Frank Denis 9b386bda33 std/crypto: add a vectorized ChaCha20 implementation
Brings a 30% speed boost on x86_64 even though we still process only
one block at a time for now.

Only enabled on x86_64 since the non-vectorized implementation seems
to currently perform better on some architectures (at least on aarch64).

But the non-vectorized implementation still gets a little speed boost
as well (~17%) with these changes.
2020-10-10 22:45:41 +02:00
..
2020-09-11 20:02:41 -04:00
2020-10-07 04:34:09 -04:00
2020-10-07 00:39:13 -07:00
2020-10-09 22:16:48 -04:00
2020-10-06 22:08:25 -06:00
2020-09-04 05:15:03 +03:00
2020-09-11 20:02:41 -04:00
2020-10-06 00:00:33 +02:00
2020-10-07 04:34:09 -04:00
2020-10-09 16:45:39 -07:00
2020-10-07 17:04:48 -04:00
2020-09-24 22:06:41 +02:00
2020-09-04 22:49:14 +03:00