Intel ARCHITECTURE IA-32 - Manual (Page 341)

Optimizing Cache Usage
6
6-51
prefetch_loop:
movaps xmm0, [esi+ecx]
movaps xmm0, [esi+ecx+64]
add ecx,128
cmp ecx,BLOCK_SIZE
jne prefetch_loop
xor ecx,ecx
align 16
cpy_loop:
movdqa xmm0,[esi+ecx]
movdqa xmm1,[esi+ecx+16]
movdqa xmm2,[esi+ecx+32]
movdqa xmm3,[esi+ecx+48]
movdqa xmm4,[esi+ecx+64]
movdqa xmm5,[esi+ecx+16+64]
movdqa xmm6,[esi+ecx+32+64]
movdqa xmm7,[esi+ecx+48+64]
movntdq [edi+ecx],xmm0
movntdq [edi+ecx+16],xmm1
movntdq [edi+ecx+32],xmm2
movntdq [edi+ecx+48],xmm3
movntdq [edi+ecx+64],xmm4
movntdq [edi+ecx+80],xmm5
movntdq [edi+ecx+96],xmm6
movntdq [edi+ecx+112],xmm7
add ecx,128
cmp ecx,BLOCK_SIZE
jne cpy_loop