Skip to content
Snippets Groups Projects
Commit e1a55db4 authored by Bram Veenboer's avatar Bram Veenboer Committed by Bram Veenboer
Browse files

Use permute_ps to swap real and imag

parent ac90b5bf
No related branches found
No related tags found
1 merge request!4Add matrixMultiplyAVX2b
Pipeline #81803 passed
......@@ -127,8 +127,8 @@ void matrixMultiplyAVX2b(const std::complex<float>* a,
__m256 b_1 = _mm256_permutevar8x32_ps(b_m, _mm256_set_epi32(3, 2, 1, 0, 3, 2, 1, 0));
__m256 b_2 = _mm256_permutevar8x32_ps(b_m, _mm256_set_epi32(7, 6, 5, 4, 7, 6, 5, 4));
__m256 b_3 = _mm256_permutevar8x32_ps(b_m, _mm256_set_epi32(2, 3, 0, 1, 2, 3, 0, 1));
__m256 b_4 = _mm256_permutevar8x32_ps(b_m, _mm256_set_epi32(6, 7, 4, 5, 6, 7, 4, 5));
__m256 b_3 = _mm256_permute_ps(b_1, _MM_SHUFFLE(2, 3, 0, 1));
__m256 b_4 = _mm256_permute_ps(b_2, _MM_SHUFFLE(2, 3, 0, 1));
__m256 c_m = _mm256_mul_ps(a_1, b_1);
c_m = _mm256_fmadd_ps(a_2, b_2, c_m);
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment