Intel ARCHITECTURE IA-32 - Manual (Page 273)

Optimizing for SIMD Floating-point Applications
5
5-11
y1 x1
movhps xmm7, [ecx+16] // xmm7 = y2 x2 y1 x1
movlps xmm0, [ecx+32] // xmm0 = -- -- y3 x3
movhps xmm0, [ecx+48] // xmm0 = y4 x4 y3 x3
movaps xmm6, xmm7 // xmm6 = y1 x1 y1 x1
shufps xmm7, xmm0, 0x88 // xmm7 = x1 x2 x3 x4 => X
shufps xmm6, xmm0, 0xDD // xmm6 = y1 y2 y3 y4 => Y
movlps xmm2, [ecx+8] // xmm2 = -- -- w1 z1
movhps xmm2, [ecx+24] // xmm2 = w2 z2 u1 z1
movlps xmm1, [ecx+40] // xmm1 = -- -- s3 z3
movhps xmm1, [ecx+56] // xmm1 = w4 z4 w3 z3
movaps xmm0, xmm2 // xmm0 = w1 z1 w1 z1
shufps xmm2, xmm1, 0x88 // xmm2 = z1 z2 z3 z4 => Z
movlps xmm7, [ecx] // xmm7 = -- --shufps xmm0, xmm1,
// 0xDD xmm6 = w1 w2 w3 w4 => W
movaps [edx], xmm7 // store X
movaps [edx+16], xmm6 // store Y
movaps [edx+32], xmm2 // store Z
movaps [edx+48], xmm0 // store W
// SWIZZLE XYZ -> XXX
}
}
Example 5-3 Swizzling Data (continued)