delta/cryptopp-git.git/ppc-simd.cpp, branch master github.com: weidai11/cryptopp.git Rename files with dashes to underscores (GH #736) 2018-11-10T13:00:14+00:00 Jeffrey Walton noloader@gmail.com 2018-11-10T13:00:14+00:00 896225069db7f34e752dd7b7bb401052c6b7cb17 Also see https://groups.google.com/forum/#!topic/cryptopp-users/HBz-6gZZFOA on the mailing list 
Also see https://groups.google.com/forum/#!topic/cryptopp-users/HBz-6gZZFOA on the mailing list
Rework Makefile and ppc-simd.h for XLC and LLVM front-end changes 2018-08-05T09:39:42+00:00 Jeffrey Walton noloader@gmail.com 2018-08-05T09:39:42+00:00 1dd0e321a6e092c0472b36d75ea06bfa3750b281 






Update comments
2018-08-03T20:16:08+00:00

Jeffrey Walton
noloader@gmail.com

2018-08-03T20:16:08+00:00

9ce1648f8387e24dc8c6e411cef151291bde36f7












Rework PPC probes for XLC and LLVM
2018-08-03T11:02:27+00:00

Jeffrey Walton
noloader@gmail.com

2018-08-03T11:02:27+00:00

4540ab4f109bdd232521dc97c5cfc998d96c0b39












Rework PPC probes for XLC and LLVM
2018-08-03T06:54:50+00:00

Jeffrey Walton
noloader@gmail.com

2018-08-03T06:54:50+00:00

7e14cab8a3a82149eb17d10677124f28f960a29e












Improve CPU_ProbePower8() test
2018-08-03T05:27:39+00:00

Jeffrey Walton
noloader@gmail.com

2018-08-03T05:27:39+00:00

c4eb38b856f420325889f40afe3c8c3621e66c8a












Squash MS LNK4221 and libtool warnings
2018-07-06T05:22:38+00:00

Jeffrey Walton
noloader@gmail.com

2018-07-06T05:22:38+00:00

0cee6f01f010a6d0721f26652d41acb219adbd86












Remove extra ; from ppc-simd.cpp (PR #620)
2018-03-31T17:06:44+00:00

Ilja
ilja.honkonen@fmi.fi

2018-03-31T17:06:44+00:00

f035ad7187ce4795e04a3536eadea3d59f01f345












Fix SHA feature detection on AIX
2018-03-05T12:05:12+00:00

Jeffrey Walton
noloader@gmail.com

2018-03-05T12:05:12+00:00

626c86987bd19bac09b41aedc0bc29c295e866d0

This one should have been fixed before the Crypto++ 6.1 release. Its no big deal, however. Power8 accelerated SHA-256 is 1.5x to 2x slower than straight C++. SHA-512 may be better, but the implementation is not ready to performance test.





This one should have been fixed before the Crypto++ 6.1 release. Its no big deal, however. Power8 accelerated SHA-256 is 1.5x to 2x slower than straight C++. SHA-512 may be better, but the implementation is not ready to performance test.







Use x86 highest basic before calling a leaf function
2018-01-11T22:59:24+00:00

Jeffrey Walton
noloader@gmail.com

2018-01-11T22:59:24+00:00

788cd1794dc39e382eb6612aa256918d8e0d3a55

This was a latent bug that just surfaced on a Sun Core2 workstation. RDSEED caused an illegal instruction exception on the Core2. It seems we managed to miss it because old processors had family and stepping values so low they never set CPUID.EBX.RDSEED[bit 18] = 1. Newer processors had the feature so CPUID.EBX.RDSEED[bit 18] = 1 was accurate.





This was a latent bug that just surfaced on a Sun Core2 workstation. RDSEED caused an illegal instruction exception on the Core2. It seems we managed to miss it because old processors had family and stepping values so low they never set CPUID.EBX.RDSEED[bit 18] = 1. Newer processors had the feature so CPUID.EBX.RDSEED[bit 18] = 1 was accurate.