> >> without the ' -mavx2' option for gcc, there are compiling error:
> >> '__m256i undeclared', the __attribute__((target("avx2"))) can't solve
> >> this issue. Any idea?
> >
> > You're right that you can't use the normal __m256i, as it doesn't get
> > declared.
>
> It should be declared. *intrin.h uses #pragma GCC target and always defines
> all vector types.
>
> In fact, the following compiles for me with just "gcc foo.c" under GCC 5.x:
>
> #include <immintrin.h>
>
> // #if defined CONFIG_IFUNC && defined CONFIG_AVX2 #pragma GCC
> push_options #pragma GCC target("avx2")
> #define AVX2_VECTYPE __m256i
> #define AVX2_SPLAT(p) _mm256_set1_epi8(*(p))
> #define AVX2_ALL_EQ(v1, v2) \
> (_mm256_movemask_epi8(_mm256_cmpeq_epi8(v1, v2)) == 0xFFFFFFFF)
> #define AVX2_VEC_OR(v1, v2) (_mm256_or_si256(v1, v2))
>
> size_t buffer_find_nonzero_offset_avx2(const void *buf, size_t len) {
> const AVX2_VECTYPE *p = buf;
> const AVX2_VECTYPE zero = (AVX2_VECTYPE){0};
> size_t i;
>
> if (!len) {
> return 0;
> }
>
> for (i = 0; i < 4; i++) {
> if (!AVX2_ALL_EQ(p[i], zero)) {
> return i * sizeof(AVX2_VECTYPE);
> }
> }
>
> for (i = 4; i < len / sizeof(AVX2_VECTYPE); i += 4) {
> AVX2_VECTYPE tmp0 = AVX2_VEC_OR(p[i + 0], p[i + 1]);
> AVX2_VECTYPE tmp1 = AVX2_VEC_OR(p[i + 2], p[i + 3]);
> AVX2_VECTYPE tmp2 = AVX2_VEC_OR(p[i + 4], p[i + 5]);
> AVX2_VECTYPE tmp3 = AVX2_VEC_OR(p[i + 6], p[i + 7]);
> AVX2_VECTYPE tmp01 = AVX2_VEC_OR(tmp0, tmp1);
> AVX2_VECTYPE tmp23 = AVX2_VEC_OR(tmp2, tmp3);
> if (!AVX2_ALL_EQ(AVX2_VEC_OR(tmp01, tmp23), zero)) {
> break;
> }
> }
>
> return i * sizeof(AVX2_VECTYPE);
> }
>
> #pragma GCC pop_options
> // #endif
>
> so perhaps the configure test is testing the wrong thing?
>
> Paolo
Hi Paolo,
what's your opinion? putting the AVX2 related code to util/cutils.c and use
the "#pragma ..." you referred?
The configure test is ok, it use the "-mavx2".
Liang
