169 lines
50 KiB
CSV
169 lines
50 KiB
CSV
Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,sig,obj,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,GRBM_COUNT,GRBM_GUI_ACTIVE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,DispatchNs,BeginNs,EndNs,CompleteNs
|
|
0,__amd_rocclr_fillBuffer.kd,0,0,0,869685,869690,33554432,256,0,0,8,32,6464,0x0,0x7fdec2404180,4040784,3830766,524288,505097,505097,505097,0,4178,0,0,482832,0,12075315587403796,12075319737980510,12075319738305467,12075315835499200
|
|
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,869685,869690,32768,256,0,0,24,24,12480,0x0,0x7fdec2435100,219112,74883,512,27388,27388,27388,0,2343,0,0,26941,0,12075315849868370,12075319753341463,12075319753348183,12075315850220494
|
|
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,869685,869690,4194304,256,0,0,24,24,12928,0x7fdfcdfa6900,0x7fdec2435140,1809384,1646053,65536,226172,226172,226172,0,2355,0,0,215251,0,12075315850313286,12075319753399863,12075319753530422,12075315850719822
|
|
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,869685,869690,4194304,256,0,0,36,24,13632,0x7fdfcdfa6800,0x7fdec2435180,3169936,3005273,65536,396241,396241,396241,0,2347,0,0,392231,0,12075315850814648,12075319753574262,12075319753821780,12075315851358448
|
|
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,869685,869690,4194304,256,0,0,28,24,14080,0x7fdfcdfa6700,0x7fdec24351c0,3189352,3021400,65536,398668,398668,398668,0,2359,0,0,398419,0,12075315851432586,12075319753956658,12075319754204016,12075315851956329
|
|
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,869685,869690,4194304,256,0,0,24,24,14528,0x7fdfcdfa6600,0x7fdec2435200,1793488,1638838,65536,224185,224185,224185,0,2434,0,0,217278,0,12075315851984842,12075319754338095,12075319754463374,12075315852385677
|
|
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,869685,869690,4194304,256,0,0,24,24,14976,0x7fdfcdfa6500,0x7fdec2435240,1717408,1550057,65536,214675,214675,214675,0,2327,0,0,220394,0,12075315852437914,12075319754493134,12075319754618413,12075315852816578
|
|
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,869685,869690,4194304,256,0,0,24,24,15424,0x7fdfcdfa6400,0x7fdec2435280,1714320,1556658,65536,214289,214289,214289,0,2318,0,0,209547,0,12075315852896025,12075319754675693,12075319754799852,12075315853264290
|
|
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,869685,869690,4194304,256,0,0,28,24,16128,0x7fdfcdfa6300,0x7fdec24352c0,3257312,3078800,65536,407163,407163,407163,0,2505,0,0,397597,0,12075315853313741,12075319754833611,12075319755084649,12075315853868222
|
|
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,869685,869690,4194304,256,0,0,28,24,16832,0x7fdfcdfa6a00,0x7fdec2435300,3180112,3016507,65536,397513,397513,397513,0,2500,0,0,398451,158,12075315853890914,12075319755219048,12075319755463206,12075315854451385
|
|
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,869685,869690,4194304,256,0,0,24,24,17536,0x7fdfcdfa6900,0x7fdec2435340,1737576,1575579,65536,217196,217196,217196,0,2380,0,0,208961,0,12075315854480008,12075319755598085,12075319755723364,12075315854860956
|
|
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,869685,869690,4194304,256,0,0,24,24,18240,0x7fdfcdfa6800,0x7fdec2435380,1771152,1616521,65536,221393,221393,221393,0,2338,0,0,212395,0,12075315854910338,12075319755752164,12075319755877123,12075315855297958
|
|
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,869685,869690,4194304,256,0,0,24,24,18944,0x7fdfcdfa6700,0x7fdec24353c0,1694304,1525377,65536,211787,211787,211787,0,2410,0,0,212491,0,12075315855357649,12075319755920322,12075319756045121,12075315855730422
|
|
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,869685,869690,4194304,256,0,0,28,24,19904,0x7fdfcdfa6600,0x7fdec2435400,3229712,3064323,65536,403713,403713,403713,0,2529,0,0,405416,0,12075315855780796,12075319756075201,12075319756325759,12075315856338081
|
|
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,869685,869690,4194304,256,0,0,28,24,20608,0x7fdfcdfa6500,0x7fdec2435440,3643816,3004078,65536,455476,455476,455476,158,2510,0,0,390636,0,12075315856367586,12075319756460158,12075319756708796,12075315856941753
|
|
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,869685,869690,4194304,256,0,0,24,24,21312,0x7fdfcdfa6400,0x7fdec2435480,1718160,1552053,65536,214769,214769,214769,0,2281,0,0,216843,0,12075315856976567,12075319756839835,12075319756964794,12075315857370039
|
|
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,869685,869690,4194304,256,0,0,24,24,22016,0x7fdfcdfa6300,0x7fdec24354c0,1740064,1576789,65536,217507,217507,217507,0,2389,0,0,216268,0,12075315857418979,12075319756996954,12075319757121913,12075315857806269
|
|
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,869685,869690,4194304,256,0,0,24,24,22720,0x7fdfcdfa6a00,0x7fdec2435500,1707024,1546990,65536,213377,213377,213377,0,2296,0,0,210444,0,12075315857865810,12075319757164152,12075319757288151,12075315858249563
|
|
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,869685,869690,4194304,256,0,0,28,24,23680,0x7fdfcdfa6900,0x7fdec2435540,3221352,3046256,65536,402668,402668,402668,0,2501,0,0,392492,0,12075315858300477,12075319757318231,12075319757567189,12075315858849608
|
|
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,869685,869690,4194304,256,0,0,28,24,24384,0x7fdfcdfa6800,0x7fdec2435580,3144592,2984630,65536,393073,393073,393073,0,2566,0,0,400764,158,12075315858879614,12075319757699028,12075319757981906,12075315859423314
|
|
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,869685,869690,4194304,256,0,0,24,24,25088,0x7fdfcdfa6700,0x7fdec24355c0,1765672,1607605,65536,220708,220708,220708,0,2305,0,0,214500,0,12075315859450855,12075319758051665,12075319758176304,12075315859834117
|
|
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,869685,869690,4194304,256,0,0,24,24,25792,0x7fdfcdfa6600,0x7fdec2435600,1661584,1501547,65536,207697,207697,207697,0,2249,0,0,215644,0,12075315859883369,12075319758209904,12075319758334863,12075315860264657
|
|
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,869685,869690,4194304,256,0,0,24,24,26496,0x7fdfcdfa6500,0x7fdec2435640,1722976,1564474,65536,215371,215371,215371,0,2347,0,0,215499,0,12075315860323707,12075319758378382,12075319758502221,12075315860695518
|
|
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,869685,869690,4194304,256,0,0,28,24,27712,0x7fdfcdfa6400,0x7fdec2435680,3255760,3066445,65536,406969,406969,406969,0,2468,0,0,399867,158,12075315860737576,12075319758533741,12075319758779179,12075315861290153
|
|
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,869685,869690,4194304,256,0,0,28,24,28416,0x7fdfcdfa6300,0x7fdec24356c0,3170080,2999943,65536,396259,396259,396259,0,2530,0,0,403444,158,12075315861315460,12075319758864778,12075319759114376,12075315861865602
|
|
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,869685,869690,4194304,256,0,0,24,24,29120,0x7fdfcdfa6a00,0x7fdec2435700,1674640,1520178,65536,209329,209329,209329,0,2306,0,0,216155,0,12075315861892973,12075319759209256,12075319759333095,12075315862275694
|
|
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,869685,869690,4194304,256,0,0,24,24,30080,0x7fdfcdfa6900,0x7fdec2435740,1770528,1606221,65536,221315,221315,221315,0,2371,0,0,211010,0,12075315862325356,12075319759364774,12075319759489253,12075315862709420
|
|
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,869685,869690,4194304,256,0,0,24,24,30784,0x7fdfcdfa6800,0x7fdec2435780,1749392,1585041,65536,218673,218673,218673,0,2381,0,0,210845,0,12075315862767638,12075319759529893,12075319759654852,12075315863136984
|
|
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,869685,869690,4194304,256,0,0,28,24,32000,0x7fdfcdfa6700,0x7fdec24357c0,3228640,3056689,65536,403579,403579,403579,0,2456,0,0,393939,0,12075315863188350,12075319759687812,12075319759935810,12075315863733292
|
|
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,869685,869690,4194304,256,0,0,28,24,32960,0x7fdfcdfa6600,0x7fdec2435800,3200208,3016637,65536,400025,400025,400025,0,2507,0,0,405570,0,12075315863765382,12075319760050849,12075319760294207,12075315864306187
|
|
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,869685,869690,4194304,256,0,0,24,24,33920,0x7fdfcdfa6500,0x7fdec2435840,1672160,1505023,65536,209019,209019,209019,0,2340,0,0,210084,0,12075315864329931,12075319760430366,12075319760555165,12075315864712031
|
|
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,869685,869690,4194304,256,0,0,24,24,34880,0x7fdfcdfa6400,0x7fdec2435880,1770192,1603134,65536,221273,221273,221273,0,2290,0,0,213014,0,12075315864761353,12075319760583164,12075319760708763,12075315865152028
|
|
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,869685,869690,4194304,256,0,0,24,24,35840,0x7fdfcdfa6300,0x7fdec24358c0,1675040,1515023,65536,209379,209379,209379,0,2352,0,0,214578,0,12075315865211409,12075319760750043,12075319760874362,12075315865578982
|
|
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,869685,869690,4194304,256,0,0,28,24,37312,0x7fdfcdfa6a00,0x7fdec2435900,3113680,2925202,65536,389209,389209,389209,0,2239,0,0,393465,0,12075315865626741,12075319760903962,12075319761151000,12075315866171663
|
|
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,869685,869690,4194304,256,0,0,28,24,38272,0x7fdfcdfa6900,0x7fdec2435940,3640872,3013320,65536,455108,455108,455108,158,2299,0,0,392748,0,12075315866196539,12075319761269719,12075319761513717,12075315866783119
|
|
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,869685,869690,4194304,256,0,0,24,24,39232,0x7fdfcdfa6800,0x7fdec2435980,1741392,1569335,65536,217673,217673,217673,0,2275,0,0,208551,0,12075315866820739,12075319761624916,12075319761750355,12075315867205634
|
|
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,869685,869690,4194304,256,0,0,24,24,40192,0x7fdfcdfa6700,0x7fdec24359c0,1791840,1633357,65536,223979,223979,223979,0,2351,0,0,215906,0,12075315867247572,12075319761780435,12075319761906673,12075315867644670
|
|
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,869685,869690,4194304,256,0,0,24,24,41152,0x7fdfcdfa6600,0x7fdec2435a00,1742032,1580598,65536,217753,217753,217753,0,4425,0,0,214796,0,12075315867702437,12075319761948273,12075319762072432,12075315868078666
|
|
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,869685,869690,4194304,256,0,0,28,24,42624,0x7fdfcdfa6500,0x7fdec2435a40,3198624,3027370,65536,399827,399827,399827,0,2530,0,0,396804,0,12075315868128289,12075319762101072,12075319762350030,12075315868679603
|
|
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,869685,869690,4194304,256,0,0,28,24,43584,0x7fdfcdfa6400,0x7fdec2435a80,3139600,2974211,65536,392449,392449,392449,0,2490,0,0,395918,0,12075315868707275,12075319762398189,12075319762642187,12075315869260813
|
|
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,869685,869690,4194304,256,0,0,24,24,44544,0x7fdfcdfa6300,0x7fdec2435ac0,1715880,1558726,65536,214484,214484,214484,0,2264,0,0,213692,0,12075315869284387,12075319762686187,12075319762811146,12075315869693347
|
|
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,869685,869690,4194304,256,0,0,24,24,45760,0x7fdfcdfa6a00,0x7fdec2435b00,1817488,1658876,65536,227185,227185,227185,0,2321,0,0,221438,0,12075315869743690,12075319762840266,12075319762965705,12075315870082821
|
|
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,869685,869690,4194304,256,0,0,24,24,46720,0x7fdfcdfa6900,0x7fdec2435b40,1662248,1502006,65536,207780,207780,207780,0,2297,0,0,219443,0,12075315870145487,12075319763007624,12075319763132423,12075315870453700
|
|
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,869685,869690,4194304,256,0,0,28,24,48448,0x7fdfcdfa6800,0x7fdec2435b80,3208208,3029913,65536,401025,401025,401025,0,2493,0,0,413315,0,12075315870504013,12075319763162183,12075319763412261,12075315870989235
|
|
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,869685,869690,4194304,256,0,0,28,24,49408,0x7fdfcdfa6700,0x7fdec2435bc0,3684008,3027904,65536,460500,460500,460500,158,2474,0,0,400634,0,12075315871024430,12075319763457221,12075319763739778,12075315871551790
|
|
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,869685,869690,4194304,256,0,0,24,24,50368,0x7fdfcdfa6600,0x7fdec2435c00,1672464,1500763,65536,209057,209057,209057,0,2326,0,0,218189,0,12075315871581736,12075319763786178,12075319763911137,12075315871900859
|
|
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,869685,869690,4194304,256,0,0,24,24,51584,0x7fdfcdfa6500,0x7fdec2435c40,1754336,1589687,65536,219291,219291,219291,0,2315,0,0,219284,0,12075315871951823,12075319763944897,12075319764071776,12075315872283289
|
|
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,869685,869690,4194304,256,0,0,24,24,52544,0x7fdfcdfa6400,0x7fdec2435c80,1657360,1494334,65536,207169,207169,207169,0,2291,0,0,217406,0,12075315872344593,12075319764114495,12075319764239934,12075315872649650
|
|
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,869685,869690,4194304,256,0,0,28,24,54272,0x7fdfcdfa6300,0x7fdec2435cc0,3251936,3086276,65536,406491,406491,406491,0,2453,0,0,409653,0,12075315872698331,12075319764268574,12075319764522172,12075315873184554
|
|
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,869685,869690,4194304,256,0,0,28,24,55488,0x7fdfcdfa6a00,0x7fdec2435d00,3146256,2963988,65536,393281,393281,393281,0,2477,0,0,398124,0,12075315873208398,12075319764567132,12075319764811770,12075315873700913
|
|
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,869685,869690,4194304,256,0,0,24,24,56704,0x7fdfcdfa6900,0x7fdec2435d40,1772712,1613211,65536,221588,221588,221588,0,4143,0,0,209665,0,12075315873725409,12075319764860249,12075319764984728,12075315874054200
|
|
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,869685,869690,4194304,256,0,0,24,24,58176,0x7fdfcdfa6800,0x7fdec2435d80,1782736,1624303,65536,222841,222841,222841,0,2497,0,0,225310,0,12075315874103231,12075319765018008,12075319765146487,12075315874429698
|
|
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,869685,869690,4194304,256,0,0,24,24,59392,0x7fdfcdfa6700,0x7fdec2435dc0,1716072,1555585,65536,214508,214508,214508,0,2332,0,0,209489,0,12075315874489068,12075319765189207,12075319765314486,12075315874799495
|
|
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,869685,869690,4194304,256,0,0,28,24,61376,0x7fdfcdfa6600,0x7fdec2435e00,3143376,2966495,65536,392921,392921,392921,0,2328,0,0,416211,0,12075315874849157,12075319765346325,12075319765598163,12075315875332685
|
|
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,869685,869690,4194304,256,0,0,28,24,62592,0x7fdfcdfa6500,0x7fdec2435e40,3194024,3016831,65536,399252,399252,399252,0,2537,0,0,394249,0,12075315875355508,12075319765641843,12075319765886321,12075315875856218
|
|
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,869685,869690,4194304,256,0,0,24,24,63808,0x7fdfcdfa6400,0x7fdec2435e80,1699856,1543353,65536,212481,212481,212481,0,2298,0,0,268359,0,12075315875887607,12075319765932561,12075319766058000,12075315876207301
|
|
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,869685,869690,4194304,256,0,0,24,24,65280,0x7fdfcdfa6300,0x7fdec2435ec0,1812128,1641405,65536,226515,226515,226515,0,2374,0,0,226059,0,12075315876258145,12075319766085679,12075319766215758,12075315876586746
|
|
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,869685,869690,4194304,256,0,0,24,24,66496,0x7fdfcdfa6a00,0x7fdec2435f00,1699792,1540917,65536,212473,212473,212473,0,4736,0,0,215804,0,12075315876648390,12075319766258478,12075319766383757,12075315876952215
|
|
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,869685,869690,4194304,256,0,0,28,24,68480,0x7fdfcdfa6900,0x7fdec2435f40,3266216,3062308,65536,408276,408276,408276,0,2474,0,0,415635,0,12075315877007377,12075319766416397,12075319766670795,12075315877496246
|
|
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,869685,869690,4194304,256,0,0,28,24,69696,0x7fdfcdfa6800,0x7fdec2435f80,3151504,2969093,65536,393937,393937,393937,0,2471,0,0,397002,0,12075315877519168,12075319766710954,12075319766955112,12075315878016021
|
|
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,869685,869690,4194304,256,0,0,24,24,70912,0x7fdfcdfa6700,0x7fdec2435fc0,1724008,1562109,65536,215500,215500,215500,0,2371,0,0,278390,0,12075315878039325,12075319766994152,12075319767118951,12075315878374147
|
|
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,869685,869690,4194304,256,0,0,24,24,72384,0x7fdfcdfa6600,0x7fdec2436000,1798736,1629771,65536,224841,224841,224841,0,2462,0,0,221798,0,12075315878423659,12075319767146791,12075319767284230,12075315878752350
|
|
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,869685,869690,4194304,256,0,0,24,24,73600,0x7fdfcdfa6500,0x7fdec2436040,1688168,1527612,65536,211020,211020,211020,0,2471,0,0,208450,0,12075315878812862,12075319767328229,12075319767452868,12075315879116186
|
|
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,869685,869690,4194304,256,0,0,28,24,75840,0x7fdfcdfa6400,0x7fdec2436080,3209744,3030054,65536,401217,401217,401217,0,2513,0,0,408694,0,12075315879166048,12075319767481668,12075319767739746,12075315879652833
|
|
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,869685,869690,4194304,256,0,0,28,24,77056,0x7fdfcdfa6300,0x7fdec24360c0,3202016,3024999,65536,400251,400251,400251,0,2516,0,0,392940,158,12075315879682949,12075319767784065,12075319768030143,12075315880163953
|
|
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,869685,869690,4194304,256,0,0,24,24,78272,0x7fdfcdfa6a00,0x7fdec2436100,1704336,1547526,65536,213041,213041,213041,0,2347,0,0,208865,0,12075315880190843,12075319768082943,12075319768207902,12075315880514183
|
|
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,869685,869690,4194304,256,0,0,24,24,80000,0x7fdfcdfa6900,0x7fdec2436140,1869088,1685810,65536,233635,233635,233635,0,2347,0,0,229472,0,12075315880564357,12075319768238622,12075319768381021,12075315880890012
|
|
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,869685,869690,4194304,256,0,0,24,24,81216,0x7fdfcdfa6800,0x7fdec2436180,1685840,1522231,65536,210729,210729,210729,0,2290,0,0,217990,0,12075315880953109,12075319768423580,12075319768548859,12075315881263335
|
|
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,869685,869690,4194304,256,0,0,28,24,83456,0x7fdfcdfa6700,0x7fdec24361c0,3262504,3066923,65536,407812,407812,407812,0,2542,0,0,412569,0,12075315881311836,12075319768577819,12075319768831417,12075315881801866
|
|
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,869685,869690,4194304,256,0,0,28,24,84928,0x7fdfcdfa6600,0x7fdec2436200,3140432,2955754,65536,392553,392553,392553,0,2466,0,0,399940,0,12075315881829628,12075319768877816,12075319769124054,12075315882322704
|
|
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,869685,869690,4194304,256,0,0,24,24,86400,0x7fdfcdfa6500,0x7fdec2436240,1788712,1627335,65536,223588,223588,223588,0,2273,0,0,225217,0,12075315882345787,12075319769174934,12075319769300533,12075315882683063
|
|
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,869685,869690,4194304,256,0,0,24,24,88128,0x7fdfcdfa6400,0x7fdec2436280,1915728,1760416,65536,239465,239465,239465,0,2337,0,0,239501,0,12075315882731523,12075319769330293,12075319769478612,12075315883066065
|
|
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,869685,869690,4194304,256,0,0,24,24,89600,0x7fdfcdfa6300,0x7fdec24362c0,1721504,1558477,65536,215187,215187,215187,0,2346,0,0,220439,0,12075315883148378,12075319769585811,12075319769711410,12075315883453776
|
|
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,869685,869690,4194304,256,0,0,28,24,92096,0x7fdfcdfa6a00,0x7fdec2436300,3258256,3075537,65536,407281,407281,407281,0,2482,0,0,415160,0,12075315883502035,12075319769743409,12075319770004687,12075315883987407
|
|
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,869685,869690,4194304,256,0,0,28,24,93568,0x7fdfcdfa6900,0x7fdec2436340,3159584,2978848,65536,394947,394947,394947,0,2458,0,0,388300,0,12075315884015519,12075319770059407,12075319770307085,12075315884502795
|
|
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,869685,869690,4194304,256,0,0,24,24,95040,0x7fdfcdfa6800,0x7fdec2436380,1674320,1504545,65536,209289,209289,209289,0,2275,0,0,222023,0,12075315884530506,12075319770360044,12075319770485323,12075315884855260
|
|
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,869685,869690,4194304,256,0,0,24,24,96768,0x7fdfcdfa6700,0x7fdec24363c0,2013032,1851755,65536,251628,251628,251628,0,2354,0,0,250938,0,12075315884903028,12075319770515723,12075319770671722,12075315885251967
|
|
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,869685,869690,4194304,256,0,0,24,24,98240,0x7fdfcdfa6600,0x7fdec2436400,1740368,1574023,65536,217545,217545,217545,0,2334,0,0,217470,0,12075315885316567,12075319770717161,12075319770842280,12075315885626833
|
|
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,869685,869690,4194304,256,0,0,28,24,100736,0x7fdfcdfa6500,0x7fdec2436440,3258208,3061829,65536,407275,407275,407275,0,2324,0,0,411828,0,12075315885674281,12075319770872200,12075319771129158,12075315886163090
|
|
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,869685,869690,4194304,256,0,0,28,24,102208,0x7fdfcdfa6400,0x7fdec2436480,3149840,2982199,65536,393729,393729,393729,0,2373,0,0,398782,0,12075315886187044,12075319771178438,12075319771457795,12075315886679099
|
|
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,869685,869690,4194304,256,0,0,24,24,103680,0x7fdfcdfa6300,0x7fdec24364c0,1779104,1614984,65536,222387,222387,222387,0,2326,0,0,221933,0,12075315886703564,12075319771546595,12075319771672354,12075315887040039
|
|
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,869685,869690,4194304,256,0,0,24,24,105664,0x7fdfcdfa6a00,0x7fdec2436500,2101456,1941218,65536,262681,262681,262681,0,2315,0,0,262303,0,12075315887089672,12075319771702753,12075319771868352,12075315887447937
|
|
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,869685,869690,4194304,256,0,0,24,24,107136,0x7fdfcdfa6900,0x7fdec2436540,1689704,1525493,65536,211212,211212,211212,0,2310,0,0,220903,0,12075315887509421,12075319771915712,12075319772041311,12075315887815751
|
|
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,869685,869690,4194304,256,0,0,28,24,109888,0x7fdfcdfa6800,0x7fdec2436580,3278032,3092273,65536,409753,409753,409753,0,2535,0,0,404114,0,12075315887863790,12075319772068990,12075319772323228,12075315888364260
|
|
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,869685,869690,4194304,256,0,0,28,24,111360,0x7fdfcdfa6700,0x7fdec24365c0,3623080,2991650,65536,452884,452884,452884,158,2518,0,0,401253,0,12075315888387643,12075319772369468,12075319772620666,12075315888919942
|
|
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,869685,869690,4194304,256,0,0,24,24,112832,0x7fdfcdfa6600,0x7fdec2436600,1782224,1610564,65536,222777,222777,222777,0,2358,0,0,224183,0,12075315888943656,12075319772669626,12075319772794744,12075315889278719
|
|
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,869685,869690,4194304,256,0,0,24,24,114816,0x7fdfcdfa6500,0x7fdec2436640,2203688,2040406,65536,275460,275460,275460,0,2376,0,0,273836,0,12075315889328672,12075319772823064,12075319772995063,12075315889685134
|
|
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,869685,869690,4194304,256,0,0,24,24,116288,0x7fdfcdfa6400,0x7fdec2436680,1746896,1579678,65536,218361,218361,218361,0,2331,0,0,214030,0,12075315889749664,12075319773038582,12075319773164341,12075315890056494
|
|
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,869685,869690,4194304,256,0,0,28,24,119040,0x7fdfcdfa6300,0x7fdec24366c0,3256040,3053749,65536,407004,407004,407004,0,2436,0,0,401940,0,12075315890104754,12075319773195861,12075319773455379,12075315890594734
|
|
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,869685,869690,4194304,256,0,0,28,24,120768,0x7fdfcdfa6a00,0x7fdec2436700,3145872,2975449,65536,393233,393233,393233,0,2439,0,0,396925,0,12075315890618358,12075319773501779,12075319773748817,12075315891105283
|
|
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,869685,869690,4194304,256,0,0,24,24,122496,0x7fdfcdfa6900,0x7fdec2436740,1755168,1589910,65536,219395,219395,219395,0,2307,0,0,224344,0,12075315891128476,12075319773794576,12075319773920175,12075315891458279
|
|
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,869685,869690,4194304,256,0,0,24,24,124736,0x7fdfcdfa6800,0x7fdec2436780,2304016,2146117,65536,288001,288001,288001,0,2537,0,0,288302,0,12075315891508001,12075319773947855,12075319774130094,12075315891871447
|
|
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,869685,869690,4194304,256,0,0,24,24,126464,0x7fdfcdfa6700,0x7fdec24367c0,1783400,1621132,65536,222924,222924,222924,0,2290,0,0,226669,0,12075315891934464,12075319774171533,12075319774297452,12075315892246333
|
|
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,869685,869690,4194304,256,0,0,20,24,127936,0x7fdfcdfa6600,0x7fdec2436800,3277456,3114069,65536,409681,409681,409681,0,2425,0,0,407978,0,12075315892295374,12075319774328812,12075319774591850,12075315892783802
|
|
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,869685,869690,4194304,256,0,0,28,24,129664,0x7fdfcdfa6500,0x7fdec2436840,3595944,2983415,65536,449492,449492,449492,158,2443,0,0,403305,0,12075315892805662,12075319774634569,12075319774880327,12075315893332481
|
|
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,869685,869690,4194304,256,0,0,24,24,131392,0x7fdfcdfa6400,0x7fdec2436880,1726928,1555361,65536,215865,215865,215865,0,2646,0,0,221427,0,12075315893356636,12075319774917767,12075319775044326,12075315893684756
|
|
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,869685,869690,4194304,256,0,0,24,24,133632,0x7fdfcdfa6300,0x7fdec24368c0,2848424,2249644,65536,356052,356052,356052,158,2372,0,0,352580,0,12075315893734288,12075319775076326,12075319775266884,12075315894185226
|
|
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,869685,869690,4194304,256,0,0,24,24,135360,0x7fdfcdfa6a00,0x7fdec2436900,1782544,1605987,65536,222817,222817,222817,0,2378,0,0,211404,0,12075315894220622,12075319775307524,12075319775434563,12075315894534856
|
|
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,869685,869690,4194304,256,0,0,20,24,136832,0x7fdfcdfa6900,0x7fdec2436940,3876768,3332759,65536,484595,484595,484595,158,4690,0,0,435515,0,12075315894582995,12075319775465283,12075319775746560,12075315895121896
|
|
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,869685,869690,4194304,256,0,0,28,24,138560,0x7fdfcdfa6800,0x7fdec2436980,3145872,2932143,65536,393233,393233,393233,0,2402,0,0,400195,0,12075315895144989,12075319775792640,12075319776043198,12075315895638506
|
|
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,869685,869690,4194304,256,0,0,24,24,140288,0x7fdfcdfa6700,0x7fdec24369c0,1809184,1647957,65536,226147,226147,226147,0,2363,0,0,222765,0,12075315895661800,12075319776093598,12075319776219196,12075315895997453
|
|
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,869685,869690,4194304,256,0,0,24,24,142784,0x7fdfcdfa6600,0x7fdec2436a00,2635984,2469422,65536,329497,329497,329497,0,2320,0,0,330020,0,12075315896047997,12075319776247196,12075319776455515,12075315896481743
|
|
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,869685,869690,4194304,256,0,0,24,24,144768,0x7fdfcdfa6500,0x7fdec2436a40,1816040,1651470,65536,227004,227004,227004,0,2327,0,0,225204,0,12075315896519884,12075319776513914,12075319776641433,12075315896831523
|
|
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,869685,869690,4194304,256,0,0,20,24,145728,0x7fdfcdfa6400,0x7fdec2436a80,3784400,3619910,65536,473049,473049,473049,0,2506,0,0,512223,158,12075315896884461,12075319776668633,12075319776974230,12075315897398667
|
|
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,869685,869690,4194304,256,0,0,28,24,147712,0x7fdfcdfa6300,0x7fdec2436ac0,3154216,2960287,65536,394276,394276,394276,0,2448,0,0,398366,0,12075315897439904,12075319777020630,12075319777270388,12075315897886734
|
|
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,869685,869690,4194304,256,0,0,24,24,149696,0x7fdfcdfa6a00,0x7fdec2436b00,1752592,1572698,65536,219073,219073,219073,0,4258,0,0,214497,0,12075315897931026,12075319777319028,12075319777446866,12075315898245751
|
|
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,869685,869690,4194304,256,0,0,24,24,152192,0x7fdfcdfa6900,0x7fdec2436b40,2849704,2690377,65536,356212,356212,356212,0,2436,0,0,355526,0,12075315898291796,12075319777477266,12075319777704784,12075315898721084
|
|
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,869685,869690,4194304,256,0,0,24,24,154176,0x7fdfcdfa6800,0x7fdec2436b80,1777680,1592381,65536,222209,222209,222209,0,2397,0,0,222800,0,12075315898782528,12075319777759984,12075319777887023,12075315899092244
|
|
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,869685,869690,4194304,256,0,0,20,24,155648,0x7fdfcdfa6700,0x7fdec2436bc0,4037864,3876945,65536,504732,504732,504732,0,2460,0,0,543404,158,12075315899142928,12075319777920783,12075319778248460,12075315899678854
|
|
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,869685,869690,4194304,256,0,0,28,24,157632,0x7fdfcdfa6600,0x7fdec2436c00,3139024,2961123,65536,392377,392377,392377,0,2451,0,0,396251,0,12075315899722395,12075319778293260,12075319778541258,12075315900170928
|
|
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,869685,869690,4194304,256,0,0,24,24,159616,0x7fdfcdfa6500,0x7fdec2436c40,1787424,1627018,65536,223427,223427,223427,0,2312,0,0,228658,0,12075315900213507,12075319778582857,12075319778711016,12075315900525778
|
|
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,869685,869690,4194304,256,0,0,24,24,162368,0x7fdfcdfa6400,0x7fdec2436c80,3053584,2892792,65536,381697,381697,381697,0,2506,0,0,427751,0,12075315900574047,12075319778743176,12075319778986694,12075315901023262
|
|
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,869685,869690,4194304,256,0,0,24,24,164608,0x7fdfcdfa6300,0x7fdec2436cc0,1819680,1654431,65536,227459,227459,227459,0,2276,0,0,222686,0,12075315901080568,12075319779044453,12075319779174212,12075315901396786
|
|
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,869685,869690,4194304,256,0,0,20,24,166336,0x7fdfcdfa6a00,0x7fdec2436d00,4588048,4424360,65536,573505,573505,573505,0,2442,0,0,571778,0,12075315901445036,12075319779201732,12075319779575969,12075315902019663
|
|
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,869685,869690,4194304,256,0,0,28,24,168576,0x7fdfcdfa6900,0x7fdec2436d40,3183712,2999084,65536,397963,397963,397963,0,2506,0,0,408103,0,12075315902067332,12075319779619809,12075319779871007,12075315902517869
|
|
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,869685,869690,4194304,256,0,0,24,24,170816,0x7fdfcdfa6800,0x7fdec2436d80,1780688,1616816,65536,222585,222585,222585,0,2298,0,0,217123,0,12075315902561280,12075319779923326,12075319780053405,12075315902868601
|
|
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,869685,869690,4194304,256,0,0,24,24,174080,0x7fdfcdfa6700,0x7fdec2436dc0,3478568,3312687,65536,434820,434820,434820,0,2292,0,0,433157,0,12075315902916550,12075319780085885,12075319780363323,12075315903407963
|
|
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,869685,869690,4194304,256,0,0,24,24,176576,0x7fdfcdfa6600,0x7fdec2436e00,1825296,1656842,65536,228161,228161,228161,0,2352,0,0,217185,0,12075315903463055,12075319780463482,12075319780599321,12075315903776628
|
|
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,869685,869690,4194304,256,0,0,20,24,177792,0x7fdfcdfa6500,0x7fdec2436e40,5166304,5004683,65536,645787,645787,645787,0,4253,0,0,675009,0,12075315903824026,12075319780629240,12075319781050837,12075315904455970
|
|
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,869685,869690,4194304,256,0,0,28,24,180288,0x7fdfcdfa6400,0x7fdec2436e80,3254480,3076317,65536,406809,406809,406809,0,4086,0,0,397458,0,12075315904497267,12075319781138356,12075319781399634,12075315904947574
|
|
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,869685,869690,4194304,256,0,0,24,24,182784,0x7fdfcdfa6300,0x7fdec2436ec0,1786336,1613291,65536,223291,223291,223291,0,2350,0,0,226529,0,12075315904990814,12075319781446514,12075319781581553,12075315905305409
|
|
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,869685,869690,4194304,256,0,0,24,24,186304,0x7fdfcdfa6a00,0x7fdec2436f00,4240912,3734948,65536,530113,530113,530113,158,2495,0,0,485508,158,12075315905354891,12075319781611312,12075319781924430,12075315905900024
|
|
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,869685,869690,4194304,256,0,0,24,24,189312,0x7fdfcdfa6900,0x7fdec2436f40,1952480,1785754,65536,244059,244059,244059,0,2316,0,0,239716,0,12075315905956519,12075319781983469,12075319782174348,12075315906288976
|
|
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,869685,869690,4194304,256,0,0,20,24,190784,0x7fdfcdfa6800,0x7fdec2436f80,6292112,6122417,65536,786513,786513,786513,0,4327,0,0,806421,0,12075315906337316,12075319782203148,12075319782718343,12075315907059007
|
|
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,869685,869690,4194304,256,0,0,28,24,193792,0x7fdfcdfa6700,0x7fdec2436fc0,3657248,3471055,65536,457155,457155,457155,0,2451,0,0,457902,0,12075315907104181,12075319782764263,12075319783065061,12075315907594823
|
|
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,869685,869690,4194304,256,0,0,24,24,196800,0x7fdfcdfa6600,0x7fdec2437000,1967696,1811449,65536,245961,245961,245961,0,2386,0,0,244996,0,12075315907646679,12075319783111940,12075319783266019,12075315907975941
|
|
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,869685,869690,4194304,256,0,0,24,24,201088,0x7fdfcdfa6500,0x7fdec2437040,4750560,4585272,65536,593819,593819,593819,0,2507,0,0,590381,0,12075315908029200,12075319783294019,12075319783679616,12075315908633893
|
|
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,869685,869690,4194304,256,0,0,24,24,204608,0x7fdfcdfa6400,0x7fdec2437080,2226192,2069831,65536,278273,278273,278273,0,2359,0,0,277114,0,12075315908688475,12075319783739615,12075319783914014,12075315909039136
|
|
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,869685,869690,4194304,256,0,0,20,24,206080,0x7fdfcdfa6300,0x7fdec24370c0,7414240,7243515,65536,926779,926779,926779,0,2327,0,0,922718,0,12075315909088608,12075319783941533,12075319784549848,12075315909908502
|
|
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,869685,869690,4194304,256,0,0,28,24,209600,0x7fdfcdfa6a00,0x7fdec2437100,4011856,3848541,65536,501481,501481,501481,0,2471,0,0,502684,0,12075315909953826,12075319784600888,12075319784931925,12075315910500201
|
|
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,869685,869690,4194304,256,0,0,24,24,213120,0x7fdfcdfa6900,0x7fdec2437140,2258408,2100363,65536,282300,282300,282300,0,2336,0,0,281005,0,12075315910523144,12075319784976885,12075319785154003,12075315910895576
|
|
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,869685,869690,4194304,256,0,0,24,24,218176,0x7fdfcdfa6800,0x7fdec2437180,5581456,5424385,65536,697681,697681,697681,0,2420,0,0,696483,0,12075315910944437,12075319785186323,12075319785640719,12075315911630001
|
|
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,869685,869690,4194304,256,0,0,24,24,222208,0x7fdfcdfa6700,0x7fdec24371c0,2513832,2354343,65536,314228,314228,314228,0,2298,0,0,310783,0,12075315911666909,12075319785699119,12075319785898637,12075315912084916
|
|
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,869685,869690,4194304,256,0,0,20,24,223936,0x7fdfcdfa6600,0x7fdec2437200,8513040,8356820,65536,1064129,1064129,1064129,0,4340,0,0,1062892,0,12075315912109792,12075319785941837,12075319786643911,12075315913048386
|
|
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,869685,869690,4194304,256,0,0,28,24,227968,0x7fdfcdfa6500,0x7fdec2437240,4571936,4394802,65536,571491,571491,571491,0,2434,0,0,565400,0,12075315913072130,12075319786701351,12075319787072548,12075315913684759
|
|
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,869685,869690,4194304,256,0,0,24,24,232000,0x7fdfcdfa6400,0x7fdec2437280,2535248,2377512,65536,316905,316905,316905,0,2317,0,0,316075,0,12075315913707040,12075319787118627,12075319787320386,12075315914147038
|
|
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,869685,869690,4194304,256,0,0,24,24,237824,0x7fdfcdfa6300,0x7fdec24372c0,6429224,6264254,65536,803652,803652,803652,0,2462,0,0,825517,0,12075315914170291,12075319787368865,12075319787893981,12075315914929872
|
|
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,869685,869690,4194304,256,0,0,24,24,242368,0x7fdfcdfa6a00,0x7fdec2437300,2790672,2633764,65536,348833,348833,348833,0,2461,0,0,399195,0,12075315914965839,12075319787951901,12075319788210298,12075315915418710
|
|
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,869685,869690,4194304,256,0,0,20,24,243584,0x7fdfcdfa6900,0x7fdec2437340,9672288,9494969,65536,1209035,1209035,1209035,0,2415,0,0,1204584,0,12075315915442254,12075319788262458,12075319789058612,12075315916479201
|
|
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,869685,869690,4194304,256,0,0,28,24,248128,0x7fdfcdfa6800,0x7fdec2437380,5097936,4933135,65536,637241,637241,637241,0,2443,0,0,637183,158,12075315916503376,12075319789105651,12075319789523568,12075315917160367
|
|
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,869685,869690,4194304,256,0,0,24,24,252672,0x7fdfcdfa6700,0x7fdec24373c0,2819944,2653711,65536,352492,352492,352492,0,2554,0,0,352588,0,12075315917190753,12075319789567887,12075319789791566,12075315917649666
|
|
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,869685,869690,4194304,256,0,0,24,24,259264,0x7fdfcdfa6600,0x7fdec2437400,7267216,7110963,65536,908401,908401,908401,0,2461,0,0,906583,0,12075315917675304,12075319789841325,12075319790436680,12075315918502340
|
|
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,869685,869690,4194304,256,0,0,24,24,264832,0x7fdfcdfa6500,0x7fdec2437440,3338472,3170744,65536,417308,417308,417308,0,2506,0,0,414882,0,12075315918539700,12075319790503240,12075319790770918,12075315919028508
|
|
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,869685,869690,4194304,256,0,0,20,24,266304,0x7fdfcdfa6400,0x7fdec2437480,11902416,11740618,65536,1487801,1487801,1487801,0,2465,0,0,1484318,0,12075315919051831,12075319790816197,12075319791799389,12075315920275896
|
|
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,869685,869690,4194304,256,0,0,28,24,271872,0x7fdfcdfa6300,0x7fdec24374c0,6227360,6054824,65536,778419,778419,778419,0,2429,0,0,778418,0,12075315920298528,12075319791845469,12075319792358585,12075315921062738
|
|
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,869685,869690,4194304,256,0,0,24,24,277440,0x7fdfcdfa6a00,0x7fdec2437500,3373072,3213750,65536,421633,421633,421633,0,2415,0,0,420803,0,12075315921092253,12075319792416984,12075319792687062,12075315921603783
|
|
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,869685,869690,4194304,256,0,0,12,24,279936,0x7fdfcdfa6900,0x7fdec2437540,9009696,8841419,65536,1126211,1126211,1126211,0,2442,0,0,1123923,0,12075315921626505,12075319792732822,12075319793469136,12075315922600736
|
|
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,869685,869690,4194304,256,0,0,24,24,286528,0x7fdfcdfa6800,0x7fdec2437580,3894800,3736105,65536,486849,486849,486849,0,2403,0,0,487515,0,12075315922639428,12075319793529935,12075319793845932,12075315923176005
|
|
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,869685,869690,4194304,256,0,0,20,24,288000,0x7fdfcdfa6700,0x7fdec24375c0,14145632,13977079,65536,1768203,1768203,1768203,0,2506,0,0,1765941,0,12075315923199138,12075319793890252,12075319795058243,12075315924604318
|
|
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,869685,869690,4194304,256,0,0,32,24,294592,0x7fdfcdfa6600,0x7fdec2437600,7342864,7172130,65536,917857,917857,917857,0,2456,0,0,915849,0,12075315924634284,12075319795114082,12075319795722717,12075315925480977
|
|
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,869685,869690,4194304,256,0,0,24,24,301184,0x7fdfcdfa6500,0x7fdec2437640,3957864,3760747,65536,494732,494732,494732,0,2496,0,0,531722,0,12075315925504682,12075319795770717,12075319796088634,12075315926066526
|
|
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,869685,869690,4194304,256,0,0,12,24,304960,0x7fdfcdfa6400,0x7fdec2437680,10690576,10526703,65536,1336321,1336321,1336321,0,2395,0,0,1335518,0,12075315926090280,12075319796140314,12075319797016627,12075315927204540
|
|
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,869685,869690,4194304,256,0,0,24,24,313600,0x7fdfcdfa6300,0x7fdec24376c0,5295456,4858194,65536,661931,661931,661931,158,4370,0,0,661579,0,12075315927239435,12075319797076466,12075319797487023,12075315927906615
|
|
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,869685,869690,4194304,256,0,0,20,24,314816,0x7fdfcdfa6a00,0x7fdec2437700,18663568,18495120,65536,2332945,2332945,2332945,0,2507,0,0,2331478,0,12075315927929347,12075319797535502,12075319799082050,12075315929727458
|
|
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,869685,869690,4194304,256,0,0,20,24,317568,0x7fdfcdfa6900,0x7fdec2437740,9617256,9436837,65536,1202156,1202156,1202156,158,2300,0,0,1197048,0,12075315929751182,12075319799131009,12075319799922683,12075315930789361
|
|
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,869685,869690,4194304,256,0,0,12,24,320320,0x7fdfcdfa6800,0x7fdec2437780,5118992,4951905,65536,639873,639873,639873,0,2456,0,0,638141,158,12075315930821731,12075319799992282,12075319800405079,12075315931464035
|
|
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,869685,869690,4194304,256,0,0,12,24,324096,0x7fdfcdfa6700,0x7fdec24377c0,14050720,13891670,65536,1756339,1756339,1756339,0,2376,0,0,1756290,0,12075315931494261,12075319800475316,12075319801633228,12075315932888321
|
|
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,869685,869690,4194304,256,0,0,12,24,328896,0x7fdfcdfa6600,0x7fdec2437800,9585168,9423228,65536,1198145,1198145,1198145,0,2428,0,0,1196429,0,12075315932928356,12075319801743146,12075319802527461,12075315933950164
|
|
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,869685,869690,4194304,256,0,0,20,24,330112,0x7fdfcdfa6500,0x7fdec2437840,36666728,36506837,65536,4583340,4583340,4583340,0,2560,0,0,4581013,0,12075315933980120,12075319802619460,12075319805670479,12075315937268310
|
|
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,869685,869690,4194304,256,0,0,20,24,332864,0x7fdfcdfa6400,0x7fdec2437880,18597072,18425477,65536,2324633,2324633,2324633,0,2570,0,0,2322087,0,12075315937295110,12075319805759758,12075319807300227,12075315939083833
|
|
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,869685,869690,4194304,256,0,0,12,24,335616,0x7fdfcdfa6300,0x7fdec24378c0,9607584,9452307,65536,1200947,1200947,1200947,0,2535,0,0,1199674,0,12075315939111385,12075319807394467,12075319808185021,12075315940139555
|
|
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,869685,869690,4194304,256,0,0,12,24,339392,0x7fdfcdfa6a00,0x7fdec2437900,27541072,27379842,65536,3442633,3442633,3442633,0,2393,0,0,3440013,0,12075315940163019,12075319808277341,12075319810557645,12075315942686708
|
|
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,869685,869690,4194304,256,0,0,12,24,344192,0x7fdfcdfa6900,0x7fdec2437940,18580256,18419864,65536,2322531,2322531,2322531,158,2352,0,0,2321590,0,12075315942730379,12075319810671404,12075319812205633,12075315944485490
|
|
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,869685,869690,4194304,256,0,0,20,24,345408,0x7fdfcdfa6800,0x7fdec2437980,72713552,72531960,65536,9089193,9089193,9089193,158,4667,0,0,9084380,158,12075315944516959,12075319812294752,12075319818351350,12075315950808660
|
|
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,869685,869690,4194304,256,0,0,20,24,348160,0x7fdfcdfa6700,0x7fdec24379c0,36587616,36419712,65536,4573451,4573451,4573451,0,4154,0,0,4569115,0,12075315950836822,12075319818441109,12075319821483968,12075315954129921
|
|
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,869685,869690,4194304,256,0,0,12,24,350912,0x7fdfcdfa6600,0x7fdec2437a00,18620624,18468332,65536,2327577,2327577,2327577,0,2488,0,0,2327718,0,12075315954160448,12075319821572928,12075319823111157,12075315955938041
|
|
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,869685,869690,4194304,256,0,0,12,24,0,0x7fdfcdfa6500,0x7fdec2437a40,54490728,54325942,65536,6811340,6811340,6811340,0,2452,0,0,6809737,0,12075315955966774,12075319823199796,12075319827726164,12075315960741406
|