Attila Fülöp 5b3b79559c ICP: gcm-avx: Support architectures lacking the MOVBE instruction ... There are a couple of x86_64 architectures which support all needed features to make the accelerated GCM implementation work but the MOVBE instruction. Those are mainly Intel Sandy- and Ivy-Bridge and AMD Bulldozer, Piledriver, and Steamroller. By using MOVBE only if available and replacing it with a MOV followed by a BSWAP if not, those architectures now benefit from the new GCM routines and performance is considerably better compared to the original implementation. Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Adam D. Moss <c@yotes.com> Signed-off-by: Attila Fülöp <attila@fueloep.org> Followup #9749 Closes #10029		2020-03-17 10:24:38 -07:00
..
avl	Wrap Linux module macros	2019-11-01 10:41:03 -07:00
icp	ICP: gcm-avx: Support architectures lacking the MOVBE instruction	2020-03-17 10:24:38 -07:00
lua	cppcheck: (error) Address of local auto-variable assigned	2019-12-18 17:25:42 -08:00
nvpair	cppcheck: (warning) Possible null pointer dereference: nvh	2019-12-18 17:25:57 -08:00
os	dmu_objset_from_ds must be called with dp_config_rwlock held	2020-03-12 10:55:02 -07:00
spl	OpenZFS restructuring - move platform specific sources	2019-09-06 11:26:26 -07:00
unicode	Wrap Linux module macros	2019-11-01 10:41:03 -07:00
zcommon	Change default to overlay=on	2020-03-06 09:28:19 -08:00
zfs	Improve zfs receive performance by batching writes	2020-03-16 11:51:56 -07:00
.gitignore	Adapt gitignore for modules	2019-12-02 13:23:47 -08:00
Makefile.in	module/Makefile.in: don't run xargs if empty	2019-10-08 10:10:23 -07:00