view release on metacpan or  search on metacpan

zlib-1.2.8/contrib/masmx64/gvmat64.asm  view on Meta::CPAN

;uInt longest_match_x64(
;    deflate_state *s,
;    IPos cur_match);                             /* current match */

; gvmat64.asm -- Asm portion of the optimized longest_match for 32 bits x86_64
;  (AMD64 on Athlon 64, Opteron, Phenom
;     and Intel EM64T on Pentium 4 with EM64T, Pentium D, Core 2 Duo, Core I5/I7)
; Copyright (C) 1995-2010 Jean-loup Gailly, Brian Raiter and Gilles Vollant.
;
; File written by Gilles Vollant, by converting to assembly the longest_match
;  from Jean-loup Gailly in deflate.c of zLib and infoZip zip.
;
;  and by taking inspiration on asm686 with masm, optimised assembly code
;        from Brian Raiter, written 1998
;
;  This software is provided 'as-is', without any express or implied
;  warranty.  In no event will the authors be held liable for any damages
;  arising from the use of this software.
;
;  Permission is granted to anyone to use this software for any purpose,
;  including commercial applications, and to alter it and redistribute it
;  freely, subject to the following restrictions:
;
;  1. The origin of this software must not be misrepresented; you must not
;     claim that you wrote the original software. If you use this software
;     in a product, an acknowledgment in the product documentation would be
;     appreciated but is not required.
;  2. Altered source versions must be plainly marked as such, and must not be
;     misrepresented as being the original software
;  3. This notice may not be removed or altered from any source distribution.
;
;
;
;         http://www.zlib.net
;         http://www.winimage.com/zLibDll
;         http://www.muppetlabs.com/~breadbox/software/assembly.html
;
; to compile this file for infozip Zip, I use option:
;   ml64.exe /Flgvmat64 /c /Zi /DINFOZIP gvmat64.asm
;
; to compile this file for zLib, I use option:
;   ml64.exe /Flgvmat64 /c /Zi gvmat64.asm
; Be carrefull to adapt zlib1222add below to your version of zLib
;   (if you use a version of zLib before 1.0.4 or after 1.2.2.2, change
;    value of zlib1222add later)
;
; This file compile with Microsoft Macro Assembler (x64) for AMD64
;
;   ml64.exe is given with Visual Studio 2005/2008/2010 and Windows WDK
;
;   (you can get Windows WDK with ml64 for AMD64 from
;      http://www.microsoft.com/whdc/Devtools/wdk/default.mspx for low price)
;


;uInt longest_match(s, cur_match)
;    deflate_state *s;
;    IPos cur_match;                             /* current match */
.code
longest_match PROC


;LocalVarsSize   equ 88
 LocalVarsSize   equ 72

; register used : rax,rbx,rcx,rdx,rsi,rdi,r8,r9,r10,r11,r12
; free register :  r14,r15
; register can be saved : rsp

 chainlenwmask   equ  rsp + 8 - LocalVarsSize    ; high word: current chain len
                                                 ; low word: s->wmask
;window          equ  rsp + xx - LocalVarsSize   ; local copy of s->window ; stored in r10
;windowbestlen   equ  rsp + xx - LocalVarsSize   ; s->window + bestlen , use r10+r11
;scanstart       equ  rsp + xx - LocalVarsSize   ; first two bytes of string ; stored in r12w
;scanend         equ  rsp + xx - LocalVarsSize   ; last two bytes of string use ebx
;scanalign       equ  rsp + xx - LocalVarsSize   ; dword-misalignment of string r13
;bestlen         equ  rsp + xx - LocalVarsSize   ; size of best match so far -> r11d
;scan            equ  rsp + xx - LocalVarsSize   ; ptr to string wanting match -> r9
IFDEF INFOZIP
ELSE
 nicematch       equ  (rsp + 16 - LocalVarsSize) ; a good enough match size
ENDIF

save_rdi        equ  rsp + 24 - LocalVarsSize
save_rsi        equ  rsp + 32 - LocalVarsSize
save_rbx        equ  rsp + 40 - LocalVarsSize
save_rbp        equ  rsp + 48 - LocalVarsSize
save_r12        equ  rsp + 56 - LocalVarsSize
save_r13        equ  rsp + 64 - LocalVarsSize
;save_r14        equ  rsp + 72 - LocalVarsSize
;save_r15        equ  rsp + 80 - LocalVarsSize


; summary of register usage
; scanend     ebx
; scanendw    bx
; chainlenwmask   edx
; curmatch    rsi
; curmatchd   esi
; windowbestlen   r8
; scanalign   r9
; scanalignd  r9d
; window      r10
; bestlen     r11
; bestlend    r11d
; scanstart   r12d
; scanstartw  r12w