Ard Biesheuvel 2fe55987b2
crypto: arm64/chacha - use combined SIMD/ALU routine for more speed ...
To some degree, most known AArch64 micro-architectures appear to be
able to issue ALU instructions in parellel to SIMD instructions
without affecting the SIMD throughput. This means we can use the ALU
to process a fifth ChaCha block while the SIMD is processing four
blocks in parallel.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2018-12-13 18:24:55 +08:00
2016-11-29 16:06:56 +08:00
2018-08-07 17:26:23 +08:00
2018-03-16 23:35:54 +08:00
2017-11-29 17:33:30 +11:00
2017-11-29 17:33:30 +11:00
2017-11-02 11:10:55 +01:00
2018-09-21 13:24:50 +08:00
2018-01-18 23:00:30 +11:00
2017-01-13 00:26:49 +08:00
2017-08-04 09:27:21 +08:00
2018-10-08 13:47:02 +08:00
2018-10-12 14:20:45 +08:00
2018-09-21 13:24:50 +08:00
2018-05-12 00:13:09 +08:00
2018-03-16 23:35:55 +08:00
2018-12-13 18:24:55 +08:00
2018-12-13 18:24:55 +08:00
2018-09-04 11:37:04 +08:00
2018-09-04 11:37:04 +08:00
2018-08-07 17:51:40 +08:00
2018-08-25 19:50:43 +08:00
2018-12-13 18:24:37 +08:00
2018-12-13 18:24:36 +08:00
2018-12-13 18:24:35 +08:00
2018-12-13 18:24:35 +08:00
2018-05-12 00:13:05 +08:00
2018-07-09 00:30:24 +08:00
2018-05-12 00:13:06 +08:00
2018-07-09 00:30:24 +08:00
2018-05-12 00:13:11 +08:00
2018-07-09 00:30:24 +08:00
2018-05-31 00:13:44 +08:00
2018-07-27 19:16:38 +08:00
2018-05-31 00:13:44 +08:00
2018-05-12 00:13:12 +08:00
2018-07-09 00:30:24 +08:00
2018-05-31 00:13:44 +08:00
2018-07-09 00:30:24 +08:00
2018-01-26 01:10:35 +11:00
2018-07-09 00:30:24 +08:00
2018-05-05 14:52:53 +08:00
2018-08-25 19:50:41 +08:00
2fe55987b2