84 KiB
84 KiB
| 1 | 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 | TCC_CYCLE_sum | TCC_BUSY_sum | TCC_PROBE_sum | TCC_PROBE_ALL_sum | TCC_NC_REQ_sum | TCC_UC_REQ_sum | TCC_CC_REQ_sum | TCC_RW_REQ_sum | TCC_EA_ATOMIC_LEVEL_sum | TCC_REQ_sum | TCC_STREAMING_REQ_sum | TCC_HIT_sum | TCC_MISS_sum | TCC_READ_sum | TCC_WRITE_sum | TCC_ATOMIC_sum | TCC_WRITEBACK_sum | TCC_EA_WRREQ_sum | TCC_EA_WRREQ_64B_sum | TCC_EA_WR_UNCACHED_32B_sum | TCC_EA_WRREQ_STALL_sum | TCC_EA_WRREQ_IO_CREDIT_STALL_sum | TCC_EA_WRREQ_GMI_CREDIT_STALL_sum | TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum | TCC_TOO_MANY_EA_WRREQS_STALL_sum | TCC_EA_ATOMIC_sum | TCC_EA_RDREQ_sum | TCC_EA_RDREQ_32B_sum | TCC_EA_RD_UNCACHED_32B_sum | TCC_EA_RDREQ_IO_CREDIT_STALL_sum | TCC_EA_RDREQ_GMI_CREDIT_STALL_sum | TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum | TCC_TAG_STALL_sum | TCC_NORMAL_WRITEBACK_sum | TCC_ALL_TC_OP_WB_WRITEBACK_sum | TCC_NORMAL_EVICT_sum | TCC_ALL_TC_OP_INV_EVICT_sum | TCC_EA_RDREQ_DRAM_sum | TCC_EA_WRREQ_DRAM_sum | TCC_EA_RDREQ_LEVEL_sum | TCC_EA_WRREQ_LEVEL_sum | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBufferAligned.kd | 0 | 0 | 0 | 155691 | 155691 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7f018c604280 | 3035792 | 2948345 | 524288 | 379473 | 379473 | 12143136.0 | 9351792.0 | 0.0 | 0.0 | 56.0 | 304.0 | 0.0 | 4194696.0 | 0.0 | 4195057.0 | 0.0 | 2097594.0 | 2097463.0 | 750.0 | 4194304.0 | 0.0 | 2064387.0 | 4128768.0 | 4128768.0 | 0.0 | 1450770.0 | 0.0 | 0.0 | 1457360.0 | 0.0 | 0.0 | 309.0 | 0.0 | 602.0 | 0.0 | 0.0 | 0.0 | 190929.0 | 2064384.0 | 0.0 | 2031623.0 | 0.0 | 142.0 | 4128768.0 | 526448.0 | 1629445996.0 | 16335241863961 | 16343179280950 | 16343179518712 | 16335386682896 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 155691 | 155691 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7f018c623f80 | 200912 | 102738 | 512 | 25113 | 25113 | 803616.0 | 259457.0 | 0.0 | 0.0 | 0.0 | 61.0 | 0.0 | 4600.0 | 0.0 | 4660.0 | 0.0 | 499.0 | 4161.0 | 4660.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 8259.0 | 0.0 | 116.0 | 0.0 | 0.0 | 0.0 | 53619.0 | 0.0 | 0.0 | 0.0 | 0.0 | 8205.0 | 0.0 | 3416027.0 | 0.0 | 16335392065267 | 16343184405785 | 16343184412985 | 16335392328611 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7f018f696380 | 0x7f018c623fc0 | 1313056 | 1205448 | 65536 | 164131 | 164131 | 5252192.0 | 4725074.0 | 0.0 | 0.0 | 0.0 | 184.0 | 0.0 | 1048968.0 | 0.0 | 1049133.0 | 0.0 | 388.0 | 1048745.0 | 1049146.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097337.0 | 0.0 | 356.0 | 0.0 | 0.0 | 334375.0 | 964875.0 | 0.0 | 0.0 | 983046.0 | 0.0 | 2097265.0 | 0.0 | 1476812669.0 | 0.0 | 16335392404579 | 16343184447706 | 16343184539866 | 16335392983106 |
| 5 | 3 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 8 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7f018f696200 | 0x7f018c624000 | 2472208 | 2373474 | 65536 | 309025 | 309025 | 9888800.0 | 9366799.0 | 0.0 | 0.0 | 0.0 | 295.0 | 0.0 | 2344520.0 | 0.0 | 2361513.0 | 0.0 | 264088.0 | 2097425.0 | 2343417.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194591.0 | 0.0 | 554.0 | 0.0 | 0.0 | 619678.0 | 2017179.0 | 0.0 | 0.0 | 2031623.0 | 0.0 | 4194526.0 | 0.0 | 2668810769.0 | 0.0 | 16335393074594 | 16343184574106 | 16343184754428 | 16335393670131 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7f018f696080 | 0x7f018c624040 | 2465056 | 2360817 | 65536 | 308131 | 308131 | 9860192.0 | 9331900.0 | 0.0 | 0.0 | 0.0 | 298.0 | 0.0 | 2341236.0 | 0.0 | 2358897.0 | 0.0 | 261475.0 | 2097422.0 | 2360361.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194593.0 | 0.0 | 562.0 | 0.0 | 0.0 | 602853.0 | 1936888.0 | 0.0 | 0.0 | 2031622.0 | 0.0 | 4194526.0 | 0.0 | 2648486536.0 | 0.0 | 16335393755049 | 16343184780988 | 16343184961629 | 16335394380876 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7f018cefdf00 | 0x7f018c624080 | 1312264 | 1210525 | 65536 | 164032 | 164032 | 5249024.0 | 4715538.0 | 0.0 | 0.0 | 0.0 | 185.0 | 0.0 | 1049080.0 | 0.0 | 1049248.0 | 0.0 | 499.0 | 1048749.0 | 1049260.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097345.0 | 0.0 | 368.0 | 0.0 | 0.0 | 421066.0 | 1241649.0 | 0.0 | 0.0 | 983047.0 | 0.0 | 2097268.0 | 0.0 | 1399900071.0 | 0.0 | 16335394465704 | 16343184985789 | 16343185078110 | 16335394980152 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7f018cefdd80 | 0x7f018c6240c0 | 1320640 | 1217725 | 65536 | 165079 | 165079 | 5282528.0 | 4728212.0 | 0.0 | 0.0 | 0.0 | 180.0 | 0.0 | 1049024.0 | 0.0 | 1049193.0 | 0.0 | 443.0 | 1048750.0 | 1049202.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097345.0 | 0.0 | 370.0 | 0.0 | 0.0 | 369121.0 | 1143373.0 | 0.0 | 0.0 | 983047.0 | 0.0 | 2097275.0 | 0.0 | 1424168357.0 | 0.0 | 16335395065190 | 16343185104830 | 16343185196831 | 16335395568129 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7f018cefdc00 | 0x7f018c624100 | 1298528 | 1195629 | 65536 | 162315 | 162315 | 5194080.0 | 4666718.0 | 0.0 | 0.0 | 0.0 | 181.0 | 0.0 | 1049080.0 | 0.0 | 1049246.0 | 0.0 | 499.0 | 1048747.0 | 1049258.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097339.0 | 0.0 | 356.0 | 0.0 | 0.0 | 383509.0 | 1189651.0 | 0.0 | 0.0 | 983047.0 | 0.0 | 2097268.0 | 0.0 | 1408346844.0 | 0.0 | 16335395667417 | 16343185241471 | 16343185332832 | 16335396155646 |
| 10 | 8 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 23 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7f018cefda80 | 0x7f018c624140 | 2467312 | 2365562 | 65536 | 308413 | 308413 | 9869216.0 | 9338244.0 | 0.0 | 0.0 | 0.0 | 279.0 | 0.0 | 2327934.0 | 0.0 | 2339781.0 | 0.0 | 242348.0 | 2097433.0 | 2316398.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194604.0 | 0.0 | 578.0 | 0.0 | 0.0 | 639058.0 | 2082377.0 | 0.0 | 0.0 | 2031624.0 | 0.0 | 4194528.0 | 0.0 | 2599216543.0 | 0.0 | 16335396239284 | 16343185371712 | 16343185551553 | 16335396760703 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7f018cefd900 | 0x7f018c624180 | 2476208 | 2378386 | 65536 | 309525 | 309525 | 9904800.0 | 9347881.0 | 0.0 | 0.0 | 0.0 | 294.0 | 0.0 | 2341317.0 | 0.0 | 2340874.0 | 0.0 | 243450.0 | 2097424.0 | 2343973.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194593.0 | 0.0 | 558.0 | 0.0 | 0.0 | 602953.0 | 1985936.0 | 0.0 | 0.0 | 2031623.0 | 0.0 | 4194517.0 | 0.0 | 2673540888.0 | 0.0 | 16335396844581 | 16343185597794 | 16343185776515 | 16335397358010 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7f018cefd780 | 0x7f018c6241c0 | 1307544 | 1207209 | 65536 | 163442 | 163442 | 5230144.0 | 4677375.0 | 0.0 | 0.0 | 0.0 | 176.0 | 0.0 | 1049136.0 | 0.0 | 1049305.0 | 0.0 | 555.0 | 1048750.0 | 1049313.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097344.0 | 0.0 | 364.0 | 0.0 | 0.0 | 407300.0 | 1268523.0 | 0.0 | 0.0 | 983047.0 | 0.0 | 2097275.0 | 0.0 | 1361919913.0 | 0.0 | 16335397442098 | 16343185812035 | 16343185904196 | 16335397868528 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7f018cefd600 | 0x7f018c624200 | 1313256 | 1211960 | 65536 | 164156 | 164156 | 5252992.0 | 4714552.0 | 0.0 | 0.0 | 0.0 | 176.0 | 0.0 | 1049136.0 | 0.0 | 1049302.0 | 0.0 | 555.0 | 1048747.0 | 1049319.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097343.0 | 0.0 | 362.0 | 0.0 | 0.0 | 424727.0 | 1195651.0 | 0.0 | 0.0 | 983047.0 | 0.0 | 2097277.0 | 0.0 | 1414538248.0 | 0.0 | 16335397952036 | 16343185936516 | 16343186028837 | 16335398401047 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7f018f696480 | 0x7f018c624240 | 1304216 | 1202463 | 65536 | 163026 | 163026 | 5216832.0 | 4660036.0 | 0.0 | 0.0 | 0.0 | 185.0 | 0.0 | 1049136.0 | 0.0 | 1049300.0 | 0.0 | 555.0 | 1048745.0 | 1049313.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097340.0 | 0.0 | 356.0 | 0.0 | 0.0 | 422490.0 | 1332750.0 | 0.0 | 0.0 | 983047.0 | 0.0 | 2097266.0 | 0.0 | 1411153568.0 | 0.0 | 16335398495344 | 16343186068837 | 16343186160998 | 16335398917645 |
| 15 | 13 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 38 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7f018f696300 | 0x7f018c624280 | 2466224 | 2363735 | 65536 | 308277 | 308277 | 9864864.0 | 9324348.0 | 0.0 | 0.0 | 0.0 | 288.0 | 0.0 | 2322985.0 | 0.0 | 2351190.0 | 0.0 | 253757.0 | 2097433.0 | 2348682.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194608.0 | 0.0 | 584.0 | 0.0 | 0.0 | 659664.0 | 2138829.0 | 0.0 | 0.0 | 2031624.0 | 0.0 | 4194530.0 | 0.0 | 2604938519.0 | 0.0 | 16335399002723 | 16343186198118 | 16343186378279 | 16335399515152 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7f018f696180 | 0x7f018c6242c0 | 2452720 | 2343963 | 65536 | 306589 | 306589 | 9810848.0 | 9275021.0 | 0.0 | 0.0 | 0.0 | 287.0 | 0.0 | 2350140.0 | 0.0 | 2351637.0 | 0.0 | 254221.0 | 2097416.0 | 2342086.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194606.0 | 0.0 | 582.0 | 0.0 | 0.0 | 734080.0 | 2399683.0 | 0.0 | 0.0 | 2031624.0 | 0.0 | 4194521.0 | 0.0 | 2657770873.0 | 0.0 | 16335399599570 | 16343186406439 | 16343186586921 | 16335400130628 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7f018f696000 | 0x7f018c624300 | 1310624 | 1207006 | 65536 | 163827 | 163827 | 5242464.0 | 4687369.0 | 0.0 | 0.0 | 0.0 | 176.0 | 0.0 | 1049192.0 | 0.0 | 1049362.0 | 0.0 | 610.0 | 1048752.0 | 1049376.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097345.0 | 0.0 | 364.0 | 0.0 | 0.0 | 349767.0 | 1099055.0 | 0.0 | 0.0 | 983048.0 | 0.0 | 2097280.0 | 0.0 | 1425801390.0 | 0.0 | 16335400215757 | 16343186613001 | 16343186705162 | 16335400638407 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7f018cefde80 | 0x7f018c624340 | 1303056 | 1203512 | 65536 | 162881 | 162881 | 5212192.0 | 4689776.0 | 0.0 | 0.0 | 0.0 | 187.0 | 0.0 | 1049248.0 | 0.0 | 1049416.0 | 0.0 | 666.0 | 1048750.0 | 1049421.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097344.0 | 0.0 | 360.0 | 0.0 | 0.0 | 475514.0 | 1440012.0 | 0.0 | 0.0 | 983048.0 | 0.0 | 2097278.0 | 0.0 | 1422266987.0 | 0.0 | 16335400722365 | 16343186733962 | 16343186825642 | 16335401149506 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7f018cefdd00 | 0x7f018c624380 | 1305424 | 1204575 | 65536 | 163177 | 163177 | 5221664.0 | 4690166.0 | 0.0 | 0.0 | 0.0 | 184.0 | 0.0 | 1049192.0 | 0.0 | 1049361.0 | 0.0 | 610.0 | 1048751.0 | 1049370.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097342.0 | 0.0 | 358.0 | 0.0 | 0.0 | 598294.0 | 1798037.0 | 0.0 | 0.0 | 983048.0 | 0.0 | 2097277.0 | 0.0 | 1443794403.0 | 0.0 | 16335401242134 | 16343186859563 | 16343186951243 | 16335401675824 |
| 20 | 18 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 53 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7f018cefdb80 | 0x7f018c6243c0 | 2456400 | 2358248 | 65536 | 307049 | 307049 | 9825568.0 | 9305704.0 | 0.0 | 0.0 | 0.0 | 284.0 | 0.0 | 2313973.0 | 0.0 | 2359496.0 | 0.0 | 262073.0 | 2097423.0 | 2349915.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194593.0 | 0.0 | 552.0 | 0.0 | 0.0 | 727033.0 | 2362092.0 | 0.0 | 0.0 | 2031625.0 | 0.0 | 4194524.0 | 0.0 | 2654942463.0 | 0.0 | 16335401760383 | 16343186988524 | 16343187168205 | 16335402271841 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7f018cefda00 | 0x7f018c624400 | 2456416 | 2349291 | 65536 | 307051 | 307051 | 9825632.0 | 9275938.0 | 0.0 | 0.0 | 0.0 | 298.0 | 0.0 | 2352537.0 | 0.0 | 2351893.0 | 0.0 | 254469.0 | 2097424.0 | 2355668.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194596.0 | 0.0 | 562.0 | 0.0 | 0.0 | 640216.0 | 2087698.0 | 0.0 | 0.0 | 2031624.0 | 0.0 | 4194528.0 | 0.0 | 2653509966.0 | 0.0 | 16335402356360 | 16343187196845 | 16343187376366 | 16335402872848 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7f018cefd880 | 0x7f018c624440 | 1306008 | 1204680 | 65536 | 163250 | 163250 | 5224000.0 | 4695624.0 | 0.0 | 0.0 | 0.0 | 181.0 | 0.0 | 1049248.0 | 0.0 | 1049419.0 | 0.0 | 666.0 | 1048753.0 | 1049422.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097337.0 | 0.0 | 346.0 | 0.0 | 0.0 | 418240.0 | 1340208.0 | 0.0 | 0.0 | 983048.0 | 0.0 | 2097275.0 | 0.0 | 1341933436.0 | 0.0 | 16335402957256 | 16343187402766 | 16343187495887 | 16335403384897 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7f018cefd700 | 0x7f018c624480 | 1296472 | 1195526 | 65536 | 162058 | 162058 | 5185856.0 | 4664175.0 | 0.0 | 0.0 | 0.0 | 183.0 | 0.0 | 1049304.0 | 0.0 | 1049477.0 | 0.0 | 721.0 | 1048756.0 | 1049484.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097344.0 | 0.0 | 358.0 | 0.0 | 0.0 | 455134.0 | 1459714.0 | 0.0 | 0.0 | 983049.0 | 0.0 | 2097278.0 | 0.0 | 1434811299.0 | 0.0 | 16335403469045 | 16343187524687 | 16343187616688 | 16335403902545 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7f018f696580 | 0x7f018c6244c0 | 1294144 | 1192980 | 65536 | 161767 | 161767 | 5176544.0 | 4661962.0 | 0.0 | 0.0 | 0.0 | 182.0 | 0.0 | 1049192.0 | 0.0 | 1049364.0 | 0.0 | 610.0 | 1048754.0 | 1049370.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097335.0 | 0.0 | 344.0 | 0.0 | 0.0 | 381161.0 | 1255020.0 | 0.0 | 0.0 | 983048.0 | 0.0 | 2097278.0 | 0.0 | 1427158896.0 | 0.0 | 16335403995163 | 16343187650288 | 16343187741649 | 16335404426814 |
| 25 | 23 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 68 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7f018f696400 | 0x7f018c624500 | 2444120 | 2346093 | 65536 | 305514 | 305514 | 9776448.0 | 9243575.0 | 0.0 | 0.0 | 0.0 | 289.0 | 0.0 | 2348579.0 | 0.0 | 2323319.0 | 0.0 | 225886.0 | 2097433.0 | 2354176.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194608.0 | 0.0 | 580.0 | 0.0 | 0.0 | 616670.0 | 2050907.0 | 0.0 | 0.0 | 2031625.0 | 0.0 | 4194532.0 | 0.0 | 2627762075.0 | 0.0 | 16335404513312 | 16343187792049 | 16343187972690 | 16335405024381 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7f018f696280 | 0x7f018c624540 | 2439008 | 2334980 | 65536 | 304875 | 304875 | 9756000.0 | 9221029.0 | 0.0 | 0.0 | 0.0 | 287.0 | 0.0 | 2334675.0 | 0.0 | 2343434.0 | 0.0 | 246006.0 | 2097428.0 | 2349164.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194601.0 | 0.0 | 568.0 | 0.0 | 0.0 | 643821.0 | 2126938.0 | 0.0 | 0.0 | 2031625.0 | 0.0 | 4194532.0 | 0.0 | 2691244783.0 | 0.0 | 16335405108979 | 16343187999411 | 16343188181812 | 16335405622038 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7f018f696100 | 0x7f018c624580 | 1296080 | 1197711 | 65536 | 162009 | 162009 | 5184288.0 | 4687110.0 | 0.0 | 0.0 | 0.0 | 182.0 | 0.0 | 1049248.0 | 0.0 | 1049414.0 | 0.0 | 665.0 | 1048749.0 | 1049428.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097345.0 | 0.0 | 362.0 | 0.0 | 0.0 | 480842.0 | 1490124.0 | 0.0 | 0.0 | 983049.0 | 0.0 | 2097284.0 | 0.0 | 1343969224.0 | 0.0 | 16335405706036 | 16343188214612 | 16343188306453 | 16335406128377 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7f018cefdf80 | 0x7f018c6245c0 | 1283872 | 1185895 | 65536 | 160483 | 160483 | 5135456.0 | 4634096.0 | 0.0 | 0.0 | 0.0 | 189.0 | 0.0 | 1049360.0 | 0.0 | 1049533.0 | 0.0 | 776.0 | 1048757.0 | 1049548.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097350.0 | 0.0 | 368.0 | 0.0 | 0.0 | 459170.0 | 1406448.0 | 0.0 | 0.0 | 983050.0 | 0.0 | 2097288.0 | 0.0 | 1361118508.0 | 0.0 | 16335406213995 | 16343188331253 | 16343188422294 | 16335406636965 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7f018cefde00 | 0x7f018c624600 | 1291408 | 1192218 | 65536 | 161425 | 161425 | 5165600.0 | 4639981.0 | 0.0 | 0.0 | 0.0 | 184.0 | 0.0 | 1049304.0 | 0.0 | 1049470.0 | 0.0 | 721.0 | 1048749.0 | 1049485.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097348.0 | 0.0 | 366.0 | 0.0 | 0.0 | 312267.0 | 887596.0 | 0.0 | 0.0 | 983049.0 | 0.0 | 2097276.0 | 0.0 | 1448508025.0 | 0.0 | 16335406729313 | 16343188454614 | 16343188546295 | 16335407144624 |
| 30 | 28 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 83 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7f018cefdc80 | 0x7f018c624640 | 2447440 | 2343870 | 65536 | 305929 | 305929 | 9789728.0 | 9284243.0 | 0.0 | 0.0 | 0.0 | 286.0 | 0.0 | 2316968.0 | 0.0 | 2353343.0 | 0.0 | 255914.0 | 2097429.0 | 2344592.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194593.0 | 0.0 | 550.0 | 0.0 | 0.0 | 512989.0 | 1638402.0 | 0.0 | 0.0 | 2031626.0 | 0.0 | 4194524.0 | 0.0 | 2657950740.0 | 0.0 | 16335407230832 | 16343188571255 | 16343188750776 | 16335407739381 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7f018cefdb00 | 0x7f018c624680 | 2449496 | 2346787 | 65536 | 306186 | 306186 | 9797952.0 | 9250870.0 | 0.0 | 0.0 | 0.0 | 289.0 | 0.0 | 2340234.0 | 0.0 | 2353464.0 | 0.0 | 256029.0 | 2097435.0 | 2338356.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194583.0 | 0.0 | 530.0 | 0.0 | 0.0 | 827694.0 | 2687277.0 | 0.0 | 0.0 | 2031625.0 | 0.0 | 4194526.0 | 0.0 | 2765194305.0 | 0.0 | 16335407823689 | 16343188774296 | 16343188954617 | 16335408332618 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7f018cefd980 | 0x7f018c6246c0 | 1297608 | 1199006 | 65536 | 162200 | 162200 | 5190400.0 | 4671351.0 | 0.0 | 0.0 | 0.0 | 185.0 | 0.0 | 1049360.0 | 0.0 | 1049527.0 | 0.0 | 777.0 | 1048750.0 | 1049547.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097352.0 | 0.0 | 372.0 | 0.0 | 0.0 | 479959.0 | 1479656.0 | 0.0 | 0.0 | 983049.0 | 0.0 | 2097277.0 | 0.0 | 1438335905.0 | 0.0 | 16335408417676 | 16343188977818 | 16343189070298 | 16335408847206 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7f018cefd800 | 0x7f018c624700 | 1308016 | 1196253 | 65536 | 163501 | 163501 | 5232032.0 | 4675136.0 | 0.0 | 0.0 | 0.0 | 186.0 | 0.0 | 1049472.0 | 0.0 | 1049646.0 | 0.0 | 888.0 | 1048758.0 | 1049662.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097348.0 | 0.0 | 360.0 | 0.0 | 0.0 | 487786.0 | 1546954.0 | 0.0 | 0.0 | 983050.0 | 0.0 | 2097288.0 | 0.0 | 1387263100.0 | 0.0 | 16335408931294 | 16343189094298 | 16343189186139 | 16335409352585 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7f018cefd680 | 0x7f018c624740 | 1296640 | 1196081 | 65536 | 162079 | 162079 | 5186528.0 | 4658776.0 | 0.0 | 0.0 | 0.0 | 175.0 | 0.0 | 1049304.0 | 0.0 | 1049475.0 | 0.0 | 721.0 | 1048754.0 | 1049484.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097347.0 | 0.0 | 364.0 | 0.0 | 0.0 | 456131.0 | 1451658.0 | 0.0 | 0.0 | 983049.0 | 0.0 | 2097284.0 | 0.0 | 1339758478.0 | 0.0 | 16335409445033 | 16343189218299 | 16343189310460 | 16335409862934 |
| 35 | 33 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 98 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7f018f696500 | 0x7f018c624780 | 2430344 | 2331843 | 65536 | 303792 | 303792 | 9721344.0 | 9222740.0 | 0.0 | 0.0 | 0.0 | 303.0 | 0.0 | 2337810.0 | 0.0 | 2327268.0 | 0.0 | 229840.0 | 2097428.0 | 2349231.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194599.0 | 0.0 | 560.0 | 0.0 | 0.0 | 655182.0 | 2162791.0 | 0.0 | 0.0 | 2031626.0 | 0.0 | 4194529.0 | 0.0 | 2587924749.0 | 0.0 | 16335409947292 | 16343189334620 | 16343189513821 | 16335410492570 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7f018f696380 | 0x7f018c6247c0 | 2433792 | 2330915 | 65536 | 304223 | 304223 | 9735136.0 | 9198262.0 | 0.0 | 0.0 | 0.0 | 290.0 | 0.0 | 2333817.0 | 0.0 | 2348259.0 | 0.0 | 250824.0 | 2097435.0 | 2326470.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194605.0 | 0.0 | 572.0 | 0.0 | 0.0 | 699069.0 | 2306010.0 | 0.0 | 0.0 | 2031626.0 | 0.0 | 4194532.0 | 0.0 | 2674873906.0 | 0.0 | 16335410576968 | 16343189538142 | 16343189717663 | 16335411095697 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7f018f696200 | 0x7f018c624800 | 1296192 | 1197458 | 65536 | 162023 | 162023 | 5184736.0 | 4650810.0 | 0.0 | 0.0 | 0.0 | 185.0 | 0.0 | 1049416.0 | 0.0 | 1049591.0 | 0.0 | 832.0 | 1048759.0 | 1049604.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097350.0 | 0.0 | 366.0 | 0.0 | 0.0 | 545706.0 | 1691754.0 | 0.0 | 0.0 | 983050.0 | 0.0 | 2097286.0 | 0.0 | 1369851276.0 | 0.0 | 16335411179665 | 16343189742143 | 16343189834784 | 16335411603655 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7f018f696080 | 0x7f018c624840 | 1290568 | 1186526 | 65536 | 161320 | 161320 | 5162240.0 | 4622764.0 | 0.0 | 0.0 | 0.0 | 187.0 | 0.0 | 1049584.0 | 0.0 | 1049751.0 | 0.0 | 999.0 | 1048752.0 | 1049768.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097353.0 | 0.0 | 366.0 | 0.0 | 0.0 | 341422.0 | 1195378.0 | 0.0 | 0.0 | 983051.0 | 0.0 | 2097286.0 | 0.0 | 1371931598.0 | 0.0 | 16335411687424 | 16343189858944 | 16343189951584 | 16335412107374 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7f018cefdf00 | 0x7f018c624880 | 1299160 | 1197662 | 65536 | 162394 | 162394 | 5196608.0 | 4652392.0 | 0.0 | 0.0 | 0.0 | 180.0 | 0.0 | 1049360.0 | 0.0 | 1049533.0 | 0.0 | 777.0 | 1048756.0 | 1049536.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097343.0 | 0.0 | 354.0 | 0.0 | 0.0 | 457482.0 | 1498445.0 | 0.0 | 0.0 | 983049.0 | 0.0 | 2097284.0 | 0.0 | 1373806801.0 | 0.0 | 16335412199412 | 16343189983905 | 16343190075585 | 16335412620283 |
| 40 | 38 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 113 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7f018cefdd80 | 0x7f018c6248c0 | 2443520 | 2341917 | 65536 | 305439 | 305439 | 9774048.0 | 9246363.0 | 0.0 | 0.0 | 0.0 | 290.0 | 0.0 | 2339461.0 | 0.0 | 2320102.0 | 0.0 | 222681.0 | 2097421.0 | 2333856.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194601.0 | 0.0 | 560.0 | 0.0 | 0.0 | 699403.0 | 2267714.0 | 0.0 | 0.0 | 2031627.0 | 0.0 | 4194528.0 | 0.0 | 2563726485.0 | 0.0 | 16335412704131 | 16343190104386 | 16343190283747 | 16335413217580 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7f018cefdc00 | 0x7f018c624900 | 2446224 | 2343221 | 65536 | 305777 | 305777 | 9784864.0 | 9264443.0 | 0.0 | 0.0 | 0.0 | 281.0 | 0.0 | 2352715.0 | 0.0 | 2341614.0 | 0.0 | 244193.0 | 2097421.0 | 2348891.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194594.0 | 0.0 | 550.0 | 0.0 | 0.0 | 619188.0 | 2042083.0 | 0.0 | 0.0 | 2031626.0 | 0.0 | 4194534.0 | 0.0 | 2724663205.0 | 0.0 | 16335413300538 | 16343190307267 | 16343190487908 | 16335413816097 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7f018cefda80 | 0x7f018c624940 | 1297416 | 1195003 | 65536 | 162176 | 162176 | 5189632.0 | 4660874.0 | 0.0 | 0.0 | 0.0 | 184.0 | 0.0 | 1049472.0 | 0.0 | 1049648.0 | 0.0 | 888.0 | 1048760.0 | 1049659.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097357.0 | 0.0 | 378.0 | 0.0 | 0.0 | 446337.0 | 1357632.0 | 0.0 | 0.0 | 983051.0 | 0.0 | 2097286.0 | 0.0 | 1301848535.0 | 0.0 | 16335413898935 | 16343190512708 | 16343190605189 | 16335414334885 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7f018cefd900 | 0x7f018c624980 | 1288704 | 1188254 | 65536 | 161087 | 161087 | 5154784.0 | 4600768.0 | 0.0 | 0.0 | 0.0 | 187.0 | 0.0 | 1049640.0 | 0.0 | 1049812.0 | 0.0 | 1054.0 | 1048758.0 | 1049815.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097353.0 | 0.0 | 364.0 | 0.0 | 0.0 | 409172.0 | 1168871.0 | 0.0 | 0.0 | 983052.0 | 0.0 | 2097288.0 | 0.0 | 1311017523.0 | 0.0 | 16335414421983 | 16343190628869 | 16343190721670 | 16335414860144 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7f018cefd780 | 0x7f018c6249c0 | 1291456 | 1193327 | 65536 | 161431 | 161431 | 5165792.0 | 4652654.0 | 0.0 | 0.0 | 0.0 | 184.0 | 0.0 | 1049416.0 | 0.0 | 1049590.0 | 0.0 | 832.0 | 1048758.0 | 1049594.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097342.0 | 0.0 | 350.0 | 0.0 | 0.0 | 416522.0 | 1249629.0 | 0.0 | 0.0 | 983050.0 | 0.0 | 2097284.0 | 0.0 | 1339510388.0 | 0.0 | 16335414956062 | 16343190753990 | 16343190845991 | 16335415383532 |
| 45 | 43 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 128 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7f018cefd600 | 0x7f018c624a00 | 2422424 | 2319503 | 65536 | 302802 | 302802 | 9689664.0 | 9166759.0 | 0.0 | 0.0 | 0.0 | 269.0 | 0.0 | 2344002.0 | 0.0 | 2353952.0 | 0.0 | 256519.0 | 2097433.0 | 2346715.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194585.0 | 0.0 | 526.0 | 0.0 | 0.0 | 769519.0 | 2485616.0 | 0.0 | 0.0 | 2031627.0 | 0.0 | 4194533.0 | 0.0 | 2871118241.0 | 0.0 | 16335415473600 | 16343190870951 | 16343191050632 | 16335415988409 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7f018f696480 | 0x7f018c624a40 | 2406232 | 2302700 | 65536 | 300778 | 300778 | 9624896.0 | 9096920.0 | 0.0 | 0.0 | 0.0 | 243.0 | 0.0 | 2348028.0 | 0.0 | 2355672.0 | 0.0 | 258239.0 | 2097433.0 | 2338798.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194577.0 | 0.0 | 512.0 | 0.0 | 0.0 | 772113.0 | 2573421.0 | 0.0 | 0.0 | 2031627.0 | 0.0 | 4194538.0 | 0.0 | 2776020321.0 | 0.0 | 16335416073627 | 16343191074152 | 16343191255114 | 16335416582656 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7f018f696300 | 0x7f018c624a80 | 1285616 | 1183891 | 65536 | 160701 | 160701 | 5142432.0 | 4631459.0 | 0.0 | 0.0 | 0.0 | 191.0 | 0.0 | 1049472.0 | 0.0 | 1049643.0 | 0.0 | 887.0 | 1048756.0 | 1049654.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097357.0 | 0.0 | 378.0 | 0.0 | 0.0 | 520842.0 | 1476430.0 | 0.0 | 0.0 | 983051.0 | 0.0 | 2097279.0 | 0.0 | 1358119080.0 | 0.0 | 16335416665914 | 16343191279114 | 16343191371435 | 16335417104264 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7f018f696180 | 0x7f018c624ac0 | 1281424 | 1177533 | 65536 | 160177 | 160177 | 5125664.0 | 4587724.0 | 0.0 | 0.0 | 0.0 | 190.0 | 0.0 | 1049696.0 | 0.0 | 1049872.0 | 0.0 | 1109.0 | 1048763.0 | 1049884.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097357.0 | 0.0 | 370.0 | 0.0 | 0.0 | 391964.0 | 1169373.0 | 0.0 | 0.0 | 983053.0 | 0.0 | 2097290.0 | 0.0 | 1359557042.0 | 0.0 | 16335417189162 | 16343191397195 | 16343191489355 | 16335417617743 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7f018f696000 | 0x7f018c624b00 | 1291472 | 1193237 | 65536 | 161433 | 161433 | 5165856.0 | 4651472.0 | 0.0 | 0.0 | 0.0 | 189.0 | 0.0 | 1049416.0 | 0.0 | 1049592.0 | 0.0 | 832.0 | 1048760.0 | 1049601.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097351.0 | 0.0 | 368.0 | 0.0 | 0.0 | 603953.0 | 1652181.0 | 0.0 | 0.0 | 983050.0 | 0.0 | 2097283.0 | 0.0 | 1338509148.0 | 0.0 | 16335417709741 | 16343191521676 | 16343191612876 | 16335418133892 |
| 50 | 48 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 143 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7f018cefde80 | 0x7f018c624b40 | 2422256 | 2316447 | 65536 | 302781 | 302781 | 9688992.0 | 9130432.0 | 0.0 | 0.0 | 0.0 | 262.0 | 0.0 | 2352783.0 | 0.0 | 2342558.0 | 0.0 | 245136.0 | 2097422.0 | 2343935.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194583.0 | 0.0 | 520.0 | 0.0 | 0.0 | 769516.0 | 2608080.0 | 0.0 | 0.0 | 2031628.0 | 0.0 | 4194544.0 | 0.0 | 2697417120.0 | 0.0 | 16335418218060 | 16343191638636 | 16343191817358 | 16335418745468 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7f018cefdd00 | 0x7f018c624b80 | 2414912 | 2315360 | 65536 | 301863 | 301863 | 9659616.0 | 9128654.0 | 0.0 | 0.0 | 0.0 | 261.0 | 0.0 | 2355958.0 | 0.0 | 2359305.0 | 0.0 | 261877.0 | 2097428.0 | 2349991.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194577.0 | 0.0 | 510.0 | 0.0 | 0.0 | 654812.0 | 2168942.0 | 0.0 | 0.0 | 2031627.0 | 0.0 | 4194531.0 | 0.0 | 2719236515.0 | 0.0 | 16335418829326 | 16343191842158 | 16343192023119 | 16335419362874 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7f018cefdb80 | 0x7f018c624bc0 | 1289584 | 1188887 | 65536 | 161197 | 161197 | 5158304.0 | 4604660.0 | 0.0 | 0.0 | 0.0 | 184.0 | 0.0 | 1049584.0 | 0.0 | 1049758.0 | 0.0 | 999.0 | 1048759.0 | 1049771.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097354.0 | 0.0 | 368.0 | 0.0 | 0.0 | 457911.0 | 1437847.0 | 0.0 | 0.0 | 983051.0 | 0.0 | 2097290.0 | 0.0 | 1338848683.0 | 0.0 | 16335419446023 | 16343192047119 | 16343192140560 | 16335419872453 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7f018cefda00 | 0x7f018c624c00 | 1289360 | 1189445 | 65536 | 161169 | 161169 | 5157408.0 | 4605177.0 | 0.0 | 0.0 | 0.0 | 187.0 | 0.0 | 1049808.0 | 0.0 | 1049984.0 | 0.0 | 1221.0 | 1048763.0 | 1049999.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097362.0 | 0.0 | 376.0 | 0.0 | 0.0 | 349786.0 | 1064472.0 | 0.0 | 0.0 | 983053.0 | 0.0 | 2097299.0 | 0.0 | 1370734670.0 | 0.0 | 16335419956431 | 16343192164240 | 16343192257041 | 16335420385102 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7f018cefd880 | 0x7f018c624c40 | 1284432 | 1185338 | 65536 | 160553 | 160553 | 5137696.0 | 4621145.0 | 0.0 | 0.0 | 0.0 | 185.0 | 0.0 | 1049528.0 | 0.0 | 1049704.0 | 0.0 | 943.0 | 1048761.0 | 1049709.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097349.0 | 0.0 | 360.0 | 0.0 | 0.0 | 627621.0 | 1937427.0 | 0.0 | 0.0 | 983051.0 | 0.0 | 2097288.0 | 0.0 | 1331677435.0 | 0.0 | 16335420476900 | 16343192289361 | 16343192381202 | 16335420897720 |
| 55 | 53 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 158 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7f018cefd700 | 0x7f018c624c80 | 2411952 | 2308573 | 65536 | 301493 | 301493 | 9647776.0 | 9134804.0 | 0.0 | 0.0 | 0.0 | 256.0 | 0.0 | 2348640.0 | 0.0 | 2350376.0 | 0.0 | 252946.0 | 2097430.0 | 2348731.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194576.0 | 0.0 | 506.0 | 0.0 | 0.0 | 558584.0 | 1834272.0 | 0.0 | 0.0 | 2031628.0 | 0.0 | 4194533.0 | 0.0 | 2806386392.0 | 0.0 | 16335420982888 | 16343192405522 | 16343192584563 | 16335421513137 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7f018f696580 | 0x7f018c624cc0 | 2403480 | 2304902 | 65536 | 300434 | 300434 | 9613888.0 | 9102912.0 | 0.0 | 0.0 | 0.0 | 241.0 | 0.0 | 2361629.0 | 0.0 | 2360022.0 | 0.0 | 262594.0 | 2097428.0 | 2367266.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194580.0 | 0.0 | 514.0 | 0.0 | 0.0 | 686772.0 | 2309952.0 | 0.0 | 0.0 | 2031628.0 | 0.0 | 4194531.0 | 0.0 | 2747112950.0 | 0.0 | 16335421597805 | 16343192609043 | 16343192790325 | 16335422130133 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7f018f696400 | 0x7f018c624d00 | 1294120 | 1195381 | 65536 | 161764 | 161764 | 5176448.0 | 4621401.0 | 0.0 | 0.0 | 0.0 | 192.0 | 0.0 | 1049640.0 | 0.0 | 1049810.0 | 0.0 | 1054.0 | 1048756.0 | 1049826.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097353.0 | 0.0 | 364.0 | 0.0 | 0.0 | 403612.0 | 1398799.0 | 0.0 | 0.0 | 983052.0 | 0.0 | 2097288.0 | 0.0 | 1390457247.0 | 0.0 | 16335422215281 | 16343192814485 | 16343192907285 | 16335422655051 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7f018f696280 | 0x7f018c624d40 | 1336536 | 1232646 | 65536 | 167066 | 167066 | 5346112.0 | 4786270.0 | 0.0 | 0.0 | 0.0 | 187.0 | 0.0 | 1049920.0 | 0.0 | 1050096.0 | 0.0 | 1332.0 | 1048764.0 | 1050101.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097360.0 | 0.0 | 368.0 | 0.0 | 0.0 | 387480.0 | 1062465.0 | 0.0 | 0.0 | 983054.0 | 0.0 | 2097301.0 | 0.0 | 1210449144.0 | 0.0 | 16335422740490 | 16343192932406 | 16343193029686 | 16335423194060 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7f018f696100 | 0x7f018c624d80 | 1289216 | 1187729 | 65536 | 161151 | 161151 | 5156832.0 | 4635536.0 | 0.0 | 0.0 | 0.0 | 190.0 | 0.0 | 1049528.0 | 0.0 | 1049708.0 | 0.0 | 943.0 | 1048765.0 | 1049712.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097350.0 | 0.0 | 362.0 | 0.0 | 0.0 | 446967.0 | 1429288.0 | 0.0 | 0.0 | 983051.0 | 0.0 | 2097288.0 | 0.0 | 1379991018.0 | 0.0 | 16335423287188 | 16343193062006 | 16343193154007 | 16335423720338 |
| 60 | 58 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 173 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7f018cefdf80 | 0x7f018c624dc0 | 2391072 | 2292985 | 65536 | 298883 | 298883 | 9564256.0 | 9073419.0 | 0.0 | 0.0 | 0.0 | 267.0 | 0.0 | 2355504.0 | 0.0 | 2342469.0 | 0.0 | 245038.0 | 2097431.0 | 2350470.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194593.0 | 0.0 | 538.0 | 0.0 | 0.0 | 664244.0 | 2180623.0 | 0.0 | 0.0 | 2031629.0 | 0.0 | 4194534.0 | 0.0 | 2772665580.0 | 0.0 | 16335423805566 | 16343193181047 | 16343193361049 | 16335424336114 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7f018cefde00 | 0x7f018c624e00 | 2408296 | 2304092 | 65536 | 301036 | 301036 | 9633152.0 | 9134168.0 | 0.0 | 0.0 | 0.0 | 259.0 | 0.0 | 2369162.0 | 0.0 | 2355700.0 | 0.0 | 258287.0 | 2097413.0 | 2373848.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194556.0 | 0.0 | 466.0 | 0.0 | 0.0 | 699382.0 | 2298599.0 | 0.0 | 0.0 | 2031628.0 | 0.0 | 4194532.0 | 0.0 | 2772422303.0 | 0.0 | 16335424420853 | 16343193384729 | 16343193562330 | 16335424957271 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7f018cefdc80 | 0x7f018c624e40 | 1287648 | 1185713 | 65536 | 160955 | 160955 | 5150560.0 | 4594260.0 | 0.0 | 0.0 | 0.0 | 189.0 | 0.0 | 1049696.0 | 0.0 | 1049867.0 | 0.0 | 1110.0 | 1048757.0 | 1049882.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097354.0 | 0.0 | 364.0 | 0.0 | 0.0 | 452315.0 | 1378047.0 | 0.0 | 0.0 | 983052.0 | 0.0 | 2097289.0 | 0.0 | 1377024122.0 | 0.0 | 16335425041639 | 16343193589050 | 16343193682171 | 16335425485609 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7f018cefdb00 | 0x7f018c624e80 | 1395672 | 1294277 | 65536 | 174458 | 174458 | 5582656.0 | 5031243.0 | 0.0 | 0.0 | 0.0 | 183.0 | 0.0 | 1049976.0 | 0.0 | 1050155.0 | 0.0 | 1387.0 | 1048768.0 | 1050155.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097357.0 | 0.0 | 360.0 | 0.0 | 0.0 | 323645.0 | 1015438.0 | 0.0 | 0.0 | 983055.0 | 0.0 | 2097299.0 | 0.0 | 1085017918.0 | 0.0 | 16335425570627 | 16343193708091 | 16343193810492 | 16335426043957 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7f018cefd980 | 0x7f018c624ec0 | 1285248 | 1183464 | 65536 | 160655 | 160655 | 5140960.0 | 4627736.0 | 0.0 | 0.0 | 0.0 | 185.0 | 0.0 | 1049528.0 | 0.0 | 1049698.0 | 0.0 | 943.0 | 1048755.0 | 1049709.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097353.0 | 0.0 | 368.0 | 0.0 | 0.0 | 510251.0 | 1419818.0 | 0.0 | 0.0 | 983051.0 | 0.0 | 2097287.0 | 0.0 | 1343812580.0 | 0.0 | 16335426137125 | 16343193842812 | 16343193934973 | 16335426579695 |
| 65 | 63 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 188 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7f018cefd800 | 0x7f018c624f00 | 2416832 | 2315590 | 65536 | 302103 | 302103 | 9667296.0 | 9113650.0 | 0.0 | 0.0 | 0.0 | 226.0 | 0.0 | 2327197.0 | 0.0 | 2341002.0 | 0.0 | 243583.0 | 2097419.0 | 2355097.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194544.0 | 0.0 | 436.0 | 0.0 | 0.0 | 635540.0 | 2103097.0 | 0.0 | 0.0 | 2031629.0 | 0.0 | 4194519.0 | 0.0 | 2767884569.0 | 0.0 | 16335426664403 | 16343193958813 | 16343194139454 | 16335427187782 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7f018cefd680 | 0x7f018c624f40 | 2404368 | 2296403 | 65536 | 300545 | 300545 | 9617440.0 | 9062123.0 | 0.0 | 0.0 | 0.0 | 244.0 | 0.0 | 2360227.0 | 0.0 | 2355598.0 | 0.0 | 258185.0 | 2097413.0 | 2362594.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194565.0 | 0.0 | 480.0 | 0.0 | 0.0 | 607461.0 | 1975742.0 | 0.0 | 0.0 | 2031629.0 | 0.0 | 4194530.0 | 0.0 | 2786265737.0 | 0.0 | 16335427271760 | 16343194166814 | 16343194346816 | 16335427825588 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7f018f696500 | 0x7f018c624f80 | 1281712 | 1177228 | 65536 | 160213 | 160213 | 5126816.0 | 4593081.0 | 0.0 | 0.0 | 0.0 | 190.0 | 0.0 | 1049696.0 | 0.0 | 1049862.0 | 0.0 | 1109.0 | 1048753.0 | 1049880.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097361.0 | 0.0 | 378.0 | 0.0 | 0.0 | 460347.0 | 1348517.0 | 0.0 | 0.0 | 983053.0 | 0.0 | 2097284.0 | 0.0 | 1400679362.0 | 0.0 | 16335427909406 | 16343194370016 | 16343194462976 | 16335428358296 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7f018f696380 | 0x7f018c624fc0 | 1434928 | 1337757 | 65536 | 179365 | 179365 | 5739680.0 | 5215168.0 | 0.0 | 0.0 | 0.0 | 174.0 | 0.0 | 1050032.0 | 0.0 | 1050210.0 | 0.0 | 1442.0 | 1048768.0 | 1050205.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097349.0 | 0.0 | 342.0 | 0.0 | 0.0 | 98775.0 | 341104.0 | 0.0 | 0.0 | 983056.0 | 0.0 | 2097297.0 | 0.0 | 1011766312.0 | 0.0 | 16335428445504 | 16343194486977 | 16343194592417 | 16335428900364 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7f018f696200 | 0x7f018c625000 | 1283128 | 1183710 | 65536 | 160390 | 160390 | 5132480.0 | 4593804.0 | 0.0 | 0.0 | 0.0 | 190.0 | 0.0 | 1049640.0 | 0.0 | 1049816.0 | 0.0 | 1054.0 | 1048762.0 | 1049827.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097348.0 | 0.0 | 354.0 | 0.0 | 0.0 | 469964.0 | 1439522.0 | 0.0 | 0.0 | 983052.0 | 0.0 | 2097287.0 | 0.0 | 1336690459.0 | 0.0 | 16335429005882 | 16343194624738 | 16343194717218 | 16335429429642 |
| 70 | 68 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 203 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7f018f696080 | 0x7f018c625040 | 2404976 | 2304273 | 65536 | 300621 | 300621 | 9619872.0 | 9060467.0 | 0.0 | 0.0 | 0.0 | 225.0 | 0.0 | 2359138.0 | 0.0 | 2343880.0 | 0.0 | 246471.0 | 2097409.0 | 2343282.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194558.0 | 0.0 | 462.0 | 0.0 | 0.0 | 515550.0 | 1698297.0 | 0.0 | 0.0 | 2031630.0 | 0.0 | 4194535.0 | 0.0 | 2731143008.0 | 0.0 | 16335429514331 | 16343194741058 | 16343194921700 | 16335430047709 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7f018cefdf00 | 0x7f018c625080 | 2407568 | 2305432 | 65536 | 300945 | 300945 | 9630240.0 | 9105118.0 | 0.0 | 0.0 | 0.0 | 251.0 | 0.0 | 2366473.0 | 0.0 | 2343198.0 | 0.0 | 245767.0 | 2097431.0 | 2330911.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194564.0 | 0.0 | 476.0 | 0.0 | 0.0 | 676945.0 | 2224648.0 | 0.0 | 0.0 | 2031629.0 | 0.0 | 4194530.0 | 0.0 | 2747649586.0 | 0.0 | 16335430132737 | 16343194945060 | 16343195126341 | 16335430673325 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7f018cefdd80 | 0x7f018c6250c0 | 1293528 | 1184942 | 65536 | 161690 | 161690 | 5174080.0 | 4596507.0 | 0.0 | 0.0 | 0.0 | 187.0 | 0.0 | 1049808.0 | 0.0 | 1049985.0 | 0.0 | 1221.0 | 1048764.0 | 1049992.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097355.0 | 0.0 | 362.0 | 0.0 | 0.0 | 619396.0 | 1900286.0 | 0.0 | 0.0 | 983053.0 | 0.0 | 2097288.0 | 0.0 | 1381159155.0 | 0.0 | 16335430757853 | 16343195150181 | 16343195244102 | 16335431201953 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7f018cefdc00 | 0x7f018c625100 | 1516528 | 1418187 | 65536 | 189565 | 189565 | 6066080.0 | 5487910.0 | 0.0 | 0.0 | 0.0 | 163.0 | 0.0 | 1050144.0 | 0.0 | 1050304.0 | 0.0 | 1554.0 | 1048750.0 | 1050310.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097334.0 | 0.0 | 308.0 | 0.0 | 0.0 | 92509.0 | 298965.0 | 0.0 | 0.0 | 983056.0 | 0.0 | 2097290.0 | 0.0 | 818301928.0 | 0.0 | 16335431286701 | 16343195267302 | 16343195379463 | 16335431748461 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7f018cefda80 | 0x7f018c625140 | 1285136 | 1185155 | 65536 | 160641 | 160641 | 5140512.0 | 4603425.0 | 0.0 | 0.0 | 0.0 | 191.0 | 0.0 | 1049696.0 | 0.0 | 1049871.0 | 0.0 | 1110.0 | 1048761.0 | 1049882.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097355.0 | 0.0 | 366.0 | 0.0 | 0.0 | 508449.0 | 1569400.0 | 0.0 | 0.0 | 983052.0 | 0.0 | 2097285.0 | 0.0 | 1386540951.0 | 0.0 | 16335431840619 | 16343195425543 | 16343195517864 | 16335432279329 |
| 75 | 73 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 218 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7f018cefd900 | 0x7f018c625180 | 2411408 | 2312681 | 65536 | 301425 | 301425 | 9645600.0 | 9100486.0 | 0.0 | 0.0 | 0.0 | 264.0 | 0.0 | 2346234.0 | 0.0 | 2337733.0 | 0.0 | 240301.0 | 2097432.0 | 2348585.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194574.0 | 0.0 | 492.0 | 0.0 | 0.0 | 549113.0 | 1824501.0 | 0.0 | 0.0 | 2031630.0 | 0.0 | 4194543.0 | 0.0 | 2794472265.0 | 0.0 | 16335432363797 | 16343195543144 | 16343195723145 | 16335432888476 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7f018cefd780 | 0x7f018c6251c0 | 2385616 | 2283149 | 65536 | 298201 | 298201 | 9542432.0 | 8993265.0 | 0.0 | 0.0 | 0.0 | 253.0 | 0.0 | 2363775.0 | 0.0 | 2344567.0 | 0.0 | 247147.0 | 2097420.0 | 2345945.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194564.0 | 0.0 | 474.0 | 0.0 | 0.0 | 610537.0 | 2001289.0 | 0.0 | 0.0 | 2031630.0 | 0.0 | 4194533.0 | 0.0 | 2759324936.0 | 0.0 | 16335432972334 | 16343195749705 | 16343195930507 | 16335433523032 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7f018cefd600 | 0x7f018c625200 | 1283888 | 1179766 | 65536 | 160485 | 160485 | 5135520.0 | 4570747.0 | 0.0 | 0.0 | 0.0 | 189.0 | 0.0 | 1049864.0 | 0.0 | 1050036.0 | 0.0 | 1276.0 | 1048760.0 | 1050050.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097358.0 | 0.0 | 366.0 | 0.0 | 0.0 | 580798.0 | 1861172.0 | 0.0 | 0.0 | 983054.0 | 0.0 | 2097300.0 | 0.0 | 1308756689.0 | 0.0 | 16335433607440 | 16343195954187 | 16343196047948 | 16335434057470 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7f018f696480 | 0x7f018c625240 | 1603456 | 1496625 | 65536 | 200431 | 200431 | 6413792.0 | 5819141.0 | 0.0 | 0.0 | 0.0 | 163.0 | 0.0 | 1050256.0 | 0.0 | 1050422.0 | 0.0 | 1665.0 | 1048757.0 | 1050413.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097335.0 | 0.0 | 306.0 | 0.0 | 0.0 | 92567.0 | 302746.0 | 0.0 | 0.0 | 983057.0 | 0.0 | 2097291.0 | 0.0 | 750792552.0 | 0.0 | 16335434148258 | 16343196074028 | 16343196192749 | 16335434627137 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7f018f696300 | 0x7f018c625280 | 1280960 | 1178051 | 65536 | 160119 | 160119 | 5123808.0 | 4581147.0 | 0.0 | 0.0 | 0.0 | 186.0 | 0.0 | 1049696.0 | 0.0 | 1049865.0 | 0.0 | 1110.0 | 1048755.0 | 1049880.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097356.0 | 0.0 | 368.0 | 0.0 | 0.0 | 370349.0 | 1101456.0 | 0.0 | 0.0 | 983052.0 | 0.0 | 2097290.0 | 0.0 | 1314117181.0 | 0.0 | 16335434720245 | 16343196224909 | 16343196316909 | 16335435167765 |
| 80 | 78 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 233 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7f018f696180 | 0x7f018c6252c0 | 2404832 | 2307127 | 65536 | 300603 | 300603 | 9619296.0 | 9062333.0 | 0.0 | 0.0 | 0.0 | 264.0 | 0.0 | 2351198.0 | 0.0 | 2352122.0 | 0.0 | 254691.0 | 2097431.0 | 2365203.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194589.0 | 0.0 | 522.0 | 0.0 | 0.0 | 655424.0 | 2160002.0 | 0.0 | 0.0 | 2031630.0 | 0.0 | 4194534.0 | 0.0 | 2711106639.0 | 0.0 | 16335435253704 | 16343196341070 | 16343196521231 | 16335435785442 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7f018f696000 | 0x7f018c625300 | 2380184 | 2277908 | 65536 | 297522 | 297522 | 9520704.0 | 8998152.0 | 0.0 | 0.0 | 0.0 | 258.0 | 0.0 | 2340489.0 | 0.0 | 2357995.0 | 0.0 | 260570.0 | 2097425.0 | 2344248.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194565.0 | 0.0 | 474.0 | 0.0 | 0.0 | 724905.0 | 2420383.0 | 0.0 | 0.0 | 2031630.0 | 0.0 | 4194533.0 | 0.0 | 2741511643.0 | 0.0 | 16335435875400 | 16343196546031 | 16343196725072 | 16335436397098 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7f018cefde80 | 0x7f018c625340 | 1289744 | 1182132 | 65536 | 161217 | 161217 | 5158944.0 | 4588807.0 | 0.0 | 0.0 | 0.0 | 192.0 | 0.0 | 1049920.0 | 0.0 | 1050093.0 | 0.0 | 1332.0 | 1048761.0 | 1050103.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097356.0 | 0.0 | 360.0 | 0.0 | 0.0 | 597380.0 | 1918874.0 | 0.0 | 0.0 | 983054.0 | 0.0 | 2097299.0 | 0.0 | 1331620880.0 | 0.0 | 16335436481257 | 16343196749713 | 16343196843153 | 16335436940246 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7f018cefdd00 | 0x7f018c625380 | 1662488 | 1562453 | 65536 | 207810 | 207810 | 6649920.0 | 6104575.0 | 0.0 | 0.0 | 0.0 | 160.0 | 0.0 | 1050312.0 | 0.0 | 1050466.0 | 0.0 | 1720.0 | 1048746.0 | 1050475.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097340.0 | 0.0 | 314.0 | 0.0 | 0.0 | 57176.0 | 207195.0 | 0.0 | 0.0 | 983058.0 | 0.0 | 2097283.0 | 0.0 | 718181742.0 | 0.0 | 16335437024765 | 16343196867793 | 16343196991634 | 16335437508644 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7f018cefdb80 | 0x7f018c6253c0 | 1279936 | 1179958 | 65536 | 159991 | 159991 | 5119712.0 | 4580514.0 | 0.0 | 0.0 | 0.0 | 188.0 | 0.0 | 1049752.0 | 0.0 | 1049929.0 | 0.0 | 1165.0 | 1048764.0 | 1049939.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097352.0 | 0.0 | 358.0 | 0.0 | 0.0 | 670186.0 | 2003460.0 | 0.0 | 0.0 | 983053.0 | 0.0 | 2097290.0 | 0.0 | 1383047139.0 | 0.0 | 16335437600452 | 16343197023634 | 16343197116915 | 16335438037742 |
| 85 | 83 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 248 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7f018cefda00 | 0x7f018c625400 | 2383904 | 2282763 | 65536 | 297987 | 297987 | 9535584.0 | 9033726.0 | 0.0 | 0.0 | 0.0 | 246.0 | 0.0 | 2346834.0 | 0.0 | 2363084.0 | 0.0 | 265655.0 | 2097429.0 | 2355359.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194574.0 | 0.0 | 490.0 | 0.0 | 0.0 | 601192.0 | 1974472.0 | 0.0 | 0.0 | 2031631.0 | 0.0 | 4194551.0 | 0.0 | 2755775772.0 | 0.0 | 16335438122690 | 16343197140915 | 16343197319317 | 16335438658839 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7f018cefd880 | 0x7f018c625440 | 2371952 | 2274505 | 65536 | 296493 | 296493 | 9487776.0 | 8955939.0 | 0.0 | 0.0 | 0.0 | 264.0 | 0.0 | 2340403.0 | 0.0 | 2332940.0 | 0.0 | 235503.0 | 2097437.0 | 2360257.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194602.0 | 0.0 | 546.0 | 0.0 | 0.0 | 633313.0 | 2058221.0 | 0.0 | 0.0 | 2031631.0 | 0.0 | 4194547.0 | 0.0 | 2741519636.0 | 0.0 | 16335438743017 | 16343197343477 | 16343197523638 | 16335439274105 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7f018cefd700 | 0x7f018c625480 | 1276320 | 1177676 | 65536 | 159539 | 159539 | 5105248.0 | 4592422.0 | 0.0 | 0.0 | 0.0 | 186.0 | 0.0 | 1049920.0 | 0.0 | 1050095.0 | 0.0 | 1331.0 | 1048764.0 | 1050101.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097361.0 | 0.0 | 370.0 | 0.0 | 0.0 | 372899.0 | 1129986.0 | 0.0 | 0.0 | 983055.0 | 0.0 | 2097299.0 | 0.0 | 1338219528.0 | 0.0 | 16335439358643 | 16343197547478 | 16343197639959 | 16335439807683 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7f018f696580 | 0x7f018c6254c0 | 1734120 | 1632987 | 65536 | 216764 | 216764 | 6936448.0 | 6400900.0 | 0.0 | 0.0 | 0.0 | 151.0 | 0.0 | 1050368.0 | 0.0 | 1050525.0 | 0.0 | 1775.0 | 1048750.0 | 1050512.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097334.0 | 0.0 | 300.0 | 0.0 | 0.0 | 41259.0 | 163735.0 | 0.0 | 0.0 | 983059.0 | 0.0 | 2097283.0 | 0.0 | 711045886.0 | 0.0 | 16335439894841 | 16343197663639 | 16343197792120 | 16335440382300 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7f018f696400 | 0x7f018c625500 | 1274472 | 1173362 | 65536 | 159308 | 159308 | 5097856.0 | 4562450.0 | 0.0 | 0.0 | 0.0 | 186.0 | 0.0 | 1049752.0 | 0.0 | 1049924.0 | 0.0 | 1165.0 | 1048759.0 | 1049944.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097355.0 | 0.0 | 364.0 | 0.0 | 0.0 | 546103.0 | 1758259.0 | 0.0 | 0.0 | 983053.0 | 0.0 | 2097288.0 | 0.0 | 1385792495.0 | 0.0 | 16335440475948 | 16343197824440 | 16343197916921 | 16335440913729 |
| 90 | 88 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 263 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7f018f696280 | 0x7f018c625540 | 2388280 | 2289373 | 65536 | 298534 | 298534 | 9553088.0 | 9007212.0 | 0.0 | 0.0 | 0.0 | 240.0 | 0.0 | 2353672.0 | 0.0 | 2354131.0 | 0.0 | 256712.0 | 2097419.0 | 2370257.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194562.0 | 0.0 | 462.0 | 0.0 | 0.0 | 712839.0 | 2386849.0 | 0.0 | 0.0 | 2031632.0 | 0.0 | 4194528.0 | 0.0 | 2736324158.0 | 0.0 | 16335440999327 | 16343197943161 | 16343198121082 | 16335441529745 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7f018f696100 | 0x7f018c625580 | 2378336 | 2278937 | 65536 | 297291 | 297291 | 9513312.0 | 8975432.0 | 0.0 | 0.0 | 0.0 | 253.0 | 0.0 | 2355963.0 | 0.0 | 2343139.0 | 0.0 | 245705.0 | 2097434.0 | 2355903.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194566.0 | 0.0 | 472.0 | 0.0 | 0.0 | 740504.0 | 2488130.0 | 0.0 | 0.0 | 2031631.0 | 0.0 | 4194531.0 | 0.0 | 2793995890.0 | 0.0 | 16335441613583 | 16343198146682 | 16343198325724 | 16335442145271 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7f018cefdf80 | 0x7f018c6255c0 | 1288136 | 1189599 | 65536 | 161016 | 161016 | 5152512.0 | 4597236.0 | 0.0 | 0.0 | 0.0 | 185.0 | 0.0 | 1050032.0 | 0.0 | 1050207.0 | 0.0 | 1443.0 | 1048764.0 | 1050218.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097363.0 | 0.0 | 370.0 | 0.0 | 0.0 | 276399.0 | 878295.0 | 0.0 | 0.0 | 983055.0 | 0.0 | 2097299.0 | 0.0 | 1363558675.0 | 0.0 | 16335442232139 | 16343198349724 | 16343198443004 | 16335442678809 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7f018cefde00 | 0x7f018c625600 | 1820504 | 1719549 | 65536 | 227562 | 227562 | 7281984.0 | 6673200.0 | 0.0 | 0.0 | 0.0 | 153.0 | 0.0 | 1050480.0 | 0.0 | 1050633.0 | 0.0 | 1887.0 | 1048746.0 | 1050628.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097332.0 | 0.0 | 292.0 | 0.0 | 0.0 | 20592.0 | 117125.0 | 0.0 | 0.0 | 983059.0 | 0.0 | 2097283.0 | 0.0 | 669064079.0 | 0.0 | 16335442762608 | 16343198466685 | 16343198602366 | 16335443242257 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7f018cefdc80 | 0x7f018c625640 | 1276368 | 1177029 | 65536 | 159545 | 159545 | 5105440.0 | 4552079.0 | 0.0 | 0.0 | 0.0 | 190.0 | 0.0 | 1049808.0 | 0.0 | 1049986.0 | 0.0 | 1221.0 | 1048765.0 | 1049989.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097360.0 | 0.0 | 372.0 | 0.0 | 0.0 | 451540.0 | 1432630.0 | 0.0 | 0.0 | 983053.0 | 0.0 | 2097292.0 | 0.0 | 1304540426.0 | 0.0 | 16335443334245 | 16343198635326 | 16343198728606 | 16335443776405 |
| 95 | 93 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 278 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7f018cefdb00 | 0x7f018c625680 | 2363904 | 2264491 | 65536 | 295487 | 295487 | 9455584.0 | 8910246.0 | 0.0 | 0.0 | 0.0 | 249.0 | 0.0 | 2364511.0 | 0.0 | 2349300.0 | 0.0 | 251869.0 | 2097431.0 | 2364643.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194571.0 | 0.0 | 478.0 | 0.0 | 0.0 | 747726.0 | 2490708.0 | 0.0 | 0.0 | 2031632.0 | 0.0 | 4194528.0 | 0.0 | 2765568118.0 | 0.0 | 16335443861133 | 16343198753407 | 16343198932288 | 16335444406901 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7f018cefd980 | 0x7f018c6256c0 | 2361640 | 2262044 | 65536 | 295204 | 295204 | 9446528.0 | 8926969.0 | 0.0 | 0.0 | 0.0 | 265.0 | 0.0 | 2360459.0 | 0.0 | 2362420.0 | 0.0 | 264997.0 | 2097423.0 | 2346673.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194583.0 | 0.0 | 504.0 | 0.0 | 0.0 | 910243.0 | 2984294.0 | 0.0 | 0.0 | 2031632.0 | 0.0 | 4194544.0 | 0.0 | 2781989557.0 | 0.0 | 16335444490810 | 16343198956128 | 16343199135969 | 16335445026678 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7f018cefd800 | 0x7f018c625700 | 1303560 | 1194724 | 65536 | 162944 | 162944 | 5214208.0 | 4653219.0 | 0.0 | 0.0 | 0.0 | 185.0 | 0.0 | 1050088.0 | 0.0 | 1050266.0 | 0.0 | 1498.0 | 1048768.0 | 1050273.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097359.0 | 0.0 | 360.0 | 0.0 | 0.0 | 346983.0 | 1108231.0 | 0.0 | 0.0 | 983056.0 | 0.0 | 2097305.0 | 0.0 | 1354352893.0 | 0.0 | 16335445111556 | 16343199158690 | 16343199254050 | 16335445566716 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7f018cefd680 | 0x7f018c625740 | 1883584 | 1785664 | 65536 | 235447 | 235447 | 7534304.0 | 6985467.0 | 0.0 | 0.0 | 0.0 | 151.0 | 0.0 | 1050592.0 | 0.0 | 1050739.0 | 0.0 | 1998.0 | 1048741.0 | 1050741.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097336.0 | 0.0 | 296.0 | 0.0 | 0.0 | 47257.0 | 186818.0 | 0.0 | 0.0 | 983060.0 | 0.0 | 2097287.0 | 0.0 | 624466956.0 | 0.0 | 16335445651274 | 16343199278530 | 16343199420611 | 16335446153103 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7f018f696500 | 0x7f018c625780 | 1278288 | 1172871 | 65536 | 159785 | 159785 | 5113120.0 | 4546019.0 | 0.0 | 0.0 | 0.0 | 193.0 | 0.0 | 1049920.0 | 0.0 | 1050094.0 | 0.0 | 1332.0 | 1048762.0 | 1050110.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097363.0 | 0.0 | 374.0 | 0.0 | 0.0 | 491386.0 | 1485651.0 | 0.0 | 0.0 | 983054.0 | 0.0 | 2097295.0 | 0.0 | 1350130151.0 | 0.0 | 16335446246031 | 16343199452932 | 16343199546212 | 16335446692931 |
| 100 | 98 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 293 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7f018f696380 | 0x7f018c6257c0 | 2381112 | 2272933 | 65536 | 297638 | 297638 | 9524416.0 | 8954714.0 | 0.0 | 0.0 | 0.0 | 274.0 | 0.0 | 2357111.0 | 0.0 | 2343447.0 | 0.0 | 246013.0 | 2097434.0 | 2357820.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194610.0 | 0.0 | 552.0 | 0.0 | 0.0 | 562852.0 | 1906479.0 | 0.0 | 0.0 | 2031633.0 | 0.0 | 4194554.0 | 0.0 | 2685025674.0 | 0.0 | 16335446778019 | 16343199570052 | 16343199747654 | 16335447308848 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7f018f696200 | 0x7f018c625800 | 2370544 | 2268223 | 65536 | 296317 | 296317 | 9482144.0 | 8926877.0 | 0.0 | 0.0 | 0.0 | 250.0 | 0.0 | 2379998.0 | 0.0 | 2341096.0 | 0.0 | 243656.0 | 2097440.0 | 2363123.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194585.0 | 0.0 | 504.0 | 0.0 | 0.0 | 646860.0 | 2159304.0 | 0.0 | 0.0 | 2031633.0 | 0.0 | 4194536.0 | 0.0 | 2692964419.0 | 0.0 | 16335447393896 | 16343199771814 | 16343199951335 | 16335447926524 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7f018f696080 | 0x7f018c625840 | 1355024 | 1252014 | 65536 | 169377 | 169377 | 5420064.0 | 4883327.0 | 0.0 | 0.0 | 0.0 | 187.0 | 0.0 | 1050144.0 | 0.0 | 1050321.0 | 0.0 | 1553.0 | 1048768.0 | 1050317.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097357.0 | 0.0 | 354.0 | 0.0 | 0.0 | 375433.0 | 1198854.0 | 0.0 | 0.0 | 983057.0 | 0.0 | 2097299.0 | 0.0 | 1143518809.0 | 0.0 | 16335448011692 | 16343199976135 | 16343200075496 | 16335448464422 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7f018cefdf00 | 0x7f018c625880 | 2043872 | 1944972 | 65536 | 255483 | 255483 | 8175456.0 | 7610277.0 | 0.0 | 0.0 | 0.0 | 149.0 | 0.0 | 1050704.0 | 0.0 | 1050847.0 | 0.0 | 2108.0 | 1048739.0 | 1050847.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097333.0 | 0.0 | 286.0 | 0.0 | 0.0 | 36965.0 | 152148.0 | 0.0 | 0.0 | 983062.0 | 0.0 | 2097281.0 | 0.0 | 630902061.0 | 0.0 | 16335448548870 | 16343200099176 | 16343200253097 | 16335449058099 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7f018cefdd80 | 0x7f018c6258c0 | 1268384 | 1166661 | 65536 | 158547 | 158547 | 5073504.0 | 4532226.0 | 0.0 | 0.0 | 0.0 | 192.0 | 0.0 | 1049976.0 | 0.0 | 1050155.0 | 0.0 | 1387.0 | 1048768.0 | 1050163.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097365.0 | 0.0 | 376.0 | 0.0 | 0.0 | 581595.0 | 1900696.0 | 0.0 | 0.0 | 983055.0 | 0.0 | 2097296.0 | 0.0 | 1299343808.0 | 0.0 | 16335449151047 | 16343200285257 | 16343200378058 | 16335449593517 |
| 105 | 103 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 308 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7f018cefdc00 | 0x7f018c625900 | 2356944 | 2256465 | 65536 | 294617 | 294617 | 9427744.0 | 8891313.0 | 0.0 | 0.0 | 0.0 | 283.0 | 0.0 | 2347743.0 | 0.0 | 2333605.0 | 0.0 | 236164.0 | 2097441.0 | 2364735.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194611.0 | 0.0 | 552.0 | 0.0 | 0.0 | 707474.0 | 2403391.0 | 0.0 | 0.0 | 2031634.0 | 0.0 | 4194548.0 | 0.0 | 2754518590.0 | 0.0 | 16335449668306 | 16343200403498 | 16343200582220 | 16335450198804 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7f018cefda80 | 0x7f018c625940 | 2361608 | 2259153 | 65536 | 295200 | 295200 | 9446400.0 | 8904165.0 | 0.0 | 0.0 | 0.0 | 252.0 | 0.0 | 2346828.0 | 0.0 | 2345631.0 | 0.0 | 248191.0 | 2097440.0 | 2358375.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194604.0 | 0.0 | 538.0 | 0.0 | 0.0 | 746594.0 | 2486081.0 | 0.0 | 0.0 | 2031634.0 | 0.0 | 4194538.0 | 0.0 | 2733692953.0 | 0.0 | 16335450284332 | 16343200606700 | 16343200787661 | 16335450819200 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7f018cefd900 | 0x7f018c625980 | 1413736 | 1310449 | 65536 | 176716 | 176716 | 5654912.0 | 5103056.0 | 0.0 | 0.0 | 0.0 | 173.0 | 0.0 | 1050312.0 | 0.0 | 1050481.0 | 0.0 | 1720.0 | 1048761.0 | 1050478.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097358.0 | 0.0 | 350.0 | 0.0 | 0.0 | 172732.0 | 546883.0 | 0.0 | 0.0 | 983058.0 | 0.0 | 2097303.0 | 0.0 | 984096753.0 | 0.0 | 16335450903518 | 16343200810861 | 16343200914542 | 16335451361908 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7f018cefd780 | 0x7f018c6259c0 | 2210368 | 2105262 | 65536 | 276295 | 276295 | 8841440.0 | 8264072.0 | 0.0 | 0.0 | 0.0 | 143.0 | 0.0 | 1050928.0 | 0.0 | 1051070.0 | 0.0 | 2331.0 | 1048739.0 | 1051075.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097335.0 | 0.0 | 282.0 | 0.0 | 0.0 | 8733.0 | 76804.0 | 0.0 | 0.0 | 983063.0 | 0.0 | 2097284.0 | 0.0 | 580059050.0 | 0.0 | 16335451445666 | 16343200939342 | 16343201106703 | 16335451988514 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7f018cefd600 | 0x7f018c625a00 | 1276880 | 1177184 | 65536 | 159609 | 159609 | 5107488.0 | 4572256.0 | 0.0 | 0.0 | 0.0 | 184.0 | 0.0 | 1050088.0 | 0.0 | 1050268.0 | 0.0 | 1498.0 | 1048770.0 | 1050274.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097364.0 | 0.0 | 370.0 | 0.0 | 0.0 | 347493.0 | 1162751.0 | 0.0 | 0.0 | 983056.0 | 0.0 | 2097305.0 | 0.0 | 1261376487.0 | 0.0 | 16335452081202 | 16343201139024 | 16343201232784 | 16335452523102 |
| 110 | 108 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 323 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7f018f696480 | 0x7f018c625a40 | 2351320 | 2250210 | 65536 | 293914 | 293914 | 9405248.0 | 8820999.0 | 0.0 | 0.0 | 0.0 | 275.0 | 0.0 | 2355847.0 | 0.0 | 2346394.0 | 0.0 | 248962.0 | 2097432.0 | 2353443.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194615.0 | 0.0 | 554.0 | 0.0 | 0.0 | 630888.0 | 2126399.0 | 0.0 | 0.0 | 2031635.0 | 0.0 | 4194545.0 | 0.0 | 2660329949.0 | 0.0 | 16335452610970 | 16343201256464 | 16343201435186 | 16335453157428 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7f018f696300 | 0x7f018c625a80 | 2367968 | 2267746 | 65536 | 295995 | 295995 | 9471840.0 | 8874553.0 | 0.0 | 0.0 | 0.0 | 258.0 | 0.0 | 2351458.0 | 0.0 | 2346435.0 | 0.0 | 249003.0 | 2097432.0 | 2375111.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194590.0 | 0.0 | 506.0 | 0.0 | 0.0 | 578306.0 | 1956250.0 | 0.0 | 0.0 | 2031635.0 | 0.0 | 4194536.0 | 0.0 | 2777557942.0 | 0.0 | 16335453242037 | 16343201461266 | 16343201640307 | 16335453774045 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7f018f696180 | 0x7f018c625ac0 | 1466272 | 1365395 | 65536 | 183283 | 183283 | 5865056.0 | 5351679.0 | 0.0 | 0.0 | 0.0 | 155.0 | 0.0 | 1050368.0 | 0.0 | 1050527.0 | 0.0 | 1775.0 | 1048752.0 | 1050526.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097337.0 | 0.0 | 306.0 | 0.0 | 0.0 | 73844.0 | 269280.0 | 0.0 | 0.0 | 983059.0 | 0.0 | 2097286.0 | 0.0 | 794612826.0 | 0.0 | 16335453859103 | 16343201664467 | 16343201772788 | 16335454328372 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7f018f696000 | 0x7f018c625b00 | 2379536 | 2278361 | 65536 | 297441 | 297441 | 9518112.0 | 8838217.0 | 0.0 | 0.0 | 0.0 | 139.0 | 0.0 | 1051040.0 | 0.0 | 1051180.0 | 0.0 | 2441.0 | 1048739.0 | 1051188.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097338.0 | 0.0 | 284.0 | 0.0 | 0.0 | 35998.0 | 148356.0 | 0.0 | 0.0 | 983065.0 | 0.0 | 2097277.0 | 0.0 | 593006806.0 | 0.0 | 16335454414711 | 16343201797428 | 16343201976629 | 16335454942259 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7f018cefde80 | 0x7f018c625b40 | 1352720 | 1255682 | 65536 | 169089 | 169089 | 5410848.0 | 4893593.0 | 0.0 | 0.0 | 0.0 | 180.0 | 0.0 | 1050200.0 | 0.0 | 1050372.0 | 0.0 | 1609.0 | 1048763.0 | 1050375.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097359.0 | 0.0 | 356.0 | 0.0 | 0.0 | 319270.0 | 1020236.0 | 0.0 | 0.0 | 983057.0 | 0.0 | 2097302.0 | 0.0 | 1086930983.0 | 0.0 | 16335455034467 | 16343202009270 | 16343202109590 | 16335455486487 |
| 115 | 113 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 338 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7f018cefdd00 | 0x7f018c625b80 | 2357952 | 2255710 | 65536 | 294743 | 294743 | 9431776.0 | 8895051.0 | 0.0 | 0.0 | 0.0 | 306.0 | 0.0 | 2339628.0 | 0.0 | 2352181.0 | 0.0 | 254736.0 | 2097445.0 | 2337520.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194636.0 | 0.0 | 588.0 | 0.0 | 0.0 | 631818.0 | 2144591.0 | 0.0 | 0.0 | 2031637.0 | 0.0 | 4194568.0 | 0.0 | 2657833881.0 | 0.0 | 16335455571055 | 16343202135831 | 16343202317272 | 16335456105133 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7f018cefdb80 | 0x7f018c625bc0 | 2380368 | 2268567 | 65536 | 297545 | 297545 | 9521440.0 | 8953998.0 | 0.0 | 0.0 | 0.0 | 285.0 | 0.0 | 2353571.0 | 0.0 | 2347603.0 | 0.0 | 250157.0 | 2097446.0 | 2354845.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194617.0 | 0.0 | 552.0 | 0.0 | 0.0 | 839369.0 | 2765571.0 | 0.0 | 0.0 | 2031637.0 | 0.0 | 4194556.0 | 0.0 | 2732959599.0 | 0.0 | 16335456188622 | 16343202340792 | 16343202524473 | 16335456729360 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7f018cefda00 | 0x7f018c625c00 | 1629984 | 1530765 | 65536 | 203747 | 203747 | 6519904.0 | 5986909.0 | 0.0 | 0.0 | 0.0 | 152.0 | 0.0 | 1050592.0 | 0.0 | 1050750.0 | 0.0 | 1997.0 | 1048753.0 | 1050752.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097343.0 | 0.0 | 310.0 | 0.0 | 0.0 | 105866.0 | 346048.0 | 0.0 | 0.0 | 983061.0 | 0.0 | 2097284.0 | 0.0 | 767037810.0 | 0.0 | 16335456812808 | 16343202549113 | 16343202669914 | 16335457285137 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7f018cefd880 | 0x7f018c625c40 | 2697888 | 2597070 | 65536 | 337235 | 337235 | 10791520.0 | 10029324.0 | 0.0 | 0.0 | 0.0 | 141.0 | 0.0 | 1051376.0 | 0.0 | 1051512.0 | 0.0 | 2774.0 | 1048738.0 | 1051520.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097338.0 | 0.0 | 272.0 | 0.0 | 0.0 | 22608.0 | 130169.0 | 0.0 | 0.0 | 983068.0 | 0.0 | 2097280.0 | 0.0 | 611721893.0 | 0.0 | 16335457368876 | 16343202693595 | 16343202897596 | 16335457933833 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7f018cefd700 | 0x7f018c625c80 | 1457904 | 1355383 | 65536 | 182237 | 182237 | 5831584.0 | 5281815.0 | 0.0 | 0.0 | 0.0 | 162.0 | 0.0 | 1050424.0 | 0.0 | 1050582.0 | 0.0 | 1831.0 | 1048751.0 | 1050587.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097349.0 | 0.0 | 328.0 | 0.0 | 0.0 | 114132.0 | 375590.0 | 0.0 | 0.0 | 983059.0 | 0.0 | 2097294.0 | 0.0 | 857503887.0 | 0.0 | 16335458014541 | 16343202942556 | 16343203051197 | 16335458484801 |
| 120 | 118 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 353 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7f018f696580 | 0x7f018c625cc0 | 2352912 | 2246428 | 65536 | 294113 | 294113 | 9411616.0 | 8869216.0 | 0.0 | 0.0 | 0.0 | 299.0 | 0.0 | 2359903.0 | 0.0 | 2338414.0 | 0.0 | 240958.0 | 2097456.0 | 2354968.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194639.0 | 0.0 | 588.0 | 0.0 | 0.0 | 926515.0 | 3103520.0 | 0.0 | 0.0 | 2031639.0 | 0.0 | 4194571.0 | 0.0 | 2712580586.0 | 0.0 | 16335458569779 | 16343203076637 | 16343203259839 | 16335459109377 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7f018f696400 | 0x7f018c625d00 | 2355936 | 2253675 | 65536 | 294491 | 294491 | 9423712.0 | 8871074.0 | 0.0 | 0.0 | 0.0 | 304.0 | 0.0 | 2365952.0 | 0.0 | 2334523.0 | 0.0 | 237070.0 | 2097453.0 | 2349671.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194648.0 | 0.0 | 606.0 | 0.0 | 0.0 | 874156.0 | 2987806.0 | 0.0 | 0.0 | 2031639.0 | 0.0 | 4194567.0 | 0.0 | 2717762020.0 | 0.0 | 16335459194555 | 16343203283999 | 16343203466400 | 16335459735683 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7f018f696280 | 0x7f018c625d40 | 1772232 | 1673094 | 65536 | 221528 | 221528 | 7088896.0 | 6555747.0 | 0.0 | 0.0 | 0.0 | 148.0 | 0.0 | 1050816.0 | 0.0 | 1050970.0 | 0.0 | 2219.0 | 1048751.0 | 1050956.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097335.0 | 0.0 | 286.0 | 0.0 | 0.0 | 67591.0 | 243949.0 | 0.0 | 0.0 | 983063.0 | 0.0 | 2097291.0 | 0.0 | 610741944.0 | 0.0 | 16335459820542 | 16343203491360 | 16343203623841 | 16335460322991 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7f018f696100 | 0x7f018c625d80 | 3011408 | 2913243 | 65536 | 376425 | 376425 | 12045600.0 | 11300099.0 | 0.0 | 0.0 | 0.0 | 143.0 | 0.0 | 1051712.0 | 0.0 | 1051850.0 | 0.0 | 3107.0 | 1048743.0 | 1051850.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097347.0 | 0.0 | 278.0 | 0.0 | 0.0 | 19514.0 | 116548.0 | 0.0 | 0.0 | 983071.0 | 0.0 | 2097294.0 | 0.0 | 602255841.0 | 0.0 | 16335460407639 | 16343203647201 | 16343203877763 | 16335461007135 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7f018cefdf80 | 0x7f018c625dc0 | 1678112 | 1577333 | 65536 | 209763 | 209763 | 6712416.0 | 6163908.0 | 0.0 | 0.0 | 0.0 | 154.0 | 0.0 | 1050704.0 | 0.0 | 1050853.0 | 0.0 | 2108.0 | 1048745.0 | 1050861.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097335.0 | 0.0 | 290.0 | 0.0 | 0.0 | 30573.0 | 141158.0 | 0.0 | 0.0 | 983062.0 | 0.0 | 2097281.0 | 0.0 | 665520323.0 | 0.0 | 16335461089804 | 16343203922723 | 16343204047684 | 16335461563603 |
| 125 | 123 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 368 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7f018cefde00 | 0x7f018c625e00 | 2479696 | 2363758 | 65536 | 309961 | 309961 | 9918752.0 | 9316657.0 | 0.0 | 0.0 | 0.0 | 296.0 | 0.0 | 2286876.0 | 0.0 | 2282647.0 | 0.0 | 185180.0 | 2097467.0 | 2290024.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194635.0 | 0.0 | 562.0 | 0.0 | 0.0 | 503931.0 | 1679154.0 | 0.0 | 0.0 | 2031643.0 | 0.0 | 4194585.0 | 0.0 | 2421278669.0 | 0.0 | 16335461647851 | 16343204071684 | 16343204262406 | 16335462210069 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7f018cefdc80 | 0x7f018c625e40 | 2494800 | 2348422 | 65536 | 311849 | 311849 | 9979168.0 | 9325174.0 | 0.0 | 0.0 | 0.0 | 287.0 | 0.0 | 2258503.0 | 0.0 | 2276572.0 | 0.0 | 179116.0 | 2097456.0 | 2263130.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194625.0 | 0.0 | 544.0 | 0.0 | 0.0 | 681581.0 | 2244763.0 | 0.0 | 0.0 | 2031643.0 | 0.0 | 4194579.0 | 0.0 | 2435752980.0 | 0.0 | 16335462282687 | 16343204286726 | 16343204478247 | 16335462855045 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7f018cefdb00 | 0x7f018c625e80 | 2103552 | 2002944 | 65536 | 262943 | 262943 | 8414176.0 | 7772103.0 | 0.0 | 0.0 | 0.0 | 155.0 | 0.0 | 1051264.0 | 0.0 | 1051422.0 | 0.0 | 2663.0 | 1048759.0 | 1051399.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097357.0 | 0.0 | 314.0 | 0.0 | 0.0 | 14230.0 | 96299.0 | 0.0 | 0.0 | 983067.0 | 0.0 | 2097285.0 | 0.0 | 604310455.0 | 0.0 | 16335462928553 | 16343204501447 | 16343204659208 | 16335463434342 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7f018cefd980 | 0x7f018c625ec0 | 3671728 | 3563381 | 65536 | 458965 | 458965 | 14686880.0 | 13726578.0 | 0.0 | 0.0 | 0.0 | 139.0 | 0.0 | 1052328.0 | 0.0 | 1052468.0 | 0.0 | 3718.0 | 1048750.0 | 1052466.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097359.0 | 0.0 | 280.0 | 0.0 | 0.0 | 19078.0 | 103225.0 | 0.0 | 0.0 | 983076.0 | 0.0 | 2097299.0 | 0.0 | 584868095.0 | 0.0 | 16335463517950 | 16343204683369 | 16343204964971 | 16335464161496 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7f018cefd800 | 0x7f018c625f00 | 1930336 | 1834372 | 65536 | 241291 | 241291 | 7721312.0 | 7083682.0 | 0.0 | 0.0 | 0.0 | 147.0 | 0.0 | 1051096.0 | 0.0 | 1051241.0 | 0.0 | 2497.0 | 1048744.0 | 1051250.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097352.0 | 0.0 | 310.0 | 0.0 | 0.0 | 61221.0 | 229019.0 | 0.0 | 0.0 | 983065.0 | 0.0 | 2097290.0 | 0.0 | 625191932.0 | 0.0 | 16335464243774 | 16343205008811 | 16343205155052 | 16335464744453 |
| 130 | 128 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 383 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7f018cefd680 | 0x7f018c625f40 | 2675688 | 2562469 | 65536 | 334460 | 334460 | 10702720.0 | 10064280.0 | 0.0 | 0.0 | 0.0 | 272.0 | 0.0 | 2253881.0 | 0.0 | 2250095.0 | 0.0 | 152650.0 | 2097445.0 | 2254422.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194632.0 | 0.0 | 542.0 | 0.0 | 0.0 | 402845.0 | 1360057.0 | 0.0 | 0.0 | 2031647.0 | 0.0 | 4194585.0 | 0.0 | 2254708891.0 | 0.0 | 16335464828191 | 16343205180812 | 16343205390414 | 16335465402578 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7f018f696500 | 0x7f018c625f80 | 2647784 | 2523947 | 65536 | 330972 | 330972 | 10591104.0 | 9964686.0 | 0.0 | 0.0 | 0.0 | 268.0 | 0.0 | 2206580.0 | 0.0 | 2228388.0 | 0.0 | 130944.0 | 2097444.0 | 2228194.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194619.0 | 0.0 | 516.0 | 0.0 | 0.0 | 403695.0 | 1331922.0 | 0.0 | 0.0 | 2031647.0 | 0.0 | 4194574.0 | 0.0 | 2085977074.0 | 0.0 | 16335465477157 | 16343205427534 | 16343205638735 | 16335466051664 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7f018f696380 | 0x7f018c625fc0 | 2427504 | 2325567 | 65536 | 303437 | 303437 | 9709984.0 | 9025450.0 | 0.0 | 0.0 | 0.0 | 151.0 | 0.0 | 1051712.0 | 0.0 | 1051876.0 | 0.0 | 3107.0 | 1048769.0 | 1051870.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097364.0 | 0.0 | 312.0 | 0.0 | 0.0 | 18271.0 | 102787.0 | 0.0 | 0.0 | 983071.0 | 0.0 | 2097298.0 | 0.0 | 597126308.0 | 0.0 | 16335466127382 | 16343205674576 | 16343205858257 | 16335466666860 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7f018f696200 | 0x7f018c626000 | 4310408 | 4208048 | 65536 | 538800 | 538800 | 17241600.0 | 16047169.0 | 0.0 | 0.0 | 0.0 | 132.0 | 0.0 | 1053000.0 | 0.0 | 1053141.0 | 0.0 | 4384.0 | 1048757.0 | 1053137.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097366.0 | 0.0 | 270.0 | 0.0 | 0.0 | 10840.0 | 85214.0 | 0.0 | 0.0 | 983082.0 | 0.0 | 2097311.0 | 0.0 | 595344737.0 | 0.0 | 16335466751508 | 16343205883377 | 16343206216499 | 16335467445233 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7f018f696080 | 0x7f018c626040 | 2143184 | 2043013 | 65536 | 267897 | 267897 | 8572704.0 | 8005168.0 | 0.0 | 0.0 | 0.0 | 149.0 | 0.0 | 1051432.0 | 0.0 | 1051578.0 | 0.0 | 2830.0 | 1048748.0 | 1051587.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097344.0 | 0.0 | 282.0 | 0.0 | 0.0 | 21221.0 | 123948.0 | 0.0 | 0.0 | 983068.0 | 0.0 | 2097294.0 | 0.0 | 592333582.0 | 0.0 | 16335467527651 | 16343206288980 | 16343206453141 | 16335468031790 |
| 135 | 133 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 398 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7f018cefdf00 | 0x7f018c626080 | 2928712 | 2811656 | 65536 | 366088 | 366088 | 11714816.0 | 11036253.0 | 0.0 | 0.0 | 0.0 | 268.0 | 0.0 | 2207062.0 | 0.0 | 2203090.0 | 0.0 | 105652.0 | 2097438.0 | 2210462.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194615.0 | 0.0 | 490.0 | 0.0 | 0.0 | 197254.0 | 644760.0 | 0.0 | 0.0 | 2031651.0 | 0.0 | 4194568.0 | 0.0 | 1999411729.0 | 0.0 | 16335468116158 | 16343206478581 | 16343206709143 | 16335468708615 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7f018cefdd80 | 0x7f018c6260c0 | 2933416 | 2822777 | 65536 | 366676 | 366676 | 11733632.0 | 11102535.0 | 0.0 | 0.0 | 0.0 | 234.0 | 0.0 | 2180935.0 | 0.0 | 2168781.0 | 0.0 | 71370.0 | 2097411.0 | 2185028.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194601.0 | 0.0 | 464.0 | 0.0 | 0.0 | 346357.0 | 1110499.0 | 0.0 | 0.0 | 2031651.0 | 0.0 | 4194543.0 | 0.0 | 1579289907.0 | 0.0 | 16335468783724 | 16343206768503 | 16343206996985 | 16335469384550 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7f018cefdc00 | 0x7f018c626100 | 2753232 | 2653780 | 65536 | 344153 | 344153 | 11012896.0 | 10233468.0 | 0.0 | 0.0 | 0.0 | 166.0 | 0.0 | 1052160.0 | 0.0 | 1052316.0 | 0.0 | 3551.0 | 1048765.0 | 1052322.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097371.0 | 0.0 | 310.0 | 0.0 | 0.0 | 24187.0 | 124944.0 | 0.0 | 0.0 | 983075.0 | 0.0 | 2097291.0 | 0.0 | 571918389.0 | 0.0 | 16335469458849 | 16343207057465 | 16343207267387 | 16335470031186 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7f018cefda80 | 0x7f018c626140 | 4950128 | 4847069 | 65536 | 618765 | 618765 | 19800480.0 | 18636877.0 | 0.0 | 0.0 | 0.0 | 135.0 | 0.0 | 1053672.0 | 0.0 | 1053812.0 | 0.0 | 5050.0 | 1048762.0 | 1053802.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097380.0 | 0.0 | 274.0 | 0.0 | 0.0 | 45388.0 | 176927.0 | 0.0 | 0.0 | 983088.0 | 0.0 | 2097318.0 | 0.0 | 583829686.0 | 0.0 | 16335470105405 | 16343207326587 | 16343207709310 | 16335470857458 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7f018cefd900 | 0x7f018c626180 | 2400216 | 2302211 | 65536 | 300026 | 300026 | 9600832.0 | 8951115.0 | 0.0 | 0.0 | 0.0 | 146.0 | 0.0 | 1051768.0 | 0.0 | 1051911.0 | 0.0 | 3163.0 | 1048748.0 | 1051904.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097352.0 | 0.0 | 286.0 | 0.0 | 0.0 | 29332.0 | 146596.0 | 0.0 | 0.0 | 983071.0 | 0.0 | 2097301.0 | 0.0 | 598496753.0 | 0.0 | 16335470938826 | 16343207773950 | 16343207958592 | 16335471469184 |
| 140 | 138 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 413 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7f018cefd780 | 0x7f018c6261c0 | 3205216 | 3088413 | 65536 | 400651 | 400651 | 12820832.0 | 12044811.0 | 0.0 | 0.0 | 0.0 | 238.0 | 0.0 | 2184323.0 | 0.0 | 2181713.0 | 0.0 | 84297.0 | 2097416.0 | 2192961.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194609.0 | 0.0 | 464.0 | 0.0 | 0.0 | 244062.0 | 806146.0 | 0.0 | 0.0 | 2031655.0 | 0.0 | 4194562.0 | 0.0 | 1714570046.0 | 0.0 | 16335471554062 | 16343207983072 | 16343208235714 | 16335472190768 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7f018cefd600 | 0x7f018c626200 | 3107616 | 3004400 | 65536 | 388451 | 388451 | 12430432.0 | 11834374.0 | 0.0 | 0.0 | 0.0 | 237.0 | 0.0 | 2116842.0 | 0.0 | 2114195.0 | 0.0 | 16790.0 | 2097405.0 | 2114907.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194600.0 | 0.0 | 446.0 | 0.0 | 0.0 | 26130.0 | 130433.0 | 0.0 | 0.0 | 2031655.0 | 0.0 | 4194542.0 | 0.0 | 1268335523.0 | 0.0 | 16335472243047 | 16343208294754 | 16343208540836 | 16335472852174 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7f018f696480 | 0x7f018c626240 | 3075920 | 2975489 | 65536 | 384489 | 384489 | 12303648.0 | 11473901.0 | 0.0 | 0.0 | 0.0 | 169.0 | 0.0 | 1052552.0 | 0.0 | 1052712.0 | 0.0 | 3940.0 | 1048772.0 | 1052708.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097378.0 | 0.0 | 310.0 | 0.0 | 0.0 | 22525.0 | 123606.0 | 0.0 | 0.0 | 983078.0 | 0.0 | 2097316.0 | 0.0 | 681809532.0 | 0.0 | 16335472925532 | 16343208603556 | 16343208839078 | 16335473542618 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7f018f696300 | 0x7f018c626280 | 5708640 | 5598886 | 65536 | 713579 | 713579 | 22834528.0 | 20998694.0 | 0.0 | 0.0 | 0.0 | 133.0 | 0.0 | 1050536.0 | 0.0 | 1050669.0 | 0.0 | 1942.0 | 1048727.0 | 1050666.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097316.0 | 0.0 | 258.0 | 0.0 | 0.0 | 0.0 | 56957.0 | 0.0 | 0.0 | 983060.0 | 0.0 | 2097263.0 | 0.0 | 540998528.0 | 0.0 | 16335473617287 | 16343208877798 | 16343209327401 | 16335474457118 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7f018f696180 | 0x7f018c6262c0 | 2883200 | 2780059 | 65536 | 360399 | 360399 | 11532768.0 | 10849050.0 | 0.0 | 0.0 | 0.0 | 138.0 | 0.0 | 1052440.0 | 0.0 | 1052581.0 | 0.0 | 3829.0 | 1048752.0 | 1052581.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097365.0 | 0.0 | 288.0 | 0.0 | 0.0 | 33005.0 | 148726.0 | 0.0 | 0.0 | 983077.0 | 0.0 | 2097312.0 | 0.0 | 583580990.0 | 0.0 | 16335474518217 | 16343209371402 | 16343209594603 | 16335475096194 |
| 145 | 143 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 428 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7f018f696000 | 0x7f018c626300 | 3748528 | 3648219 | 65536 | 468565 | 468565 | 14994080.0 | 14284334.0 | 0.0 | 0.0 | 0.0 | 253.0 | 0.0 | 2114071.0 | 0.0 | 2114149.0 | 0.0 | 16715.0 | 2097434.0 | 2114292.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194620.0 | 0.0 | 454.0 | 0.0 | 0.0 | 19616.0 | 112160.0 | 0.0 | 0.0 | 2031663.0 | 0.0 | 4194581.0 | 0.0 | 1191833321.0 | 0.0 | 16335475171162 | 16343209628204 | 16343209926606 | 16335475841328 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7f018cefde80 | 0x7f018c626340 | 3772328 | 3671212 | 65536 | 471540 | 471540 | 15089280.0 | 14320594.0 | 0.0 | 0.0 | 0.0 | 217.0 | 0.0 | 2135063.0 | 0.0 | 2143669.0 | 0.0 | 46257.0 | 2097412.0 | 2141955.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194608.0 | 0.0 | 430.0 | 0.0 | 0.0 | 55134.0 | 221617.0 | 0.0 | 0.0 | 2031663.0 | 0.0 | 4194558.0 | 0.0 | 1405720458.0 | 0.0 | 16335475915526 | 16343209961966 | 16343210258928 | 16335476574082 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7f018cefdd00 | 0x7f018c626380 | 3825248 | 3721452 | 65536 | 478155 | 478155 | 15300960.0 | 14569687.0 | 0.0 | 0.0 | 0.0 | 144.0 | 0.0 | 1050312.0 | 0.0 | 1050459.0 | 0.0 | 1720.0 | 1048739.0 | 1050461.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097327.0 | 0.0 | 288.0 | 0.0 | 0.0 | 0.0 | 59062.0 | 0.0 | 0.0 | 983058.0 | 0.0 | 2097274.0 | 0.0 | 546229919.0 | 0.0 | 16335476648300 | 16343210322288 | 16343210616050 | 16335477303476 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7f018cefdb80 | 0x7f018c6263c0 | 6992576 | 6892345 | 65536 | 874071 | 874071 | 27970272.0 | 23743395.0 | 0.0 | 0.0 | 0.0 | 132.0 | 0.0 | 1050872.0 | 0.0 | 1051004.0 | 0.0 | 2275.0 | 1048729.0 | 1051008.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097321.0 | 0.0 | 256.0 | 0.0 | 0.0 | 0.0 | 56819.0 | 0.0 | 0.0 | 983063.0 | 0.0 | 2097276.0 | 0.0 | 544584404.0 | 0.0 | 16335477381074 | 16343210680051 | 16343211233495 | 16335478298334 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7f018cefda00 | 0x7f018c626400 | 3386144 | 3282526 | 65536 | 423267 | 423267 | 13544544.0 | 12755696.0 | 0.0 | 0.0 | 0.0 | 167.0 | 0.0 | 1053000.0 | 0.0 | 1053162.0 | 0.0 | 4384.0 | 1048778.0 | 1053151.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097376.0 | 0.0 | 290.0 | 0.0 | 0.0 | 28740.0 | 135799.0 | 0.0 | 0.0 | 983082.0 | 0.0 | 2097315.0 | 0.0 | 574018067.0 | 0.0 | 16335478386152 | 16343211301335 | 16343211563097 | 16335479015688 |
| 150 | 148 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 443 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7f018cefd880 | 0x7f018c626440 | 4408936 | 4309367 | 65536 | 551116 | 551116 | 17635712.0 | 16754694.0 | 0.0 | 0.0 | 0.0 | 209.0 | 0.0 | 2133768.0 | 0.0 | 2128831.0 | 0.0 | 31417.0 | 2097414.0 | 2127435.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194616.0 | 0.0 | 412.0 | 0.0 | 0.0 | 60910.0 | 238301.0 | 0.0 | 0.0 | 2031671.0 | 0.0 | 4194557.0 | 0.0 | 1267091388.0 | 0.0 | 16335479090036 | 16343211623258 | 16343211973980 | 16335479807430 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7f018cefd700 | 0x7f018c626480 | 4413696 | 4310495 | 65536 | 551711 | 551711 | 17654752.0 | 16853907.0 | 0.0 | 0.0 | 0.0 | 217.0 | 0.0 | 2126153.0 | 0.0 | 2132145.0 | 0.0 | 34726.0 | 2097419.0 | 2123436.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194622.0 | 0.0 | 426.0 | 0.0 | 0.0 | 19171.0 | 108471.0 | 0.0 | 0.0 | 2031671.0 | 0.0 | 4194562.0 | 0.0 | 1214145549.0 | 0.0 | 16335479879229 | 16343212034781 | 16343212385023 | 16335480591313 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7f018f696580 | 0x7f018c6264c0 | 4472384 | 4364036 | 65536 | 559047 | 559047 | 17889504.0 | 16894584.0 | 0.0 | 0.0 | 0.0 | 149.0 | 0.0 | 1050984.0 | 0.0 | 1051131.0 | 0.0 | 2386.0 | 1048745.0 | 1051126.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097337.0 | 0.0 | 284.0 | 0.0 | 0.0 | 0.0 | 46232.0 | 0.0 | 0.0 | 983064.0 | 0.0 | 2097280.0 | 0.0 | 547134066.0 | 0.0 | 16335480665872 | 16343212445663 | 16343212790466 | 16335481374546 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7f018f696400 | 0x7f018c626500 | 8292552 | 8187808 | 65536 | 1036568 | 1036568 | 33170176.0 | 27704762.0 | 0.0 | 0.0 | 0.0 | 135.0 | 0.0 | 1051208.0 | 0.0 | 1051343.0 | 0.0 | 2608.0 | 1048735.0 | 1051342.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097329.0 | 0.0 | 260.0 | 0.0 | 0.0 | 0.0 | 56332.0 | 0.0 | 0.0 | 983066.0 | 0.0 | 2097276.0 | 0.0 | 551120229.0 | 0.0 | 16335481449084 | 16343212853026 | 16343213509831 | 16335482473492 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7f018f696280 | 0x7f018c626540 | 5723208 | 5624137 | 65536 | 715400 | 715400 | 22892800.0 | 20352242.0 | 0.0 | 0.0 | 0.0 | 141.0 | 0.0 | 1050984.0 | 0.0 | 1051120.0 | 0.0 | 2386.0 | 1048734.0 | 1051121.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097331.0 | 0.0 | 272.0 | 0.0 | 0.0 | 0.0 | 57546.0 | 0.0 | 0.0 | 983064.0 | 0.0 | 2097275.0 | 0.0 | 551637959.0 | 0.0 | 16335482551970 | 16343213575911 | 16343214019115 | 16335483379022 |
| 155 | 153 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 458 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7f018f696100 | 0x7f018c626580 | 5739296 | 5637460 | 65536 | 717411 | 717411 | 22957152.0 | 22331469.0 | 0.0 | 0.0 | 0.0 | 218.0 | 0.0 | 2099728.0 | 0.0 | 2099883.0 | 0.0 | 2497.0 | 2097386.0 | 2099841.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194561.0 | 0.0 | 426.0 | 0.0 | 0.0 | 101.0 | 58514.0 | 0.0 | 0.0 | 2031640.0 | 0.0 | 4194508.0 | 0.0 | 1072898615.0 | 0.0 | 16335483428581 | 16343214052715 | 16343214513358 | 16335484275882 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7f018cefdf80 | 0x7f018c6265c0 | 5741520 | 5630313 | 65536 | 717689 | 717689 | 22966048.0 | 22327511.0 | 0.0 | 0.0 | 0.0 | 201.0 | 0.0 | 2099813.0 | 0.0 | 2099901.0 | 0.0 | 2514.0 | 2097387.0 | 2099855.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194546.0 | 0.0 | 398.0 | 0.0 | 0.0 | 0.0 | 53618.0 | 0.0 | 0.0 | 2031640.0 | 0.0 | 4194501.0 | 0.0 | 1078955744.0 | 0.0 | 16335484324741 | 16343214575438 | 16343215032882 | 16335485174342 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7f018cefde00 | 0x7f018c626600 | 5758880 | 5656846 | 65536 | 719859 | 719859 | 23035488.0 | 20298031.0 | 0.0 | 0.0 | 0.0 | 138.0 | 0.0 | 1051040.0 | 0.0 | 1051177.0 | 0.0 | 2442.0 | 1048735.0 | 1051181.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097331.0 | 0.0 | 270.0 | 0.0 | 0.0 | 0.0 | 55121.0 | 0.0 | 0.0 | 983064.0 | 0.0 | 2097277.0 | 0.0 | 551271977.0 | 0.0 | 16335485225131 | 16343215093842 | 16343215542645 | 16335486039483 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7f018cefdc80 | 0x7f018c626640 | 10893832 | 10782915 | 65536 | 1361728 | 1361728 | 43575296.0 | 34954056.0 | 0.0 | 0.0 | 0.0 | 131.0 | 0.0 | 1050536.0 | 0.0 | 1050667.0 | 0.0 | 1942.0 | 1048725.0 | 1050666.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097317.0 | 0.0 | 260.0 | 0.0 | 0.0 | 0.0 | 57346.0 | 0.0 | 0.0 | 983060.0 | 0.0 | 2097262.0 | 0.0 | 552426509.0 | 0.0 | 16335486113851 | 16343215601366 | 16343216465852 | 16335487386553 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7f018cefdb00 | 0x7f018c626680 | 10925936 | 10818975 | 65536 | 1365741 | 1365741 | 43703712.0 | 31612301.0 | 0.0 | 0.0 | 0.0 | 129.0 | 0.0 | 1050984.0 | 0.0 | 1051114.0 | 0.0 | 2386.0 | 1048728.0 | 1051113.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097327.0 | 0.0 | 264.0 | 0.0 | 0.0 | 0.0 | 57353.0 | 0.0 | 0.0 | 983064.0 | 0.0 | 2097270.0 | 0.0 | 564768947.0 | 0.0 | 16335487442492 | 16343216532892 | 16343217382498 | 16335488673745 |
| 160 | 158 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 473 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7f018cefd980 | 0x7f018c6266c0 | 10938952 | 10829774 | 65536 | 1367368 | 1367368 | 43755776.0 | 41944228.0 | 0.0 | 0.0 | 0.0 | 203.0 | 0.0 | 2099616.0 | 0.0 | 2099884.0 | 0.0 | 2509.0 | 2097375.0 | 2099826.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194549.0 | 0.0 | 402.0 | 0.0 | 0.0 | 0.0 | 54672.0 | 0.0 | 0.0 | 2031640.0 | 0.0 | 4194490.0 | 0.0 | 1068994226.0 | 0.0 | 16335488724564 | 16343217442019 | 16343218322825 | 16335489968656 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7f018cefd800 | 0x7f018c626700 | 10919936 | 10813901 | 65536 | 1364991 | 1364991 | 43679712.0 | 41539879.0 | 0.0 | 0.0 | 0.0 | 202.0 | 0.0 | 2099563.0 | 0.0 | 2099882.0 | 0.0 | 2512.0 | 2097370.0 | 2099797.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194549.0 | 0.0 | 404.0 | 0.0 | 0.0 | 0.0 | 56479.0 | 0.0 | 0.0 | 2031640.0 | 0.0 | 4194499.0 | 0.0 | 1076339238.0 | 0.0 | 16335490042885 | 16343218411146 | 16343219287152 | 16335491330706 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7f018cefd680 | 0x7f018c626740 | 10959224 | 10853241 | 65536 | 1369902 | 1369902 | 43836864.0 | 33246890.0 | 0.0 | 0.0 | 0.0 | 136.0 | 0.0 | 1051040.0 | 0.0 | 1051173.0 | 0.0 | 2442.0 | 1048731.0 | 1051171.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097325.0 | 0.0 | 258.0 | 0.0 | 0.0 | 0.0 | 55706.0 | 0.0 | 0.0 | 983064.0 | 0.0 | 2097273.0 | 0.0 | 560286189.0 | 0.0 | 16335491376025 | 16343219360272 | 16343220215638 | 16335492705066 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7f018f696500 | 0x7f018c626780 | 21252672 | 21153651 | 65536 | 2656583 | 2656583 | 85010656.0 | 43019490.0 | 0.0 | 0.0 | 0.0 | 132.0 | 0.0 | 1050536.0 | 0.0 | 1050667.0 | 0.0 | 1942.0 | 1048725.0 | 1050666.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097313.0 | 0.0 | 252.0 | 0.0 | 0.0 | 0.0 | 57196.0 | 0.0 | 0.0 | 983060.0 | 0.0 | 2097260.0 | 0.0 | 573803565.0 | 0.0 | 16335492748745 | 16343220280919 | 16343221975971 | 16335494870818 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7f018f696380 | 0x7f018c6267c0 | 21312928 | 21199322 | 65536 | 2664115 | 2664115 | 85251680.0 | 50086710.0 | 0.0 | 0.0 | 0.0 | 136.0 | 0.0 | 1050984.0 | 0.0 | 1051119.0 | 0.0 | 2386.0 | 1048733.0 | 1051121.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097327.0 | 0.0 | 264.0 | 0.0 | 0.0 | 0.0 | 57829.0 | 0.0 | 0.0 | 983064.0 | 0.0 | 2097277.0 | 0.0 | 579973622.0 | 0.0 | 16335494924027 | 16343222068931 | 16343223730543 | 16335497015231 |
| 165 | 163 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 488 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7f018f696200 | 0x7f018c626800 | 21316920 | 21208144 | 65536 | 2664614 | 2664614 | 85267648.0 | 74237825.0 | 0.0 | 0.0 | 0.0 | 211.0 | 0.0 | 2099666.0 | 0.0 | 2099866.0 | 0.0 | 2484.0 | 2097382.0 | 2099875.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194549.0 | 0.0 | 402.0 | 0.0 | 0.0 | 137.0 | 50844.0 | 0.0 | 0.0 | 2031640.0 | 0.0 | 4194497.0 | 0.0 | 1086295391.0 | 0.0 | 16335497061120 | 16343223851024 | 16343225571516 | 16335499218852 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7f018f696080 | 0x7f018c626840 | 21310408 | 21195639 | 65536 | 2663800 | 2663800 | 85241600.0 | 76556583.0 | 0.0 | 0.0 | 0.0 | 218.0 | 0.0 | 2099560.0 | 0.0 | 2099921.0 | 0.0 | 2539.0 | 2097382.0 | 2099778.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194551.0 | 0.0 | 408.0 | 0.0 | 0.0 | 0.0 | 52865.0 | 0.0 | 0.0 | 2031640.0 | 0.0 | 4194505.0 | 0.0 | 1090860108.0 | 0.0 | 16335499264821 | 16343225659837 | 16343227371369 | 16335501413974 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7f018cefdf00 | 0x7f018c626880 | 21337448 | 21228961 | 65536 | 2667180 | 2667180 | 85349760.0 | 47910185.0 | 0.0 | 0.0 | 0.0 | 136.0 | 0.0 | 1051040.0 | 0.0 | 1051178.0 | 0.0 | 2442.0 | 1048736.0 | 1051174.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097327.0 | 0.0 | 262.0 | 0.0 | 0.0 | 0.0 | 56766.0 | 0.0 | 0.0 | 983064.0 | 0.0 | 2097274.0 | 0.0 | 579819417.0 | 0.0 | 16335501458583 | 16343227473770 | 16343229142901 | 16335503561746 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 155691 | 155691 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7f018cefdd80 | 0x7f018c6268c0 | 42011104 | 41898674 | 65536 | 5251387 | 5251387 | 168044384.0 | 67346023.0 | 0.0 | 0.0 | 0.0 | 133.0 | 0.0 | 1050536.0 | 0.0 | 1050667.0 | 0.0 | 1942.0 | 1048725.0 | 1050668.0 | 0.0 | 0.0 | 31.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097314.0 | 0.0 | 254.0 | 0.0 | 0.0 | 0.0 | 57065.0 | 0.0 | 0.0 | 983060.0 | 0.0 | 2097263.0 | 0.0 | 586053045.0 | 0.0 | 16335503606755 | 16343229227702 | 16343232581966 | 16335507392682 |