Gvozden Neskovic 70b258fc96 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 <neskovic@gmail.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Issue #4952		2016-08-16 14:11:14 -07:00
..
Makefile.am	Initial attempt to document events and payloads.	2014-07-25 11:58:36 -07:00
vdev_id.conf.5	Add extra keyword 'slot' to vdev_id.conf	2015-08-30 10:03:56 -07:00
zfs-events.5	Man page white space and spelling corrections	2015-12-18 13:33:37 -08:00
zfs-module-parameters.5	Fletcher4 implementation using avx512f instruction set	2016-08-16 14:11:14 -07:00
zpool-features.5	Implement large_dnode pool feature	2016-06-24 13:13:21 -07:00