mov esi, this ; vector u
movups xmm0, [esi] ; first vector in xmm0
movaps xmm2, xmm0 ; copy original vector
mulps xmm0, xmm0 ; mul with 2nd vector
movaps xmm1, xmm0 ; copy result
shufps xmm1, xmm1, 4Eh ; shuffle: f1,f0,f3,f2
addps xmm0, xmm1 ; add: f3+f1,f2+f0,f1+f3,f0+f2
movaps xmm1, xmm0 ; copy results
shufps xmm1, xmm1, 11h ; shuffle: f0+f2,f1+f3,f0+f2,f1+f3
addps xmm0, xmm1 ; add: x,x,f0+f1+f2+f3,f0+f1+f2+f3 rsqrtps xmm0, xmm0 ; recip. sqrt (faster than ss + shufps)
mulps xmm2, xmm0 ; mul by reciprocal
movups [esi], xmm2 ; bring back result
核心思想 xmm寄存器 4分量 全部赋值为x*x +y*y + z*z, rsqrtps 求向量长度的倒数，最终乘以xmm2存的原向量，完成标准化。
rsqrtps用的查表方式，近似求的开方倒数，提高执行速度。精确求利用rsqrtss指令。