aae108d228
Fix PowerPC-64 detection using Clang
2018-11-18 01:52:42 -05:00
889c98b9af
Add Newlib test
2018-11-17 15:50:04 -05:00
0564266151
Cleanup makefile
2018-11-17 15:28:30 -05:00
c4c413e3f3
Drop GCM to POWER7 if POWER8 unavailable
2018-11-17 00:47:17 -05:00
bbc5c63d33
Drop GCM to POWER7 on PowerPC
...
GCM can do some bulk XOR's using the SIMD unit. However, we still need loads and stores to be fast. Fast loads and stores of unaligned data requires the VSX unit
2018-11-17 00:41:49 -05:00
4f86bcc39d
Remove -qxlcompatmacros after Commit 96d3fa208e
2018-11-14 20:18:56 -05:00
7bd02896a0
Fix XLC flags with LLVM front-end
2018-11-14 20:01:05 -05:00
7c9858f89c
Cleanup PowerPC and XLC feature tests
2018-11-14 08:19:39 -05:00
fc1e98e70d
Make feature test output filename configurable (PR #737 , GH #738 )
2018-11-13 14:02:40 -05:00
e69106f257
Add "Invalid mnemonic" to bad result on PPC
2018-11-13 01:57:12 -05:00
9550ccc9a3
Port SIMON64 to Altivec
...
SIMON64 runs about 4x faster than C++ for POWER4 and friends. If POWER7 is available it goes back to full speed due to efficient unaligned loads
2018-11-12 21:51:11 -05:00
a0608a6b80
Port SPECK64 to Altivec
...
SPECK64 runs about 4x faster than C++ for POWER4 and friends. If POWER7 is available it goes back to full speed due to efficient unaligned loads
2018-11-12 20:56:15 -05:00
cac97f041d
Rename PPC feature tests to test_ppc_xxx.cxx (PR #737 )
2018-11-12 15:43:01 -05:00
ff212dae3e
Rename x86 feature tests to test_x86_xxx.cxx (PR #737 )
2018-11-12 15:37:14 -05:00
41639e5ec6
Fix ARM A-32 and Aarch64 feature tests (PR #737 )
2018-11-12 14:59:36 -05:00
886fd7903d
Remove wildcard from a.out clean recipe
2018-11-12 05:25:01 -05:00
a0f3744ed4
Use __cpp_lib_uncaught_exceptions for CRYPTOPP_CXX17_EXCEPTIONS
...
Also see https://bugs.llvm.org/show_bug.cgi?id=39631
2018-11-12 03:37:32 -05:00
499a5e289d
Remove a.out artifacts whenever feature tests run (GH #738 )
2018-11-12 01:57:09 -05:00
f91584a7bc
Remove a.out artifacts on OS X during clean (GH #738 )
2018-11-12 00:56:54 -05:00
4e404cceeb
Fix incorrect Macport compiler detection (GH #738 )
2018-11-11 13:44:39 -05:00
b163176f82
Fix missing 'no such instruction' in assembler messages (GH #738 )
2018-11-11 13:35:03 -05:00
de75959fd7
Move HAS_NEWLIB down to _XOPEN_SOURCE test
2018-11-11 11:54:58 -05:00
40da78e5ad
Cleanup GNUmakefile (PR #737 )
2018-11-11 09:59:55 -05:00
213569a46d
Remove Darwin requirement for Port compilers
...
I seem to recall someone used one on Linux at one time
2018-11-11 07:53:49 -05:00
6e94562c52
Move to feature-based availability testing in Makefile (PR #737 )
2018-11-11 01:14:43 -05:00
896225069d
Rename files with dashes to underscores (GH #736 )
...
Also see https://groups.google.com/forum/#!topic/cryptopp-users/HBz-6gZZFOA on the mailing list
2018-11-10 08:00:14 -05:00
aa1d0a5129
Lower Binutil version to 2.23 for AVX
2018-11-08 19:03:33 -05:00
d9011f07d2
Add ChaCha AVX2 implementation (GH #735 )
2018-11-08 16:20:31 -05:00
5dca85b819
Split Blake2 SIMD files into blake2s-simd.cpp and blake2b-simd.cpp (GH #729 , GH #731 )
...
The split was required for Blake2b and Power8; Blake2s only requires Power7
2018-11-02 19:09:36 -04:00
659c0c113c
Add BLAKE2b Power8 implementation (GH #729 )
2018-10-30 06:20:31 -04:00
81db4ea5e3
Switch to pch.cpp for compile tests.
...
adhoc.cpp was a bit uncomfortable because we had to copy it out from adhoc.cpp.proto. For some reason CMake could not perform the copy, so we started using pch.cpp in CMake. This commit keeps them consistent.
We may have problems with one test, and that is the Newlib tests. I seem to recall they a C++ header included to properly identify its use. We cross that bridge during MinGW testing.
2018-10-29 08:41:54 -04:00
d7d76fa5f7
Add ChaCha Power8 implementation
2018-10-27 08:40:07 -04:00
21d69598ab
Add CRYPTOPP_DISABLE_ASM to dependency recipe
...
This stops the inclusion of SSE headers without arch options that break the recipe
2018-10-26 11:10:07 -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
b51faab9b3
Update comments in GNU Makefile
2018-09-09 03:44:50 -04:00
03297cdfa6
Add -xregs=no%appl for SunCC on Sparc
2018-09-09 03:01:10 -04:00
243673c32a
Add notes on -stdlib=libc++ for MacOS
2018-08-24 04:43:12 -04:00
f3238742b2
Fix compile with IBM XLC
...
-pthread was causing "xlC: 1501-210 (W) command option t contains an incorrect subargument"
2018-08-23 04:56:45 -04:00
899236b99c
Tweak Makefile test to compile but not link (GH #707 )
2018-08-21 06:28:28 -04:00
5489cfe3c6
Remove Asan workaround from VMAC
...
I was not able to duplicate it under GCC. That includes the GCC's supplied with Debian 8 and Ubuntu 14. It looks like the problem was with Asan insread of the library
2018-08-19 08:32:23 -04:00
5e3f38cf86
Allow previous version of shared library on Solaris
2018-08-19 07:04:19 -04:00
3e23c55885
Remove makefile debug print statements
2018-08-19 06:12:09 -04:00
9886b555d0
Add SONAME to shared object for Solaris
...
Also see https://blogs.oracle.com/solaris/how-to-name-a-solaris-shared-object-v2
2018-08-19 06:10:30 -04:00
964b92b614
Rework -pthread test for GCC on Solaris
...
It looks like GCC is rejecting the -pthread option but it is advertising Pthread support by defining 39 related macros. I'm not sure what to make of it, but we can't use -pthread because it breaks the compile.
2018-08-18 23:51:14 -04:00
ea05f2fefd
Fix build for MinGW due to deleted winpipes.cpp ( #705 )
...
On my MinGW-w64 setup, the build failed:
>mingw32-make: *** No rule to make target 'winpipes.o', needed by 'libcryptopp.a'.
>mingw32-make: Target 'default' not remade because of errors.
Looks like `winpipes.cpp` was removed in f2171cbe2
2018-08-18 11:17:50 -04:00
7a43a04048
Split simon-simd.cpp and speck-simd.cpp into separate source files
...
SIMON-64 and SIMON-128 have different ISA requirements. The same applies to SPECK-64 and SPECK-128. GCC generated code that resulted in a SIGILL due to the ISA differences on a down level machine. The instructions was a mtfprwz from POWER8. It was prsent in a function prologue on a POWER7 machine.
2018-08-15 09:59:40 -04:00
6c621f91ce
Add POWER8 SIMON-128 implementation
...
Performance went from about 30 to 40 cpb to 5.5 to 9 cpb, depending on endian-ness
2018-08-12 09:21:09 -04:00
898dab99b8
Add POWER8 SPECK-128 implementation
...
Performance went from about 14 cpb to 2-3 cpb, depending on endian-ness
2018-08-12 04:08:33 -04:00
d4428d7f1c
Add VectorLoad and VectorStore test code
...
Applies to POWER4 and above only
2018-08-06 22:19:59 -04:00
58b7abe106
Update comments
2018-08-05 12:32:36 -04:00
Jeffrey Walton
Tanzinul Islam