c0b273dac8
Remove xorInput parameter from ChaCha SIMD functions
...
We can use the input pointer directly after checking KeystreamOperation
2018-10-26 10:10:52 -04:00
61a696f710
Update comments
2018-10-26 04:26:18 -04:00
76ab8ffa4b
Update comments
2018-10-26 03:12:46 -04:00
c992fe98a9
Fix failed compile on Ubuntu with -msse2
...
Also see https://github.com/noloader/cryptopp-cmake/issues/36
2018-10-26 02:43:35 -04:00
99c65bdb35
Rename ARM Shuffle() to Extract()
...
Extract() is the equivalent to SSE's _mm_shuffle_epi32(), but ARM naming calls it vector extract
2018-10-26 00:44:10 -04:00
d3a3189ba3
Sync CRYPTOPP_ARM_ACLE_AVAILABLE with Autotools
2018-10-25 14:08:09 -04:00
b4b3623938
Whitespace check-in
2018-10-25 12:15:33 -04:00
b1050636a6
Add ChaCha NEON implementation
2018-10-25 12:08:32 -04:00
babdf8b38b
Add XOP aware CHAM and LEA
2018-10-24 17:12:03 -04:00
ed4d57cecb
Add XOP aware ChaCha
...
ChaCha is about 50% faster using XOP for the rotates on AMD machines
2018-10-24 16:15:13 -04:00
b4c4c5aa14
Add SSSE3 rotates when available
...
This change obtains the remaining 0.1 to 0.15 cpb. It should be engaged with -march=native
2018-10-24 15:34:54 -04:00
18dcbdf514
Move input xor to ChaCha_OperateKeystream_SSE2
...
This picks up about 0.2 cpb in ChaCha::OperateKeystream. It may not sound like much but it puts SSE2 intrinsics version on par with the ASM version of Salsa20. Salsa20 leads ChaCha by 0.1 to 0.15 cpb, which equates to about 50 MB/s.
2018-10-24 11:00:35 -04:00
d230999b40
Fix ChaCha compile on ARM and MIPS
2018-10-24 01:11:45 -04:00
6a5d2ab03d
Remove unneeded params from ChaCha_OperateKeystream_SSE2
2018-10-23 08:52:29 -04:00
916c4484a2
Add ChaCha SSE2 implementation
...
Thanks to Jack Lloyd and Botan for allowing us to use the implementation.
The numbers for SSE2 are very good. When compared with Salsa20 ASM the results are:
* Salsa20 2.55 cpb; ChaCha/20 2.90 cpb
* Salsa20/12 1.61 cpb; ChaCha/12 1.90 cpb
* Salsa20/8 1.34 cpb; ChaCha/8 1.5 cpb
2018-10-23 07:57:59 -04:00
Jeffrey Walton