- mov %r10,%r11
- shr \$`log($N/8)/log(2)`,%r10
- and \$`$N/8-1`,%r11
- not %r10
- lea .Lmagic_masks(%rip),%rax
- and \$`2**5/($N/8)-1`,%r10 # 5 is "window size"
- lea 96($bp,%r11,8),$bp # pointer within 1st cache line
- movq 0(%rax,%r10,8),%xmm4 # set of masks denoting which
- movq 8(%rax,%r10,8),%xmm5 # cache line contains element
- movq 16(%rax,%r10,8),%xmm6 # denoted by 7th argument
- movq 24(%rax,%r10,8),%xmm7
-
- movq `0*$STRIDE/4-96`($bp),%xmm0
- movq `1*$STRIDE/4-96`($bp),%xmm1
- pand %xmm4,%xmm0
- movq `2*$STRIDE/4-96`($bp),%xmm2
- pand %xmm5,%xmm1
- movq `3*$STRIDE/4-96`($bp),%xmm3
- pand %xmm6,%xmm2
- por %xmm1,%xmm0
- pand %xmm7,%xmm3
+ movdqa 0(%r10),%xmm0 # 00000001000000010000000000000000
+ movdqa 16(%r10),%xmm1 # 00000002000000020000000200000002
+ lea 24-112(%rsp,$num,8),%r10# place the mask after tp[num+3] (+ICache optimization)
+ and \$-16,%r10
+
+ pshufd \$0,%xmm5,%xmm5 # broadcast index
+ movdqa %xmm1,%xmm4
+ movdqa %xmm1,%xmm2
+___
+########################################################################
+# calculate mask by comparing 0..31 to index and save result to stack
+#
+$code.=<<___;
+ paddd %xmm0,%xmm1
+ pcmpeqd %xmm5,%xmm0 # compare to 1,0
+ .byte 0x67
+ movdqa %xmm4,%xmm3
+___
+for($k=0;$k<$STRIDE/16-4;$k+=4) {
+$code.=<<___;
+ paddd %xmm1,%xmm2
+ pcmpeqd %xmm5,%xmm1 # compare to 3,2
+ movdqa %xmm0,`16*($k+0)+112`(%r10)
+ movdqa %xmm4,%xmm0
+
+ paddd %xmm2,%xmm3
+ pcmpeqd %xmm5,%xmm2 # compare to 5,4
+ movdqa %xmm1,`16*($k+1)+112`(%r10)
+ movdqa %xmm4,%xmm1
+
+ paddd %xmm3,%xmm0
+ pcmpeqd %xmm5,%xmm3 # compare to 7,6
+ movdqa %xmm2,`16*($k+2)+112`(%r10)
+ movdqa %xmm4,%xmm2
+
+ paddd %xmm0,%xmm1
+ pcmpeqd %xmm5,%xmm0
+ movdqa %xmm3,`16*($k+3)+112`(%r10)
+ movdqa %xmm4,%xmm3
+___
+}
+$code.=<<___; # last iteration can be optimized
+ paddd %xmm1,%xmm2
+ pcmpeqd %xmm5,%xmm1
+ movdqa %xmm0,`16*($k+0)+112`(%r10)
+
+ paddd %xmm2,%xmm3
+ .byte 0x67
+ pcmpeqd %xmm5,%xmm2
+ movdqa %xmm1,`16*($k+1)+112`(%r10)
+
+ pcmpeqd %xmm5,%xmm3
+ movdqa %xmm2,`16*($k+2)+112`(%r10)
+ pand `16*($k+0)-128`($bp),%xmm0 # while it's still in register
+
+ pand `16*($k+1)-128`($bp),%xmm1
+ pand `16*($k+2)-128`($bp),%xmm2
+ movdqa %xmm3,`16*($k+3)+112`(%r10)
+ pand `16*($k+3)-128`($bp),%xmm3
+ por %xmm2,%xmm0
+ por %xmm3,%xmm1
+___
+for($k=0;$k<$STRIDE/16-4;$k+=4) {
+$code.=<<___;
+ movdqa `16*($k+0)-128`($bp),%xmm4
+ movdqa `16*($k+1)-128`($bp),%xmm5
+ movdqa `16*($k+2)-128`($bp),%xmm2
+ pand `16*($k+0)+112`(%r10),%xmm4
+ movdqa `16*($k+3)-128`($bp),%xmm3
+ pand `16*($k+1)+112`(%r10),%xmm5
+ por %xmm4,%xmm0
+ pand `16*($k+2)+112`(%r10),%xmm2
+ por %xmm5,%xmm1
+ pand `16*($k+3)+112`(%r10),%xmm3