.file	"absdiffmmx.cc"
	.version	"01.01"
/ GNU C++ version egcs-2.90.29 980515 (egcs-1.0.3 release) (i386-redhat-linux) compiled by GNU C version egcs-2.90.29 980515 (egcs-1.0.3 release).
/ options passed:  -O
/ options enabled:  -fdefer-pop -fthread-jumps -fpeephole -ffunction-cse
/ -finline -fkeep-static-consts -fpcc-struct-return -fexceptions -fcommon
/ -fverbose-asm -fgnu-linker -falias-check -fargument-alias -m80387
/ -mhard-float -mno-soft-float -mieee-fp -mfp-ret-in-387
/ -mschedule-prologue -mcpu=i386 -march=pentium

gcc2_compiled.:
.text
	.align 4
.globl absdiffmmx__FPUcPiT0N20Ucii
	.type	 absdiffmmx__FPUcPiT0N20Ucii,@function
absdiffmmx__FPUcPiT0N20Ucii:
.LFB1:
	pushl %ebp
.LCFI0:
	movl %esp,%ebp
.LCFI1:
	subl $32,%esp
.LCFI2:
	pushl %edi
.LCFI3:
	pushl %esi
.LCFI4:
	pushl %ebx
.LCFI5:
	movb 28(%ebp),%dl
	leal -8(%ebp),%ecx
	movl %ecx,-12(%ebp)
	xorl %eax,%eax
	.align 4
.L5:
	movl -12(%ebp),%ebx
	movb %dl,(%eax,%ebx)
	incl %eax
	cmpl $7,%eax
	jle .L5
#APP
	
	movq -8(%ebp),%mm7

#NO_APP
	movl $0,-32(%ebp)
	.align 4
.L7:
	movl 32(%ebp),%esi
	cmpl %esi,-32(%ebp)
	jge .L8
	movl 36(%ebp),%eax
	imull -32(%ebp),%eax
	movl 16(%ebp),%edi
	addl %eax,%edi
	movl %edi,-16(%ebp)
	movl 8(%ebp),%ecx
	addl %eax,%ecx
	movl %ecx,-28(%ebp)
	movl 20(%ebp),%ebx
	addl %eax,%ebx
	movl %ebx,-24(%ebp)
	addl 24(%ebp),%eax
	movl %eax,-20(%ebp)
	movl 36(%ebp),%eax
	testl %eax,%eax
	jge .L11
	addl $7,%eax
.L11:
	movl %eax,%edx
	sarl $3,%edx
	xorl %eax,%eax
#APP
	
	pxor %mm3, %mm3 	 # clear row-used flag
#NO_APP
	cmpl %edx,%eax
	jge .L13
	.align 4
.L14:
	movl -28(%ebp),%esi
	movl -24(%ebp),%edi
	movl -16(%ebp),%ecx
	movl -20(%ebp),%ebx
#APP
	
	 movq (%edi,%eax,8),%mm0       	# u  load ref  
	 movq (%ecx,%eax,8),%mm1       	# u  load input 
	 movq %mm0,%mm2    	# v copy ref 
	 movq (%ebx,%eax,8),%mm4       	# u  load var image data 
	 psubusb %mm1, %mm0	# v  ref - inp 
	 psubusb %mm2, %mm1	# u inp - ref  ?subtract stall? 
	 paddusb %mm7,%mm4 	# v add base threshold to variance
	 por %mm1, %mm0    	# u get abs diff (via or) 
	 psubusb %mm4,%mm0 	# u subtract with saturate thresh
	 movq %mm0,(%esi,%eax,8)       	# u store result, 
	 por %mm0, %mm3    	# v mark row used if it was 
#NO_APP
	incl %eax
	cmpl %edx,%eax
	jl .L14
.L13:
#APP
	
	movq %mm3,-8(%ebp)
#NO_APP
	movl -32(%ebp),%esi
	movl 12(%ebp),%edi
	movl $0,(%edi,%esi,4)
	xorl %edx,%edx
	.align 4
.L19:
	movl -12(%ebp),%ecx
	movzbl (%edx,%ecx),%eax
	movl -32(%ebp),%ebx
	movl 12(%ebp),%esi
	orl %eax,(%esi,%ebx,4)
	incl %edx
	cmpl $7,%edx
	jle .L19
	incl %ebx
	movl %ebx,-32(%ebp)
	jmp .L7
	.align 4
.L8:
#APP
	emms
#NO_APP
	leal -44(%ebp),%esp
	popl %ebx
	popl %esi
	popl %edi
	leave
	ret
.LFE1:
.Lfe1:
	.size	 absdiffmmx__FPUcPiT0N20Ucii,.Lfe1-absdiffmmx__FPUcPiT0N20Ucii

.section	.eh_frame,"aw",@progbits
__FRAME_BEGIN__:
	.4byte	.LLCIE1
.LSCIE1:
	.4byte	0x0
	.byte	0x1
	.byte	0x0
	.byte	0x1
	.byte	0x7c
	.byte	0x8
	.byte	0xc
	.byte	0x4
	.byte	0x4
	.byte	0x88
	.byte	0x1
	.align 4
.LECIE1:
	.set	.LLCIE1,.LECIE1-.LSCIE1
	.4byte	.LLFDE1
.LSFDE1:
	.4byte	.LSFDE1-__FRAME_BEGIN__
	.4byte	.LFB1
	.4byte	.LFE1-.LFB1
	.byte	0x4
	.4byte	.LCFI0-.LFB1
	.byte	0xe
	.byte	0x8
	.byte	0x85
	.byte	0x2
	.byte	0x4
	.4byte	.LCFI1-.LCFI0
	.byte	0xd
	.byte	0x5
	.byte	0x4
	.4byte	.LCFI3-.LCFI1
	.byte	0x87
	.byte	0xb
	.byte	0x4
	.4byte	.LCFI4-.LCFI3
	.byte	0x86
	.byte	0xc
	.byte	0x4
	.4byte	.LCFI5-.LCFI4
	.byte	0x83
	.byte	0xd
	.align 4
.LEFDE1:
	.set	.LLFDE1,.LEFDE1-.LSFDE1
	.ident	"GCC: (GNU) egcs-2.90.29 980515 (egcs-1.0.3 release)"