Intel ARCHITECTURE IA-32 - Manual (Page 281)

Optimizing for SIMD Floating-point Applications
5
5-19
Figure 5-3 Horizontal Add Using movhlps/movlhps
Example 5-9 Horizontal Add Using movhlps/movlhps
void horiz_add(Vertex_soa *in, float *out) {
__asm {
mov ecx, in // load structure addresses
mov edx, out
movaps xmm0, [ecx] // load A1 A2 A3 A4 => xmm0
movaps xmm1, [ecx+16] // load B1 B2 B3 B4 => xmm1
movaps xmm2, [ecx+32] // load C1 C2 C3 C4 => xmm2
movaps xmm3, [ecx+48] // load D1 D2 D3 D4 => xmm3
continued
A1+A2+A3+A4 B1+B2+B3+B4 C1+C2+C3+C4 D1+D2+D3+D4
A1+A3 B1+B3 C1+C3 D1+D3 A2+A4 B2+B4 C2+C4 D2+D4
A1+A3 A2+A4 B1+B3 B2+B4 C1+C3 C2+C4 D1+D3 D2+D4
A1 A2 A3 A4 B1 B2 B3 B4 C1 C2 C3 C4 D1 D2 D3 D4
A1 A2 B1 B2 A3 A4 B3 B4 C1 C2 D1 D2 C3 C4 D3 D4
ADDPS
SHUFPS SHUFPS
ADDPS ADDPS
M O VLHPS M O VLHPS
xm m 0 xm m 2
M O VHLPS M O VHLPS
xm m 1 xm m 3