Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

SSE42 support #1

Merged
merged 2 commits into from
Sep 18, 2017
Merged

SSE42 support #1

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a979b4a
specify SSE42 'target' attribute for Fast_CRC32()
tchaikov Sep 7, 2017
7ea5181
compile with correct flags to determine SSE4.2 support
benesch Aug 14, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion build_tools/build_detect_platform
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -456,7 +456,7 @@ elif test -z "$PORTABLE"; then
fi
fi

$CXX $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
#include <cstdint>
#include <nmmintrin.h>
int main() {
Expand Down
14 changes: 11 additions & 3 deletions util/crc32c.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -313,6 +313,15 @@ static inline void Slow_CRC32(uint64_t* l, uint8_t const **p) {
table0_[c >> 24];
}

#if defined(HAVE_SSE42) && defined(__GNUC__)
#if defined(__clang__)
#if __has_cpp_attribute(gnu::target)
__attribute__ ((target ("sse4.2")))
#endif
#else // gcc supports this since 4.4
__attribute__ ((target ("sse4.2")))
#endif
#endif
static inline void Fast_CRC32(uint64_t* l, uint8_t const **p) {
#ifndef HAVE_SSE42
Slow_CRC32(l, p);
Expand Down Expand Up @@ -376,8 +385,7 @@ static bool isSSE42() {
return false;
#elif defined(__GNUC__) && defined(__x86_64__) && !defined(IOS_CROSS_COMPILE)
uint32_t c_;
uint32_t d_;
__asm__("cpuid" : "=c"(c_), "=d"(d_) : "a"(1) : "ebx");
__asm__("cpuid" : "=c"(c_) : "a"(1) : "ebx", "edx");
return c_ & (1U << 20); // copied from CpuId.h in Folly.
#elif defined(_WIN64)
int info[4];
Expand All @@ -398,7 +406,7 @@ bool IsFastCrc32Supported() {
return isSSE42();
}

Function ChosenExtend = Choose_Extend();
static Function ChosenExtend = Choose_Extend();

uint32_t Extend(uint32_t crc, const char* buf, size_t size) {
return ChosenExtend(crc, buf, size);
Expand Down