In case anyone cares and since intrinsics seem to be the way to go these days here is a solution in terms of intrinsics.
int horizontal_max_Vec4i(__m128i x) {
__m128i max1 = _mm_shuffle_epi32(x, _MM_SHUFFLE(0,0,3,2));
__m128i max2 = _mm_max_epi32(x,max1);
__m128i max3 = _mm_shuffle_epi32(max2, _MM_SHUFFLE(0,0,0,1));
__m128i max4 = _mm_max_epi32(max2,max3);
return _mm_cvtsi128_si32(max4);
}
I don't know if that's any better than this:
int horizontal_max_Vec4i(__m128i x) {
int result[4] __attribute__((aligned(16))) = {0};
_mm_store_si128((__m128i *) result, x);
return max(max(max(result[0], result[1]), result[2]), result[3]);
}
与恶龙缠斗过久,自身亦成为恶龙;凝视深渊过久,深渊将回以凝视…