- GPU: NVIDIA A100-SXM4-40GB
- Block size: 512
- --------------------------------------
-
- Code version: V0
- Total Mem-xch Sorting
- Q20: 8733 [usec] 5649 [usec] 3134 [usec]
- Q21: 12 [msec] 8329 [usec] 4105 [usec]
- Q22: 59 [msec] 53 [msec] 6074 [usec]
- Q23: 37 [msec] 22 [msec] 14 [msec]
- Q24: 56 [msec] 26 [msec] 29 [msec]
- Q25: 98 [msec] 39 [msec] 59 [msec]
- Q26: 229 [msec] 102 [msec] 120 [msec]
- Q27: 420 [msec] 164 [msec] 256 [msec]
- Q28: 976 [msec] 429 [msec] 554 [msec]
- Q29: 1910 [msec] 745 [msec] 1164 [msec]
- Q30: 3971 [msec] 1521 [msec] 2453 [msec]
-
- Code version: V1
- Total Mem-xch Sorting
- Q20: 2676 [usec] 1254 [usec] 1417 [usec]
- Q21: 6308 [usec] 4098 [usec] 2193 [usec]
- Q22: 10 [msec] 6454 [usec] 3699 [usec]
- Q23: 18 [msec] 10 [msec] 8329 [usec]
- Q24: 34 [msec] 17 [msec] 17 [msec]
- Q25: 83 [msec] 45 [msec] 37 [msec]
- Q26: 134 [msec] 63 [msec] 71 [msec]
- Q27: 331 [msec] 177 [msec] 153 [msec]
- Q28: 664 [msec] 318 [msec] 351 [msec]
- Q29: 1364 [msec] 621 [msec] 742 [msec]
- Q30: 2938 [msec] 1384 [msec] 1556 [msec]
-
- Code version: V2
- Total Mem-xch Sorting
- Q20: 2883 [usec] 1307 [usec] 1574 [usec]
- Q21: 5861 [usec] 3444 [usec] 2411 [usec]
- Q22: 12 [msec] 8167 [usec] 4134 [usec]
- Q23: 21 [msec] 12 [msec] 8940 [usec]
- Q24: 34 [msec] 15 [msec] 19 [msec]
- Q25: 86 [msec] 45 [msec] 40 [msec]
- Q26: 135 [msec] 59 [msec] 76 [msec]
- Q27: 331 [msec] 167 [msec] 163 [msec]
- Q28: 749 [msec] 371 [msec] 372 [msec]
- Q29: 1459 [msec] 666 [msec] 788 [msec]
- Q30: 3063 [msec] 1409 [msec] 1650 [msec]
|
