ARM NEON编译错误

在aarch64的ARM处理器上编译NEON程序,出现如下错误：

/usr/lib/gcc/arm-linux-gnueabihf/6/include/arm_neon.h:5792:1: error: inlining failed in call to always_inline ‘vdupq_n_s32’: target specific option mismatch
 vdupq_n_s32 (int32_t __a)
 ^~~~~~~~~~~
convolution_neon_int32.c:94:13: note: called from here
   int32x4_t sum_t = vdupq_n_s32(0);
             ^~~~~
In file included from convolution_neon_int32.c:3:0:
/usr/lib/gcc/arm-linux-gnueabihf/6/include/arm_neon.h:583:1: error: inlining failed in call to always_inline ‘vaddq_s32’: target specific option mismatch
 vaddq_s32 (int32x4_t __a, int32x4_t __b)
 ^~~~~~~~~
convolution_neon_int32.c:103:10: note: called from here
    sum_t = vaddq_s32(sum_t, multiply_t);
    ~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
In file included from convolution_neon_int32.c:3:0:
/usr/lib/gcc/arm-linux-gnueabihf/6/include/arm_neon.h:1072:1: error: inlining failed in call to always_inline ‘vmulq_s32’: target specific option mismatch
 vmulq_s32 (int32x4_t __a, int32x4_t __b)
 ^~~~~~~~~
convolution_neon_int32.c:102:15: note: called from here
    multiply_t = vmulq_s32(matb_t, veca_t);
    ~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~
In file included from convolution_neon_int32.c:3:0:
/usr/lib/gcc/arm-linux-gnueabihf/6/include/arm_neon.h:8997:1: error: inlining failed in call to always_inline ‘vld1q_s32’: target specific option mismatch
 vld1q_s32 (const int32_t * __a)
 ^~~~~~~~~
convolution_neon_int32.c:101:11: note: called from here
    veca_t = vld1q_s32(ptr_veca);
    ~~~~~~~^~~~~~~~~~~~~~~~~~~~~
In file included from convolution_neon_int32.c:3:0:
/usr/lib/gcc/arm-linux-gnueabihf/6/include/arm_neon.h:8997:1: error: inlining failed in call to always_inline ‘vld1q_s32’: target specific option mismatch
 vld1q_s32 (const int32_t * __a)
 ^~~~~~~~~
convolution_neon_int32.c:99:11: note: called from here
    matb_t = vld1q_s32(ptr_matB);
    ~~~~~~~^~~~~~~~~~~~~~~~~~~~~
In file included from convolution_neon_int32.c:3:0:
/usr/lib/gcc/arm-linux-gnueabihf/6/include/arm_neon.h:5299:1: error: inlining failed in call to always_inline ‘vget_lane_s32’: target specific option mismatch
 vget_lane_s32 (int32x2_t __a, const int __b)
 ^~~~~~~~~~~~~
convolution_neon_int32.c:117:10: note: called from here
   sum += vget_lane_s32(half_t, 1);
          ^~~~~~~~~~~~~~~~~~~~~~~~
In file included from convolution_neon_int32.c:3:0:
/usr/lib/gcc/arm-linux-gnueabihf/6/include/arm_neon.h:5299:1: error: inlining failed in call to always_inline ‘vget_lane_s32’: target specific option mismatch
 vget_lane_s32 (int32x2_t __a, const int __b)
 ^~~~~~~~~~~~~
convolution_neon_int32.c:116:10: note: called from here
   sum += vget_lane_s32(half_t, 0);
          ^~~~~~~~~~~~~~~~~~~~~~~~
In file included from convolution_neon_int32.c:3:0:
/usr/lib/gcc/arm-linux-gnueabihf/6/include/arm_neon.h:3061:1: error: inlining failed in call to always_inline ‘vpadd_s32’: target specific option mismatch
 vpadd_s32 (int32x2_t __a, int32x2_t __b)

解决办法是加入下编译选项：-march=armv8-a -marm -mfpu=neon

arm-linux-gnueabihf-gcc -march=armv8-a -marm -mfpu=neon  convolution_neon_int32.c -o convolution_neon_int32