Which AVX memory access pattern is better?

sun__lei — Mon, 28 Oct 2019 16:42:40 GMT

For example, there are an array A. it’s length is length_A. Using AVX gather(_mm256_i32gather_i32) function to read array A. There are two memory access pattern.

mm256 register = (A[0], A[1],….A[7])

mm256 register = (A[8], A[9],….A[15]),,,and so on

stride = length_a /8;

mm256 register = (A[0], A[stride+0],….A[7*stride+0])

mm256 register = (A[1], A[stride+1],….A[7*stride+1]),,,and so on

which is better when length_A is very large?

topic Which AVX memory access pattern is better? in Intel® Moderncode for Parallel Architectures

Which AVX memory access pattern is better?