Created
October 19, 2023 05:48
-
-
Save geohot/471f465159ee08ab774deb583584ff52 to your computer and use it in GitHub Desktop.
kernels for BS=1024 CIFAR BEAM=2 WINO=1
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| *** 0 E_64_32_6_6n5 arg 2 sz [64, 1, 1] [32, 1, 1] OPs 33M/ 0.00G mem 3.07 GB tm 3.20us/ 0.00ms (10483.20 GFLOPS, 297.02 GB/s) | |
| *** 1 r_128_31_31_3_2_3_2_2_2_8n26 arg 3 sz [31, 31, 128] [2, 3, 1] OPs 283M/ 0.03G mem 3.07 GB tm 218.44us/ 0.22ms ( 1297.42 GFLOPS, 216.24 GB/s) | |
| *** 2 r_1024_32_16_2_3_4_4_8n6 arg 3 sz [32, 1024, 1] [2, 16, 1] OPs 805M/ 0.32G mem 3.07 GB tm 64.68us/ 0.29ms (12450.43 GFLOPS, 1426.62 GB/s) | |
| *** 3 E_262144_32_4n6 arg 2 sz [262144, 1, 1] [32, 1, 1] OPs 503M/ 1.12G mem 3.07 GB tm 93.80us/ 0.38ms ( 5365.85 GFLOPS, 1430.89 GB/s) | |
| *** 4 E_16384_2_8_8_6_6n2 arg 2 sz [16384, 1, 1] [8, 8, 2] OPs 68174M/ 1.63G mem 3.07 GB tm 363.04us/ 0.74ms (187785.52 GFLOPS, 6007.66 GB/s) | |
| *** 5 r_36_1024_4_16_4_32_4_4n10 arg 3 sz [4, 1024, 36] [4, 16, 1] OPs 9663M/ 69.80G mem 3.07 GB tm 586.09us/ 1.33ms (16488.50 GFLOPS, 773.15 GB/s) | |
| *** 6 E_16384_4_32_4_4_2n6 arg 2 sz [4, 16384, 1] [32, 1, 1] OPs 33487M/ 79.46G mem 3.07 GB tm 623.77us/ 1.95ms (53685.71 GFLOPS, 4572.43 GB/s) | |
| *** 7 r_131072_8_16_2_2n6 arg 2 sz [131072, 1, 1] [16, 8, 1] OPs 67M/ 112.95G mem 3.07 GB tm 208.00us/ 2.16ms ( 322.64 GFLOPS, 806.59 GB/s) | |
| *** 8 E_1024_16_2_2_4_4_4_4n12 arg 2 sz [1024, 1, 1] [2, 2, 16] OPs 0M/ 113.02G mem 3.07 GB tm 56.96us/ 2.22ms ( 0.00 GFLOPS, 1767.23 GB/s) | |
| *** 9 r_32768_32_16n6 arg 2 sz [32768, 1, 1] [32, 1, 1] OPs 16M/ 113.02G mem 3.07 GB tm 31.76us/ 2.25ms ( 528.25 GFLOPS, 2245.06 GB/s) | |
| *** 10 r_64_16_8_8_16n6 arg 2 sz [64, 1, 1] [8, 16, 1] OPs 1M/ 113.03G mem 3.07 GB tm 4.60us/ 2.25ms ( 227.97 GFLOPS, 911.86 GB/s) | |
| *** 11 r_256_8_2_4_2_4_4_16_2n6 arg 3 sz [8, 256, 1] [32, 4, 2] OPs 50M/ 113.04G mem 3.07 GB tm 26.60us/ 2.28ms ( 1892.17 GFLOPS, 2680.58 GB/s) | |
| *** 12 r_64_4_16_4_16_4n14 arg 2 sz [64, 1, 1] [16, 4, 1] OPs 1M/ 113.09G mem 3.07 GB tm 4.68us/ 2.29ms ( 224.11 GFLOPS, 896.28 GB/s) | |
| *** 13 E_256_16_2_6_6_2n12 arg 2 sz [256, 1, 1] [2, 16, 1] OPs 268M/ 113.09G mem 3.07 GB tm 4.64us/ 2.29ms (57838.34 GFLOPS, 1638.44 GB/s) | |
| *** 14 E_128_32_6_6n4 arg 2 sz [128, 1, 1] [32, 1, 1] OPs 67M/ 113.36G mem 3.07 GB tm 3.36us/ 2.29ms (19968.00 GFLOPS, 565.70 GB/s) | |
| *** 15 E_1024_32_16_2_8_2n31 arg 5 sz [32, 1024, 1] [2, 16, 1] OPs 318M/ 113.42G mem 3.07 GB tm 53.16us/ 2.35ms ( 5996.26 GFLOPS, 1262.38 GB/s) | |
| *** 16 E_65536_4_4_6_6n30 arg 2 sz [65536, 1, 1] [4, 4, 1] OPs 34087M/ 113.74G mem 3.07 GB tm 90.60us/ 2.44ms (376233.25 GFLOPS, 12036.50 GB/s) | |
| *** 17 r_36_1024_2_16_2_64_4_2_2n18 arg 3 sz [2, 1024, 36] [2, 16, 1] OPs 4831M/ 147.83G mem 3.07 GB tm 218.00us/ 2.66ms (22164.19 GFLOPS, 693.98 GB/s) | |
| *** 18 E_8192_32_4_4_4n14 arg 2 sz [8192, 1, 1] [4, 32, 1] OPs 8371M/ 152.66G mem 3.07 GB tm 94.08us/ 2.75ms (88985.35 GFLOPS, 7578.91 GB/s) | |
| *** 19 E_1024_16_2_2_4_4_4_4n12 arg 2 sz [1024, 1, 1] [2, 2, 16] OPs 0M/ 161.03G mem 3.07 GB tm 44.24us/ 2.79ms ( 0.00 GFLOPS, 2275.39 GB/s) | |
| *** 20 r_32768_32_16n6 arg 2 sz [32768, 1, 1] [32, 1, 1] OPs 16M/ 161.03G mem 3.07 GB tm 33.56us/ 2.83ms ( 499.92 GFLOPS, 2124.65 GB/s) | |
| *** 21 r_64_16_8_8_16n6 arg 2 sz [64, 1, 1] [8, 16, 1] OPs 1M/ 161.05G mem 3.07 GB tm 4.72us/ 2.83ms ( 222.17 GFLOPS, 888.68 GB/s) | |
| *** 22 r_256_8_2_4_2_4_4_16_2n6 arg 3 sz [8, 256, 1] [32, 4, 2] OPs 50M/ 161.05G mem 3.07 GB tm 27.68us/ 2.86ms ( 1818.27 GFLOPS, 2575.90 GB/s) | |
| *** 23 r_64_4_16_4_16_4n14 arg 2 sz [64, 1, 1] [16, 4, 1] OPs 1M/ 161.10G mem 3.07 GB tm 4.88us/ 2.86ms ( 214.92 GFLOPS, 859.54 GB/s) | |
| *** 24 E_1024_8_4_8_16_4n9 arg 6 sz [4, 8, 1024] [16, 8, 1] OPs 335M/ 161.10G mem 3.07 GB tm 141.52us/ 3.01ms ( 2370.97 GFLOPS, 711.30 GB/s) | |
| *** 25 E_65536_4_4_6_6n30 arg 2 sz [65536, 1, 1] [4, 4, 1] OPs 34087M/ 161.44G mem 3.07 GB tm 104.84us/ 3.11ms (325131.47 GFLOPS, 10401.65 GB/s) | |
| *** 26 r_36_512_4_2_16_4_16_4_4_4n2 arg 3 sz [4, 512, 36] [4, 16, 2] OPs 19327M/ 195.52G mem 3.07 GB tm 917.17us/ 4.03ms (21072.84 GFLOPS, 412.87 GB/s) | |
| *** 27 E_32768_4_32_4_4n18 arg 2 sz [4, 32768, 1] [32, 1, 1] OPs 33487M/ 214.85G mem 3.07 GB tm 554.85us/ 4.58ms (60354.37 GFLOPS, 5140.40 GB/s) | |
| *** 28 r_131072_16_8_2_2n18 arg 2 sz [131072, 1, 1] [8, 16, 1] OPs 67M/ 248.34G mem 3.07 GB tm 204.84us/ 4.79ms ( 327.61 GFLOPS, 819.03 GB/s) | |
| *** 29 E_131072_2_16_2_8n10 arg 3 sz [2, 131072, 1] [2, 16, 1] OPs 134M/ 248.41G mem 3.07 GB tm 332.16us/ 5.12ms ( 404.07 GFLOPS, 909.16 GB/s) | |
| *** 30 r_524288_32_4n8 arg 2 sz [524288, 1, 1] [32, 1, 1] OPs 67M/ 248.54G mem 3.07 GB tm 224.08us/ 5.34ms ( 299.48 GFLOPS, 748.71 GB/s) | |
| *** 31 E_131072_32_4n12 arg 2 sz [131072, 1, 1] [32, 1, 1] OPs 0M/ 248.61G mem 3.07 GB tm 75.20us/ 5.42ms ( 0.00 GFLOPS, 1338.59 GB/s) | |
| *** 32 r_256_16_64_64n6 arg 2 sz [256, 1, 1] [16, 1, 1] OPs 16M/ 248.61G mem 3.07 GB tm 26.20us/ 5.45ms ( 640.34 GFLOPS, 2561.35 GB/s) | |
| *** 33 r_256_4_4_64_16_4n6 arg 3 sz [256, 1, 1] [4, 4, 1] OPs 50M/ 248.62G mem 3.07 GB tm 25.28us/ 5.47ms ( 1991.01 GFLOPS, 2654.70 GB/s) | |
| *** 34 E_2048_2_8_6_6_4n16 arg 2 sz [2048, 1, 1] [8, 2, 1] OPs 2146M/ 248.67G mem 3.07 GB tm 10.88us/ 5.48ms (197330.82 GFLOPS, 5589.85 GB/s) | |
| *** 35 E_2048_32_6_6n4 arg 2 sz [2048, 1, 1] [32, 1, 1] OPs 1073M/ 250.82G mem 3.07 GB tm 6.20us/ 5.49ms (173141.88 GFLOPS, 4904.66 GB/s) | |
| *** 36 E_1024_32_8_16_4n14 arg 5 sz [32, 1024, 1] [16, 8, 1] OPs 318M/ 251.89G mem 3.07 GB tm 75.84us/ 5.56ms ( 4203.10 GFLOPS, 1327.33 GB/s) | |
| *** 37 E_8192_32_2_2_6_6n2 arg 2 sz [8192, 1, 1] [32, 1, 1] OPs 34087M/ 252.21G mem 3.07 GB tm 52.60us/ 5.62ms (648031.57 GFLOPS, 20731.91 GB/s) | |
| *** 38 r_36_64_4_4_8_4_2_256_4_4n4 arg 3 sz [4, 64, 36] [8, 8, 4] OPs 19327M/ 286.30G mem 3.07 GB tm 885.33us/ 6.50ms (21830.70 GFLOPS, 175.88 GB/s) | |
| *** 39 E_16384_2_32_4_4n10 arg 2 sz [2, 16384, 1] [32, 1, 1] OPs 8371M/ 305.63G mem 3.07 GB tm 117.68us/ 6.62ms (71140.04 GFLOPS, 6059.02 GB/s) | |
| *** 40 E_131072_32_4n12 arg 2 sz [131072, 1, 1] [32, 1, 1] OPs 0M/ 314.00G mem 3.07 GB tm 46.60us/ 6.67ms ( 0.00 GFLOPS, 2160.11 GB/s) | |
| *** 41 r_256_16_64_64n6 arg 2 sz [256, 1, 1] [16, 1, 1] OPs 16M/ 314.00G mem 3.07 GB tm 29.20us/ 6.70ms ( 574.57 GFLOPS, 2298.28 GB/s) | |
| *** 42 r_256_4_4_64_16_4n6 arg 3 sz [256, 1, 1] [4, 4, 1] OPs 50M/ 314.02G mem 3.07 GB tm 25.08us/ 6.72ms ( 2006.88 GFLOPS, 2675.87 GB/s) | |
| *** 43 E_1024_32_8_16_4n17 arg 6 sz [32, 1024, 1] [16, 8, 1] OPs 335M/ 314.07G mem 3.07 GB tm 127.88us/ 6.85ms ( 2623.88 GFLOPS, 1049.58 GB/s) | |
| *** 44 E_8192_32_2_2_6_6n2 arg 2 sz [8192, 1, 1] [32, 1, 1] OPs 34087M/ 314.40G mem 3.07 GB tm 78.08us/ 6.93ms (436560.86 GFLOPS, 13966.51 GB/s) | |
| *** 45 r_36_64_8_2_4_2_4_64_4_4_4_2_2n4 arg 3 sz [8, 64, 36] [8, 4, 2] OPs 38654M/ 348.49G mem 3.07 GB tm 1485.10us/ 8.41ms (26028.44 GFLOPS, 158.86 GB/s) | |
| *** 46 E_32768_32_2_4_4n8 arg 2 sz [32768, 1, 1] [2, 32, 1] OPs 16743M/ 387.14G mem 3.07 GB tm 283.28us/ 8.69ms (59105.78 GFLOPS, 5034.06 GB/s) | |
| *** 47 r_16384_32_2_2_4_4n10 arg 2 sz [16384, 1, 1] [32, 1, 1] OPs 33M/ 403.89G mem 3.07 GB tm 102.00us/ 8.80ms ( 328.96 GFLOPS, 822.40 GB/s) | |
| *** 48 E_65536_32_2_2_4n6 arg 3 sz [65536, 1, 1] [2, 2, 32] OPs 67M/ 403.92G mem 3.07 GB tm 116.24us/ 8.91ms ( 577.33 GFLOPS, 1298.98 GB/s) | |
| *** 49 r_16384_32_4_4_4n10 arg 2 sz [16384, 1, 1] [32, 1, 1] OPs 33M/ 403.99G mem 3.07 GB tm 88.00us/ 9.00ms ( 381.30 GFLOPS, 953.24 GB/s) | |
| *** 50 E_1024_16_2_4_4_4_4n6 arg 2 sz [1024, 1, 1] [2, 16, 1] OPs 0M/ 404.02G mem 3.07 GB tm 34.88us/ 9.04ms ( 0.00 GFLOPS, 1442.95 GB/s) | |
| *** 51 r_512_16_64_16n6 arg 2 sz [512, 1, 1] [16, 1, 1] OPs 8M/ 404.02G mem 3.07 GB tm 17.88us/ 9.05ms ( 469.19 GFLOPS, 1876.76 GB/s) | |
| *** 52 r_512_16_64_16n13 arg 3 sz [512, 1, 1] [16, 1, 1] OPs 25M/ 404.03G mem 3.07 GB tm 17.60us/ 9.07ms ( 1429.91 GFLOPS, 1906.63 GB/s) | |
| *** 53 E_8192_32_6_6n4 arg 2 sz [8192, 1, 1] [32, 1, 1] OPs 4293M/ 404.06G mem 3.07 GB tm 15.00us/ 9.09ms (286261.25 GFLOPS, 8109.00 GB/s) | |
| *** 54 E_1024_32_8_4_2_4n18 arg 5 sz [32, 1024, 1] [2, 4, 8] OPs 159M/ 408.35G mem 3.07 GB tm 22.28us/ 9.11ms ( 7153.66 GFLOPS, 2259.33 GB/s) | |
| *** 55 E_16384_32_6_6n2 arg 2 sz [16384, 1, 1] [32, 1, 1] OPs 17043M/ 408.51G mem 3.07 GB tm 29.64us/ 9.14ms (575018.70 GFLOPS, 18396.08 GB/s) | |
| *** 56 r_36_64_8_8_2_2_4_2_128_4_4n4 arg 3 sz [8, 64, 36] [16, 2, 8] OPs 19327M/ 425.55G mem 3.07 GB tm 1160.69us/ 10.30ms (16651.58 GFLOPS, 81.31 GB/s) | |
| *** 57 E_16384_32_4_4n16 arg 2 sz [16384, 1, 1] [32, 1, 1] OPs 4185M/ 444.88G mem 3.07 GB tm 23.24us/ 10.32ms (180109.09 GFLOPS, 15339.96 GB/s) | |
| *** 58 E_1024_16_2_4_4_4_4n6 arg 2 sz [1024, 1, 1] [2, 16, 1] OPs 0M/ 449.07G mem 3.07 GB tm 20.44us/ 10.34ms ( 0.00 GFLOPS, 2462.41 GB/s) | |
| *** 59 r_512_16_64_16n6 arg 2 sz [512, 1, 1] [16, 1, 1] OPs 8M/ 449.07G mem 3.07 GB tm 16.76us/ 10.36ms ( 500.54 GFLOPS, 2002.18 GB/s) | |
| *** 60 r_512_16_64_16n13 arg 3 sz [512, 1, 1] [16, 1, 1] OPs 25M/ 449.07G mem 3.07 GB tm 17.00us/ 10.38ms ( 1480.38 GFLOPS, 1973.92 GB/s) | |
| *** 61 E_1024_32_2_4_4_2_4n8 arg 6 sz [32, 1024, 1] [8, 4, 2] OPs 167M/ 449.10G mem 3.07 GB tm 39.04us/ 10.42ms ( 4297.44 GFLOPS, 1719.13 GB/s) | |
| *** 62 r_16384_32_4_4n8 arg 2 sz [16384, 1, 1] [32, 1, 1] OPs 8M/ 449.27G mem 3.07 GB tm 7.56us/ 10.42ms ( 1109.60 GFLOPS, 2357.91 GB/s) | |
| *** 63 E_16384_32_4_4n29 arg 3 sz [16384, 1, 1] [32, 1, 1] OPs 16M/ 449.28G mem 3.07 GB tm 16.00us/ 10.44ms ( 1048.58 GFLOPS, 2162.69 GB/s) | |
| *** 64 r_16384_32_16n14 arg 2 sz [16384, 1, 1] [32, 1, 1] OPs 8M/ 449.29G mem 3.07 GB tm 8.00us/ 10.45ms ( 1048.58 GFLOPS, 2228.22 GB/s) | |
| *** 65 E_n9 arg 1 sz [1, 1, 1] [1, 1, 1] OPs 0M/ 449.30G mem 3.07 GB tm 1.52us/ 10.45ms ( 0.00 GFLOPS, 0.00 GB/s) | |
| *** 66 E_512_2n6 arg 2 sz [512, 1, 1] [1, 1, 1] OPs 0M/ 449.30G mem 3.07 GB tm 1.72us/ 10.45ms ( 1.19 GFLOPS, 1.19 GB/s) | |
| *** 67 r_512_5_2_16_32_2n22 arg 3 sz [5, 512, 1] [16, 2, 1] OPs 10M/ 449.30G mem 3.07 GB tm 3.28us/ 10.45ms ( 3200.00 GFLOPS, 329.05 GB/s) | |
| *** 68 r_32_32_10n8 arg 2 sz [32, 1, 1] [32, 1, 1] OPs 0M/ 449.31G mem 3.07 GB tm 1.80us/ 10.46ms ( 5.69 GFLOPS, 12.52 GB/s) | |
| *** 69 E_64_10_16n6 arg 3 sz [10, 64, 1] [16, 1, 1] OPs 0M/ 449.31G mem 3.07 GB tm 1.96us/ 10.46ms ( 15.67 GFLOPS, 21.94 GB/s) | |
| *** 70 r_32_32_10n13 arg 2 sz [32, 1, 1] [32, 1, 1] OPs 0M/ 449.31G mem 3.07 GB tm 1.96us/ 10.46ms ( 5.22 GFLOPS, 11.49 GB/s) | |
| *** 71 r_256_4_10n14 arg 4 sz [256, 1, 1] [4, 1, 1] OPs 0M/ 449.31G mem 3.07 GB tm 2.08us/ 10.46ms ( 25.11 GFLOPS, 12.80 GB/s) | |
| *** 72 E_128_5_8_2n8 arg 3 sz [5, 128, 1] [8, 1, 1] OPs 0M/ 449.31G mem 3.07 GB tm 1.84us/ 10.46ms ( 11.13 GFLOPS, 23.37 GB/s) | |
| *** 73 r_32_32_10n13 arg 2 sz [32, 1, 1] [32, 1, 1] OPs 0M/ 449.31G mem 3.07 GB tm 1.60us/ 10.46ms ( 6.40 GFLOPS, 14.08 GB/s) | |
| *** 74 r_512_2_10n18 arg 5 sz [512, 1, 1] [2, 1, 1] OPs 0M/ 449.31G mem 3.07 GB tm 2.04us/ 10.47ms ( 35.14 GFLOPS, 23.09 GB/s) | |
| *** 75 E_64_5_16_2n20 arg 8 sz [5, 64, 1] [2, 16, 1] OPs 0M/ 449.31G mem 3.07 GB tm 1.92us/ 10.47ms ( 48.00 GFLOPS, 46.94 GB/s) | |
| *** 76 r_32_8_8_16_10_4_4n5 arg 3 sz [8, 32, 1] [16, 8, 1] OPs 10M/ 449.31G mem 3.07 GB tm 3.16us/ 10.47ms ( 3318.28 GFLOPS, 341.55 GB/s) | |
| *** 77 E_256_32_8_4_4_4_2n14 arg 8 sz [32, 256, 1] [4, 8, 1] OPs 310M/ 449.32G mem 3.07 GB tm 43.56us/ 10.52ms ( 7125.15 GFLOPS, 1974.00 GB/s) | |
| *** 78 r_512_4_4_64_16n20 arg 3 sz [512, 1, 1] [4, 4, 1] OPs 25M/ 449.63G mem 3.07 GB tm 20.28us/ 10.54ms ( 1240.92 GFLOPS, 1654.76 GB/s) | |
| *** 79 r_128_4_16_1024n12 arg 5 sz [128, 1, 1] [16, 4, 1] OPs 33M/ 449.66G mem 3.07 GB tm 26.56us/ 10.56ms ( 1263.51 GFLOPS, 2526.83 GB/s) | |
| *** 80 r_512_16_64_16n32 arg 3 sz [512, 1, 1] [16, 1, 1] OPs 33M/ 449.69G mem 3.07 GB tm 16.76us/ 10.58ms ( 2002.05 GFLOPS, 2002.30 GB/s) | |
| *** 81 r_512_2_8_64_16n26 arg 5 sz [512, 1, 1] [8, 2, 1] OPs 41M/ 449.72G mem 3.07 GB tm 16.84us/ 10.60ms ( 2490.74 GFLOPS, 1993.03 GB/s) | |
| *** 82 E_512_32_2_16_4_4n8 arg 7 sz [32, 512, 1] [4, 16, 2] OPs 58M/ 449.77G mem 3.07 GB tm 28.80us/ 10.62ms ( 2038.90 GFLOPS, 2913.00 GB/s) | |
| *** 83 E_65536_8_6n6 arg 2 sz [65536, 1, 1] [8, 1, 1] OPs 78M/ 449.83G mem 3.07 GB tm 11.20us/ 10.64ms ( 7021.71 GFLOPS, 2246.95 GB/s) | |
| *** 84 E_16384_32_6_6n5 arg 3 sz [16384, 1, 1] [32, 1, 1] OPs 6606M/ 449.90G mem 3.07 GB tm 24.20us/ 10.66ms (272965.12 GFLOPS, 12998.34 GB/s) | |
| *** 85 r_36_128_8_2_2_2_128_4_4_2_8n8 arg 3 sz [128, 36, 1] [4, 2, 8] OPs 19327M/ 456.51G mem 3.07 GB tm 918.45us/ 11.58ms (21043.47 GFLOPS, 102.75 GB/s) | |
| *** 86 E_8192_32_6_2n4 arg 2 sz [8192, 1, 1] [32, 1, 1] OPs 113M/ 475.84G mem 3.07 GB tm 5.96us/ 11.58ms (19001.04 GFLOPS, 4926.20 GB/s) | |
| *** 87 E_2048_2_4_4_6_4_2n8 arg 2 sz [2048, 1, 1] [4, 4, 2] OPs 113M/ 475.95G mem 3.07 GB tm 6.68us/ 11.59ms (16953.03 GFLOPS, 4395.23 GB/s) | |
| *** 88 E_8192_16_6_4n18 arg 2 sz [8192, 1, 1] [16, 1, 1] OPs 113M/ 476.06G mem 3.07 GB tm 7.28us/ 11.60ms (15555.80 GFLOPS, 4032.99 GB/s) | |
| *** 89 E_512_8_2_2_6_2_4_2_2n10 arg 2 sz [512, 1, 1] [2, 2, 8] OPs 113M/ 476.18G mem 3.07 GB tm 10.80us/ 11.61ms (10485.76 GFLOPS, 2718.53 GB/s) | |
| *** 90 E_1024_32_6_4_4n4 arg 2 sz [1024, 1, 1] [32, 1, 1] OPs 113M/ 476.29G mem 3.07 GB tm 7.80us/ 11.62ms (14518.74 GFLOPS, 3764.12 GB/s) | |
| *** 91 E_1024_32_6_2_4_2n6 arg 2 sz [1024, 1, 1] [32, 1, 1] OPs 113M/ 476.40G mem 3.07 GB tm 11.24us/ 11.63ms (10075.29 GFLOPS, 2612.11 GB/s) | |
| *** 92 E_16384_32_6_6n8 arg 8 sz [16384, 1, 1] [32, 1, 1] OPs 4756M/ 476.52G mem 3.07 GB tm 54.20us/ 11.68ms (87755.36 GFLOPS, 5107.46 GB/s) | |
| *** 93 r_8192_32_2_7_7_6_6n12 arg 2 sz [8192, 1, 1] [2, 32, 1] OPs 924M/ 481.27G mem 3.07 GB tm 30.84us/ 11.71ms (29988.46 GFLOPS, 61200.93 GB/s) | |
| *** 94 E_512_32_2_16_4_4n22 arg 9 sz [32, 512, 1] [4, 16, 2] OPs 318M/ 482.20G mem 3.07 GB tm 179.96us/ 11.89ms ( 1771.30 GFLOPS, 571.05 GB/s) | |
| *** 95 r_512_4_4_64_16n20 arg 3 sz [512, 1, 1] [4, 4, 1] OPs 25M/ 482.52G mem 3.07 GB tm 27.04us/ 11.92ms ( 930.65 GFLOPS, 1241.02 GB/s) | |
| *** 96 r_128_4_16_1024n12 arg 5 sz [128, 1, 1] [16, 4, 1] OPs 33M/ 482.54G mem 3.07 GB tm 39.52us/ 11.96ms ( 849.19 GFLOPS, 1698.25 GB/s) | |
| *** 97 r_512_16_64_16n32 arg 3 sz [512, 1, 1] [16, 1, 1] OPs 33M/ 482.58G mem 3.07 GB tm 16.84us/ 11.98ms ( 1992.43 GFLOPS, 1992.67 GB/s) | |
| *** 98 r_512_2_8_64_16n26 arg 5 sz [512, 1, 1] [8, 2, 1] OPs 41M/ 482.61G mem 3.07 GB tm 17.36us/ 11.99ms ( 2416.13 GFLOPS, 1933.33 GB/s) | |
| *** 99 E_512_128_16_4_2n16 arg 7 sz [128, 512, 1] [16, 1, 1] OPs 58M/ 482.65G mem 3.07 GB tm 28.56us/ 12.02ms ( 2055.96 GFLOPS, 2937.37 GB/s) | |
| *** 100 E_65536_2_4_8_4_2n12 arg 4 sz [2, 65536, 1] [8, 4, 1] OPs 67M/ 482.71G mem 3.07 GB tm 201.84us/ 12.22ms ( 332.48 GFLOPS, 831.21 GB/s) | |
| *** 101 E_32768_32_2_6n2 arg 2 sz [32768, 1, 1] [2, 32, 1] OPs 314M/ 482.78G mem 3.07 GB tm 94.88us/ 12.32ms ( 3315.45 GFLOPS, 1060.94 GB/s) | |
| *** 102 E_32768_32_2_6_6n2 arg 3 sz [32768, 1, 1] [2, 32, 1] OPs 26424M/ 483.09G mem 3.07 GB tm 333.32us/ 12.65ms (79274.57 GFLOPS, 3774.98 GB/s) | |
| *** 103 r_36_256_2_2_8_512_4_8_4n8 arg 3 sz [256, 36, 1] [8, 2, 2] OPs 38654M/ 509.52G mem 3.07 GB tm 1480.97us/ 14.13ms (26100.87 GFLOPS, 159.31 GB/s) | |
| *** 104 E_16384_32_6_2n4 arg 2 sz [16384, 1, 1] [32, 1, 1] OPs 226M/ 548.17G mem 3.07 GB tm 10.64us/ 14.14ms (21286.88 GFLOPS, 5518.82 GB/s) | |
| *** 105 E_16384_16_6_4n16 arg 2 sz [16384, 1, 1] [16, 1, 1] OPs 226M/ 548.40G mem 3.07 GB tm 11.52us/ 14.16ms (19660.80 GFLOPS, 5097.25 GB/s) | |
| *** 106 E_16384_2_2_4_6_4n14 arg 2 sz [16384, 1, 1] [4, 2, 2] OPs 226M/ 548.62G mem 3.07 GB tm 33.00us/ 14.19ms ( 6863.41 GFLOPS, 1779.40 GB/s) | |
| *** 107 E_16384_16_6_2_2n8 arg 2 sz [16384, 1, 1] [16, 1, 1] OPs 226M/ 548.85G mem 3.07 GB tm 25.68us/ 14.21ms ( 8819.45 GFLOPS, 2286.53 GB/s) | |
| *** 108 E_32768_32_6n14 arg 2 sz [32768, 1, 1] [32, 1, 1] OPs 226M/ 549.08G mem 3.07 GB tm 37.56us/ 14.25ms ( 6030.15 GFLOPS, 1563.37 GB/s) | |
| *** 109 E_16384_16_6_4n33 arg 2 sz [16384, 1, 1] [16, 1, 1] OPs 226M/ 549.30G mem 3.07 GB tm 32.92us/ 14.28ms ( 6880.09 GFLOPS, 1783.73 GB/s) | |
| *** 110 E_32768_32_6_6n2 arg 8 sz [32768, 1, 1] [32, 1, 1] OPs 9512M/ 549.53G mem 3.07 GB tm 338.80us/ 14.62ms (28077.32 GFLOPS, 1634.13 GB/s) | |
| *** 111 r_32_2_10_5_16_8_7_7_4_4_2_2n6 arg 2 sz [50, 2, 32] [8, 16, 1] OPs 1284M/ 559.04G mem 3.07 GB tm 626.45us/ 15.25ms ( 2050.47 GFLOPS, 4184.62 GB/s) | |
| *** 112 E_1024_32_8_8_2_4n12 arg 6 sz [32, 1024, 1] [2, 8, 8] OPs 587M/ 560.33G mem 3.07 GB tm 225.28us/ 15.48ms ( 2606.52 GFLOPS, 744.73 GB/s) | |
| *** 113 r_256_2_8_64_16_4n8 arg 3 sz [256, 1, 1] [8, 2, 1] OPs 50M/ 560.91G mem 3.07 GB tm 63.32us/ 15.54ms ( 794.87 GFLOPS, 1059.85 GB/s) | |
| *** 114 r_256_16_64_64n21 arg 5 sz [256, 1, 1] [16, 1, 1] OPs 67M/ 560.96G mem 3.07 GB tm 147.16us/ 15.69ms ( 456.04 GFLOPS, 912.06 GB/s) | |
| *** 115 r_256_16_64_64n28 arg 3 sz [256, 1, 1] [16, 1, 1] OPs 67M/ 561.03G mem 3.07 GB tm 54.24us/ 15.74ms ( 1237.26 GFLOPS, 1237.30 GB/s) | |
| *** 116 r_256_4_4_64_16_4n15 arg 5 sz [256, 1, 1] [4, 4, 1] OPs 83M/ 561.10G mem 3.07 GB tm 78.84us/ 15.82ms ( 1064.01 GFLOPS, 851.26 GB/s) | |
| *** 117 E_1024_32_8_16_4n8 arg 7 sz [32, 1024, 1] [16, 8, 1] OPs 117M/ 561.18G mem 3.07 GB tm 155.20us/ 15.97ms ( 756.70 GFLOPS, 1081.03 GB/s) | |
| *** 118 E_32768_2_16_6n12 arg 2 sz [2, 32768, 1] [16, 1, 1] OPs 157M/ 561.30G mem 3.07 GB tm 38.52us/ 16.01ms ( 4083.13 GFLOPS, 1306.60 GB/s) | |
| *** 119 E_16384_32_2_6_6n2 arg 3 sz [16384, 1, 1] [2, 32, 1] OPs 13212M/ 561.46G mem 3.07 GB tm 48.76us/ 16.06ms (270955.43 GFLOPS, 12902.64 GB/s) | |
| *** 120 r_36_128_4_8_16_64_4_4_4n4 arg 3 sz [4, 128, 36] [16, 8, 1] OPs 19327M/ 574.67G mem 3.07 GB tm 790.77us/ 16.85ms (24441.27 GFLOPS, 196.91 GB/s) | |
| *** 121 E_16384_32_6_2n4 arg 2 sz [16384, 1, 1] [32, 1, 1] OPs 226M/ 594.00G mem 3.07 GB tm 10.28us/ 16.86ms (22032.34 GFLOPS, 5712.09 GB/s) | |
| *** 122 E_16384_16_6_4n16 arg 2 sz [16384, 1, 1] [16, 1, 1] OPs 226M/ 594.22G mem 3.07 GB tm 11.28us/ 16.87ms (20079.11 GFLOPS, 5205.70 GB/s) | |
| *** 123 E_16384_2_2_4_6_4n14 arg 2 sz [16384, 1, 1] [4, 2, 2] OPs 226M/ 594.45G mem 3.07 GB tm 13.68us/ 16.89ms (16556.46 GFLOPS, 4292.42 GB/s) | |
| *** 124 E_16384_16_6_2_2n8 arg 2 sz [16384, 1, 1] [16, 1, 1] OPs 226M/ 594.68G mem 3.07 GB tm 27.20us/ 16.91ms ( 8326.93 GFLOPS, 2158.83 GB/s) | |
| *** 125 E_32768_32_6n14 arg 2 sz [32768, 1, 1] [32, 1, 1] OPs 226M/ 594.90G mem 3.07 GB tm 27.64us/ 16.94ms ( 8194.07 GFLOPS, 2124.39 GB/s) | |
| *** 126 E_16384_16_6_4n33 arg 2 sz [16384, 1, 1] [16, 1, 1] OPs 226M/ 595.13G mem 3.07 GB tm 35.00us/ 16.98ms ( 6471.21 GFLOPS, 1677.72 GB/s) | |
| *** 127 E_32768_32_6_6n2 arg 8 sz [32768, 1, 1] [32, 1, 1] OPs 9512M/ 595.35G mem 3.07 GB tm 347.48us/ 17.32ms (27375.96 GFLOPS, 1593.31 GB/s) | |
| *** 128 r_32_2_10_5_16_8_7_7_4_4_2_2n6 arg 2 sz [50, 2, 32] [8, 16, 1] OPs 1284M/ 604.87G mem 3.07 GB tm 500.49us/ 17.83ms ( 2566.52 GFLOPS, 5237.80 GB/s) | |
| *** 129 E_1024_32_8_8_2_4n15 arg 7 sz [32, 1024, 1] [2, 8, 8] OPs 603M/ 606.15G mem 3.07 GB tm 318.60us/ 18.14ms ( 1895.71 GFLOPS, 631.91 GB/s) | |
| *** 130 r_256_2_8_64_16_4n8 arg 3 sz [256, 1, 1] [8, 2, 1] OPs 50M/ 606.76G mem 3.07 GB tm 71.60us/ 18.22ms ( 702.95 GFLOPS, 937.29 GB/s) | |
| *** 131 r_256_16_64_64n21 arg 5 sz [256, 1, 1] [16, 1, 1] OPs 67M/ 606.81G mem 3.07 GB tm 120.12us/ 18.34ms ( 558.70 GFLOPS, 1117.38 GB/s) | |
| *** 132 r_256_16_64_64n28 arg 3 sz [256, 1, 1] [16, 1, 1] OPs 67M/ 606.87G mem 3.07 GB tm 43.08us/ 18.38ms ( 1557.77 GFLOPS, 1557.82 GB/s) | |
| *** 133 r_256_4_4_64_16_4n15 arg 5 sz [256, 1, 1] [4, 4, 1] OPs 83M/ 606.94G mem 3.07 GB tm 73.88us/ 18.45ms ( 1135.43 GFLOPS, 908.39 GB/s) | |
| *** 134 E_1024_32_8_16_4n11 arg 7 sz [32, 1024, 1] [16, 8, 1] OPs 117M/ 607.02G mem 3.07 GB tm 151.20us/ 18.60ms ( 776.71 GFLOPS, 1109.62 GB/s) | |
| *** 135 E_2097152_2_8_2n6 arg 4 sz [2097152, 1, 1] [2, 8, 2] OPs 134M/ 607.14G mem 3.07 GB tm 422.60us/ 19.03ms ( 317.60 GFLOPS, 793.99 GB/s) | |
| *** 136 E_32768_32_4_6n2 arg 2 sz [32768, 1, 1] [4, 32, 1] OPs 629M/ 607.28G mem 3.07 GB tm 236.04us/ 19.26ms ( 2665.40 GFLOPS, 852.93 GB/s) | |
| *** 137 E_32768_32_4_6_6n2 arg 3 sz [32768, 1, 1] [4, 32, 1] OPs 52848M/ 607.91G mem 3.07 GB tm 902.29us/ 20.16ms (58571.29 GFLOPS, 2789.11 GB/s) | |
| *** 138 r_36_1024_8_4_256_4_4_2n8 arg 3 sz [1024, 36, 1] [4, 8, 1] OPs 19327M/ 660.75G mem 3.07 GB tm 812.41us/ 20.98ms (23790.20 GFLOPS, 466.10 GB/s) | |
| *** 139 E_16384_32_6_2n11 arg 2 sz [16384, 1, 1] [32, 1, 1] OPs 226M/ 680.08G mem 3.07 GB tm 10.56us/ 20.99ms (21448.15 GFLOPS, 5560.63 GB/s) | |
| *** 140 E_16384_2_4_2_6_4n26 arg 2 sz [16384, 1, 1] [2, 4, 2] OPs 226M/ 680.31G mem 3.07 GB tm 24.72us/ 21.01ms ( 9161.94 GFLOPS, 2375.32 GB/s) | |
| *** 141 E_16384_16_6_4n52 arg 2 sz [16384, 1, 1] [16, 1, 1] OPs 226M/ 680.53G mem 3.07 GB tm 25.60us/ 21.04ms ( 8847.36 GFLOPS, 2293.76 GB/s) | |
| *** 142 E_16384_16_6_4n59 arg 2 sz [16384, 1, 1] [16, 1, 1] OPs 226M/ 680.76G mem 3.07 GB tm 25.84us/ 21.06ms ( 8765.19 GFLOPS, 2272.46 GB/s) | |
| *** 143 E_16384_2_16_6_2n12 arg 2 sz [16384, 1, 1] [16, 2, 1] OPs 226M/ 680.99G mem 3.07 GB tm 27.00us/ 21.09ms ( 8388.61 GFLOPS, 2174.83 GB/s) | |
| *** 144 E_16384_16_2_6_2n30 arg 2 sz [16384, 1, 1] [2, 16, 1] OPs 226M/ 681.21G mem 3.07 GB tm 30.44us/ 21.12ms ( 7440.37 GFLOPS, 1928.99 GB/s) | |
| *** 145 E_32768_32_6_6n5 arg 8 sz [32768, 1, 1] [32, 1, 1] OPs 9512M/ 681.44G mem 3.07 GB tm 337.36us/ 21.46ms (28197.17 GFLOPS, 1641.11 GB/s) | |
| *** 146 r_32_2_18_9_32_7_7_4_2_2_4n4 arg 2 sz [162, 2, 32] [32, 1, 1] OPs 1040M/ 690.95G mem 3.07 GB tm 649.21us/ 22.11ms ( 1602.65 GFLOPS, 3270.71 GB/s) | |
| *** 147 E_1024_32_2_16_4_4n14 arg 6 sz [32, 1024, 1] [4, 16, 2] OPs 587M/ 691.99G mem 3.07 GB tm 202.20us/ 22.31ms ( 2904.04 GFLOPS, 829.73 GB/s) | |
| *** 148 r_1024_64_2_8_16n22 arg 4 sz [2, 64, 1024] [8, 1, 1] OPs 67M/ 692.58G mem 3.07 GB tm 196.40us/ 22.51ms ( 341.69 GFLOPS, 704.74 GB/s) | |
| *** 149 r_64_16_4_4_16_4n34 arg 2 sz [64, 1, 1] [4, 16, 1] OPs 1M/ 692.65G mem 3.07 GB tm 7.32us/ 22.51ms ( 143.25 GFLOPS, 573.03 GB/s) | |
| *** 150 r_64_64_4_16_4n34 arg 3 sz [64, 1, 1] [64, 1, 1] OPs 1M/ 692.65G mem 3.07 GB tm 5.56us/ 22.52ms ( 188.72 GFLOPS, 754.47 GB/s) | |
| *** 151 r_512_64_16_16_2n24 arg 4 sz [64, 512, 1] [16, 1, 1] OPs 83M/ 692.65G mem 3.07 GB tm 61.96us/ 22.58ms ( 1353.87 GFLOPS, 1150.80 GB/s) | |
| *** 152 r_512_64_4_2_2_16_2n10 arg 3 sz [64, 512, 1] [2, 2, 4] OPs 67M/ 692.73G mem 3.07 GB tm 87.28us/ 22.67ms ( 768.88 GFLOPS, 816.94 GB/s) | |
| *** 153 r_64_16_4_4_16_4n34 arg 2 sz [64, 1, 1] [4, 16, 1] OPs 1M/ 692.80G mem 3.07 GB tm 4.24us/ 22.67ms ( 247.31 GFLOPS, 989.28 GB/s) | |
| *** 154 r_64_8_8_4_16_4n26 arg 3 sz [64, 1, 1] [8, 8, 1] OPs 1M/ 692.80G mem 3.07 GB tm 5.88us/ 22.68ms ( 178.35 GFLOPS, 713.40 GB/s) | |
| *** 155 E_1024_32_2_16_4_4n17 arg 8 sz [32, 1024, 1] [4, 16, 2] OPs 687M/ 692.80G mem 3.07 GB tm 132.68us/ 22.81ms ( 5184.36 GFLOPS, 758.70 GB/s) | |
| *** 156 E_8192_32_4_6n10 arg 2 sz [8192, 1, 1] [4, 32, 1] OPs 157M/ 693.49G mem 3.07 GB tm 19.92us/ 22.83ms ( 7895.90 GFLOPS, 2526.69 GB/s) | |
| *** 157 E_8192_32_4_6_6n2 arg 3 sz [8192, 1, 1] [4, 32, 1] OPs 13212M/ 693.65G mem 3.07 GB tm 59.44us/ 22.89ms (222271.79 GFLOPS, 10584.37 GB/s) | |
| *** 158 r_36_1024_2_8_4_4_4_4_4_2_2n6 arg 3 sz [2, 1024, 36] [4, 8, 1] OPs 4831M/ 706.86G mem 3.07 GB tm 212.60us/ 23.10ms (22727.15 GFLOPS, 711.61 GB/s) | |
| *** 159 E_16384_32_6_2n11 arg 2 sz [16384, 1, 1] [32, 1, 1] OPs 226M/ 711.69G mem 3.07 GB tm 10.20us/ 23.11ms (22205.14 GFLOPS, 5756.89 GB/s) | |
| *** 160 E_16384_2_4_2_6_4n26 arg 2 sz [16384, 1, 1] [2, 4, 2] OPs 226M/ 711.92G mem 3.07 GB tm 10.84us/ 23.12ms (20894.13 GFLOPS, 5417.00 GB/s) | |
| *** 161 E_16384_16_6_4n52 arg 2 sz [16384, 1, 1] [16, 1, 1] OPs 226M/ 712.14G mem 3.07 GB tm 13.00us/ 23.14ms (17422.49 GFLOPS, 4516.94 GB/s) | |
| *** 162 E_16384_16_6_4n59 arg 2 sz [16384, 1, 1] [16, 1, 1] OPs 226M/ 712.37G mem 3.07 GB tm 31.16us/ 23.17ms ( 7268.46 GFLOPS, 1884.42 GB/s) | |
| *** 163 E_16384_2_16_6_2n12 arg 2 sz [16384, 1, 1] [16, 2, 1] OPs 226M/ 712.60G mem 3.07 GB tm 39.40us/ 23.21ms ( 5748.54 GFLOPS, 1490.36 GB/s) | |
| *** 164 E_16384_16_2_6_2n30 arg 2 sz [16384, 1, 1] [2, 16, 1] OPs 226M/ 712.82G mem 3.07 GB tm 70.52us/ 23.28ms ( 3211.75 GFLOPS, 832.68 GB/s) | |
| *** 165 E_32768_32_6_6n5 arg 8 sz [32768, 1, 1] [32, 1, 1] OPs 9512M/ 713.05G mem 3.07 GB tm 420.28us/ 23.70ms (22633.94 GFLOPS, 1317.32 GB/s) | |
| *** 166 r_32_2_18_9_32_7_7_4_2_2_4n4 arg 2 sz [162, 2, 32] [32, 1, 1] OPs 1040M/ 722.56G mem 3.07 GB tm 636.29us/ 24.33ms ( 1635.19 GFLOPS, 3337.13 GB/s) | |
| *** 167 E_1024_32_2_16_4_4n20 arg 7 sz [32, 1024, 1] [4, 16, 2] OPs 603M/ 723.60G mem 3.07 GB tm 275.48us/ 24.61ms ( 2192.44 GFLOPS, 730.82 GB/s) | |
| *** 168 r_32768_32_16n6 arg 2 sz [32768, 1, 1] [32, 1, 1] OPs 16M/ 724.21G mem 3.07 GB tm 77.36us/ 24.69ms ( 216.87 GFLOPS, 921.69 GB/s) | |
| *** 169 r_64_16_4_4_16_4n34 arg 2 sz [64, 1, 1] [4, 16, 1] OPs 1M/ 724.22G mem 3.07 GB tm 4.36us/ 24.69ms ( 240.50 GFLOPS, 962.06 GB/s) | |
| *** 170 E_8_2_4n20 arg 4 sz [8, 1, 1] [1, 1, 1] OPs 0M/ 724.23G mem 3.07 GB tm 1.80us/ 24.69ms ( 0.14 GFLOPS, 0.57 GB/s) | |
| *** 171 r_32768_32_16n6 arg 2 sz [32768, 1, 1] [32, 1, 1] OPs 16M/ 724.23G mem 3.07 GB tm 87.24us/ 24.78ms ( 192.31 GFLOPS, 817.31 GB/s) | |
| *** 172 r_64_16_4_4_16_4n34 arg 2 sz [64, 1, 1] [4, 16, 1] OPs 1M/ 724.24G mem 3.07 GB tm 4.48us/ 24.79ms ( 234.06 GFLOPS, 936.29 GB/s) | |
| *** 173 E_8_2_4n20 arg 4 sz [8, 1, 1] [1, 1, 1] OPs 0M/ 724.24G mem 3.07 GB tm 1.64us/ 24.79ms ( 0.16 GFLOPS, 0.63 GB/s) | |
| *** 174 r_256_16_64_64n39 arg 2 sz [256, 1, 1] [16, 1, 1] OPs 16M/ 724.24G mem 3.07 GB tm 84.16us/ 24.87ms ( 199.35 GFLOPS, 797.40 GB/s) | |
| *** 175 E_32_2_4n16 arg 4 sz [32, 1, 1] [1, 1, 1] OPs 0M/ 724.26G mem 3.07 GB tm 1.84us/ 24.87ms ( 0.56 GFLOPS, 2.23 GB/s) | |
| *** 176 r_256_16_64_64n39 arg 2 sz [256, 1, 1] [16, 1, 1] OPs 16M/ 724.26G mem 3.07 GB tm 79.84us/ 24.95ms ( 210.14 GFLOPS, 840.55 GB/s) | |
| *** 177 E_32_2_4n16 arg 4 sz [32, 1, 1] [1, 1, 1] OPs 0M/ 724.28G mem 3.07 GB tm 1.68us/ 24.95ms ( 0.61 GFLOPS, 2.44 GB/s) | |
| *** 178 r_512_16_64_16n45 arg 2 sz [512, 1, 1] [16, 1, 1] OPs 8M/ 724.28G mem 3.07 GB tm 40.76us/ 25.00ms ( 205.80 GFLOPS, 823.27 GB/s) | |
| *** 179 E_256_2n17 arg 4 sz [256, 1, 1] [1, 1, 1] OPs 0M/ 724.29G mem 3.07 GB tm 1.96us/ 25.00ms ( 1.04 GFLOPS, 4.18 GB/s) | |
| *** 180 r_512_16_64_16n45 arg 2 sz [512, 1, 1] [16, 1, 1] OPs 8M/ 724.29G mem 3.07 GB tm 40.48us/ 25.04ms ( 207.23 GFLOPS, 828.96 GB/s) | |
| *** 181 E_256_2n17 arg 4 sz [256, 1, 1] [1, 1, 1] OPs 0M/ 724.29G mem 3.07 GB tm 1.84us/ 25.04ms ( 1.11 GFLOPS, 4.46 GB/s) | |
| *** 182 E_8_4_2n16 arg 5 sz [8, 1, 1] [4, 1, 1] OPs 0M/ 724.29G mem 3.07 GB tm 2.12us/ 25.04ms ( 0.18 GFLOPS, 0.49 GB/s) | |
| *** 183 E_8_4_2n16 arg 5 sz [8, 1, 1] [4, 1, 1] OPs 0M/ 724.29G mem 3.07 GB tm 1.68us/ 25.04ms ( 0.23 GFLOPS, 0.62 GB/s) | |
| *** 184 E_128_2n25 arg 5 sz [128, 1, 1] [1, 1, 1] OPs 0M/ 724.29G mem 3.07 GB tm 1.84us/ 25.05ms ( 0.83 GFLOPS, 2.23 GB/s) | |
| *** 185 E_128_2n25 arg 5 sz [128, 1, 1] [1, 1, 1] OPs 0M/ 724.29G mem 3.07 GB tm 1.56us/ 25.05ms ( 0.98 GFLOPS, 2.63 GB/s) | |
| *** 186 E_64_2_4n18 arg 5 sz [64, 1, 1] [1, 1, 1] OPs 0M/ 724.29G mem 3.07 GB tm 1.96us/ 25.05ms ( 1.57 GFLOPS, 4.18 GB/s) | |
| *** 187 E_64_2_4n18 arg 5 sz [64, 1, 1] [1, 1, 1] OPs 0M/ 724.29G mem 3.07 GB tm 1.64us/ 25.05ms ( 1.87 GFLOPS, 5.00 GB/s) | |
| *** 188 E_1048576_4_2_2_4n8 arg 3 sz [1048576, 1, 1] [2, 2, 4] OPs 134M/ 724.29G mem 3.07 GB tm 327.68us/ 25.38ms ( 409.60 GFLOPS, 921.59 GB/s) | |
| *** 189 r_524288_32_4n17 arg 2 sz [524288, 1, 1] [32, 1, 1] OPs 67M/ 724.43G mem 3.07 GB tm 221.92us/ 25.60ms ( 302.40 GFLOPS, 755.99 GB/s) | |
| *** 190 r_1024_64_2_8_16n22 arg 4 sz [2, 64, 1024] [8, 1, 1] OPs 67M/ 724.50G mem 3.07 GB tm 176.88us/ 25.78ms ( 379.40 GFLOPS, 782.52 GB/s) | |
| *** 191 r_64_16_4_4_16_4n34 arg 2 sz [64, 1, 1] [4, 16, 1] OPs 1M/ 724.56G mem 3.07 GB tm 6.72us/ 25.78ms ( 156.04 GFLOPS, 624.19 GB/s) | |
| *** 192 r_64_64_4_16_4n34 arg 3 sz [64, 1, 1] [64, 1, 1] OPs 1M/ 724.56G mem 3.07 GB tm 5.24us/ 25.79ms ( 200.24 GFLOPS, 800.54 GB/s) | |
| *** 193 r_512_64_16_16_2n24 arg 4 sz [64, 512, 1] [16, 1, 1] OPs 83M/ 724.56G mem 3.07 GB tm 58.76us/ 25.85ms ( 1427.58 GFLOPS, 1213.45 GB/s) | |
| *** 194 r_512_64_4_2_2_16_2n10 arg 3 sz [64, 512, 1] [2, 2, 4] OPs 67M/ 724.65G mem 3.07 GB tm 87.56us/ 25.94ms ( 766.42 GFLOPS, 814.33 GB/s) | |
| *** 195 r_64_16_4_4_16_4n34 arg 2 sz [64, 1, 1] [4, 16, 1] OPs 1M/ 724.72G mem 3.07 GB tm 4.40us/ 25.94ms ( 238.31 GFLOPS, 953.31 GB/s) | |
| *** 196 r_64_8_8_4_16_4n26 arg 3 sz [64, 1, 1] [8, 8, 1] OPs 1M/ 724.72G mem 3.07 GB tm 5.36us/ 25.95ms ( 195.65 GFLOPS, 782.62 GB/s) | |
| *** 197 E_1024_32_2_16_4_4n23 arg 9 sz [32, 1024, 1] [4, 16, 2] OPs 704M/ 724.72G mem 3.07 GB tm 188.24us/ 26.13ms ( 3743.28 GFLOPS, 713.01 GB/s) | |
| *** 198 E_1048576_2_16_2n22 arg 4 sz [1048576, 1, 1] [2, 16, 2] OPs 134M/ 725.42G mem 3.07 GB tm 413.16us/ 26.55ms ( 324.85 GFLOPS, 812.13 GB/s) | |
| *** 199 E_32768_16_8_6n2 arg 2 sz [32768, 1, 1] [8, 16, 1] OPs 629M/ 725.56G mem 3.07 GB tm 124.44us/ 26.67ms ( 5055.73 GFLOPS, 1617.83 GB/s) | |
| *** 200 E_32768_16_8_6_6n2 arg 3 sz [32768, 1, 1] [8, 16, 1] OPs 52848M/ 726.19G mem 3.07 GB tm 936.49us/ 27.61ms (56432.30 GFLOPS, 2687.25 GB/s) | |
| *** 201 r_36_1024_8_4_8_4_4_4_4_2n18 arg 3 sz [8, 1024, 36] [8, 4, 1] OPs 9663M/ 779.03G mem 3.07 GB tm 613.21us/ 28.22ms (15759.27 GFLOPS, 738.96 GB/s) | |
| *** 202 E_32768_32_6_2n4 arg 2 sz [32768, 1, 1] [32, 1, 1] OPs 452M/ 788.70G mem 3.07 GB tm 20.80us/ 28.24ms (21778.12 GFLOPS, 5646.18 GB/s) | |
| *** 203 E_32768_16_6_4n10 arg 2 sz [32768, 1, 1] [16, 1, 1] OPs 452M/ 789.15G mem 3.07 GB tm 51.52us/ 28.29ms ( 8792.24 GFLOPS, 2279.47 GB/s) | |
| *** 204 E_32768_16_6_4n19 arg 2 sz [32768, 1, 1] [16, 1, 1] OPs 452M/ 789.60G mem 3.07 GB tm 69.32us/ 28.36ms ( 6534.60 GFLOPS, 1694.16 GB/s) | |
| *** 205 E_32768_16_6_4n30 arg 2 sz [32768, 1, 1] [16, 1, 1] OPs 452M/ 790.06G mem 3.07 GB tm 58.52us/ 28.42ms ( 7740.55 GFLOPS, 2006.81 GB/s) | |
| *** 206 E_32768_2_4_2_6_4n12 arg 2 sz [32768, 1, 1] [2, 4, 2] OPs 452M/ 790.51G mem 3.07 GB tm 74.24us/ 28.50ms ( 6101.55 GFLOPS, 1581.88 GB/s) | |
| *** 207 E_32768_16_6_4n47 arg 2 sz [32768, 1, 1] [16, 1, 1] OPs 452M/ 790.96G mem 3.07 GB tm 73.36us/ 28.57ms ( 6174.74 GFLOPS, 1600.86 GB/s) | |
| *** 208 E_131072_16_6_6n8 arg 8 sz [131072, 1, 1] [16, 1, 1] OPs 19025M/ 791.42G mem 3.07 GB tm 637.09us/ 29.21ms (29863.10 GFLOPS, 1738.06 GB/s) | |
| *** 209 r_32_8_34_17_4_2_4_7_7_4_2n6 arg 2 sz [578, 8, 32] [4, 2, 4] OPs 1856M/ 810.44G mem 3.07 GB tm 1026.73us/ 30.23ms ( 1807.79 GFLOPS, 3689.36 GB/s) | |
| *** 210 E_32768_2_16_8_4n10 arg 3 sz [2, 32768, 1] [8, 16, 1] OPs 1040M/ 812.30G mem 3.07 GB tm 256.24us/ 30.49ms ( 4059.38 GFLOPS, 785.69 GB/s) | |
| *** 211 r_1024_32_3_4_4_2_8_4_2_2n18 arg 3 sz [3, 32, 1024] [2, 4, 4] OPs 805M/ 813.34G mem 3.07 GB tm 236.00us/ 30.72ms ( 3412.29 GFLOPS, 497.63 GB/s) | |
| *** 212 r_32_2_3_16_64_8_4_2n10 arg 2 sz [2, 32, 1] [16, 3, 1] OPs 12M/ 814.14G mem 3.07 GB tm 31.12us/ 30.76ms ( 404.34 GFLOPS, 808.70 GB/s) | |
| *** 213 E_3_32_4n14 arg 4 sz [3, 1, 1] [32, 1, 1] OPs 0M/ 814.15G mem 3.07 GB tm 1.80us/ 30.76ms ( 0.85 GFLOPS, 1.71 GB/s) | |
| *** 214 r_36_8_4_8_8_1024_16_4n26 arg 3 sz [4, 8, 36] [8, 8, 1] OPs 9663M/ 814.15G mem 3.07 GB tm 731.25us/ 31.49ms (13215.34 GFLOPS, 619.67 GB/s) | |
| *** 215 E_64_32_3_3n2 arg 2 sz [64, 1, 1] [32, 1, 1] OPs 7M/ 823.82G mem 3.07 GB tm 3.36us/ 31.49ms ( 2139.43 GFLOPS, 249.93 GB/s) | |
| *** 216 E_192_32_3n20 arg 4 sz [192, 1, 1] [32, 1, 1] OPs 0M/ 823.83G mem 3.07 GB tm 1.92us/ 31.49ms ( 38.40 GFLOPS, 76.80 GB/s) | |
| *** 217 r_36_4_4_4_16_1024_16_4n18 arg 3 sz [4, 4, 36] [16, 4, 1] OPs 4831M/ 823.83G mem 3.07 GB tm 312.72us/ 31.81ms (15450.86 GFLOPS, 483.78 GB/s) | |
| *** 218 E_128_32_3_3n2 arg 2 sz [128, 1, 1] [32, 1, 1] OPs 14M/ 828.66G mem 3.07 GB tm 3.32us/ 31.81ms ( 4330.41 GFLOPS, 505.85 GB/s) | |
| *** 219 E_384_32_3n18 arg 4 sz [384, 1, 1] [32, 1, 1] OPs 0M/ 828.67G mem 3.07 GB tm 2.16us/ 31.81ms ( 68.27 GFLOPS, 136.54 GB/s) | |
| *** 220 r_36_8_8_16_1024_16_4_4n2 arg 3 sz [8, 36, 1] [16, 8, 1] OPs 19327M/ 828.67G mem 3.07 GB tm 1315.29us/ 33.13ms (14694.33 GFLOPS, 287.90 GB/s) | |
| *** 221 E_256_32_2_3_3n8 arg 2 sz [256, 1, 1] [2, 32, 1] OPs 57M/ 848.00G mem 3.07 GB tm 3.92us/ 33.13ms (14670.37 GFLOPS, 1713.65 GB/s) | |
| *** 222 E_1536_32_3n18 arg 4 sz [1536, 1, 1] [32, 1, 1] OPs 0M/ 848.06G mem 3.07 GB tm 2.84us/ 33.13ms ( 207.68 GFLOPS, 415.37 GB/s) | |
| *** 223 r_36_16_16_2_4_2_2_1024_4_4_2n4 arg 3 sz [16, 16, 36] [4, 4, 2] OPs 19327M/ 848.06G mem 3.07 GB tm 895.77us/ 34.03ms (21576.27 GFLOPS, 173.83 GB/s) | |
| *** 224 E_1024_4_8_3_3_2n10 arg 2 sz [1024, 1, 1] [8, 4, 1] OPs 230M/ 867.38G mem 3.07 GB tm 6.64us/ 34.04ms (34643.28 GFLOPS, 4046.66 GB/s) | |
| *** 225 E_6144_32_3n21 arg 4 sz [6144, 1, 1] [32, 1, 1] OPs 2M/ 867.61G mem 3.07 GB tm 5.32us/ 34.04ms ( 443.48 GFLOPS, 886.95 GB/s) | |
| *** 226 r_36_32_2_16_4_1024_4_4_4_2n16 arg 3 sz [2, 32, 36] [4, 16, 1] OPs 38654M/ 867.62G mem 3.07 GB tm 1462.85us/ 35.50ms (26424.17 GFLOPS, 161.28 GB/s) | |
| *** 227 E_1024_32_3_3_4n6 arg 2 sz [1024, 1, 1] [32, 1, 1] OPs 460M/ 906.27G mem 3.07 GB tm 11.12us/ 35.52ms (41372.55 GFLOPS, 4832.70 GB/s) | |
| *** 228 E_12288_32_3n18 arg 4 sz [12288, 1, 1] [32, 1, 1] OPs 4M/ 906.73G mem 3.07 GB tm 9.80us/ 35.53ms ( 481.49 GFLOPS, 962.98 GB/s) | |
| *** 229 r_36_8_16_4_4_4_1024_4_4_2n12 arg 3 sz [16, 8, 36] [4, 4, 4] OPs 19327M/ 906.74G mem 3.07 GB tm 746.21us/ 36.27ms (25900.79 GFLOPS, 126.47 GB/s) | |
| *** 230 E_8192_32_3_3n12 arg 2 sz [8192, 1, 1] [32, 1, 1] OPs 920M/ 926.06G mem 3.07 GB tm 12.52us/ 36.28ms (73486.58 GFLOPS, 8583.91 GB/s) | |
| *** 231 E_24576_32_3n18 arg 4 sz [24576, 1, 1] [32, 1, 1] OPs 9M/ 926.98G mem 3.07 GB tm 18.88us/ 36.30ms ( 499.82 GFLOPS, 999.65 GB/s) | |
| *** 232 r_10_32_4_8_128_4n6 arg 3 sz [32, 10, 1] [8, 4, 1] OPs 10M/ 926.99G mem 3.07 GB tm 7.36us/ 36.31ms ( 1424.70 GFLOPS, 146.64 GB/s) | |
| *** 233 E_160_8_4n18 arg 4 sz [160, 1, 1] [8, 1, 1] OPs 0M/ 927.00G mem 3.07 GB tm 1.88us/ 36.31ms ( 10.89 GFLOPS, 21.79 GB/s) | |
| *** 234 E_96_4n20 arg 5 sz [96, 1, 1] [1, 1, 1] OPs 0M/ 927.00G mem 3.07 GB tm 1.92us/ 36.31ms ( 1.20 GFLOPS, 1.60 GB/s) | |
| *** 235 E_288_32_2n20 arg 5 sz [288, 1, 1] [32, 1, 1] OPs 0M/ 927.00G mem 3.07 GB tm 1.92us/ 36.32ms ( 57.60 GFLOPS, 76.80 GB/s) | |
| *** 236 E_384_32_3n25 arg 5 sz [384, 1, 1] [32, 1, 1] OPs 0M/ 927.00G mem 3.07 GB tm 2.20us/ 36.32ms ( 100.54 GFLOPS, 134.05 GB/s) | |
| *** 237 E_2304_32_2n21 arg 5 sz [2304, 1, 1] [32, 1, 1] OPs 0M/ 927.00G mem 3.07 GB tm 2.92us/ 36.32ms ( 302.99 GFLOPS, 403.99 GB/s) | |
| *** 238 E_6144_32_3n28 arg 5 sz [6144, 1, 1] [32, 1, 1] OPs 3M/ 927.01G mem 3.07 GB tm 6.00us/ 36.33ms ( 589.82 GFLOPS, 786.43 GB/s) | |
| *** 239 E_12288_32_3n31 arg 5 sz [12288, 1, 1] [32, 1, 1] OPs 7M/ 927.01G mem 3.07 GB tm 10.92us/ 36.34ms ( 648.16 GFLOPS, 864.21 GB/s) | |
| *** 240 E_24576_32_3n25 arg 5 sz [24576, 1, 1] [32, 1, 1] OPs 14M/ 927.02G mem 3.07 GB tm 8.48us/ 36.35ms ( 1669.31 GFLOPS, 2225.75 GB/s) | |
| *** 241 E_40_32_4n12 arg 5 sz [40, 1, 1] [32, 1, 1] OPs 0M/ 927.03G mem 3.07 GB tm 1.84us/ 36.35ms ( 16.70 GFLOPS, 22.26 GB/s) | |
| *** 242 E_n14 arg 2 sz [1, 1, 1] [1, 1, 1] OPs 0M/ 927.03G mem 3.07 GB tm 1.84us/ 36.35ms ( 0.00 GFLOPS, 0.00 GB/s) | |
| *** 243 E_n4 arg 4 sz [1, 1, 1] [1, 1, 1] OPs 0M/ 927.03G mem 3.07 GB tm 1.92us/ 36.35ms ( 0.01 GFLOPS, 0.01 GB/s) | |
| *** 244 E_n14 arg 2 sz [1, 1, 1] [1, 1, 1] OPs 0M/ 927.03G mem 3.07 GB tm 1.72us/ 36.35ms ( 0.00 GFLOPS, 0.00 GB/s) | |
| *** 245 E_n4 arg 4 sz [1, 1, 1] [1, 1, 1] OPs 0M/ 927.03G mem 3.07 GB tm 1.68us/ 36.36ms ( 0.01 GFLOPS, 0.01 GB/s) | |
| *** 246 E_256_4n14 arg 2 sz [256, 1, 1] [4, 1, 1] OPs 0M/ 927.03G mem 3.07 GB tm 1.84us/ 36.36ms ( 1.11 GFLOPS, 2.23 GB/s) | |
| *** 247 r_32_16_10_2n14 arg 5 sz [16, 32, 1] [10, 1, 1] OPs 0M/ 927.03G mem 3.07 GB tm 2.12us/ 36.36ms ( 28.98 GFLOPS, 22.22 GB/s) | |
| *** 248 r_64_4_4n10 arg 2 sz [1, 1, 1] [64, 1, 1] OPs 0M/ 927.03G mem 3.07 GB tm 2.36us/ 36.36ms ( 1.30 GFLOPS, 0.87 GB/s) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment