inffas32.asm

gcc的组建

;/* inffas32.asm is a hand tuned assembler version of inffast.c -- fast decoding
; *
; * inffas32.asm is derivated from inffas86.c, with translation of assembly code
; *
; * Copyright (C) 1995-2003 Mark Adler
; * For conditions of distribution and use, see copyright notice in zlib.h
; *
; * Copyright (C) 2003 Chris Anderson <[e-mail]>
; * Please use the copyright conditions above.
; *
; * Mar-13-2003 -- Most of this is derived from inffast.S which is derived from
; * the gcc -S output of zlib-1.2.0/inffast.c.  Zlib-1.2.0 is in beta release at
; * the moment.  I have successfully compiled and tested this code with gcc2.96,
; * gcc3.2, icc5.0, msvc6.0.  It is very close to the speed of inffast.S
; * compiled with gcc -DNO_MMX, but inffast.S is still faster on the P3 with MMX
; * enabled.  I will attempt to merge the MMX code into this version.  Newer
; * versions of this and inffast.S can be found at
; * http://www.eetbeetee.com/zlib/ and http://www.charm.net/~christop/zlib/
; * 
; * 2005 : modification by Gilles Vollant
; */
; For Visual C++ 4.x and higher and ML 6.x and higher
;   ml.exe is in directory \MASM611C of Win95 DDK
;   ml.exe is also distributed in http://www.masm32.com/masmdl.htm
;    and in VC++2003 toolkit at http://msdn.microsoft.com/visualc/vctoolkit2003/
;
;
;   compile with command line option
;   ml  /coff /Zi /c /Flinffas32.lst inffas32.asm

;   if you define NO_GZIP (see inflate.h), compile with
;   ml  /coff /Zi /c /Flinffas32.lst /DNO_GUNZIP inffas32.asm


; zlib122sup is 0 fort zlib 1.2.2.1 and lower
; zlib122sup is 8 fort zlib 1.2.2.2 and more (with addition of dmax and head 
;        in inflate_state in inflate.h)
zlib1222sup      equ    8


IFDEF GUNZIP
  INFLATE_MODE_TYPE    equ 11
  INFLATE_MODE_BAD     equ 26
ELSE
  IFNDEF NO_GUNZIP
    INFLATE_MODE_TYPE    equ 11
    INFLATE_MODE_BAD     equ 26
  ELSE
    INFLATE_MODE_TYPE    equ 3
    INFLATE_MODE_BAD     equ 17
  ENDIF
ENDIF


; 75 "inffast.S"
;FILE "inffast.S"

;;;GLOBAL _inflate_fast

;;;SECTION .text



	.586p
	.mmx

	name	inflate_fast_x86
	.MODEL	FLAT

_DATA			segment
inflate_fast_use_mmx:
	dd	1


_TEXT			segment
PUBLIC _inflate_fast

ALIGN 4
_inflate_fast:
	jmp inflate_fast_entry



ALIGN 4
	db	'Fast decoding Code from Chris Anderson'
	db	0

ALIGN 4
invalid_literal_length_code_msg:
	db	'invalid literal/length code'
	db	0

ALIGN 4
invalid_distance_code_msg:
	db	'invalid distance code'
	db	0

ALIGN 4
invalid_distance_too_far_msg:
	db	'invalid distance too far back'
	db	0


ALIGN 4
inflate_fast_mask:
dd	0
dd	1
dd	3
dd	7
dd	15
dd	31
dd	63
dd	127
dd	255
dd	511
dd	1023
dd	2047
dd	4095
dd	8191
dd	16383
dd	32767
dd	65535
dd	131071
dd	262143
dd	524287
dd	1048575
dd	2097151
dd	4194303
dd	8388607
dd	16777215
dd	33554431
dd	67108863
dd	134217727
dd	268435455
dd	536870911
dd	1073741823
dd	2147483647
dd	4294967295


mode_state	 equ	0	;/* state->mode	*/
wsize_state	 equ	(32+zlib1222sup)	;/* state->wsize */
write_state	 equ	(36+4+zlib1222sup)	;/* state->write */
window_state	 equ	(40+4+zlib1222sup)	;/* state->window */
hold_state	 equ	(44+4+zlib1222sup)	;/* state->hold	*/
bits_state	 equ	(48+4+zlib1222sup)	;/* state->bits	*/
lencode_state	 equ	(64+4+zlib1222sup)	;/* state->lencode */
distcode_state	 equ	(68+4+zlib1222sup)	;/* state->distcode */
lenbits_state	 equ	(72+4+zlib1222sup)	;/* state->lenbits */
distbits_state	 equ	(76+4+zlib1222sup)	;/* state->distbits */


;;SECTION .text
; 205 "inffast.S"
;GLOBAL	inflate_fast_use_mmx

;SECTION .data


; GLOBAL inflate_fast_use_mmx:object
;.size inflate_fast_use_mmx, 4
; 226 "inffast.S"
;SECTION .text

ALIGN 4
inflate_fast_entry:
	push  edi
	push  esi
	push  ebp
	push  ebx
	pushfd
	sub  esp,64
	cld




	mov  esi, [esp+88]
	mov  edi, [esi+28]







	mov  edx, [esi+4]
	mov  eax, [esi+0]

	add  edx,eax
	sub  edx,11

	mov  [esp+44],eax
	mov  [esp+20],edx

	mov  ebp, [esp+92]
	mov  ecx, [esi+16]
	mov  ebx, [esi+12]

	sub  ebp,ecx
	neg  ebp
	add  ebp,ebx

	sub  ecx,257
	add  ecx,ebx

	mov  [esp+60],ebx
	mov  [esp+40],ebp
	mov  [esp+16],ecx
; 285 "inffast.S"
	mov  eax, [edi+lencode_state]
	mov  ecx, [edi+distcode_state]

	mov  [esp+8],eax
	mov  [esp+12],ecx

	mov  eax,1
	mov  ecx, [edi+lenbits_state]
	shl  eax,cl
	dec  eax
	mov  [esp+0],eax

	mov  eax,1
	mov  ecx, [edi+distbits_state]
	shl  eax,cl
	dec  eax
	mov  [esp+4],eax

	mov  eax, [edi+wsize_state]
	mov  ecx, [edi+write_state]
	mov  edx, [edi+window_state]

	mov  [esp+52],eax
	mov  [esp+48],ecx
	mov  [esp+56],edx

	mov  ebp, [edi+hold_state]
	mov  ebx, [edi+bits_state]
; 321 "inffast.S"
	mov  esi, [esp+44]
	mov  ecx, [esp+20]
	cmp  ecx,esi
	ja   L_align_long

	add  ecx,11
	sub  ecx,esi
	mov  eax,12
	sub  eax,ecx
	lea  edi, [esp+28]
	rep movsb
	mov  ecx,eax
	xor  eax,eax
	rep stosb
	lea  esi, [esp+28]
	mov  [esp+20],esi
	jmp  L_is_aligned


L_align_long:
	test  esi,3
	jz   L_is_aligned
	xor  eax,eax
	mov  al, [esi]
	inc  esi
	mov  ecx,ebx
	add  ebx,8
	shl  eax,cl
	or  ebp,eax
	jmp L_align_long

L_is_aligned:
	mov  edi, [esp+60]
; 366 "inffast.S"
L_check_mmx:
	cmp  dword ptr [inflate_fast_use_mmx],2
	je   L_init_mmx
	ja   L_do_loop

	push  eax
	push  ebx
	push  ecx
	push  edx
	pushfd
	mov  eax, [esp]
	xor  dword ptr [esp],0200000h




	popfd
	pushfd
	pop  edx
	xor  edx,eax
	jz   L_dont_use_mmx
	xor  eax,eax
	cpuid
	cmp  ebx,0756e6547h
	jne  L_dont_use_mmx
	cmp  ecx,06c65746eh
	jne  L_dont_use_mmx
	cmp  edx,049656e69h
	jne  L_dont_use_mmx
	mov  eax,1
	cpuid
	shr  eax,8
	and  eax,15
	cmp  eax,6
	jne  L_dont_use_mmx
	test  edx,0800000h
	jnz  L_use_mmx
	jmp  L_dont_use_mmx
L_use_mmx:
	mov  dword ptr [inflate_fast_use_mmx],2
	jmp  L_check_mmx_pop
L_dont_use_mmx:
	mov  dword ptr [inflate_fast_use_mmx],3
L_check_mmx_pop:
	pop  edx
	pop  ecx
	pop  ebx
	pop  eax
	jmp  L_check_mmx
; 426 "inffast.S"
ALIGN 4
L_do_loop:
; 437 "inffast.S"
	cmp  bl,15
	ja   L_get_length_code

	xor  eax,eax
	lodsw
	mov  cl,bl
	add  bl,16
	shl  eax,cl
	or  ebp,eax

L_get_length_code:
	mov  edx, [esp+0]
	mov  ecx, [esp+8]
	and  edx,ebp
	mov  eax, [ecx+edx*4]

L_dolen:






	mov  cl,ah
	sub  bl,ah
	shr  ebp,cl






	test  al,al
	jnz   L_test_for_length_base

	shr  eax,16
	stosb

L_while_test:


	cmp  [esp+16],edi
	jbe  L_break_loop

	cmp  [esp+20],esi
	ja   L_do_loop
	jmp  L_break_loop

L_test_for_length_base:
; 502 "inffast.S"
	mov  edx,eax
	shr  edx,16
	mov  cl,al

	test  al,16
	jz   L_test_for_second_level_length
	and  cl,15
	jz   L_save_len
	cmp  bl,cl
	jae  L_add_bits_to_len

	mov  ch,cl
	xor  eax,eax
	lodsw
	mov  cl,bl
	add  bl,16
	shl  eax,cl
	or  ebp,eax
	mov  cl,ch

L_add_bits_to_len:
	mov  eax,1
	shl  eax,cl
	dec  eax
	sub  bl,cl
	and  eax,ebp
	shr  ebp,cl
	add  edx,eax

L_save_len:
	mov  [esp+24],edx


L_decode_distance:
; 549 "inffast.S"
	cmp  bl,15
	ja   L_get_distance_code

	xor  eax,eax
	lodsw
	mov  cl,bl
	add  bl,16
	shl  eax,cl
	or  ebp,eax

L_get_distance_code:
	mov  edx, [esp+4]
	mov  ecx, [esp+12]
	and  edx,ebp
	mov  eax, [ecx+edx*4]


L_dodist:
	mov  edx,eax
	shr  edx,16
	mov  cl,ah
	sub  bl,ah
	shr  ebp,cl
; 584 "inffast.S"
	mov  cl,al

	test  al,16
	jz  L_test_for_second_level_dist
	and  cl,15
	jz  L_check_dist_one
	cmp  bl,cl
	jae  L_add_bits_to_dist

	mov  ch,cl
	xor  eax,eax
	lodsw
	mov  cl,bl
	add  bl,16
	shl  eax,cl
	or  ebp,eax
	mov  cl,ch

L_add_bits_to_dist:
	mov  eax,1
	shl  eax,cl
	dec  eax
	sub  bl,cl
	and  eax,ebp
	shr  ebp,cl
	add  edx,eax
	jmp  L_check_window

L_check_window:
; 625 "inffast.S"
	mov  [esp+44],esi
	mov  eax,edi
	sub  eax, [esp+40]

	cmp  eax,edx
	jb   L_clip_window

	mov  ecx, [esp+24]
	mov  esi,edi
	sub  esi,edx

	sub  ecx,3
	mov  al, [esi]
	mov  [edi],al
	mov  al, [esi+1]
	mov  dl, [esi+2]
	add  esi,3
	mov  [edi+1],al
	mov  [edi+2],dl
	add  edi,3
	rep movsb

	mov  esi, [esp+44]
	jmp  L_while_test

ALIGN 4
L_check_dist_one:
	cmp  edx,1
	jne  L_check_window
	cmp  [esp+40],edi
	je  L_check_window

	dec  edi
	mov  ecx, [esp+24]
	mov  al, [edi]
	sub  ecx,3

	mov  [edi+1],al
	mov  [edi+2],al
	mov  [edi+3],al
	add  edi,4
	rep stosb

	jmp  L_while_test

ALIGN 4
L_test_for_second_level_length:




	test  al,64
	jnz   L_test_for_end_of_block

	mov  eax,1
	shl  eax,cl
	dec  eax
	and  eax,ebp
	add  eax,edx
	mov  edx, [esp+8]
	mov  eax, [edx+eax*4]
	jmp  L_dolen

ALIGN 4
L_test_for_second_level_dist:




	test  al,64
	jnz   L_invalid_distance_code

	mov  eax,1
	shl  eax,cl
	dec  eax
	and  eax,ebp
	add  eax,edx