Store packed double-precision (64-bit) floating-point elements from a into memory using mask. See: "Note about mask load/store" to know why you must address valid memory only.
double[4] A = [0.0, 1, 2, 3]; __m256i M = _mm256_setr_epi64x(-9, 0, -1, 0); __m256d B = _mm256_setr_pd(2, 3, 4, 5); _mm256_maskstore_pd(A.ptr, M, B); double[4] correct = [2.0, 1, 4, 3]; assert(A == correct);
Store packed double-precision (64-bit) floating-point elements from a into memory using mask. See: "Note about mask load/store" to know why you must address valid memory only.