1 2 3 4 5 6 7 8 9 10 11 12 13
vdpphps(xm1, xm2, xm3); vdpphps(xm1, xm2, ptr[rax+128]); vdpphps(xm1, xm2, ptr_b[rax+128]); vdpphps(ym1, ym2, ym3); vdpphps(ym1, ym2, ptr[rax+128]); vdpphps(ym1, ym2, ptr_b[rax+128]); vdpphps(zm1, zm2, zm3); vdpphps(zm1, zm2, ptr[rax+128]); vdpphps(zm1, zm2, ptr_b[rax+128]); // skip vmpsadbw