mirror of
https://git.tukaani.org/xz.git
synced 2024-04-04 12:36:23 +02:00
liblzma: Set the MSVC optimization fix to only cover lzma_crc64_clmul().
After testing a 32-bit Release build on MSVC, only lzma_crc64_clmul() has the bug. crc_simd_body() and lzma_crc32_clmul() do not need the optimizations disabled.
This commit is contained in:
parent
5ce0f7a48b
commit
1c8884f0af
1 changed files with 15 additions and 15 deletions
|
@ -42,21 +42,6 @@
|
||||||
MASK_H(in, mask, high)
|
MASK_H(in, mask, high)
|
||||||
|
|
||||||
|
|
||||||
// MSVC (VS2015 - VS2022) produces bad 32-bit x86 code from the CLMUL CRC
|
|
||||||
// code when optimizations are enabled (release build). According to the bug
|
|
||||||
// report, the ebx register is corrupted and the calculated result is wrong.
|
|
||||||
// Trying to workaround the problem with "__asm mov ebx, ebx" didn't help.
|
|
||||||
// The following pragma works and performance is still good. x86-64 builds
|
|
||||||
// aren't affected by this problem.
|
|
||||||
//
|
|
||||||
// NOTE: Another pragma after lzma_crc64_clmul() restores the optimizations.
|
|
||||||
// If the #if condition here is updated, the other one must be updated too.
|
|
||||||
#if defined(_MSC_VER) && !defined(__INTEL_COMPILER) && !defined(__clang__) \
|
|
||||||
&& defined(_M_IX86)
|
|
||||||
# pragma optimize("g", off)
|
|
||||||
#endif
|
|
||||||
|
|
||||||
|
|
||||||
#if (defined(__GNUC__) || defined(__clang__)) && !defined(__EDG__)
|
#if (defined(__GNUC__) || defined(__clang__)) && !defined(__EDG__)
|
||||||
__attribute__((__target__("ssse3,sse4.1,pclmul")))
|
__attribute__((__target__("ssse3,sse4.1,pclmul")))
|
||||||
#endif
|
#endif
|
||||||
|
@ -314,6 +299,21 @@ calc_hi(uint64_t poly, uint64_t a)
|
||||||
|
|
||||||
#ifdef HAVE_CHECK_CRC64
|
#ifdef HAVE_CHECK_CRC64
|
||||||
|
|
||||||
|
// MSVC (VS2015 - VS2022) produces bad 32-bit x86 code from the CLMUL CRC
|
||||||
|
// code when optimizations are enabled (release build). According to the bug
|
||||||
|
// report, the ebx register is corrupted and the calculated result is wrong.
|
||||||
|
// Trying to workaround the problem with "__asm mov ebx, ebx" didn't help.
|
||||||
|
// The following pragma works and performance is still good. x86-64 builds
|
||||||
|
// and CRC32 CLMUL aren't affected by this problem. The problem does not
|
||||||
|
// happen in crc_simd_body() either (which is shared with CRC32 CLMUL anyway).
|
||||||
|
//
|
||||||
|
// NOTE: Another pragma after lzma_crc64_clmul() restores the optimizations.
|
||||||
|
// If the #if condition here is updated, the other one must be updated too.
|
||||||
|
#if defined(_MSC_VER) && !defined(__INTEL_COMPILER) && !defined(__clang__) \
|
||||||
|
&& defined(_M_IX86)
|
||||||
|
# pragma optimize("g", off)
|
||||||
|
#endif
|
||||||
|
|
||||||
#if (defined(__GNUC__) || defined(__clang__)) && !defined(__EDG__)
|
#if (defined(__GNUC__) || defined(__clang__)) && !defined(__EDG__)
|
||||||
__attribute__((__target__("ssse3,sse4.1,pclmul")))
|
__attribute__((__target__("ssse3,sse4.1,pclmul")))
|
||||||
#endif
|
#endif
|
||||||
|
|
Loading…
Reference in a new issue