Advertisement
Falvyu

highway/bench_sort - Perf on Zen 4 (7700X) [with FIX]

Feb 17th, 2023
26
0
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 6.43 KB | Software | 0 0
  1. Running main() from gmock_main.cc
  2. [==========] Running 15 tests from 1 test suite.
  3. [----------] Global test environment set-up.
  4. [----------] 15 tests from BenchSortGroup/BenchSort
  5. [ RUN ] BenchSortGroup/BenchSort.BenchAllPartition/AVX3
  6. AVX3: vq: f32: uniform8: 1.05E+06 43273 MB/s ( 1 threads)
  7. AVX3: vq: i32: uniform8: 1.05E+06 43322 MB/s ( 1 threads)
  8. AVX3: vq: i64: uniform8: 1.05E+06 40729 MB/s ( 1 threads)
  9. AVX3: vq: U128: uniform8: 5.24E+05 30218 MB/s ( 1 threads)
  10. AVX3: vq: KV128: uniform8: 5.24E+05 32933 MB/s ( 1 threads)
  11. [ OK ] BenchSortGroup/BenchSort.BenchAllPartition/AVX3 (1031 ms)
  12. [ RUN ] BenchSortGroup/BenchSort.BenchAllPartition/AVX2
  13. AVX2: vq: f32: uniform8: 1.05E+06 31346 MB/s ( 1 threads)
  14. AVX2: vq: i32: uniform8: 1.05E+06 31908 MB/s ( 1 threads)
  15. AVX2: vq: i64: uniform8: 1.05E+06 29761 MB/s ( 1 threads)
  16. AVX2: vq: U128: uniform8: 5.24E+05 19068 MB/s ( 1 threads)
  17. AVX2: vq: KV128: uniform8: 5.24E+05 23330 MB/s ( 1 threads)
  18. [ OK ] BenchSortGroup/BenchSort.BenchAllPartition/AVX2 (1511 ms)
  19. [ RUN ] BenchSortGroup/BenchSort.BenchAllPartition/SSE4
  20. SSE4: vq: f32: uniform8: 1.05E+06 16346 MB/s ( 1 threads)
  21. SSE4: vq: i32: uniform8: 1.05E+06 16364 MB/s ( 1 threads)
  22. SSE4: vq: i64: uniform8: 1.05E+06 14913 MB/s ( 1 threads)
  23. SSE4: vq: U128: uniform8: 5.24E+05 10715 MB/s ( 1 threads)
  24. SSE4: vq: KV128: uniform8: 5.24E+05 12869 MB/s ( 1 threads)
  25. [ OK ] BenchSortGroup/BenchSort.BenchAllPartition/SSE4 (2546 ms)
  26. [ RUN ] BenchSortGroup/BenchSort.BenchAllPartition/SSSE3
  27. [ OK ] BenchSortGroup/BenchSort.BenchAllPartition/SSSE3 (0 ms)
  28. [ RUN ] BenchSortGroup/BenchSort.BenchAllPartition/EMU128
  29. EMU128: vq: f32: uniform8: 1.05E+06 1210 MB/s ( 1 threads)
  30. EMU128: vq: i32: uniform8: 1.05E+06 1473 MB/s ( 1 threads)
  31. EMU128: vq: i64: uniform8: 1.05E+06 2966 MB/s ( 1 threads)
  32. EMU128: vq: U128: uniform8: 5.24E+05 10107 MB/s ( 1 threads)
  33. EMU128: vq: KV128: uniform8: 5.24E+05 14222 MB/s ( 1 threads)
  34. [ OK ] BenchSortGroup/BenchSort.BenchAllPartition/EMU128 (6653 ms)
  35. [ RUN ] BenchSortGroup/BenchSort.BenchAllBase/AVX3
  36. AVX3: vq: f32: uniform32: 1.54E+05 6761 MB/s ( 1 threads)
  37. AVX3: vq: i64: uniform32: 7.68E+04 9767 MB/s ( 1 threads)
  38. AVX3: vq: U128: uniform32: 3.84E+04 5429 MB/s ( 1 threads)
  39. [ OK ] BenchSortGroup/BenchSort.BenchAllBase/AVX3 (8 ms)
  40. [ RUN ] BenchSortGroup/BenchSort.BenchAllBase/AVX2
  41. AVX2: vq: f32: uniform32: 7.68E+04 7747 MB/s ( 1 threads)
  42. AVX2: vq: i64: uniform32: 3.84E+04 8223 MB/s ( 1 threads)
  43. AVX2: vq: U128: uniform32: 1.92E+04 8674 MB/s ( 1 threads)
  44. [ OK ] BenchSortGroup/BenchSort.BenchAllBase/AVX2 (3 ms)
  45. [ RUN ] BenchSortGroup/BenchSort.BenchAllBase/SSE4
  46. [ OK ] BenchSortGroup/BenchSort.BenchAllBase/SSE4 (0 ms)
  47. [ RUN ] BenchSortGroup/BenchSort.BenchAllBase/SSSE3
  48. [ OK ] BenchSortGroup/BenchSort.BenchAllBase/SSSE3 (0 ms)
  49. [ RUN ] BenchSortGroup/BenchSort.BenchAllBase/EMU128
  50. EMU128: vq: f32: uniform32: 3.84E+04 354 MB/s ( 1 threads)
  51. EMU128: vq: i64: uniform32: 1.92E+04 5355 MB/s ( 1 threads)
  52. EMU128: vq: U128: uniform32: 9.60E+03 4520 MB/s ( 1 threads)
  53. [ OK ] BenchSortGroup/BenchSort.BenchAllBase/EMU128 (14 ms)
  54. [ RUN ] BenchSortGroup/BenchSort.BenchAllSort/AVX3
  55. AVX3: std: f32: uniform32: 1.00E+06 76 MB/s ( 1 threads)
  56. AVX3: heap: f32: uniform32: 1.00E+06 45 MB/s ( 1 threads)
  57. AVX3: vq: f32: uniform32: 1.00E+06 1508 MB/s ( 1 threads)
  58. AVX3: std: i32: uniform32: 1.00E+06 109 MB/s ( 1 threads)
  59. AVX3: heap: i32: uniform32: 1.00E+06 57 MB/s ( 1 threads)
  60. AVX3: vq: i32: uniform32: 1.00E+06 1750 MB/s ( 1 threads)
  61. AVX3: std: i64: uniform32: 1.00E+06 217 MB/s ( 1 threads)
  62. AVX3: heap: i64: uniform32: 1.00E+06 101 MB/s ( 1 threads)
  63. AVX3: vq: i64: uniform32: 1.00E+06 1725 MB/s ( 1 threads)
  64. AVX3: std: U128: uniform32: 1.00E+06 340 MB/s ( 1 threads)
  65. AVX3: heap: U128: uniform32: 1.00E+06 119 MB/s ( 1 threads)
  66. AVX3: vq: U128: uniform32: 1.00E+06 1126 MB/s ( 1 threads)
  67. AVX3: std: KV128: uniform32: 1.00E+06 404 MB/s ( 1 threads)
  68. AVX3: heap: KV128: uniform32: 1.00E+06 132 MB/s ( 1 threads)
  69. AVX3: vq: KV128: uniform32: 1.00E+06 1347 MB/s ( 1 threads)
  70. [ OK ] BenchSortGroup/BenchSort.BenchAllSort/AVX3 (22672 ms)
  71. [ RUN ] BenchSortGroup/BenchSort.BenchAllSort/AVX2
  72. AVX2: vq: f32: uniform32: 1.00E+06 1150 MB/s ( 1 threads)
  73. AVX2: vq: i32: uniform32: 1.00E+06 1281 MB/s ( 1 threads)
  74. AVX2: vq: i64: uniform32: 1.00E+06 1113 MB/s ( 1 threads)
  75. AVX2: vq: U128: uniform32: 1.00E+06 899 MB/s ( 1 threads)
  76. AVX2: vq: KV128: uniform32: 1.00E+06 1110 MB/s ( 1 threads)
  77. [ OK ] BenchSortGroup/BenchSort.BenchAllSort/AVX2 (1538 ms)
  78. [ RUN ] BenchSortGroup/BenchSort.BenchAllSort/SSE4
  79. [ OK ] BenchSortGroup/BenchSort.BenchAllSort/SSE4 (0 ms)
  80. [ RUN ] BenchSortGroup/BenchSort.BenchAllSort/SSSE3
  81. [ OK ] BenchSortGroup/BenchSort.BenchAllSort/SSSE3 (0 ms)
  82. [ RUN ] BenchSortGroup/BenchSort.BenchAllSort/EMU128
  83. EMU128: vq: f32: uniform32: 1.00E+06 47 MB/s ( 1 threads)
  84. EMU128: vq: i32: uniform32: 1.00E+06 70 MB/s ( 1 threads)
  85. EMU128: vq: i64: uniform32: 1.00E+06 155 MB/s ( 1 threads)
  86. EMU128: vq: U128: uniform32: 1.00E+06 312 MB/s ( 1 threads)
  87. EMU128: vq: KV128: uniform32: 1.00E+06 552 MB/s ( 1 threads)
  88. [ OK ] BenchSortGroup/BenchSort.BenchAllSort/EMU128 (8471 ms)
  89. [----------] 15 tests from BenchSortGroup/BenchSort (44451 ms total)
  90.  
  91. [----------] Global test environment tear-down
  92. [==========] 15 tests from 1 test suite ran. (44451 ms total)
  93. [ PASSED ] 15 tests.
  94.  
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement