047904191617 0.0 2.0 Instr per wave
8 Atomic Instr 0.0 0.0 0.0 Instr per wave
@@ -0,0 +1,5 @@
Metric,Value
Buffer Coalescing,69.91017964071857
Cache Util,80.45833971711706
Cache BW,2.4166113224751506
Cache Hit,20.508982035928145
1 Metric Value
2 Buffer Coalescing 69.91017964071857
3 Cache Util 80.45833971711706
4 Cache BW 2.4166113224751506
5 Cache Hit 20.508982035928145
@@ -0,0 +1,6 @@
Metric,Mean,Min,Max,Unit
Stalled on L2 Data,60.556746490524745,13.572332317476718,84.89731714206611,Pct
Stalled on L2 Req,28.870392262702243,0.003934095522428448,66.73376329343735,Pct
Tag RAM Stall (Read),0.0,0.0,0.0,Pct
Tag RAM Stall (Write),0.0,0.0,0.0,Pct
Tag RAM Stall (Atomic),0.0,0.0,0.0,Pct
1 Metric Mean Min Max Unit
2 Stalled on L2 Data 60.556746490524745 13.572332317476718 84.89731714206611 Pct
3 Stalled on L2 Req 28.870392262702243 0.003934095522428448 66.73376329343735 Pct
4 Tag RAM Stall (Read) 0.0 0.0 0.0 Pct
5 Tag RAM Stall (Write) 0.0 0.0 0.0 Pct
6 Tag RAM Stall (Atomic) 0.0 0.0 0.0 Pct
@@ -0,0 +1,15 @@
Metric,Avg,Min,Max,Unit
Total Req,279.76047904191614,128.0,512.0,Req per wave
Read Req,278.9940119760479,0.0,512.0,Req per wave
Write Req,0.7664670658682635,0.0,128.0,Req per wave
Atomic Req,0.0,0.0,0.0,Req per wave
Cache Accesses,70.13173652694611,32.0,128.0,Req per wave
Cache Hits,25.676646706586826,0.0,64.0,Req per wave
Cache Hit Rate,20.508982035928145,0.0,75.0,Pct
Invalidate,0.009641818657606662,0.0006866455078125,0.703125, per wave
L1-TCR Read,44.35928143712575,0.0,64.0,Req per wave
L1-L2 Write,0.09580838323353294,0.0,16.0,Req per wave
L1-L2 Atomic,0.0,0.0,0.0,Req per wave
L1 Access Latency,1513.3359868112439,407.1349925994873,3212.031982421875,Cycles
L1-L2 Read Latency,737.760770951409,352.1864833831787,2220.0745849609375,Cycles
L1-L2 Write Latency,331.53173184394836,331.53173184394836,331.53173184394836,Cycles
1 Metric Avg Min Max Unit
2 Total Req 279.76047904191614 128.0 512.0 Req per wave
3 Read Req 278.9940119760479 0.0 512.0 Req per wave
4 Write Req 0.7664670658682635 0.0 128.0 Req per wave
5 Atomic Req 0.0 0.0 0.0 Req per wave
6 Cache Accesses 70.13173652694611 32.0 128.0 Req per wave
7 Cache Hits 25.676646706586826 0.0 64.0 Req per wave
8 Cache Hit Rate 20.508982035928145 0.0 75.0 Pct
9 Invalidate 0.009641818657606662 0.0006866455078125 0.703125 per wave
10 L1-TCR Read 44.35928143712575 0.0 64.0 Req per wave
11 L1-L2 Write 0.09580838323353294 0.0 16.0 Req per wave
12 L1-L2 Atomic 0.0 0.0 0.0 Req per wave
13 L1 Access Latency 1513.3359868112439 407.1349925994873 3212.031982421875 Cycles
14 L1-L2 Read Latency 737.760770951409 352.1864833831787 2220.0745849609375 Cycles
15 L1-L2 Write Latency 331.53173184394836 331.53173184394836 331.53173184394836 Cycles
@@ -0,0 +1,13 @@
Xfer,Mean,Min,Max,Unit
NC - Read,0.0,0.0,0.0,Req per wave
UC - Read,0.0,0.0,0.0,Req per wave
CC - Read,0.0,0.0,0.0,Req per wave
RW - Read,44.35928143712575,0.0,64.0,Req per wave
RW - Write,0.09580838323353294,0.0,16.0,Req per wave
NC - Write,0.0,0.0,0.0,Req per wave
UC - Write,0.0,0.0,0.0,Req per wave
CC - Write,0.0,0.0,0.0,Req per wave
NC - Atomic,0.0,0.0,0.0,Req per wave
UC - Atomic,0.0,0.0,0.0,Req per wave
CC - Atomic,0.0,0.0,0.0,Req per wave
RW - Atomic,0.0,0.0,0.0,Req per wave
1 Xfer Mean Min Max Unit
2 NC - Read 0.0 0.0 0.0 Req per wave
3 UC - Read 0.0 0.0 0.0 Req per wave
4 CC - Read 0.0 0.0 0.0 Req per wave
5 RW - Read 44.35928143712575 0.0 64.0 Req per wave
6 RW - Write 0.09580838323353294 0.0 16.0 Req per wave
7 NC - Write 0.0 0.0 0.0 Req per wave
8 UC - Write 0.0 0.0 0.0 Req per wave
9 CC - Write 0.0 0.0 0.0 Req per wave
10 NC - Atomic 0.0 0.0 0.0 Req per wave
11 UC - Atomic 0.0 0.0 0.0 Req per wave
12 CC - Atomic 0.0 0.0 0.0 Req per wave
13 RW - Atomic 0.0 0.0 0.0 Req per wave
@@ -0,0 +1,6 @@
Metric,Mean,Min,Max,Units
Req,69.94011976047904,32.0,128.0, per wave
Hit Ratio,97.67132547801127,91.943359375,98.99572134017944,Pct
Hits,68.49201277772823,29.421875,125.98385620117188, per wave
Misses (Translation),0.15855599591831962,0.02923583984375,0.234375, per wave
Misses (Permission),0.0,0.0,0.0, per wave
1 Metric Mean Min Max Units
2 Req 69.94011976047904 32.0 128.0 per wave
3 Hit Ratio 97.67132547801127 91.943359375 98.99572134017944 Pct
4 Hits 68.49201277772823 29.421875 125.98385620117188 per wave
5 Misses (Translation) 0.15855599591831962 0.02923583984375 0.234375 per wave
6 Misses (Permission) 0.0 0.0 0.0 per wave
@@ -0,0 +1,5 @@
Metric,Value,Unit
L2 Util,87.6670149861896,Pct
Cache Hit,0.3929601391220619,Pct
L2-EA Rd BW,837.9967513054252,Gb/s
L2-EA Wr BW,4.968599175317518,Gb/s
1 Metric Value Unit
2 L2 Util 87.6670149861896 Pct
3 Cache Hit 0.3929601391220619 Pct
4 L2-EA Rd BW 837.9967513054252 Gb/s
5 L2-EA Wr BW 4.968599175317518 Gb/s
@@ -0,0 +1,16 @@
Metric,Avg,Min,Max,Unit
Read BW,2840.9054072031718,1.3026123046875,4100.251953125,Bytes per wave
Write BW,3.0659223545097305,0.0,512.009033203125,Bytes per wave
Read (32B),0.0,0.0,0.0,Req per wave
Read (Uncached 32B),0.05846560358287332,0.011932373046875,0.859375,Req per wave
Read (64B),44.38914698754956,0.020353317260742188,64.06643676757812,Req per wave
HBM Read,44.38884401606942,0.019989013671875,64.06318664550781,Req per wave
Write (32B),0.0,0.0,0.0,Req per wave
Write (Uncached 32B),0.0,0.0,0.0,Req per wave
Write (64B),0.04790503678921454,0.0,8.000141143798828,Req per wave
HBM Write,0.047904545675494715,0.0,8.000059127807617,Req per wave
Read Latency,449.8986946067636,238.5193024302473,1202.4691219192202,Cycles
Write Latency,144.17015133113895,144.17015133113895,144.17015133113895,Cycles
Atomic Latency,,,,Cycles
Read Stall,5.088426813223754,0.0,15.79519703341474,Pct
Write Stall,0.008584797566255725,0.0,1.4336611935647061,Pct
1 Metric Avg Min Max Unit
2 Read BW 2840.9054072031718 1.3026123046875 4100.251953125 Bytes per wave
3 Write BW 3.0659223545097305 0.0 512.009033203125 Bytes per wave
4 Read (32B) 0.0 0.0 0.0 Req per wave
5 Read (Uncached 32B) 0.05846560358287332 0.011932373046875 0.859375 Req per wave
6 Read (64B) 44.38914698754956 0.020353317260742188 64.06643676757812 Req per wave
7 HBM Read 44.38884401606942 0.019989013671875 64.06318664550781 Req per wave
8 Write (32B) 0.0 0.0 0.0 Req per wave
9 Write (Uncached 32B) 0.0 0.0 0.0 Req per wave
10 Write (64B) 0.04790503678921454 0.0 8.000141143798828 Req per wave
11 HBM Write 0.047904545675494715 0.0 8.000059127807617 Req per wave
12 Read Latency 449.8986946067636 238.5193024302473 1202.4691219192202 Cycles
13 Write Latency 144.17015133113895 144.17015133113895 144.17015133113895 Cycles
14 Atomic Latency Cycles
15 Read Stall 5.088426813223754 0.0 15.79519703341474 Pct
16 Write Stall 0.008584797566255725 0.0 1.4336611935647061 Pct
@@ -0,0 +1,19 @@
Metric,Avg,Min,Max,Unit
Req,44.51748940473545,16.021072387695312,64.09295654296875,Req per wave
Streaming Req,0.0,0.0,0.0,Req per wave
Read Req,44.41905537907949,0.021387100219726562,64.08915710449219,Req per wave
Write Req,0.09580838323353294,0.0,16.0,Req per wave
Atomic Req,0.0,0.0,0.0,Req per wave
Probe Req,0.0,0.0,0.0,Req per wave
Hits,0.0776433773383409,0.0064544677734375,8.00080680847168,Hits per wave
Misses,44.43984602739711,8.020265579223633,64.06283569335938,Misses per wave
Cache Hit,0.3929601391220619,0.010077842398269183,49.939271322539874,Pct
Writeback,0.048735030396969733,0.0004730224609375,8.000154495239258, per wave
NC Req,0.0012861240409805389,0.00018310546875,0.09375,Req per wave
UC Req,0.029895736785705933,0.0066070556640625,0.427734375,Req per wave
CC Req,0.0,0.0,0.0,Req per wave
RW Req,44.48417563067225,16.000640869140625,64.076904296875,Req per wave
Writeback (Normal),0.047156282527718,0.0,7.875099182128906, per wave
Writeback (TC Req),0.0007484687302640813,0.0,0.12499427795410156, per wave
Evict (Normal),42.33437258326365,0.0,62.00164794921875, per wave
Evict (TC Req),0.0,0.0,0.0, per wave
1 Metric Avg Min Max Unit
2 Req 44.51748940473545 16.021072387695312 64.09295654296875 Req per wave
3 Streaming Req 0.0 0.0 0.0 Req per wave
4 Read Req 44.41905537907949 0.021387100219726562 64.08915710449219 Req per wave
5 Write Req 0.09580838323353294 0.0 16.0 Req per wave
6 Atomic Req 0.0 0.0 0.0 Req per wave
7 Probe Req 0.0 0.0 0.0 Req per wave
8 Hits 0.0776433773383409 0.0064544677734375 8.00080680847168 Hits per wave
9 Misses 44.43984602739711 8.020265579223633 64.06283569335938 Misses per wave
10 Cache Hit 0.3929601391220619 0.010077842398269183 49.939271322539874 Pct
11 Writeback 0.048735030396969733 0.0004730224609375 8.000154495239258 per wave
12 NC Req 0.0012861240409805389 0.00018310546875 0.09375 Req per wave
13 UC Req 0.029895736785705933 0.0066070556640625 0.427734375 Req per wave
14 CC Req 0.0 0.0 0.0 Req per wave
15 RW Req 44.48417563067225 16.000640869140625 64.076904296875 Req per wave
16 Writeback (Normal) 0.047156282527718 0.0 7.875099182128906 per wave
17 Writeback (TC Req) 0.0007484687302640813 0.0 0.12499427795410156 per wave
18 Evict (Normal) 42.33437258326365 0.0 62.00164794921875 per wave
19 Evict (TC Req) 0.0 0.0 0.0 per wave
@@ -0,0 +1,8 @@
Metric,Avg,Min,Max,Unit
Read - Remote Socket Stall,0.0,0.0,0.0,Req per wave
Read - Peer GCD Stall,0.0,0.0,0.0,Req per wave
Read - HBM Stall,6.544649592416729,0.0,23.859893798828125,Req per wave
Write - Remote Socket Stall,0.0,0.0,0.0,Req per wave
Write - Peer GCD Stall,0.0,0.0,0.0,Req per wave
Write - HBM Stall,0.0024867600309634637,0.0,0.41528892517089844,Req per wave
Write - Credit Starvation,0.0,0.0,0.0,Req per wave
1 Metric Avg Min Max Unit
2 Read - Remote Socket Stall 0.0 0.0 0.0 Req per wave
3 Read - Peer GCD Stall 0.0 0.0 0.0 Req per wave
4 Read - HBM Stall 6.544649592416729 0.0 23.859893798828125 Req per wave
5 Write - Remote Socket Stall 0.0 0.0 0.0 Req per wave
6 Write - Peer GCD Stall 0.0 0.0 0.0 Req per wave
7 Write - HBM Stall 0.0024867600309634637 0.0 0.41528892517089844 Req per wave
8 Write - Credit Starvation 0.0 0.0 0.0 Req per wave
@@ -0,0 +1,17 @@
Channel,Hit Rate,Req,Read Req,Write Req,AtomicReq,EA Read Req,EA Write Req,EA AtomicReq,EA Read Lat - cycles,EA Write Lat - cycles,EA Atomic Lat - cycles,EA Read Stall - IO,EA Read Stall - GMI,EA Read Stall - DRAM,EA Write Stall - IO,EA Write Stall - GMI,EA Write Stall - DRAM,EA Write Stall - Starve
0,0.35953952688975355,1.3952912085070581,1.3922971965310103,0.0029940119760479044,0.0,1.386243260549214,0.0014970516730211452,0.0,570.969501847125,135.13963654673626,,0.0,0.0,0.17990331592674028,0.0,0.0,1.8628057605492142e-05,0.0
1,0.3654665110334509,1.3912592905010293,1.3882652785249814,0.0029940119760479044,0.0,1.3875555735148355,0.0014970059880239522,0.0,459.5942808323869,134.44371032714844,,0.0,0.0,0.17202877570055203,0.0,0.0,1.8308262625140346e-05,0.0
2,0.3568017238180907,1.389967136040419,1.3869731240643712,0.0029940119760479044,0.0,1.3862430778092254,0.0014970059880239522,0.0,432.10194009625326,133.78314971923828,,0.0,0.0,0.1460032206095621,0.0,0.0,2.0147083762163172e-05,0.0
3,0.36043683046723596,1.3899715218001496,1.3869775098241017,0.0029940119760479044,0.0,1.3862431691792196,0.0014970973580183383,0.0,431.9876949781433,223.37428288068355,,0.0,0.0,0.1531682728293413,0.0,0.0,0.0004926784309798372,0.0
4,0.3533882219204135,1.3985119322816768,1.395517920305629,0.0029940119760479044,0.0,1.386243260549214,0.0014970059880239522,0.0,439.5954431182189,135.42496490478516,,0.0,0.0,0.21008236822253928,0.0,0.0,1.768009391373503e-05,0.0
5,0.36273585985372836,1.3899764557798466,1.3869824438037988,0.0029940119760479044,0.0,1.386243260549214,0.0014970059880239522,0.0,446.90540106239695,133.756103515625,,0.0,0.0,0.18641854474644462,0.0,0.0,1.2449161735123502e-05,0.0
6,0.3589398273883731,1.3899715218001496,1.3869775098241017,0.0029940119760479044,0.0,1.3862431691792196,0.0014970059880239522,0.0,442.16025141001927,139.21971893310547,,0.0,0.0,0.1852218719299682,0.0,0.0,1.0107805628976423e-05,0.0
7,0.3602145621489667,1.3899759075598803,1.3869818955838322,0.0029940119760479044,0.0,1.392241095354457,0.0014970973580183383,0.0,440.74157542421574,241.52182636557828,,0.0,0.0,0.30040672439301086,0.0,0.0,0.0005738835134905969,0.0
8,0.354109589338428,1.3906931505945628,1.387699138618515,0.0029940119760479044,0.0,1.386243260549214,0.0014970973580183383,0.0,421.8716549565,133.55741531888924,,0.0,0.0,0.15900133327095808,0.0,0.0,8.406039483532934e-06,0.0
9,0.3604368304672359,1.3899715218001496,1.3869775098241017,0.0029940119760479044,0.0,1.3862431691792196,0.0014970059880239522,0.0,426.3854590889427,133.53572845458984,,0.0,0.0,0.1621015171804828,0.0,0.0,1.0187754374064371e-05,0.0
10,0.3565881786288848,1.3899452072417664,1.3869511952657185,0.0029940119760479044,0.0,1.3862694037888579,0.0014970516730211452,0.0,430.4613038906543,131.8203485001068,,0.0,0.0,0.13873062590639035,0.0,0.0,1.877653384636976e-05,0.0
11,0.3604390230545021,1.389967136040419,1.3869731240643712,0.0029940119760479044,0.0,1.3956271531339177,0.0014970059880239522,0.0,430.32363654990974,128.9033660888672,,0.0,0.0,0.538919140478808,0.0,0.0,2.092372871444611e-05,0.0
12,0.3595841527203406,1.3900158476686764,1.3870218356926285,0.0029940119760479044,0.0,1.3862435346591973,0.0014970059880239522,0.0,429.47851173467126,133.48489379882812,,0.0,0.0,0.14632868052956588,0.0,0.0,1.8319683874438624e-05,0.0
13,0.3640730353860431,1.3899715218001496,1.3869775098241017,0.0029940119760479044,0.0,1.3862431691792196,0.0014970059880239522,0.0,435.6470809336949,133.8506088256836,,0.0,0.0,0.15510385479041916,0.0,0.0,1.3328597931090943e-05,0.0
14,0.6082974782277631,1.3922082592627245,1.3892142472866766,0.0029940119760479044,0.0,1.3862897907188552,0.0014970059880239522,0.0,439.22009070865283,138.74565887451172,,0.0,0.0,0.16263338191780502,0.0,0.0,1.3123015443721932e-05,0.0
15,0.36000958471288586,1.389967136040419,1.3869731240643712,0.0029940119760479044,0.0,1.3862430778092254,0.0014970973580183383,0.0,445.907033496285,141.86062709795544,,0.0,0.0,0.1670199639782934,0.0,0.0,1.908490757742328e-05,0.0
1 Channel Hit Rate Req Read Req Write Req AtomicReq EA Read Req EA Write Req EA AtomicReq EA Read Lat - cycles EA Write Lat - cycles EA Atomic Lat - cycles EA Read Stall - IO EA Read Stall - GMI EA Read Stall - DRAM EA Write Stall - IO EA Write Stall - GMI EA Write Stall - DRAM EA Write Stall - Starve
2 0 0.35953952688975355 1.3952912085070581 1.3922971965310103 0.0029940119760479044 0.0 1.386243260549214 0.0014970516730211452 0.0 570.969501847125 135.13963654673626 0.0 0.0 0.17990331592674028 0.0 0.0 1.8628057605492142e-05 0.0
3 1 0.3654665110334509 1.3912592905010293 1.3882652785249814 0.0029940119760479044 0.0 1.3875555735148355 0.0014970059880239522 0.0 459.5942808323869 134.44371032714844 0.0 0.0 0.17202877570055203 0.0 0.0 1.8308262625140346e-05 0.0
4 2 0.3568017238180907 1.389967136040419 1.3869731240643712 0.0029940119760479044 0.0 1.3862430778092254 0.0014970059880239522 0.0 432.10194009625326 133.78314971923828 0.0 0.0 0.1460032206095621 0.0 0.0 2.0147083762163172e-05 0.0
5 3 0.36043683046723596 1.3899715218001496 1.3869775098241017 0.0029940119760479044 0.0 1.3862431691792196 0.0014970973580183383 0.0 431.9876949781433 223.37428288068355 0.0 0.0 0.1531682728293413 0.0 0.0 0.0004926784309798372 0.0
6 4 0.3533882219204135 1.3985119322816768 1.395517920305629 0.0029940119760479044 0.0 1.386243260549214 0.0014970059880239522 0.0 439.5954431182189 135.42496490478516 0.0 0.0 0.21008236822253928 0.0 0.0 1.768009391373503e-05 0.0
7 5 0.36273585985372836 1.3899764557798466 1.3869824438037988 0.0029940119760479044 0.0 1.386243260549214 0.0014970059880239522 0.0 446.90540106239695 133.756103515625 0.0 0.0 0.18641854474644462 0.0 0.0 1.2449161735123502e-05 0.0
8 6 0.3589398273883731 1.3899715218001496 1.3869775098241017 0.0029940119760479044 0.0 1.3862431691792196 0.0014970059880239522 0.0 442.16025141001927 139.21971893310547 0.0 0.0 0.1852218719299682 0.0 0.0 1.0107805628976423e-05 0.0
9 7 0.3602145621489667 1.3899759075598803 1.3869818955838322 0.0029940119760479044 0.0 1.392241095354457 0.0014970973580183383 0.0 440.74157542421574 241.52182636557828 0.0 0.0 0.30040672439301086 0.0 0.0 0.0005738835134905969 0.0
10 8 0.354109589338428 1.3906931505945628 1.387699138618515 0.0029940119760479044 0.0 1.386243260549214 0.0014970973580183383 0.0 421.8716549565 133.55741531888924 0.0 0.0 0.15900133327095808 0.0 0.0 8.406039483532934e-06 0.0
11 9 0.3604368304672359 1.3899715218001496 1.3869775098241017 0.0029940119760479044 0.0 1.3862431691792196 0.0014970059880239522 0.0 426.3854590889427 133.53572845458984 0.0 0.0 0.1621015171804828 0.0 0.0 1.0187754374064371e-05 0.0
12 10 0.3565881786288848 1.3899452072417664 1.3869511952657185 0.0029940119760479044 0.0 1.3862694037888579 0.0014970516730211452 0.0 430.4613038906543 131.8203485001068 0.0 0.0 0.13873062590639035 0.0 0.0 1.877653384636976e-05 0.0
13 11 0.3604390230545021 1.389967136040419 1.3869731240643712 0.0029940119760479044 0.0 1.3956271531339177 0.0014970059880239522 0.0 430.32363654990974 128.9033660888672 0.0 0.0 0.538919140478808 0.0 0.0 2.092372871444611e-05 0.0
14 12 0.3595841527203406 1.3900158476686764 1.3870218356926285 0.0029940119760479044 0.0 1.3862435346591973 0.0014970059880239522 0.0 429.47851173467126 133.48489379882812 0.0 0.0 0.14632868052956588 0.0 0.0 1.8319683874438624e-05 0.0
15 13 0.3640730353860431 1.3899715218001496 1.3869775098241017 0.0029940119760479044 0.0 1.3862431691792196 0.0014970059880239522 0.0 435.6470809336949 133.8506088256836 0.0 0.0 0.15510385479041916 0.0 0.0 1.3328597931090943e-05 0.0
16 14 0.6082974782277631 1.3922082592627245 1.3892142472866766 0.0029940119760479044 0.0 1.3862897907188552 0.0014970059880239522 0.0 439.22009070865283 138.74565887451172 0.0 0.0 0.16263338191780502 0.0 0.0 1.3123015443721932e-05 0.0
17 15 0.36000958471288586 1.389967136040419 1.3869731240643712 0.0029940119760479044 0.0 1.3862430778092254 0.0014970973580183383 0.0 445.907033496285 141.86062709795544 0.0 0.0 0.1670199639782934 0.0 0.0 1.908490757742328e-05 0.0
@@ -0,0 +1,17 @@
Channel,Hit Rate,Req,Read Req,Write Req,AtomicReq,EA Read Req,EA Write Req,EA AtomicReq,EA Read Lat - cycles,EA Write Lat - cycles,EA Atomic Lat - cycles,EA Read Stall - IO,EA Read Stall - GMI,EA Read Stall - DRAM,EA Write Stall - IO,EA Write Stall - GMI,EA Write Stall - DRAM,EA Write Stall - Starve
16,0.3612977421304405,1.3900109936377245,1.3870169816616766,0.0029940119760479044,0.0,1.3862707743387737,0.0014970516730211452,0.0,431.5294022489758,130.14297811956422,,0.0,0.0,0.15725561815821482,0.0,0.0,1.7874255151805763e-05,0.0
17,0.3670100813688908,1.3899731664600488,1.3869791544840007,0.0029940119760479044,0.0,1.3870952400618684,0.0014970516730211452,0.0,426.9558519873341,129.30576917208336,,0.0,0.0,0.1726041325552021,0.0,0.0,9.5367431640625e-06,0.0
18,0.6083500063563475,1.3922088074826908,1.389214795506643,0.0029940119760479044,0.0,1.3862897678763566,0.0014970059880239522,0.0,432.06957349634496,132.12712860107422,,0.0,0.0,0.14280508806605538,0.0,0.0,1.913059257461639e-05,0.0
19,0.35958077370786723,1.3899583645209581,1.3869643525449102,0.0029940119760479044,0.0,1.3862428950692365,0.0014970059880239522,0.0,437.63221429189986,129.4333038330078,,0.0,0.0,0.1531245979720247,0.0,0.0,1.1329879303892215e-05,0.0
20,0.35392796934398496,1.391509358754415,1.388515346778367,0.0029940119760479044,0.0,1.3875289277402227,0.0014970059880239522,0.0,811.7004301483141,133.68848419189453,,0.0,0.0,0.16598940181161115,0.0,0.0,2.2134381140063624e-05,0.0
21,0.36364641610907317,1.3899890648390718,1.386995052863024,0.0029940119760479044,0.0,1.3862435346591973,0.0014970516730211452,0.0,437.40377162728964,132.78351490738197,,0.0,0.0,0.16326264706914295,0.0,0.0,1.0370494362836826e-05,0.0
22,0.3597969825898013,1.3899802933196108,1.386986281343563,0.0029940119760479044,0.0,1.3862433519192086,0.0014970516730211452,0.0,430.5889922856214,140.03120327138453,,0.0,0.0,0.1757850875397642,0.0,0.0,1.8525266361807634e-05,0.0
23,0.36000958471288586,1.3899759075598803,1.3869818955838322,0.0029940119760479044,0.0,1.3875702383989346,0.0014970516730211452,0.0,441.1934617611169,142.12518691446184,,0.0,0.0,0.23842899528092254,0.0,0.0,1.290601170705464e-05,0.0
24,0.3530550532087085,1.399509132979159,1.396515121003111,0.0029940119760479044,0.0,1.3862430778092254,0.0014970059880239522,0.0,490.291600969767,129.4861068725586,,0.0,0.0,0.13940109892519648,0.0,0.0,1.0861608082662799e-05,0.0
25,0.5100608553897089,1.3912395545822418,1.388245542606194,0.0029940119760479044,0.0,1.3862433519192086,0.0014970059880239522,0.0,427.4452241722763,129.14566040039062,,0.0,0.0,0.14213808710703593,0.0,0.0,9.045629444236527e-06,0.0
26,0.35616109237090826,1.3899539787612276,1.3869599667851797,0.0029940119760479044,0.0,1.3862428036992422,0.0014970059880239522,0.0,428.6962462331467,129.80755615234375,,0.0,0.0,0.18506279676974177,0.0,0.0,9.376845673886602e-06,0.0
27,0.3584118597942073,1.3912483261017028,1.388254314125655,0.0029940119760479044,0.0,1.3971230512607598,0.0014970516730211452,0.0,428.7998139556537,224.08753700143427,,0.0,0.0,0.7622465944575693,0.0,0.0,0.0005312936748573166,0.0
28,0.36065499553685976,1.3900333907075986,1.3870393787315505,0.0029940119760479044,0.0,1.3862439001391749,0.0014971430430155315,0.0,474.67427356944387,133.9064874431662,,0.0,0.0,0.14261485573774327,0.0,0.0,1.805699514057822e-05,0.0
29,0.3640717800237613,1.3899802933196108,1.386986281343563,0.0029940119760479044,0.0,1.3862433519192086,0.0014970516730211452,0.0,449.40416072713805,134.73186548262078,,0.0,0.0,0.17094202098732222,0.0,0.0,1.92333838183009e-05,0.0
30,0.4495893286050978,1.3905197874514643,1.3875257754754164,0.0029940119760479044,0.0,1.386254590428518,0.0014970516730211452,0.0,429.08242578600925,140.09480759254174,,0.0,0.0,0.16488071829972867,0.0,0.0,1.9164856322511227e-05,0.0
31,0.3604382401738407,1.3899715218001496,1.3869775098241017,0.0029940119760479044,0.0,1.3862431691792196,0.0014970516730211452,0.0,434.52128353718905,240.92268607525406,,0.0,0.0,0.1661185989836733,0.0,0.0,0.0005427834516513847,0.0
1 Channel Hit Rate Req Read Req Write Req AtomicReq EA Read Req EA Write Req EA AtomicReq EA Read Lat - cycles EA Write Lat - cycles EA Atomic Lat - cycles EA Read Stall - IO EA Read Stall - GMI EA Read Stall - DRAM EA Write Stall - IO EA Write Stall - GMI EA Write Stall - DRAM EA Write Stall - Starve
2 16 0.3612977421304405 1.3900109936377245 1.3870169816616766 0.0029940119760479044 0.0 1.3862707743387737 0.0014970516730211452 0.0 431.5294022489758 130.14297811956422 0.0 0.0 0.15725561815821482 0.0 0.0 1.7874255151805763e-05 0.0
3 17 0.3670100813688908 1.3899731664600488 1.3869791544840007 0.0029940119760479044 0.0 1.3870952400618684 0.0014970516730211452 0.0 426.9558519873341 129.30576917208336 0.0 0.0 0.1726041325552021 0.0 0.0 9.5367431640625e-06 0.0
4 18 0.6083500063563475 1.3922088074826908 1.389214795506643 0.0029940119760479044 0.0 1.3862897678763566 0.0014970059880239522 0.0 432.06957349634496 132.12712860107422 0.0 0.0 0.14280508806605538 0.0 0.0 1.913059257461639e-05 0.0
5 19 0.35958077370786723 1.3899583645209581 1.3869643525449102 0.0029940119760479044 0.0 1.3862428950692365 0.0014970059880239522 0.0 437.63221429189986 129.4333038330078 0.0 0.0 0.1531245979720247 0.0 0.0 1.1329879303892215e-05 0.0
6 20 0.35392796934398496 1.391509358754415 1.388515346778367 0.0029940119760479044 0.0 1.3875289277402227 0.0014970059880239522 0.0 811.7004301483141 133.68848419189453 0.0 0.0 0.16598940181161115 0.0 0.0 2.2134381140063624e-05 0.0
7 21 0.36364641610907317 1.3899890648390718 1.386995052863024 0.0029940119760479044 0.0 1.3862435346591973 0.0014970516730211452 0.0 437.40377162728964 132.78351490738197 0.0 0.0 0.16326264706914295 0.0 0.0 1.0370494362836826e-05 0.0
8 22 0.3597969825898013 1.3899802933196108 1.386986281343563 0.0029940119760479044 0.0 1.3862433519192086 0.0014970516730211452 0.0 430.5889922856214 140.03120327138453 0.0 0.0 0.1757850875397642 0.0 0.0 1.8525266361807634e-05 0.0
9 23 0.36000958471288586 1.3899759075598803 1.3869818955838322 0.0029940119760479044 0.0 1.3875702383989346 0.0014970516730211452 0.0 441.1934617611169 142.12518691446184 0.0 0.0 0.23842899528092254 0.0 0.0 1.290601170705464e-05 0.0
10 24 0.3530550532087085 1.399509132979159 1.396515121003111 0.0029940119760479044 0.0 1.3862430778092254 0.0014970059880239522 0.0 490.291600969767 129.4861068725586 0.0 0.0 0.13940109892519648 0.0 0.0 1.0861608082662799e-05 0.0
11 25 0.5100608553897089 1.3912395545822418 1.388245542606194 0.0029940119760479044 0.0 1.3862433519192086 0.0014970059880239522 0.0 427.4452241722763 129.14566040039062 0.0 0.0 0.14213808710703593 0.0 0.0 9.045629444236527e-06 0.0
12 26 0.35616109237090826 1.3899539787612276 1.3869599667851797 0.0029940119760479044 0.0 1.3862428036992422 0.0014970059880239522 0.0 428.6962462331467 129.80755615234375 0.0 0.0 0.18506279676974177 0.0 0.0 9.376845673886602e-06 0.0
13 27 0.3584118597942073 1.3912483261017028 1.388254314125655 0.0029940119760479044 0.0 1.3971230512607598 0.0014970516730211452 0.0 428.7998139556537 224.08753700143427 0.0 0.0 0.7622465944575693 0.0 0.0 0.0005312936748573166 0.0
14 28 0.36065499553685976 1.3900333907075986 1.3870393787315505 0.0029940119760479044 0.0 1.3862439001391749 0.0014971430430155315 0.0 474.67427356944387 133.9064874431662 0.0 0.0 0.14261485573774327 0.0 0.0 1.805699514057822e-05 0.0
15 29 0.3640717800237613 1.3899802933196108 1.386986281343563 0.0029940119760479044 0.0 1.3862433519192086 0.0014970516730211452 0.0 449.40416072713805 134.73186548262078 0.0 0.0 0.17094202098732222 0.0 0.0 1.92333838183009e-05 0.0
16 30 0.4495893286050978 1.3905197874514643 1.3875257754754164 0.0029940119760479044 0.0 1.386254590428518 0.0014970516730211452 0.0 429.08242578600925 140.09480759254174 0.0 0.0 0.16488071829972867 0.0 0.0 1.9164856322511227e-05 0.0
17 31 0.3604382401738407 1.3899715218001496 1.3869775098241017 0.0029940119760479044 0.0 1.3862431691792196 0.0014970516730211452 0.0 434.52128353718905 240.92268607525406 0.0 0.0 0.1661185989836733 0.0 0.0 0.0005427834516513847 0.0
@@ -0,0 +1,55 @@
Metric,Value,Alias
Wave Life,33701.0,wave_life_
Active CUs,89/120,active_cu_
SALU,47.0,salu_
SMEM,2.0,smem_
VALU,735.0,valu_
MFMA,,mfma_
VMEM,8.0,vmem_
LDS_Per_Workgroup,0.0,lds_
GWS,0.0,gws_
BR,22.0,br_
VGPR,24.0,vgpr_
SGPR,24.0,sgpr_
LDS_Per_Workgroup Allocation,0.0,lds_alloc_
Scratch Allocation,0.0,scratch_alloc_
Wavefronts,67894.0,wavefronts_
Workgroups,16973.0,workgroups_
LDS_Per_Workgroup Req,0.0,lds_req_
IL1 Fetch,163.0,il1_fetch_
IL1 Hit,100.0,il1_hit_
IL1_L2 Rd,0.0,il1_l2_req_
vL1D Rd,2.0,sl1_rd_
vL1D Hit,98.0,sl1_hit_
vL1D_L2 Rd,0.0,sl1_l2_rd_
vL1D_L2 Wr,0.0,sl1_l2_wr_
vL1D_L2 Atomic,0.0,sl1_l2_atom_
VL1 Rd,279.0,vl1_rd_
VL1 Wr,1.0,vl1_wr_
VL1 Atomic,0.0,vl1_atom_
VL1 Hit,21.0,vl1_hit_
VL1 Lat,1513.0,vl1_lat_
VL1_L2 Rd,44.0,vl1_l2_rd_
VL1_L2 Wr,0.0,vl1_l2_wr_
vL1_L2 Atomic,0.0,vl1_l2_atom_
L2 Rd,44.0,l2_rd_
L2 Wr,0.0,l2_wr_
L2 Atomic,0.0,l2_atom_
L2 Hit,0.0,l2_hit_
L2 Rd Lat,738.0,l2_rd_lat_
L2 Wr Lat,332.0,l2_wr_lat_
Fabric Rd Lat,450.0,fabric_rd_lat_
Fabric Wr Lat,144.0,fabric_wr_lat_
Fabric Atomic Lat,,fabric_atom_lat_
Fabric_L2 Rd,44.0,l2_fabric_rd_
Fabric_L2 Wr,0.0,l2_fabric_wr_
Fabric_l2 Atomic,0.0,l2_fabric_atom_
HBM Rd,44.0,hbm_rd_
HBM Wr,0.0,hbm_wr_
LDS_Per_Workgroup Util,0.0,lds_util_
VL1 Coalesce,70.0,vl1_coales_
VL1 Stall,29.0,vl1_stall_
LDS_Per_Workgroup Lat,,lds_lat_
vL1D Lat,,sl1_lat_
IL1 Lat,,il1_lat_
Wave Occupancy,37.0,wave_occ_
1 Metric Value Alias
2 Wave Life 33701.0 wave_life_
3 Active CUs 89/120 active_cu_
4 SALU 47.0 salu_
5 SMEM 2.0 smem_
6 VALU 735.0 valu_
7 MFMA mfma_
8 VMEM 8.0 vmem_
9 LDS_Per_Workgroup 0.0 lds_
10 GWS 0.0 gws_
11 BR 22.0 br_
12 VGPR 24.0 vgpr_
13 SGPR 24.0 sgpr_
14 LDS_Per_Workgroup Allocation 0.0 lds_alloc_
15 Scratch Allocation 0.0 scratch_alloc_
16 Wavefronts 67894.0 wavefronts_
17 Workgroups 16973.0 workgroups_
18 LDS_Per_Workgroup Req 0.0 lds_req_
19 IL1 Fetch 163.0 il1_fetch_
20 IL1 Hit 100.0 il1_hit_
21 IL1_L2 Rd 0.0 il1_l2_req_
22 vL1D Rd 2.0 sl1_rd_
23 vL1D Hit 98.0 sl1_hit_
24 vL1D_L2 Rd 0.0 sl1_l2_rd_
25 vL1D_L2 Wr 0.0 sl1_l2_wr_
26 vL1D_L2 Atomic 0.0 sl1_l2_atom_
27 VL1 Rd 279.0 vl1_rd_
28 VL1 Wr 1.0 vl1_wr_
29 VL1 Atomic 0.0 vl1_atom_
30 VL1 Hit 21.0 vl1_hit_
31 VL1 Lat 1513.0 vl1_lat_
32 VL1_L2 Rd 44.0 vl1_l2_rd_
33 VL1_L2 Wr 0.0 vl1_l2_wr_
34 vL1_L2 Atomic 0.0 vl1_l2_atom_
35 L2 Rd 44.0 l2_rd_
36 L2 Wr 0.0 l2_wr_
37 L2 Atomic 0.0 l2_atom_
38 L2 Hit 0.0 l2_hit_
39 L2 Rd Lat 738.0 l2_rd_lat_
40 L2 Wr Lat 332.0 l2_wr_lat_
41 Fabric Rd Lat 450.0 fabric_rd_lat_
42 Fabric Wr Lat 144.0 fabric_wr_lat_
43 Fabric Atomic Lat fabric_atom_lat_
44 Fabric_L2 Rd 44.0 l2_fabric_rd_
45 Fabric_L2 Wr 0.0 l2_fabric_wr_
46 Fabric_l2 Atomic 0.0 l2_fabric_atom_
47 HBM Rd 44.0 hbm_rd_
48 HBM Wr 0.0 hbm_wr_
49 LDS_Per_Workgroup Util 0.0 lds_util_
50 VL1 Coalesce 70.0 vl1_coales_
51 VL1 Stall 29.0 vl1_stall_
52 LDS_Per_Workgroup Lat lds_lat_
53 vL1D Lat sl1_lat_
54 IL1 Lat il1_lat_
55 Wave Occupancy 37.0 wave_occ_
@@ -0,0 +1,168 @@
Dispatch_ID,Kernel_Name,GPU_ID
0,__amd_rocclr_fillBuffer.kd,0
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0
1 Dispatch_ID Kernel_Name GPU_ID
2 0 __amd_rocclr_fillBuffer.kd 0
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0
5 3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0
10 8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0
15 13 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0
20 18 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0
25 23 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0
30 28 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0
35 33 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0
40 38 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0
45 43 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0
50 48 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0
55 53 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0
60 58 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0
65 63 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0
70 68 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0
75 73 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0
80 78 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0
85 83 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0
90 88 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0
95 93 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0
100 98 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0
105 103 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0
110 108 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0
115 113 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0
120 118 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0
125 123 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0
130 128 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0
135 133 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0
140 138 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0
145 143 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0
150 148 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0
155 153 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0
160 158 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0
165 163 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0
@@ -0,0 +1,30 @@
Metric,Value,Unit,Peak,PoP
VALU FLOPs,,Gflops,23070.72,
VALU IOPs,,Gops,23070.72,
MFMA FLOPs (BF16),,Gflops,92282.88,
MFMA FLOPs (F16),,Gflops,184565.76,
MFMA FLOPs (F32),,Gflops,46141.44,
MFMA FLOPs (F64),,Gflops,46141.44,
MFMA IOPs (Int8),,Gops,184565.76,
Active CUs,89,Cus,120,74.16666666666667
SALU Util,2.1142315362209505,Pct,100,2.1142315362209505
VALU Util,59.27505815065561,Pct,100,59.27505815065561
MFMA Util,,Pct,100,
VALU Active Threads/Wave,63.96805399754944,Threads,64,99.950084371171
IPC - Issue,0.8437287060051507,Instr/cycle,5,16.874574120103013
LDS_Per_Workgroup BW,0.0,Gb/sec,23070.72,0.0
LDS_Per_Workgroup Bank Conflict,,Conflicts/access,32,
Instr Cache Hit Rate,99.99351101937752,Pct,100,99.99351101937752
Instr Cache BW,1410.0001369988809,Gb/s,4614.144,30.558217017043262
Scalar L1D Cache Hit Rate,99.3562044853034,Pct,100,99.3562044853034
Scalar L1D Cache BW,43.047065285053684,Gb/s,4614.144,0.9329371880256377
Vector L1D Cache Hit Rate,20.508982035928145,Pct,100,20.508982035928145
Vector L1D Cache BW,1219.6973641978805,Gb/s,11535.36,10.573552660670153
L2 Cache Hit Rate,0.3929601391220619,Pct,100,0.3929601391220619
L2-Fabric Read BW,837.9967513054252,Gb/s,1228.8,68.19635020389202
L2-Fabric Write BW,4.968599175317518,Gb/s,1228.8,0.40434563601216783
L2-Fabric Read Latency,449.8986946067636,Cycles,,
L2-Fabric Write Latency,144.17015133113895,Cycles,,
Wave Occupancy,3303.5573155153597,Wavefronts,4800,68.82411073990332
Instr Fetch BW,683.181314670256,Gb/s,2307.072,29.612483471268167
Instr Fetch Latency,18.659688472420168,Cycles,,
1 Metric Value Unit Peak PoP
2 VALU FLOPs Gflops 23070.72
3 VALU IOPs Gops 23070.72
4 MFMA FLOPs (BF16) Gflops 92282.88
5 MFMA FLOPs (F16) Gflops 184565.76
6 MFMA FLOPs (F32) Gflops 46141.44
7 MFMA FLOPs (F64) Gflops 46141.44
8 MFMA IOPs (Int8) Gops 184565.76
9 Active CUs 89 Cus 120 74.16666666666667
10 SALU Util 2.1142315362209505 Pct 100 2.1142315362209505
11 VALU Util 59.27505815065561 Pct 100 59.27505815065561
12 MFMA Util Pct 100
13 VALU Active Threads/Wave 63.96805399754944 Threads 64 99.950084371171
14 IPC - Issue 0.8437287060051507 Instr/cycle 5 16.874574120103013
15 LDS_Per_Workgroup BW 0.0 Gb/sec 23070.72 0.0
16 LDS_Per_Workgroup Bank Conflict Conflicts/access 32
17 Instr Cache Hit Rate 99.99351101937752 Pct 100 99.99351101937752
18 Instr Cache BW 1410.0001369988809 Gb/s 4614.144 30.558217017043262
19 Scalar L1D Cache Hit Rate 99.3562044853034 Pct 100 99.3562044853034
20 Scalar L1D Cache BW 43.047065285053684 Gb/s 4614.144 0.9329371880256377
21 Vector L1D Cache Hit Rate 20.508982035928145 Pct 100 20.508982035928145
22 Vector L1D Cache BW 1219.6973641978805 Gb/s 11535.36 10.573552660670153
23 L2 Cache Hit Rate 0.3929601391220619 Pct 100 0.3929601391220619
24 L2-Fabric Read BW 837.9967513054252 Gb/s 1228.8 68.19635020389202
25 L2-Fabric Write BW 4.968599175317518 Gb/s 1228.8 0.40434563601216783
26 L2-Fabric Read Latency 449.8986946067636 Cycles
27 L2-Fabric Write Latency 144.17015133113895 Cycles
28 Wave Occupancy 3303.5573155153597 Wavefronts 4800 68.82411073990332
29 Instr Fetch BW 683.181314670256 Gb/s 2307.072 29.612483471268167
30 Instr Fetch Latency 18.659688472420168 Cycles
@@ -0,0 +1,9 @@
Metric,Avg,Min,Max,Unit
GPU Busy Cycles,617647.8802395209,29252,9086511,Cycles/kernel
CPF Busy,617647.8802395209,29252,9086511,Cycles/kernel
CPF Util,100.0,100.0,100.0,Pct
CPF Stall,0.0013238950114949502,0.0,0.05621295459558693,Cycles/kernel
L2Cache Intf Busy,4424.275449101797,4070,6721,Cycles/kernel
L2Cache Intf Util,1.3820129131011347,0.047288665775111524,15.514721998977132,Pct
L2Cache Intf Stall,0.0,0.0,0.0,Pct
UTCL1 Stall,8.51497005988024,0,158,Cycles/kernel
1 Metric Avg Min Max Unit
2 GPU Busy Cycles 617647.8802395209 29252 9086511 Cycles/kernel
3 CPF Busy 617647.8802395209 29252 9086511 Cycles/kernel
4 CPF Util 100.0 100.0 100.0 Pct
5 CPF Stall 0.0013238950114949502 0.0 0.05621295459558693 Cycles/kernel
6 L2Cache Intf Busy 4424.275449101797 4070 6721 Cycles/kernel
7 L2Cache Intf Util 1.3820129131011347 0.047288665775111524 15.514721998977132 Pct
8 L2Cache Intf Stall 0.0 0.0 0.0 Pct
9 UTCL1 Stall 8.51497005988024 0 158 Cycles/kernel
@@ -0,0 +1,13 @@
Metric,Avg,Min,Max,Unit
GPU Busy Cycles,617647.8802395209,29252,9086511,Cycles
CPC Busy Cycles,613885.2754491018,29252,9023540,Cycles
CPC Util,99.47486127900184,77.89692394173777,100.0,Pct
CPC Stall Cycles,14587.299401197604,11162,71529,Cycles
CPC Stall Rate,4.05020731065374,0.7254863080219156,40.48953917680842,Pct
CPC Packet Decoding,45016.7245508982,14401,472917,Cycles
SPI Intf Busy Cycles,561853.5988023952,694,8537397,Cycles
SPI Intf Util,88.36404447687384,2.3724873512922193,97.00206536094642,Pct
L2Cache Intf Util,0.23792982867321724,0.008517015875321452,2.3058296288264843,Pct
UTCL1 Stall Cycles,2074.5988023952095,1928,2545,Cycles
UTCL2 Intf Busy Cycles,2592.011976047904,2384,3506,Cycles
UTCL2 Intf Util,0.8264968648331307,0.032164736268969825,9.740988951276943,Pct
1 Metric Avg Min Max Unit
2 GPU Busy Cycles 617647.8802395209 29252 9086511 Cycles
3 CPC Busy Cycles 613885.2754491018 29252 9023540 Cycles
4 CPC Util 99.47486127900184 77.89692394173777 100.0 Pct
5 CPC Stall Cycles 14587.299401197604 11162 71529 Cycles
6 CPC Stall Rate 4.05020731065374 0.7254863080219156 40.48953917680842 Pct
7 CPC Packet Decoding 45016.7245508982 14401 472917 Cycles
8 SPI Intf Busy Cycles 561853.5988023952 694 8537397 Cycles
9 SPI Intf Util 88.36404447687384 2.3724873512922193 97.00206536094642 Pct
10 L2Cache Intf Util 0.23792982867321724 0.008517015875321452 2.3058296288264843 Pct
11 UTCL1 Stall Cycles 2074.5988023952095 1928 2545 Cycles
12 UTCL2 Intf Busy Cycles 2592.011976047904 2384 3506 Cycles
13 UTCL2 Intf Util 0.8264968648331307 0.032164736268969825 9.740988951276943 Pct
@@ -0,0 +1,9 @@
Metric,Avg,Min,Max,Unit
GPU Busy,617647.8802395209,29252,9086511,Cycles
CS Busy,4770921.808383234,87929,72542635,Cycles
SPI Busy,596640.6946107785,11567,9068905,Cycles
SQ Busy,4753722.874251497,75154,72528061,Cycles
Dispatched Workgroups,16973.413173652694,128,131072,Workgroups
Dispatched Wavefronts,67893.65269461078,512,524288,Wavefronts
Wave Alloc Failed,285847.15568862273,114,1628686,Cycles
Wave Alloc Failed - CS,333804.0658682635,626,1073884,Cycles
1 Metric Avg Min Max Unit
2 GPU Busy 617647.8802395209 29252 9086511 Cycles
3 CS Busy 4770921.808383234 87929 72542635 Cycles
4 SPI Busy 596640.6946107785 11567 9068905 Cycles
5 SQ Busy 4753722.874251497 75154 72528061 Cycles
6 Dispatched Workgroups 16973.413173652694 128 131072 Workgroups
7 Dispatched Wavefronts 67893.65269461078 512 524288 Wavefronts
8 Wave Alloc Failed 285847.15568862273 114 1628686 Cycles
9 Wave Alloc Failed - CS 333804.0658682635 626 1073884 Cycles
@@ -0,0 +1,15 @@
Metric,Avg,Min,Max,Unit
Wave request Failed (CS),333804.0658682635,626,1073884,Cycles
CS Stall,17938.610778443115,0,645839,Cycles
CS Stall Rate,4.714904919206833,0.0,71.47929295332877,Pct
Scratch Stall,0.0,0,0,Cycles
Insufficient SIMD Waveslots,52552.071856287424,0,795555,Simd
Insufficient SIMD VGPRs,609426.6347305389,0,29972781,Simd
Insufficient SIMD SGPRs,0.0,0,0,Simd
Insufficient CU LDS_Per_Workgroup,0.0,0,0,Cu
Insufficient CU Barries,0.0,0,0,Cu
Insufficient Bulky Resource,0.0,0,0,Cu
Reach CU Threadgroups Limit,0.0,0,0,Cycles
Reach CU Wave Limit,0.0,0,0,Cycles
VGPR Writes,4.0,4.0,4.0,Cycles/wave
SGPR Writes,5.005988023952096,5.0,6.0,Cycles/wave
1 Metric Avg Min Max Unit
2 Wave request Failed (CS) 333804.0658682635 626 1073884 Cycles
3 CS Stall 17938.610778443115 0 645839 Cycles
4 CS Stall Rate 4.714904919206833 0.0 71.47929295332877 Pct
5 Scratch Stall 0.0 0 0 Cycles
6 Insufficient SIMD Waveslots 52552.071856287424 0 795555 Simd
7 Insufficient SIMD VGPRs 609426.6347305389 0 29972781 Simd
8 Insufficient SIMD SGPRs 0.0 0 0 Simd
9 Insufficient CU LDS_Per_Workgroup 0.0 0 0 Cu
10 Insufficient CU Barries 0.0 0 0 Cu
11 Insufficient Bulky Resource 0.0 0 0 Cu
12 Reach CU Threadgroups Limit 0.0 0 0 Cycles
13 Reach CU Wave Limit 0.0 0 0 Cycles
14 VGPR Writes 4.0 4.0 4.0 Cycles/wave
15 SGPR Writes 5.005988023952096 5.0 6.0 Cycles/wave
@@ -0,0 +1,10 @@
Metric,Avg,Min,Max,Unit
Grid Size,4345193.77245509,32768,33554432,Work items
Workgroup Size,256.0,256,256,Work items
Total Wavefronts,67893.65269461078,512,524288,Wavefronts
Saved Wavefronts,0.0,0,0,Wavefronts
Restored Wavefronts,0.0,0,0,Wavefronts
VGPRs,23.976047904191617,8,36,Registers
SGPRs,24.047904191616766,24,32,Registers
LDS_Per_Workgroup Allocation,0.0,0,0,Bytes
Scratch Allocation,0.0,0,0,Bytes
1 Metric Avg Min Max Unit
2 Grid Size 4345193.77245509 32768 33554432 Work items
3 Workgroup Size 256.0 256 256 Work items
4 Total Wavefronts 67893.65269461078 512 524288 Wavefronts
5 Saved Wavefronts 0.0 0 0 Wavefronts
6 Restored Wavefronts 0.0 0 0 Wavefronts
7 VGPRs 23.976047904191617 8 36 Registers
8 SGPRs 24.047904191616766 24 32 Registers
9 LDS_Per_Workgroup Allocation 0.0 0 0 Bytes
10 Scratch Allocation 0.0 0 0 Bytes
@@ -0,0 +1,9 @@
Metric,Avg,Min,Max,Unit
Kernel Time (Nanosec),395047.60479041917,6720,6057561,Ns
Kernel Time (Cycles),617647.8802395209,29252,9086511,Cycle
Instr/wavefront,842.5329341317365,62.0,20596.0,Instr/wavefront
Wave Cycles,33701.426573519224,2837.008590698242,547911.8947753906,Cycles/wave
Dependency Wait Cycles,4403.9484733535855,937.2289428710938,26312.92041015625,Cycles/wave
Issue Wait Cycles,25397.85530693374,129.21875,443282.9743652344,Cycles/wave
Active Cycles,3899.6230088650823,248.0,78316.0,Cycles/wave
Wavefront Occupancy,3303.5573155153597,159.4041712249003,3951.9657239313624,Wavefronts
1 Metric Avg Min Max Unit
2 Kernel Time (Nanosec) 395047.60479041917 6720 6057561 Ns
3 Kernel Time (Cycles) 617647.8802395209 29252 9086511 Cycle
4 Instr/wavefront 842.5329341317365 62.0 20596.0 Instr/wavefront
5 Wave Cycles 33701.426573519224 2837.008590698242 547911.8947753906 Cycles/wave
6 Dependency Wait Cycles 4403.9484733535855 937.2289428710938 26312.92041015625 Cycles/wave
7 Issue Wait Cycles 25397.85530693374 129.21875 443282.9743652344 Cycles/wave
8 Active Cycles 3899.6230088650823 248.0 78316.0 Cycles/wave
9 Wavefront Occupancy 3303.5573155153597 159.4041712249003 3951.9657239313624 Wavefronts
@@ -0,0 +1,2 @@
workload_name,host_name,host_cpu,host_distro,host_kernel,host_rocmver,date,gpu_soc,numSE,numCU,numSIMD,waveSize,maxWavesPerCU,maxWorkgroupSize,L1,L2,sclk,mclk,cur_sclk,cur_mclk,L2Banks,name,numSQC,numPipes,hbmBW,ip_blocks
dev01p3,vesuvius,AMD EPYC 7542 32-Core Processor,,4.18.0-240.15.1.el8_3.x86_64,4.2.0-21,Thu Sep 22 11:34:46 2022 (CDT),gfx908,8,120,4,64,40,1024,16,,1502,1200,300,1200,32,mi100,48,4,1228.8,SQ|LDS_Per_Workgroup|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF
1 workload_name host_name host_cpu host_distro host_kernel host_rocmver date gpu_soc numSE numCU numSIMD waveSize maxWavesPerCU maxWorkgroupSize L1 L2 sclk mclk cur_sclk cur_mclk L2Banks name numSQC numPipes hbmBW ip_blocks
2 dev01p3 vesuvius AMD EPYC 7542 32-Core Processor 4.18.0-240.15.1.el8_3.x86_64 4.2.0-21 Thu Sep 22 11:34:46 2022 (CDT) gfx908 8 120 4 64 40 1024 16 1502 1200 300 1200 32 mi100 48 4 1228.8 SQ|LDS_Per_Workgroup|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF
@@ -0,0 +1,168 @@
Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,grd,Workgroup_Size,LDS_Per_Workgroup,scr,vgpr,SGPR,fbar,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs
0,"__amd_rocclr_fillBuffer.kd",0,0,0,932098,932103,33554432,256,0,0,8,32,6464,0x0,0x7fa24b804180,12076540386173827,12076540386221406,12076540386544923,12076540386650935
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,932098,932103,32768,256,0,0,24,24,12480,0x0,0x7fa24b835100,12076540401083130,12076540401193523,12076540401200243,12076540401205969
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,932098,932103,4194304,256,0,0,24,24,12928,0x7fa37b76c900,0x7fa24b835140,12076540401247406,12076540401262003,12076540401399282,12076540401402695
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,932098,932103,4194304,256,0,0,36,24,13632,0x7fa37b76c800,0x7fa24b835180,12076540401444472,12076540401457521,12076540401703919,12076540401799793
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,932098,932103,4194304,256,0,0,28,24,14080,0x7fa37b76c700,0x7fa24b8351c0,12076540401826413,12076540401838798,12076540402084556,12076540402186092
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,932098,932103,4194304,256,0,0,24,24,14528,0x7fa37b76c600,0x7fa24b835200,12076540402210087,12076540402221835,12076540402347114,12076540402350528
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,932098,932103,4194304,256,0,0,24,24,14976,0x7fa37b76c500,0x7fa24b835240,12076540402377959,12076540402389514,12076540402514153,12076540402517328
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,932098,932103,4194304,256,0,0,24,24,15424,0x7fa37b76c400,0x7fa24b835280,12076540402573472,12076540402591432,12076540402714951,12076540402718081
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,932098,932103,4194304,256,0,0,28,24,16128,0x7fa37b76c300,0x7fa24b8352c0,12076540402744971,12076540402757991,12076540403006309,12076540403102807
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,932098,932103,4194304,256,0,0,28,24,16832,0x7fa37b76ca00,0x7fa24b835300,12076540403124207,12076540403136068,12076540403378626,12076540403474108
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,932098,932103,4194304,256,0,0,24,24,17536,0x7fa37b76c900,0x7fa24b835340,12076540403501368,12076540403513344,12076540403637983,12076540403641259
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,932098,932103,4194304,256,0,0,24,24,18240,0x7fa37b76c800,0x7fa24b835380,12076540403671585,12076540403683423,12076540403808062,12076540403811215
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,932098,932103,4194304,256,0,0,24,24,18944,0x7fa37b76c700,0x7fa24b8353c0,12076540403853794,12076540403865982,12076540403990941,12076540403994165
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,932098,932103,4194304,256,0,0,28,24,19904,0x7fa37b76c600,0x7fa24b835400,12076540404030533,12076540404041500,12076540404291578,12076540404388158
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,932098,932103,4194304,256,0,0,28,24,20608,0x7fa37b76c500,0x7fa24b835440,12076540404410650,12076540404422137,12076540404668375,12076540404734953
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,932098,932103,4194304,256,0,0,24,24,21312,0x7fa37b76c400,0x7fa24b835480,12076540404756443,12076540404768374,12076540404892693,12076540404895913
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,932098,932103,4194304,256,0,0,24,24,22016,0x7fa37b76c300,0x7fa24b8354c0,12076540404924496,12076540404936053,12076540405061492,12076540405064686
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,932098,932103,4194304,256,0,0,24,24,22720,0x7fa37b76ca00,0x7fa24b835500,12076540405102136,12076540405113491,12076540405238610,12076540405241916
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,932098,932103,4194304,256,0,0,28,24,23680,0x7fa37b76c900,0x7fa24b835540,12076540405267634,12076540405279410,12076540405525328,12076540405568243
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,932098,932103,4194304,256,0,0,28,24,24384,0x7fa37b76c800,0x7fa24b835580,12076540405589843,12076540405601168,12076540405847246,12076540405887176
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,932098,932103,4194304,256,0,0,24,24,25088,0x7fa37b76c700,0x7fa24b8355c0,12076540405908506,12076540405920365,12076540406045004,12076540406048446
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,932098,932103,4194304,256,0,0,24,24,25792,0x7fa37b76c600,0x7fa24b835600,12076540406075627,12076540406087084,12076540406212363,12076540406215527
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,932098,932103,4194304,256,0,0,24,24,26496,0x7fa37b76c500,0x7fa24b835640,12076540406251805,12076540406265642,12076540406390441,12076540406393769
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,932098,932103,4194304,256,0,0,28,24,27712,0x7fa37b76c400,0x7fa24b835680,12076540406420258,12076540406433641,12076540406681959,12076540406747416
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,932098,932103,4194304,256,0,0,28,24,28416,0x7fa37b76c300,0x7fa24b8356c0,12076540406767334,12076540406780518,12076540407025476,12076540407091987
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,932098,932103,4194304,256,0,0,24,24,29120,0x7fa37b76ca00,0x7fa24b835700,12076540407114048,12076540407127075,12076540407251714,12076540407254860
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,932098,932103,4194304,256,0,0,24,24,30080,0x7fa37b76c900,0x7fa24b835740,12076540407280919,12076540407292194,12076540407417153,12076540407420338
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,932098,932103,4194304,256,0,0,24,24,30784,0x7fa37b76c800,0x7fa24b835780,12076540407456515,12076540407468672,12076540407593311,12076540407596656
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,932098,932103,4194304,256,0,0,28,24,32000,0x7fa37b76c700,0x7fa24b8357c0,12076540407621933,12076540407633951,12076540407880669,12076540407901854
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,932098,932103,4194304,256,0,0,28,24,32960,0x7fa37b76c600,0x7fa24b835800,12076540407922542,12076540407934109,12076540408178267,12076540408225095
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,932098,932103,4194304,256,0,0,24,24,33920,0x7fa37b76c500,0x7fa24b835840,12076540408245032,12076540408258746,12076540408384185,12076540408387197
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,932098,932103,4194304,256,0,0,24,24,34880,0x7fa37b76c400,0x7fa24b835880,12076540408412634,12076540408424185,12076540408549784,12076540408552995
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,932098,932103,4194304,256,0,0,24,24,35840,0x7fa37b76c300,0x7fa24b8358c0,12076540408589162,12076540408602103,12076540408727062,12076540408730535
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,932098,932103,4194304,256,0,0,28,24,37312,0x7fa37b76ca00,0x7fa24b835900,12076540408756053,12076540408768662,12076540409019380,12076540409046954
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,932098,932103,4194304,256,0,0,28,24,38272,0x7fa37b76c900,0x7fa24b835940,12076540409066591,12076540409079699,12076540409323057,12076540409399740
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,932098,932103,4194304,256,0,0,24,24,39232,0x7fa37b76c800,0x7fa24b835980,12076540409420138,12076540409432816,12076540409557615,12076540409561211
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,932098,932103,4194304,256,0,0,24,24,40192,0x7fa37b76c700,0x7fa24b8359c0,12076540409587960,12076540409599215,12076540409724974,12076540409728361
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,932098,932103,4194304,256,0,0,24,24,41152,0x7fa37b76c600,0x7fa24b835a00,12076540409763156,12076540409776494,12076540409900493,12076540409903898
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,932098,932103,4194304,256,0,0,28,24,42624,0x7fa37b76c500,0x7fa24b835a40,12076540409930127,12076540409943852,12076540410191850,12076540410228722
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,932098,932103,4194304,256,0,0,28,24,43584,0x7fa37b76c400,0x7fa24b835a80,12076540410249972,12076540410262890,12076540410511208,12076540410540242
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,932098,932103,4194304,256,0,0,24,24,44544,0x7fa37b76c300,0x7fa24b835ac0,12076540410562503,12076540410576007,12076540410700646,12076540410703886
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,932098,932103,4194304,256,0,0,24,24,45760,0x7fa37b76ca00,0x7fa24b835b00,12076540410728812,12076540410741126,12076540410867365,12076540410870506
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,932098,932103,4194304,256,0,0,24,24,46720,0x7fa37b76c900,0x7fa24b835b40,12076540410904900,12076540410916324,12076540411041283,12076540411044530
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,932098,932103,4194304,256,0,0,28,24,48448,0x7fa37b76c800,0x7fa24b835b80,12076540411071279,12076540411084003,12076540411343361,12076540411367771
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,932098,932103,4194304,256,0,0,28,24,49408,0x7fa37b76c700,0x7fa24b835bc0,12076540411388309,12076540411400640,12076540411648958,12076540411672698
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,932098,932103,4194304,256,0,0,24,24,50368,0x7fa37b76c600,0x7fa24b835c00,12076540411692495,12076540411705598,12076540411830557,12076540411833758
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,932098,932103,4194304,256,0,0,24,24,51584,0x7fa37b76c500,0x7fa24b835c40,12076540411860127,12076540411871997,12076540411998396,12076540412004345
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,932098,932103,4194304,256,0,0,24,24,52544,0x7fa37b76c400,0x7fa24b835c80,12076540412038969,12076540412052315,12076540412178074,12076540412181254
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,932098,932103,4194304,256,0,0,28,24,54272,0x7fa37b76c300,0x7fa24b835cc0,12076540412207333,12076540412219994,12076540412475992,12076540412499686
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,932098,932103,4194304,256,0,0,28,24,55488,0x7fa37b76ca00,0x7fa24b835d00,12076540412521808,12076540412534231,12076540412777589,12076540412805065
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,932098,932103,4194304,256,0,0,24,24,56704,0x7fa37b76c900,0x7fa24b835d40,12076540412826154,12076540412839349,12076540412964628,12076540412967787
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,932098,932103,4194304,256,0,0,24,24,58176,0x7fa37b76c800,0x7fa24b835d80,12076540412992724,12076540413005427,12076540413133906,12076540413137202
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,932098,932103,4194304,256,0,0,24,24,59392,0x7fa37b76c700,0x7fa24b835dc0,12076540413173951,12076540413186226,12076540413310865,12076540413313921
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,932098,932103,4194304,256,0,0,28,24,61376,0x7fa37b76c600,0x7fa24b835e00,12076540413340140,12076540413353905,12076540413617902,12076540413645127
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,932098,932103,4194304,256,0,0,28,24,62592,0x7fa37b76c500,0x7fa24b835e40,12076540413665505,12076540413678382,12076540413923980,12076540413943142
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,932098,932103,4194304,256,0,0,24,24,63808,0x7fa37b76c400,0x7fa24b835e80,12076540413970773,12076540413984299,12076540414109578,12076540414112957
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,932098,932103,4194304,256,0,0,24,24,65280,0x7fa37b76c300,0x7fa24b835ec0,12076540414141060,12076540414153738,12076540414283337,12076540414286610
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,932098,932103,4194304,256,0,0,24,24,66496,0x7fa37b76ca00,0x7fa24b835f00,12076540414322748,12076540414334057,12076540414459176,12076540414462327
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,932098,932103,4194304,256,0,0,28,24,68480,0x7fa37b76c900,0x7fa24b835f40,12076540414488045,12076540414500615,12076540414756933,12076540414779597
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,932098,932103,4194304,256,0,0,28,24,69696,0x7fa37b76c800,0x7fa24b835f80,12076540414800396,12076540414811653,12076540415061731,12076540415089103
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,932098,932103,4194304,256,0,0,24,24,70912,0x7fa37b76c700,0x7fa24b835fc0,12076540415111024,12076540415122850,12076540415247489,12076540415250674
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,932098,932103,4194304,256,0,0,24,24,72384,0x7fa37b76c600,0x7fa24b836000,12076540415277353,12076540415290369,12076540415427488,12076540415430729
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,932098,932103,4194304,256,0,0,24,24,73600,0x7fa37b76c500,0x7fa24b836040,12076540415467918,12076540415480447,12076540415604606,12076540415607708
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,932098,932103,4194304,256,0,0,28,24,75840,0x7fa37b76c400,0x7fa24b836080,12076540415633856,12076540415646686,12076540415902844,12076540415925509
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,932098,932103,4194304,256,0,0,28,24,77056,0x7fa37b76c300,0x7fa24b8360c0,12076540415946348,12076540415959163,12076540416203801,12076540416230777
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,932098,932103,4194304,256,0,0,24,24,78272,0x7fa37b76ca00,0x7fa24b836100,12076540416251545,12076540416264121,12076540416389400,12076540416392588
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,932098,932103,4194304,256,0,0,24,24,80000,0x7fa37b76c900,0x7fa24b836140,12076540416417754,12076540416430680,12076540416572758,12076540416576059
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,932098,932103,4194304,256,0,0,24,24,81216,0x7fa37b76c800,0x7fa24b836180,12076540416610393,12076540416622518,12076540416747157,12076540416750413
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,932098,932103,4194304,256,0,0,28,24,83456,0x7fa37b76c700,0x7fa24b8361c0,12076540416775430,12076540416787477,12076540417050355,12076540417074186
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,932098,932103,4194304,256,0,0,28,24,84928,0x7fa37b76c600,0x7fa24b836200,12076540417096307,12076540417108434,12076540417356112,12076540417382219
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,932098,932103,4194304,256,0,0,24,24,86400,0x7fa37b76c500,0x7fa24b836240,12076540417405532,12076540417418352,12076540417543470,12076540417547145
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,932098,932103,4194304,256,0,0,24,24,88128,0x7fa37b76c400,0x7fa24b836280,12076540417573023,12076540417584270,12076540417734669,12076540417737900
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,932098,932103,4194304,256,0,0,24,24,89600,0x7fa37b76c300,0x7fa24b8362c0,12076540417788534,12076540417802188,12076540417927627,12076540417931210
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,932098,932103,4194304,256,0,0,28,24,92096,0x7fa37b76ca00,0x7fa24b836300,12076540417957489,12076540417969707,12076540418227945,12076540418255663
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,932098,932103,4194304,256,0,0,28,24,93568,0x7fa37b76c900,0x7fa24b836340,12076540418276923,12076540418289544,12076540418536422,12076540418562494
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,932098,932103,4194304,256,0,0,24,24,95040,0x7fa37b76c800,0x7fa24b836380,12076540418583633,12076540418596902,12076540418722661,12076540418725888
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,932098,932103,4194304,256,0,0,24,24,96768,0x7fa37b76c700,0x7fa24b8363c0,12076540418752057,12076540418763141,12076540418920419,12076540418923536
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,932098,932103,4194304,256,0,0,24,24,98240,0x7fa37b76c600,0x7fa24b836400,12076540418959793,12076540418972259,12076540419097538,12076540419101066
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,932098,932103,4194304,256,0,0,28,24,100736,0x7fa37b76c500,0x7fa24b836440,12076540419127214,12076540419138658,12076540419401215,12076540419427723
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,932098,932103,4194304,256,0,0,28,24,102208,0x7fa37b76c400,0x7fa24b836480,12076540419448182,12076540419460575,12076540419708093,12076540419730847
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,932098,932103,4194304,256,0,0,24,24,103680,0x7fa37b76c300,0x7fa24b8364c0,12076540419751025,12076540419764252,12076540419890811,12076540419893941
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,932098,932103,4194304,256,0,0,24,24,105664,0x7fa37b76ca00,0x7fa24b836500,12076540419918857,12076540419930171,12076540420095290,12076540420098742
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,932098,932103,4194304,256,0,0,24,24,107136,0x7fa37b76c900,0x7fa24b836540,12076540420135400,12076540420150489,12076540420276408,12076540420279859
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,932098,932103,4194304,256,0,0,28,24,109888,0x7fa37b76c800,0x7fa24b836580,12076540420305276,12076540420318008,12076540420571606,12076540420594534
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,932098,932103,4194304,256,0,0,28,24,111360,0x7fa37b76c700,0x7fa24b8365c0,12076540420615002,12076540420627125,12076540420872403,12076540420899311
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,932098,932103,4194304,256,0,0,24,24,112832,0x7fa37b76c600,0x7fa24b836600,12076540420921983,12076540420934803,12076540421060082,12076540421063877
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,932098,932103,4194304,256,0,0,24,24,114816,0x7fa37b76c500,0x7fa24b836640,12076540421090587,12076540421101842,12076540421274480,12076540421277594
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,932098,932103,4194304,256,0,0,24,24,116288,0x7fa37b76c400,0x7fa24b836680,12076540421312720,12076540421326160,12076540421451599,12076540421454754
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,932098,932103,4194304,256,0,0,28,24,119040,0x7fa37b76c300,0x7fa24b8366c0,12076540421479440,12076540421492718,12076540421745036,12076540421764159
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,932098,932103,4194304,256,0,0,28,24,120768,0x7fa37b76ca00,0x7fa24b836700,12076540421789136,12076540421801516,12076540422047274,12076540422072483
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,932098,932103,4194304,256,0,0,24,24,122496,0x7fa37b76c900,0x7fa24b836740,12076540422092781,12076540422107593,12076540422233032,12076540422236468
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,932098,932103,4194304,256,0,0,24,24,124736,0x7fa37b76c800,0x7fa24b836780,12076540422261475,12076540422272872,12076540422455431,12076540422458691
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,932098,932103,4194304,256,0,0,24,24,126464,0x7fa37b76c700,0x7fa24b8367c0,12076540422494809,12076540422509830,12076540422635589,12076540422639247
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,932098,932103,4194304,256,0,0,20,24,127936,0x7fa37b76c600,0x7fa24b836800,12076540422664795,12076540422677989,12076540422941027,12076540422968189
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,932098,932103,4194304,256,0,0,28,24,129664,0x7fa37b76c500,0x7fa24b836840,12076540422988697,12076540423001026,12076540423247904,12076540423272044
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,932098,932103,4194304,256,0,0,24,24,131392,0x7fa37b76c400,0x7fa24b836880,12076540423292362,12076540423305184,12076540423432543,12076540423435899
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,932098,932103,4194304,256,0,0,24,24,133632,0x7fa37b76c300,0x7fa24b8368c0,12076540423460936,12076540423472062,12076540423663261,12076540423666969
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,932098,932103,4194304,256,0,0,24,24,135360,0x7fa37b76ca00,0x7fa24b836900,12076540423701824,12076540423713980,12076540423841019,12076540423844219
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,932098,932103,4194304,256,0,0,20,24,136832,0x7fa37b76c900,0x7fa24b836940,12076540423869045,12076540423882779,12076540424197336,12076540424219978
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,932098,932103,4194304,256,0,0,28,24,138560,0x7fa37b76c800,0x7fa24b836980,12076540424241117,12076540424254136,12076540424502614,12076540424528902
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,932098,932103,4194304,256,0,0,24,24,140288,0x7fa37b76c700,0x7fa24b8369c0,12076540424550693,12076540424564053,12076540424690292,12076540424693298
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,932098,932103,4194304,256,0,0,24,24,142784,0x7fa37b76c600,0x7fa24b836a00,12076540424719276,12076540424731732,12076540424941170,12076540424966687
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,932098,932103,4194304,256,0,0,24,24,144768,0x7fa37b76c500,0x7fa24b836a40,12076540424996853,12076540425013650,12076540425141489,12076540425145038
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,932098,932103,4194304,256,0,0,20,24,145728,0x7fa37b76c400,0x7fa24b836a80,12076540425170345,12076540425182928,12076540425489166,12076540425516479
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,932098,932103,4194304,256,0,0,28,24,147712,0x7fa37b76c300,0x7fa24b836ac0,12076540425536857,12076540425549485,12076540425802283,12076540425829051
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,932098,932103,4194304,256,0,0,24,24,149696,0x7fa37b76ca00,0x7fa24b836b00,12076540425850601,12076540425863243,12076540425990602,12076540425993707
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,932098,932103,4194304,256,0,0,24,24,152192,0x7fa37b76c900,0x7fa24b836b40,12076540426023062,12076540426034922,12076540426261800,12076540426292042
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,932098,932103,4194304,256,0,0,24,24,154176,0x7fa37b76c800,0x7fa24b836b80,12076540426323901,12076540426335399,12076540426461798,12076540426465004
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,932098,932103,4194304,256,0,0,20,24,155648,0x7fa37b76c700,0x7fa24b836bc0,12076540426490080,12076540426502598,12076540426831075,12076540426849509
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,932098,932103,4194304,256,0,0,28,24,157632,0x7fa37b76c600,0x7fa24b836c00,12076540426871049,12076540426883715,12076540427132353,12076540427159325
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,932098,932103,4194304,256,0,0,24,24,159616,0x7fa37b76c500,0x7fa24b836c40,12076540427179653,12076540427192352,12076540427322111,12076540427325344
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,932098,932103,4194304,256,0,0,24,24,162368,0x7fa37b76c400,0x7fa24b836c80,12076540427351443,12076540427362911,12076540427606749,12076540427632766
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,932098,932103,4194304,256,0,0,24,24,164608,0x7fa37b76c300,0x7fa24b836cc0,12076540427663042,12076540427675548,12076540427806107,12076540427809485
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,932098,932103,4194304,256,0,0,20,24,166336,0x7fa37b76ca00,0x7fa24b836d00,12076540427835373,12076540427848667,12076540428224024,12076540428247239
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,932098,932103,4194304,256,0,0,28,24,168576,0x7fa37b76c900,0x7fa24b836d40,12076540428267787,12076540428279863,12076540428534101,12076540428556244
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,932098,932103,4194304,256,0,0,24,24,170816,0x7fa37b76c800,0x7fa24b836d80,12076540428579327,12076540428592341,12076540428722260,12076540428725839
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,932098,932103,4194304,256,0,0,24,24,174080,0x7fa37b76c700,0x7fa24b836dc0,12076540428750745,12076540428761939,12076540429041137,12076540429067414
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,932098,932103,4194304,256,0,0,24,24,176576,0x7fa37b76c600,0x7fa24b836e00,12076540429097460,12076540429108497,12076540429243695,12076540429246908
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,932098,932103,4194304,256,0,0,20,24,177792,0x7fa37b76c500,0x7fa24b836e40,12076540429272255,12076540429285135,12076540429707852,12076540429726500
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,932098,932103,4194304,256,0,0,28,24,180288,0x7fa37b76c400,0x7fa24b836e80,12076540429746588,12076540429759051,12076540430020489,12076540430046846
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,932098,932103,4194304,256,0,0,24,24,182784,0x7fa37b76c300,0x7fa24b836ec0,12076540430068987,12076540430081449,12076540430217128,12076540430220489
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,932098,932103,4194304,256,0,0,24,24,186304,0x7fa37b76ca00,0x7fa24b836f00,12076540430246458,12076540430258727,12076540430573285,12076540430599134
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,932098,932103,4194304,256,0,0,24,24,189312,0x7fa37b76c900,0x7fa24b836f40,12076540430630261,12076540430643364,12076540430795203,12076540430798444
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,932098,932103,4194304,256,0,0,20,24,190784,0x7fa37b76c800,0x7fa24b836f80,12076540430823852,12076540430836642,12076540431353438,12076540431386388
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,932098,932103,4194304,256,0,0,28,24,193792,0x7fa37b76c700,0x7fa24b836fc0,12076540431407147,12076540431419678,12076540431716955,12076540431742490
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,932098,932103,4194304,256,0,0,24,24,196800,0x7fa37b76c600,0x7fa24b837000,12076540431762678,12076540431775195,12076540431929434,12076540431932754
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,932098,932103,4194304,256,0,0,24,24,201088,0x7fa37b76c500,0x7fa24b837040,12076540431958202,12076540431969273,12076540432354710,12076540432381479
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,932098,932103,4194304,256,0,0,24,24,204608,0x7fa37b76c400,0x7fa24b837080,12076540432412286,12076540432424310,12076540432599988,12076540432603392
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,932098,932103,4194304,256,0,0,20,24,206080,0x7fa37b76c300,0x7fa24b8370c0,12076540432628438,12076540432641588,12076540433252303,12076540433279840
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,932098,932103,4194304,256,0,0,28,24,209600,0x7fa37b76ca00,0x7fa24b837100,12076540433301510,12076540433313902,12076540433639820,12076540433666018
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,932098,932103,4194304,256,0,0,24,24,213120,0x7fa37b76c900,0x7fa24b837140,12076540433689081,12076540433701739,12076540433879178,12076540433882511
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,932098,932103,4194304,256,0,0,24,24,218176,0x7fa37b76c800,0x7fa24b837180,12076540433907898,12076540433919017,12076540434373894,12076540434404552
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,932098,932103,4194304,256,0,0,24,24,222208,0x7fa37b76c700,0x7fa24b8371c0,12076540434437033,12076540434450213,12076540434649572,12076540434675256
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,932098,932103,4194304,256,0,0,20,24,223936,0x7fa37b76c600,0x7fa24b837200,12076540434693860,12076540434706371,12076540435410365,12076540435438014
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,932098,932103,4194304,256,0,0,28,24,227968,0x7fa37b76c500,0x7fa24b837240,12076540435460607,12076540435473085,12076540435846522,12076540435869407
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,932098,932103,4194304,256,0,0,24,24,232000,0x7fa37b76c400,0x7fa24b837280,12076540435891328,12076540435904121,12076540436106360,12076540436138077
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,932098,932103,4194304,256,0,0,24,24,237824,0x7fa37b76c300,0x7fa24b8372c0,12076540436158855,12076540436171479,12076540436714355,12076540436742832
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,932098,932103,4194304,256,0,0,24,24,242368,0x7fa37b76ca00,0x7fa24b837300,12076540436774420,12076540436787314,12076540437011632,12076540437038902
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,932098,932103,4194304,256,0,0,20,24,243584,0x7fa37b76c900,0x7fa24b837340,12076540437060412,12076540437072272,12076540437872265,12076540437898561
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,932098,932103,4194304,256,0,0,28,24,248128,0x7fa37b76c800,0x7fa24b837380,12076540437919691,12076540437931145,12076540438350181,12076540438380418
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,932098,932103,4194304,256,0,0,24,24,252672,0x7fa37b76c700,0x7fa24b8373c0,12076540438401136,12076540438412901,12076540438637379,12076540438663264
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,932098,932103,4194304,256,0,0,24,24,259264,0x7fa37b76c600,0x7fa24b837400,12076540438684584,12076540438695619,12076540439292894,12076540439320246
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,932098,932103,4194304,256,0,0,24,24,264832,0x7fa37b76c500,0x7fa24b837440,12076540439351434,12076540439364733,12076540439634811,12076540439660890
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,932098,932103,4194304,256,0,0,20,24,266304,0x7fa37b76c400,0x7fa24b837480,12076540439682540,12076540439694491,12076540440680723,12076540440708128
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,932098,932103,4194304,256,0,0,28,24,271872,0x7fa37b76c300,0x7fa24b8374c0,12076540440730229,12076540440742482,12076540441257678,12076540441285702
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,932098,932103,4194304,256,0,0,24,24,277440,0x7fa37b76ca00,0x7fa24b837500,12076540441310839,12076540441323597,12076540441595435,12076540441621757
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,932098,932103,4194304,256,0,0,12,24,279936,0x7fa37b76c900,0x7fa24b837540,12076540441641935,12076540441654155,12076540442393029,12076540442420723
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,932098,932103,4194304,256,0,0,24,24,286528,0x7fa37b76c800,0x7fa24b837580,12076540442451310,12076540442463748,12076540442778625,12076540442805529
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,932098,932103,4194304,256,0,0,20,24,288000,0x7fa37b76c700,0x7fa24b8375c0,12076540442827770,12076540442840545,12076540444014135,12076540444047469
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,932098,932103,4194304,256,0,0,32,24,294592,0x7fa37b76c600,0x7fa24b837600,12076540444068769,12076540444081335,12076540444690290,12076540444716133
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,932098,932103,4194304,256,0,0,24,24,301184,0x7fa37b76c500,0x7fa24b837640,12076540444737002,12076540444749649,12076540445069967,12076540445095158
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,932098,932103,4194304,256,0,0,12,24,304960,0x7fa37b76c400,0x7fa24b837680,12076540445118341,12076540445131086,12076540446008519,12076540446032892
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,932098,932103,4194304,256,0,0,24,24,313600,0x7fa37b76c300,0x7fa24b8376c0,12076540446066705,12076540446078759,12076540446489155,12076540446512805
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,932098,932103,4194304,256,0,0,20,24,314816,0x7fa37b76ca00,0x7fa24b837700,12076540446535387,12076540446547075,12076540448097782,12076540448147035
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,932098,932103,4194304,256,0,0,20,24,317568,0x7fa37b76c900,0x7fa24b837740,12076540448168445,12076540448180982,12076540448976495,12076540449047079
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,932098,932103,4194304,256,0,0,12,24,320320,0x7fa37b76c800,0x7fa24b837780,12076540449065874,12076540449078198,12076540449492275,12076540449566515
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,932098,932103,4194304,256,0,0,12,24,324096,0x7fa37b76c700,0x7fa24b8377c0,12076540449589047,12076540449600913,12076540450760106,12076540450830276
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,932098,932103,4194304,256,0,0,12,24,328896,0x7fa37b76c600,0x7fa24b837800,12076540450862266,12076540450874185,12076540451659780,12076540451733727
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,932098,932103,4194304,256,0,0,20,24,330112,0x7fa37b76c500,0x7fa24b837840,12076540451755287,12076540451767779,12076540454823280,12076540454894306
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,932098,932103,4194304,256,0,0,20,24,332864,0x7fa37b76c400,0x7fa24b837880,12076540454915335,12076540454928399,12076540456472549,12076540456546870
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,932098,932103,4194304,256,0,0,12,24,335616,0x7fa37b76c300,0x7fa24b8378c0,12076540456570103,12076540456583108,12076540457375103,12076540457446192
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,932098,932103,4194304,256,0,0,12,24,339392,0x7fa37b76ca00,0x7fa24b837900,12076540457467352,12076540457480382,12076540459761328,12076540459831249
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,932098,932103,4194304,256,0,0,12,24,344192,0x7fa37b76c900,0x7fa24b837940,12076540459862988,12076540459876527,12076540461412197,12076540461485726
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,932098,932103,4194304,256,0,0,20,24,345408,0x7fa37b76c800,0x7fa24b837980,12076540461508910,12076540461520996,12076540467578557,12076540467648971
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,932098,932103,4194304,256,0,0,20,24,348160,0x7fa37b76c700,0x7fa24b8379c0,12076540467671022,12076540467683676,12076540470728457,12076540470798379
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,932098,932103,4194304,256,0,0,12,24,350912,0x7fa37b76c600,0x7fa24b837a00,12076540470819829,12076540470833096,12076540472372606,12076540472447206
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,932098,932103,4194304,256,0,0,12,24,0,0x7fa37b76c500,0x7fa24b837a40,12076540472467394,12076540472478525,12076540477004736,12076540477075495
1 Dispatch_ID Kernel_Name GPU_ID queue-id queue-index pid tid grd Workgroup_Size LDS_Per_Workgroup scr vgpr SGPR fbar sig obj DispatchNs Start_Timestamp End_Timestamp CompleteNs
2 0 __amd_rocclr_fillBuffer.kd 0 0 0 932098 932103 33554432 256 0 0 8 32 6464 0x0 0x7fa24b804180 12076540386173827 12076540386221406 12076540386544923 12076540386650935
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 932098 932103 32768 256 0 0 24 24 12480 0x0 0x7fa24b835100 12076540401083130 12076540401193523 12076540401200243 12076540401205969
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 4 932098 932103 4194304 256 0 0 24 24 12928 0x7fa37b76c900 0x7fa24b835140 12076540401247406 12076540401262003 12076540401399282 12076540401402695
5 3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 6 932098 932103 4194304 256 0 0 36 24 13632 0x7fa37b76c800 0x7fa24b835180 12076540401444472 12076540401457521 12076540401703919 12076540401799793
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 8 932098 932103 4194304 256 0 0 28 24 14080 0x7fa37b76c700 0x7fa24b8351c0 12076540401826413 12076540401838798 12076540402084556 12076540402186092
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 10 932098 932103 4194304 256 0 0 24 24 14528 0x7fa37b76c600 0x7fa24b835200 12076540402210087 12076540402221835 12076540402347114 12076540402350528
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 12 932098 932103 4194304 256 0 0 24 24 14976 0x7fa37b76c500 0x7fa24b835240 12076540402377959 12076540402389514 12076540402514153 12076540402517328
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 14 932098 932103 4194304 256 0 0 24 24 15424 0x7fa37b76c400 0x7fa24b835280 12076540402573472 12076540402591432 12076540402714951 12076540402718081
10 8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 16 932098 932103 4194304 256 0 0 28 24 16128 0x7fa37b76c300 0x7fa24b8352c0 12076540402744971 12076540402757991 12076540403006309 12076540403102807
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 18 932098 932103 4194304 256 0 0 28 24 16832 0x7fa37b76ca00 0x7fa24b835300 12076540403124207 12076540403136068 12076540403378626 12076540403474108
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 20 932098 932103 4194304 256 0 0 24 24 17536 0x7fa37b76c900 0x7fa24b835340 12076540403501368 12076540403513344 12076540403637983 12076540403641259
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 22 932098 932103 4194304 256 0 0 24 24 18240 0x7fa37b76c800 0x7fa24b835380 12076540403671585 12076540403683423 12076540403808062 12076540403811215
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 24 932098 932103 4194304 256 0 0 24 24 18944 0x7fa37b76c700 0x7fa24b8353c0 12076540403853794 12076540403865982 12076540403990941 12076540403994165
15 13 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 26 932098 932103 4194304 256 0 0 28 24 19904 0x7fa37b76c600 0x7fa24b835400 12076540404030533 12076540404041500 12076540404291578 12076540404388158
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 28 932098 932103 4194304 256 0 0 28 24 20608 0x7fa37b76c500 0x7fa24b835440 12076540404410650 12076540404422137 12076540404668375 12076540404734953
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 30 932098 932103 4194304 256 0 0 24 24 21312 0x7fa37b76c400 0x7fa24b835480 12076540404756443 12076540404768374 12076540404892693 12076540404895913
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 32 932098 932103 4194304 256 0 0 24 24 22016 0x7fa37b76c300 0x7fa24b8354c0 12076540404924496 12076540404936053 12076540405061492 12076540405064686
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 34 932098 932103 4194304 256 0 0 24 24 22720 0x7fa37b76ca00 0x7fa24b835500 12076540405102136 12076540405113491 12076540405238610 12076540405241916
20 18 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 36 932098 932103 4194304 256 0 0 28 24 23680 0x7fa37b76c900 0x7fa24b835540 12076540405267634 12076540405279410 12076540405525328 12076540405568243
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 38 932098 932103 4194304 256 0 0 28 24 24384 0x7fa37b76c800 0x7fa24b835580 12076540405589843 12076540405601168 12076540405847246 12076540405887176
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 40 932098 932103 4194304 256 0 0 24 24 25088 0x7fa37b76c700 0x7fa24b8355c0 12076540405908506 12076540405920365 12076540406045004 12076540406048446
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 42 932098 932103 4194304 256 0 0 24 24 25792 0x7fa37b76c600 0x7fa24b835600 12076540406075627 12076540406087084 12076540406212363 12076540406215527
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 44 932098 932103 4194304 256 0 0 24 24 26496 0x7fa37b76c500 0x7fa24b835640 12076540406251805 12076540406265642 12076540406390441 12076540406393769
25 23 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 46 932098 932103 4194304 256 0 0 28 24 27712 0x7fa37b76c400 0x7fa24b835680 12076540406420258 12076540406433641 12076540406681959 12076540406747416
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 48 932098 932103 4194304 256 0 0 28 24 28416 0x7fa37b76c300 0x7fa24b8356c0 12076540406767334 12076540406780518 12076540407025476 12076540407091987
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 50 932098 932103 4194304 256 0 0 24 24 29120 0x7fa37b76ca00 0x7fa24b835700 12076540407114048 12076540407127075 12076540407251714 12076540407254860
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 52 932098 932103 4194304 256 0 0 24 24 30080 0x7fa37b76c900 0x7fa24b835740 12076540407280919 12076540407292194 12076540407417153 12076540407420338
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 54 932098 932103 4194304 256 0 0 24 24 30784 0x7fa37b76c800 0x7fa24b835780 12076540407456515 12076540407468672 12076540407593311 12076540407596656
30 28 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 56 932098 932103 4194304 256 0 0 28 24 32000 0x7fa37b76c700 0x7fa24b8357c0 12076540407621933 12076540407633951 12076540407880669 12076540407901854
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 58 932098 932103 4194304 256 0 0 28 24 32960 0x7fa37b76c600 0x7fa24b835800 12076540407922542 12076540407934109 12076540408178267 12076540408225095
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 60 932098 932103 4194304 256 0 0 24 24 33920 0x7fa37b76c500 0x7fa24b835840 12076540408245032 12076540408258746 12076540408384185 12076540408387197
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 62 932098 932103 4194304 256 0 0 24 24 34880 0x7fa37b76c400 0x7fa24b835880 12076540408412634 12076540408424185 12076540408549784 12076540408552995
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 64 932098 932103 4194304 256 0 0 24 24 35840 0x7fa37b76c300 0x7fa24b8358c0 12076540408589162 12076540408602103 12076540408727062 12076540408730535
35 33 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 66 932098 932103 4194304 256 0 0 28 24 37312 0x7fa37b76ca00 0x7fa24b835900 12076540408756053 12076540408768662 12076540409019380 12076540409046954
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 68 932098 932103 4194304 256 0 0 28 24 38272 0x7fa37b76c900 0x7fa24b835940 12076540409066591 12076540409079699 12076540409323057 12076540409399740
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 70 932098 932103 4194304 256 0 0 24 24 39232 0x7fa37b76c800 0x7fa24b835980 12076540409420138 12076540409432816 12076540409557615 12076540409561211
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 72 932098 932103 4194304 256 0 0 24 24 40192 0x7fa37b76c700 0x7fa24b8359c0 12076540409587960 12076540409599215 12076540409724974 12076540409728361
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 74 932098 932103 4194304 256 0 0 24 24 41152 0x7fa37b76c600 0x7fa24b835a00 12076540409763156 12076540409776494 12076540409900493 12076540409903898
40 38 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 76 932098 932103 4194304 256 0 0 28 24 42624 0x7fa37b76c500 0x7fa24b835a40 12076540409930127 12076540409943852 12076540410191850 12076540410228722
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 78 932098 932103 4194304 256 0 0 28 24 43584 0x7fa37b76c400 0x7fa24b835a80 12076540410249972 12076540410262890 12076540410511208 12076540410540242
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 80 932098 932103 4194304 256 0 0 24 24 44544 0x7fa37b76c300 0x7fa24b835ac0 12076540410562503 12076540410576007 12076540410700646 12076540410703886
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 82 932098 932103 4194304 256 0 0 24 24 45760 0x7fa37b76ca00 0x7fa24b835b00 12076540410728812 12076540410741126 12076540410867365 12076540410870506
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 84 932098 932103 4194304 256 0 0 24 24 46720 0x7fa37b76c900 0x7fa24b835b40 12076540410904900 12076540410916324 12076540411041283 12076540411044530
45 43 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 86 932098 932103 4194304 256 0 0 28 24 48448 0x7fa37b76c800 0x7fa24b835b80 12076540411071279 12076540411084003 12076540411343361 12076540411367771
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 88 932098 932103 4194304 256 0 0 28 24 49408 0x7fa37b76c700 0x7fa24b835bc0 12076540411388309 12076540411400640 12076540411648958 12076540411672698
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 90 932098 932103 4194304 256 0 0 24 24 50368 0x7fa37b76c600 0x7fa24b835c00 12076540411692495 12076540411705598 12076540411830557 12076540411833758
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 92 932098 932103 4194304 256 0 0 24 24 51584 0x7fa37b76c500 0x7fa24b835c40 12076540411860127 12076540411871997 12076540411998396 12076540412004345
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 94 932098 932103 4194304 256 0 0 24 24 52544 0x7fa37b76c400 0x7fa24b835c80 12076540412038969 12076540412052315 12076540412178074 12076540412181254
50 48 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 96 932098 932103 4194304 256 0 0 28 24 54272 0x7fa37b76c300 0x7fa24b835cc0 12076540412207333 12076540412219994 12076540412475992 12076540412499686
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 98 932098 932103 4194304 256 0 0 28 24 55488 0x7fa37b76ca00 0x7fa24b835d00 12076540412521808 12076540412534231 12076540412777589 12076540412805065
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 100 932098 932103 4194304 256 0 0 24 24 56704 0x7fa37b76c900 0x7fa24b835d40 12076540412826154 12076540412839349 12076540412964628 12076540412967787
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 102 932098 932103 4194304 256 0 0 24 24 58176 0x7fa37b76c800 0x7fa24b835d80 12076540412992724 12076540413005427 12076540413133906 12076540413137202
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 104 932098 932103 4194304 256 0 0 24 24 59392 0x7fa37b76c700 0x7fa24b835dc0 12076540413173951 12076540413186226 12076540413310865 12076540413313921
55 53 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 106 932098 932103 4194304 256 0 0 28 24 61376 0x7fa37b76c600 0x7fa24b835e00 12076540413340140 12076540413353905 12076540413617902 12076540413645127
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 108 932098 932103 4194304 256 0 0 28 24 62592 0x7fa37b76c500 0x7fa24b835e40 12076540413665505 12076540413678382 12076540413923980 12076540413943142
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 110 932098 932103 4194304 256 0 0 24 24 63808 0x7fa37b76c400 0x7fa24b835e80 12076540413970773 12076540413984299 12076540414109578 12076540414112957
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 112 932098 932103 4194304 256 0 0 24 24 65280 0x7fa37b76c300 0x7fa24b835ec0 12076540414141060 12076540414153738 12076540414283337 12076540414286610
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 114 932098 932103 4194304 256 0 0 24 24 66496 0x7fa37b76ca00 0x7fa24b835f00 12076540414322748 12076540414334057 12076540414459176 12076540414462327
60 58 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 116 932098 932103 4194304 256 0 0 28 24 68480 0x7fa37b76c900 0x7fa24b835f40 12076540414488045 12076540414500615 12076540414756933 12076540414779597
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 118 932098 932103 4194304 256 0 0 28 24 69696 0x7fa37b76c800 0x7fa24b835f80 12076540414800396 12076540414811653 12076540415061731 12076540415089103
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 120 932098 932103 4194304 256 0 0 24 24 70912 0x7fa37b76c700 0x7fa24b835fc0 12076540415111024 12076540415122850 12076540415247489 12076540415250674
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 122 932098 932103 4194304 256 0 0 24 24 72384 0x7fa37b76c600 0x7fa24b836000 12076540415277353 12076540415290369 12076540415427488 12076540415430729
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 124 932098 932103 4194304 256 0 0 24 24 73600 0x7fa37b76c500 0x7fa24b836040 12076540415467918 12076540415480447 12076540415604606 12076540415607708
65 63 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 126 932098 932103 4194304 256 0 0 28 24 75840 0x7fa37b76c400 0x7fa24b836080 12076540415633856 12076540415646686 12076540415902844 12076540415925509
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 128 932098 932103 4194304 256 0 0 28 24 77056 0x7fa37b76c300 0x7fa24b8360c0 12076540415946348 12076540415959163 12076540416203801 12076540416230777
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 130 932098 932103 4194304 256 0 0 24 24 78272 0x7fa37b76ca00 0x7fa24b836100 12076540416251545 12076540416264121 12076540416389400 12076540416392588
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 132 932098 932103 4194304 256 0 0 24 24 80000 0x7fa37b76c900 0x7fa24b836140 12076540416417754 12076540416430680 12076540416572758 12076540416576059
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 134 932098 932103 4194304 256 0 0 24 24 81216 0x7fa37b76c800 0x7fa24b836180 12076540416610393 12076540416622518 12076540416747157 12076540416750413
70 68 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 136 932098 932103 4194304 256 0 0 28 24 83456 0x7fa37b76c700 0x7fa24b8361c0 12076540416775430 12076540416787477 12076540417050355 12076540417074186
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 138 932098 932103 4194304 256 0 0 28 24 84928 0x7fa37b76c600 0x7fa24b836200 12076540417096307 12076540417108434 12076540417356112 12076540417382219
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 140 932098 932103 4194304 256 0 0 24 24 86400 0x7fa37b76c500 0x7fa24b836240 12076540417405532 12076540417418352 12076540417543470 12076540417547145
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 142 932098 932103 4194304 256 0 0 24 24 88128 0x7fa37b76c400 0x7fa24b836280 12076540417573023 12076540417584270 12076540417734669 12076540417737900
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 144 932098 932103 4194304 256 0 0 24 24 89600 0x7fa37b76c300 0x7fa24b8362c0 12076540417788534 12076540417802188 12076540417927627 12076540417931210
75 73 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 146 932098 932103 4194304 256 0 0 28 24 92096 0x7fa37b76ca00 0x7fa24b836300 12076540417957489 12076540417969707 12076540418227945 12076540418255663
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 148 932098 932103 4194304 256 0 0 28 24 93568 0x7fa37b76c900 0x7fa24b836340 12076540418276923 12076540418289544 12076540418536422 12076540418562494
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 150 932098 932103 4194304 256 0 0 24 24 95040 0x7fa37b76c800 0x7fa24b836380 12076540418583633 12076540418596902 12076540418722661 12076540418725888
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 152 932098 932103 4194304 256 0 0 24 24 96768 0x7fa37b76c700 0x7fa24b8363c0 12076540418752057 12076540418763141 12076540418920419 12076540418923536
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 154 932098 932103 4194304 256 0 0 24 24 98240 0x7fa37b76c600 0x7fa24b836400 12076540418959793 12076540418972259 12076540419097538 12076540419101066
80 78 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 156 932098 932103 4194304 256 0 0 28 24 100736 0x7fa37b76c500 0x7fa24b836440 12076540419127214 12076540419138658 12076540419401215 12076540419427723
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 158 932098 932103 4194304 256 0 0 28 24 102208 0x7fa37b76c400 0x7fa24b836480 12076540419448182 12076540419460575 12076540419708093 12076540419730847
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 160 932098 932103 4194304 256 0 0 24 24 103680 0x7fa37b76c300 0x7fa24b8364c0 12076540419751025 12076540419764252 12076540419890811 12076540419893941
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 162 932098 932103 4194304 256 0 0 24 24 105664 0x7fa37b76ca00 0x7fa24b836500 12076540419918857 12076540419930171 12076540420095290 12076540420098742
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 164 932098 932103 4194304 256 0 0 24 24 107136 0x7fa37b76c900 0x7fa24b836540 12076540420135400 12076540420150489 12076540420276408 12076540420279859
85 83 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 166 932098 932103 4194304 256 0 0 28 24 109888 0x7fa37b76c800 0x7fa24b836580 12076540420305276 12076540420318008 12076540420571606 12076540420594534
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 168 932098 932103 4194304 256 0 0 28 24 111360 0x7fa37b76c700 0x7fa24b8365c0 12076540420615002 12076540420627125 12076540420872403 12076540420899311
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 170 932098 932103 4194304 256 0 0 24 24 112832 0x7fa37b76c600 0x7fa24b836600 12076540420921983 12076540420934803 12076540421060082 12076540421063877
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 172 932098 932103 4194304 256 0 0 24 24 114816 0x7fa37b76c500 0x7fa24b836640 12076540421090587 12076540421101842 12076540421274480 12076540421277594
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 174 932098 932103 4194304 256 0 0 24 24 116288 0x7fa37b76c400 0x7fa24b836680 12076540421312720 12076540421326160 12076540421451599 12076540421454754
90 88 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 176 932098 932103 4194304 256 0 0 28 24 119040 0x7fa37b76c300 0x7fa24b8366c0 12076540421479440 12076540421492718 12076540421745036 12076540421764159
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 178 932098 932103 4194304 256 0 0 28 24 120768 0x7fa37b76ca00 0x7fa24b836700 12076540421789136 12076540421801516 12076540422047274 12076540422072483
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 180 932098 932103 4194304 256 0 0 24 24 122496 0x7fa37b76c900 0x7fa24b836740 12076540422092781 12076540422107593 12076540422233032 12076540422236468
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 182 932098 932103 4194304 256 0 0 24 24 124736 0x7fa37b76c800 0x7fa24b836780 12076540422261475 12076540422272872 12076540422455431 12076540422458691
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 184 932098 932103 4194304 256 0 0 24 24 126464 0x7fa37b76c700 0x7fa24b8367c0 12076540422494809 12076540422509830 12076540422635589 12076540422639247
95 93 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 186 932098 932103 4194304 256 0 0 20 24 127936 0x7fa37b76c600 0x7fa24b836800 12076540422664795 12076540422677989 12076540422941027 12076540422968189
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 188 932098 932103 4194304 256 0 0 28 24 129664 0x7fa37b76c500 0x7fa24b836840 12076540422988697 12076540423001026 12076540423247904 12076540423272044
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 190 932098 932103 4194304 256 0 0 24 24 131392 0x7fa37b76c400 0x7fa24b836880 12076540423292362 12076540423305184 12076540423432543 12076540423435899
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 192 932098 932103 4194304 256 0 0 24 24 133632 0x7fa37b76c300 0x7fa24b8368c0 12076540423460936 12076540423472062 12076540423663261 12076540423666969
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 194 932098 932103 4194304 256 0 0 24 24 135360 0x7fa37b76ca00 0x7fa24b836900 12076540423701824 12076540423713980 12076540423841019 12076540423844219
100 98 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 196 932098 932103 4194304 256 0 0 20 24 136832 0x7fa37b76c900 0x7fa24b836940 12076540423869045 12076540423882779 12076540424197336 12076540424219978
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 198 932098 932103 4194304 256 0 0 28 24 138560 0x7fa37b76c800 0x7fa24b836980 12076540424241117 12076540424254136 12076540424502614 12076540424528902
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 200 932098 932103 4194304 256 0 0 24 24 140288 0x7fa37b76c700 0x7fa24b8369c0 12076540424550693 12076540424564053 12076540424690292 12076540424693298
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 202 932098 932103 4194304 256 0 0 24 24 142784 0x7fa37b76c600 0x7fa24b836a00 12076540424719276 12076540424731732 12076540424941170 12076540424966687
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 204 932098 932103 4194304 256 0 0 24 24 144768 0x7fa37b76c500 0x7fa24b836a40 12076540424996853 12076540425013650 12076540425141489 12076540425145038
105 103 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 206 932098 932103 4194304 256 0 0 20 24 145728 0x7fa37b76c400 0x7fa24b836a80 12076540425170345 12076540425182928 12076540425489166 12076540425516479
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 208 932098 932103 4194304 256 0 0 28 24 147712 0x7fa37b76c300 0x7fa24b836ac0 12076540425536857 12076540425549485 12076540425802283 12076540425829051
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 210 932098 932103 4194304 256 0 0 24 24 149696 0x7fa37b76ca00 0x7fa24b836b00 12076540425850601 12076540425863243 12076540425990602 12076540425993707
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 212 932098 932103 4194304 256 0 0 24 24 152192 0x7fa37b76c900 0x7fa24b836b40 12076540426023062 12076540426034922 12076540426261800 12076540426292042
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 214 932098 932103 4194304 256 0 0 24 24 154176 0x7fa37b76c800 0x7fa24b836b80 12076540426323901 12076540426335399 12076540426461798 12076540426465004
110 108 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 216 932098 932103 4194304 256 0 0 20 24 155648 0x7fa37b76c700 0x7fa24b836bc0 12076540426490080 12076540426502598 12076540426831075 12076540426849509
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 218 932098 932103 4194304 256 0 0 28 24 157632 0x7fa37b76c600 0x7fa24b836c00 12076540426871049 12076540426883715 12076540427132353 12076540427159325
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 220 932098 932103 4194304 256 0 0 24 24 159616 0x7fa37b76c500 0x7fa24b836c40 12076540427179653 12076540427192352 12076540427322111 12076540427325344
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 222 932098 932103 4194304 256 0 0 24 24 162368 0x7fa37b76c400 0x7fa24b836c80 12076540427351443 12076540427362911 12076540427606749 12076540427632766
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 224 932098 932103 4194304 256 0 0 24 24 164608 0x7fa37b76c300 0x7fa24b836cc0 12076540427663042 12076540427675548 12076540427806107 12076540427809485
115 113 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 226 932098 932103 4194304 256 0 0 20 24 166336 0x7fa37b76ca00 0x7fa24b836d00 12076540427835373 12076540427848667 12076540428224024 12076540428247239
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 228 932098 932103 4194304 256 0 0 28 24 168576 0x7fa37b76c900 0x7fa24b836d40 12076540428267787 12076540428279863 12076540428534101 12076540428556244
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 230 932098 932103 4194304 256 0 0 24 24 170816 0x7fa37b76c800 0x7fa24b836d80 12076540428579327 12076540428592341 12076540428722260 12076540428725839
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 232 932098 932103 4194304 256 0 0 24 24 174080 0x7fa37b76c700 0x7fa24b836dc0 12076540428750745 12076540428761939 12076540429041137 12076540429067414
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 234 932098 932103 4194304 256 0 0 24 24 176576 0x7fa37b76c600 0x7fa24b836e00 12076540429097460 12076540429108497 12076540429243695 12076540429246908
120 118 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 236 932098 932103 4194304 256 0 0 20 24 177792 0x7fa37b76c500 0x7fa24b836e40 12076540429272255 12076540429285135 12076540429707852 12076540429726500
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 238 932098 932103 4194304 256 0 0 28 24 180288 0x7fa37b76c400 0x7fa24b836e80 12076540429746588 12076540429759051 12076540430020489 12076540430046846
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 240 932098 932103 4194304 256 0 0 24 24 182784 0x7fa37b76c300 0x7fa24b836ec0 12076540430068987 12076540430081449 12076540430217128 12076540430220489
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 242 932098 932103 4194304 256 0 0 24 24 186304 0x7fa37b76ca00 0x7fa24b836f00 12076540430246458 12076540430258727 12076540430573285 12076540430599134
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 244 932098 932103 4194304 256 0 0 24 24 189312 0x7fa37b76c900 0x7fa24b836f40 12076540430630261 12076540430643364 12076540430795203 12076540430798444
125 123 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 246 932098 932103 4194304 256 0 0 20 24 190784 0x7fa37b76c800 0x7fa24b836f80 12076540430823852 12076540430836642 12076540431353438 12076540431386388
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 248 932098 932103 4194304 256 0 0 28 24 193792 0x7fa37b76c700 0x7fa24b836fc0 12076540431407147 12076540431419678 12076540431716955 12076540431742490
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 250 932098 932103 4194304 256 0 0 24 24 196800 0x7fa37b76c600 0x7fa24b837000 12076540431762678 12076540431775195 12076540431929434 12076540431932754
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 252 932098 932103 4194304 256 0 0 24 24 201088 0x7fa37b76c500 0x7fa24b837040 12076540431958202 12076540431969273 12076540432354710 12076540432381479
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 254 932098 932103 4194304 256 0 0 24 24 204608 0x7fa37b76c400 0x7fa24b837080 12076540432412286 12076540432424310 12076540432599988 12076540432603392
130 128 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 256 932098 932103 4194304 256 0 0 20 24 206080 0x7fa37b76c300 0x7fa24b8370c0 12076540432628438 12076540432641588 12076540433252303 12076540433279840
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 258 932098 932103 4194304 256 0 0 28 24 209600 0x7fa37b76ca00 0x7fa24b837100 12076540433301510 12076540433313902 12076540433639820 12076540433666018
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 260 932098 932103 4194304 256 0 0 24 24 213120 0x7fa37b76c900 0x7fa24b837140 12076540433689081 12076540433701739 12076540433879178 12076540433882511
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 262 932098 932103 4194304 256 0 0 24 24 218176 0x7fa37b76c800 0x7fa24b837180 12076540433907898 12076540433919017 12076540434373894 12076540434404552
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 264 932098 932103 4194304 256 0 0 24 24 222208 0x7fa37b76c700 0x7fa24b8371c0 12076540434437033 12076540434450213 12076540434649572 12076540434675256
135 133 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 266 932098 932103 4194304 256 0 0 20 24 223936 0x7fa37b76c600 0x7fa24b837200 12076540434693860 12076540434706371 12076540435410365 12076540435438014
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 268 932098 932103 4194304 256 0 0 28 24 227968 0x7fa37b76c500 0x7fa24b837240 12076540435460607 12076540435473085 12076540435846522 12076540435869407
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 270 932098 932103 4194304 256 0 0 24 24 232000 0x7fa37b76c400 0x7fa24b837280 12076540435891328 12076540435904121 12076540436106360 12076540436138077
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 272 932098 932103 4194304 256 0 0 24 24 237824 0x7fa37b76c300 0x7fa24b8372c0 12076540436158855 12076540436171479 12076540436714355 12076540436742832
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 274 932098 932103 4194304 256 0 0 24 24 242368 0x7fa37b76ca00 0x7fa24b837300 12076540436774420 12076540436787314 12076540437011632 12076540437038902
140 138 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 276 932098 932103 4194304 256 0 0 20 24 243584 0x7fa37b76c900 0x7fa24b837340 12076540437060412 12076540437072272 12076540437872265 12076540437898561
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 278 932098 932103 4194304 256 0 0 28 24 248128 0x7fa37b76c800 0x7fa24b837380 12076540437919691 12076540437931145 12076540438350181 12076540438380418
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 280 932098 932103 4194304 256 0 0 24 24 252672 0x7fa37b76c700 0x7fa24b8373c0 12076540438401136 12076540438412901 12076540438637379 12076540438663264
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 282 932098 932103 4194304 256 0 0 24 24 259264 0x7fa37b76c600 0x7fa24b837400 12076540438684584 12076540438695619 12076540439292894 12076540439320246
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 284 932098 932103 4194304 256 0 0 24 24 264832 0x7fa37b76c500 0x7fa24b837440 12076540439351434 12076540439364733 12076540439634811 12076540439660890
145 143 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 286 932098 932103 4194304 256 0 0 20 24 266304 0x7fa37b76c400 0x7fa24b837480 12076540439682540 12076540439694491 12076540440680723 12076540440708128
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 288 932098 932103 4194304 256 0 0 28 24 271872 0x7fa37b76c300 0x7fa24b8374c0 12076540440730229 12076540440742482 12076540441257678 12076540441285702
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 290 932098 932103 4194304 256 0 0 24 24 277440 0x7fa37b76ca00 0x7fa24b837500 12076540441310839 12076540441323597 12076540441595435 12076540441621757
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 292 932098 932103 4194304 256 0 0 12 24 279936 0x7fa37b76c900 0x7fa24b837540 12076540441641935 12076540441654155 12076540442393029 12076540442420723
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 294 932098 932103 4194304 256 0 0 24 24 286528 0x7fa37b76c800 0x7fa24b837580 12076540442451310 12076540442463748 12076540442778625 12076540442805529
150 148 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 296 932098 932103 4194304 256 0 0 20 24 288000 0x7fa37b76c700 0x7fa24b8375c0 12076540442827770 12076540442840545 12076540444014135 12076540444047469
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 298 932098 932103 4194304 256 0 0 32 24 294592 0x7fa37b76c600 0x7fa24b837600 12076540444068769 12076540444081335 12076540444690290 12076540444716133
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 300 932098 932103 4194304 256 0 0 24 24 301184 0x7fa37b76c500 0x7fa24b837640 12076540444737002 12076540444749649 12076540445069967 12076540445095158
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 302 932098 932103 4194304 256 0 0 12 24 304960 0x7fa37b76c400 0x7fa24b837680 12076540445118341 12076540445131086 12076540446008519 12076540446032892
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 304 932098 932103 4194304 256 0 0 24 24 313600 0x7fa37b76c300 0x7fa24b8376c0 12076540446066705 12076540446078759 12076540446489155 12076540446512805
155 153 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 306 932098 932103 4194304 256 0 0 20 24 314816 0x7fa37b76ca00 0x7fa24b837700 12076540446535387 12076540446547075 12076540448097782 12076540448147035
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 308 932098 932103 4194304 256 0 0 20 24 317568 0x7fa37b76c900 0x7fa24b837740 12076540448168445 12076540448180982 12076540448976495 12076540449047079
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 310 932098 932103 4194304 256 0 0 12 24 320320 0x7fa37b76c800 0x7fa24b837780 12076540449065874 12076540449078198 12076540449492275 12076540449566515
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 312 932098 932103 4194304 256 0 0 12 24 324096 0x7fa37b76c700 0x7fa24b8377c0 12076540449589047 12076540449600913 12076540450760106 12076540450830276
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 314 932098 932103 4194304 256 0 0 12 24 328896 0x7fa37b76c600 0x7fa24b837800 12076540450862266 12076540450874185 12076540451659780 12076540451733727
160 158 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 316 932098 932103 4194304 256 0 0 20 24 330112 0x7fa37b76c500 0x7fa24b837840 12076540451755287 12076540451767779 12076540454823280 12076540454894306
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 318 932098 932103 4194304 256 0 0 20 24 332864 0x7fa37b76c400 0x7fa24b837880 12076540454915335 12076540454928399 12076540456472549 12076540456546870
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 320 932098 932103 4194304 256 0 0 12 24 335616 0x7fa37b76c300 0x7fa24b8378c0 12076540456570103 12076540456583108 12076540457375103 12076540457446192
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 322 932098 932103 4194304 256 0 0 12 24 339392 0x7fa37b76ca00 0x7fa24b837900 12076540457467352 12076540457480382 12076540459761328 12076540459831249
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 324 932098 932103 4194304 256 0 0 12 24 344192 0x7fa37b76c900 0x7fa24b837940 12076540459862988 12076540459876527 12076540461412197 12076540461485726
165 163 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 326 932098 932103 4194304 256 0 0 20 24 345408 0x7fa37b76c800 0x7fa24b837980 12076540461508910 12076540461520996 12076540467578557 12076540467648971
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 328 932098 932103 4194304 256 0 0 20 24 348160 0x7fa37b76c700 0x7fa24b8379c0 12076540467671022 12076540467683676 12076540470728457 12076540470798379
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 330 932098 932103 4194304 256 0 0 12 24 350912 0x7fa37b76c600 0x7fa24b837a00 12076540470819829 12076540470833096 12076540472372606 12076540472447206
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 332 932098 932103 4194304 256 0 0 12 24 0 0x7fa37b76c500 0x7fa24b837a40 12076540472467394 12076540472478525 12076540477004736 12076540477075495