diff options
| author | Gvozden Neskovic <[email protected]> | 2016-07-06 13:42:04 +0200 |
|---|---|---|
| committer | Brian Behlendorf <[email protected]> | 2016-08-16 14:11:14 -0700 |
| commit | 70b258fc962fd40673b9a47574cb83d8438e7d94 (patch) | |
| tree | 6e45c08b144622dc78f1106681ce5566c77b588d /cmd | |
| parent | 32ffaa3de58981814342fe6d3556c03d41d121f8 (diff) | |
Fletcher4 implementation using avx512f instruction set
Algorithm runs 8 parallel sums, consuming 8x uint32_t elements per
loop iteration. Size alignment of main fletcher4 methods is adjusted
accordingly. New implementation is called 'avx512f'.
Note: byteswap method can be implemented more efficiently when avx512bw hardware
becomes available. Currently, it is ~ 2x slower than native method.
Table shows result of full (native) fletcher4 calculation for different buffer size:
fletcher4 4KB 16KB 64KB 128KB 256KB 1MB 16MB
--------------------------------------------------------------------
[scalar] 1213 1228 1231 1231 1225 1200 1160
[sse2] 2374 2442 2459 2456 2462 2250 2220
[avx2] 4288 4753 4871 4893 4900 4050 3882
[avx512f] 5975 8445 9196 9221 9262 6307 5620
Signed-off-by: Gvozden Neskovic <[email protected]>
Signed-off-by: Brian Behlendorf <[email protected]>
Issue #4952
Diffstat (limited to 'cmd')
0 files changed, 0 insertions, 0 deletions