OSchip
/
llvm-project
mirror of https://github.com/THU-DSP-LAB/llvm-project.git
13
0
Fork 2
Code Issues Packages Projects Releases Wiki Activity

[libc] Fix builtin definition for memory functions 

The memory functions are highly performance sensitive and use builtins
where possible, but also need to define those functions names when they
don't exist to avoid compilation errors. Previously all those
redefinitions were behind the SSE2 flag for x86, which caused errors on
CPUs that supported SSE2 but not AVX512. This patch splits the various
CPU extensions out to avoid errors on such CPUs.

Reviewed By: gchatelet

Differential Revision: https://reviews.llvm.org/D137868
This commit is contained in:
Michael Jones 2022-11-11 14:08:58 -08:00
parent 9777e98a61
commit da5d00ad0c
3 changed files with 15 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
libc/cmake/modules/LLVMLibCCheckCpuFeatures.cmake
View File

@ -6,7 +6,7 @@
set(ALL_CPU_FEATURES "")
if(${LIBC_TARGET_ARCHITECTURE_IS_X86})
set(ALL_CPU_FEATURES SSE2 SSE4_2 AVX2 AVX512F FMA)
set(ALL_CPU_FEATURES SSE2 SSE4_2 AVX2 AVX512F AVX512BW FMA)
set(LIBC_COMPILE_OPTIONS_NATIVE -march=native)
elseif(${LIBC_TARGET_ARCHITECTURE_IS_AARCH64})
set(LIBC_COMPILE_OPTIONS_NATIVE -mcpu=native)

4
libc/src/string/CMakeLists.txt
View File

@ -355,7 +355,7 @@ if(${LIBC_TARGET_ARCHITECTURE_IS_X86})
add_bcmp(bcmp_x86_64_opt_sse2 COMPILE_OPTIONS -march=k8 REQUIRE SSE2)
add_bcmp(bcmp_x86_64_opt_sse4 COMPILE_OPTIONS -march=nehalem REQUIRE SSE4_2)
add_bcmp(bcmp_x86_64_opt_avx2 COMPILE_OPTIONS -march=haswell REQUIRE AVX2)
add_bcmp(bcmp_x86_64_opt_avx512 COMPILE_OPTIONS -march=skylake-avx512 REQUIRE AVX512F)
add_bcmp(bcmp_x86_64_opt_avx512 COMPILE_OPTIONS -march=skylake-avx512 REQUIRE AVX512BW)
add_bcmp(bcmp_opt_host COMPILE_OPTIONS ${LIBC_COMPILE_OPTIONS_NATIVE})
add_bcmp(bcmp)
else()
@ -409,7 +409,7 @@ if(${LIBC_TARGET_ARCHITECTURE_IS_X86})
add_memcmp(memcmp_x86_64_opt_sse2 COMPILE_OPTIONS -march=k8 REQUIRE SSE2)
add_memcmp(memcmp_x86_64_opt_sse4 COMPILE_OPTIONS -march=nehalem REQUIRE SSE4_2)
add_memcmp(memcmp_x86_64_opt_avx2 COMPILE_OPTIONS -march=haswell REQUIRE AVX2)
add_memcmp(memcmp_x86_64_opt_avx512 COMPILE_OPTIONS -march=skylake-avx512 REQUIRE AVX512F)
add_memcmp(memcmp_x86_64_opt_avx512 COMPILE_OPTIONS -march=skylake-avx512 REQUIRE AVX512BW)
add_memcmp(memcmp_opt_host COMPILE_OPTIONS ${LIBC_COMPILE_OPTIONS_NATIVE})
add_memcmp(memcmp)
elseif(${LIBC_TARGET_ARCHITECTURE_IS_AARCH64})

17
libc/src/string/memory_utils/op_x86.h
View File

@ -20,15 +20,22 @@
#include "src/string/memory_utils/op_builtin.h"
#include "src/string/memory_utils/op_generic.h"
#ifdef __SSE2__
#if defined(__AVX512BW__) || defined(__AVX512F__) || defined(__AVX2__) || \
defined(__SSE2__)
#include <immintrin.h>
#else
#endif
// Define fake functions to prevent the compiler from failing on undefined
// functions in case SSE2 is not present.
// functions in case the CPU extension is not present.
#ifndef __AVX512BW__
#define _mm512_cmpneq_epi8_mask(A, B) 0
#define _mm_movemask_epi8(A) 0
#endif
#ifndef __AVX2__
#define _mm256_movemask_epi8(A) 0
#endif // __SSE2__
#endif
#ifndef __SSE2__
#define _mm_movemask_epi8(A) 0
#endif
namespace __llvm_libc::x86 {