调用always_inline‘_mm_mullo_epi32’时内联失败：目标特定选项不匹配

我正在尝试使用 cmake 编译 C 程序，该程序使用 SIMD 内在函数。当我尝试编译它时，出现两个错误

/usr/lib/gcc/x86_64-linux-gnu/5/include/smmintrin.h：326：1：错误：调用always_inline'_mm_mullo_epi32'时内联失败：目标特定选项不匹配 _mm_mullo_epi32 (__m128i __X, __m128i __Y)

/usr/lib/gcc/x86_64-linux-gnu/5/include/tmmintrin.h：136：1：错误：调用always_inline'_mm_shuffle_epi8'时内联失败：目标特定选项不匹配 _mm_shuffle_epi8（__m128i __X，__m128i __Y）

这个问题已经在这里解决了堆栈溢出 https://stackoverflow.com/questions/35772562/inlining-failed-in-call-to-always-inline-m128i-mm-cvtepu8-epi32-m128i-t通过设置

set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -msse4.1")

我尝试了同样的选择和许多其他选择。但我的项目仍然无法编译。

set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -msse4.1")  
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -sse4_1")  
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=nehalem")  
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -msse4.1 -msse4.2")  
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=native")  
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -ssse3")  

gcc查找指令开关的通用方法

文件 intrin.sh：

#!/bin/bash

get_instruction ()
{
    [ -z "$1" ] && exit
    func_name="$1 "

    header_file=`grep --include=\*intrin.h -Rl "$func_name" /usr/lib/gcc | head -n1`
    [ -z "$header_file" ] && exit
    >&2 echo "find in: $header_file"

    target_directive=`grep "#pragma GCC target(\|$func_name" $header_file | grep -B 1 "$func_name" | head -n1`
    echo $target_directive | grep -o '"[^,]*[,"]' | sed 's/"//g' | sed 's/,//g'
}

instruction=`get_instruction $1`
if [ -z "$instruction" ]; then
    echo "Error: function not found: $1"
else
    echo "add this option to gcc: -m$instruction"
fi

Usage:

./intrin.sh _mm_shuffle_epi8      # output: -mssse3
./intrin.sh _mm_cvtepu8_epi32     # output: -msse4.1
./intrin.sh _mm_loadu_ps          # output: -msse
./intrin.sh _mm_clmulepi64_si128  # output: -mpclmul
./intrin.sh _mm256_loadu_si256    # output: -mavx
./intrin.sh _mm512_and_ps         # output: -mavx512dq