summaryrefslogtreecommitdiff
path: root/gcm_simd.cpp
Commit message (Collapse)AuthorAgeFilesLines
* Fix SIGIL on PowerPC during cpu feature probes (GH #1115)Jeffrey Walton2022-03-291-53/+0
| | | | Also see GH #1112
* Move UINT64_CAST to config_asm.hJeffrey Walton2021-05-231-9/+1
|
* Move M128_CAST and CONST_M128_CAST to config_asm.hJeffrey Walton2021-04-201-2/+0
|
* Clear elevated warnings on Apple M1Jeffrey Walton2021-03-061-11/+13
|
* Fix polynomial multiply detection on PPC64Jeffrey Walton2020-04-061-1/+1
|
* Restore SIGILL handler if sigprocmask failsJeffrey Walton2020-02-171-0/+6
| | | | We've never encountered this case, but better safe then sorry.
* Rename VecPolyMultiplyLE to VecIntelMultiply (PR #908)Jeffrey Walton2019-10-261-19/+19
| | | The LE multiplies are compatible with Intel's _mm_clmulepi64_si128
* Fix ARM headers and Android compile (PR #896)Jeffrey Walton2019-10-161-3/+2
| | | | | | | | | | | * Test fix ARM headers This problem has been festering for some time. The header file includes are slightly different than the ISA options. Some platforms need an include, others don't. * Fix cryptest-android.sh and cryptest-ios.sh * Fix MSVC ARM32 and ARM64 compile * Split ARM32 and ARM64 recipes in GNUmakefile
* Update commentsJeffrey Walton2019-07-211-1/+1
|
* Fix crash in GCM mode on ARM with -mthumbJeffrey Walton2019-05-211-8/+1
|
* Use PowerPC unaligned loads and stores with Power8 (GH #825, PR #826)Jeffrey Walton2019-04-271-3/+3
| | | Use PowerPC unaligned loads and stores with Power8. Formerly we were using Power7 as the floor because the IBM POWER Architecture manuals said unaligned loads and stores were available. However, some compilers generate bad code for unaligned loads and stores using `-march=power7`, so bump to a known good.
* Fix self test failure with IBM XL C/C++ on AIXJeffrey Walton2019-01-221-3/+4
|
* Update CPU_ProbePMULL testJeffrey Walton2019-01-201-9/+15
|
* Add VecPolyMultiply for Intel-equivalent F2N multipliesJeffrey Walton2019-01-201-116/+21
|
* Use carryless multiplies for NIST b233 and k233 curves (GH #783, PR #784)Jeffrey Walton2019-01-161-142/+23
| | | Use carryless multiplies for NIST b233 and k233 curves.
* Fix GCM ARM64 compile with MSVC compiler (GH #776)Jeffrey Walton2019-01-041-64/+88
|
* Fix <arm_neon.h> include for ARM64 with MSVC compiler (GH #776)Jeffrey Walton2019-01-041-1/+2
|
* Update comments in config.hJeffrey Walton2018-12-091-1/+1
| | | | | Some comments in config.h were old. Time for a refresh. Switch from CRYPTOPP_BOOL_ARM64 to CRYPTOPP_BOOL_ARMV8. Aarch32 is ARMv8, and that's the important part.
* Add separate Polynomial Multiply feature test on POWER8 (GH#742)Jeffrey Walton2018-11-191-1/+1
|
* Fix LLVM Clang compile on PowerPCJeffrey Walton2018-11-191-5/+16
|
* Drop GCM to POWER7 on PowerPCJeffrey Walton2018-11-171-2/+2
| | | | 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
* Rename PPC vector functions from VectorFunc to VecFuncJeffrey Walton2018-11-151-68/+68
|
* Add Octet suffix for vec_sldJeffrey Walton2018-11-141-1/+1
| | | | We need to make room for packed shifts and rotates
* Add Octet suffix for vec_sldJeffrey Walton2018-11-141-5/+5
| | | | We need to make room for packed shifts and rotates
* Fix compile when using XLC with LLVM front-end without -qxlcompatmacrosJeffrey Walton2018-11-141-4/+4
|
* Rename files with dashes to underscores (GH #736)Jeffrey Walton2018-11-101-0/+915
Also see https://groups.google.com/forum/#!topic/cryptopp-users/HBz-6gZZFOA on the mailing list