0
void GEPDOT_AVX__12_4 (int k, double *A, double *B, double *C) {
double *A_end = A + 12 * k - 20;
asm volatile (
"vmovapd (%[A]), %%ymm13\n\t"
"addq $128, %[A]\n\t"
"vmovapd -96(%[A]), %%ymm14\n\t"
"vmovapd -64(%[A]), %%ymm13\n\t"
"vmovapd -32(%[A]...