169 lines
66 KiB
CSV
169 lines
66 KiB
CSV
|
|
Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,sig,obj,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,TCP_TCC_READ_REQ_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RDREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WRREQ_sum,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,SQ_LDS_IDX_ACTIVE,SQ_LDS_BANK_CONFLICT,DispatchNs,BeginNs,EndNs,CompleteNs
|
||
|
|
0,"__amd_rocclr_fillBufferAligned.kd",0,0,0,162308,162308,33554432,256,0,0,4,32,4160,0x0,0x7f61e0a04280,0,0,0,0,0,0,0,0,0.0000000000,8388608.0000000000,4194304.0000000000,0.0000000000,0.0000000000,310.0000000000,4128768.0000000000,4128768.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520518872806,16491023118595,16520667653084,16520667762073
|
||
|
|
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,162308,162308,32768,256,0,0,12,24,13888,0x0,0x7f61e0a23f80,0,0,0,0,0,0,0,0,8192.0000000000,16384.0000000000,0.0000000000,0.0000000000,0.0000000000,8260.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520673724714,16520667653084,16520674074179,16520674084211
|
||
|
|
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,162308,162308,4194304,256,0,0,12,24,14336,0x7f61e3a19380,0x7f61e0a23fc0,0,0,0,0,0,0,262144,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097346.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520674678969,16520674074179,16520675351614,16520675353724
|
||
|
|
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,162308,162308,4194304,256,0,0,16,24,15040,0x7f61e3a19200,0x7f61e0a24000,0,0,0,0,0,0,262144,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194666.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520675954242,16520675351614,16520676571129,16520676572270
|
||
|
|
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,162308,162308,4194304,256,0,0,16,24,15488,0x7f61e3a19080,0x7f61e0a24040,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194600.0000000000,0.0000000000,0.0000000000,0,0,262144,0,0,0,0,0,0.0000000000,0,0,16520677171458,16520676571129,16520677845204,16520677846773
|
||
|
|
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,162308,162308,4194304,256,0,0,12,24,15936,0x7f61e127df00,0x7f61e0a24080,0,0,262144,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097342.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520678445121,16520677845204,16520679028560,16520679029209
|
||
|
|
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,162308,162308,4194304,256,0,0,12,24,16384,0x7f61e127dd80,0x7f61e0a240c0,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097344.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520679623907,16520679028560,16520680248235,16520680249694
|
||
|
|
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,162308,162308,4194304,256,0,0,12,24,17088,0x7f61e127dc00,0x7f61e0a24100,0,0,0,0,0,0,655360,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097340.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520680859882,16520680248235,16520681467431,16520681468849
|
||
|
|
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,162308,162308,4194304,256,0,0,16,24,17792,0x7f61e127da80,0x7f61e0a24140,0,0,0,0,0,0,786432,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194604.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520682064177,16520681467431,16520682780866,16520682781671
|
||
|
|
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,162308,162308,4194304,256,0,0,16,24,18496,0x7f61e127d900,0x7f61e0a24180,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194601.0000000000,0.0000000000,0.0000000000,0,0,786432,0,0,0,0,0,0.0000000000,0,0,16520683376689,16520682780866,16520684062621,16520684063344
|
||
|
|
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,162308,162308,4194304,256,0,0,16,24,19200,0x7f61e127d780,0x7f61e0a241c0,0,0,786432,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097342.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520684660302,16520684062621,16520685282136,16520685283219
|
||
|
|
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,162308,162308,4194304,256,0,0,16,24,19904,0x7f61e127d600,0x7f61e0a24200,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097342.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520685878827,16520685282136,16520686509652,16520686510404
|
||
|
|
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,162308,162308,4194304,256,0,0,12,24,20608,0x7f61e3a19480,0x7f61e0a24240,0,0,0,0,0,0,1048576,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097342.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520687115792,16520686509652,16520687712687,16520687713430
|
||
|
|
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,162308,162308,4194304,256,0,0,16,24,21312,0x7f61e3a19300,0x7f61e0a24280,0,0,0,0,0,0,1310720,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194609.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520688309898,16520687712687,16520689008842,16520689009472
|
||
|
|
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,162308,162308,4194304,256,0,0,16,24,22016,0x7f61e3a19180,0x7f61e0a242c0,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194601.0000000000,0.0000000000,0.0000000000,0,0,1310720,0,0,0,0,0,0.0000000000,0,0,16520689605761,16520689008842,16520690330277,16520690331294
|
||
|
|
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,162308,162308,4194304,256,0,0,16,24,22720,0x7f61e3a19000,0x7f61e0a24300,0,0,1310720,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097347.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520690926912,16520690330277,16520691540993,16520691541649
|
||
|
|
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,162308,162308,4194304,256,0,0,12,24,23424,0x7f61e127de80,0x7f61e0a24340,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097339.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520692136587,16520691540993,16520692710748,16520692711326
|
||
|
|
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,162308,162308,4194304,256,0,0,12,24,24128,0x7f61e127dd00,0x7f61e0a24380,0,0,0,0,0,0,1441792,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097345.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520693315084,16520692710748,16520693912664,16520693913722
|
||
|
|
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,162308,162308,4194304,256,0,0,16,24,24832,0x7f61e127db80,0x7f61e0a243c0,0,0,0,0,0,0,1835008,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194610.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520694510210,16520693912664,16520695203859,16520695204604
|
||
|
|
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,162308,162308,4194304,256,0,0,16,24,25536,0x7f61e127da00,0x7f61e0a24400,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194603.0000000000,0.0000000000,0.0000000000,0,0,1835008,0,0,0,0,0,0.0000000000,0,0,16520695799983,16520695203859,16520696506254,16520696506927
|
||
|
|
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,162308,162308,4194304,256,0,0,12,24,26240,0x7f61e127d880,0x7f61e0a24440,0,0,1835008,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097348.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520697102195,16520696506254,16520697701449,16520697702073
|
||
|
|
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,162308,162308,4194304,256,0,0,12,24,26944,0x7f61e127d700,0x7f61e0a24480,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097349.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520698298851,16520697701449,16520698910405,16520698911098
|
||
|
|
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,162308,162308,4194304,256,0,0,12,24,27648,0x7f61e3a19580,0x7f61e0a244c0,0,0,0,0,0,0,1835008,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097341.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520699515416,16520698910405,16520700098560,16520700099345
|
||
|
|
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,162308,162308,4194304,256,0,0,16,24,28608,0x7f61e3a19400,0x7f61e0a24500,0,0,0,0,0,0,2359296,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194613.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520700696203,16520700098560,16520701396475,16520701397217
|
||
|
|
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,162308,162308,4194304,256,0,0,16,24,29312,0x7f61e3a19280,0x7f61e0a24540,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194587.0000000000,0.0000000000,0.0000000000,0,0,2359296,0,0,0,0,0,0.0000000000,0,0,16520701993015,16520701396475,16520702708310,16520702708568
|
||
|
|
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,162308,162308,4194304,256,0,0,12,24,30016,0x7f61e3a19100,0x7f61e0a24580,0,0,2359296,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097342.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520703304607,16520702708310,16520703910546,16520703910984
|
||
|
|
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,162308,162308,4194304,256,0,0,8,24,30976,0x7f61e127df80,0x7f61e0a245c0,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097347.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520704507552,16520703910546,16520705148301,16520705148609
|
||
|
|
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,162308,162308,4194304,256,0,0,12,24,31680,0x7f61e127de00,0x7f61e0a24600,0,0,0,0,0,0,2228224,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097338.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520705752607,16520705148301,16520706360297,16520706360764
|
||
|
|
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,162308,162308,4194304,256,0,0,16,24,32640,0x7f61e127dc80,0x7f61e0a24640,0,0,0,0,0,0,2883584,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194595.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520706956403,16520706360297,16520707684612,16520707685336
|
||
|
|
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,162308,162308,4194304,256,0,0,12,24,33600,0x7f61e127db00,0x7f61e0a24680,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194600.0000000000,0.0000000000,0.0000000000,0,0,2883584,0,0,0,0,0,0.0000000000,0,0,16520708280794,16520707684612,16520708993567,16520708993848
|
||
|
|
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,162308,162308,4194304,256,0,0,12,24,34560,0x7f61e127d980,0x7f61e0a246c0,0,0,2883584,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097348.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520709589196,16520708993567,16520710246362,16520710247252
|
||
|
|
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,162308,162308,4194304,256,0,0,8,24,35520,0x7f61e127d800,0x7f61e0a24700,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097353.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520710842140,16520710246362,16520711452597,16520711453347
|
||
|
|
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,162308,162308,4194304,256,0,0,12,24,36224,0x7f61e127d680,0x7f61e0a24740,0,0,0,0,0,0,2621440,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097341.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520712055665,16520711452597,16520712678193,16520712678672
|
||
|
|
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,162308,162308,4194304,256,0,0,12,24,37184,0x7f61e3a19500,0x7f61e0a24780,0,0,0,0,0,0,3407872,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194602.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520713279150,16520712678193,16520713966508,16520713967055
|
||
|
|
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,162308,162308,4194304,256,0,0,12,24,38144,0x7f61e3a19380,0x7f61e0a247c0,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194596.0000000000,0.0000000000,0.0000000000,0,0,3407872,0,0,0,0,0,0.0000000000,0,0,16520714564483,16520713966508,16520715298663,16520715299316
|
||
|
|
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,162308,162308,4194304,256,0,0,12,24,39104,0x7f61e3a19200,0x7f61e0a24800,0,0,3407872,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097349.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520715895794,16520715298663,16520716500898,16520716501482
|
||
|
|
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,162308,162308,4194304,256,0,0,8,24,40320,0x7f61e3a19080,0x7f61e0a24840,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097357.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520717098560,16520716500898,16520717700734,16520717701428
|
||
|
|
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,162308,162308,4194304,256,0,0,12,24,41280,0x7f61e127df00,0x7f61e0a24880,0,0,0,0,0,0,3014656,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097342.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520718305445,16520717700734,16520718896889,16520718897194
|
||
|
|
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,162308,162308,4194304,256,0,0,12,24,42240,0x7f61e127dd80,0x7f61e0a248c0,0,0,0,0,0,0,3932160,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194596.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520719492092,16520718896889,16520720255444,16520720255434
|
||
|
|
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,162308,162308,4194304,256,0,0,12,24,43200,0x7f61e127dc00,0x7f61e0a24900,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194594.0000000000,0.0000000000,0.0000000000,0,0,3932160,0,0,0,0,0,0.0000000000,0,0,16520720850002,16520720255444,16520721500719,16520721500878
|
||
|
|
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,162308,162308,4194304,256,0,0,8,24,44160,0x7f61e127da80,0x7f61e0a24940,0,0,3932160,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097353.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520722096396,16520721500719,16520722656395,16520722656726
|
||
|
|
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,162308,162308,4194304,256,0,0,12,24,45376,0x7f61e127d900,0x7f61e0a24980,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097359.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520723251434,16520722656395,16520723909830,16520723909810
|
||
|
|
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,162308,162308,4194304,256,0,0,12,24,46336,0x7f61e127d780,0x7f61e0a249c0,0,0,0,0,0,0,3407872,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097356.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520724513067,16520723909830,16520725163265,16520725163593
|
||
|
|
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,162308,162308,4194304,256,0,0,12,24,47552,0x7f61e127d600,0x7f61e0a24a00,0,0,0,0,0,0,4456448,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194593.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520725760801,16520725163265,16520726515740,16520726516594
|
||
|
|
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,162308,162308,4194304,256,0,0,12,24,48512,0x7f61e3a19480,0x7f61e0a24a40,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194573.0000000000,0.0000000000,0.0000000000,0,0,4456448,0,0,0,0,0,0.0000000000,0,0,16520727112242,16520726515740,16520727746456,16520727746748
|
||
|
|
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,162308,162308,4194304,256,0,0,8,24,49472,0x7f61e3a19300,0x7f61e0a24a80,0,0,4456448,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097358.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520728343406,16520727746456,16520728939731,16520728940415
|
||
|
|
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,162308,162308,4194304,256,0,0,12,24,50688,0x7f61e3a19180,0x7f61e0a24ac0,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097363.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520729536553,16520728939731,16520730122927,16520730123421
|
||
|
|
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,162308,162308,4194304,256,0,0,12,24,51648,0x7f61e3a19000,0x7f61e0a24b00,0,0,0,0,0,0,3801088,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097358.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520730728139,16520730120725,16520731313834,16520731316247
|
||
|
|
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,162308,162308,4194304,256,0,0,12,24,52864,0x7f61e127de80,0x7f61e0a24b40,0,0,0,0,0,0,4980736,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194581.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520731913105,16520731313834,16520732622784,16520732625409
|
||
|
|
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,162308,162308,4194304,256,0,0,12,24,54080,0x7f61e127dd00,0x7f61e0a24b80,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194567.0000000000,0.0000000000,0.0000000000,0,0,4980736,0,0,0,0,0,0.0000000000,0,0,16520733221727,16520732622784,16520733912853,16520733915561
|
||
|
|
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,162308,162308,4194304,256,0,0,8,24,55296,0x7f61e127db80,0x7f61e0a24bc0,0,0,4980736,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097359.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520734511389,16520733912853,16520735117483,16520735120207
|
||
|
|
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,162308,162308,4194304,256,0,0,12,24,56768,0x7f61e127da00,0x7f61e0a24c00,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097362.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520735715395,16520735117483,16520736307234,16520736309794
|
||
|
|
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,162308,162308,4194304,256,0,0,12,24,57728,0x7f61e127d880,0x7f61e0a24c40,0,0,0,0,0,0,4194304,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097354.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520736912751,16520736307234,16520737500664,16520737503270
|
||
|
|
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,162308,162308,4194304,256,0,0,12,24,58944,0x7f61e127d700,0x7f61e0a24c80,0,0,0,0,0,0,5505024,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194586.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520738107488,16520737500664,16520738770734,16520738773873
|
||
|
|
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,162308,162308,4194304,256,0,0,12,24,60160,0x7f61e3a19580,0x7f61e0a24cc0,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194593.0000000000,0.0000000000,0.0000000000,0,0,5505024,0,0,0,0,0,0.0000000000,0,0,16520739370051,16520738770734,16520740064003,16520740066746
|
||
|
|
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,162308,162308,4194304,256,0,0,8,24,61376,0x7f61e3a19400,0x7f61e0a24d00,0,0,5505024,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097359.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520740662214,16520740064003,16520741262873,16520741265572
|
||
|
|
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,162308,162308,4194304,256,0,0,12,24,62848,0x7f61e3a19280,0x7f61e0a24d40,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097354.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520741860890,16520741262873,16520742483023,16520742485577
|
||
|
|
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,162308,162308,4194304,256,0,0,12,24,63808,0x7f61e3a19100,0x7f61e0a24d80,0,0,0,0,0,0,4587520,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097356.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520743090155,16520742483023,16520743713893,16520743716871
|
||
|
|
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,162308,162308,4194304,256,0,0,12,24,65024,0x7f61e127df80,0x7f61e0a24dc0,0,0,0,0,0,0,6029312,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194572.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520744313069,16520743713893,16520745007963,16520745010674
|
||
|
|
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,162308,162308,4194304,256,0,0,12,24,66240,0x7f61e127de00,0x7f61e0a24e00,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194562.0000000000,0.0000000000,0.0000000000,0,0,6029312,0,0,0,0,0,0.0000000000,0,0,16520745605132,16520745007963,16520746294992,16520746297836
|
||
|
|
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,162308,162308,4194304,256,0,0,8,24,67456,0x7f61e127dc80,0x7f61e0a24e40,0,0,6029312,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097358.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520746895534,16520746294992,16520747471143,16520747473683
|
||
|
|
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,162308,162308,4194304,256,0,0,12,24,68928,0x7f61e127db00,0x7f61e0a24e80,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097356.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520748072631,16520747471143,16520748692093,16520748694658
|
||
|
|
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,162308,162308,4194304,256,0,0,12,24,70144,0x7f61e127d980,0x7f61e0a24ec0,0,0,0,0,0,0,4980736,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097356.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520749312156,16520748692093,16520749912083,16520749914674
|
||
|
|
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,162308,162308,4194304,256,0,0,12,24,71616,0x7f61e127d800,0x7f61e0a24f00,0,0,0,0,0,0,6553600,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194544.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520750510672,16520749912083,16520751212872,16520751215616
|
||
|
|
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,162308,162308,4194304,256,0,0,12,24,72832,0x7f61e127d680,0x7f61e0a24f40,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194587.0000000000,0.0000000000,0.0000000000,0,0,6553600,0,0,0,0,0,0.0000000000,0,0,16520751814234,16520751212872,16520752480862,16520752483639
|
||
|
|
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,162308,162308,4194304,256,0,0,8,24,74048,0x7f61e3a19500,0x7f61e0a24f80,0,0,6553600,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097355.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520753087727,16520752480862,16520753682132,16520753684575
|
||
|
|
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,162308,162308,4194304,256,0,0,12,24,75776,0x7f61e3a19380,0x7f61e0a24fc0,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097352.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520754282973,16520753682132,16520754875723,16520754877821
|
||
|
|
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,162308,162308,4194304,256,0,0,12,24,76992,0x7f61e3a19200,0x7f61e0a25000,0,0,0,0,0,0,5373952,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097353.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520755489929,16520754875723,16520756080513,16520756082727
|
||
|
|
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,162308,162308,4194304,256,0,0,12,24,78464,0x7f61e3a19080,0x7f61e0a25040,0,0,0,0,0,0,7077888,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194551.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520756683705,16520756080513,16520757347222,16520757349540
|
||
|
|
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,162308,162308,4194304,256,0,0,12,24,79936,0x7f61e127df00,0x7f61e0a25080,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194569.0000000000,0.0000000000,0.0000000000,0,0,7077888,0,0,0,0,0,0.0000000000,0,0,16520757945818,16520757347222,16520758612972,16520758615704
|
||
|
|
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,162308,162308,4194304,256,0,0,8,24,81408,0x7f61e127dd80,0x7f61e0a250c0,0,0,7077888,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097363.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520759211442,16520758612972,16520759878242,16520759880357
|
||
|
|
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,162308,162308,4194304,256,0,0,12,24,83136,0x7f61e127dc00,0x7f61e0a25100,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097352.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520760478715,16520759878242,16520761096312,16520761098913
|
||
|
|
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,162308,162308,4194304,256,0,0,12,24,84352,0x7f61e127da80,0x7f61e0a25140,0,0,0,0,0,0,5767168,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097351.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520761705550,16520761096312,16520762308782,16520762311728
|
||
|
|
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,162308,162308,4194304,256,0,0,12,24,85824,0x7f61e127d900,0x7f61e0a25180,0,0,0,0,0,0,7602176,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194581.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520762908006,16520762308782,16520763600452,16520763603340
|
||
|
|
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,162308,162308,4194304,256,0,0,12,24,87296,0x7f61e127d780,0x7f61e0a251c0,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194565.0000000000,0.0000000000,0.0000000000,0,0,7602176,0,0,0,0,0,0.0000000000,0,0,16520764199398,16520763600452,16520764912121,16520764914922
|
||
|
|
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,162308,162308,4194304,256,0,0,12,24,88768,0x7f61e127d600,0x7f61e0a25200,0,0,7602176,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097357.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520765511080,16520764912121,16520766101391,16520766104258
|
||
|
|
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,162308,162308,4194304,256,0,0,12,24,90752,0x7f61e3a19480,0x7f61e0a25240,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097333.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520766700556,16520766101391,16520767318341,16520767321094
|
||
|
|
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,162308,162308,4194304,256,0,0,12,24,91968,0x7f61e3a19300,0x7f61e0a25280,0,0,0,0,0,0,6160384,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097358.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520767931291,16520767318341,16520768557851,16520768560738
|
||
|
|
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,162308,162308,4194304,256,0,0,12,24,93440,0x7f61e3a19180,0x7f61e0a252c0,0,0,0,0,0,0,8126464,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194595.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520769157096,16520768557851,16520769830801,16520769833351
|
||
|
|
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,162308,162308,4194304,256,0,0,12,24,94912,0x7f61e3a19000,0x7f61e0a25300,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194559.0000000000,0.0000000000,0.0000000000,0,0,8126464,0,0,0,0,0,0.0000000000,0,0,16520770428860,16520769830801,16520771109510,16520771111954
|
||
|
|
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,162308,162308,4194304,256,0,0,12,24,96384,0x7f61e127de80,0x7f61e0a25340,0,0,8126464,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097367.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520771706393,16520771109510,16520772313981,16520772316840
|
||
|
|
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,162308,162308,4194304,256,0,0,12,24,98368,0x7f61e127dd00,0x7f61e0a25380,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097338.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520772912148,16520772313981,16520773526611,16520773529356
|
||
|
|
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,162308,162308,4194304,256,0,0,12,24,99584,0x7f61e127db80,0x7f61e0a253c0,0,0,0,0,0,0,6553600,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097360.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520774133384,16520773526611,16520774746761,16520774749611
|
||
|
|
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,162308,162308,4194304,256,0,0,12,24,101312,0x7f61e127da00,0x7f61e0a25400,0,0,0,0,0,0,8650752,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194580.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520775344949,16520774746761,16520776012991,16520776015724
|
||
|
|
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,162308,162308,4194304,256,0,0,12,24,102784,0x7f61e127d880,0x7f61e0a25440,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194579.0000000000,0.0000000000,0.0000000000,0,0,8650752,0,0,0,0,0,0.0000000000,0,0,16520776610342,16520776012991,16520777291380,16520777294067
|
||
|
|
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,162308,162308,4194304,256,0,0,12,24,104256,0x7f61e127d700,0x7f61e0a25480,0,0,8650752,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097361.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520777888945,16520777291380,16520778501770,16520778504413
|
||
|
|
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,162308,162308,4194304,256,0,0,12,24,106240,0x7f61e3a19580,0x7f61e0a254c0,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097339.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520779101371,16520778501770,16520779726560,16520779729408
|
||
|
|
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,162308,162308,4194304,256,0,0,12,24,107712,0x7f61e3a19400,0x7f61e0a25500,0,0,0,0,0,0,6946816,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097361.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520780331446,16520779726560,16520780963030,16520780965312
|
||
|
|
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,162308,162308,4194304,256,0,0,16,24,109440,0x7f61e3a19280,0x7f61e0a25540,0,0,0,0,0,0,9175040,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194565.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520781561360,16520780963030,16520782241900,16520782244855
|
||
|
|
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,162308,162308,4194304,256,0,0,16,24,111168,0x7f61e3a19100,0x7f61e0a25580,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194591.0000000000,0.0000000000,0.0000000000,0,0,9175040,0,0,0,0,0,0.0000000000,0,0,16520782840743,16520782241900,16520783528289,16520783530848
|
||
|
|
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,162308,162308,4194304,256,0,0,8,24,112896,0x7f61e127df80,0x7f61e0a255c0,0,0,9175040,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097367.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520784126836,16520783528289,16520784711480,16520784714385
|
||
|
|
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,162308,162308,4194304,256,0,0,12,24,115136,0x7f61e127de00,0x7f61e0a25600,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097329.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520785310103,16520784711480,16520785957710,16520785960429
|
||
|
|
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,162308,162308,4194304,256,0,0,12,24,116608,0x7f61e127dc80,0x7f61e0a25640,0,0,0,0,0,0,7340032,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097357.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520786567867,16520785957710,16520787200420,16520787203413
|
||
|
|
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,162308,162308,4194304,256,0,0,16,24,118336,0x7f61e127db00,0x7f61e0a25680,0,0,0,0,0,0,9699328,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194578.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520787806701,16520787200420,16520788488729,16520788491566
|
||
|
|
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,162308,162308,4194304,256,0,0,16,24,120064,0x7f61e127d980,0x7f61e0a256c0,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194597.0000000000,0.0000000000,0.0000000000,0,0,9699328,0,0,0,0,0,0.0000000000,0,0,16520789093793,16520788488729,16520789792398,16520789795498
|
||
|
|
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,162308,162308,4194304,256,0,0,12,24,121792,0x7f61e127d800,0x7f61e0a25700,0,0,9699328,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097368.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520790401985,16520789792398,16520790976549,16520790979234
|
||
|
|
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,162308,162308,4194304,256,0,0,12,24,124032,0x7f61e127d680,0x7f61e0a25740,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097335.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520791581302,16520790976549,16520792207099,16520792209649
|
||
|
|
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,162308,162308,4194304,256,0,0,12,24,125504,0x7f61e3a19500,0x7f61e0a25780,0,0,0,0,0,0,8126464,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097364.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520792817707,16520792207099,16520793423569,16520793426664
|
||
|
|
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,162308,162308,4194304,256,0,0,12,24,127488,0x7f61e3a19380,0x7f61e0a257c0,0,0,0,0,0,0,10747904,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194603.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520794022432,16520793423568,16520794730116,16520794732856
|
||
|
|
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,162308,162308,4194304,256,0,0,12,24,129216,0x7f61e3a19200,0x7f61e0a25800,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194601.0000000000,0.0000000000,0.0000000000,0,0,10747904,0,0,0,0,0,0.0000000000,0,0,16520795329764,16520794730116,16520796011546,16520796014239
|
||
|
|
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,162308,162308,4194304,256,0,0,12,24,130944,0x7f61e3a19080,0x7f61e0a25840,0,0,10747904,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097361.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520796612637,16520796011546,16520797211056,16520797213785
|
||
|
|
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,162308,162308,4194304,256,0,0,12,24,133440,0x7f61e127df00,0x7f61e0a25880,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097337.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520797811033,16520797211056,16520798491686,16520798494468
|
||
|
|
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,162308,162308,4194304,256,0,0,12,24,134912,0x7f61e127dd80,0x7f61e0a258c0,0,0,0,0,0,0,8912896,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097371.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520799100015,16520798491686,16520799699836,16520799702713
|
||
|
|
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,162308,162308,4194304,256,0,0,12,24,136896,0x7f61e127dc00,0x7f61e0a25900,0,0,0,0,0,0,11796480,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194625.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520800299761,16520799699836,16520800979506,16520800982316
|
||
|
|
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,162308,162308,4194304,256,0,0,12,24,138880,0x7f61e127da80,0x7f61e0a25940,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194593.0000000000,0.0000000000,0.0000000000,0,0,11796480,0,0,0,0,0,0.0000000000,0,0,16520801581164,16520800979506,16520802260455,16520802264069
|
||
|
|
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,162308,162308,4194304,256,0,0,12,24,140864,0x7f61e127d900,0x7f61e0a25980,0,0,11796480,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097354.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520802863167,16520802260455,16520803457405,16520803460265
|
||
|
|
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,162308,162308,4194304,256,0,0,12,24,143616,0x7f61e127d780,0x7f61e0a259c0,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097338.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520804054944,16520803457405,16520804724435,16520804727009
|
||
|
|
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,162308,162308,4194304,256,0,0,12,24,145344,0x7f61e127d600,0x7f61e0a25a00,0,0,0,0,0,0,9699328,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097366.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520805334497,16520804724435,16520805920905,16520805923745
|
||
|
|
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,162308,162308,4194304,256,0,0,12,24,147584,0x7f61e3a19480,0x7f61e0a25a40,0,0,0,0,0,0,12845056,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194609.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520806522493,16520805920905,16520807207295,16520807210338
|
||
|
|
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,162308,162308,4194304,256,0,0,12,24,149568,0x7f61e3a19300,0x7f61e0a25a80,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194608.0000000000,0.0000000000,0.0000000000,0,0,12845056,0,0,0,0,0,0.0000000000,0,0,16520807806036,16520807207295,16520808469845,16520808472941
|
||
|
|
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,162308,162308,4194304,256,0,0,12,24,151552,0x7f61e3a19180,0x7f61e0a25ac0,0,0,12845056,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097345.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520809067579,16520808469845,16520809631275,16520809634328
|
||
|
|
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,162308,162308,4194304,256,0,0,12,24,154304,0x7f61e3a19000,0x7f61e0a25b00,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097340.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520810229616,16520809631275,16520810927745,16520810930521
|
||
|
|
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,162308,162308,4194304,256,0,0,12,24,156288,0x7f61e127de80,0x7f61e0a25b40,0,0,0,0,0,0,11272192,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097361.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520811537908,16520810927745,16520812134455,16520812137166
|
||
|
|
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,162308,162308,4194304,256,0,0,12,24,158784,0x7f61e127dd00,0x7f61e0a25b80,0,0,0,0,0,0,14942208,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194635.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520812733215,16520812134455,16520813378125,16520813384001
|
||
|
|
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,162308,162308,4194304,256,0,0,12,24,161024,0x7f61e127db80,0x7f61e0a25bc0,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194632.0000000000,0.0000000000,0.0000000000,0,0,14942208,0,0,0,0,0,0.0000000000,0,0,16520813979759,16520813378125,16520814672354,16520814675143
|
||
|
|
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,162308,162308,4194304,256,0,0,12,24,163264,0x7f61e127da00,0x7f61e0a25c00,0,0,14942208,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097344.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520815273421,16520814672354,16520815868984,16520815871829
|
||
|
|
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,162308,162308,4194304,256,0,0,12,24,166528,0x7f61e127d880,0x7f61e0a25c40,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097342.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520816478427,16520815868984,16520817195694,16520817260638
|
||
|
|
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,162308,162308,4194304,256,0,0,12,24,168512,0x7f61e127d700,0x7f61e0a25c80,0,0,0,0,0,0,12845056,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097356.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520817810048,16520817195694,16520818418084,16520818420856
|
||
|
|
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,162308,162308,4194304,256,0,0,12,24,171264,0x7f61e3a19580,0x7f61e0a25cc0,0,0,0,0,0,0,17039360,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194642.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520819019444,16520818418084,16520819710073,16520819712858
|
||
|
|
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,162308,162308,4194304,256,0,0,12,24,173760,0x7f61e3a19400,0x7f61e0a25d00,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194646.0000000000,0.0000000000,0.0000000000,0,0,17039360,0,0,0,0,0,0.0000000000,0,0,16520820312846,16520819710073,16520820972463,16520820977362
|
||
|
|
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,162308,162308,4194304,256,0,0,12,24,176256,0x7f61e3a19280,0x7f61e0a25d40,0,0,17039360,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097336.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520821572340,16520820972463,16520822197733,16520822200546
|
||
|
|
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,162308,162308,4194304,256,0,0,12,24,179776,0x7f61e3a19100,0x7f61e0a25d80,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097351.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520822797805,16520822197733,16520823521082,16520823585746
|
||
|
|
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,162308,162308,4194304,256,0,0,12,24,182272,0x7f61e127df80,0x7f61e0a25dc0,0,0,0,0,0,0,15990784,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097343.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520824135655,16520823521082,16520824726992,16520824729794
|
||
|
|
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,162308,162308,4194304,256,0,0,12,24,185536,0x7f61e127de00,0x7f61e0a25e00,0,0,0,0,0,0,21233664,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194643.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520825331882,16520824726992,16520825991622,16520826055415
|
||
|
|
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,162308,162308,4194304,256,0,0,12,24,188544,0x7f61e127dc80,0x7f61e0a25e40,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194638.0000000000,0.0000000000,0.0000000000,0,0,21233664,0,0,0,0,0,0.0000000000,0,0,16520826596045,16520825991622,16520827289211,16520827328598
|
||
|
|
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,162308,162308,4194304,256,0,0,12,24,191552,0x7f61e127db00,0x7f61e0a25e80,0,0,21233664,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097370.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520827891977,16520827289211,16520828524721,16520828527694
|
||
|
|
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,162308,162308,4194304,256,0,0,12,24,195840,0x7f61e127d980,0x7f61e0a25ec0,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097353.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520829121802,16520828524721,16520829876870,16520829940062
|
||
|
|
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,162308,162308,4194304,256,0,0,12,24,198592,0x7f61e127d800,0x7f61e0a25f00,0,0,0,0,0,0,19136512,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097347.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520830491322,16520829876870,16520831122940,16520831125718
|
||
|
|
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,162308,162308,4194304,256,0,0,12,24,202368,0x7f61e127d680,0x7f61e0a25f40,0,0,0,0,0,0,25427968,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194619.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520831721736,16520831122940,16520832423570,16520832466859
|
||
|
|
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,162308,162308,4194304,256,0,0,12,24,205888,0x7f61e3a19500,0x7f61e0a25f80,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194628.0000000000,0.0000000000,0.0000000000,0,0,25427968,0,0,0,0,0,0.0000000000,0,0,16520833029498,16520832423570,16520833734119,16520833798740
|
||
|
|
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,162308,162308,4194304,256,0,0,12,24,209408,0x7f61e3a19380,0x7f61e0a25fc0,0,0,25427968,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097373.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520834339860,16520833734119,16520835043548,16520835047764
|
||
|
|
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,162308,162308,4194304,256,0,0,12,24,214464,0x7f61e3a19200,0x7f61e0a26000,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097368.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520835645652,16520835043548,16520836472177,16520836536270
|
||
|
|
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,162308,162308,4194304,256,0,0,12,24,217728,0x7f61e3a19080,0x7f61e0a26040,0,0,0,0,0,0,22282240,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097353.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520837078280,16520836472177,16520837714727,16520837717566
|
||
|
|
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,162308,162308,4194304,256,0,0,12,24,222016,0x7f61e127df00,0x7f61e0a26080,0,0,0,0,0,0,29622272,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194605.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520838313285,16520837714727,16520839043036,16520839107805
|
||
|
|
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,162308,162308,4194304,256,0,0,12,24,226048,0x7f61e127dd80,0x7f61e0a260c0,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194604.0000000000,0.0000000000,0.0000000000,0,0,29622272,0,0,0,0,0,0.0000000000,0,0,16520839641856,16520839043036,16520840378705,16520840421097
|
||
|
|
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,162308,162308,4194304,256,0,0,12,24,230080,0x7f61e127dc00,0x7f61e0a26100,0,0,29622272,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097377.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520840976686,16520840378705,16520841669574,16520841732399
|
||
|
|
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,162308,162308,4194304,256,0,0,12,24,235904,0x7f61e127da80,0x7f61e0a26140,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097380.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520842273979,16520841669574,16520843156122,16520843220314
|
||
|
|
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,162308,162308,4194304,256,0,0,12,24,239424,0x7f61e127d900,0x7f61e0a26180,0,0,0,0,0,0,25427968,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097361.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520843762534,16520843156122,16520844421712,16520844427480
|
||
|
|
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,162308,162308,4194304,256,0,0,12,24,244224,0x7f61e127d780,0x7f61e0a261c0,0,0,0,0,0,0,33816576,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194622.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520845019328,16520844421712,16520845769701,16520845832248
|
||
|
|
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,162308,162308,4194304,256,0,0,12,24,248768,0x7f61e127d600,0x7f61e0a26200,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194608.0000000000,0.0000000000,0.0000000000,0,0,33816576,0,0,0,0,0,0.0000000000,0,0,16520846368538,16520845769701,16520847108410,16520847172209
|
||
|
|
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,162308,162308,4194304,256,0,0,12,24,253312,0x7f61e3a19480,0x7f61e0a26240,0,0,33816576,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097386.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520847706579,16520847108410,16520848447119,16520848511539
|
||
|
|
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,162308,162308,4194304,256,0,0,8,24,255552,0x7f61e3a19300,0x7f61e0a26280,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097319.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520849052469,16520848447119,16520849985827,16520850050843
|
||
|
|
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,162308,162308,4194304,256,0,0,12,24,259840,0x7f61e3a19180,0x7f61e0a262c0,0,0,0,0,0,0,31719424,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097369.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520850595343,16520849985827,16520851326776,16520851390703
|
||
|
|
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,162308,162308,4194304,256,0,0,12,24,265664,0x7f61e3a19000,0x7f61e0a26300,0,0,0,0,0,0,42205184,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194635.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520851925474,16520851326776,16520852706605,16520852771103
|
||
|
|
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,162308,162308,4194304,256,0,0,12,24,271232,0x7f61e127de80,0x7f61e0a26340,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194603.0000000000,0.0000000000,0.0000000000,0,0,42205184,0,0,0,0,0,0.0000000000,0,0,16520853305023,16520852706605,16520854096673,16520854164972
|
||
|
|
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,162308,162308,4194304,256,0,0,8,24,273216,0x7f61e127dd00,0x7f61e0a26380,0,0,42205184,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097331.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520854694152,16520854096673,16520855490902,16520855553321
|
||
|
|
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,162308,162308,4194304,256,0,0,8,24,275712,0x7f61e127db80,0x7f61e0a263c0,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097326.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520856090881,16520855496381,16520857122301,16520857170091
|
||
|
|
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,162308,162308,4194304,256,0,0,12,24,280768,0x7f61e127da00,0x7f61e0a26400,0,0,0,0,0,0,38010880,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097389.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520857722511,16520857122301,16520858486141,16520858547631
|
||
|
|
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,162308,162308,4194304,256,0,0,12,24,287616,0x7f61e127d880,0x7f61e0a26440,0,0,0,0,0,0,50593792,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194621.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520859080761,16520858486141,16520859918142,16520859976968
|
||
|
|
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,162308,162308,4194304,256,0,0,12,24,294208,0x7f61e127d700,0x7f61e0a26480,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194617.0000000000,0.0000000000,0.0000000000,0,0,50593792,0,0,0,0,0,0.0000000000,0,0,16520860509548,16520859918142,16520861337823,16520861397966
|
||
|
|
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,162308,162308,4194304,256,0,0,8,24,296960,0x7f61e3a19580,0x7f61e0a264c0,0,0,50593792,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097334.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520861929366,16520861337823,16520862795424,16520862855652
|
||
|
|
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,162308,162308,4194304,256,0,0,8,24,299968,0x7f61e3a19400,0x7f61e0a26500,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097329.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520863388442,16520862795424,16520864547104,16520864606388
|
||
|
|
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,162308,162308,4194304,256,0,0,8,24,302720,0x7f61e3a19280,0x7f61e0a26540,0,0,0,0,0,0,67371008,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097330.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520865147738,16520864547104,16520866070945,16520866130862
|
||
|
|
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,162308,162308,4194304,256,0,0,12,24,305472,0x7f61e3a19100,0x7f61e0a26580,0,0,0,0,0,0,67371008,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194552.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520866665402,16520866070945,16520867591906,16520867649036
|
||
|
|
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,162308,162308,4194304,256,0,0,12,24,308224,0x7f61e127df80,0x7f61e0a265c0,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194555.0000000000,0.0000000000,0.0000000000,0,0,67371008,0,0,0,0,0,0.0000000000,0,0,16520868184406,16520867591906,16520869133667,16520869190820
|
||
|
|
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,162308,162308,4194304,256,0,0,8,24,310976,0x7f61e127de00,0x7f61e0a26600,0,0,67371008,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097332.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520869725570,16520869133667,16520870727748,16520870787921
|
||
|
|
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,162308,162308,4194304,256,0,0,8,24,313216,0x7f61e127dc80,0x7f61e0a26640,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097319.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520871331171,16520870727748,16520872686949,16520872745779
|
||
|
|
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,162308,162308,4194304,256,0,0,8,24,315968,0x7f61e127db00,0x7f61e0a26680,0,0,0,0,0,0,134479872,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097328.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520873288419,16520872686949,16520874614630,16520874676238
|
||
|
|
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,162308,162308,4194304,256,0,0,12,24,318720,0x7f61e127d980,0x7f61e0a266c0,0,0,0,0,0,0,134479872,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194547.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520875211978,16520874614630,16520876595751,16520876653185
|
||
|
|
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,162308,162308,4194304,256,0,0,12,24,321472,0x7f61e127d800,0x7f61e0a26700,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194552.0000000000,0.0000000000,0.0000000000,0,0,134479872,0,0,0,0,0,0.0000000000,0,0,16520877191805,16520876595751,16520878578792,16520878639902
|
||
|
|
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,162308,162308,4194304,256,0,0,8,24,324224,0x7f61e127d680,0x7f61e0a26740,0,0,134479872,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097329.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520879171322,16520878578792,16520880519593,16520880579151
|
||
|
|
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,162308,162308,4194304,256,0,0,8,24,326464,0x7f61e3a19500,0x7f61e0a26780,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097315.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520881111391,16520880519593,16520883284715,16520883347019
|
||
|
|
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,162308,162308,4194304,256,0,0,8,24,329216,0x7f61e3a19380,0x7f61e0a267c0,0,0,0,0,0,0,268697600,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097332.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520883891169,16520883284715,16520886041836,16520886122277
|
||
|
|
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,162308,162308,4194304,256,0,0,12,24,331968,0x7f61e3a19200,0x7f61e0a26800,0,0,0,0,0,0,268697600,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194552.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520886635238,16520886041836,16520888859758,16520888923314
|
||
|
|
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,162308,162308,4194304,256,0,0,12,24,334720,0x7f61e3a19080,0x7f61e0a26840,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194556.0000000000,0.0000000000,0.0000000000,0,0,268697600,0,0,0,0,0,0.0000000000,0,0,16520889452185,16520888859758,16520891649519,16520891711172
|
||
|
|
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,162308,162308,4194304,256,0,0,8,24,337472,0x7f61e127df00,0x7f61e0a26880,0,0,268697600,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097330.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520892243172,16520891649519,16520894431121,16520894494909
|
||
|
|
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,162308,162308,4194304,256,0,0,8,24,0,0x7f61e127dd80,0x7f61e0a268c0,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097317.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,16520895024680,16520894431121,16520898866963,16520898930916
|