This commit was generated by cvs2svn to compensate for changes in r104181,

which included commits to RCS files with non-trunk default branches.


git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@104182 138bc75d-0d04-0410-961f-82ee72b054a4

37 files changed, 3772 insertions, 3244 deletions

diff --git a/zlib/contrib/ada/mtest.adb b/zlib/contrib/ada/mtest.adb
index 91a96cd1e9c..c4dfd080f0c 100644
--- a/zlib/contrib/ada/mtest.adb
+++ b/zlib/contrib/ada/mtest.adb
@@ -5,10 +5,10 @@
 --                                                            --
 --  Open source license information is in the zlib.ads file.  --
 ----------------------------------------------------------------
---  Continuous test for ZLib multithreading. If the test is fail
---  Wou should provide thread safe allocation routines for the Z_Stream.
+--  Continuous test for ZLib multithreading. If the test would fail
+--  we should provide thread safe allocation routines for the Z_Stream.
 --
---  $Id: mtest.adb,v 1.2 2003/08/12 12:11:05 vagul Exp $
+--  $Id: mtest.adb,v 1.4 2004/07/23 07:49:54 vagul Exp $
 
 with ZLib;
 with Ada.Streams;
@@ -148,6 +148,9 @@ procedure MTest is
 
    pragma Unreferenced (Test);
 
+   Dummy : Character;
+
 begin
-   null;
+   Ada.Text_IO.Get_Immediate (Dummy);
+   Stop := True;
 end MTest;
diff --git a/zlib/contrib/ada/read.adb b/zlib/contrib/ada/read.adb
index 184ea00c318..1f2efbfeb80 100644
--- a/zlib/contrib/ada/read.adb
+++ b/zlib/contrib/ada/read.adb
@@ -6,7 +6,7 @@
 --  Open source license information is in the zlib.ads file.  --
 ----------------------------------------------------------------
 
---  $Id: read.adb,v 1.7 2003/08/12 12:12:35 vagul Exp $
+--  $Id: read.adb,v 1.8 2004/05/31 10:53:40 vagul Exp $
 
 --  Test/demo program for the generic read interface.
 
@@ -68,7 +68,11 @@ procedure Read is
    --  ZLib.Read
    --  reading data from the File_In.
 
-   procedure Read is new ZLib.Read (Read, Read_Buffer, Read_First, Read_Last);
+   procedure Read is new ZLib.Read
+                           (Read,
+                            Read_Buffer,
+                            Rest_First => Read_First,
+                            Rest_Last  => Read_Last);
 
    ----------
    -- Read --
@@ -103,6 +107,7 @@ procedure Read is
       Pack_Size := 0;
       Offset := 1;
       Read_First := Read_Buffer'Last + 1;
+      Read_Last  := Read_Buffer'Last;
    end Reset;
 
 begin
diff --git a/zlib/contrib/ada/readme.txt b/zlib/contrib/ada/readme.txt
index ad02c225ad0..ce4d2cadf0d 100644
--- a/zlib/contrib/ada/readme.txt
+++ b/zlib/contrib/ada/readme.txt
@@ -1,23 +1,34 @@
-
-			ZLib for Ada thick binding (ZLib.Ada)
-			Release 1.2
+                        ZLib for Ada thick binding (ZLib.Ada)
+                        Release 1.3
 
 ZLib.Ada is a thick binding interface to the popular ZLib data
 compression library, available at http://www.gzip.org/zlib/.
 It provides Ada-style access to the ZLib C library.
 
 
-	Here are the main changes since ZLib.Ada 1.1:
+        Here are the main changes since ZLib.Ada 1.2:
+
+- Attension: ZLib.Read generic routine have a initialization requirement
+  for Read_Last parameter now. It is a bit incompartible with previous version,
+  but extends functionality, we could use new parameters Allow_Read_Some and
+  Flush now.
+
+- Added Is_Open routines to ZLib and ZLib.Streams packages.
 
-- The default header type has a name "Default" now. Auto is used only for
-  automatic GZip/ZLib header detection.
+- Add pragma Assert to check Stream_Element is 8 bit.
 
-- Added test for multitasking mtest.adb.
+- Fix extraction to buffer with exact known decompressed size. Error reported by
+  Steve Sangwine.
 
-- Added GNAT project file zlib.gpr.
+- Fix definition of ULong (changed to unsigned_long), fix regression on 64 bits
+  computers. Patch provided by Pascal Obry.
 
+- Add Status_Error exception definition.
 
-	How to build ZLib.Ada under GNAT
+- Add pragma Assertion that Ada.Streams.Stream_Element size is 8 bit.
+
+
+        How to build ZLib.Ada under GNAT
 
 You should have the ZLib library already build on your computer, before
 building ZLib.Ada. Make the directory of ZLib.Ada sources current and
@@ -30,7 +41,7 @@ Or use the GNAT project file build for GNAT 3.15 or later:
   gnatmake -Pzlib.gpr -L<directory where libz.a is>
 
 
-	How to build ZLib.Ada under Aonix ObjectAda for Win32 7.2.2
+        How to build ZLib.Ada under Aonix ObjectAda for Win32 7.2.2
 
 1. Make a project with all *.ads and *.adb files from the distribution.
 2. Build the libz.a library from the ZLib C sources.
@@ -40,7 +51,7 @@ Or use the GNAT project file build for GNAT 3.15 or later:
 6. Build the executable using test.adb as a main procedure.
 
 
-	How to use ZLib.Ada
+        How to use ZLib.Ada
 
 The source files test.adb and read.adb are small demo programs that show
 the main functionality of ZLib.Ada.
@@ -50,3 +61,5 @@ The routines from the package specifications are commented.
 
 Homepage: http://zlib-ada.sourceforge.net/
 Author: Dmitriy Anisimkov <anisimkov@yahoo.com>
+
+Contributors: Pascal Obry <pascal@obry.org>, Steve Sangwine <sjs@essex.ac.uk>
diff --git a/zlib/contrib/ada/zlib-streams.adb b/zlib/contrib/ada/zlib-streams.adb
index d213b5c1766..b6497bae286 100644
--- a/zlib/contrib/ada/zlib-streams.adb
+++ b/zlib/contrib/ada/zlib-streams.adb
@@ -6,7 +6,7 @@
 --  Open source license information is in the zlib.ads file.  --
 ----------------------------------------------------------------
 
---  $Id: zlib-streams.adb,v 1.9 2003/08/12 13:15:31 vagul Exp $
+--  $Id: zlib-streams.adb,v 1.10 2004/05/31 10:53:40 vagul Exp $
 
 with Ada.Unchecked_Deallocation;
 
@@ -90,6 +90,7 @@ package body ZLib.Streams is
 
          Stream.Buffer     := new Buffer_Subtype;
          Stream.Rest_First := Stream.Buffer'Last + 1;
+         Stream.Rest_Last  := Stream.Buffer'Last;
       end if;
    end Create;
 
@@ -113,6 +114,15 @@ package body ZLib.Streams is
       end loop;
    end Flush;
 
+   -------------
+   -- Is_Open --
+   -------------
+
+   function Is_Open (Stream : Stream_Type) return Boolean is
+   begin
+      return Is_Open (Stream.Reader) or else Is_Open (Stream.Writer);
+   end Is_Open;
+
    ----------
    -- Read --
    ----------
diff --git a/zlib/contrib/ada/zlib-streams.ads b/zlib/contrib/ada/zlib-streams.ads
index 1d5e9048991..f0193c6baee 100644
--- a/zlib/contrib/ada/zlib-streams.ads
+++ b/zlib/contrib/ada/zlib-streams.ads
@@ -6,7 +6,7 @@
 --  Open source license information is in the zlib.ads file.  --
 ----------------------------------------------------------------
 
---  $Id: zlib-streams.ads,v 1.11 2003/08/12 13:15:31 vagul Exp $
+--  $Id: zlib-streams.ads,v 1.12 2004/05/31 10:53:40 vagul Exp $
 
 package ZLib.Streams is
 
@@ -77,6 +77,8 @@ package ZLib.Streams is
    --  !!! When the Need_Header is False ZLib-Ada is using undocumented
    --  ZLib 1.1.4 functionality to do not create/wait for ZLib headers.
 
+   function Is_Open (Stream : Stream_Type) return Boolean;
+
    procedure Close (Stream : in out Stream_Type);
 
 private
diff --git a/zlib/contrib/ada/zlib-thin.adb b/zlib/contrib/ada/zlib-thin.adb
index 163bd5b972f..0ca4a712046 100644
--- a/zlib/contrib/ada/zlib-thin.adb
+++ b/zlib/contrib/ada/zlib-thin.adb
@@ -6,12 +6,11 @@
 --  Open source license information is in the zlib.ads file.  --
 ----------------------------------------------------------------
 
---  $Id: zlib-thin.adb,v 1.6 2003/01/21 15:26:37 vagul Exp $
+--  $Id: zlib-thin.adb,v 1.8 2003/12/14 18:27:31 vagul Exp $
 
 package body ZLib.Thin is
 
-   ZLIB_VERSION : constant Chars_Ptr :=
-      Interfaces.C.Strings.New_String ("1.1.4");
+   ZLIB_VERSION  : constant Chars_Ptr := zlibVersion;
 
    Z_Stream_Size : constant Int := Z_Stream'Size / System.Storage_Unit;
 
@@ -38,14 +37,6 @@ package body ZLib.Thin is
    ------------------
 
    function Deflate_Init
-     (strm  : in Z_Streamp;
-      level : in Int := Z_DEFAULT_COMPRESSION)
-      return  Int is
-   begin
-      return deflateInit (strm, level, ZLIB_VERSION, Z_Stream_Size);
-   end Deflate_Init;
-
-   function Deflate_Init
      (strm       : Z_Streamp;
       level      : Int;
       method     : Int;
@@ -69,16 +60,15 @@ package body ZLib.Thin is
    -- Inflate_Init --
    ------------------
 
-   function Inflate_Init (strm : Z_Streamp) return Int is
-   begin
-      return inflateInit (strm, ZLIB_VERSION, Z_Stream_Size);
-   end Inflate_Init;
-
    function Inflate_Init (strm : Z_Streamp; windowBits : Int) return Int is
    begin
       return inflateInit2 (strm, windowBits, ZLIB_VERSION, Z_Stream_Size);
    end Inflate_Init;
 
+   ------------------------
+   -- Last_Error_Message --
+   ------------------------
+
    function Last_Error_Message (Strm : in Z_Stream) return String is
       use Interfaces.C.Strings;
    begin
@@ -89,54 +79,28 @@ package body ZLib.Thin is
       end if;
    end Last_Error_Message;
 
-   -------------
-   -- Need_In --
-   -------------
-
-   function Need_In (strm : Z_Stream) return Boolean is
-   begin
-      return strm.Avail_In = 0;
-   end Need_In;
-
-   --------------
-   -- Need_Out --
-   --------------
-
-   function Need_Out (strm : Z_Stream) return Boolean is
-   begin
-      return strm.Avail_Out = 0;
-   end Need_Out;
-
    ------------
    -- Set_In --
    ------------
 
    procedure Set_In
      (Strm   : in out Z_Stream;
-      Buffer : in Byte_Access;
-      Size   : in UInt) is
+      Buffer : in     Voidp;
+      Size   : in     UInt) is
    begin
       Strm.Next_In  := Buffer;
       Strm.Avail_In := Size;
    end Set_In;
 
-   procedure Set_In
-     (Strm   : in out Z_Stream;
-      Buffer : in Voidp;
-      Size   : in UInt) is
-   begin
-      Set_In (Strm, Bytes.To_Pointer (Buffer), Size);
-   end Set_In;
-
    ------------------
    -- Set_Mem_Func --
    ------------------
 
    procedure Set_Mem_Func
      (Strm   : in out Z_Stream;
-      Opaque : in Voidp;
-      Alloc  : in alloc_func;
-      Free   : in free_func) is
+      Opaque : in     Voidp;
+      Alloc  : in     alloc_func;
+      Free   : in     free_func) is
    begin
       Strm.opaque := Opaque;
       Strm.zalloc := Alloc;
@@ -149,21 +113,13 @@ package body ZLib.Thin is
 
    procedure Set_Out
      (Strm   : in out Z_Stream;
-      Buffer : in Byte_Access;
-      Size   : in UInt) is
+      Buffer : in     Voidp;
+      Size   : in     UInt) is
    begin
       Strm.Next_Out  := Buffer;
       Strm.Avail_Out := Size;
    end Set_Out;
 
-   procedure Set_Out
-     (Strm   : in out Z_Stream;
-      Buffer : in Voidp;
-      Size   : in UInt) is
-   begin
-      Set_Out (Strm, Bytes.To_Pointer (Buffer), Size);
-   end Set_Out;
-
    --------------
    -- Total_In --
    --------------
diff --git a/zlib/contrib/ada/zlib-thin.ads b/zlib/contrib/ada/zlib-thin.ads
index c227374f64b..d4407eb800d 100644
--- a/zlib/contrib/ada/zlib-thin.ads
+++ b/zlib/contrib/ada/zlib-thin.ads
@@ -6,10 +6,11 @@
 --  Open source license information is in the zlib.ads file.  --
 ----------------------------------------------------------------
 
---  $Id: zlib-thin.ads,v 1.8 2003/08/12 13:16:51 vagul Exp $
+--  $Id: zlib-thin.ads,v 1.11 2004/07/23 06:33:11 vagul Exp $
 
 with Interfaces.C.Strings;
-with System.Address_To_Access_Conversions;
+
+with System;
 
 private package ZLib.Thin is
 
@@ -36,18 +37,18 @@ private package ZLib.Thin is
                                                 --  zconf.h:216
    type Int is new Interfaces.C.int;
 
-   type ULong is new Interfaces.C.unsigned;     --  32 bits or more
-                                                --  zconf.h:217
+   type ULong is new Interfaces.C.unsigned_long;     --  32 bits or more
+                                                     --  zconf.h:217
    subtype Chars_Ptr is Interfaces.C.Strings.chars_ptr;
 
    type ULong_Access is access ULong;
    type Int_Access is access Int;
-   subtype Voidp is System.Address;            --  zconf.h:232
 
-   package Bytes is new System.Address_To_Access_Conversions (Byte);
+   subtype Voidp is System.Address;            --  zconf.h:232
 
-   subtype Byte_Access is Bytes.Object_Pointer;
+   subtype Byte_Access is Voidp;
 
+   Nul : constant Voidp := System.Null_Address;
    --  end from zconf
 
    Z_NO_FLUSH : constant := 8#0000#;   --  zlib.h:125
@@ -251,12 +252,6 @@ private package ZLib.Thin is
       stream_size : Int)
       return        Int;
 
-   function Deflate_Init
-     (strm  : in Z_Streamp;
-      level : in Int := Z_DEFAULT_COMPRESSION)
-      return  Int;
-   pragma Inline (Deflate_Init);
-
    function deflateInit2
      (strm        : Z_Streamp;
       level       : Int;
@@ -284,9 +279,6 @@ private package ZLib.Thin is
       stream_size : Int)
       return        Int;
 
-   function Inflate_Init (strm : Z_Streamp) return Int;
-   pragma Inline (Inflate_Init);
-
    function inflateInit2
      (strm        : in Z_Streamp;
       windowBits  : in Int;
@@ -318,20 +310,6 @@ private package ZLib.Thin is
    --  has dropped to zero. The application must initialize zalloc, zfree and
    --  opaque before calling the init function.
 
-   function Need_In (strm : in Z_Stream) return Boolean;
-   --  return true when we do not need to setup Next_In and Avail_In fields.
-   pragma Inline (Need_In);
-
-   function Need_Out (strm : in Z_Stream) return Boolean;
-   --  return true when we do not need to setup Next_Out and Avail_Out field.
-   pragma Inline (Need_Out);
-
-   procedure Set_In
-     (Strm   : in out Z_Stream;
-      Buffer : in Byte_Access;
-      Size   : in UInt);
-   pragma Inline (Set_In);
-
    procedure Set_In
      (Strm   : in out Z_Stream;
       Buffer : in Voidp;
@@ -340,12 +318,6 @@ private package ZLib.Thin is
 
    procedure Set_Out
      (Strm   : in out Z_Stream;
-      Buffer : in Byte_Access;
-      Size   : in UInt);
-   pragma Inline (Set_Out);
-
-   procedure Set_Out
-     (Strm   : in out Z_Stream;
       Buffer : in Voidp;
       Size   : in UInt);
    pragma Inline (Set_Out);
@@ -388,19 +360,13 @@ private package ZLib.Thin is
 
    function zlibCompileFlags return ULong;
 
-   function deflatePrime
-     (strm     : Z_Streamp;
-      bits     : Int;
-      value    : Int)
-      return     Int;
-
 private
 
    type Z_Stream is record            -- zlib.h:68
-      Next_In   : Byte_Access;        -- next input byte
+      Next_In   : Voidp      := Nul;  -- next input byte
       Avail_In  : UInt       := 0;    -- number of bytes available at next_in
       Total_In  : ULong      := 0;    -- total nb of input bytes read so far
-      Next_Out  : Byte_Access;        -- next output byte should be put there
+      Next_Out  : Voidp      := Nul;  -- next output byte should be put there
       Avail_Out : UInt       := 0;    -- remaining free space at next_out
       Total_Out : ULong      := 0;    -- total nb of bytes output so far
       msg       : Chars_Ptr;          -- last error message, NULL if no error
@@ -460,14 +426,13 @@ private
    pragma Import (C, inflateSyncPoint, "inflateSyncPoint");
    pragma Import (C, get_crc_table, "get_crc_table");
 
-   --  added in zlib 1.2.1:
+   --  since zlib 1.2.0:
 
    pragma Import (C, inflateCopy, "inflateCopy");
    pragma Import (C, compressBound, "compressBound");
    pragma Import (C, deflateBound, "deflateBound");
    pragma Import (C, gzungetc, "gzungetc");
    pragma Import (C, zlibCompileFlags, "zlibCompileFlags");
-   pragma Import (C, deflatePrime, "deflatePrime");
 
    pragma Import (C, inflateBackInit, "inflateBackInit_");
 
diff --git a/zlib/contrib/ada/zlib.adb b/zlib/contrib/ada/zlib.adb
index 93bf8852f72..8b6fd686ac7 100644
--- a/zlib/contrib/ada/zlib.adb
+++ b/zlib/contrib/ada/zlib.adb
@@ -1,12 +1,12 @@
 ----------------------------------------------------------------
 --  ZLib for Ada thick binding.                               --
 --                                                            --
---  Copyright (C) 2002-2003 Dmitriy Anisimkov                 --
+--  Copyright (C) 2002-2004 Dmitriy Anisimkov                 --
 --                                                            --
 --  Open source license information is in the zlib.ads file.  --
 ----------------------------------------------------------------
 
---  $Id: zlib.adb,v 1.19 2003/07/13 16:02:19 vagul Exp $
+--  $Id: zlib.adb,v 1.31 2004/09/06 06:53:19 vagul Exp $
 
 with Ada.Exceptions;
 with Ada.Unchecked_Conversion;
@@ -34,7 +34,7 @@ package body ZLib is
        VERSION_ERROR);
 
    type Flate_Step_Function is access
-     function (Strm : Thin.Z_Streamp; flush : Thin.Int) return Thin.Int;
+     function (Strm : in Thin.Z_Streamp; Flush : in Thin.Int) return Thin.Int;
    pragma Convention (C, Flate_Step_Function);
 
    type Flate_End_Function is access
@@ -82,13 +82,13 @@ package body ZLib is
    Flush_Finish : constant array (Boolean) of Flush_Mode
      := (True => Finish, False => No_Flush);
 
-   procedure Raise_Error (Stream : Z_Stream);
+   procedure Raise_Error (Stream : in Z_Stream);
    pragma Inline (Raise_Error);
 
-   procedure Raise_Error (Message : String);
+   procedure Raise_Error (Message : in String);
    pragma Inline (Raise_Error);
 
-   procedure Check_Error (Stream : Z_Stream; Code : Thin.Int);
+   procedure Check_Error (Stream : in Z_Stream; Code : in Thin.Int);
 
    procedure Free is new Ada.Unchecked_Deallocation
       (Z_Stream, Z_Stream_Access);
@@ -118,7 +118,7 @@ package body ZLib is
    -- Check_Error --
    -----------------
 
-   procedure Check_Error (Stream : Z_Stream; Code : Thin.Int) is
+   procedure Check_Error (Stream : in Z_Stream; Code : in Thin.Int) is
       use type Thin.Int;
    begin
       if Code /= Thin.Z_OK then
@@ -138,10 +138,11 @@ package body ZLib is
    is
       Code : Thin.Int;
    begin
-      Code := Flate (Filter.Compression).Done
-          (To_Thin_Access (Filter.Strm));
+      if not Ignore_Error and then not Is_Open (Filter) then
+         raise Status_Error;
+      end if;
 
-      Filter.Opened := False;
+      Code := Flate (Filter.Compression).Done (To_Thin_Access (Filter.Strm));
 
       if Ignore_Error or else Code = Thin.Z_OK then
          Free (Filter.Strm);
@@ -154,7 +155,7 @@ package body ZLib is
             Ada.Exceptions.Raise_Exception
                (ZLib_Error'Identity,
                 Return_Code_Enum'Image (Return_Code (Code))
-                & ": " & Error_Message);
+                  & ": " & Error_Message);
          end;
       end if;
    end Close;
@@ -170,10 +171,9 @@ package body ZLib is
    is
       use Thin;
    begin
-      return Unsigned_32 (crc32
-        (ULong (CRC),
-         Bytes.To_Pointer (Data'Address),
-         Data'Length));
+      return Unsigned_32 (crc32 (ULong (CRC),
+                                 Data'Address,
+                                 Data'Length));
    end CRC32;
 
    procedure CRC32
@@ -192,13 +192,17 @@ package body ZLib is
       Level        : in     Compression_Level  := Default_Compression;
       Strategy     : in     Strategy_Type      := Default_Strategy;
       Method       : in     Compression_Method := Deflated;
-      Window_Bits  : in     Window_Bits_Type   := 15;
-      Memory_Level : in     Memory_Level_Type  := 8;
+      Window_Bits  : in     Window_Bits_Type   := Default_Window_Bits;
+      Memory_Level : in     Memory_Level_Type  := Default_Memory_Level;
       Header       : in     Header_Type        := Default)
    is
       use type Thin.Int;
       Win_Bits : Thin.Int := Thin.Int (Window_Bits);
    begin
+      if Is_Open (Filter) then
+         raise Status_Error;
+      end if;
+
       --  We allow ZLib to make header only in case of default header type.
       --  Otherwise we would either do header by ourselfs, or do not do
       --  header at all.
@@ -216,10 +220,9 @@ package body ZLib is
          Filter.Offset := Simple_GZip_Header'Last + 1;
       end if;
 
-      Filter.Strm := new Z_Stream;
+      Filter.Strm        := new Z_Stream;
       Filter.Compression := True;
       Filter.Stream_End  := False;
-      Filter.Opened      := True;
       Filter.Header      := Header;
 
       if Thin.Deflate_Init
@@ -255,18 +258,18 @@ package body ZLib is
    -----------------------
 
    procedure Generic_Translate
-     (Filter : in out ZLib.Filter_Type;
-      In_Buffer_Size  : Integer := Default_Buffer_Size;
-      Out_Buffer_Size : Integer := Default_Buffer_Size)
+     (Filter          : in out ZLib.Filter_Type;
+      In_Buffer_Size  : in     Integer := Default_Buffer_Size;
+      Out_Buffer_Size : in     Integer := Default_Buffer_Size)
    is
-      In_Buffer : Stream_Element_Array
-         (1 .. Stream_Element_Offset (In_Buffer_Size));
+      In_Buffer  : Stream_Element_Array
+                     (1 .. Stream_Element_Offset (In_Buffer_Size));
       Out_Buffer : Stream_Element_Array
-        (1 .. Stream_Element_Offset (Out_Buffer_Size));
-      Last : Stream_Element_Offset;
-      In_Last : Stream_Element_Offset;
-      In_First : Stream_Element_Offset;
-      Out_Last : Stream_Element_Offset;
+                     (1 .. Stream_Element_Offset (Out_Buffer_Size));
+      Last       : Stream_Element_Offset;
+      In_Last    : Stream_Element_Offset;
+      In_First   : Stream_Element_Offset;
+      Out_Last   : Stream_Element_Offset;
    begin
       Main : loop
          Data_In (In_Buffer, Last);
@@ -275,18 +278,21 @@ package body ZLib is
 
          loop
             Translate
-              (Filter,
-               In_Buffer (In_First .. Last),
-               In_Last,
-               Out_Buffer,
-               Out_Last,
-               Flush_Finish (Last < In_Buffer'First));
+              (Filter   => Filter,
+               In_Data  => In_Buffer (In_First .. Last),
+               In_Last  => In_Last,
+               Out_Data => Out_Buffer,
+               Out_Last => Out_Last,
+               Flush    => Flush_Finish (Last < In_Buffer'First));
 
-            Data_Out (Out_Buffer (Out_Buffer'First .. Out_Last));
+            if Out_Buffer'First <= Out_Last then
+               Data_Out (Out_Buffer (Out_Buffer'First .. Out_Last));
+            end if;
 
             exit Main when Stream_End (Filter);
 
             --  The end of in buffer.
+
             exit when In_Last = Last;
 
             In_First := In_Last + 1;
@@ -301,7 +307,7 @@ package body ZLib is
 
    procedure Inflate_Init
      (Filter      : in out Filter_Type;
-      Window_Bits : in     Window_Bits_Type := 15;
+      Window_Bits : in     Window_Bits_Type := Default_Window_Bits;
       Header      : in     Header_Type      := Default)
    is
       use type Thin.Int;
@@ -320,6 +326,10 @@ package body ZLib is
       end Check_Version;
 
    begin
+      if Is_Open (Filter) then
+         raise Status_Error;
+      end if;
+
       case Header is
          when None =>
             Check_Version;
@@ -344,10 +354,9 @@ package body ZLib is
          when Default => null;
       end case;
 
-      Filter.Strm := new Z_Stream;
+      Filter.Strm        := new Z_Stream;
       Filter.Compression := False;
       Filter.Stream_End  := False;
-      Filter.Opened      := True;
       Filter.Header      := Header;
 
       if Thin.Inflate_Init
@@ -357,16 +366,25 @@ package body ZLib is
       end if;
    end Inflate_Init;
 
+   -------------
+   -- Is_Open --
+   -------------
+
+   function Is_Open (Filter : in Filter_Type) return Boolean is
+   begin
+      return Filter.Strm /= null;
+   end Is_Open;
+
    -----------------
    -- Raise_Error --
    -----------------
 
-   procedure Raise_Error (Message : String) is
+   procedure Raise_Error (Message : in String) is
    begin
       Ada.Exceptions.Raise_Exception (ZLib_Error'Identity, Message);
    end Raise_Error;
 
-   procedure Raise_Error (Stream : Z_Stream) is
+   procedure Raise_Error (Stream : in Z_Stream) is
    begin
       Raise_Error (Last_Error_Message (Stream));
    end Raise_Error;
@@ -378,21 +396,29 @@ package body ZLib is
    procedure Read
      (Filter : in out Filter_Type;
       Item   :    out Ada.Streams.Stream_Element_Array;
-      Last   :    out Ada.Streams.Stream_Element_Offset)
+      Last   :    out Ada.Streams.Stream_Element_Offset;
+      Flush  : in     Flush_Mode := No_Flush)
    is
       In_Last    : Stream_Element_Offset;
       Item_First : Ada.Streams.Stream_Element_Offset := Item'First;
+      V_Flush    : Flush_Mode := Flush;
 
    begin
       pragma Assert (Rest_First in Buffer'First .. Buffer'Last + 1);
+      pragma Assert (Rest_Last in Buffer'First - 1 .. Buffer'Last);
 
       loop
-         if Rest_First > Buffer'Last then
+         if Rest_Last = Buffer'First - 1 then
+            V_Flush := Finish;
+
+         elsif Rest_First > Rest_Last then
             Read (Buffer, Rest_Last);
             Rest_First := Buffer'First;
-         end if;
 
-         pragma Assert (Rest_Last in Buffer'First - 1 .. Buffer'Last);
+            if Rest_Last < Buffer'First then
+               V_Flush := Finish;
+            end if;
+         end if;
 
          Translate
            (Filter   => Filter,
@@ -400,11 +426,13 @@ package body ZLib is
             In_Last  => In_Last,
             Out_Data => Item (Item_First .. Item'Last),
             Out_Last => Last,
-            Flush    => Flush_Finish (Rest_Last < Rest_First));
+            Flush    => V_Flush);
 
          Rest_First := In_Last + 1;
 
-         exit when Last = Item'Last or else Stream_End (Filter);
+         exit when Stream_End (Filter)
+           or else Last = Item'Last
+           or else (Last >= Item'First and then Allow_Read_Some);
 
          Item_First := Last + 1;
       end loop;
@@ -489,11 +517,11 @@ package body ZLib is
       Code : Thin.Int;
 
    begin
-      if Filter.Opened = False then
-         raise ZLib_Error;
+      if not Is_Open (Filter) then
+         raise Status_Error;
       end if;
 
-      if Out_Data'Length = 0 then
+      if Out_Data'Length = 0 and then In_Data'Length = 0 then
          raise Constraint_Error;
       end if;
 
@@ -514,7 +542,6 @@ package body ZLib is
          - Stream_Element_Offset (Avail_In (Filter.Strm.all));
       Out_Last := Out_Data'Last
          - Stream_Element_Offset (Avail_Out (Filter.Strm.all));
-
    end Translate_Auto;
 
    --------------------
@@ -529,7 +556,7 @@ package body ZLib is
       Out_Last  :    out Ada.Streams.Stream_Element_Offset;
       Flush     : in     Flush_Mode)
    is
-      Out_First  : Stream_Element_Offset;
+      Out_First : Stream_Element_Offset;
 
       procedure Add_Data (Data : in Stream_Element_Array);
       --  Add data to stream from the Filter.Offset till necessary,
@@ -596,7 +623,7 @@ package body ZLib is
          Add_Data (Simple_GZip_Header);
 
          Translate_Auto
-           (Filter => Filter,
+           (Filter   => Filter,
             In_Data  => In_Data,
             In_Last  => In_Last,
             Out_Data => Out_Data (Out_First .. Out_Data'Last),
@@ -604,7 +631,6 @@ package body ZLib is
             Flush    => Flush);
 
          CRC32 (Filter.CRC, In_Data (In_Data'First .. In_Last));
-
       end if;
 
       if Filter.Stream_End and then Out_Last <= Out_Data'Last then
@@ -642,10 +668,11 @@ package body ZLib is
    procedure Write
      (Filter : in out Filter_Type;
       Item   : in     Ada.Streams.Stream_Element_Array;
-      Flush  : in     Flush_Mode)
+      Flush  : in     Flush_Mode := No_Flush)
    is
-      Buffer : Stream_Element_Array (1 .. Buffer_Size);
-      In_Last, Out_Last : Stream_Element_Offset;
+      Buffer   : Stream_Element_Array (1 .. Buffer_Size);
+      In_Last  : Stream_Element_Offset;
+      Out_Last : Stream_Element_Offset;
       In_First : Stream_Element_Offset := Item'First;
    begin
       if Item'Length = 0 and Flush = No_Flush then
@@ -654,7 +681,7 @@ package body ZLib is
 
       loop
          Translate
-           (Filter => Filter,
+           (Filter   => Filter,
             In_Data  => Item (In_First .. Item'Last),
             In_Last  => In_Last,
             Out_Data => Buffer,
diff --git a/zlib/contrib/ada/zlib.ads b/zlib/contrib/ada/zlib.ads
index b72e4d2d5d7..79ffc4095cf 100644
--- a/zlib/contrib/ada/zlib.ads
+++ b/zlib/contrib/ada/zlib.ads
@@ -1,7 +1,7 @@
 ------------------------------------------------------------------------------
 --                      ZLib for Ada thick binding.                         --
 --                                                                          --
---              Copyright (C) 2002-2003 Dmitriy Anisimkov                   --
+--              Copyright (C) 2002-2004 Dmitriy Anisimkov                   --
 --                                                                          --
 --  This library is free software; you can redistribute it and/or modify    --
 --  it under the terms of the GNU General Public License as published by    --
@@ -25,7 +25,7 @@
 --  covered by the  GNU Public License.                                     --
 ------------------------------------------------------------------------------
 
---  $Id: zlib.ads,v 1.17 2003/08/12 13:19:07 vagul Exp $
+--  $Id: zlib.ads,v 1.26 2004/09/06 06:53:19 vagul Exp $
 
 with Ada.Streams;
 
@@ -33,7 +33,8 @@ with Interfaces;
 
 package ZLib is
 
-   ZLib_Error : exception;
+   ZLib_Error   : exception;
+   Status_Error : exception;
 
    type Compression_Level is new Integer range -1 .. 9;
 
@@ -55,12 +56,15 @@ package ZLib is
 
    subtype Count is Ada.Streams.Stream_Element_Count;
 
+   Default_Memory_Level : constant Memory_Level_Type := 8;
+   Default_Window_Bits  : constant Window_Bits_Type  := 15;
+
    ----------------------------------
    -- Compression method constants --
    ----------------------------------
 
    Deflated : constant Compression_Method;
-   --  Only one method allowed in this ZLib version.
+   --  Only one method allowed in this ZLib version
 
    ---------------------------------
    -- Compression level constants --
@@ -79,21 +83,29 @@ package ZLib is
    --  Regular way for compression, no flush
 
    Partial_Flush : constant Flush_Mode;
-   --  will be removed, use Z_SYNC_FLUSH instead
+   --  Will be removed, use Z_SYNC_FLUSH instead
 
    Sync_Flush    : constant Flush_Mode;
-   --  all pending output is flushed to the output buffer and the output
+   --  All pending output is flushed to the output buffer and the output
    --  is aligned on a byte boundary, so that the decompressor can get all
    --  input data available so far. (In particular avail_in is zero after the
    --  call if enough output space has been provided  before the call.)
    --  Flushing may degrade compression for some compression algorithms and so
    --  it should be used only when necessary.
 
+   Block_Flush   : constant Flush_Mode;
+   --  Z_BLOCK requests that inflate() stop
+   --  if and when it get to the next deflate block boundary. When decoding the
+   --  zlib or gzip format, this will cause inflate() to return immediately
+   --  after the header and before the first block. When doing a raw inflate,
+   --  inflate() will go ahead and process the first block, and will return
+   --  when it gets to the end of that block, or when it runs out of data.
+
    Full_Flush    : constant Flush_Mode;
-   --  all output is flushed as with SYNC_FLUSH, and the compression state
+   --  All output is flushed as with SYNC_FLUSH, and the compression state
    --  is reset so that decompression can restart from this point if previous
    --  compressed data has been damaged or if random access is desired. Using
-   --  FULL_FLUSH too often can seriously degrade the compression.
+   --  Full_Flush too often can seriously degrade the compression.
 
    Finish        : constant Flush_Mode;
    --  Just for tell the compressor that input data is complete.
@@ -111,7 +123,7 @@ package ZLib is
 
    Default_Buffer_Size : constant := 4096;
 
-   type Filter_Type is limited private;
+   type Filter_Type is tagged limited private;
    --  The filter is for compression and for decompression.
    --  The usage of the type is depend of its initialization.
 
@@ -124,8 +136,8 @@ package ZLib is
       Level        : in     Compression_Level  := Default_Compression;
       Strategy     : in     Strategy_Type      := Default_Strategy;
       Method       : in     Compression_Method := Deflated;
-      Window_Bits  : in     Window_Bits_Type   := 15;
-      Memory_Level : in     Memory_Level_Type  := 8;
+      Window_Bits  : in     Window_Bits_Type   := Default_Window_Bits;
+      Memory_Level : in     Memory_Level_Type  := Default_Memory_Level;
       Header       : in     Header_Type        := Default);
    --  Compressor initialization.
    --  When Header parameter is Auto or Default, then default zlib header
@@ -136,7 +148,7 @@ package ZLib is
 
    procedure Inflate_Init
      (Filter      : in out Filter_Type;
-      Window_Bits : in     Window_Bits_Type := 15;
+      Window_Bits : in     Window_Bits_Type := Default_Window_Bits;
       Header      : in     Header_Type      := Default);
    --  Decompressor initialization.
    --  Default header type mean that ZLib default header is expecting in the
@@ -146,10 +158,14 @@ package ZLib is
    --  input compressed stream.
    --  Auto header type mean that header type (GZip or Native) would be
    --  detected automatically in the input stream.
-   --  Note that header types parameter values None, GZip and Auto is
-   --  supporting for inflate routine only in ZLib versions 1.2.0.2 and later.
+   --  Note that header types parameter values None, GZip and Auto are
+   --  supported for inflate routine only in ZLib versions 1.2.0.2 and later.
    --  Deflate_Init is supporting all header types.
 
+   function Is_Open (Filter : in Filter_Type) return Boolean;
+   pragma Inline (Is_Open);
+   --  Is the filter opened for compression or decompression.
+
    procedure Close
      (Filter       : in out Filter_Type;
       Ignore_Error : in     Boolean := False);
@@ -167,31 +183,31 @@ package ZLib is
      (Filter          : in out Filter_Type;
       In_Buffer_Size  : in     Integer := Default_Buffer_Size;
       Out_Buffer_Size : in     Integer := Default_Buffer_Size);
-   --  Compressing/decompressing data arrived from Data_In routine
+   --  Compress/decompress data fetch from Data_In routine and pass the result
    --  to the Data_Out routine. User should provide Data_In and Data_Out
    --  for compression/decompression data flow.
-   --  Compression or decompression depend on initialization of Filter.
+   --  Compression or decompression depend on Filter initialization.
 
    function Total_In (Filter : in Filter_Type) return Count;
    pragma Inline (Total_In);
-   --  Return total number of input bytes read so far.
+   --  Returns total number of input bytes read so far
 
    function Total_Out (Filter : in Filter_Type) return Count;
    pragma Inline (Total_Out);
-   --  Return total number of bytes output so far.
+   --  Returns total number of bytes output so far
 
    function CRC32
      (CRC    : in Unsigned_32;
       Data   : in Ada.Streams.Stream_Element_Array)
       return Unsigned_32;
    pragma Inline (CRC32);
-   --  Calculate CRC32, it could be necessary for make gzip format.
+   --  Compute CRC32, it could be necessary for make gzip format
 
    procedure CRC32
      (CRC  : in out Unsigned_32;
       Data : in     Ada.Streams.Stream_Element_Array);
    pragma Inline (CRC32);
-   --  Calculate CRC32, it could be necessary for make gzip format.
+   --  Compute CRC32, it could be necessary for make gzip format
 
    -------------------------------------------------
    --  Below is more complex low level routines.  --
@@ -204,15 +220,11 @@ package ZLib is
       Out_Data  :    out Ada.Streams.Stream_Element_Array;
       Out_Last  :    out Ada.Streams.Stream_Element_Offset;
       Flush     : in     Flush_Mode);
-   --  Compressing/decompressing the datas from In_Data buffer to the
-   --  Out_Data buffer.
-   --  In_Data is incoming data portion,
-   --  In_Last is the index of last element from In_Data accepted by the
-   --  Filter.
-   --  Out_Data is the buffer for output data from the filter.
-   --  Out_Last is the last element of the received data from Filter.
-   --  To tell the filter that incoming data is complete put the
-   --  Flush parameter to FINISH.
+   --  Compress/decompress the In_Data buffer and place the result into
+   --  Out_Data. In_Last is the index of last element from In_Data accepted by
+   --  the Filter. Out_Last is the last element of the received data from
+   --  Filter. To tell the filter that incoming data are complete put the
+   --  Flush parameter to Finish.
 
    function Stream_End (Filter : in Filter_Type) return Boolean;
    pragma Inline (Stream_End);
@@ -239,10 +251,9 @@ package ZLib is
    procedure Write
      (Filter  : in out Filter_Type;
       Item    : in     Ada.Streams.Stream_Element_Array;
-      Flush   : in     Flush_Mode);
-   --  Compressing/Decompressing data from Item to the
-   --  generic parameter procedure Write.
-   --  Output buffer size could be set in Buffer_Size generic parameter.
+      Flush   : in     Flush_Mode := No_Flush);
+   --  Compress/Decompress data from Item to the generic parameter procedure
+   --  Write. Output buffer size could be set in Buffer_Size generic parameter.
 
    generic
       with procedure Read
@@ -257,33 +268,41 @@ package ZLib is
 
       Rest_First, Rest_Last : in out Ada.Streams.Stream_Element_Offset;
       --  Rest_First have to be initialized to Buffer'Last + 1
+      --  Rest_Last have to be initialized to Buffer'Last
       --  before usage.
 
+      Allow_Read_Some : in Boolean := False;
+      --  Is it allowed to return Last < Item'Last before end of data.
+
    procedure Read
      (Filter : in out Filter_Type;
       Item   :    out Ada.Streams.Stream_Element_Array;
-      Last   :    out Ada.Streams.Stream_Element_Offset);
-   --  Compressing/Decompressing data from generic parameter
-   --  procedure Read to the Item.
-   --  User should provide Buffer for the operation
-   --  and Rest_First variable first time initialized to the Buffer'Last + 1.
+      Last   :    out Ada.Streams.Stream_Element_Offset;
+      Flush  : in     Flush_Mode := No_Flush);
+   --  Compress/Decompress data from generic parameter procedure Read to the
+   --  Item. User should provide Buffer and initialized Rest_First, Rest_Last
+   --  indicators. If Allow_Read_Some is True, Read routines could return
+   --  Last < Item'Last only at end of stream.
 
 private
 
    use Ada.Streams;
 
-   type Flush_Mode is new Integer range 0 .. 4;
+   pragma Assert (Ada.Streams.Stream_Element'Size    =    8);
+   pragma Assert (Ada.Streams.Stream_Element'Modulus = 2**8);
+
+   type Flush_Mode is new Integer range 0 .. 5;
 
    type Compression_Method is new Integer range 8 .. 8;
 
    type Strategy_Type is new Integer range 0 .. 3;
 
    No_Flush      : constant Flush_Mode := 0;
+   Partial_Flush : constant Flush_Mode := 1;
    Sync_Flush    : constant Flush_Mode := 2;
    Full_Flush    : constant Flush_Mode := 3;
    Finish        : constant Flush_Mode := 4;
-   Partial_Flush : constant Flush_Mode := 1;
-   --  will be removed, use Z_SYNC_FLUSH instead
+   Block_Flush   : constant Flush_Mode := 5;
 
    Filtered         : constant Strategy_Type := 1;
    Huffman_Only     : constant Strategy_Type := 2;
@@ -296,7 +315,7 @@ private
 
    type Z_Stream_Access is access all Z_Stream;
 
-   type Filter_Type is record
+   type Filter_Type is tagged limited record
       Strm        : Z_Stream_Access;
       Compression : Boolean;
       Stream_End  : Boolean;
@@ -304,8 +323,6 @@ private
       CRC         : Unsigned_32;
       Offset      : Stream_Element_Offset;
       --  Offset for gzip header/footer output.
-
-      Opened      : Boolean := False;
    end record;
 
 end ZLib;
diff --git a/zlib/contrib/ada/zlib.gpr b/zlib/contrib/ada/zlib.gpr
index 0f58985e30b..296b22aa966 100644
--- a/zlib/contrib/ada/zlib.gpr
+++ b/zlib/contrib/ada/zlib.gpr
@@ -3,10 +3,10 @@ project Zlib is
    for Languages use ("Ada");
    for Source_Dirs use (".");
    for Object_Dir use ".";
-   for Main use ("test.adb", "mtest.adb", "read.adb");
+   for Main use ("test.adb", "mtest.adb", "read.adb", "buffer_demo");
 
    package Compiler is
-      for Default_Switches ("ada") use ("-gnatwbcfilopru", "-gnatVcdfimorst", "-gnatyabcefhiklmnoprst");
+      for Default_Switches ("ada") use ("-gnatwcfilopru", "-gnatVcdfimorst", "-gnatyabcefhiklmnoprst");
    end Compiler;
 
    package Linker is
@@ -18,4 +18,3 @@ project Zlib is
    end Builder;
 
 end Zlib;
-
diff --git a/zlib/contrib/delphi/ZLib.pas b/zlib/contrib/delphi/ZLib.pas
index 61ffd08fd1a..3f2b8b4a5cd 100644
--- a/zlib/contrib/delphi/ZLib.pas
+++ b/zlib/contrib/delphi/ZLib.pas
@@ -152,7 +152,7 @@ procedure DecompressToUserBuf(const InBuf: Pointer; InBytes: Integer;
   const OutBuf: Pointer; BufSize: Integer);
 
 const
-  zlib_version = '1.2.1';
+  zlib_version = '1.2.3';
 
 type
   EZlibError = class(Exception);
@@ -344,7 +344,7 @@ begin
     strm.avail_out := OutBytes;
     DCheck(inflateInit_(strm, zlib_version, sizeof(strm)));
     try
-      while DCheck(inflate(strm, Z_FINISH)) <> Z_STREAM_END do
+      while DCheck(inflate(strm, Z_NO_FLUSH)) <> Z_STREAM_END do
       begin
         P := OutBuf;
         Inc(OutBytes, BufInc);
@@ -510,7 +510,7 @@ begin
         Result := Count - FZRec.avail_out;
         Exit;
       end;
-          FZRec.next_in := FBuffer;
+      FZRec.next_in := FBuffer;
       FStrmPos := FStrm.Position;
       Progress(Self);
     end;
diff --git a/zlib/contrib/infback9/infback9.c b/zlib/contrib/infback9/infback9.c
index 34a95fc0dac..f5ddde67da6 100644
--- a/zlib/contrib/infback9/infback9.c
+++ b/zlib/contrib/infback9/infback9.c
@@ -430,6 +430,9 @@ void FAR *out_desc;
                 }
             }
 
+            /* handle error breaks in while */
+            if (mode == BAD) break;
+
             /* build code tables */
             state->next = state->codes;
             lencode = (code const FAR *)(state->next);
diff --git a/zlib/contrib/infback9/infback9.h b/zlib/contrib/infback9/infback9.h
index 10bf58c368e..1073c0a38e6 100644
--- a/zlib/contrib/infback9/infback9.h
+++ b/zlib/contrib/infback9/infback9.h
@@ -16,6 +16,10 @@
  * zlib.h must be included before this header file.
  */
 
+#ifdef __cplusplus
+extern "C" {
+#endif
+
 ZEXTERN int ZEXPORT inflateBack9 OF((z_stream FAR *strm,
                                     in_func in, void FAR *in_desc,
                                     out_func out, void FAR *out_desc));
@@ -27,3 +31,7 @@ ZEXTERN int ZEXPORT inflateBack9Init_ OF((z_stream FAR *strm,
 #define inflateBack9Init(strm, window) \
         inflateBack9Init_((strm), (window), \
         ZLIB_VERSION, sizeof(z_stream))
+
+#ifdef __cplusplus
+}
+#endif
diff --git a/zlib/contrib/infback9/inftree9.c b/zlib/contrib/infback9/inftree9.c
index fe76a1b1cd8..0993f75646c 100644
--- a/zlib/contrib/infback9/inftree9.c
+++ b/zlib/contrib/infback9/inftree9.c
@@ -1,5 +1,5 @@
 /* inftree9.c -- generate Huffman trees for efficient decoding
- * Copyright (C) 1995-2003 Mark Adler
+ * Copyright (C) 1995-2005 Mark Adler
  * For conditions of distribution and use, see copyright notice in zlib.h
  */
 
@@ -9,7 +9,7 @@
 #define MAXBITS 15
 
 const char inflate9_copyright[] =
-   " inflate9 1.2.1 Copyright 1995-2003 Mark Adler ";
+   " inflate9 1.2.3 Copyright 1995-2005 Mark Adler ";
 /*
   If you use the zlib library in a product, an acknowledgment is welcome
   in the documentation of your product. If for some reason you cannot
@@ -64,7 +64,7 @@ unsigned short FAR *work;
     static const unsigned short lext[31] = { /* Length codes 257..285 extra */
         128, 128, 128, 128, 128, 128, 128, 128, 129, 129, 129, 129,
         130, 130, 130, 130, 131, 131, 131, 131, 132, 132, 132, 132,
-        133, 133, 133, 133, 144, 76, 66};
+        133, 133, 133, 133, 144, 201, 196};
     static const unsigned short dbase[32] = { /* Distance codes 0..31 base */
         1, 2, 3, 4, 5, 7, 9, 13, 17, 25, 33, 49,
         65, 97, 129, 193, 257, 385, 513, 769, 1025, 1537, 2049, 3073,
@@ -128,7 +128,7 @@ unsigned short FAR *work;
         left -= count[len];
         if (left < 0) return -1;        /* over-subscribed */
     }
-    if (left > 0 && (type == CODES || (codes - count[0] != 1)))
+    if (left > 0 && (type == CODES || max != 1))
         return -1;                      /* incomplete set */
 
     /* generate offsets into symbol table for each length for sorting */
diff --git a/zlib/contrib/infback9/inftree9.h b/zlib/contrib/infback9/inftree9.h
index 6a699a798f5..a268084eea6 100644
--- a/zlib/contrib/infback9/inftree9.h
+++ b/zlib/contrib/infback9/inftree9.h
@@ -36,12 +36,12 @@ typedef struct {
  */
 
 /* Maximum size of dynamic tree.  The maximum found in a long but non-
-   exhaustive search was 1004 code structures (850 for length/literals
-   and 154 for distances, the latter actually the result of an
+   exhaustive search was 1444 code structures (852 for length/literals
+   and 592 for distances, the latter actually the result of an
    exhaustive search).  The true maximum is not known, but the value
    below is more than safe. */
-#define ENOUGH 1440
-#define MAXD 154
+#define ENOUGH 2048
+#define MAXD 592
 
 /* Type of code to build for inftable() */
 typedef enum {
diff --git a/zlib/contrib/inflate86/inffas86.c b/zlib/contrib/inflate86/inffas86.c
index 4534693a47d..6da76358ccb 100644
--- a/zlib/contrib/inflate86/inffas86.c
+++ b/zlib/contrib/inflate86/inffas86.c
@@ -7,6 +7,15 @@
  * Copyright (C) 2003 Chris Anderson <christop@charm.net>
  * Please use the copyright conditions above.
  *
+ * Dec-29-2003 -- I added AMD64 inflate asm support.  This version is also
+ * slightly quicker on x86 systems because, instead of using rep movsb to copy
+ * data, it uses rep movsw, which moves data in 2-byte chunks instead of single
+ * bytes.  I've tested the AMD64 code on a Fedora Core 1 + the x86_64 updates
+ * from http://fedora.linux.duke.edu/fc1_x86_64
+ * which is running on an Athlon 64 3000+ / Gigabyte GA-K8VT800M system with
+ * 1GB ram.  The 64-bit version is about 4% faster than the 32-bit version,
+ * when decompressing mozilla-source-1.3.tar.gz.
+ *
  * 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,
@@ -65,33 +74,44 @@ unsigned start;         /* inflate()'s starting value for strm->avail_out */
 {
     struct inflate_state FAR *state;
     struct inffast_ar {
-      void *esp;                  /* esp save */
-      unsigned char FAR *in;      /* local strm->next_in */
-      unsigned char FAR *last;    /* while in < last, enough input available */
-      unsigned char FAR *out;     /* local strm->next_out */
-      unsigned char FAR *beg;     /* inflate()'s initial strm->next_out */
-      unsigned char FAR *end;     /* while out < end, enough space available */
-      unsigned wsize;             /* window size or zero if not using window */
-      unsigned write;             /* window write index */
-      unsigned char FAR *window;  /* allocated sliding window, if wsize != 0 */
-      unsigned long hold;         /* local strm->hold */
-      unsigned bits;              /* local strm->bits */
-      code const FAR *lcode;      /* local strm->lencode */
-      code const FAR *dcode;      /* local strm->distcode */
-      unsigned lmask;             /* mask for first level of length codes */
-      unsigned dmask;             /* mask for first level of distance codes */
-      unsigned len;               /* match length, unused bytes */
-      unsigned dist;              /* match distance */
-      unsigned status;            /* this is set when state changes */
+/* 64   32                               x86  x86_64 */
+/* ar offset                              register */
+/*  0    0 */ void *esp;                /* esp save */
+/*  8    4 */ void *ebp;                /* ebp save */
+/* 16    8 */ unsigned char FAR *in;    /* esi rsi  local strm->next_in */
+/* 24   12 */ unsigned char FAR *last;  /*     r9   while in < last */
+/* 32   16 */ unsigned char FAR *out;   /* edi rdi  local strm->next_out */
+/* 40   20 */ unsigned char FAR *beg;   /*          inflate()'s init next_out */
+/* 48   24 */ unsigned char FAR *end;   /*     r10  while out < end */
+/* 56   28 */ unsigned char FAR *window;/*          size of window, wsize!=0 */
+/* 64   32 */ code const FAR *lcode;    /* ebp rbp  local strm->lencode */
+/* 72   36 */ code const FAR *dcode;    /*     r11  local strm->distcode */
+/* 80   40 */ unsigned long hold;       /* edx rdx  local strm->hold */
+/* 88   44 */ unsigned bits;            /* ebx rbx  local strm->bits */
+/* 92   48 */ unsigned wsize;           /*          window size */
+/* 96   52 */ unsigned write;           /*          window write index */
+/*100   56 */ unsigned lmask;           /*     r12  mask for lcode */
+/*104   60 */ unsigned dmask;           /*     r13  mask for dcode */
+/*108   64 */ unsigned len;             /*     r14  match length */
+/*112   68 */ unsigned dist;            /*     r15  match distance */
+/*116   72 */ unsigned status;          /*          set when state chng*/
     } ar;
 
+#if defined( __GNUC__ ) && defined( __amd64__ ) && ! defined( __i386 )
+#define PAD_AVAIL_IN 6
+#define PAD_AVAIL_OUT 258
+#else
+#define PAD_AVAIL_IN 5
+#define PAD_AVAIL_OUT 257
+#endif
+
     /* copy state to local variables */
     state = (struct inflate_state FAR *)strm->state;
     ar.in = strm->next_in;
-    ar.last = ar.in + (strm->avail_in - 5);
+    ar.last = ar.in + (strm->avail_in - PAD_AVAIL_IN);
     ar.out = strm->next_out;
     ar.beg = ar.out - (start - strm->avail_out);
-    ar.end = ar.out + (strm->avail_out - 257);
+    ar.end = ar.out + (strm->avail_out - PAD_AVAIL_OUT);
     ar.wsize = state->wsize;
     ar.write = state->write;
     ar.window = state->window;
@@ -105,32 +125,368 @@ unsigned start;         /* inflate()'s starting value for strm->avail_out */
     /* decode literals and length/distances until end-of-block or not enough
        input data or output space */
 
-    /* align in on 2 byte boundary */
-    if (((unsigned long)(void *)ar.in & 0x1) != 0) {
+    /* align in on 1/2 hold size boundary */
+    while (((unsigned long)(void *)ar.in & (sizeof(ar.hold) / 2 - 1)) != 0) {
         ar.hold += (unsigned long)*ar.in++ << ar.bits;
         ar.bits += 8;
     }
 
-#if defined( __GNUC__ ) || defined( __ICC )
+#if defined( __GNUC__ ) && defined( __amd64__ ) && ! defined( __i386 )
+    __asm__ __volatile__ (
+"        leaq    %0, %%rax\n"
+"        movq    %%rbp, 8(%%rax)\n"       /* save regs rbp and rsp */
+"        movq    %%rsp, (%%rax)\n"
+"        movq    %%rax, %%rsp\n"          /* make rsp point to &ar */
+"        movq    16(%%rsp), %%rsi\n"      /* rsi  = in */
+"        movq    32(%%rsp), %%rdi\n"      /* rdi  = out */
+"        movq    24(%%rsp), %%r9\n"       /* r9   = last */
+"        movq    48(%%rsp), %%r10\n"      /* r10  = end */
+"        movq    64(%%rsp), %%rbp\n"      /* rbp  = lcode */
+"        movq    72(%%rsp), %%r11\n"      /* r11  = dcode */
+"        movq    80(%%rsp), %%rdx\n"      /* rdx  = hold */
+"        movl    88(%%rsp), %%ebx\n"      /* ebx  = bits */
+"        movl    100(%%rsp), %%r12d\n"    /* r12d = lmask */
+"        movl    104(%%rsp), %%r13d\n"    /* r13d = dmask */
+                                          /* r14d = len */
+                                          /* r15d = dist */
+"        cld\n"
+"        cmpq    %%rdi, %%r10\n"
+"        je      .L_one_time\n"           /* if only one decode left */
+"        cmpq    %%rsi, %%r9\n"
+"        je      .L_one_time\n"
+"        jmp     .L_do_loop\n"
+
+".L_one_time:\n"
+"        movq    %%r12, %%r8\n"           /* r8 = lmask */
+"        cmpb    $32, %%bl\n"
+"        ja      .L_get_length_code_one_time\n"
+
+"        lodsl\n"                         /* eax = *(uint *)in++ */
+"        movb    %%bl, %%cl\n"            /* cl = bits, needs it for shifting */
+"        addb    $32, %%bl\n"             /* bits += 32 */
+"        shlq    %%cl, %%rax\n"
+"        orq     %%rax, %%rdx\n"          /* hold |= *((uint *)in)++ << bits */
+"        jmp     .L_get_length_code_one_time\n"
+
+".align 32,0x90\n"
+".L_while_test:\n"
+"        cmpq    %%rdi, %%r10\n"
+"        jbe     .L_break_loop\n"
+"        cmpq    %%rsi, %%r9\n"
+"        jbe     .L_break_loop\n"
+
+".L_do_loop:\n"
+"        movq    %%r12, %%r8\n"           /* r8 = lmask */
+"        cmpb    $32, %%bl\n"
+"        ja      .L_get_length_code\n"    /* if (32 < bits) */
+
+"        lodsl\n"                         /* eax = *(uint *)in++ */
+"        movb    %%bl, %%cl\n"            /* cl = bits, needs it for shifting */
+"        addb    $32, %%bl\n"             /* bits += 32 */
+"        shlq    %%cl, %%rax\n"
+"        orq     %%rax, %%rdx\n"          /* hold |= *((uint *)in)++ << bits */
+
+".L_get_length_code:\n"
+"        andq    %%rdx, %%r8\n"            /* r8 &= hold */
+"        movl    (%%rbp,%%r8,4), %%eax\n"  /* eax = lcode[hold & lmask] */
+
+"        movb    %%ah, %%cl\n"            /* cl = this.bits */
+"        subb    %%ah, %%bl\n"            /* bits -= this.bits */
+"        shrq    %%cl, %%rdx\n"           /* hold >>= this.bits */
+
+"        testb   %%al, %%al\n"
+"        jnz     .L_test_for_length_base\n" /* if (op != 0) 45.7% */
+
+"        movq    %%r12, %%r8\n"            /* r8 = lmask */
+"        shrl    $16, %%eax\n"            /* output this.val char */
+"        stosb\n"
+
+".L_get_length_code_one_time:\n"
+"        andq    %%rdx, %%r8\n"            /* r8 &= hold */
+"        movl    (%%rbp,%%r8,4), %%eax\n" /* eax = lcode[hold & lmask] */
+
+".L_dolen:\n"
+"        movb    %%ah, %%cl\n"            /* cl = this.bits */
+"        subb    %%ah, %%bl\n"            /* bits -= this.bits */
+"        shrq    %%cl, %%rdx\n"           /* hold >>= this.bits */
+
+"        testb   %%al, %%al\n"
+"        jnz     .L_test_for_length_base\n" /* if (op != 0) 45.7% */
+
+"        shrl    $16, %%eax\n"            /* output this.val char */
+"        stosb\n"
+"        jmp     .L_while_test\n"
+
+".align 32,0x90\n"
+".L_test_for_length_base:\n"
+"        movl    %%eax, %%r14d\n"         /* len = this */
+"        shrl    $16, %%r14d\n"           /* len = this.val */
+"        movb    %%al, %%cl\n"
+
+"        testb   $16, %%al\n"
+"        jz      .L_test_for_second_level_length\n" /* if ((op & 16) == 0) 8% */
+"        andb    $15, %%cl\n"             /* op &= 15 */
+"        jz      .L_decode_distance\n"    /* if (!op) */
+
+".L_add_bits_to_len:\n"
+"        subb    %%cl, %%bl\n"
+"        xorl    %%eax, %%eax\n"
+"        incl    %%eax\n"
+"        shll    %%cl, %%eax\n"
+"        decl    %%eax\n"
+"        andl    %%edx, %%eax\n"          /* eax &= hold */
+"        shrq    %%cl, %%rdx\n"
+"        addl    %%eax, %%r14d\n"         /* len += hold & mask[op] */
+
+".L_decode_distance:\n"
+"        movq    %%r13, %%r8\n"           /* r8 = dmask */
+"        cmpb    $32, %%bl\n"
+"        ja      .L_get_distance_code\n"  /* if (32 < bits) */
+
+"        lodsl\n"                         /* eax = *(uint *)in++ */
+"        movb    %%bl, %%cl\n"            /* cl = bits, needs it for shifting */
+"        addb    $32, %%bl\n"             /* bits += 32 */
+"        shlq    %%cl, %%rax\n"
+"        orq     %%rax, %%rdx\n"          /* hold |= *((uint *)in)++ << bits */
+
+".L_get_distance_code:\n"
+"        andq    %%rdx, %%r8\n"           /* r8 &= hold */
+"        movl    (%%r11,%%r8,4), %%eax\n" /* eax = dcode[hold & dmask] */
+
+".L_dodist:\n"
+"        movl    %%eax, %%r15d\n"         /* dist = this */
+"        shrl    $16, %%r15d\n"           /* dist = this.val */
+"        movb    %%ah, %%cl\n"
+"        subb    %%ah, %%bl\n"            /* bits -= this.bits */
+"        shrq    %%cl, %%rdx\n"           /* hold >>= this.bits */
+"        movb    %%al, %%cl\n"            /* cl = this.op */
+
+"        testb   $16, %%al\n"             /* if ((op & 16) == 0) */
+"        jz      .L_test_for_second_level_dist\n"
+"        andb    $15, %%cl\n"             /* op &= 15 */
+"        jz      .L_check_dist_one\n"
+
+".L_add_bits_to_dist:\n"
+"        subb    %%cl, %%bl\n"
+"        xorl    %%eax, %%eax\n"
+"        incl    %%eax\n"
+"        shll    %%cl, %%eax\n"
+"        decl    %%eax\n"                 /* (1 << op) - 1 */
+"        andl    %%edx, %%eax\n"          /* eax &= hold */
+"        shrq    %%cl, %%rdx\n"
+"        addl    %%eax, %%r15d\n"         /* dist += hold & ((1 << op) - 1) */
+
+".L_check_window:\n"
+"        movq    %%rsi, %%r8\n"           /* save in so from can use it's reg */
+"        movq    %%rdi, %%rax\n"
+"        subq    40(%%rsp), %%rax\n"      /* nbytes = out - beg */
+
+"        cmpl    %%r15d, %%eax\n"
+"        jb      .L_clip_window\n"        /* if (dist > nbytes) 4.2% */
+
+"        movl    %%r14d, %%ecx\n"         /* ecx = len */
+"        movq    %%rdi, %%rsi\n"
+"        subq    %%r15, %%rsi\n"          /* from = out - dist */
+
+"        sarl    %%ecx\n"
+"        jnc     .L_copy_two\n"           /* if len % 2 == 0 */
+
+"        rep     movsw\n"
+"        movb    (%%rsi), %%al\n"
+"        movb    %%al, (%%rdi)\n"
+"        incq    %%rdi\n"
+
+"        movq    %%r8, %%rsi\n"           /* move in back to %rsi, toss from */
+"        jmp     .L_while_test\n"
+
+".L_copy_two:\n"
+"        rep     movsw\n"
+"        movq    %%r8, %%rsi\n"           /* move in back to %rsi, toss from */
+"        jmp     .L_while_test\n"
+
+".align 32,0x90\n"
+".L_check_dist_one:\n"
+"        cmpl    $1, %%r15d\n"            /* if dist 1, is a memset */
+"        jne     .L_check_window\n"
+"        cmpq    %%rdi, 40(%%rsp)\n"      /* if out == beg, outside window */
+"        je      .L_check_window\n"
+
+"        movl    %%r14d, %%ecx\n"         /* ecx = len */
+"        movb    -1(%%rdi), %%al\n"
+"        movb    %%al, %%ah\n"
+
+"        sarl    %%ecx\n"
+"        jnc     .L_set_two\n"
+"        movb    %%al, (%%rdi)\n"
+"        incq    %%rdi\n"
+
+".L_set_two:\n"
+"        rep     stosw\n"
+"        jmp     .L_while_test\n"
+
+".align 32,0x90\n"
+".L_test_for_second_level_length:\n"
+"        testb   $64, %%al\n"
+"        jnz     .L_test_for_end_of_block\n" /* if ((op & 64) != 0) */
+
+"        xorl    %%eax, %%eax\n"
+"        incl    %%eax\n"
+"        shll    %%cl, %%eax\n"
+"        decl    %%eax\n"
+"        andl    %%edx, %%eax\n"         /* eax &= hold */
+"        addl    %%r14d, %%eax\n"        /* eax += len */
+"        movl    (%%rbp,%%rax,4), %%eax\n" /* eax = lcode[val+(hold&mask[op])]*/
+"        jmp     .L_dolen\n"
+
+".align 32,0x90\n"
+".L_test_for_second_level_dist:\n"
+"        testb   $64, %%al\n"
+"        jnz     .L_invalid_distance_code\n" /* if ((op & 64) != 0) */
+
+"        xorl    %%eax, %%eax\n"
+"        incl    %%eax\n"
+"        shll    %%cl, %%eax\n"
+"        decl    %%eax\n"
+"        andl    %%edx, %%eax\n"         /* eax &= hold */
+"        addl    %%r15d, %%eax\n"        /* eax += dist */
+"        movl    (%%r11,%%rax,4), %%eax\n" /* eax = dcode[val+(hold&mask[op])]*/
+"        jmp     .L_dodist\n"
+
+".align 32,0x90\n"
+".L_clip_window:\n"
+"        movl    %%eax, %%ecx\n"         /* ecx = nbytes */
+"        movl    92(%%rsp), %%eax\n"     /* eax = wsize, prepare for dist cmp */
+"        negl    %%ecx\n"                /* nbytes = -nbytes */
+
+"        cmpl    %%r15d, %%eax\n"
+"        jb      .L_invalid_distance_too_far\n" /* if (dist > wsize) */
+
+"        addl    %%r15d, %%ecx\n"         /* nbytes = dist - nbytes */
+"        cmpl    $0, 96(%%rsp)\n"
+"        jne     .L_wrap_around_window\n" /* if (write != 0) */
+
+"        movq    56(%%rsp), %%rsi\n"     /* from  = window */
+"        subl    %%ecx, %%eax\n"         /* eax  -= nbytes */
+"        addq    %%rax, %%rsi\n"         /* from += wsize - nbytes */
+
+"        movl    %%r14d, %%eax\n"        /* eax = len */
+"        cmpl    %%ecx, %%r14d\n"
+"        jbe     .L_do_copy\n"           /* if (nbytes >= len) */
+
+"        subl    %%ecx, %%eax\n"         /* eax -= nbytes */
+"        rep     movsb\n"
+"        movq    %%rdi, %%rsi\n"
+"        subq    %%r15, %%rsi\n"         /* from = &out[ -dist ] */
+"        jmp     .L_do_copy\n"
+
+".align 32,0x90\n"
+".L_wrap_around_window:\n"
+"        movl    96(%%rsp), %%eax\n"     /* eax = write */
+"        cmpl    %%eax, %%ecx\n"
+"        jbe     .L_contiguous_in_window\n" /* if (write >= nbytes) */
+
+"        movl    92(%%rsp), %%esi\n"     /* from  = wsize */
+"        addq    56(%%rsp), %%rsi\n"     /* from += window */
+"        addq    %%rax, %%rsi\n"         /* from += write */
+"        subq    %%rcx, %%rsi\n"         /* from -= nbytes */
+"        subl    %%eax, %%ecx\n"         /* nbytes -= write */
+
+"        movl    %%r14d, %%eax\n"        /* eax = len */
+"        cmpl    %%ecx, %%eax\n"
+"        jbe     .L_do_copy\n"           /* if (nbytes >= len) */
+
+"        subl    %%ecx, %%eax\n"         /* len -= nbytes */
+"        rep     movsb\n"
+"        movq    56(%%rsp), %%rsi\n"     /* from = window */
+"        movl    96(%%rsp), %%ecx\n"     /* nbytes = write */
+"        cmpl    %%ecx, %%eax\n"
+"        jbe     .L_do_copy\n"           /* if (nbytes >= len) */
+
+"        subl    %%ecx, %%eax\n"         /* len -= nbytes */
+"        rep     movsb\n"
+"        movq    %%rdi, %%rsi\n"
+"        subq    %%r15, %%rsi\n"         /* from = out - dist */
+"        jmp     .L_do_copy\n"
+
+".align 32,0x90\n"
+".L_contiguous_in_window:\n"
+"        movq    56(%%rsp), %%rsi\n"     /* rsi = window */
+"        addq    %%rax, %%rsi\n"
+"        subq    %%rcx, %%rsi\n"         /* from += write - nbytes */
+
+"        movl    %%r14d, %%eax\n"        /* eax = len */
+"        cmpl    %%ecx, %%eax\n"
+"        jbe     .L_do_copy\n"           /* if (nbytes >= len) */
+
+"        subl    %%ecx, %%eax\n"         /* len -= nbytes */
+"        rep     movsb\n"
+"        movq    %%rdi, %%rsi\n"
+"        subq    %%r15, %%rsi\n"         /* from = out - dist */
+"        jmp     .L_do_copy\n"           /* if (nbytes >= len) */
+
+".align 32,0x90\n"
+".L_do_copy:\n"
+"        movl    %%eax, %%ecx\n"         /* ecx = len */
+"        rep     movsb\n"
+
+"        movq    %%r8, %%rsi\n"          /* move in back to %esi, toss from */
+"        jmp     .L_while_test\n"
+
+".L_test_for_end_of_block:\n"
+"        testb   $32, %%al\n"
+"        jz      .L_invalid_literal_length_code\n"
+"        movl    $1, 116(%%rsp)\n"
+"        jmp     .L_break_loop_with_status\n"
+
+".L_invalid_literal_length_code:\n"
+"        movl    $2, 116(%%rsp)\n"
+"        jmp     .L_break_loop_with_status\n"
+
+".L_invalid_distance_code:\n"
+"        movl    $3, 116(%%rsp)\n"
+"        jmp     .L_break_loop_with_status\n"
+
+".L_invalid_distance_too_far:\n"
+"        movl    $4, 116(%%rsp)\n"
+"        jmp     .L_break_loop_with_status\n"
+
+".L_break_loop:\n"
+"        movl    $0, 116(%%rsp)\n"
+
+".L_break_loop_with_status:\n"
+/* put in, out, bits, and hold back into ar and pop esp */
+"        movq    %%rsi, 16(%%rsp)\n"     /* in */
+"        movq    %%rdi, 32(%%rsp)\n"     /* out */
+"        movl    %%ebx, 88(%%rsp)\n"     /* bits */
+"        movq    %%rdx, 80(%%rsp)\n"     /* hold */
+"        movq    (%%rsp), %%rax\n"       /* restore rbp and rsp */
+"        movq    8(%%rsp), %%rbp\n"
+"        movq    %%rax, %%rsp\n"
+          :
+          : "m" (ar)
+          : "memory", "%rax", "%rbx", "%rcx", "%rdx", "%rsi", "%rdi",
+            "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15"
+    );
+#elif ( defined( __GNUC__ ) || defined( __ICC ) ) && defined( __i386 )
     __asm__ __volatile__ (
 "        leal    %0, %%eax\n"
-"        pushf\n"
-"        pushl   %%ebp\n"
-"        movl    %%esp, (%%eax)\n"
+"        movl    %%esp, (%%eax)\n"        /* save esp, ebp */
+"        movl    %%ebp, 4(%%eax)\n"
 "        movl    %%eax, %%esp\n"
-"        movl    4(%%esp), %%esi\n"       /* esi = in */
-"        movl    12(%%esp), %%edi\n"      /* edi = out */
-"        movl    36(%%esp), %%edx\n"      /* edx = hold */
-"        movl    40(%%esp), %%ebx\n"      /* ebx = bits */
-"        movl    44(%%esp), %%ebp\n"      /* ebp = lcode */
+"        movl    8(%%esp), %%esi\n"       /* esi = in */
+"        movl    16(%%esp), %%edi\n"      /* edi = out */
+"        movl    40(%%esp), %%edx\n"      /* edx = hold */
+"        movl    44(%%esp), %%ebx\n"      /* ebx = bits */
+"        movl    32(%%esp), %%ebp\n"      /* ebp = lcode */
 
 "        cld\n"
 "        jmp     .L_do_loop\n"
 
+".align 32,0x90\n"
 ".L_while_test:\n"
-"        cmpl    %%edi, 20(%%esp)\n"
+"        cmpl    %%edi, 24(%%esp)\n"      /* out < end */
 "        jbe     .L_break_loop\n"
-"        cmpl    %%esi, 8(%%esp)\n"
+"        cmpl    %%esi, 12(%%esp)\n"      /* in < last */
 "        jbe     .L_break_loop\n"
 
 ".L_do_loop:\n"
@@ -145,7 +501,7 @@ unsigned start;         /* inflate()'s starting value for strm->avail_out */
 "        orl     %%eax, %%edx\n"        /* hold |= *((ushort *)in)++ << bits */
 
 ".L_get_length_code:\n"
-"        movl    52(%%esp), %%eax\n"      /* eax = lmask */
+"        movl    56(%%esp), %%eax\n"      /* eax = lmask */
 "        andl    %%edx, %%eax\n"          /* eax &= hold */
 "        movl    (%%ebp,%%eax,4), %%eax\n" /* eax = lcode[hold & lmask] */
 
@@ -161,10 +517,11 @@ unsigned start;         /* inflate()'s starting value for strm->avail_out */
 "        stosb\n"
 "        jmp     .L_while_test\n"
 
+".align 32,0x90\n"
 ".L_test_for_length_base:\n"
 "        movl    %%eax, %%ecx\n"          /* len = this */
 "        shrl    $16, %%ecx\n"            /* len = this.val */
-"        movl    %%ecx, 60(%%esp)\n"      /* len = this */
+"        movl    %%ecx, 64(%%esp)\n"      /* save len */
 "        movb    %%al, %%cl\n"
 
 "        testb   $16, %%al\n"
@@ -184,13 +541,14 @@ unsigned start;         /* inflate()'s starting value for strm->avail_out */
 "        movb    %%ch, %%cl\n"            /* move op back to ecx */
 
 ".L_add_bits_to_len:\n"
-"        movl    $1, %%eax\n"
+"        subb    %%cl, %%bl\n"
+"        xorl    %%eax, %%eax\n"
+"        incl    %%eax\n"
 "        shll    %%cl, %%eax\n"
 "        decl    %%eax\n"
-"        subb    %%cl, %%bl\n"
 "        andl    %%edx, %%eax\n"          /* eax &= hold */
 "        shrl    %%cl, %%edx\n"
-"        addl    %%eax, 60(%%esp)\n"      /* len += hold & mask[op] */
+"        addl    %%eax, 64(%%esp)\n"      /* len += hold & mask[op] */
 
 ".L_decode_distance:\n"
 "        cmpb    $15, %%bl\n"
@@ -204,8 +562,8 @@ unsigned start;         /* inflate()'s starting value for strm->avail_out */
 "        orl     %%eax, %%edx\n"         /* hold |= *((ushort *)in)++ << bits */
 
 ".L_get_distance_code:\n"
-"        movl    56(%%esp), %%eax\n"      /* eax = dmask */
-"        movl    48(%%esp), %%ecx\n"      /* ecx = dcode */
+"        movl    60(%%esp), %%eax\n"      /* eax = dmask */
+"        movl    36(%%esp), %%ecx\n"      /* ecx = dcode */
 "        andl    %%edx, %%eax\n"          /* eax &= hold */
 "        movl    (%%ecx,%%eax,4), %%eax\n"/* eax = dcode[hold & dmask] */
 
@@ -234,223 +592,228 @@ unsigned start;         /* inflate()'s starting value for strm->avail_out */
 "        movb    %%ch, %%cl\n"            /* move op back to ecx */
 
 ".L_add_bits_to_dist:\n"
-"        movl    $1, %%eax\n"
+"        subb    %%cl, %%bl\n"
+"        xorl    %%eax, %%eax\n"
+"        incl    %%eax\n"
 "        shll    %%cl, %%eax\n"
 "        decl    %%eax\n"                 /* (1 << op) - 1 */
-"        subb    %%cl, %%bl\n"
 "        andl    %%edx, %%eax\n"          /* eax &= hold */
 "        shrl    %%cl, %%edx\n"
 "        addl    %%eax, %%ebp\n"          /* dist += hold & ((1 << op) - 1) */
 
 ".L_check_window:\n"
-"        movl    %%esi, 4(%%esp)\n"       /* save in so from can use it's reg */
+"        movl    %%esi, 8(%%esp)\n"       /* save in so from can use it's reg */
 "        movl    %%edi, %%eax\n"
-"        subl    16(%%esp), %%eax\n"      /* nbytes = out - beg */
+"        subl    20(%%esp), %%eax\n"      /* nbytes = out - beg */
 
 "        cmpl    %%ebp, %%eax\n"
 "        jb      .L_clip_window\n"        /* if (dist > nbytes) 4.2% */
 
-"        movl    60(%%esp), %%ecx\n"
+"        movl    64(%%esp), %%ecx\n"      /* ecx = len */
 "        movl    %%edi, %%esi\n"
 "        subl    %%ebp, %%esi\n"          /* from = out - dist */
 
-"        subl    $3, %%ecx\n"             /* copy from to out */
+"        sarl    %%ecx\n"
+"        jnc     .L_copy_two\n"           /* if len % 2 == 0 */
+
+"        rep     movsw\n"
 "        movb    (%%esi), %%al\n"
 "        movb    %%al, (%%edi)\n"
-"        movb    1(%%esi), %%al\n"
-"        movb    2(%%esi), %%ah\n"
-"        addl    $3, %%esi\n"
-"        movb    %%al, 1(%%edi)\n"
-"        movb    %%ah, 2(%%edi)\n"
-"        addl    $3, %%edi\n"
-"        rep     movsb\n"
+"        incl    %%edi\n"
 
-"        movl    4(%%esp), %%esi\n"      /* move in back to %esi, toss from */
-"        movl    44(%%esp), %%ebp\n"     /* ebp = lcode */
+"        movl    8(%%esp), %%esi\n"       /* move in back to %esi, toss from */
+"        movl    32(%%esp), %%ebp\n"      /* ebp = lcode */
 "        jmp     .L_while_test\n"
 
+".L_copy_two:\n"
+"        rep     movsw\n"
+"        movl    8(%%esp), %%esi\n"       /* move in back to %esi, toss from */
+"        movl    32(%%esp), %%ebp\n"      /* ebp = lcode */
+"        jmp     .L_while_test\n"
+
+".align 32,0x90\n"
 ".L_check_dist_one:\n"
 "        cmpl    $1, %%ebp\n"            /* if dist 1, is a memset */
 "        jne     .L_check_window\n"
-"        cmpl    %%edi, 16(%%esp)\n"
-"        je      .L_check_window\n"
+"        cmpl    %%edi, 20(%%esp)\n"
+"        je      .L_check_window\n"      /* out == beg, if outside window */
+
+"        movl    64(%%esp), %%ecx\n"      /* ecx = len */
+"        movb    -1(%%edi), %%al\n"
+"        movb    %%al, %%ah\n"
+
+"        sarl    %%ecx\n"
+"        jnc     .L_set_two\n"
+"        movb    %%al, (%%edi)\n"
+"        incl    %%edi\n"
 
-"        decl    %%edi\n"
-"        movl    60(%%esp), %%ecx\n"
-"        movb    (%%edi), %%al\n"
-"        subl    $3, %%ecx\n"
-
-"        movb    %%al, 1(%%edi)\n"       /* memset out with from[-1] */
-"        movb    %%al, 2(%%edi)\n"
-"        movb    %%al, 3(%%edi)\n"
-"        addl    $4, %%edi\n"
-"        rep     stosb\n"
-"        movl    44(%%esp), %%ebp\n"      /* ebp = lcode */
+".L_set_two:\n"
+"        rep     stosw\n"
+"        movl    32(%%esp), %%ebp\n"      /* ebp = lcode */
 "        jmp     .L_while_test\n"
 
+".align 32,0x90\n"
 ".L_test_for_second_level_length:\n"
 "        testb   $64, %%al\n"
 "        jnz     .L_test_for_end_of_block\n" /* if ((op & 64) != 0) */
 
-"        movl    $1, %%eax\n"
+"        xorl    %%eax, %%eax\n"
+"        incl    %%eax\n"
 "        shll    %%cl, %%eax\n"
 "        decl    %%eax\n"
 "        andl    %%edx, %%eax\n"         /* eax &= hold */
-"        addl    60(%%esp), %%eax\n"     /* eax += this.val */
+"        addl    64(%%esp), %%eax\n"     /* eax += len */
 "        movl    (%%ebp,%%eax,4), %%eax\n" /* eax = lcode[val+(hold&mask[op])]*/
 "        jmp     .L_dolen\n"
 
+".align 32,0x90\n"
 ".L_test_for_second_level_dist:\n"
 "        testb   $64, %%al\n"
 "        jnz     .L_invalid_distance_code\n" /* if ((op & 64) != 0) */
 
-"        movl    $1, %%eax\n"
+"        xorl    %%eax, %%eax\n"
+"        incl    %%eax\n"
 "        shll    %%cl, %%eax\n"
 "        decl    %%eax\n"
 "        andl    %%edx, %%eax\n"         /* eax &= hold */
-"        addl    %%ebp, %%eax\n"         /* eax += this.val */
-"        movl    48(%%esp), %%ecx\n"     /* ecx = dcode */
+"        addl    %%ebp, %%eax\n"         /* eax += dist */
+"        movl    36(%%esp), %%ecx\n"     /* ecx = dcode */
 "        movl    (%%ecx,%%eax,4), %%eax\n" /* eax = dcode[val+(hold&mask[op])]*/
 "        jmp     .L_dodist\n"
 
+".align 32,0x90\n"
 ".L_clip_window:\n"
 "        movl    %%eax, %%ecx\n"
-"        movl    24(%%esp), %%eax\n"     /* prepare for dist compare */
+"        movl    48(%%esp), %%eax\n"     /* eax = wsize */
 "        negl    %%ecx\n"                /* nbytes = -nbytes */
-"        movl    32(%%esp), %%esi\n"     /* from = window */
+"        movl    28(%%esp), %%esi\n"     /* from = window */
 
 "        cmpl    %%ebp, %%eax\n"
 "        jb      .L_invalid_distance_too_far\n" /* if (dist > wsize) */
 
 "        addl    %%ebp, %%ecx\n"         /* nbytes = dist - nbytes */
-"        cmpl    $0, 28(%%esp)\n"
+"        cmpl    $0, 52(%%esp)\n"
 "        jne     .L_wrap_around_window\n" /* if (write != 0) */
 
 "        subl    %%ecx, %%eax\n"
 "        addl    %%eax, %%esi\n"         /* from += wsize - nbytes */
 
-"        movl    60(%%esp), %%eax\n"
-"        cmpl    %%ecx, %%eax\n"
-"        jbe     .L_do_copy1\n"          /* if (nbytes >= len) */
-
-"        subl    %%ecx, %%eax\n"         /* len -= nbytes */
-"        rep     movsb\n"
-"        movl    %%edi, %%esi\n"
-"        subl    %%ebp, %%esi\n"         /* from = out - dist */
-"        jmp     .L_do_copy1\n"
-
+"        movl    64(%%esp), %%eax\n"     /* eax = len */
 "        cmpl    %%ecx, %%eax\n"
-"        jbe     .L_do_copy1\n"          /* if (nbytes >= len) */
+"        jbe     .L_do_copy\n"           /* if (nbytes >= len) */
 
 "        subl    %%ecx, %%eax\n"         /* len -= nbytes */
 "        rep     movsb\n"
 "        movl    %%edi, %%esi\n"
 "        subl    %%ebp, %%esi\n"         /* from = out - dist */
-"        jmp     .L_do_copy1\n"
+"        jmp     .L_do_copy\n"
 
+".align 32,0x90\n"
 ".L_wrap_around_window:\n"
-"        movl    28(%%esp), %%eax\n"
+"        movl    52(%%esp), %%eax\n"     /* eax = write */
 "        cmpl    %%eax, %%ecx\n"
 "        jbe     .L_contiguous_in_window\n" /* if (write >= nbytes) */
 
-"        addl    24(%%esp), %%esi\n"
-"        addl    %%eax, %%esi\n"
-"        subl    %%ecx, %%esi\n"         /* from += wsize + write - nbytes */
+"        addl    48(%%esp), %%esi\n"     /* from += wsize */
+"        addl    %%eax, %%esi\n"         /* from += write */
+"        subl    %%ecx, %%esi\n"         /* from -= nbytes */
 "        subl    %%eax, %%ecx\n"         /* nbytes -= write */
 
-"        movl    60(%%esp), %%eax\n"
+"        movl    64(%%esp), %%eax\n"     /* eax = len */
 "        cmpl    %%ecx, %%eax\n"
-"        jbe     .L_do_copy1\n"          /* if (nbytes >= len) */
+"        jbe     .L_do_copy\n"           /* if (nbytes >= len) */
 
 "        subl    %%ecx, %%eax\n"         /* len -= nbytes */
 "        rep     movsb\n"
-"        movl    32(%%esp), %%esi\n"     /* from = window */
-"        movl    28(%%esp), %%ecx\n"     /* nbytes = write */
+"        movl    28(%%esp), %%esi\n"     /* from = window */
+"        movl    52(%%esp), %%ecx\n"     /* nbytes = write */
 "        cmpl    %%ecx, %%eax\n"
-"        jbe     .L_do_copy1\n"          /* if (nbytes >= len) */
+"        jbe     .L_do_copy\n"           /* if (nbytes >= len) */
 
 "        subl    %%ecx, %%eax\n"         /* len -= nbytes */
 "        rep     movsb\n"
 "        movl    %%edi, %%esi\n"
 "        subl    %%ebp, %%esi\n"         /* from = out - dist */
-"        jmp     .L_do_copy1\n"
+"        jmp     .L_do_copy\n"
 
+".align 32,0x90\n"
 ".L_contiguous_in_window:\n"
 "        addl    %%eax, %%esi\n"
 "        subl    %%ecx, %%esi\n"         /* from += write - nbytes */
 
-"        movl    60(%%esp), %%eax\n"
+"        movl    64(%%esp), %%eax\n"     /* eax = len */
 "        cmpl    %%ecx, %%eax\n"
-"        jbe     .L_do_copy1\n"          /* if (nbytes >= len) */
+"        jbe     .L_do_copy\n"           /* if (nbytes >= len) */
 
 "        subl    %%ecx, %%eax\n"         /* len -= nbytes */
 "        rep     movsb\n"
 "        movl    %%edi, %%esi\n"
 "        subl    %%ebp, %%esi\n"         /* from = out - dist */
+"        jmp     .L_do_copy\n"           /* if (nbytes >= len) */
 
-".L_do_copy1:\n"
+".align 32,0x90\n"
+".L_do_copy:\n"
 "        movl    %%eax, %%ecx\n"
 "        rep     movsb\n"
 
-"        movl    4(%%esp), %%esi\n"      /* move in back to %esi, toss from */
-"        movl    44(%%esp), %%ebp\n"     /* ebp = lcode */
+"        movl    8(%%esp), %%esi\n"      /* move in back to %esi, toss from */
+"        movl    32(%%esp), %%ebp\n"     /* ebp = lcode */
 "        jmp     .L_while_test\n"
 
 ".L_test_for_end_of_block:\n"
 "        testb   $32, %%al\n"
 "        jz      .L_invalid_literal_length_code\n"
-"        movl    $1, 68(%%esp)\n"
+"        movl    $1, 72(%%esp)\n"
 "        jmp     .L_break_loop_with_status\n"
 
 ".L_invalid_literal_length_code:\n"
-"        movl    $2, 68(%%esp)\n"
+"        movl    $2, 72(%%esp)\n"
 "        jmp     .L_break_loop_with_status\n"
 
 ".L_invalid_distance_code:\n"
-"        movl    $3, 68(%%esp)\n"
+"        movl    $3, 72(%%esp)\n"
 "        jmp     .L_break_loop_with_status\n"
 
 ".L_invalid_distance_too_far:\n"
-"        movl    4(%%esp), %%esi\n"
-"        movl    $4, 68(%%esp)\n"
+"        movl    8(%%esp), %%esi\n"
+"        movl    $4, 72(%%esp)\n"
 "        jmp     .L_break_loop_with_status\n"
 
 ".L_break_loop:\n"
-"        movl    $0, 68(%%esp)\n"
+"        movl    $0, 72(%%esp)\n"
 
 ".L_break_loop_with_status:\n"
 /* put in, out, bits, and hold back into ar and pop esp */
-"        movl    %%esi, 4(%%esp)\n"
-"        movl    %%edi, 12(%%esp)\n"
-"        movl    %%ebx, 40(%%esp)\n"
-"        movl    %%edx, 36(%%esp)\n"
+"        movl    %%esi, 8(%%esp)\n"      /* save in */
+"        movl    %%edi, 16(%%esp)\n"     /* save out */
+"        movl    %%ebx, 44(%%esp)\n"     /* save bits */
+"        movl    %%edx, 40(%%esp)\n"     /* save hold */
+"        movl    4(%%esp), %%ebp\n"      /* restore esp, ebp */
 "        movl    (%%esp), %%esp\n"
-"        popl    %%ebp\n"
-"        popf\n"
           :
           : "m" (ar)
           : "memory", "%eax", "%ebx", "%ecx", "%edx", "%esi", "%edi"
     );
-#elif defined( _MSC_VER )
+#elif defined( _MSC_VER ) && ! defined( _M_AMD64 )
     __asm {
 	lea	eax, ar
-	pushfd
-	push	ebp
-	mov	[eax], esp
+	mov	[eax], esp         /* save esp, ebp */
+	mov	[eax+4], ebp
 	mov	esp, eax
-	mov	esi, [esp+4]       /* esi = in */
-	mov	edi, [esp+12]      /* edi = out */
-	mov	edx, [esp+36]      /* edx = hold */
-	mov	ebx, [esp+40]      /* ebx = bits */
-	mov	ebp, [esp+44]      /* ebp = lcode */
+	mov	esi, [esp+8]       /* esi = in */
+	mov	edi, [esp+16]      /* edi = out */
+	mov	edx, [esp+40]      /* edx = hold */
+	mov	ebx, [esp+44]      /* ebx = bits */
+	mov	ebp, [esp+32]      /* ebp = lcode */
 
 	cld
 	jmp	L_do_loop
 
+ALIGN 4
 L_while_test:
-	cmp	[esp+20], edi
+	cmp	[esp+24], edi
 	jbe	L_break_loop
-	cmp	[esp+8], esi
+	cmp	[esp+12], esi
 	jbe	L_break_loop
 
 L_do_loop:
@@ -465,7 +828,7 @@ L_do_loop:
 	or	edx, eax        /* hold |= *((ushort *)in)++ << bits */
 
 L_get_length_code:
-	mov	eax, [esp+52]      /* eax = lmask */
+	mov	eax, [esp+56]      /* eax = lmask */
 	and	eax, edx          /* eax &= hold */
 	mov	eax, [ebp+eax*4] /* eax = lcode[hold & lmask] */
 
@@ -481,10 +844,11 @@ L_dolen:
 	stosb
 	jmp	L_while_test
 
+ALIGN 4
 L_test_for_length_base:
 	mov	ecx, eax          /* len = this */
 	shr	ecx, 16            /* len = this.val */
-	mov	[esp+60], ecx      /* len = this */
+	mov	[esp+64], ecx      /* save len */
 	mov	cl, al
 
 	test	al, 16
@@ -504,13 +868,14 @@ L_test_for_length_base:
 	mov	cl, ch            /* move op back to ecx */
 
 L_add_bits_to_len:
-	mov	eax, 1
+	sub	bl, cl
+	xor	eax, eax
+	inc	eax
 	shl	eax, cl
 	dec	eax
-	sub	bl, cl
 	and	eax, edx          /* eax &= hold */
 	shr	edx, cl
-	add	[esp+60], eax      /* len += hold & mask[op] */
+	add	[esp+64], eax      /* len += hold & mask[op] */
 
 L_decode_distance:
 	cmp	bl, 15
@@ -524,8 +889,8 @@ L_decode_distance:
 	or	edx, eax         /* hold |= *((ushort *)in)++ << bits */
 
 L_get_distance_code:
-	mov	eax, [esp+56]      /* eax = dmask */
-	mov	ecx, [esp+48]      /* ecx = dcode */
+	mov	eax, [esp+60]      /* eax = dmask */
+	mov	ecx, [esp+36]      /* ecx = dcode */
 	and	eax, edx          /* eax &= hold */
 	mov	eax, [ecx+eax*4]/* eax = dcode[hold & dmask] */
 
@@ -554,200 +919,207 @@ L_dodist:
 	mov	cl, ch            /* move op back to ecx */
 
 L_add_bits_to_dist:
-	mov	eax, 1
+	sub	bl, cl
+	xor	eax, eax
+	inc	eax
 	shl	eax, cl
 	dec	eax                 /* (1 << op) - 1 */
-	sub	bl, cl
 	and	eax, edx          /* eax &= hold */
 	shr	edx, cl
 	add	ebp, eax          /* dist += hold & ((1 << op) - 1) */
 
 L_check_window:
-	mov	[esp+4], esi       /* save in so from can use it's reg */
+	mov	[esp+8], esi       /* save in so from can use it's reg */
 	mov	eax, edi
-	sub	eax, [esp+16]      /* nbytes = out - beg */
+	sub	eax, [esp+20]      /* nbytes = out - beg */
 
 	cmp	eax, ebp
 	jb	L_clip_window        /* if (dist > nbytes) 4.2% */
 
-	mov	ecx, [esp+60]
+	mov	ecx, [esp+64]      /* ecx = len */
 	mov	esi, edi
 	sub	esi, ebp          /* from = out - dist */
 
-	sub	ecx, 3             /* copy from to out */
+	sar	ecx, 1
+	jnc	L_copy_two
+
+	rep     movsw
 	mov	al, [esi]
 	mov	[edi], al
-	mov	al, [esi+1]
-	mov	ah, [esi+2]
-	add	esi, 3
-	mov	[edi+1], al
-	mov	[edi+2], ah
-	add	edi, 3
-	rep     movsb
+	inc	edi
+
+	mov	esi, [esp+8]      /* move in back to %esi, toss from */
+	mov	ebp, [esp+32]     /* ebp = lcode */
+	jmp	L_while_test
 
-	mov	esi, [esp+4]      /* move in back to %esi, toss from */
-	mov	ebp, [esp+44]     /* ebp = lcode */
+L_copy_two:
+	rep     movsw
+	mov	esi, [esp+8]      /* move in back to %esi, toss from */
+	mov	ebp, [esp+32]     /* ebp = lcode */
 	jmp	L_while_test
 
+ALIGN 4
 L_check_dist_one:
 	cmp	ebp, 1            /* if dist 1, is a memset */
 	jne	L_check_window
-	cmp	[esp+16], edi
-	je	L_check_window
-
-	dec	edi
-	mov	ecx, [esp+60]
-	mov	al, [edi]
-	sub	ecx, 3
-
-	mov	[edi+1], al       /* memset out with from[-1] */
-	mov	[edi+2], al
-	mov	[edi+3], al
-	add	edi, 4
-	rep     stosb
-	mov	ebp, [esp+44]      /* ebp = lcode */
+	cmp	[esp+20], edi
+	je	L_check_window    /* out == beg, if outside window */
+
+	mov	ecx, [esp+64]     /* ecx = len */
+	mov	al, [edi-1]
+	mov	ah, al
+
+	sar	ecx, 1
+	jnc	L_set_two
+	mov	[edi], al         /* memset out with from[-1] */
+	inc	edi
+
+L_set_two:
+	rep     stosw
+	mov	ebp, [esp+32]     /* ebp = lcode */
 	jmp	L_while_test
 
+ALIGN 4
 L_test_for_second_level_length:
 	test	al, 64
 	jnz	L_test_for_end_of_block /* if ((op & 64) != 0) */
 
-	mov	eax, 1
+	xor	eax, eax
+	inc	eax
 	shl	eax, cl
 	dec	eax
 	and	eax, edx         /* eax &= hold */
-	add	eax, [esp+60]     /* eax += this.val */
+	add	eax, [esp+64]     /* eax += len */
 	mov	eax, [ebp+eax*4] /* eax = lcode[val+(hold&mask[op])]*/
 	jmp	L_dolen
 
+ALIGN 4
 L_test_for_second_level_dist:
 	test	al, 64
 	jnz	L_invalid_distance_code /* if ((op & 64) != 0) */
 
-	mov	eax, 1
+	xor	eax, eax
+	inc	eax
 	shl	eax, cl
 	dec	eax
 	and	eax, edx         /* eax &= hold */
-	add	eax, ebp         /* eax += this.val */
-	mov	ecx, [esp+48]     /* ecx = dcode */
+	add	eax, ebp         /* eax += dist */
+	mov	ecx, [esp+36]     /* ecx = dcode */
 	mov	eax, [ecx+eax*4] /* eax = dcode[val+(hold&mask[op])]*/
 	jmp	L_dodist
 
+ALIGN 4
 L_clip_window:
 	mov	ecx, eax
-	mov	eax, [esp+24]     /* prepare for dist compare */
+	mov	eax, [esp+48]     /* eax = wsize */
 	neg	ecx                /* nbytes = -nbytes */
-	mov	esi, [esp+32]     /* from = window */
+	mov	esi, [esp+28]     /* from = window */
 
 	cmp	eax, ebp
 	jb	L_invalid_distance_too_far /* if (dist > wsize) */
 
 	add	ecx, ebp         /* nbytes = dist - nbytes */
-	cmp	dword ptr [esp+28], 0
+	cmp	dword ptr [esp+52], 0
 	jne	L_wrap_around_window /* if (write != 0) */
 
 	sub	eax, ecx
 	add	esi, eax         /* from += wsize - nbytes */
 
-	mov	eax, [esp+60]
-	cmp	eax, ecx
-	jbe	L_do_copy1          /* if (nbytes >= len) */
-
-	sub	eax, ecx         /* len -= nbytes */
-	rep     movsb
-	mov	esi, edi
-	sub	esi, ebp         /* from = out - dist */
-	jmp	L_do_copy1
-
+	mov	eax, [esp+64]    /* eax = len */
 	cmp	eax, ecx
-	jbe	L_do_copy1          /* if (nbytes >= len) */
+	jbe	L_do_copy          /* if (nbytes >= len) */
 
 	sub	eax, ecx         /* len -= nbytes */
 	rep     movsb
 	mov	esi, edi
 	sub	esi, ebp         /* from = out - dist */
-	jmp	L_do_copy1
+	jmp	L_do_copy
 
+ALIGN 4
 L_wrap_around_window:
-	mov	eax, [esp+28]
+	mov	eax, [esp+52]    /* eax = write */
 	cmp	ecx, eax
 	jbe	L_contiguous_in_window /* if (write >= nbytes) */
 
-	add	esi, [esp+24]
-	add	esi, eax
-	sub	esi, ecx         /* from += wsize + write - nbytes */
+	add	esi, [esp+48]    /* from += wsize */
+	add	esi, eax         /* from += write */
+	sub	esi, ecx         /* from -= nbytes */
 	sub	ecx, eax         /* nbytes -= write */
 
-	mov	eax, [esp+60]
+	mov	eax, [esp+64]    /* eax = len */
 	cmp	eax, ecx
-	jbe	L_do_copy1          /* if (nbytes >= len) */
+	jbe	L_do_copy          /* if (nbytes >= len) */
 
 	sub	eax, ecx         /* len -= nbytes */
 	rep     movsb
-	mov	esi, [esp+32]     /* from = window */
-	mov	ecx, [esp+28]     /* nbytes = write */
+	mov	esi, [esp+28]     /* from = window */
+	mov	ecx, [esp+52]     /* nbytes = write */
 	cmp	eax, ecx
-	jbe	L_do_copy1          /* if (nbytes >= len) */
+	jbe	L_do_copy          /* if (nbytes >= len) */
 
 	sub	eax, ecx         /* len -= nbytes */
 	rep     movsb
 	mov	esi, edi
 	sub	esi, ebp         /* from = out - dist */
-	jmp	L_do_copy1
+	jmp	L_do_copy
 
+ALIGN 4
 L_contiguous_in_window:
 	add	esi, eax
 	sub	esi, ecx         /* from += write - nbytes */
 
-	mov	eax, [esp+60]
+	mov	eax, [esp+64]    /* eax = len */
 	cmp	eax, ecx
-	jbe	L_do_copy1          /* if (nbytes >= len) */
+	jbe	L_do_copy          /* if (nbytes >= len) */
 
 	sub	eax, ecx         /* len -= nbytes */
 	rep     movsb
 	mov	esi, edi
 	sub	esi, ebp         /* from = out - dist */
+	jmp	L_do_copy
 
-L_do_copy1:
+ALIGN 4
+L_do_copy:
 	mov	ecx, eax
 	rep     movsb
 
-	mov	esi, [esp+4]      /* move in back to %esi, toss from */
-	mov	ebp, [esp+44]     /* ebp = lcode */
+	mov	esi, [esp+8]      /* move in back to %esi, toss from */
+	mov	ebp, [esp+32]     /* ebp = lcode */
 	jmp	L_while_test
 
 L_test_for_end_of_block:
 	test	al, 32
 	jz	L_invalid_literal_length_code
-	mov	dword ptr [esp+68], 1
+	mov	dword ptr [esp+72], 1
 	jmp	L_break_loop_with_status
 
 L_invalid_literal_length_code:
-	mov	dword ptr [esp+68], 2
+	mov	dword ptr [esp+72], 2
 	jmp	L_break_loop_with_status
 
 L_invalid_distance_code:
-	mov	dword ptr [esp+68], 3
+	mov	dword ptr [esp+72], 3
 	jmp	L_break_loop_with_status
 
 L_invalid_distance_too_far:
 	mov	esi, [esp+4]
-	mov	dword ptr [esp+68], 4
+	mov	dword ptr [esp+72], 4
 	jmp	L_break_loop_with_status
 
 L_break_loop:
-	mov	dword ptr [esp+68], 0
+	mov	dword ptr [esp+72], 0
 
 L_break_loop_with_status:
 /* put in, out, bits, and hold back into ar and pop esp */
-	mov	[esp+4], esi
-	mov	[esp+12], edi
-	mov	[esp+40], ebx
-	mov	[esp+36], edx
+	mov	[esp+8], esi     /* save in */
+	mov	[esp+16], edi    /* save out */
+	mov	[esp+44], ebx    /* save bits */
+	mov	[esp+40], edx    /* save hold */
+	mov	ebp, [esp+4]     /* restore esp, ebp */
 	mov	esp, [esp]
-	pop	ebp
-	popfd
     }
+#else
+#error "x86 architecture not defined"
 #endif
 
     if (ar.status > 1) {
@@ -772,10 +1144,12 @@ L_break_loop_with_status:
     /* update state and return */
     strm->next_in = ar.in;
     strm->next_out = ar.out;
-    strm->avail_in = (unsigned)(ar.in < ar.last ? 5 + (ar.last - ar.in) :
-                                                  5 - (ar.in - ar.last));
-    strm->avail_out = (unsigned)(ar.out < ar.end ? 257 + (ar.end - ar.out) :
-                                                   257 - (ar.out - ar.end));
+    strm->avail_in = (unsigned)(ar.in < ar.last ?
+                                PAD_AVAIL_IN + (ar.last - ar.in) :
+                                PAD_AVAIL_IN - (ar.in - ar.last));
+    strm->avail_out = (unsigned)(ar.out < ar.end ?
+                                 PAD_AVAIL_OUT + (ar.end - ar.out) :
+                                 PAD_AVAIL_OUT - (ar.out - ar.end));
     state->hold = ar.hold;
     state->bits = ar.bits;
     return;
diff --git a/zlib/contrib/inflate86/inffast.S b/zlib/contrib/inflate86/inffast.S
index f9bffd5eb9d..2245a2905bd 100644
--- a/zlib/contrib/inflate86/inffast.S
+++ b/zlib/contrib/inflate86/inffast.S
@@ -188,17 +188,8 @@
 /*
  * typedef enum inflate_mode consts, in inflate.h
  */
-#ifndef NO_GUNZIP
-#define GUNZIP
-#endif
-
-#ifdef GUNZIP
 #define INFLATE_MODE_TYPE 11  /* state->mode flags enum-ed in inflate.h */
 #define INFLATE_MODE_BAD  26
-#else
-#define INFLATE_MODE_TYPE 3
-#define INFLATE_MODE_BAD  17
-#endif
 
 
 #if ! defined( USE_MMX ) && ! defined( NO_MMX )
diff --git a/zlib/contrib/masm686/match.asm b/zlib/contrib/masm686/match.asm
index 2287804d443..4b03a71abd5 100644
--- a/zlib/contrib/masm686/match.asm
+++ b/zlib/contrib/masm686/match.asm
@@ -1,408 +1,413 @@
-
-; match.asm -- Pentium-Pro optimized version of longest_match()
-;
-; Updated for zlib 1.1.3 and converted to MASM 6.1x
-; Copyright (C) 2000 Dan Higdon <hdan@kinesoft.com>
-;                    and Chuck Walbourn <chuckw@kinesoft.com>
-; Corrections by Cosmin Truta <cosmint@cs.ubbcluj.ro>
-;
-; This is free software; you can redistribute it and/or modify it
-; under the terms of the GNU General Public License.
-
-; Based on match.S
-; Written for zlib 1.1.2
-; Copyright (C) 1998 Brian Raiter <breadbox@muppetlabs.com>
-
-	.686P
-	.MODEL	FLAT
-
-;===========================================================================
-; EQUATES
-;===========================================================================
-
-MAX_MATCH	EQU 258
-MIN_MATCH	EQU 3
-MIN_LOOKAHEAD	EQU (MAX_MATCH + MIN_MATCH + 1)
-MAX_MATCH_8	EQU ((MAX_MATCH + 7) AND (NOT 7))
-
-;===========================================================================
-; STRUCTURES
-;===========================================================================
-
-; This STRUCT assumes a 4-byte alignment
-
-DEFLATE_STATE	STRUCT
-ds_strm			dd ?
-ds_status		dd ?
-ds_pending_buf		dd ?
-ds_pending_buf_size	dd ?
-ds_pending_out		dd ?
-ds_pending		dd ?
-ds_wrap			dd ?
-ds_data_type		db ?
-ds_method		db ?
-			db ?	; padding
-			db ?	; padding
-ds_last_flush		dd ?
-ds_w_size		dd ?	; used
-ds_w_bits		dd ?
-ds_w_mask		dd ?	; used
-ds_window		dd ?	; used
-ds_window_size		dd ?
-ds_prev			dd ?	; used
-ds_head			dd ?
-ds_ins_h		dd ?
-ds_hash_size		dd ?
-ds_hash_bits		dd ?
-ds_hash_mask		dd ?
-ds_hash_shift		dd ?
-ds_block_start		dd ?
-ds_match_length		dd ?	; used
-ds_prev_match		dd ?	; used
-ds_match_available	dd ?
-ds_strstart		dd ?	; used
-ds_match_start		dd ?	; used
-ds_lookahead		dd ?	; used
-ds_prev_length		dd ?	; used
-ds_max_chain_length	dd ?	; used
-ds_max_laxy_match	dd ?
-ds_level		dd ?
-ds_strategy		dd ?
-ds_good_match		dd ?	; used
-ds_nice_match		dd ?	; used
-
-; Don't need anymore of the struct for match
-DEFLATE_STATE	ENDS
-
-;===========================================================================
-; CODE
-;===========================================================================
-_TEXT	SEGMENT
-
-;---------------------------------------------------------------------------
-; match_init
-;---------------------------------------------------------------------------
-	ALIGN	4
-PUBLIC	_match_init
-_match_init	PROC
-	; no initialization needed
-	ret
-_match_init	ENDP
-
-;---------------------------------------------------------------------------
-; uInt longest_match(deflate_state *deflatestate, IPos curmatch)
-;---------------------------------------------------------------------------
-	ALIGN	4
-
-PUBLIC	_longest_match
-_longest_match	PROC
-
-; Since this code uses EBP for a scratch register, the stack frame must
-; be manually constructed and referenced relative to the ESP register.
-
-; Stack image
-; Variables
-chainlenwmask	=  0	; high word: current chain len
-			; low word: s->wmask
-window		=  4	; local copy of s->window
-windowbestlen	=  8	; s->window + bestlen
-scanend		= 12	; last two bytes of string
-scanstart	= 16	; first two bytes of string
-scanalign	= 20	; dword-misalignment of string
-nicematch	= 24	; a good enough match size
-bestlen		= 28	; size of best match so far
-scan		= 32	; ptr to string wanting match
-varsize		= 36	; number of bytes (also offset to last saved register)
-
-; Saved Registers (actually pushed into place)
-ebx_save	= 36
-edi_save	= 40
-esi_save	= 44
-ebp_save	= 48
-
-; Parameters
-retaddr		= 52
-deflatestate	= 56
-curmatch	= 60
-
-; Save registers that the compiler may be using
-	push	ebp
-	push	edi
-	push	esi
-	push	ebx
-
-; Allocate local variable space
-	sub	esp,varsize
-
-; Retrieve the function arguments. ecx will hold cur_match
-; throughout the entire function. edx will hold the pointer to the
-; deflate_state structure during the function's setup (before
-; entering the main loop).
-
-	mov	edx, [esp+deflatestate]
-ASSUME	edx:PTR DEFLATE_STATE
-
-	mov	ecx, [esp+curmatch]
-
-; uInt wmask = s->w_mask;
-; unsigned chain_length = s->max_chain_length;
-; if (s->prev_length >= s->good_match) {
-;     chain_length >>= 2;
-; }
-
-	mov	eax, [edx].ds_prev_length
-	mov	ebx, [edx].ds_good_match
-	cmp	eax, ebx
-	mov	eax, [edx].ds_w_mask
-	mov	ebx, [edx].ds_max_chain_length
-	jl	SHORT LastMatchGood
-	shr	ebx, 2
-LastMatchGood:
-
-; chainlen is decremented once beforehand so that the function can
-; use the sign flag instead of the zero flag for the exit test.
-; It is then shifted into the high word, to make room for the wmask
-; value, which it will always accompany.
-
-	dec	ebx
-	shl	ebx, 16
-	or	ebx, eax
-	mov	[esp+chainlenwmask], ebx
-
-; if ((uInt)nice_match > s->lookahead) nice_match = s->lookahead;
-
-	mov	eax, [edx].ds_nice_match
-	mov	ebx, [edx].ds_lookahead
-	cmp	ebx, eax
-	jl	SHORT LookaheadLess
-	mov	ebx, eax
-LookaheadLess:
-	mov	[esp+nicematch], ebx
-
-;/* register Bytef *scan = s->window + s->strstart;                     */
-
-	mov	esi, [edx].ds_window
-	mov	[esp+window], esi
-	mov	ebp, [edx].ds_strstart
-	lea	edi, [esi+ebp]
-	mov	[esp+scan],edi
-
-;/* Determine how many bytes the scan ptr is off from being             */
-;/* dword-aligned.                                                      */
-
-	mov	eax, edi
-	neg	eax
-	and	eax, 3
-	mov	[esp+scanalign], eax
-
-;/* IPos limit = s->strstart > (IPos)MAX_DIST(s) ?                      */
-;/*     s->strstart - (IPos)MAX_DIST(s) : NIL;                          */
-
-	mov	eax, [edx].ds_w_size
-	sub	eax, MIN_LOOKAHEAD
-	sub	ebp, eax
-	jg	SHORT LimitPositive
-	xor	ebp, ebp
-LimitPositive:
-
-;/* int best_len = s->prev_length;                                      */
-
-	mov	eax, [edx].ds_prev_length
-	mov	[esp+bestlen], eax
-
-;/* Store the sum of s->window + best_len in %esi locally, and in %esi. */
-
-	add	esi, eax
-	mov	[esp+windowbestlen], esi
-
-;/* register ush scan_start = *(ushf*)scan;                             */
-;/* register ush scan_end   = *(ushf*)(scan+best_len-1);                */
-;/* Posf *prev = s->prev;                                               */
-
-	movzx	ebx, WORD PTR[edi]
-	mov	[esp+scanstart], ebx
-	movzx	ebx, WORD PTR[eax+edi-1]
-	mov	[esp+scanend], ebx
-	mov	edi, [edx].ds_prev
-
-;/* Jump into the main loop.                                            */
-
-	mov	edx, [esp+chainlenwmask]
-	jmp	SHORT LoopEntry
-
-;/* do {
-; *     match = s->window + cur_match;
-; *     if (*(ushf*)(match+best_len-1) != scan_end ||
-; *         *(ushf*)match != scan_start) continue;
-; *     [...]
-; * } while ((cur_match = prev[cur_match & wmask]) > limit
-; *          && --chain_length != 0);
-; *
-; * Here is the inner loop of the function. The function will spend the
-; * majority of its time in this loop, and majority of that time will
-; * be spent in the first ten instructions.
-; *
-; * Within this loop:
-; * %ebx = scanend
-; * %ecx = curmatch
-; * %edx = chainlenwmask - i.e., ((chainlen << 16) | wmask)
-; * %esi = windowbestlen - i.e., (window + bestlen)
-; * %edi = prev
-; * %ebp = limit
-; */
-
-	ALIGN	4
-LookupLoop:
-	and	ecx, edx
-	movzx	ecx, WORD PTR[edi+ecx*2]
-	cmp	ecx, ebp
-	jbe	LeaveNow
-	sub	edx, 000010000H
-	js	LeaveNow
-
-LoopEntry:
-	movzx	eax, WORD PTR[esi+ecx-1]
-	cmp	eax, ebx
-	jnz	SHORT LookupLoop
-
-	mov	eax, [esp+window]
-	movzx	eax, WORD PTR[eax+ecx]
-	cmp	eax, [esp+scanstart]
-	jnz	SHORT LookupLoop
-
-;/* Store the current value of chainlen.                                */
-
-	mov	[esp+chainlenwmask], edx
-
-;/* Point %edi to the string under scrutiny, and %esi to the string we  */
-;/* are hoping to match it up with. In actuality, %esi and %edi are     */
-;/* both pointed (MAX_MATCH_8 - scanalign) bytes ahead, and %edx is     */
-;/* initialized to -(MAX_MATCH_8 - scanalign).                          */
-
-	mov	esi, [esp+window]
-	mov	edi, [esp+scan]
-	add	esi, ecx
-	mov	eax, [esp+scanalign]
-	mov	edx, -MAX_MATCH_8
-	lea	edi, [edi+eax+MAX_MATCH_8]
-	lea	esi, [esi+eax+MAX_MATCH_8]
-
-;/* Test the strings for equality, 8 bytes at a time. At the end,
-; * adjust %edx so that it is offset to the exact byte that mismatched.
-; *
-; * We already know at this point that the first three bytes of the
-; * strings match each other, and they can be safely passed over before
-; * starting the compare loop. So what this code does is skip over 0-3
-; * bytes, as much as necessary in order to dword-align the %edi
-; * pointer. (%esi will still be misaligned three times out of four.)
-; *
-; * It should be confessed that this loop usually does not represent
-; * much of the total running time. Replacing it with a more
-; * straightforward "rep cmpsb" would not drastically degrade
-; * performance.
-; */
-
-LoopCmps:
-	mov	eax, DWORD PTR[esi+edx]
-	xor	eax, DWORD PTR[edi+edx]
-	jnz	SHORT LeaveLoopCmps
-
-	mov	eax, DWORD PTR[esi+edx+4]
-	xor	eax, DWORD PTR[edi+edx+4]
-	jnz	SHORT LeaveLoopCmps4
-
-	add	edx, 8
-	jnz	SHORT LoopCmps
-	jmp	LenMaximum
-	ALIGN	4
-
-LeaveLoopCmps4:
-	add	edx, 4
-
-LeaveLoopCmps:
-	test	eax, 00000FFFFH
-	jnz	SHORT LenLower
-
-	add	edx, 2
-	shr	eax, 16
-
-LenLower:
-	sub	al, 1
-	adc	edx, 0
-
-;/* Calculate the length of the match. If it is longer than MAX_MATCH,  */
-;/* then automatically accept it as the best possible match and leave.  */
-
-	lea	eax, [edi+edx]
-	mov	edi, [esp+scan]
-	sub	eax, edi
-	cmp	eax, MAX_MATCH
-	jge	SHORT LenMaximum
-
-;/* If the length of the match is not longer than the best match we     */
-;/* have so far, then forget it and return to the lookup loop.          */
-
-	mov	edx, [esp+deflatestate]
-	mov	ebx, [esp+bestlen]
-	cmp	eax, ebx
-	jg	SHORT LongerMatch
-	mov	esi, [esp+windowbestlen]
-	mov	edi, [edx].ds_prev
-	mov	ebx, [esp+scanend]
-	mov	edx, [esp+chainlenwmask]
-	jmp	LookupLoop
-	ALIGN	4
-
-;/*         s->match_start = cur_match;                                 */
-;/*         best_len = len;                                             */
-;/*         if (len >= nice_match) break;                               */
-;/*         scan_end = *(ushf*)(scan+best_len-1);                       */
-
-LongerMatch:
-	mov	ebx, [esp+nicematch]
-	mov	[esp+bestlen], eax
-	mov	[edx].ds_match_start, ecx
-	cmp	eax, ebx
-	jge	SHORT LeaveNow
-	mov	esi, [esp+window]
-	add	esi, eax
-	mov	[esp+windowbestlen], esi
-	movzx	ebx, WORD PTR[edi+eax-1]
-	mov	edi, [edx].ds_prev
-	mov	[esp+scanend], ebx
-	mov	edx, [esp+chainlenwmask]
-	jmp	LookupLoop
-	ALIGN	4
-
-;/* Accept the current string, with the maximum possible length.        */
-
-LenMaximum:
-	mov	edx, [esp+deflatestate]
-	mov	DWORD PTR[esp+bestlen], MAX_MATCH
-	mov	[edx].ds_match_start, ecx
-
-;/* if ((uInt)best_len <= s->lookahead) return (uInt)best_len;          */
-;/* return s->lookahead;                                                */
-
-LeaveNow:
-	mov	edx, [esp+deflatestate]
-	mov	ebx, [esp+bestlen]
-	mov	eax, [edx].ds_lookahead
-	cmp	ebx, eax
-	jg	SHORT LookaheadRet
-	mov	eax, ebx
-LookaheadRet:
-
-; Restore the stack and return from whence we came.
-
-	add	esp, varsize
-	pop	ebx
-	pop	esi
-	pop	edi
-	pop	ebp
-	ret
-
-_longest_match	ENDP
-
-_TEXT	ENDS
-END
+

+; match.asm -- Pentium-Pro optimized version of longest_match()

+;

+; Updated for zlib 1.1.3 and converted to MASM 6.1x

+; Copyright (C) 2000 Dan Higdon <hdan@kinesoft.com>

+;                    and Chuck Walbourn <chuckw@kinesoft.com>

+; Corrections by Cosmin Truta <cosmint@cs.ubbcluj.ro>

+;

+; This is free software; you can redistribute it and/or modify it

+; under the terms of the GNU General Public License.

+

+; Based on match.S

+; Written for zlib 1.1.2

+; Copyright (C) 1998 Brian Raiter <breadbox@muppetlabs.com>

+;

+; Modified by Gilles Vollant (2005) for add gzhead and gzindex

+

+	.686P

+	.MODEL	FLAT

+

+;===========================================================================

+; EQUATES

+;===========================================================================

+

+MAX_MATCH	EQU 258

+MIN_MATCH	EQU 3

+MIN_LOOKAHEAD	EQU (MAX_MATCH + MIN_MATCH + 1)

+MAX_MATCH_8	EQU ((MAX_MATCH + 7) AND (NOT 7))

+

+;===========================================================================

+; STRUCTURES

+;===========================================================================

+

+; This STRUCT assumes a 4-byte alignment

+

+DEFLATE_STATE	STRUCT

+ds_strm			dd ?

+ds_status		dd ?

+ds_pending_buf		dd ?

+ds_pending_buf_size	dd ?

+ds_pending_out		dd ?

+ds_pending		dd ?

+ds_wrap			dd ?

+; gzhead and gzindex are added in zlib 1.2.2.2 (see deflate.h)

+ds_gzhead               dd ?

+ds_gzindex              dd ?

+ds_data_type		db ?

+ds_method		db ?

+			db ?	; padding

+			db ?	; padding

+ds_last_flush		dd ?

+ds_w_size		dd ?	; used

+ds_w_bits		dd ?

+ds_w_mask		dd ?	; used

+ds_window		dd ?	; used

+ds_window_size		dd ?

+ds_prev			dd ?	; used

+ds_head			dd ?

+ds_ins_h		dd ?

+ds_hash_size		dd ?

+ds_hash_bits		dd ?

+ds_hash_mask		dd ?

+ds_hash_shift		dd ?

+ds_block_start		dd ?

+ds_match_length		dd ?	; used

+ds_prev_match		dd ?	; used

+ds_match_available	dd ?

+ds_strstart		dd ?	; used

+ds_match_start		dd ?	; used

+ds_lookahead		dd ?	; used

+ds_prev_length		dd ?	; used

+ds_max_chain_length	dd ?	; used

+ds_max_laxy_match	dd ?

+ds_level		dd ?

+ds_strategy		dd ?

+ds_good_match		dd ?	; used

+ds_nice_match		dd ?	; used

+

+; Don't need anymore of the struct for match

+DEFLATE_STATE	ENDS

+

+;===========================================================================

+; CODE

+;===========================================================================

+_TEXT	SEGMENT

+

+;---------------------------------------------------------------------------

+; match_init

+;---------------------------------------------------------------------------

+	ALIGN	4

+PUBLIC	_match_init

+_match_init	PROC

+	; no initialization needed

+	ret

+_match_init	ENDP

+

+;---------------------------------------------------------------------------

+; uInt longest_match(deflate_state *deflatestate, IPos curmatch)

+;---------------------------------------------------------------------------

+	ALIGN	4

+

+PUBLIC	_longest_match

+_longest_match	PROC

+

+; Since this code uses EBP for a scratch register, the stack frame must

+; be manually constructed and referenced relative to the ESP register.

+

+; Stack image

+; Variables

+chainlenwmask	=  0	; high word: current chain len

+			; low word: s->wmask

+window		=  4	; local copy of s->window

+windowbestlen	=  8	; s->window + bestlen

+scanend		= 12	; last two bytes of string

+scanstart	= 16	; first two bytes of string

+scanalign	= 20	; dword-misalignment of string

+nicematch	= 24	; a good enough match size

+bestlen		= 28	; size of best match so far

+scan		= 32	; ptr to string wanting match

+varsize		= 36	; number of bytes (also offset to last saved register)

+

+; Saved Registers (actually pushed into place)

+ebx_save	= 36

+edi_save	= 40

+esi_save	= 44

+ebp_save	= 48

+

+; Parameters

+retaddr		= 52

+deflatestate	= 56

+curmatch	= 60

+

+; Save registers that the compiler may be using

+	push	ebp

+	push	edi

+	push	esi

+	push	ebx

+

+; Allocate local variable space

+	sub	esp,varsize

+

+; Retrieve the function arguments. ecx will hold cur_match

+; throughout the entire function. edx will hold the pointer to the

+; deflate_state structure during the function's setup (before

+; entering the main loop).

+

+	mov	edx, [esp+deflatestate]

+ASSUME	edx:PTR DEFLATE_STATE

+

+	mov	ecx, [esp+curmatch]

+

+; uInt wmask = s->w_mask;

+; unsigned chain_length = s->max_chain_length;

+; if (s->prev_length >= s->good_match) {

+;     chain_length >>= 2;

+; }

+

+	mov	eax, [edx].ds_prev_length

+	mov	ebx, [edx].ds_good_match

+	cmp	eax, ebx

+	mov	eax, [edx].ds_w_mask

+	mov	ebx, [edx].ds_max_chain_length

+	jl	SHORT LastMatchGood

+	shr	ebx, 2

+LastMatchGood:

+

+; chainlen is decremented once beforehand so that the function can

+; use the sign flag instead of the zero flag for the exit test.

+; It is then shifted into the high word, to make room for the wmask

+; value, which it will always accompany.

+

+	dec	ebx

+	shl	ebx, 16

+	or	ebx, eax

+	mov	[esp+chainlenwmask], ebx

+

+; if ((uInt)nice_match > s->lookahead) nice_match = s->lookahead;

+

+	mov	eax, [edx].ds_nice_match

+	mov	ebx, [edx].ds_lookahead

+	cmp	ebx, eax

+	jl	SHORT LookaheadLess

+	mov	ebx, eax

+LookaheadLess:

+	mov	[esp+nicematch], ebx

+

+;/* register Bytef *scan = s->window + s->strstart;                     */

+

+	mov	esi, [edx].ds_window

+	mov	[esp+window], esi

+	mov	ebp, [edx].ds_strstart

+	lea	edi, [esi+ebp]

+	mov	[esp+scan],edi

+

+;/* Determine how many bytes the scan ptr is off from being             */

+;/* dword-aligned.                                                      */

+

+	mov	eax, edi

+	neg	eax

+	and	eax, 3

+	mov	[esp+scanalign], eax

+

+;/* IPos limit = s->strstart > (IPos)MAX_DIST(s) ?                      */

+;/*     s->strstart - (IPos)MAX_DIST(s) : NIL;                          */

+

+	mov	eax, [edx].ds_w_size

+	sub	eax, MIN_LOOKAHEAD

+	sub	ebp, eax

+	jg	SHORT LimitPositive

+	xor	ebp, ebp

+LimitPositive:

+

+;/* int best_len = s->prev_length;                                      */

+

+	mov	eax, [edx].ds_prev_length

+	mov	[esp+bestlen], eax

+

+;/* Store the sum of s->window + best_len in %esi locally, and in %esi. */

+

+	add	esi, eax

+	mov	[esp+windowbestlen], esi

+

+;/* register ush scan_start = *(ushf*)scan;                             */

+;/* register ush scan_end   = *(ushf*)(scan+best_len-1);                */

+;/* Posf *prev = s->prev;                                               */

+

+	movzx	ebx, WORD PTR[edi]

+	mov	[esp+scanstart], ebx

+	movzx	ebx, WORD PTR[eax+edi-1]

+	mov	[esp+scanend], ebx

+	mov	edi, [edx].ds_prev

+

+;/* Jump into the main loop.                                            */

+

+	mov	edx, [esp+chainlenwmask]

+	jmp	SHORT LoopEntry

+

+;/* do {

+; *     match = s->window + cur_match;

+; *     if (*(ushf*)(match+best_len-1) != scan_end ||

+; *         *(ushf*)match != scan_start) continue;

+; *     [...]

+; * } while ((cur_match = prev[cur_match & wmask]) > limit

+; *          && --chain_length != 0);

+; *

+; * Here is the inner loop of the function. The function will spend the

+; * majority of its time in this loop, and majority of that time will

+; * be spent in the first ten instructions.

+; *

+; * Within this loop:

+; * %ebx = scanend

+; * %ecx = curmatch

+; * %edx = chainlenwmask - i.e., ((chainlen << 16) | wmask)

+; * %esi = windowbestlen - i.e., (window + bestlen)

+; * %edi = prev

+; * %ebp = limit

+; */

+

+	ALIGN	4

+LookupLoop:

+	and	ecx, edx

+	movzx	ecx, WORD PTR[edi+ecx*2]

+	cmp	ecx, ebp

+	jbe	LeaveNow

+	sub	edx, 000010000H

+	js	LeaveNow

+

+LoopEntry:

+	movzx	eax, WORD PTR[esi+ecx-1]

+	cmp	eax, ebx

+	jnz	SHORT LookupLoop

+

+	mov	eax, [esp+window]

+	movzx	eax, WORD PTR[eax+ecx]

+	cmp	eax, [esp+scanstart]

+	jnz	SHORT LookupLoop

+

+;/* Store the current value of chainlen.                                */

+

+	mov	[esp+chainlenwmask], edx

+

+;/* Point %edi to the string under scrutiny, and %esi to the string we  */

+;/* are hoping to match it up with. In actuality, %esi and %edi are     */

+;/* both pointed (MAX_MATCH_8 - scanalign) bytes ahead, and %edx is     */

+;/* initialized to -(MAX_MATCH_8 - scanalign).                          */

+

+	mov	esi, [esp+window]

+	mov	edi, [esp+scan]

+	add	esi, ecx

+	mov	eax, [esp+scanalign]

+	mov	edx, -MAX_MATCH_8

+	lea	edi, [edi+eax+MAX_MATCH_8]

+	lea	esi, [esi+eax+MAX_MATCH_8]

+

+;/* Test the strings for equality, 8 bytes at a time. At the end,

+; * adjust %edx so that it is offset to the exact byte that mismatched.

+; *

+; * We already know at this point that the first three bytes of the

+; * strings match each other, and they can be safely passed over before

+; * starting the compare loop. So what this code does is skip over 0-3

+; * bytes, as much as necessary in order to dword-align the %edi

+; * pointer. (%esi will still be misaligned three times out of four.)

+; *

+; * It should be confessed that this loop usually does not represent

+; * much of the total running time. Replacing it with a more

+; * straightforward "rep cmpsb" would not drastically degrade

+; * performance.

+; */

+

+LoopCmps:

+	mov	eax, DWORD PTR[esi+edx]

+	xor	eax, DWORD PTR[edi+edx]

+	jnz	SHORT LeaveLoopCmps

+

+	mov	eax, DWORD PTR[esi+edx+4]

+	xor	eax, DWORD PTR[edi+edx+4]

+	jnz	SHORT LeaveLoopCmps4

+

+	add	edx, 8

+	jnz	SHORT LoopCmps

+	jmp	LenMaximum

+	ALIGN	4

+

+LeaveLoopCmps4:

+	add	edx, 4

+

+LeaveLoopCmps:

+	test	eax, 00000FFFFH

+	jnz	SHORT LenLower

+

+	add	edx, 2

+	shr	eax, 16

+

+LenLower:

+	sub	al, 1

+	adc	edx, 0

+

+;/* Calculate the length of the match. If it is longer than MAX_MATCH,  */

+;/* then automatically accept it as the best possible match and leave.  */

+

+	lea	eax, [edi+edx]

+	mov	edi, [esp+scan]

+	sub	eax, edi

+	cmp	eax, MAX_MATCH

+	jge	SHORT LenMaximum

+

+;/* If the length of the match is not longer than the best match we     */

+;/* have so far, then forget it and return to the lookup loop.          */

+

+	mov	edx, [esp+deflatestate]

+	mov	ebx, [esp+bestlen]

+	cmp	eax, ebx

+	jg	SHORT LongerMatch

+	mov	esi, [esp+windowbestlen]

+	mov	edi, [edx].ds_prev

+	mov	ebx, [esp+scanend]

+	mov	edx, [esp+chainlenwmask]

+	jmp	LookupLoop

+	ALIGN	4

+

+;/*         s->match_start = cur_match;                                 */

+;/*         best_len = len;                                             */

+;/*         if (len >= nice_match) break;                               */

+;/*         scan_end = *(ushf*)(scan+best_len-1);                       */

+

+LongerMatch:

+	mov	ebx, [esp+nicematch]

+	mov	[esp+bestlen], eax

+	mov	[edx].ds_match_start, ecx

+	cmp	eax, ebx

+	jge	SHORT LeaveNow

+	mov	esi, [esp+window]

+	add	esi, eax

+	mov	[esp+windowbestlen], esi

+	movzx	ebx, WORD PTR[edi+eax-1]

+	mov	edi, [edx].ds_prev

+	mov	[esp+scanend], ebx

+	mov	edx, [esp+chainlenwmask]

+	jmp	LookupLoop

+	ALIGN	4

+

+;/* Accept the current string, with the maximum possible length.        */

+

+LenMaximum:

+	mov	edx, [esp+deflatestate]

+	mov	DWORD PTR[esp+bestlen], MAX_MATCH

+	mov	[edx].ds_match_start, ecx

+

+;/* if ((uInt)best_len <= s->lookahead) return (uInt)best_len;          */

+;/* return s->lookahead;                                                */

+

+LeaveNow:

+	mov	edx, [esp+deflatestate]

+	mov	ebx, [esp+bestlen]

+	mov	eax, [edx].ds_lookahead

+	cmp	ebx, eax

+	jg	SHORT LookaheadRet

+	mov	eax, ebx

+LookaheadRet:

+

+; Restore the stack and return from whence we came.

+

+	add	esp, varsize

+	pop	ebx

+	pop	esi

+	pop	edi

+	pop	ebp

+	ret

+

+_longest_match	ENDP

+

+_TEXT	ENDS

+END

diff --git a/zlib/contrib/masmx86/gvmat32.asm b/zlib/contrib/masmx86/gvmat32.asm
index ec360e67ada..874bb2d482b 100644
--- a/zlib/contrib/masmx86/gvmat32.asm
+++ b/zlib/contrib/masmx86/gvmat32.asm
@@ -1,905 +1,972 @@
-;
-; gvmat32.asm -- Asm portion of the optimized longest_match for 32 bits x86
-; Copyright (C) 1995-1996 Jean-loup Gailly and Gilles Vollant.
-; File written by Gilles Vollant, by modifiying the longest_match
-;  from Jean-loup Gailly in deflate.c
-; It need wmask == 0x7fff
-;     (assembly code is faster with a fixed wmask)
-;
-; For Visual C++ 4.2 and ML 6.11c (version in directory \MASM611C of Win95 DDK)
-;   I compile with : "ml /coff /Zi /c gvmat32.asm"
-;
-
-;uInt longest_match_7fff(s, cur_match)
-;    deflate_state *s;
-;    IPos cur_match;                             /* current match */
-
-	NbStack         equ     76
-	cur_match       equ     dword ptr[esp+NbStack-0]
-	str_s           equ     dword ptr[esp+NbStack-4]
-; 5 dword on top (ret,ebp,esi,edi,ebx)
-	adrret          equ     dword ptr[esp+NbStack-8]
-	pushebp         equ     dword ptr[esp+NbStack-12]
-	pushedi         equ     dword ptr[esp+NbStack-16]
-	pushesi         equ     dword ptr[esp+NbStack-20]
-	pushebx         equ     dword ptr[esp+NbStack-24]
-
-	chain_length    equ     dword ptr [esp+NbStack-28]
-	limit           equ     dword ptr [esp+NbStack-32]
-	best_len        equ     dword ptr [esp+NbStack-36]
-	window          equ     dword ptr [esp+NbStack-40]
-	prev            equ     dword ptr [esp+NbStack-44]
-	scan_start      equ      word ptr [esp+NbStack-48]
-	wmask           equ     dword ptr [esp+NbStack-52]
-	match_start_ptr equ     dword ptr [esp+NbStack-56]
-	nice_match      equ     dword ptr [esp+NbStack-60]
-	scan            equ     dword ptr [esp+NbStack-64]
-
-	windowlen       equ     dword ptr [esp+NbStack-68]
-	match_start     equ     dword ptr [esp+NbStack-72]
-	strend          equ     dword ptr [esp+NbStack-76]
-	NbStackAdd      equ     (NbStack-24)
-
-    .386p
-
-    name    gvmatch
-    .MODEL  FLAT
-
-
-
-;  all the +4 offsets are due to the addition of pending_buf_size (in zlib
-;  in the deflate_state structure since the asm code was first written
-;  (if you compile with zlib 1.0.4 or older, remove the +4).
-;  Note : these value are good with a 8 bytes boundary pack structure
-    dep_chain_length    equ     70h+4
-    dep_window          equ     2ch+4
-    dep_strstart        equ     60h+4
-    dep_prev_length     equ     6ch+4
-    dep_nice_match      equ     84h+4
-    dep_w_size          equ     20h+4
-    dep_prev            equ     34h+4
-    dep_w_mask          equ     28h+4
-    dep_good_match      equ     80h+4
-    dep_match_start     equ     64h+4
-    dep_lookahead       equ     68h+4
-
-
-_TEXT                   segment
-
-IFDEF NOUNDERLINE
-			public  longest_match_7fff
-			public  longest_match_686
-;                        public  match_init
-ELSE
-			public  _longest_match_7fff
-			public  _longest_match_686
-;                        public  _match_init
-ENDIF
-
-    MAX_MATCH           equ     258
-    MIN_MATCH           equ     3
-    MIN_LOOKAHEAD       equ     (MAX_MATCH+MIN_MATCH+1)
-
-
-
-IFDEF NOUNDERLINE
-;match_init      proc near
-;                ret
-;match_init      endp
-ELSE
-;_match_init     proc near
-;                ret
-;_match_init     endp
-ENDIF
-
-
-IFDEF NOUNDERLINE
-longest_match_7fff   proc near
-ELSE
-_longest_match_7fff  proc near
-ENDIF
-
-	mov     edx,[esp+4]
-
-
-
-	push    ebp
-	push    edi
-	push    esi
-	push    ebx
-
-	sub     esp,NbStackAdd
-
-; initialize or check the variables used in match.asm.
-	mov     ebp,edx
-
-; chain_length = s->max_chain_length
-; if (prev_length>=good_match) chain_length >>= 2
-	mov     edx,[ebp+dep_chain_length]
-	mov     ebx,[ebp+dep_prev_length]
-	cmp     [ebp+dep_good_match],ebx
-	ja      noshr
-	shr     edx,2
-noshr:
-; we increment chain_length because in the asm, the --chain_lenght is in the beginning of the loop
-	inc     edx
-	mov     edi,[ebp+dep_nice_match]
-	mov     chain_length,edx
-	mov     eax,[ebp+dep_lookahead]
-	cmp     eax,edi
-; if ((uInt)nice_match > s->lookahead) nice_match = s->lookahead;
-	jae     nolookaheadnicematch
-	mov     edi,eax
-nolookaheadnicematch:
-; best_len = s->prev_length
-	mov     best_len,ebx
-
-; window = s->window
-	mov     esi,[ebp+dep_window]
-	mov     ecx,[ebp+dep_strstart]
-	mov     window,esi
-
-	mov     nice_match,edi
-; scan = window + strstart
-	add     esi,ecx
-	mov     scan,esi
-; dx = *window
-	mov     dx,word ptr [esi]
-; bx = *(window+best_len-1)
-	mov     bx,word ptr [esi+ebx-1]
-	add     esi,MAX_MATCH-1
-; scan_start = *scan
-	mov     scan_start,dx
-; strend = scan + MAX_MATCH-1
-	mov     strend,esi
-; bx = scan_end = *(window+best_len-1)
-
-;    IPos limit = s->strstart > (IPos)MAX_DIST(s) ?
-;        s->strstart - (IPos)MAX_DIST(s) : NIL;
-
-	mov     esi,[ebp+dep_w_size]
-	sub     esi,MIN_LOOKAHEAD
-; here esi = MAX_DIST(s)
-	sub     ecx,esi
-	ja      nodist
-	xor     ecx,ecx
-nodist:
-	mov     limit,ecx
-
-; prev = s->prev
-	mov     edx,[ebp+dep_prev]
-	mov     prev,edx
-
-;
-	mov     edx,dword ptr [ebp+dep_match_start]
-	mov     bp,scan_start
-	mov     eax,cur_match
-	mov     match_start,edx
-
-	mov     edx,window
-	mov     edi,edx
-	add     edi,best_len
-	mov     esi,prev
-	dec     edi
-; windowlen = window + best_len -1
-	mov     windowlen,edi
-
-	jmp     beginloop2
-	align   4
-
-; here, in the loop
-;       eax = ax = cur_match
-;       ecx = limit
-;        bx = scan_end
-;        bp = scan_start
-;       edi = windowlen (window + best_len -1)
-;       esi = prev
-
-
-;// here; chain_length <=16
-normalbeg0add16:
-	add     chain_length,16
-	jz      exitloop
-normalbeg0:
-	cmp     word ptr[edi+eax],bx
-	je      normalbeg2noroll
-rcontlabnoroll:
-; cur_match = prev[cur_match & wmask]
-	and     eax,7fffh
-	mov     ax,word ptr[esi+eax*2]
-; if cur_match > limit, go to exitloop
-	cmp     ecx,eax
-	jnb     exitloop
-; if --chain_length != 0, go to exitloop
-	dec     chain_length
-	jnz     normalbeg0
-	jmp     exitloop
-
-normalbeg2noroll:
-; if (scan_start==*(cur_match+window)) goto normalbeg2
-	cmp     bp,word ptr[edx+eax]
-	jne     rcontlabnoroll
-	jmp     normalbeg2
-
-contloop3:
-	mov     edi,windowlen
-
-; cur_match = prev[cur_match & wmask]
-	and     eax,7fffh
-	mov     ax,word ptr[esi+eax*2]
-; if cur_match > limit, go to exitloop
-	cmp     ecx,eax
-jnbexitloopshort1:
-	jnb     exitloop
-; if --chain_length != 0, go to exitloop
-
-
-; begin the main loop
-beginloop2:
-	sub     chain_length,16+1
-; if chain_length <=16, don't use the unrolled loop
-	jna     normalbeg0add16
-
-do16:
-	cmp     word ptr[edi+eax],bx
-	je      normalbeg2dc0
-
-maccn   MACRO   lab
-	and     eax,7fffh
-	mov     ax,word ptr[esi+eax*2]
-	cmp     ecx,eax
-	jnb     exitloop
-	cmp     word ptr[edi+eax],bx
-	je      lab
-	ENDM
-
-rcontloop0:
-	maccn   normalbeg2dc1
-
-rcontloop1:
-	maccn   normalbeg2dc2
-
-rcontloop2:
-	maccn   normalbeg2dc3
-
-rcontloop3:
-	maccn   normalbeg2dc4
-
-rcontloop4:
-	maccn   normalbeg2dc5
-
-rcontloop5:
-	maccn   normalbeg2dc6
-
-rcontloop6:
-	maccn   normalbeg2dc7
-
-rcontloop7:
-	maccn   normalbeg2dc8
-
-rcontloop8:
-	maccn   normalbeg2dc9
-
-rcontloop9:
-	maccn   normalbeg2dc10
-
-rcontloop10:
-	maccn   short normalbeg2dc11
-
-rcontloop11:
-	maccn   short normalbeg2dc12
-
-rcontloop12:
-	maccn   short normalbeg2dc13
-
-rcontloop13:
-	maccn   short normalbeg2dc14
-
-rcontloop14:
-	maccn   short normalbeg2dc15
-
-rcontloop15:
-	and     eax,7fffh
-	mov     ax,word ptr[esi+eax*2]
-	cmp     ecx,eax
-	jnb     exitloop
-
-	sub     chain_length,16
-	ja      do16
-	jmp     normalbeg0add16
-
-;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
-
-normbeg MACRO   rcontlab,valsub
-; if we are here, we know that *(match+best_len-1) == scan_end
-	cmp     bp,word ptr[edx+eax]
-; if (match != scan_start) goto rcontlab
-	jne     rcontlab
-; calculate the good chain_length, and we'll compare scan and match string
-	add     chain_length,16-valsub
-	jmp     iseq
-	ENDM
-
-
-normalbeg2dc11:
-	normbeg rcontloop11,11
-
-normalbeg2dc12:
-	normbeg short rcontloop12,12
-
-normalbeg2dc13:
-	normbeg short rcontloop13,13
-
-normalbeg2dc14:
-	normbeg short rcontloop14,14
-
-normalbeg2dc15:
-	normbeg short rcontloop15,15
-
-normalbeg2dc10:
-	normbeg rcontloop10,10
-
-normalbeg2dc9:
-	normbeg rcontloop9,9
-
-normalbeg2dc8:
-	normbeg rcontloop8,8
-
-normalbeg2dc7:
-	normbeg rcontloop7,7
-
-normalbeg2dc6:
-	normbeg rcontloop6,6
-
-normalbeg2dc5:
-	normbeg rcontloop5,5
-
-normalbeg2dc4:
-	normbeg rcontloop4,4
-
-normalbeg2dc3:
-	normbeg rcontloop3,3
-
-normalbeg2dc2:
-	normbeg rcontloop2,2
-
-normalbeg2dc1:
-	normbeg rcontloop1,1
-
-normalbeg2dc0:
-	normbeg rcontloop0,0
-
-
-; we go in normalbeg2 because *(ushf*)(match+best_len-1) == scan_end
-
-normalbeg2:
-	mov     edi,window
-
-	cmp     bp,word ptr[edi+eax]
-	jne     contloop3                   ; if *(ushf*)match != scan_start, continue
-
-iseq:
-; if we are here, we know that *(match+best_len-1) == scan_end
-; and (match == scan_start)
-
-	mov     edi,edx
-	mov     esi,scan                    ; esi = scan
-	add     edi,eax                     ; edi = window + cur_match = match
-
-	mov     edx,[esi+3]                 ; compare manually dword at match+3
-	xor     edx,[edi+3]                 ; and scan +3
-
-	jz      begincompare                ; if equal, go to long compare
-
-; we will determine the unmatch byte and calculate len (in esi)
-	or      dl,dl
-	je      eq1rr
-	mov     esi,3
-	jmp     trfinval
-eq1rr:
-	or      dx,dx
-	je      eq1
-
-	mov     esi,4
-	jmp     trfinval
-eq1:
-	and     edx,0ffffffh
-	jz      eq11
-	mov     esi,5
-	jmp     trfinval
-eq11:
-	mov     esi,6
-	jmp     trfinval
-
-begincompare:
-	; here we now scan and match begin same
-	add     edi,6
-	add     esi,6
-	mov     ecx,(MAX_MATCH-(2+4))/4     ; scan for at most MAX_MATCH bytes
-	repe    cmpsd                       ; loop until mismatch
-
-	je      trfin                       ; go to trfin if not unmatch
-; we determine the unmatch byte
-	sub     esi,4
-	mov     edx,[edi-4]
-	xor     edx,[esi]
-
-	or      dl,dl
-	jnz     trfin
-	inc     esi
-
-	or      dx,dx
-	jnz     trfin
-	inc     esi
-
-	and     edx,0ffffffh
-	jnz     trfin
-	inc     esi
-
-trfin:
-	sub     esi,scan          ; esi = len
-trfinval:
-; here we have finised compare, and esi contain len of equal string
-	cmp     esi,best_len        ; if len > best_len, go newbestlen
-	ja      short newbestlen
-; now we restore edx, ecx and esi, for the big loop
-	mov     esi,prev
-	mov     ecx,limit
-	mov     edx,window
-	jmp     contloop3
-
-newbestlen:
-	mov     best_len,esi        ; len become best_len
-
-	mov     match_start,eax     ; save new position as match_start
-	cmp     esi,nice_match      ; if best_len >= nice_match, exit
-	jae     exitloop
-	mov     ecx,scan
-	mov     edx,window          ; restore edx=window
-	add     ecx,esi
-	add     esi,edx
-
-	dec     esi
-	mov     windowlen,esi       ; windowlen = window + best_len-1
-	mov     bx,[ecx-1]          ; bx = *(scan+best_len-1) = scan_end
-
-; now we restore ecx and esi, for the big loop :
-	mov     esi,prev
-	mov     ecx,limit
-	jmp     contloop3
-
-exitloop:
-; exit : s->match_start=match_start
-	mov     ebx,match_start
-	mov     ebp,str_s
-	mov     ecx,best_len
-	mov     dword ptr [ebp+dep_match_start],ebx
-	mov     eax,dword ptr [ebp+dep_lookahead]
-	cmp     ecx,eax
-	ja      minexlo
-	mov     eax,ecx
-minexlo:
-; return min(best_len,s->lookahead)
-
-; restore stack and register ebx,esi,edi,ebp
-	add     esp,NbStackAdd
-
-	pop     ebx
-	pop     esi
-	pop     edi
-	pop     ebp
-	ret
-InfoAuthor:
-; please don't remove this string !
-; Your are free use gvmat32 in any fre or commercial apps if you don't remove the string in the binary!
-	db     0dh,0ah,"GVMat32 optimised assembly code written 1996-98 by Gilles Vollant",0dh,0ah
-
-
-
-IFDEF NOUNDERLINE
-longest_match_7fff   endp
-ELSE
-_longest_match_7fff  endp
-ENDIF
-
-
-IFDEF NOUNDERLINE
-cpudetect32     proc near
-ELSE
-_cpudetect32    proc near
-ENDIF
-
-	push	ebx
-
-	pushfd                  ; push original EFLAGS
-	pop     eax             ; get original EFLAGS
-	mov     ecx, eax        ; save original EFLAGS
-	xor     eax, 40000h     ; flip AC bit in EFLAGS
-	push    eax             ; save new EFLAGS value on stack
-	popfd                   ; replace current EFLAGS value
-	pushfd                  ; get new EFLAGS
-	pop     eax             ; store new EFLAGS in EAX
-	xor     eax, ecx        ; can’t toggle AC bit, processor=80386
-	jz      end_cpu_is_386  ; jump if 80386 processor
-	push    ecx
-	popfd                   ; restore AC bit in EFLAGS first
-
-	pushfd
-	pushfd
-	pop     ecx
-
-	mov     eax, ecx        ; get original EFLAGS
-	xor     eax, 200000h    ; flip ID bit in EFLAGS
-	push    eax             ; save new EFLAGS value on stack
-	popfd                   ; replace current EFLAGS value
-	pushfd                  ; get new EFLAGS
-	pop		eax	            ; store new EFLAGS in EAX
-	popfd                   ; restore original EFLAGS
-	xor		eax, ecx        ; can’t toggle ID bit,
-	je		is_old_486		; processor=old
-
-	mov     eax,1
-	db      0fh,0a2h        ;CPUID
-
-exitcpudetect:
-	pop	ebx
-	ret
-
-end_cpu_is_386:
-	mov     eax,0300h
-	jmp     exitcpudetect
-
-is_old_486:
-	mov     eax,0400h
-	jmp     exitcpudetect
-
-IFDEF NOUNDERLINE
-cpudetect32     endp
-ELSE
-_cpudetect32    endp
-ENDIF
-
-
-
-
-MAX_MATCH       equ     258
-MIN_MATCH       equ     3
-MIN_LOOKAHEAD   equ     (MAX_MATCH + MIN_MATCH + 1)
-MAX_MATCH_8_     equ     ((MAX_MATCH + 7) AND 0FFF0h)
-
-
-;;; stack frame offsets
-
-chainlenwmask	equ  esp + 0	; high word: current chain len
-					; low word: s->wmask
-window		equ  esp + 4	; local copy of s->window
-windowbestlen	equ  esp + 8	; s->window + bestlen
-scanstart	equ  esp + 16	; first two bytes of string
-scanend		equ  esp + 12	; last two bytes of string
-scanalign	equ  esp + 20	; dword-misalignment of string
-nicematch	equ  esp + 24	; a good enough match size
-bestlen		equ  esp + 28	; size of best match so far
-scan		equ  esp + 32	; ptr to string wanting match
-
-LocalVarsSize	equ 36
-;	saved ebx	byte esp + 36
-;	saved edi	byte esp + 40
-;	saved esi	byte esp + 44
-;	saved ebp	byte esp + 48
-;	return address	byte esp + 52
-deflatestate	equ  esp + 56	; the function arguments
-curmatch	equ  esp + 60
-
-;;; Offsets for fields in the deflate_state structure. These numbers
-;;; are calculated from the definition of deflate_state, with the
-;;; assumption that the compiler will dword-align the fields. (Thus,
-;;; changing the definition of deflate_state could easily cause this
-;;; program to crash horribly, without so much as a warning at
-;;; compile time. Sigh.)
-
-dsWSize		equ 36
-dsWMask		equ 44
-dsWindow	equ 48
-dsPrev		equ 56
-dsMatchLen	equ 88
-dsPrevMatch	equ 92
-dsStrStart	equ 100
-dsMatchStart	equ 104
-dsLookahead	equ 108
-dsPrevLen	equ 112
-dsMaxChainLen	equ 116
-dsGoodMatch	equ 132
-dsNiceMatch	equ 136
-
-
-;;; match.asm -- Pentium-Pro-optimized version of longest_match()
-;;; Written for zlib 1.1.2
-;;; Copyright (C) 1998 Brian Raiter <breadbox@muppetlabs.com>
-;;; You can look at http://www.muppetlabs.com/~breadbox/software/assembly.html
-;;;
-;;; This is free software; you can redistribute it and/or modify it
-;;; under the terms of the GNU General Public License.
-
-;GLOBAL	_longest_match, _match_init
-
-
-;SECTION	.text
-
-;;; uInt longest_match(deflate_state *deflatestate, IPos curmatch)
-
-;_longest_match:
-IFDEF NOUNDERLINE
-longest_match_686   proc near
-ELSE
-_longest_match_686  proc near
-ENDIF
-
-
-;;; Save registers that the compiler may be using, and adjust esp to
-;;; make room for our stack frame.
-
-		push	ebp
-		push	edi
-		push	esi
-		push	ebx
-		sub	esp, LocalVarsSize
-
-;;; Retrieve the function arguments. ecx will hold cur_match
-;;; throughout the entire function. edx will hold the pointer to the
-;;; deflate_state structure during the function's setup (before
-;;; entering the main loop.
-
-		mov	edx, [deflatestate]
-		mov	ecx, [curmatch]
-
-;;; uInt wmask = s->w_mask;
-;;; unsigned chain_length = s->max_chain_length;
-;;; if (s->prev_length >= s->good_match) {
-;;;     chain_length >>= 2;
-;;; }
-
-		mov	eax, [edx + dsPrevLen]
-		mov	ebx, [edx + dsGoodMatch]
-		cmp	eax, ebx
-		mov	eax, [edx + dsWMask]
-		mov	ebx, [edx + dsMaxChainLen]
-		jl	LastMatchGood
-		shr	ebx, 2
-LastMatchGood:
-
-;;; chainlen is decremented once beforehand so that the function can
-;;; use the sign flag instead of the zero flag for the exit test.
-;;; It is then shifted into the high word, to make room for the wmask
-;;; value, which it will always accompany.
-
-		dec	ebx
-		shl	ebx, 16
-		or	ebx, eax
-		mov	[chainlenwmask], ebx
-
-;;; if ((uInt)nice_match > s->lookahead) nice_match = s->lookahead;
-
-		mov	eax, [edx + dsNiceMatch]
-		mov	ebx, [edx + dsLookahead]
-		cmp	ebx, eax
-		jl	LookaheadLess
-		mov	ebx, eax
-LookaheadLess:	mov	[nicematch], ebx
-
-;;; register Bytef *scan = s->window + s->strstart;
-
-		mov	esi, [edx + dsWindow]
-		mov	[window], esi
-		mov	ebp, [edx + dsStrStart]
-		lea	edi, [esi + ebp]
-		mov	[scan], edi
-
-;;; Determine how many bytes the scan ptr is off from being
-;;; dword-aligned.
-
-		mov	eax, edi
-		neg	eax
-		and	eax, 3
-		mov	[scanalign], eax
-
-;;; IPos limit = s->strstart > (IPos)MAX_DIST(s) ?
-;;;     s->strstart - (IPos)MAX_DIST(s) : NIL;
-
-		mov	eax, [edx + dsWSize]
-		sub	eax, MIN_LOOKAHEAD
-		sub	ebp, eax
-		jg	LimitPositive
-		xor	ebp, ebp
-LimitPositive:
-
-;;; int best_len = s->prev_length;
-
-		mov	eax, [edx + dsPrevLen]
-		mov	[bestlen], eax
-
-;;; Store the sum of s->window + best_len in esi locally, and in esi.
-
-		add	esi, eax
-		mov	[windowbestlen], esi
-
-;;; register ush scan_start = *(ushf*)scan;
-;;; register ush scan_end   = *(ushf*)(scan+best_len-1);
-;;; Posf *prev = s->prev;
-
-		movzx	ebx, word ptr [edi]
-		mov	[scanstart], ebx
-		movzx	ebx, word ptr [edi + eax - 1]
-		mov	[scanend], ebx
-		mov	edi, [edx + dsPrev]
-
-;;; Jump into the main loop.
-
-		mov	edx, [chainlenwmask]
-		jmp	short LoopEntry
-
-align 4
-
-;;; do {
-;;;     match = s->window + cur_match;
-;;;     if (*(ushf*)(match+best_len-1) != scan_end ||
-;;;         *(ushf*)match != scan_start) continue;
-;;;     [...]
-;;; } while ((cur_match = prev[cur_match & wmask]) > limit
-;;;          && --chain_length != 0);
-;;;
-;;; Here is the inner loop of the function. The function will spend the
-;;; majority of its time in this loop, and majority of that time will
-;;; be spent in the first ten instructions.
-;;;
-;;; Within this loop:
-;;; ebx = scanend
-;;; ecx = curmatch
-;;; edx = chainlenwmask - i.e., ((chainlen << 16) | wmask)
-;;; esi = windowbestlen - i.e., (window + bestlen)
-;;; edi = prev
-;;; ebp = limit
-
-LookupLoop:
-		and	ecx, edx
-		movzx	ecx, word ptr [edi + ecx*2]
-		cmp	ecx, ebp
-		jbe	LeaveNow
-		sub	edx, 00010000h
-		js	LeaveNow
-LoopEntry:	movzx	eax, word ptr [esi + ecx - 1]
-		cmp	eax, ebx
-		jnz	LookupLoop
-		mov	eax, [window]
-		movzx	eax, word ptr [eax + ecx]
-		cmp	eax, [scanstart]
-		jnz	LookupLoop
-
-;;; Store the current value of chainlen.
-
-		mov	[chainlenwmask], edx
-
-;;; Point edi to the string under scrutiny, and esi to the string we
-;;; are hoping to match it up with. In actuality, esi and edi are
-;;; both pointed (MAX_MATCH_8 - scanalign) bytes ahead, and edx is
-;;; initialized to -(MAX_MATCH_8 - scanalign).
-
-		mov	esi, [window]
-		mov	edi, [scan]
-		add	esi, ecx
-		mov	eax, [scanalign]
-		mov	edx, 0fffffef8h; -(MAX_MATCH_8)
-		lea	edi, [edi + eax + 0108h] ;MAX_MATCH_8]
-		lea	esi, [esi + eax + 0108h] ;MAX_MATCH_8]
-
-;;; Test the strings for equality, 8 bytes at a time. At the end,
-;;; adjust edx so that it is offset to the exact byte that mismatched.
-;;;
-;;; We already know at this point that the first three bytes of the
-;;; strings match each other, and they can be safely passed over before
-;;; starting the compare loop. So what this code does is skip over 0-3
-;;; bytes, as much as necessary in order to dword-align the edi
-;;; pointer. (esi will still be misaligned three times out of four.)
-;;;
-;;; It should be confessed that this loop usually does not represent
-;;; much of the total running time. Replacing it with a more
-;;; straightforward "rep cmpsb" would not drastically degrade
-;;; performance.
-
-LoopCmps:
-		mov	eax, [esi + edx]
-		xor	eax, [edi + edx]
-		jnz	LeaveLoopCmps
-		mov	eax, [esi + edx + 4]
-		xor	eax, [edi + edx + 4]
-		jnz	LeaveLoopCmps4
-		add	edx, 8
-		jnz	LoopCmps
-		jmp	short LenMaximum
-LeaveLoopCmps4:	add	edx, 4
-LeaveLoopCmps:	test	eax, 0000FFFFh
-		jnz	LenLower
-		add	edx,  2
-		shr	eax, 16
-LenLower:	sub	al, 1
-		adc	edx, 0
-
-;;; Calculate the length of the match. If it is longer than MAX_MATCH,
-;;; then automatically accept it as the best possible match and leave.
-
-		lea	eax, [edi + edx]
-		mov	edi, [scan]
-		sub	eax, edi
-		cmp	eax, MAX_MATCH
-		jge	LenMaximum
-
-;;; If the length of the match is not longer than the best match we
-;;; have so far, then forget it and return to the lookup loop.
-
-		mov	edx, [deflatestate]
-		mov	ebx, [bestlen]
-		cmp	eax, ebx
-		jg	LongerMatch
-		mov	esi, [windowbestlen]
-		mov	edi, [edx + dsPrev]
-		mov	ebx, [scanend]
-		mov	edx, [chainlenwmask]
-		jmp	LookupLoop
-
-;;;         s->match_start = cur_match;
-;;;         best_len = len;
-;;;         if (len >= nice_match) break;
-;;;         scan_end = *(ushf*)(scan+best_len-1);
-
-LongerMatch:	mov	ebx, [nicematch]
-		mov	[bestlen], eax
-		mov	[edx + dsMatchStart], ecx
-		cmp	eax, ebx
-		jge	LeaveNow
-		mov	esi, [window]
-		add	esi, eax
-		mov	[windowbestlen], esi
-		movzx	ebx, word ptr [edi + eax - 1]
-		mov	edi, [edx + dsPrev]
-		mov	[scanend], ebx
-		mov	edx, [chainlenwmask]
-		jmp	LookupLoop
-
-;;; Accept the current string, with the maximum possible length.
-
-LenMaximum:	mov	edx, [deflatestate]
-		mov	dword ptr [bestlen], MAX_MATCH
-		mov	[edx + dsMatchStart], ecx
-
-;;; if ((uInt)best_len <= s->lookahead) return (uInt)best_len;
-;;; return s->lookahead;
-
-LeaveNow:
-		mov	edx, [deflatestate]
-		mov	ebx, [bestlen]
-		mov	eax, [edx + dsLookahead]
-		cmp	ebx, eax
-		jg	LookaheadRet
-		mov	eax, ebx
-LookaheadRet:
-
-;;; Restore the stack and return from whence we came.
-
-		add	esp, LocalVarsSize
-		pop	ebx
-		pop	esi
-		pop	edi
-		pop	ebp
-
-		ret
-; please don't remove this string !
-; Your can freely use gvmat32 in any free or commercial app if you don't remove the string in the binary!
-	db     0dh,0ah,"asm686 with masm, optimised assembly code from Brian Raiter, written 1998",0dh,0ah
-
-IFDEF NOUNDERLINE
-longest_match_686   endp
-ELSE
-_longest_match_686  endp
-ENDIF
-
-_TEXT   ends
-end
+; gvmat32.asm -- Asm portion of the optimized longest_match for 32 bits x86

+; Copyright (C) 1995-1996 Jean-loup Gailly and Gilles Vollant.

+; File written by Gilles Vollant, by modifiying the longest_match

+;  from Jean-loup Gailly in deflate.c

+;

+;         http://www.zlib.net

+;         http://www.winimage.com/zLibDll

+;         http://www.muppetlabs.com/~breadbox/software/assembly.html

+;

+; 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/

+;

+; this file contain two implementation of longest_match

+;

+;  longest_match_7fff : written 1996 by Gilles Vollant optimized for 

+;            first Pentium. Assume s->w_mask == 0x7fff

+;  longest_match_686 : written by Brian raiter (1998), optimized for Pentium Pro

+;

+;  for using an seembly version of longest_match, you need define ASMV in project

+;  There is two way in using gvmat32.asm

+;

+;  A) Suggested method

+;    if you want include both longest_match_7fff and longest_match_686

+;    compile the asm file running

+;           ml /coff /Zi /Flgvmat32.lst /c gvmat32.asm

+;    and include gvmat32c.c in your project

+;    if you have an old cpu (386,486 or first Pentium) and s->w_mask==0x7fff,

+;        longest_match_7fff will be used

+;    if you have a more modern CPU (Pentium Pro, II and higher)

+;        longest_match_686 will be used

+;    on old cpu with s->w_mask!=0x7fff, longest_match_686 will be used,

+;        but this is not a sitation you'll find often

+;

+;  B) Alternative

+;    if you are not interresed in old cpu performance and want the smaller

+;       binaries possible

+;

+;    compile the asm file running

+;           ml /coff /Zi /c /Flgvmat32.lst /DNOOLDPENTIUMCODE gvmat32.asm

+;    and do not include gvmat32c.c in your project (ou define also 

+;              NOOLDPENTIUMCODE)

+;

+; note : as I known, longest_match_686 is very faster than longest_match_7fff

+;        on pentium Pro/II/III, faster (but less) in P4, but it seem

+;        longest_match_7fff can be faster (very very litte) on AMD Athlon64/K8

+;

+; see below : zlib1222add must be adjuster if you use a zlib version < 1.2.2.2

+

+;uInt longest_match_7fff(s, cur_match)

+;    deflate_state *s;

+;    IPos cur_match;                             /* current match */

+

+    NbStack         equ     76

+    cur_match       equ     dword ptr[esp+NbStack-0]

+    str_s           equ     dword ptr[esp+NbStack-4]

+; 5 dword on top (ret,ebp,esi,edi,ebx)

+    adrret          equ     dword ptr[esp+NbStack-8]

+    pushebp         equ     dword ptr[esp+NbStack-12]

+    pushedi         equ     dword ptr[esp+NbStack-16]

+    pushesi         equ     dword ptr[esp+NbStack-20]

+    pushebx         equ     dword ptr[esp+NbStack-24]

+

+    chain_length    equ     dword ptr [esp+NbStack-28]

+    limit           equ     dword ptr [esp+NbStack-32]

+    best_len        equ     dword ptr [esp+NbStack-36]

+    window          equ     dword ptr [esp+NbStack-40]

+    prev            equ     dword ptr [esp+NbStack-44]

+    scan_start      equ      word ptr [esp+NbStack-48]

+    wmask           equ     dword ptr [esp+NbStack-52]

+    match_start_ptr equ     dword ptr [esp+NbStack-56]

+    nice_match      equ     dword ptr [esp+NbStack-60]

+    scan            equ     dword ptr [esp+NbStack-64]

+

+    windowlen       equ     dword ptr [esp+NbStack-68]

+    match_start     equ     dword ptr [esp+NbStack-72]

+    strend          equ     dword ptr [esp+NbStack-76]

+    NbStackAdd      equ     (NbStack-24)

+

+    .386p

+

+    name    gvmatch

+    .MODEL  FLAT

+

+

+

+;  all the +zlib1222add offsets are due to the addition of fields

+;  in zlib in the deflate_state structure since the asm code was first written

+;  (if you compile with zlib 1.0.4 or older, use "zlib1222add equ (-4)").

+;  (if you compile with zlib between 1.0.5 and 1.2.2.1, use "zlib1222add equ 0").

+;  if you compile with zlib 1.2.2.2 or later , use "zlib1222add equ 8").

+

+    zlib1222add         equ     8

+

+;  Note : these value are good with a 8 bytes boundary pack structure

+    dep_chain_length    equ     74h+zlib1222add

+    dep_window          equ     30h+zlib1222add

+    dep_strstart        equ     64h+zlib1222add

+    dep_prev_length     equ     70h+zlib1222add

+    dep_nice_match      equ     88h+zlib1222add

+    dep_w_size          equ     24h+zlib1222add

+    dep_prev            equ     38h+zlib1222add

+    dep_w_mask          equ     2ch+zlib1222add

+    dep_good_match      equ     84h+zlib1222add

+    dep_match_start     equ     68h+zlib1222add

+    dep_lookahead       equ     6ch+zlib1222add

+

+

+_TEXT                   segment

+

+IFDEF NOUNDERLINE

+   IFDEF NOOLDPENTIUMCODE

+            public  longest_match

+            public  match_init

+   ELSE            

+            public  longest_match_7fff

+            public  cpudetect32

+            public  longest_match_686

+   ENDIF

+ELSE

+   IFDEF NOOLDPENTIUMCODE

+            public  _longest_match

+            public  _match_init

+   ELSE

+            public  _longest_match_7fff

+            public  _cpudetect32

+            public  _longest_match_686

+   ENDIF

+ENDIF

+

+    MAX_MATCH           equ     258

+    MIN_MATCH           equ     3

+    MIN_LOOKAHEAD       equ     (MAX_MATCH+MIN_MATCH+1)

+

+

+

+IFNDEF NOOLDPENTIUMCODE

+IFDEF NOUNDERLINE

+longest_match_7fff   proc near

+ELSE

+_longest_match_7fff  proc near

+ENDIF

+

+    mov     edx,[esp+4]

+

+

+

+    push    ebp

+    push    edi

+    push    esi

+    push    ebx

+

+    sub     esp,NbStackAdd

+

+; initialize or check the variables used in match.asm.

+    mov     ebp,edx

+

+; chain_length = s->max_chain_length

+; if (prev_length>=good_match) chain_length >>= 2

+    mov     edx,[ebp+dep_chain_length]

+    mov     ebx,[ebp+dep_prev_length]

+    cmp     [ebp+dep_good_match],ebx

+    ja      noshr

+    shr     edx,2

+noshr:

+; we increment chain_length because in the asm, the --chain_lenght is in the beginning of the loop

+    inc     edx

+    mov     edi,[ebp+dep_nice_match]

+    mov     chain_length,edx

+    mov     eax,[ebp+dep_lookahead]

+    cmp     eax,edi

+; if ((uInt)nice_match > s->lookahead) nice_match = s->lookahead;

+    jae     nolookaheadnicematch

+    mov     edi,eax

+nolookaheadnicematch:

+; best_len = s->prev_length

+    mov     best_len,ebx

+

+; window = s->window

+    mov     esi,[ebp+dep_window]

+    mov     ecx,[ebp+dep_strstart]

+    mov     window,esi

+

+    mov     nice_match,edi

+; scan = window + strstart

+    add     esi,ecx

+    mov     scan,esi

+; dx = *window

+    mov     dx,word ptr [esi]

+; bx = *(window+best_len-1)

+    mov     bx,word ptr [esi+ebx-1]

+    add     esi,MAX_MATCH-1

+; scan_start = *scan

+    mov     scan_start,dx

+; strend = scan + MAX_MATCH-1

+    mov     strend,esi

+; bx = scan_end = *(window+best_len-1)

+

+;    IPos limit = s->strstart > (IPos)MAX_DIST(s) ?

+;        s->strstart - (IPos)MAX_DIST(s) : NIL;

+

+    mov     esi,[ebp+dep_w_size]

+    sub     esi,MIN_LOOKAHEAD

+; here esi = MAX_DIST(s)

+    sub     ecx,esi

+    ja      nodist

+    xor     ecx,ecx

+nodist:

+    mov     limit,ecx

+

+; prev = s->prev

+    mov     edx,[ebp+dep_prev]

+    mov     prev,edx

+

+;

+    mov     edx,dword ptr [ebp+dep_match_start]

+    mov     bp,scan_start

+    mov     eax,cur_match

+    mov     match_start,edx

+

+    mov     edx,window

+    mov     edi,edx

+    add     edi,best_len

+    mov     esi,prev

+    dec     edi

+; windowlen = window + best_len -1

+    mov     windowlen,edi

+

+    jmp     beginloop2

+    align   4

+

+; here, in the loop

+;       eax = ax = cur_match

+;       ecx = limit

+;        bx = scan_end

+;        bp = scan_start

+;       edi = windowlen (window + best_len -1)

+;       esi = prev

+

+

+;// here; chain_length <=16

+normalbeg0add16:

+    add     chain_length,16

+    jz      exitloop

+normalbeg0:

+    cmp     word ptr[edi+eax],bx

+    je      normalbeg2noroll

+rcontlabnoroll:

+; cur_match = prev[cur_match & wmask]

+    and     eax,7fffh

+    mov     ax,word ptr[esi+eax*2]

+; if cur_match > limit, go to exitloop

+    cmp     ecx,eax

+    jnb     exitloop

+; if --chain_length != 0, go to exitloop

+    dec     chain_length

+    jnz     normalbeg0

+    jmp     exitloop

+

+normalbeg2noroll:

+; if (scan_start==*(cur_match+window)) goto normalbeg2

+    cmp     bp,word ptr[edx+eax]

+    jne     rcontlabnoroll

+    jmp     normalbeg2

+

+contloop3:

+    mov     edi,windowlen

+

+; cur_match = prev[cur_match & wmask]

+    and     eax,7fffh

+    mov     ax,word ptr[esi+eax*2]

+; if cur_match > limit, go to exitloop

+    cmp     ecx,eax

+jnbexitloopshort1:

+    jnb     exitloop

+; if --chain_length != 0, go to exitloop

+

+

+; begin the main loop

+beginloop2:

+    sub     chain_length,16+1

+; if chain_length <=16, don't use the unrolled loop

+    jna     normalbeg0add16

+

+do16:

+    cmp     word ptr[edi+eax],bx

+    je      normalbeg2dc0

+

+maccn   MACRO   lab

+    and     eax,7fffh

+    mov     ax,word ptr[esi+eax*2]

+    cmp     ecx,eax

+    jnb     exitloop

+    cmp     word ptr[edi+eax],bx

+    je      lab

+    ENDM

+

+rcontloop0:

+    maccn   normalbeg2dc1

+

+rcontloop1:

+    maccn   normalbeg2dc2

+

+rcontloop2:

+    maccn   normalbeg2dc3

+

+rcontloop3:

+    maccn   normalbeg2dc4

+

+rcontloop4:

+    maccn   normalbeg2dc5

+

+rcontloop5:

+    maccn   normalbeg2dc6

+

+rcontloop6:

+    maccn   normalbeg2dc7

+

+rcontloop7:

+    maccn   normalbeg2dc8

+

+rcontloop8:

+    maccn   normalbeg2dc9

+

+rcontloop9:

+    maccn   normalbeg2dc10

+

+rcontloop10:

+    maccn   short normalbeg2dc11

+

+rcontloop11:

+    maccn   short normalbeg2dc12

+

+rcontloop12:

+    maccn   short normalbeg2dc13

+

+rcontloop13:

+    maccn   short normalbeg2dc14

+

+rcontloop14:

+    maccn   short normalbeg2dc15

+

+rcontloop15:

+    and     eax,7fffh

+    mov     ax,word ptr[esi+eax*2]

+    cmp     ecx,eax

+    jnb     exitloop

+

+    sub     chain_length,16

+    ja      do16

+    jmp     normalbeg0add16

+

+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;

+

+normbeg MACRO   rcontlab,valsub

+; if we are here, we know that *(match+best_len-1) == scan_end

+    cmp     bp,word ptr[edx+eax]

+; if (match != scan_start) goto rcontlab

+    jne     rcontlab

+; calculate the good chain_length, and we'll compare scan and match string

+    add     chain_length,16-valsub

+    jmp     iseq

+    ENDM

+

+

+normalbeg2dc11:

+    normbeg rcontloop11,11

+

+normalbeg2dc12:

+    normbeg short rcontloop12,12

+

+normalbeg2dc13:

+    normbeg short rcontloop13,13

+

+normalbeg2dc14:

+    normbeg short rcontloop14,14

+

+normalbeg2dc15:

+    normbeg short rcontloop15,15

+

+normalbeg2dc10:

+    normbeg rcontloop10,10

+

+normalbeg2dc9:

+    normbeg rcontloop9,9

+

+normalbeg2dc8:

+    normbeg rcontloop8,8

+

+normalbeg2dc7:

+    normbeg rcontloop7,7

+

+normalbeg2dc6:

+    normbeg rcontloop6,6

+

+normalbeg2dc5:

+    normbeg rcontloop5,5

+

+normalbeg2dc4:

+    normbeg rcontloop4,4

+

+normalbeg2dc3:

+    normbeg rcontloop3,3

+

+normalbeg2dc2:

+    normbeg rcontloop2,2

+

+normalbeg2dc1:

+    normbeg rcontloop1,1

+

+normalbeg2dc0:

+    normbeg rcontloop0,0

+

+

+; we go in normalbeg2 because *(ushf*)(match+best_len-1) == scan_end

+

+normalbeg2:

+    mov     edi,window

+

+    cmp     bp,word ptr[edi+eax]

+    jne     contloop3                   ; if *(ushf*)match != scan_start, continue

+

+iseq:

+; if we are here, we know that *(match+best_len-1) == scan_end

+; and (match == scan_start)

+

+    mov     edi,edx

+    mov     esi,scan                    ; esi = scan

+    add     edi,eax                     ; edi = window + cur_match = match

+

+    mov     edx,[esi+3]                 ; compare manually dword at match+3

+    xor     edx,[edi+3]                 ; and scan +3

+

+    jz      begincompare                ; if equal, go to long compare

+

+; we will determine the unmatch byte and calculate len (in esi)

+    or      dl,dl

+    je      eq1rr

+    mov     esi,3

+    jmp     trfinval

+eq1rr:

+    or      dx,dx

+    je      eq1

+

+    mov     esi,4

+    jmp     trfinval

+eq1:

+    and     edx,0ffffffh

+    jz      eq11

+    mov     esi,5

+    jmp     trfinval

+eq11:

+    mov     esi,6

+    jmp     trfinval

+

+begincompare:

+    ; here we now scan and match begin same

+    add     edi,6

+    add     esi,6

+    mov     ecx,(MAX_MATCH-(2+4))/4     ; scan for at most MAX_MATCH bytes

+    repe    cmpsd                       ; loop until mismatch

+

+    je      trfin                       ; go to trfin if not unmatch

+; we determine the unmatch byte

+    sub     esi,4

+    mov     edx,[edi-4]

+    xor     edx,[esi]

+

+    or      dl,dl

+    jnz     trfin

+    inc     esi

+

+    or      dx,dx

+    jnz     trfin

+    inc     esi

+

+    and     edx,0ffffffh

+    jnz     trfin

+    inc     esi

+

+trfin:

+    sub     esi,scan          ; esi = len

+trfinval:

+; here we have finised compare, and esi contain len of equal string

+    cmp     esi,best_len        ; if len > best_len, go newbestlen

+    ja      short newbestlen

+; now we restore edx, ecx and esi, for the big loop

+    mov     esi,prev

+    mov     ecx,limit

+    mov     edx,window

+    jmp     contloop3

+

+newbestlen:

+    mov     best_len,esi        ; len become best_len

+

+    mov     match_start,eax     ; save new position as match_start

+    cmp     esi,nice_match      ; if best_len >= nice_match, exit

+    jae     exitloop

+    mov     ecx,scan

+    mov     edx,window          ; restore edx=window

+    add     ecx,esi

+    add     esi,edx

+

+    dec     esi

+    mov     windowlen,esi       ; windowlen = window + best_len-1

+    mov     bx,[ecx-1]          ; bx = *(scan+best_len-1) = scan_end

+

+; now we restore ecx and esi, for the big loop :

+    mov     esi,prev

+    mov     ecx,limit

+    jmp     contloop3

+

+exitloop:

+; exit : s->match_start=match_start

+    mov     ebx,match_start

+    mov     ebp,str_s

+    mov     ecx,best_len

+    mov     dword ptr [ebp+dep_match_start],ebx

+    mov     eax,dword ptr [ebp+dep_lookahead]

+    cmp     ecx,eax

+    ja      minexlo

+    mov     eax,ecx

+minexlo:

+; return min(best_len,s->lookahead)

+

+; restore stack and register ebx,esi,edi,ebp

+    add     esp,NbStackAdd

+

+    pop     ebx

+    pop     esi

+    pop     edi

+    pop     ebp

+    ret

+InfoAuthor:

+; please don't remove this string !

+; Your are free use gvmat32 in any fre or commercial apps if you don't remove the string in the binary!

+    db     0dh,0ah,"GVMat32 optimised assembly code written 1996-98 by Gilles Vollant",0dh,0ah

+

+

+

+IFDEF NOUNDERLINE

+longest_match_7fff   endp

+ELSE

+_longest_match_7fff  endp

+ENDIF

+

+

+IFDEF NOUNDERLINE

+cpudetect32     proc near

+ELSE

+_cpudetect32    proc near

+ENDIF

+

+    push    ebx

+

+    pushfd                  ; push original EFLAGS

+    pop     eax             ; get original EFLAGS

+    mov     ecx, eax        ; save original EFLAGS

+    xor     eax, 40000h     ; flip AC bit in EFLAGS

+    push    eax             ; save new EFLAGS value on stack

+    popfd                   ; replace current EFLAGS value

+    pushfd                  ; get new EFLAGS

+    pop     eax             ; store new EFLAGS in EAX

+    xor     eax, ecx        ; can’t toggle AC bit, processor=80386

+    jz      end_cpu_is_386  ; jump if 80386 processor

+    push    ecx

+    popfd                   ; restore AC bit in EFLAGS first

+

+    pushfd

+    pushfd

+    pop     ecx

+

+    mov     eax, ecx        ; get original EFLAGS

+    xor     eax, 200000h    ; flip ID bit in EFLAGS

+    push    eax             ; save new EFLAGS value on stack

+    popfd                   ; replace current EFLAGS value

+    pushfd                  ; get new EFLAGS

+    pop     eax             ; store new EFLAGS in EAX

+    popfd                   ; restore original EFLAGS

+    xor     eax, ecx        ; can’t toggle ID bit,

+    je      is_old_486      ; processor=old

+

+    mov     eax,1

+    db      0fh,0a2h        ;CPUID

+

+exitcpudetect:

+    pop ebx

+    ret

+

+end_cpu_is_386:

+    mov     eax,0300h

+    jmp     exitcpudetect

+

+is_old_486:

+    mov     eax,0400h

+    jmp     exitcpudetect

+

+IFDEF NOUNDERLINE

+cpudetect32     endp

+ELSE

+_cpudetect32    endp

+ENDIF

+ENDIF

+

+MAX_MATCH       equ     258

+MIN_MATCH       equ     3

+MIN_LOOKAHEAD   equ     (MAX_MATCH + MIN_MATCH + 1)

+MAX_MATCH_8_     equ     ((MAX_MATCH + 7) AND 0FFF0h)

+

+

+;;; stack frame offsets

+

+chainlenwmask   equ  esp + 0    ; high word: current chain len

+                    ; low word: s->wmask

+window      equ  esp + 4    ; local copy of s->window

+windowbestlen   equ  esp + 8    ; s->window + bestlen

+scanstart   equ  esp + 16   ; first two bytes of string

+scanend     equ  esp + 12   ; last two bytes of string

+scanalign   equ  esp + 20   ; dword-misalignment of string

+nicematch   equ  esp + 24   ; a good enough match size

+bestlen     equ  esp + 28   ; size of best match so far

+scan        equ  esp + 32   ; ptr to string wanting match

+

+LocalVarsSize   equ 36

+;   saved ebx   byte esp + 36

+;   saved edi   byte esp + 40

+;   saved esi   byte esp + 44

+;   saved ebp   byte esp + 48

+;   return address  byte esp + 52

+deflatestate    equ  esp + 56   ; the function arguments

+curmatch    equ  esp + 60

+

+;;; Offsets for fields in the deflate_state structure. These numbers

+;;; are calculated from the definition of deflate_state, with the

+;;; assumption that the compiler will dword-align the fields. (Thus,

+;;; changing the definition of deflate_state could easily cause this

+;;; program to crash horribly, without so much as a warning at

+;;; compile time. Sigh.)

+

+dsWSize     equ 36+zlib1222add

+dsWMask     equ 44+zlib1222add

+dsWindow    equ 48+zlib1222add

+dsPrev      equ 56+zlib1222add

+dsMatchLen  equ 88+zlib1222add

+dsPrevMatch equ 92+zlib1222add

+dsStrStart  equ 100+zlib1222add

+dsMatchStart    equ 104+zlib1222add

+dsLookahead equ 108+zlib1222add

+dsPrevLen   equ 112+zlib1222add

+dsMaxChainLen   equ 116+zlib1222add

+dsGoodMatch equ 132+zlib1222add

+dsNiceMatch equ 136+zlib1222add

+

+

+;;; match.asm -- Pentium-Pro-optimized version of longest_match()

+;;; Written for zlib 1.1.2

+;;; Copyright (C) 1998 Brian Raiter <breadbox@muppetlabs.com>

+;;; You can look at http://www.muppetlabs.com/~breadbox/software/assembly.html

+;;;

+;;; This is free software; you can redistribute it and/or modify it

+;;; under the terms of the GNU General Public License.

+

+;GLOBAL _longest_match, _match_init

+

+

+;SECTION    .text

+

+;;; uInt longest_match(deflate_state *deflatestate, IPos curmatch)

+

+;_longest_match:

+IFDEF NOOLDPENTIUMCODE

+    IFDEF NOUNDERLINE

+    longest_match       proc near

+    ELSE

+    _longest_match      proc near

+    ENDIF

+ELSE

+    IFDEF NOUNDERLINE

+    longest_match_686   proc near

+    ELSE

+    _longest_match_686  proc near

+    ENDIF

+ENDIF

+

+;;; Save registers that the compiler may be using, and adjust esp to

+;;; make room for our stack frame.

+

+        push    ebp

+        push    edi

+        push    esi

+        push    ebx

+        sub esp, LocalVarsSize

+

+;;; Retrieve the function arguments. ecx will hold cur_match

+;;; throughout the entire function. edx will hold the pointer to the

+;;; deflate_state structure during the function's setup (before

+;;; entering the main loop.

+

+        mov edx, [deflatestate]

+        mov ecx, [curmatch]

+

+;;; uInt wmask = s->w_mask;

+;;; unsigned chain_length = s->max_chain_length;

+;;; if (s->prev_length >= s->good_match) {

+;;;     chain_length >>= 2;

+;;; }

+

+        mov eax, [edx + dsPrevLen]

+        mov ebx, [edx + dsGoodMatch]

+        cmp eax, ebx

+        mov eax, [edx + dsWMask]

+        mov ebx, [edx + dsMaxChainLen]

+        jl  LastMatchGood

+        shr ebx, 2

+LastMatchGood:

+

+;;; chainlen is decremented once beforehand so that the function can

+;;; use the sign flag instead of the zero flag for the exit test.

+;;; It is then shifted into the high word, to make room for the wmask

+;;; value, which it will always accompany.

+

+        dec ebx

+        shl ebx, 16

+        or  ebx, eax

+        mov [chainlenwmask], ebx

+

+;;; if ((uInt)nice_match > s->lookahead) nice_match = s->lookahead;

+

+        mov eax, [edx + dsNiceMatch]

+        mov ebx, [edx + dsLookahead]

+        cmp ebx, eax

+        jl  LookaheadLess

+        mov ebx, eax

+LookaheadLess:  mov [nicematch], ebx

+

+;;; register Bytef *scan = s->window + s->strstart;

+

+        mov esi, [edx + dsWindow]

+        mov [window], esi

+        mov ebp, [edx + dsStrStart]

+        lea edi, [esi + ebp]

+        mov [scan], edi

+

+;;; Determine how many bytes the scan ptr is off from being

+;;; dword-aligned.

+

+        mov eax, edi

+        neg eax

+        and eax, 3

+        mov [scanalign], eax

+

+;;; IPos limit = s->strstart > (IPos)MAX_DIST(s) ?

+;;;     s->strstart - (IPos)MAX_DIST(s) : NIL;

+

+        mov eax, [edx + dsWSize]

+        sub eax, MIN_LOOKAHEAD

+        sub ebp, eax

+        jg  LimitPositive

+        xor ebp, ebp

+LimitPositive:

+

+;;; int best_len = s->prev_length;

+

+        mov eax, [edx + dsPrevLen]

+        mov [bestlen], eax

+

+;;; Store the sum of s->window + best_len in esi locally, and in esi.

+

+        add esi, eax

+        mov [windowbestlen], esi

+

+;;; register ush scan_start = *(ushf*)scan;

+;;; register ush scan_end   = *(ushf*)(scan+best_len-1);

+;;; Posf *prev = s->prev;

+

+        movzx   ebx, word ptr [edi]

+        mov [scanstart], ebx

+        movzx   ebx, word ptr [edi + eax - 1]

+        mov [scanend], ebx

+        mov edi, [edx + dsPrev]

+

+;;; Jump into the main loop.

+

+        mov edx, [chainlenwmask]

+        jmp short LoopEntry

+

+align 4

+

+;;; do {

+;;;     match = s->window + cur_match;

+;;;     if (*(ushf*)(match+best_len-1) != scan_end ||

+;;;         *(ushf*)match != scan_start) continue;

+;;;     [...]

+;;; } while ((cur_match = prev[cur_match & wmask]) > limit

+;;;          && --chain_length != 0);

+;;;

+;;; Here is the inner loop of the function. The function will spend the

+;;; majority of its time in this loop, and majority of that time will

+;;; be spent in the first ten instructions.

+;;;

+;;; Within this loop:

+;;; ebx = scanend

+;;; ecx = curmatch

+;;; edx = chainlenwmask - i.e., ((chainlen << 16) | wmask)

+;;; esi = windowbestlen - i.e., (window + bestlen)

+;;; edi = prev

+;;; ebp = limit

+

+LookupLoop:

+        and ecx, edx

+        movzx   ecx, word ptr [edi + ecx*2]

+        cmp ecx, ebp

+        jbe LeaveNow

+        sub edx, 00010000h

+        js  LeaveNow

+LoopEntry:  movzx   eax, word ptr [esi + ecx - 1]

+        cmp eax, ebx

+        jnz LookupLoop

+        mov eax, [window]

+        movzx   eax, word ptr [eax + ecx]

+        cmp eax, [scanstart]

+        jnz LookupLoop

+

+;;; Store the current value of chainlen.

+

+        mov [chainlenwmask], edx

+

+;;; Point edi to the string under scrutiny, and esi to the string we

+;;; are hoping to match it up with. In actuality, esi and edi are

+;;; both pointed (MAX_MATCH_8 - scanalign) bytes ahead, and edx is

+;;; initialized to -(MAX_MATCH_8 - scanalign).

+

+        mov esi, [window]

+        mov edi, [scan]

+        add esi, ecx

+        mov eax, [scanalign]

+        mov edx, 0fffffef8h; -(MAX_MATCH_8)

+        lea edi, [edi + eax + 0108h] ;MAX_MATCH_8]

+        lea esi, [esi + eax + 0108h] ;MAX_MATCH_8]

+

+;;; Test the strings for equality, 8 bytes at a time. At the end,

+;;; adjust edx so that it is offset to the exact byte that mismatched.

+;;;

+;;; We already know at this point that the first three bytes of the

+;;; strings match each other, and they can be safely passed over before

+;;; starting the compare loop. So what this code does is skip over 0-3

+;;; bytes, as much as necessary in order to dword-align the edi

+;;; pointer. (esi will still be misaligned three times out of four.)

+;;;

+;;; It should be confessed that this loop usually does not represent

+;;; much of the total running time. Replacing it with a more

+;;; straightforward "rep cmpsb" would not drastically degrade

+;;; performance.

+

+LoopCmps:

+        mov eax, [esi + edx]

+        xor eax, [edi + edx]

+        jnz LeaveLoopCmps

+        mov eax, [esi + edx + 4]

+        xor eax, [edi + edx + 4]

+        jnz LeaveLoopCmps4

+        add edx, 8

+        jnz LoopCmps

+        jmp short LenMaximum

+LeaveLoopCmps4: add edx, 4

+LeaveLoopCmps:  test    eax, 0000FFFFh

+        jnz LenLower

+        add edx,  2

+        shr eax, 16

+LenLower:   sub al, 1

+        adc edx, 0

+

+;;; Calculate the length of the match. If it is longer than MAX_MATCH,

+;;; then automatically accept it as the best possible match and leave.

+

+        lea eax, [edi + edx]

+        mov edi, [scan]

+        sub eax, edi

+        cmp eax, MAX_MATCH

+        jge LenMaximum

+

+;;; If the length of the match is not longer than the best match we

+;;; have so far, then forget it and return to the lookup loop.

+

+        mov edx, [deflatestate]

+        mov ebx, [bestlen]

+        cmp eax, ebx

+        jg  LongerMatch

+        mov esi, [windowbestlen]

+        mov edi, [edx + dsPrev]

+        mov ebx, [scanend]

+        mov edx, [chainlenwmask]

+        jmp LookupLoop

+

+;;;         s->match_start = cur_match;

+;;;         best_len = len;

+;;;         if (len >= nice_match) break;

+;;;         scan_end = *(ushf*)(scan+best_len-1);

+

+LongerMatch:    mov ebx, [nicematch]

+        mov [bestlen], eax

+        mov [edx + dsMatchStart], ecx

+        cmp eax, ebx

+        jge LeaveNow

+        mov esi, [window]

+        add esi, eax

+        mov [windowbestlen], esi

+        movzx   ebx, word ptr [edi + eax - 1]

+        mov edi, [edx + dsPrev]

+        mov [scanend], ebx

+        mov edx, [chainlenwmask]

+        jmp LookupLoop

+

+;;; Accept the current string, with the maximum possible length.

+

+LenMaximum: mov edx, [deflatestate]

+        mov dword ptr [bestlen], MAX_MATCH

+        mov [edx + dsMatchStart], ecx

+

+;;; if ((uInt)best_len <= s->lookahead) return (uInt)best_len;

+;;; return s->lookahead;

+

+LeaveNow:

+        mov edx, [deflatestate]

+        mov ebx, [bestlen]

+        mov eax, [edx + dsLookahead]

+        cmp ebx, eax

+        jg  LookaheadRet

+        mov eax, ebx

+LookaheadRet:

+

+;;; Restore the stack and return from whence we came.

+

+        add esp, LocalVarsSize

+        pop ebx

+        pop esi

+        pop edi

+        pop ebp

+

+        ret

+; please don't remove this string !

+; Your can freely use gvmat32 in any free or commercial app if you don't remove the string in the binary!

+    db     0dh,0ah,"asm686 with masm, optimised assembly code from Brian Raiter, written 1998",0dh,0ah

+

+

+IFDEF NOOLDPENTIUMCODE

+    IFDEF NOUNDERLINE

+    longest_match       endp

+    ELSE

+    _longest_match      endp

+    ENDIF

+

+    IFDEF NOUNDERLINE

+    match_init      proc near

+                    ret

+    match_init      endp

+    ELSE

+    _match_init     proc near

+                    ret

+    _match_init     endp

+    ENDIF    

+ELSE

+    IFDEF NOUNDERLINE

+    longest_match_686   endp

+    ELSE

+    _longest_match_686  endp

+    ENDIF

+ENDIF

+

+_TEXT   ends

+end

diff --git a/zlib/contrib/masmx86/gvmat32c.c b/zlib/contrib/masmx86/gvmat32c.c
index 9ed25f3432f..7ad2b27943b 100644
--- a/zlib/contrib/masmx86/gvmat32c.c
+++ b/zlib/contrib/masmx86/gvmat32c.c
@@ -1,206 +1,62 @@
-/* gvmat32.c -- C portion of the optimized longest_match for 32 bits x86
- * Copyright (C) 1995-1996 Jean-loup Gailly and Gilles Vollant.
- * File written by Gilles Vollant, by modifiying the longest_match
- *  from Jean-loup Gailly in deflate.c
- *  it prepare all parameters and call the assembly longest_match_gvasm
- *  longest_match execute standard C code is wmask != 0x7fff
- *     (assembly code is faster with a fixed wmask)
- *
- */
-
-#include "deflate.h"
-
-#ifdef ASMV
-#define NIL 0
-
-#define UNALIGNED_OK
-
-
-/* if your C compiler don't add underline before function name,
-        define ADD_UNDERLINE_ASMFUNC */
-#ifdef ADD_UNDERLINE_ASMFUNC
-#define longest_match_7fff _longest_match_7fff
-#define longest_match_686  _longest_match_686
-#define cpudetect32        _cpudetect32
-#endif
-
-
-
-void match_init()
-{
-}
-
-unsigned long cpudetect32();
-
-uInt longest_match_c(
-    deflate_state *s,
-    IPos cur_match);                             /* current match */
-
-
-uInt longest_match_7fff(
-    deflate_state *s,
-    IPos cur_match);                             /* current match */
-
-uInt longest_match_686(
-    deflate_state *s,
-    IPos cur_match);                             /* current match */
-
-uInt longest_match(
-    deflate_state *s,
-    IPos cur_match)                             /* current match */
-{
-    static uInt iIsPPro=2;
-
-    if ((s->w_mask == 0x7fff) && (iIsPPro==0))
-        return longest_match_7fff(s,cur_match);
-
-    if (iIsPPro==1)
-        return longest_match_686(s,cur_match);
-
-    if (iIsPPro==2)
-        iIsPPro = (((cpudetect32()/0x100)&0xf)>=6) ? 1 : 0;
-
-    return longest_match_c(s,cur_match);
-}
-
-
-
-uInt longest_match_c(s, cur_match)
-    deflate_state *s;
-    IPos cur_match;                             /* current match */
-{
-    unsigned chain_length = s->max_chain_length;/* max hash chain length */
-    register Bytef *scan = s->window + s->strstart; /* current string */
-    register Bytef *match;                       /* matched string */
-    register int len;                           /* length of current match */
-    int best_len = s->prev_length;              /* best match length so far */
-    int nice_match = s->nice_match;             /* stop if match long enough */
-    IPos limit = s->strstart > (IPos)MAX_DIST(s) ?
-        s->strstart - (IPos)MAX_DIST(s) : NIL;
-    /* Stop when cur_match becomes <= limit. To simplify the code,
-     * we prevent matches with the string of window index 0.
-     */
-    Posf *prev = s->prev;
-    uInt wmask = s->w_mask;
-
-#ifdef UNALIGNED_OK
-    /* Compare two bytes at a time. Note: this is not always beneficial.
-     * Try with and without -DUNALIGNED_OK to check.
-     */
-    register Bytef *strend = s->window + s->strstart + MAX_MATCH - 1;
-    register ush scan_start = *(ushf*)scan;
-    register ush scan_end   = *(ushf*)(scan+best_len-1);
-#else
-    register Bytef *strend = s->window + s->strstart + MAX_MATCH;
-    register Byte scan_end1  = scan[best_len-1];
-    register Byte scan_end   = scan[best_len];
-#endif
-
-    /* The code is optimized for HASH_BITS >= 8 and MAX_MATCH-2 multiple of 16.
-     * It is easy to get rid of this optimization if necessary.
-     */
-    Assert(s->hash_bits >= 8 && MAX_MATCH == 258, "Code too clever");
-
-    /* Do not waste too much time if we already have a good match: */
-    if (s->prev_length >= s->good_match) {
-        chain_length >>= 2;
-    }
-    /* Do not look for matches beyond the end of the input. This is necessary
-     * to make deflate deterministic.
-     */
-    if ((uInt)nice_match > s->lookahead) nice_match = s->lookahead;
-
-    Assert((ulg)s->strstart <= s->window_size-MIN_LOOKAHEAD, "need lookahead");
-
-    do {
-        Assert(cur_match < s->strstart, "no future");
-        match = s->window + cur_match;
-
-        /* Skip to next match if the match length cannot increase
-         * or if the match length is less than 2:
-         */
-#if (defined(UNALIGNED_OK) && MAX_MATCH == 258)
-        /* This code assumes sizeof(unsigned short) == 2. Do not use
-         * UNALIGNED_OK if your compiler uses a different size.
-         */
-        if (*(ushf*)(match+best_len-1) != scan_end ||
-            *(ushf*)match != scan_start) continue;
-
-        /* It is not necessary to compare scan[2] and match[2] since they are
-         * always equal when the other bytes match, given that the hash keys
-         * are equal and that HASH_BITS >= 8. Compare 2 bytes at a time at
-         * strstart+3, +5, ... up to strstart+257. We check for insufficient
-         * lookahead only every 4th comparison; the 128th check will be made
-         * at strstart+257. If MAX_MATCH-2 is not a multiple of 8, it is
-         * necessary to put more guard bytes at the end of the window, or
-         * to check more often for insufficient lookahead.
-         */
-        Assert(scan[2] == match[2], "scan[2]?");
-        scan++, match++;
-        do {
-        } while (*(ushf*)(scan+=2) == *(ushf*)(match+=2) &&
-                 *(ushf*)(scan+=2) == *(ushf*)(match+=2) &&
-                 *(ushf*)(scan+=2) == *(ushf*)(match+=2) &&
-                 *(ushf*)(scan+=2) == *(ushf*)(match+=2) &&
-                 scan < strend);
-        /* The funny "do {}" generates better code on most compilers */
-
-        /* Here, scan <= window+strstart+257 */
-        Assert(scan <= s->window+(unsigned)(s->window_size-1), "wild scan");
-        if (*scan == *match) scan++;
-
-        len = (MAX_MATCH - 1) - (int)(strend-scan);
-        scan = strend - (MAX_MATCH-1);
-
-#else /* UNALIGNED_OK */
-
-        if (match[best_len]   != scan_end  ||
-            match[best_len-1] != scan_end1 ||
-            *match            != *scan     ||
-            *++match          != scan[1])      continue;
-
-        /* The check at best_len-1 can be removed because it will be made
-         * again later. (This heuristic is not always a win.)
-         * It is not necessary to compare scan[2] and match[2] since they
-         * are always equal when the other bytes match, given that
-         * the hash keys are equal and that HASH_BITS >= 8.
-         */
-        scan += 2, match++;
-        Assert(*scan == *match, "match[2]?");
-
-        /* We check for insufficient lookahead only every 8th comparison;
-         * the 256th check will be made at strstart+258.
-         */
-        do {
-        } while (*++scan == *++match && *++scan == *++match &&
-                 *++scan == *++match && *++scan == *++match &&
-                 *++scan == *++match && *++scan == *++match &&
-                 *++scan == *++match && *++scan == *++match &&
-                 scan < strend);
-
-        Assert(scan <= s->window+(unsigned)(s->window_size-1), "wild scan");
-
-        len = MAX_MATCH - (int)(strend - scan);
-        scan = strend - MAX_MATCH;
-
-#endif /* UNALIGNED_OK */
-
-        if (len > best_len) {
-            s->match_start = cur_match;
-            best_len = len;
-            if (len >= nice_match) break;
-#ifdef UNALIGNED_OK
-            scan_end = *(ushf*)(scan+best_len-1);
-#else
-            scan_end1  = scan[best_len-1];
-            scan_end   = scan[best_len];
-#endif
-        }
-    } while ((cur_match = prev[cur_match & wmask]) > limit
-             && --chain_length != 0);
-
-    if ((uInt)best_len <= s->lookahead) return (uInt)best_len;
-    return s->lookahead;
-}
-
-#endif /* ASMV */
+/* gvmat32.c -- C portion of the optimized longest_match for 32 bits x86

+ * Copyright (C) 1995-1996 Jean-loup Gailly and Gilles Vollant.

+ * File written by Gilles Vollant, by modifiying the longest_match

+ *  from Jean-loup Gailly in deflate.c

+ *  it prepare all parameters and call the assembly longest_match_gvasm

+ *  longest_match execute standard C code is wmask != 0x7fff

+ *     (assembly code is faster with a fixed wmask)

+ *

+ * Read comment at beginning of gvmat32.asm for more information

+ */

+

+#if defined(ASMV) && (!defined(NOOLDPENTIUMCODE))

+#include "deflate.h"

+

+/* if your C compiler don't add underline before function name,

+        define ADD_UNDERLINE_ASMFUNC */

+#ifdef ADD_UNDERLINE_ASMFUNC

+#define longest_match_7fff _longest_match_7fff

+#define longest_match_686  _longest_match_686

+#define cpudetect32        _cpudetect32

+#endif

+

+

+unsigned long cpudetect32();

+

+uInt longest_match_c(

+    deflate_state *s,

+    IPos cur_match);                             /* current match */

+

+

+uInt longest_match_7fff(

+    deflate_state *s,

+    IPos cur_match);                             /* current match */

+

+uInt longest_match_686(

+    deflate_state *s,

+    IPos cur_match);                             /* current match */

+

+

+static uInt iIsPPro=2;

+

+void match_init ()

+{

+    iIsPPro = (((cpudetect32()/0x100)&0xf)>=6) ? 1 : 0;

+}

+

+uInt longest_match(

+    deflate_state *s,

+    IPos cur_match)                             /* current match */

+{

+    if (iIsPPro!=0)

+        return longest_match_686(s,cur_match);

+

+    if (s->w_mask != 0x7fff)

+        return longest_match_686(s,cur_match);

+

+    /* now ((s->w_mask == 0x7fff) && (iIsPPro==0)) */

+        return longest_match_7fff(s,cur_match);

+}

+

+

+#endif /* defined(ASMV) && (!defined(NOOLDPENTIUMCODE)) */

diff --git a/zlib/contrib/masmx86/inffas32.asm b/zlib/contrib/masmx86/inffas32.asm
index 7d76e1c6600..4a205125ec5 100644
--- a/zlib/contrib/masmx86/inffas32.asm
+++ b/zlib/contrib/masmx86/inffas32.asm
@@ -1,1033 +1,1083 @@
-; 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	;/* state->wsize */
-write_state	 equ	(36+4)	;/* state->write */
-window_state	 equ	(40+4)	;/* state->window */
-hold_state	 equ	(44+4)	;/* state->hold	*/
-bits_state	 equ	(48+4)	;/* state->bits	*/
-lencode_state	 equ	(64+4)	;/* state->lencode */
-distcode_state	 equ	(68+4)	;/* state->distcode */
-lenbits_state	 equ	(72+4)	;/* state->lenbits */
-distbits_state	 equ	(76+4)	;/* 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
-	mov  edx, [esp+12]
-	mov  eax, [edx+eax*4]
-	jmp  L_dodist
-
-ALIGN 4
-L_clip_window:
-; 721 "inffast.S"
-	mov  ecx,eax
-	mov  eax, [esp+52]
-	neg  ecx
-	mov  esi, [esp+56]
-
-	cmp  eax,edx
-	jb   L_invalid_distance_too_far
-
-	add  ecx,edx
-	cmp  dword ptr [esp+48],0
-	jne  L_wrap_around_window
-
-	sub  eax,ecx
-	add  esi,eax
-; 749 "inffast.S"
-	mov  eax, [esp+24]
-	cmp  eax,ecx
-	jbe  L_do_copy1
-
-	sub  eax,ecx
-	rep movsb
-	mov  esi,edi
-	sub  esi,edx
-	jmp  L_do_copy1
-
-	cmp  eax,ecx
-	jbe  L_do_copy1
-
-	sub  eax,ecx
-	rep movsb
-	mov  esi,edi
-	sub  esi,edx
-	jmp  L_do_copy1
-
-L_wrap_around_window:
-; 793 "inffast.S"
-	mov  eax, [esp+48]
-	cmp  ecx,eax
-	jbe  L_contiguous_in_window
-
-	add  esi, [esp+52]
-	add  esi,eax
-	sub  esi,ecx
-	sub  ecx,eax
-
-
-	mov  eax, [esp+24]
-	cmp  eax,ecx
-	jbe  L_do_copy1
-
-	sub  eax,ecx
-	rep movsb
-	mov  esi, [esp+56]
-	mov  ecx, [esp+48]
-	cmp  eax,ecx
-	jbe  L_do_copy1
-
-	sub  eax,ecx
-	rep movsb
-	mov  esi,edi
-	sub  esi,edx
-	jmp  L_do_copy1
-
-L_contiguous_in_window:
-; 836 "inffast.S"
-	add  esi,eax
-	sub  esi,ecx
-
-
-	mov  eax, [esp+24]
-	cmp  eax,ecx
-	jbe  L_do_copy1
-
-	sub  eax,ecx
-	rep movsb
-	mov  esi,edi
-	sub  esi,edx
-
-L_do_copy1:
-; 862 "inffast.S"
-	mov  ecx,eax
-	rep movsb
-
-	mov  esi, [esp+44]
-	jmp  L_while_test
-; 878 "inffast.S"
-ALIGN 4
-L_init_mmx:
-	emms
-
-
-
-
-
-	movd mm0,ebp
-	mov  ebp,ebx
-; 896 "inffast.S"
-	movd mm4,[esp+0]
-	movq mm3,mm4
-	movd mm5,[esp+4]
-	movq mm2,mm5
-	pxor mm1,mm1
-	mov  ebx, [esp+8]
-	jmp  L_do_loop_mmx
-
-ALIGN 4
-L_do_loop_mmx:
-	psrlq mm0,mm1
-
-	cmp  ebp,32
-	ja  L_get_length_code_mmx
-
-	movd mm6,ebp
-	movd mm7,[esi]
-	add  esi,4
-	psllq mm7,mm6
-	add  ebp,32
-	por mm0,mm7
-
-L_get_length_code_mmx:
-	pand mm4,mm0
-	movd eax,mm4
-	movq mm4,mm3
-	mov  eax, [ebx+eax*4]
-
-L_dolen_mmx:
-	movzx  ecx,ah
-	movd mm1,ecx
-	sub  ebp,ecx
-
-	test  al,al
-	jnz L_test_for_length_base_mmx
-
-	shr  eax,16
-	stosb
-
-L_while_test_mmx:
-
-
-	cmp  [esp+16],edi
-	jbe L_break_loop
-
-	cmp  [esp+20],esi
-	ja L_do_loop_mmx
-	jmp L_break_loop
-
-L_test_for_length_base_mmx:
-
-	mov  edx,eax
-	shr  edx,16
-
-	test  al,16
-	jz  L_test_for_second_level_length_mmx
-	and  eax,15
-	jz L_decode_distance_mmx
-
-	psrlq mm0,mm1
-	movd mm1,eax
-	movd ecx,mm0
-	sub  ebp,eax
-	and  ecx, [inflate_fast_mask+eax*4]
-	add  edx,ecx
-
-L_decode_distance_mmx:
-	psrlq mm0,mm1
-
-	cmp  ebp,32
-	ja L_get_dist_code_mmx
-
-	movd mm6,ebp
-	movd mm7,[esi]
-	add  esi,4
-	psllq mm7,mm6
-	add  ebp,32
-	por mm0,mm7
-
-L_get_dist_code_mmx:
-	mov  ebx, [esp+12]
-	pand mm5,mm0
-	movd eax,mm5
-	movq mm5,mm2
-	mov  eax, [ebx+eax*4]
-
-L_dodist_mmx:
-
-	movzx  ecx,ah
-	mov  ebx,eax
-	shr  ebx,16
-	sub  ebp,ecx
-	movd mm1,ecx
-
-	test  al,16
-	jz L_test_for_second_level_dist_mmx
-	and  eax,15
-	jz L_check_dist_one_mmx
-
-L_add_bits_to_dist_mmx:
-	psrlq mm0,mm1
-	movd mm1,eax
-	movd ecx,mm0
-	sub  ebp,eax
-	and  ecx, [inflate_fast_mask+eax*4]
-	add  ebx,ecx
-
-L_check_window_mmx:
-	mov  [esp+44],esi
-	mov  eax,edi
-	sub  eax, [esp+40]
-
-	cmp  eax,ebx
-	jb L_clip_window_mmx
-
-	mov  ecx,edx
-	mov  esi,edi
-	sub  esi,ebx
-
-	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]
-	mov  ebx, [esp+8]
-	jmp  L_while_test_mmx
-
-ALIGN 4
-L_check_dist_one_mmx:
-	cmp  ebx,1
-	jne  L_check_window_mmx
-	cmp  [esp+40],edi
-	je   L_check_window_mmx
-
-	dec  edi
-	mov  ecx,edx
-	mov  al, [edi]
-	sub  ecx,3
-
-	mov  [edi+1],al
-	mov  [edi+2],al
-	mov  [edi+3],al
-	add  edi,4
-	rep stosb
-
-	mov  ebx, [esp+8]
-	jmp  L_while_test_mmx
-
-ALIGN 4
-L_test_for_second_level_length_mmx:
-	test  al,64
-	jnz L_test_for_end_of_block
-
-	and  eax,15
-	psrlq mm0,mm1
-	movd ecx,mm0
-	and  ecx, [inflate_fast_mask+eax*4]
-	add  ecx,edx
-	mov  eax, [ebx+ecx*4]
-	jmp L_dolen_mmx
-
-ALIGN 4
-L_test_for_second_level_dist_mmx:
-	test  al,64
-	jnz L_invalid_distance_code
-
-	and  eax,15
-	psrlq mm0,mm1
-	movd ecx,mm0
-	and  ecx, [inflate_fast_mask+eax*4]
-	mov  eax, [esp+12]
-	add  ecx,ebx
-	mov  eax, [eax+ecx*4]
-	jmp  L_dodist_mmx
-
-ALIGN 4
-L_clip_window_mmx:
-
-	mov  ecx,eax
-	mov  eax, [esp+52]
-	neg  ecx
-	mov  esi, [esp+56]
-
-	cmp  eax,ebx
-	jb  L_invalid_distance_too_far
-
-	add  ecx,ebx
-	cmp  dword ptr [esp+48],0
-	jne  L_wrap_around_window_mmx
-
-	sub  eax,ecx
-	add  esi,eax
-
-	cmp  edx,ecx
-	jbe  L_do_copy1_mmx
-
-	sub  edx,ecx
-	rep movsb
-	mov  esi,edi
-	sub  esi,ebx
-	jmp  L_do_copy1_mmx
-
-	cmp  edx,ecx
-	jbe  L_do_copy1_mmx
-
-	sub  edx,ecx
-	rep movsb
-	mov  esi,edi
-	sub  esi,ebx
-	jmp  L_do_copy1_mmx
-
-L_wrap_around_window_mmx:
-
-	mov  eax, [esp+48]
-	cmp  ecx,eax
-	jbe  L_contiguous_in_window_mmx
-
-	add  esi, [esp+52]
-	add  esi,eax
-	sub  esi,ecx
-	sub  ecx,eax
-
-
-	cmp  edx,ecx
-	jbe  L_do_copy1_mmx
-
-	sub  edx,ecx
-	rep movsb
-	mov  esi, [esp+56]
-	mov  ecx, [esp+48]
-	cmp  edx,ecx
-	jbe  L_do_copy1_mmx
-
-	sub  edx,ecx
-	rep movsb
-	mov  esi,edi
-	sub  esi,ebx
-	jmp  L_do_copy1_mmx
-
-L_contiguous_in_window_mmx:
-
-	add  esi,eax
-	sub  esi,ecx
-
-
-	cmp  edx,ecx
-	jbe  L_do_copy1_mmx
-
-	sub  edx,ecx
-	rep movsb
-	mov  esi,edi
-	sub  esi,ebx
-
-L_do_copy1_mmx:
-
-
-	mov  ecx,edx
-	rep movsb
-
-	mov  esi, [esp+44]
-	mov  ebx, [esp+8]
-	jmp  L_while_test_mmx
-; 1174 "inffast.S"
-L_invalid_distance_code:
-
-
-
-
-
-	mov  ecx, invalid_distance_code_msg
-	mov  edx,26
-	jmp  L_update_stream_state
-
-L_test_for_end_of_block:
-
-
-
-
-
-	test  al,32
-	jz  L_invalid_literal_length_code
-
-	mov  ecx,0
-	mov  edx,11
-	jmp  L_update_stream_state
-
-L_invalid_literal_length_code:
-
-
-
-
-
-	mov  ecx, invalid_literal_length_code_msg
-	mov  edx,26
-	jmp  L_update_stream_state
-
-L_invalid_distance_too_far:
-
-
-
-	mov  esi, [esp+44]
-	mov  ecx, invalid_distance_too_far_msg
-	mov  edx,26
-	jmp  L_update_stream_state
-
-L_update_stream_state:
-
-	mov  eax, [esp+88]
-	test  ecx,ecx
-	jz  L_skip_msg
-	mov  [eax+24],ecx
-L_skip_msg:
-	mov  eax, [eax+28]
-	mov  [eax+mode_state],edx
-	jmp  L_break_loop
-
-ALIGN 4
-L_break_loop:
-; 1243 "inffast.S"
-	cmp  dword ptr [inflate_fast_use_mmx],2
-	jne  L_update_next_in
-
-
-
-	mov  ebx,ebp
-
-L_update_next_in:
-; 1266 "inffast.S"
-	mov  eax, [esp+88]
-	mov  ecx,ebx
-	mov  edx, [eax+28]
-	shr  ecx,3
-	sub  esi,ecx
-	shl  ecx,3
-	sub  ebx,ecx
-	mov  [eax+12],edi
-	mov  [edx+bits_state],ebx
-	mov  ecx,ebx
-
-	lea  ebx, [esp+28]
-	cmp  [esp+20],ebx
-	jne  L_buf_not_used
-
-	sub  esi,ebx
-	mov  ebx, [eax+0]
-	mov  [esp+20],ebx
-	add  esi,ebx
-	mov  ebx, [eax+4]
-	sub  ebx,11
-	add  [esp+20],ebx
-
-L_buf_not_used:
-	mov  [eax+0],esi
-
-	mov  ebx,1
-	shl  ebx,cl
-	dec  ebx
-
-
-
-
-
-	cmp  dword ptr [inflate_fast_use_mmx],2
-	jne  L_update_hold
-
-
-
-	psrlq mm0,mm1
-	movd ebp,mm0
-
-	emms
-
-L_update_hold:
-
-
-
-	and  ebp,ebx
-	mov  [edx+hold_state],ebp
-
-
-
-
-	mov  ebx, [esp+20]
-	cmp  ebx,esi
-	jbe  L_last_is_smaller
-
-	sub  ebx,esi
-	add  ebx,11
-	mov  [eax+4],ebx
-	jmp  L_fixup_out
-L_last_is_smaller:
-	sub  esi,ebx
-	neg  esi
-	add  esi,11
-	mov  [eax+4],esi
-
-
-
-
-L_fixup_out:
-
-	mov  ebx, [esp+16]
-	cmp  ebx,edi
-	jbe  L_end_is_smaller
-
-	sub  ebx,edi
-	add  ebx,257
-	mov  [eax+16],ebx
-	jmp  L_done
-L_end_is_smaller:
-	sub  edi,ebx
-	neg  edi
-	add  edi,257
-	mov  [eax+16],edi
-
-
-
-
-
-L_done:
-	add  esp,64
-	popfd
-	pop  ebx
-	pop  ebp
-	pop  esi
-	pop  edi
-	ret
-
-
-
-
-_TEXT	ends
-end
+;/* 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 <christop@charm.net>

+; * 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

+	mov  edx, [esp+12]

+	mov  eax, [edx+eax*4]

+	jmp  L_dodist

+

+ALIGN 4

+L_clip_window:

+; 721 "inffast.S"

+	mov  ecx,eax

+	mov  eax, [esp+52]

+	neg  ecx

+	mov  esi, [esp+56]

+

+	cmp  eax,edx

+	jb   L_invalid_distance_too_far

+

+	add  ecx,edx

+	cmp  dword ptr [esp+48],0

+	jne  L_wrap_around_window

+

+	sub  eax,ecx

+	add  esi,eax

+; 749 "inffast.S"

+	mov  eax, [esp+24]

+	cmp  eax,ecx

+	jbe  L_do_copy1

+

+	sub  eax,ecx

+	rep movsb

+	mov  esi,edi

+	sub  esi,edx

+	jmp  L_do_copy1

+

+	cmp  eax,ecx

+	jbe  L_do_copy1

+

+	sub  eax,ecx

+	rep movsb

+	mov  esi,edi

+	sub  esi,edx

+	jmp  L_do_copy1

+

+L_wrap_around_window:

+; 793 "inffast.S"

+	mov  eax, [esp+48]

+	cmp  ecx,eax

+	jbe  L_contiguous_in_window

+

+	add  esi, [esp+52]

+	add  esi,eax

+	sub  esi,ecx

+	sub  ecx,eax

+

+

+	mov  eax, [esp+24]

+	cmp  eax,ecx

+	jbe  L_do_copy1

+

+	sub  eax,ecx

+	rep movsb

+	mov  esi, [esp+56]

+	mov  ecx, [esp+48]

+	cmp  eax,ecx

+	jbe  L_do_copy1

+

+	sub  eax,ecx

+	rep movsb

+	mov  esi,edi

+	sub  esi,edx

+	jmp  L_do_copy1

+

+L_contiguous_in_window:

+; 836 "inffast.S"

+	add  esi,eax

+	sub  esi,ecx

+

+

+	mov  eax, [esp+24]

+	cmp  eax,ecx

+	jbe  L_do_copy1

+

+	sub  eax,ecx

+	rep movsb

+	mov  esi,edi

+	sub  esi,edx

+

+L_do_copy1:

+; 862 "inffast.S"

+	mov  ecx,eax

+	rep movsb

+

+	mov  esi, [esp+44]

+	jmp  L_while_test

+; 878 "inffast.S"

+ALIGN 4

+L_init_mmx:

+	emms

+

+

+

+

+

+	movd mm0,ebp

+	mov  ebp,ebx

+; 896 "inffast.S"

+	movd mm4,[esp+0]

+	movq mm3,mm4

+	movd mm5,[esp+4]

+	movq mm2,mm5

+	pxor mm1,mm1

+	mov  ebx, [esp+8]

+	jmp  L_do_loop_mmx

+

+ALIGN 4

+L_do_loop_mmx:

+	psrlq mm0,mm1

+

+	cmp  ebp,32

+	ja  L_get_length_code_mmx

+

+	movd mm6,ebp

+	movd mm7,[esi]

+	add  esi,4

+	psllq mm7,mm6

+	add  ebp,32

+	por mm0,mm7

+

+L_get_length_code_mmx:

+	pand mm4,mm0

+	movd eax,mm4

+	movq mm4,mm3

+	mov  eax, [ebx+eax*4]

+

+L_dolen_mmx:

+	movzx  ecx,ah

+	movd mm1,ecx

+	sub  ebp,ecx

+

+	test  al,al

+	jnz L_test_for_length_base_mmx

+

+	shr  eax,16

+	stosb

+

+L_while_test_mmx:

+

+

+	cmp  [esp+16],edi

+	jbe L_break_loop

+

+	cmp  [esp+20],esi

+	ja L_do_loop_mmx

+	jmp L_break_loop

+

+L_test_for_length_base_mmx:

+

+	mov  edx,eax

+	shr  edx,16

+

+	test  al,16

+	jz  L_test_for_second_level_length_mmx

+	and  eax,15

+	jz L_decode_distance_mmx

+

+	psrlq mm0,mm1

+	movd mm1,eax

+	movd ecx,mm0

+	sub  ebp,eax

+	and  ecx, [inflate_fast_mask+eax*4]

+	add  edx,ecx

+

+L_decode_distance_mmx:

+	psrlq mm0,mm1

+

+	cmp  ebp,32

+	ja L_get_dist_code_mmx

+

+	movd mm6,ebp

+	movd mm7,[esi]

+	add  esi,4

+	psllq mm7,mm6

+	add  ebp,32

+	por mm0,mm7

+

+L_get_dist_code_mmx:

+	mov  ebx, [esp+12]

+	pand mm5,mm0

+	movd eax,mm5

+	movq mm5,mm2

+	mov  eax, [ebx+eax*4]

+

+L_dodist_mmx:

+

+	movzx  ecx,ah

+	mov  ebx,eax

+	shr  ebx,16

+	sub  ebp,ecx

+	movd mm1,ecx

+

+	test  al,16

+	jz L_test_for_second_level_dist_mmx

+	and  eax,15

+	jz L_check_dist_one_mmx

+

+L_add_bits_to_dist_mmx:

+	psrlq mm0,mm1

+	movd mm1,eax

+	movd ecx,mm0

+	sub  ebp,eax

+	and  ecx, [inflate_fast_mask+eax*4]

+	add  ebx,ecx

+

+L_check_window_mmx:

+	mov  [esp+44],esi

+	mov  eax,edi

+	sub  eax, [esp+40]

+

+	cmp  eax,ebx

+	jb L_clip_window_mmx

+

+	mov  ecx,edx

+	mov  esi,edi

+	sub  esi,ebx

+

+	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]

+	mov  ebx, [esp+8]

+	jmp  L_while_test_mmx

+

+ALIGN 4

+L_check_dist_one_mmx:

+	cmp  ebx,1

+	jne  L_check_window_mmx

+	cmp  [esp+40],edi

+	je   L_check_window_mmx

+

+	dec  edi

+	mov  ecx,edx

+	mov  al, [edi]

+	sub  ecx,3

+

+	mov  [edi+1],al

+	mov  [edi+2],al

+	mov  [edi+3],al

+	add  edi,4

+	rep stosb

+

+	mov  ebx, [esp+8]

+	jmp  L_while_test_mmx

+

+ALIGN 4

+L_test_for_second_level_length_mmx:

+	test  al,64

+	jnz L_test_for_end_of_block

+

+	and  eax,15

+	psrlq mm0,mm1

+	movd ecx,mm0

+	and  ecx, [inflate_fast_mask+eax*4]

+	add  ecx,edx

+	mov  eax, [ebx+ecx*4]

+	jmp L_dolen_mmx

+

+ALIGN 4

+L_test_for_second_level_dist_mmx:

+	test  al,64

+	jnz L_invalid_distance_code

+

+	and  eax,15

+	psrlq mm0,mm1

+	movd ecx,mm0

+	and  ecx, [inflate_fast_mask+eax*4]

+	mov  eax, [esp+12]

+	add  ecx,ebx

+	mov  eax, [eax+ecx*4]

+	jmp  L_dodist_mmx

+

+ALIGN 4

+L_clip_window_mmx:

+

+	mov  ecx,eax

+	mov  eax, [esp+52]

+	neg  ecx

+	mov  esi, [esp+56]

+

+	cmp  eax,ebx

+	jb  L_invalid_distance_too_far

+

+	add  ecx,ebx

+	cmp  dword ptr [esp+48],0

+	jne  L_wrap_around_window_mmx

+

+	sub  eax,ecx

+	add  esi,eax

+

+	cmp  edx,ecx

+	jbe  L_do_copy1_mmx

+

+	sub  edx,ecx

+	rep movsb

+	mov  esi,edi

+	sub  esi,ebx

+	jmp  L_do_copy1_mmx

+

+	cmp  edx,ecx

+	jbe  L_do_copy1_mmx

+

+	sub  edx,ecx

+	rep movsb

+	mov  esi,edi

+	sub  esi,ebx

+	jmp  L_do_copy1_mmx

+

+L_wrap_around_window_mmx:

+

+	mov  eax, [esp+48]

+	cmp  ecx,eax

+	jbe  L_contiguous_in_window_mmx

+

+	add  esi, [esp+52]

+	add  esi,eax

+	sub  esi,ecx

+	sub  ecx,eax

+

+

+	cmp  edx,ecx

+	jbe  L_do_copy1_mmx

+

+	sub  edx,ecx

+	rep movsb

+	mov  esi, [esp+56]

+	mov  ecx, [esp+48]

+	cmp  edx,ecx

+	jbe  L_do_copy1_mmx

+

+	sub  edx,ecx

+	rep movsb

+	mov  esi,edi

+	sub  esi,ebx

+	jmp  L_do_copy1_mmx

+

+L_contiguous_in_window_mmx:

+

+	add  esi,eax

+	sub  esi,ecx

+

+

+	cmp  edx,ecx

+	jbe  L_do_copy1_mmx

+

+	sub  edx,ecx

+	rep movsb

+	mov  esi,edi

+	sub  esi,ebx

+

+L_do_copy1_mmx:

+

+

+	mov  ecx,edx

+	rep movsb

+

+	mov  esi, [esp+44]

+	mov  ebx, [esp+8]

+	jmp  L_while_test_mmx

+; 1174 "inffast.S"

+L_invalid_distance_code:

+

+

+

+

+

+	mov  ecx, invalid_distance_code_msg

+	mov  edx,INFLATE_MODE_BAD

+	jmp  L_update_stream_state

+

+L_test_for_end_of_block:

+

+

+

+

+

+	test  al,32

+	jz  L_invalid_literal_length_code

+

+	mov  ecx,0

+	mov  edx,INFLATE_MODE_TYPE

+	jmp  L_update_stream_state

+

+L_invalid_literal_length_code:

+

+

+

+

+

+	mov  ecx, invalid_literal_length_code_msg

+	mov  edx,INFLATE_MODE_BAD

+	jmp  L_update_stream_state

+

+L_invalid_distance_too_far:

+

+

+

+	mov  esi, [esp+44]

+	mov  ecx, invalid_distance_too_far_msg

+	mov  edx,INFLATE_MODE_BAD

+	jmp  L_update_stream_state

+

+L_update_stream_state:

+

+	mov  eax, [esp+88]

+	test  ecx,ecx

+	jz  L_skip_msg

+	mov  [eax+24],ecx

+L_skip_msg:

+	mov  eax, [eax+28]

+	mov  [eax+mode_state],edx

+	jmp  L_break_loop

+

+ALIGN 4

+L_break_loop:

+; 1243 "inffast.S"

+	cmp  dword ptr [inflate_fast_use_mmx],2

+	jne  L_update_next_in

+

+

+

+	mov  ebx,ebp

+

+L_update_next_in:

+; 1266 "inffast.S"

+	mov  eax, [esp+88]

+	mov  ecx,ebx

+	mov  edx, [eax+28]

+	shr  ecx,3

+	sub  esi,ecx

+	shl  ecx,3

+	sub  ebx,ecx

+	mov  [eax+12],edi

+	mov  [edx+bits_state],ebx

+	mov  ecx,ebx

+

+	lea  ebx, [esp+28]

+	cmp  [esp+20],ebx

+	jne  L_buf_not_used

+

+	sub  esi,ebx

+	mov  ebx, [eax+0]

+	mov  [esp+20],ebx

+	add  esi,ebx

+	mov  ebx, [eax+4]

+	sub  ebx,11

+	add  [esp+20],ebx

+

+L_buf_not_used:

+	mov  [eax+0],esi

+

+	mov  ebx,1

+	shl  ebx,cl

+	dec  ebx

+

+

+

+

+

+	cmp  dword ptr [inflate_fast_use_mmx],2

+	jne  L_update_hold

+

+

+

+	psrlq mm0,mm1

+	movd ebp,mm0

+

+	emms

+

+L_update_hold:

+

+

+

+	and  ebp,ebx

+	mov  [edx+hold_state],ebp

+

+

+

+

+	mov  ebx, [esp+20]

+	cmp  ebx,esi

+	jbe  L_last_is_smaller

+

+	sub  ebx,esi

+	add  ebx,11

+	mov  [eax+4],ebx

+	jmp  L_fixup_out

+L_last_is_smaller:

+	sub  esi,ebx

+	neg  esi

+	add  esi,11

+	mov  [eax+4],esi

+

+

+

+

+L_fixup_out:

+

+	mov  ebx, [esp+16]

+	cmp  ebx,edi

+	jbe  L_end_is_smaller

+

+	sub  ebx,edi

+	add  ebx,257

+	mov  [eax+16],ebx

+	jmp  L_done

+L_end_is_smaller:

+	sub  edi,ebx

+	neg  edi

+	add  edi,257

+	mov  [eax+16],edi

+

+

+

+

+

+L_done:

+	add  esp,64

+	popfd

+	pop  ebx

+	pop  ebp

+	pop  esi

+	pop  edi

+	ret

+

+_TEXT	ends

+end

diff --git a/zlib/contrib/masmx86/mkasm.bat b/zlib/contrib/masmx86/mkasm.bat
index f3fa0a00f39..70a51f83777 100755
--- a/zlib/contrib/masmx86/mkasm.bat
+++ b/zlib/contrib/masmx86/mkasm.bat
@@ -1,3 +1,3 @@
-cl /I..\.. /O2 /c gvmat32c.c

+cl /DASMV /I..\.. /O2 /c gvmat32c.c

 ml /coff /Zi /c /Flgvmat32.lst gvmat32.asm

 ml /coff /Zi /c /Flinffas32.lst inffas32.asm

diff --git a/zlib/contrib/minizip/crypt.h b/zlib/contrib/minizip/crypt.h
index 9c7a89cbe82..622f4bc2ec4 100644
--- a/zlib/contrib/minizip/crypt.h
+++ b/zlib/contrib/minizip/crypt.h
@@ -1,9 +1,9 @@
 /* crypt.h -- base code for crypt/uncrypt ZIPfile
 
 
-   Version 1.00, September 10th, 2003
+   Version 1.01e, February 12th, 2005
 
-   Copyright (C) 1998-2003 Gilles Vollant
+   Copyright (C) 1998-2005 Gilles Vollant
 
    This code is a modified version of crypting code in Infozip distribution
 
diff --git a/zlib/contrib/minizip/ioapi.c b/zlib/contrib/minizip/ioapi.c
index 80443b761f3..f1bee23e64b 100644
--- a/zlib/contrib/minizip/ioapi.c
+++ b/zlib/contrib/minizip/ioapi.c
@@ -1,9 +1,9 @@
 /* ioapi.c -- IO base function header for compress/uncompress .zip
    files using zlib + zip or unzip API
 
-   Version 1.00, September 10th, 2003
+   Version 1.01e, February 12th, 2005
 
-   Copyright (C) 1998-2003 Gilles Vollant
+   Copyright (C) 1998-2005 Gilles Vollant
 */
 
 #include <stdio.h>
@@ -94,7 +94,7 @@ uLong ZCALLBACK fread_file_func (opaque, stream, buf, size)
    uLong size;
 {
     uLong ret;
-    ret = fread(buf, 1, (size_t)size, (FILE *)stream);
+    ret = (uLong)fread(buf, 1, (size_t)size, (FILE *)stream);
     return ret;
 }
 
@@ -106,7 +106,7 @@ uLong ZCALLBACK fwrite_file_func (opaque, stream, buf, size)
    uLong size;
 {
     uLong ret;
-    ret = fwrite(buf, 1, (size_t)size, (FILE *)stream);
+    ret = (uLong)fwrite(buf, 1, (size_t)size, (FILE *)stream);
     return ret;
 }
 
diff --git a/zlib/contrib/minizip/ioapi.h b/zlib/contrib/minizip/ioapi.h
index 6bc2a2cc872..7d457baab34 100644
--- a/zlib/contrib/minizip/ioapi.h
+++ b/zlib/contrib/minizip/ioapi.h
@@ -1,9 +1,9 @@
 /* ioapi.h -- IO base function header for compress/uncompress .zip
    files using zlib + zip or unzip API
 
-   Version 1.00, September 10th, 2003
+   Version 1.01e, February 12th, 2005
 
-   Copyright (C) 1998-2003 Gilles Vollant
+   Copyright (C) 1998-2005 Gilles Vollant
 */
 
 #ifndef _ZLIBIOAPI_H
diff --git a/zlib/contrib/minizip/iowin32.c b/zlib/contrib/minizip/iowin32.c
index 02b27cb7614..a9b5f783996 100644
--- a/zlib/contrib/minizip/iowin32.c
+++ b/zlib/contrib/minizip/iowin32.c
@@ -2,9 +2,9 @@
    files using zlib + zip or unzip API
    This IO API version uses the Win32 API (for Microsoft Windows)
 
-   Version 1.00, September 10th, 2003
+   Version 1.01e, February 12th, 2005
 
-   Copyright (C) 1998-2003 Gilles Vollant
+   Copyright (C) 1998-2005 Gilles Vollant
 */
 
 #include <stdlib.h>
diff --git a/zlib/contrib/minizip/iowin32.h b/zlib/contrib/minizip/iowin32.h
index c0ebd50738e..a3a437adf84 100644
--- a/zlib/contrib/minizip/iowin32.h
+++ b/zlib/contrib/minizip/iowin32.h
@@ -2,9 +2,9 @@
    files using zlib + zip or unzip API
    This IO API version uses the Win32 API (for Microsoft Windows)
 
-   Version 1.00, September 10th, 2003
+   Version 1.01e, February 12th, 2005
 
-   Copyright (C) 1998-2003 Gilles Vollant
+   Copyright (C) 1998-2005 Gilles Vollant
 */
 
 #include <windows.h>
diff --git a/zlib/contrib/pascal/zlibpas.pas b/zlib/contrib/pascal/zlibpas.pas
index 6d5ebe0f30e..836848c2b7b 100644
--- a/zlib/contrib/pascal/zlibpas.pas
+++ b/zlib/contrib/pascal/zlibpas.pas
@@ -10,7 +10,7 @@ unit zlibpas;
 interface
 
 const
-  ZLIB_VERSION = '1.2.1';
+  ZLIB_VERSION = '1.2.3';
 
 type
   alloc_func = function(opaque: Pointer; items, size: Integer): Pointer;
diff --git a/zlib/contrib/puff/puff.c b/zlib/contrib/puff/puff.c
index 7a8116b4480..ce0cc405e38 100644
--- a/zlib/contrib/puff/puff.c
+++ b/zlib/contrib/puff/puff.c
@@ -1,8 +1,8 @@
 /*
  * puff.c
- * Copyright (C) 2002, 2003 Mark Adler
+ * Copyright (C) 2002-2004 Mark Adler
  * For conditions of distribution and use, see copyright notice in puff.h
- * version 1.7, 3 Mar 2003
+ * version 1.8, 9 Jan 2004
  *
  * puff.c is a simple inflate written to be an unambiguous way to specify the
  * deflate format.  It is not written for speed but rather simplicity.  As a
@@ -60,6 +60,7 @@
  * 1.6   7 Aug 2002     - Minor format changes
  * 1.7   3 Mar 2003     - Added test code for distribution
  *                      - Added zlib-like license
+ * 1.8   9 Jan 2004     - Added some comments on no distance codes case
  */
 
 #include <setjmp.h>             /* for setjmp(), longjmp(), and jmp_buf */
@@ -577,6 +578,9 @@ local int fixed(struct state *s)
  *   block is fewer bits), but it is allowed by the format.  So incomplete
  *   literal/length codes of one symbol should also be permitted.
  *
+ * - If there are only literal codes and no lengths, then there are no distance
+ *   codes.  This is represented by one distance code with zero bits.
+ *
  * - The list of up to 286 length/literal lengths and up to 30 distance lengths
  *   are themselves compressed using Huffman codes and run-length encoding.  In
  *   the list of code lengths, a 0 symbol means no code, a 1..15 symbol means
diff --git a/zlib/contrib/testzlib/testzlib.c b/zlib/contrib/testzlib/testzlib.c
index fdabc5c192f..e5574f45e7f 100644
--- a/zlib/contrib/testzlib/testzlib.c
+++ b/zlib/contrib/testzlib/testzlib.c
@@ -1,149 +1,275 @@
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <windows.h>
-#include "zlib.h"
-
-int ReadFileMemory(const char* filename,long* plFileSize,void** pFilePtr)
-{
-    FILE* stream;
-    void* ptr;
-    int retVal=1;
-    stream=fopen(filename, "rb");
-    if (stream==NULL)
-        return 0;
-
-    fseek(stream,0,SEEK_END);
-
-    *plFileSize=ftell(stream);
-    fseek(stream,0,SEEK_SET);
-    ptr=malloc((*plFileSize)+1);
-    if (ptr==NULL)
-        retVal=0;
-    else
-    {
-        if (fread(ptr, 1, *plFileSize,stream) != (*plFileSize))
-            retVal=0;
-    }
-    fclose(stream);
-    *pFilePtr=ptr;
-    return retVal;
-}
-
-int main(int argc, char *argv[])
-{
-    int BlockSizeCompress=0x8000;
-    int BlockSizeUncompress=0x8000;
-    int cprLevel=Z_DEFAULT_COMPRESSION ;
-    long lFileSize;
-    unsigned char* FilePtr;
-    long lBufferSizeCpr;
-    long lBufferSizeUncpr;
-    long lCompressedSize=0;
-    unsigned char* CprPtr;
-    unsigned char* UncprPtr;
-    long lSizeCpr,lSizeUncpr;
-    DWORD dwGetTick;
-
-    if (argc<=1)
-    {
-        printf("run TestZlib <File> [BlockSizeCompress] [BlockSizeUncompress] [compres. level]\n");
-        return 0;
-    }
-
-    if (ReadFileMemory(argv[1],&lFileSize,&FilePtr)==0)
-    {
-        printf("error reading %s\n",argv[1]);
-        return 1;
-    }
-    else printf("file %s read, %u bytes\n",argv[1],lFileSize);
-
-    if (argc>=3)
-        BlockSizeCompress=atol(argv[2]);
-
-    if (argc>=4)
-        BlockSizeUncompress=atol(argv[3]);
-
-    if (argc>=5)
-        cprLevel=(int)atol(argv[4]);
-
-    lBufferSizeCpr = lFileSize + (lFileSize/0x10) + 0x200;
-    lBufferSizeUncpr = lBufferSizeCpr;
-
-    CprPtr=(unsigned char*)malloc(lBufferSizeCpr + BlockSizeCompress);
-    UncprPtr=(unsigned char*)malloc(lBufferSizeUncpr + BlockSizeUncompress);
-
-    dwGetTick=GetTickCount();
-    {
-        z_stream zcpr;
-        int ret=Z_OK;
-        long lOrigToDo = lFileSize;
-        long lOrigDone = 0;
-        int step=0;
-        memset(&zcpr,0,sizeof(z_stream));
-        deflateInit(&zcpr,cprLevel);
-
-        zcpr.next_in = FilePtr;
-        zcpr.next_out = CprPtr;
-
-
-        do
-        {
-            long all_read_before = zcpr.total_in;
-            zcpr.avail_in = min(lOrigToDo,BlockSizeCompress);
-            zcpr.avail_out = BlockSizeCompress;
-            ret=deflate(&zcpr,(zcpr.avail_in==lOrigToDo) ? Z_FINISH : Z_SYNC_FLUSH);
-            lOrigDone += (zcpr.total_in-all_read_before);
-            lOrigToDo -= (zcpr.total_in-all_read_before);
-            step++;
-        } while (ret==Z_OK);
-
-        lSizeCpr=zcpr.total_out;
-        deflateEnd(&zcpr);
-        dwGetTick=GetTickCount()-dwGetTick;
-        printf("total compress size = %u, in %u step\n",lSizeCpr,step);
-        printf("time = %u msec = %f sec\n\n",dwGetTick,dwGetTick/(double)1000.);
-    }
-
-    dwGetTick=GetTickCount();
-    {
-        z_stream zcpr;
-        int ret=Z_OK;
-        long lOrigToDo = lSizeCpr;
-        long lOrigDone = 0;
-        int step=0;
-        memset(&zcpr,0,sizeof(z_stream));
-        inflateInit(&zcpr);
-
-        zcpr.next_in = CprPtr;
-        zcpr.next_out = UncprPtr;
-
-
-        do
-        {
-            long all_read_before = zcpr.total_in;
-            zcpr.avail_in = min(lOrigToDo,BlockSizeUncompress);
-            zcpr.avail_out = BlockSizeUncompress;
-            ret=inflate(&zcpr,Z_SYNC_FLUSH);
-            lOrigDone += (zcpr.total_in-all_read_before);
-            lOrigToDo -= (zcpr.total_in-all_read_before);
-            step++;
-        } while (ret==Z_OK);
-
-        lSizeUncpr=zcpr.total_out;
-        inflateEnd(&zcpr);
-        dwGetTick=GetTickCount()-dwGetTick;
-        printf("total uncompress size = %u, in %u step\n",lSizeUncpr,step);
-        printf("time = %u msec = %f sec\n\n",dwGetTick,dwGetTick/(double)1000.);
-    }
-
-    if (lSizeUncpr==lFileSize)
-    {
-        if (memcmp(FilePtr,UncprPtr,lFileSize)==0)
-            printf("compare ok\n");
-
-    }
-
-    return 0;
-
-}
+#include <stdio.h>

+#include <stdlib.h>

+#include <windows.h>

+

+#include "zlib.h"

+

+

+void MyDoMinus64(LARGE_INTEGER *R,LARGE_INTEGER A,LARGE_INTEGER B)

+{

+    R->HighPart = A.HighPart - B.HighPart;

+    if (A.LowPart >= B.LowPart)

+        R->LowPart = A.LowPart - B.LowPart;

+    else

+    {

+        R->LowPart = A.LowPart - B.LowPart;

+        R->HighPart --;

+    }

+}

+

+#ifdef _M_X64

+// see http://msdn2.microsoft.com/library/twchhe95(en-us,vs.80).aspx for __rdtsc

+unsigned __int64 __rdtsc(void);

+void BeginCountRdtsc(LARGE_INTEGER * pbeginTime64)

+{

+ //   printf("rdtsc = %I64x\n",__rdtsc());

+   pbeginTime64->QuadPart=__rdtsc();

+}

+

+LARGE_INTEGER GetResRdtsc(LARGE_INTEGER beginTime64,BOOL fComputeTimeQueryPerf)

+{

+    LARGE_INTEGER LIres;

+    unsigned _int64 res=__rdtsc()-((unsigned _int64)(beginTime64.QuadPart));

+    LIres.QuadPart=res;

+   // printf("rdtsc = %I64x\n",__rdtsc());

+    return LIres;

+}

+#else

+#ifdef _M_IX86

+void myGetRDTSC32(LARGE_INTEGER * pbeginTime64)

+{

+    DWORD dwEdx,dwEax;

+    _asm

+    {

+        rdtsc

+        mov dwEax,eax

+        mov dwEdx,edx

+    }

+    pbeginTime64->LowPart=dwEax;

+    pbeginTime64->HighPart=dwEdx;

+}

+

+void BeginCountRdtsc(LARGE_INTEGER * pbeginTime64)

+{

+    myGetRDTSC32(pbeginTime64);

+}

+

+LARGE_INTEGER GetResRdtsc(LARGE_INTEGER beginTime64,BOOL fComputeTimeQueryPerf)

+{

+    LARGE_INTEGER LIres,endTime64;

+    myGetRDTSC32(&endTime64);

+

+    LIres.LowPart=LIres.HighPart=0;

+    MyDoMinus64(&LIres,endTime64,beginTime64);

+    return LIres;

+}

+#else

+void myGetRDTSC32(LARGE_INTEGER * pbeginTime64)

+{

+}

+

+void BeginCountRdtsc(LARGE_INTEGER * pbeginTime64)

+{

+}

+

+LARGE_INTEGER GetResRdtsc(LARGE_INTEGER beginTime64,BOOL fComputeTimeQueryPerf)

+{

+    LARGE_INTEGER lr;

+    lr.QuadPart=0;

+    return lr;

+}

+#endif

+#endif

+

+void BeginCountPerfCounter(LARGE_INTEGER * pbeginTime64,BOOL fComputeTimeQueryPerf)

+{

+    if ((!fComputeTimeQueryPerf) || (!QueryPerformanceCounter(pbeginTime64)))

+    {

+        pbeginTime64->LowPart = GetTickCount();

+        pbeginTime64->HighPart = 0;

+    }

+}

+

+DWORD GetMsecSincePerfCounter(LARGE_INTEGER beginTime64,BOOL fComputeTimeQueryPerf)

+{

+    LARGE_INTEGER endTime64,ticksPerSecond,ticks;

+    DWORDLONG ticksShifted,tickSecShifted;

+    DWORD dwLog=16+0;

+    DWORD dwRet;

+    if ((!fComputeTimeQueryPerf) || (!QueryPerformanceCounter(&endTime64)))

+        dwRet = (GetTickCount() - beginTime64.LowPart)*1;

+    else

+    {

+        MyDoMinus64(&ticks,endTime64,beginTime64);

+        QueryPerformanceFrequency(&ticksPerSecond);

+

+    

+        {

+            ticksShifted = Int64ShrlMod32(*(DWORDLONG*)&ticks,dwLog);

+            tickSecShifted = Int64ShrlMod32(*(DWORDLONG*)&ticksPerSecond,dwLog);

+        

+        } 

+

+        dwRet = (DWORD)((((DWORD)ticksShifted)*1000)/(DWORD)(tickSecShifted));

+        dwRet *=1;

+    }

+    return dwRet;

+}

+

+int ReadFileMemory(const char* filename,long* plFileSize,void** pFilePtr)

+{

+    FILE* stream;

+    void* ptr;

+    int retVal=1;

+    stream=fopen(filename, "rb");

+    if (stream==NULL)

+        return 0;

+

+    fseek(stream,0,SEEK_END);

+

+    *plFileSize=ftell(stream);

+    fseek(stream,0,SEEK_SET);

+    ptr=malloc((*plFileSize)+1);

+    if (ptr==NULL)

+        retVal=0;

+    else

+    {

+        if (fread(ptr, 1, *plFileSize,stream) != (*plFileSize))

+            retVal=0;

+    }

+    fclose(stream);

+    *pFilePtr=ptr;

+    return retVal;

+}

+

+int main(int argc, char *argv[])

+{

+    int BlockSizeCompress=0x8000;

+    int BlockSizeUncompress=0x8000;

+    int cprLevel=Z_DEFAULT_COMPRESSION ;

+    long lFileSize;

+    unsigned char* FilePtr;

+    long lBufferSizeCpr;

+    long lBufferSizeUncpr;

+    long lCompressedSize=0;

+    unsigned char* CprPtr;

+    unsigned char* UncprPtr;

+    long lSizeCpr,lSizeUncpr;

+    DWORD dwGetTick,dwMsecQP;

+    LARGE_INTEGER li_qp,li_rdtsc,dwResRdtsc;

+

+    if (argc<=1)

+    {

+        printf("run TestZlib <File> [BlockSizeCompress] [BlockSizeUncompress] [compres. level]\n");

+        return 0;

+    }

+

+    if (ReadFileMemory(argv[1],&lFileSize,&FilePtr)==0)

+    {

+        printf("error reading %s\n",argv[1]);

+        return 1;

+    }

+    else printf("file %s read, %u bytes\n",argv[1],lFileSize);

+

+    if (argc>=3)

+        BlockSizeCompress=atol(argv[2]);

+

+    if (argc>=4)

+        BlockSizeUncompress=atol(argv[3]);

+

+    if (argc>=5)

+        cprLevel=(int)atol(argv[4]);

+

+    lBufferSizeCpr = lFileSize + (lFileSize/0x10) + 0x200;

+    lBufferSizeUncpr = lBufferSizeCpr;

+

+    CprPtr=(unsigned char*)malloc(lBufferSizeCpr + BlockSizeCompress);

+

+    BeginCountPerfCounter(&li_qp,TRUE);

+    dwGetTick=GetTickCount();

+    BeginCountRdtsc(&li_rdtsc);

+    {

+        z_stream zcpr;

+        int ret=Z_OK;

+        long lOrigToDo = lFileSize;

+        long lOrigDone = 0;

+        int step=0;

+        memset(&zcpr,0,sizeof(z_stream));

+        deflateInit(&zcpr,cprLevel);

+

+        zcpr.next_in = FilePtr;

+        zcpr.next_out = CprPtr;

+

+

+        do

+        {

+            long all_read_before = zcpr.total_in;

+            zcpr.avail_in = min(lOrigToDo,BlockSizeCompress);

+            zcpr.avail_out = BlockSizeCompress;

+            ret=deflate(&zcpr,(zcpr.avail_in==lOrigToDo) ? Z_FINISH : Z_SYNC_FLUSH);

+            lOrigDone += (zcpr.total_in-all_read_before);

+            lOrigToDo -= (zcpr.total_in-all_read_before);

+            step++;

+        } while (ret==Z_OK);

+

+        lSizeCpr=zcpr.total_out;

+        deflateEnd(&zcpr);

+        dwGetTick=GetTickCount()-dwGetTick;

+        dwMsecQP=GetMsecSincePerfCounter(li_qp,TRUE);

+        dwResRdtsc=GetResRdtsc(li_rdtsc,TRUE);

+        printf("total compress size = %u, in %u step\n",lSizeCpr,step);

+        printf("time = %u msec = %f sec\n",dwGetTick,dwGetTick/(double)1000.);

+        printf("defcpr time QP = %u msec = %f sec\n",dwMsecQP,dwMsecQP/(double)1000.);

+        printf("defcpr result rdtsc = %I64x\n\n",dwResRdtsc.QuadPart);

+    }

+

+    CprPtr=(unsigned char*)realloc(CprPtr,lSizeCpr);

+    UncprPtr=(unsigned char*)malloc(lBufferSizeUncpr + BlockSizeUncompress);

+

+    BeginCountPerfCounter(&li_qp,TRUE);

+    dwGetTick=GetTickCount();

+    BeginCountRdtsc(&li_rdtsc);

+    {

+        z_stream zcpr;

+        int ret=Z_OK;

+        long lOrigToDo = lSizeCpr;

+        long lOrigDone = 0;

+        int step=0;

+        memset(&zcpr,0,sizeof(z_stream));

+        inflateInit(&zcpr);

+

+        zcpr.next_in = CprPtr;

+        zcpr.next_out = UncprPtr;

+

+

+        do

+        {

+            long all_read_before = zcpr.total_in;

+            zcpr.avail_in = min(lOrigToDo,BlockSizeUncompress);

+            zcpr.avail_out = BlockSizeUncompress;

+            ret=inflate(&zcpr,Z_SYNC_FLUSH);

+            lOrigDone += (zcpr.total_in-all_read_before);

+            lOrigToDo -= (zcpr.total_in-all_read_before);

+            step++;

+        } while (ret==Z_OK);

+

+        lSizeUncpr=zcpr.total_out;

+        inflateEnd(&zcpr);

+        dwGetTick=GetTickCount()-dwGetTick;

+        dwMsecQP=GetMsecSincePerfCounter(li_qp,TRUE);

+        dwResRdtsc=GetResRdtsc(li_rdtsc,TRUE);

+        printf("total uncompress size = %u, in %u step\n",lSizeUncpr,step);

+        printf("time = %u msec = %f sec\n",dwGetTick,dwGetTick/(double)1000.);

+        printf("uncpr  time QP = %u msec = %f sec\n",dwMsecQP,dwMsecQP/(double)1000.);

+        printf("uncpr  result rdtsc = %I64x\n\n",dwResRdtsc.QuadPart);

+    }

+

+    if (lSizeUncpr==lFileSize)

+    {

+        if (memcmp(FilePtr,UncprPtr,lFileSize)==0)

+            printf("compare ok\n");

+

+    }

+

+    return 0;

+}

diff --git a/zlib/contrib/vstudio/readme.txt b/zlib/contrib/vstudio/readme.txt
index 3a4b85c8ef4..16159f9cd0d 100644
--- a/zlib/contrib/vstudio/readme.txt
+++ b/zlib/contrib/vstudio/readme.txt
@@ -1,8 +1,8 @@
-Building instructions for the DLL versions of Zlib 1.21

-=======================================================

+Building instructions for the DLL versions of Zlib 1.2.3

+========================================================

 

 This directory contains projects that build zlib and minizip using

-Microsoft Visual C++ 7.0/7.1.

+Microsoft Visual C++ 7.0/7.1, and Visual C++ .

 

 You don't need to build these projects yourself. You can download the

 binaries from:

@@ -11,18 +11,36 @@ binaries from:
 More information can be found at this site.

 

 

-Build instructions

-------------------

-- Unzip zlib*.zip and copy the files from contrib\vstudio\vc7,

-  from contrib\vstudio\masmx86 and from contrib\minizip into the same

-  directory.

+Build instructions for Visual Studio 7.x (32 bits)

+--------------------------------------------------

+- Uncompress current zlib, including all contrib/* files

 - Download the crtdll library from

     http://www.winimage.com/zLibDll/crtdll.zip

-  Unzip crtdll.zip to extract crtdll.lib.

-- If you are using x86, use the Release target.

-- Open zlibvc.sln with Microsoft Visual C++ 7.0 or 7.1

+  Unzip crtdll.zip to extract crtdll.lib on contrib\vstudio\vc7.

+- Open contrib\vstudio\vc7\zlibvc.sln with Microsoft Visual C++ 7.x

   (Visual Studio .Net 2002 or 2003).

 

+Build instructions for Visual Studio 2005 (32 bits or 64 bits)

+--------------------------------------------------------------

+- Uncompress current zlib, including all contrib/* files

+- For 32 bits only: download the crtdll library from

+    http://www.winimage.com/zLibDll/crtdll.zip

+  Unzip crtdll.zip to extract crtdll.lib on contrib\vstudio\vc8.

+- Open contrib\vstudio\vc8\zlibvc.sln with Microsoft Visual C++ 8.0

+

+Build instructions for Visual Studio 2005 64 bits, PSDK compiler

+----------------------------------------------------------------

+at the time of writing this text file, Visual Studio 2005 (and 

+  Microsoft Visual C++ 8.0) is on the beta 2 stage.

+Using you can get the free 64 bits compiler from Platform SDK, 

+  which is NOT a beta, and compile using the Visual studio 2005 IDE

+see http://www.winimage.com/misc/sdk64onvs2005/ for instruction

+

+- Uncompress current zlib, including all contrib/* files

+- start Visual Studio 2005 from a platform SDK command prompt, using

+  the /useenv switch

+- Open contrib\vstudio\vc8\zlibvc.sln with Microsoft Visual C++ 8.0

+

 

 Important

 ---------

diff --git a/zlib/contrib/vstudio/vc7/miniunz.vcproj b/zlib/contrib/vstudio/vc7/miniunz.vcproj
index 935c250e5f9..ad5117c8451 100644
--- a/zlib/contrib/vstudio/vc7/miniunz.vcproj
+++ b/zlib/contrib/vstudio/vc7/miniunz.vcproj
@@ -19,6 +19,7 @@
 			<Tool

 				Name="VCCLCompilerTool"

 				Optimization="0"

+				AdditionalIncludeDirectories="..\..\..;..\..\minizip"

 				PreprocessorDefinitions="WIN32;ZLIB_WINAPI;_DEBUG;_CONSOLE"

 				MinimalRebuild="TRUE"

 				BasicRuntimeChecks="3"

@@ -63,6 +64,7 @@
 				Optimization="2"

 				InlineFunctionExpansion="1"

 				OmitFramePointers="TRUE"

+				AdditionalIncludeDirectories="..\..\..;..\..\minizip"

 				PreprocessorDefinitions="WIN32;ZLIB_WINAPI;NDEBUG;_CONSOLE"

 				StringPooling="TRUE"

 				RuntimeLibrary="4"

@@ -104,7 +106,7 @@
 			Name="Source Files"

 			Filter="cpp;c;cxx;def;odl;idl;hpj;bat;asm">

 			<File

-				RelativePath="miniunz.c">

+				RelativePath="..\..\minizip\miniunz.c">

 			</File>

 		</Filter>

 		<Filter

@@ -116,7 +118,7 @@
 			Filter="rc;ico;cur;bmp;dlg;rc2;rct;bin;rgs;gif;jpg;jpeg;jpe">

 		</Filter>

 		<File

-			RelativePath="zlibwapi.lib">

+			RelativePath="ReleaseDll\zlibwapi.lib">

 		</File>

 	</Files>

 	<Globals>

diff --git a/zlib/contrib/vstudio/vc7/minizip.vcproj b/zlib/contrib/vstudio/vc7/minizip.vcproj
index e6f910742c1..fb5b6320d50 100644
--- a/zlib/contrib/vstudio/vc7/minizip.vcproj
+++ b/zlib/contrib/vstudio/vc7/minizip.vcproj
@@ -19,6 +19,7 @@
 			<Tool

 				Name="VCCLCompilerTool"

 				Optimization="0"

+				AdditionalIncludeDirectories="..\..\..;..\..\minizip"

 				PreprocessorDefinitions="WIN32;ZLIB_WINAPI;_DEBUG;_CONSOLE"

 				MinimalRebuild="TRUE"

 				BasicRuntimeChecks="3"

@@ -63,6 +64,7 @@
 				Optimization="2"

 				InlineFunctionExpansion="1"

 				OmitFramePointers="TRUE"

+				AdditionalIncludeDirectories="..\..\..;..\..\minizip"

 				PreprocessorDefinitions="WIN32;ZLIB_WINAPI;NDEBUG;_CONSOLE"

 				StringPooling="TRUE"

 				RuntimeLibrary="4"

@@ -104,7 +106,7 @@
 			Name="Source Files"

 			Filter="cpp;c;cxx;def;odl;idl;hpj;bat;asm">

 			<File

-				RelativePath="minizip.c">

+				RelativePath="..\..\minizip\minizip.c">

 			</File>

 		</Filter>

 		<Filter

@@ -116,7 +118,7 @@
 			Filter="rc;ico;cur;bmp;dlg;rc2;rct;bin;rgs;gif;jpg;jpeg;jpe">

 		</Filter>

 		<File

-			RelativePath="zlibwapi.lib">

+			RelativePath="ReleaseDll\zlibwapi.lib">

 		</File>

 	</Files>

 	<Globals>

diff --git a/zlib/contrib/vstudio/vc7/zlib.rc b/zlib/contrib/vstudio/vc7/zlib.rc
index 6c51679853b..72cb8b4c31e 100644
--- a/zlib/contrib/vstudio/vc7/zlib.rc
+++ b/zlib/contrib/vstudio/vc7/zlib.rc
@@ -2,8 +2,8 @@
 

 #define IDR_VERSION1  1

 IDR_VERSION1	VERSIONINFO	MOVEABLE IMPURE LOADONCALL DISCARDABLE

-  FILEVERSION	 1,2,1,0

-  PRODUCTVERSION 1,2,1,0

+  FILEVERSION	 1,2,3,0

+  PRODUCTVERSION 1,2,3,0

   FILEFLAGSMASK	VS_FFI_FILEFLAGSMASK

   FILEFLAGS	0

   FILEOS	VOS_DOS_WINDOWS32

@@ -17,7 +17,7 @@ BEGIN
 

     BEGIN

       VALUE "FileDescription", "zlib data compression library\0"

-      VALUE "FileVersion",	"1.2.1.0\0"

+      VALUE "FileVersion",	"1.2.3.0\0"

       VALUE "InternalName",	"zlib\0"

       VALUE "OriginalFilename",	"zlib.dll\0"

       VALUE "ProductName",	"ZLib.DLL\0"

diff --git a/zlib/contrib/vstudio/vc7/zlibstat.vcproj b/zlib/contrib/vstudio/vc7/zlibstat.vcproj
index eb182f7a884..766d7a4d6e7 100644
--- a/zlib/contrib/vstudio/vc7/zlibstat.vcproj
+++ b/zlib/contrib/vstudio/vc7/zlibstat.vcproj
@@ -20,6 +20,7 @@
 			<Tool

 				Name="VCCLCompilerTool"

 				Optimization="0"

+				AdditionalIncludeDirectories="..\..\..;..\..\masmx86"

 				PreprocessorDefinitions="WIN32;ZLIB_WINAPI"

 				ExceptionHandling="FALSE"

 				RuntimeLibrary="5"

@@ -61,6 +62,7 @@
 			<Tool

 				Name="VCCLCompilerTool"

 				InlineFunctionExpansion="1"

+				AdditionalIncludeDirectories="..\..\..;..\..\masmx86"

 				PreprocessorDefinitions="WIN32;ZLIB_WINAPI"

 				StringPooling="TRUE"

 				ExceptionHandling="FALSE"

@@ -102,6 +104,7 @@
 			<Tool

 				Name="VCCLCompilerTool"

 				InlineFunctionExpansion="1"

+				AdditionalIncludeDirectories="..\..\..;..\..\masmx86"

 				PreprocessorDefinitions="WIN32;ZLIB_WINAPI;ASMV;ASMINF"

 				StringPooling="TRUE"

 				ExceptionHandling="FALSE"

@@ -117,7 +120,7 @@
 				Name="VCCustomBuildTool"/>

 			<Tool

 				Name="VCLibrarianTool"

-				AdditionalOptions="gvmat32.obj inffas32.obj /NODEFAULTLIB "

+				AdditionalOptions="..\..\masmx86\gvmat32.obj ..\..\masmx86\inffas32.obj /NODEFAULTLIB "

 				OutputFile=".\zlibstat\zlibstat.lib"

 				SuppressStartupBanner="TRUE"/>

 			<Tool

@@ -144,6 +147,7 @@
 			<Tool

 				Name="VCCLCompilerTool"

 				InlineFunctionExpansion="1"

+				AdditionalIncludeDirectories="..\..\..;..\..\masmx86"

 				PreprocessorDefinitions="WIN32;ZLIB_WINAPI"

 				StringPooling="TRUE"

 				ExceptionHandling="FALSE"

@@ -182,49 +186,49 @@
 			Name="Source Files"

 			Filter="">

 			<File

-				RelativePath=".\adler32.c">

+				RelativePath="..\..\..\adler32.c">

 			</File>

 			<File

-				RelativePath=".\compress.c">

+				RelativePath="..\..\..\compress.c">

 			</File>

 			<File

-				RelativePath=".\crc32.c">

+				RelativePath="..\..\..\crc32.c">

 			</File>

 			<File

-				RelativePath=".\deflate.c">

+				RelativePath="..\..\..\deflate.c">

 			</File>

 			<File

-				RelativePath=".\gvmat32c.c">

+				RelativePath="..\..\masmx86\gvmat32c.c">

 			</File>

 			<File

-				RelativePath=".\gzio.c">

+				RelativePath="..\..\..\gzio.c">

 			</File>

 			<File

-				RelativePath=".\infback.c">

+				RelativePath="..\..\..\infback.c">

 			</File>

 			<File

-				RelativePath=".\inffast.c">

+				RelativePath="..\..\..\inffast.c">

 			</File>

 			<File

-				RelativePath=".\inflate.c">

+				RelativePath="..\..\..\inflate.c">

 			</File>

 			<File

-				RelativePath=".\inftrees.c">

+				RelativePath="..\..\..\inftrees.c">

 			</File>

 			<File

-				RelativePath=".\ioapi.c">

+				RelativePath="..\..\minizip\ioapi.c">

 			</File>

 			<File

-				RelativePath=".\trees.c">

+				RelativePath="..\..\..\trees.c">

 			</File>

 			<File

-				RelativePath=".\uncompr.c">

+				RelativePath="..\..\..\uncompr.c">

 			</File>

 			<File

-				RelativePath=".\unzip.c">

+				RelativePath="..\..\minizip\unzip.c">

 			</File>

 			<File

-				RelativePath=".\zip.c">

+				RelativePath="..\..\minizip\zip.c">

 			</File>

 			<File

 				RelativePath=".\zlib.rc">

@@ -233,7 +237,7 @@
 				RelativePath=".\zlibvc.def">

 			</File>

 			<File

-				RelativePath=".\zutil.c">

+				RelativePath="..\..\..\zutil.c">

 			</File>

 		</Filter>

 	</Files>

diff --git a/zlib/contrib/vstudio/vc7/zlibvc.sln b/zlib/contrib/vstudio/vc7/zlibvc.sln
index 5a007ff697b..927b42b7bde 100644
--- a/zlib/contrib/vstudio/vc7/zlibvc.sln
+++ b/zlib/contrib/vstudio/vc7/zlibvc.sln
@@ -7,6 +7,8 @@ Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "minizip", "minizip.vcproj",
 EndProject

 Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "miniunz", "miniunz.vcproj", "{C52F9E7B-498A-42BE-8DB4-85A15694382A}"

 EndProject

+Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "testZlibDll", "testzlib.vcproj", "{AA6666AA-E09F-4135-9C0C-4FE50C3C654C}"

+EndProject

 Global

 	GlobalSection(SolutionConfiguration) = preSolution

 		ConfigName.0 = Debug

@@ -58,6 +60,16 @@ Global
 		{C52F9E7B-498A-42BE-8DB4-85A15694382A}.ReleaseWithoutAsm.Build.0 = Release|Win32

 		{C52F9E7B-498A-42BE-8DB4-85A15694382A}.ReleaseWithoutCrtdll.ActiveCfg = Release|Win32

 		{C52F9E7B-498A-42BE-8DB4-85A15694382A}.ReleaseWithoutCrtdll.Build.0 = Release|Win32

+		{AA6666AA-E09F-4135-9C0C-4FE50C3C654C}.Debug.ActiveCfg = Debug|Win32

+		{AA6666AA-E09F-4135-9C0C-4FE50C3C654C}.Debug.Build.0 = Debug|Win32

+		{AA6666AA-E09F-4135-9C0C-4FE50C3C654C}.Release.ActiveCfg = Release|Win32

+		{AA6666AA-E09F-4135-9C0C-4FE50C3C654C}.Release.Build.0 = Release|Win32

+		{AA6666AA-E09F-4135-9C0C-4FE50C3C654C}.ReleaseAxp.ActiveCfg = Release|Win32

+		{AA6666AA-E09F-4135-9C0C-4FE50C3C654C}.ReleaseAxp.Build.0 = Release|Win32

+		{AA6666AA-E09F-4135-9C0C-4FE50C3C654C}.ReleaseWithoutAsm.ActiveCfg = Release|Win32

+		{AA6666AA-E09F-4135-9C0C-4FE50C3C654C}.ReleaseWithoutAsm.Build.0 = Release|Win32

+		{AA6666AA-E09F-4135-9C0C-4FE50C3C654C}.ReleaseWithoutCrtdll.ActiveCfg = Release|Win32

+		{AA6666AA-E09F-4135-9C0C-4FE50C3C654C}.ReleaseWithoutCrtdll.Build.0 = Release|Win32

 	EndGlobalSection

 	GlobalSection(ExtensibilityGlobals) = postSolution

 	EndGlobalSection

diff --git a/zlib/contrib/vstudio/vc7/zlibvc.vcproj b/zlib/contrib/vstudio/vc7/zlibvc.vcproj
index 4e57bcdff6f..8533b49475e 100644
--- a/zlib/contrib/vstudio/vc7/zlibvc.vcproj
+++ b/zlib/contrib/vstudio/vc7/zlibvc.vcproj
@@ -20,6 +20,7 @@
 			<Tool

 				Name="VCCLCompilerTool"

 				Optimization="0"

+				AdditionalIncludeDirectories="..\..\..;..\..\masmx86"

 				PreprocessorDefinitions="WIN32,ZLIB_WINAPI,ASMV,ASMINF"

 				ExceptionHandling="FALSE"

 				RuntimeLibrary="1"

@@ -35,7 +36,7 @@
 			<Tool

 				Name="VCLinkerTool"

 				AdditionalOptions="/MACHINE:I386"

-				AdditionalDependencies="gvmat32.obj inffas32.obj"

+				AdditionalDependencies="..\..\masmx86\gvmat32.obj ..\..\masmx86\inffas32.obj"

 				OutputFile=".\DebugDll\zlibwapi.dll"

 				LinkIncremental="2"

 				SuppressStartupBanner="TRUE"

@@ -72,10 +73,12 @@
 			IntermediateDirectory=".\zlibDllWithoutAsm"

 			ConfigurationType="2"

 			UseOfMFC="0"

-			ATLMinimizesCRunTimeLibraryUsage="FALSE">

+			ATLMinimizesCRunTimeLibraryUsage="FALSE"

+			WholeProgramOptimization="TRUE">

 			<Tool

 				Name="VCCLCompilerTool"

 				InlineFunctionExpansion="1"

+				AdditionalIncludeDirectories="..\..\..;..\..\masmx86"

 				PreprocessorDefinitions="WIN32,ZLIB_WINAPI"

 				StringPooling="TRUE"

 				ExceptionHandling="FALSE"

@@ -134,10 +137,12 @@
 			IntermediateDirectory=".\zlibDllWithoutCrtDll"

 			ConfigurationType="2"

 			UseOfMFC="0"

-			ATLMinimizesCRunTimeLibraryUsage="FALSE">

+			ATLMinimizesCRunTimeLibraryUsage="FALSE"

+			WholeProgramOptimization="TRUE">

 			<Tool

 				Name="VCCLCompilerTool"

 				InlineFunctionExpansion="1"

+				AdditionalIncludeDirectories="..\..\..;..\..\masmx86"

 				PreprocessorDefinitions="WIN32,ZLIB_WINAPI,ASMV,ASMINF"

 				StringPooling="TRUE"

 				ExceptionHandling="FALSE"

@@ -156,7 +161,7 @@
 			<Tool

 				Name="VCLinkerTool"

 				AdditionalOptions="/MACHINE:I386"

-				AdditionalDependencies="gvmat32.obj inffas32.obj "

+				AdditionalDependencies="..\..\masmx86\gvmat32.obj ..\..\masmx86\inffas32.obj "

 				OutputFile=".\zlibDllWithoutCrtDll\zlibwapi.dll"

 				LinkIncremental="1"

 				SuppressStartupBanner="TRUE"

@@ -196,10 +201,12 @@
 			IntermediateDirectory=".\zlibvc__"

 			ConfigurationType="2"

 			UseOfMFC="0"

-			ATLMinimizesCRunTimeLibraryUsage="FALSE">

+			ATLMinimizesCRunTimeLibraryUsage="FALSE"

+			WholeProgramOptimization="TRUE">

 			<Tool

 				Name="VCCLCompilerTool"

 				InlineFunctionExpansion="1"

+				AdditionalIncludeDirectories="..\..\..;..\..\masmx86"

 				PreprocessorDefinitions="WIN32,ZLIB_WINAPI"

 				StringPooling="TRUE"

 				ExceptionHandling="FALSE"

@@ -256,10 +263,12 @@
 			IntermediateDirectory=".\ReleaseDll"

 			ConfigurationType="2"

 			UseOfMFC="0"

-			ATLMinimizesCRunTimeLibraryUsage="FALSE">

+			ATLMinimizesCRunTimeLibraryUsage="FALSE"

+			WholeProgramOptimization="TRUE">

 			<Tool

 				Name="VCCLCompilerTool"

 				InlineFunctionExpansion="1"

+				AdditionalIncludeDirectories="..\..\..;..\..\masmx86"

 				PreprocessorDefinitions="WIN32,ZLIB_WINAPI,ASMV,ASMINF"

 				StringPooling="TRUE"

 				ExceptionHandling="FALSE"

@@ -278,7 +287,7 @@
 			<Tool

 				Name="VCLinkerTool"

 				AdditionalOptions="/MACHINE:I386"

-				AdditionalDependencies="gvmat32.obj inffas32.obj crtdll.lib"

+				AdditionalDependencies="..\..\masmx86\gvmat32.obj ..\..\masmx86\inffas32.obj crtdll.lib"

 				OutputFile=".\ReleaseDll\zlibwapi.dll"

 				LinkIncremental="1"

 				SuppressStartupBanner="TRUE"

@@ -318,19 +327,19 @@
 			Name="Source Files"

 			Filter="cpp;c;cxx;rc;def;r;odl;hpj;bat;for;f90">

 			<File

-				RelativePath=".\adler32.c">

+				RelativePath="..\..\..\adler32.c">

 			</File>

 			<File

-				RelativePath=".\compress.c">

+				RelativePath="..\..\..\compress.c">

 			</File>

 			<File

-				RelativePath=".\crc32.c">

+				RelativePath="..\..\..\crc32.c">

 			</File>

 			<File

-				RelativePath=".\deflate.c">

+				RelativePath="..\..\..\deflate.c">

 			</File>

 			<File

-				RelativePath=".\gvmat32c.c">

+				RelativePath="..\..\masmx86\gvmat32c.c">

 				<FileConfiguration

 					Name="ReleaseWithoutAsm|Win32"

 					ExcludedFromBuild="TRUE">

@@ -339,34 +348,34 @@
 				</FileConfiguration>

 			</File>

 			<File

-				RelativePath=".\gzio.c">

+				RelativePath="..\..\..\gzio.c">

 			</File>

 			<File

-				RelativePath=".\infback.c">

+				RelativePath="..\..\..\infback.c">

 			</File>

 			<File

-				RelativePath=".\inffast.c">

+				RelativePath="..\..\..\inffast.c">

 			</File>

 			<File

-				RelativePath=".\inflate.c">

+				RelativePath="..\..\..\inflate.c">

 			</File>

 			<File

-				RelativePath=".\inftrees.c">

+				RelativePath="..\..\..\inftrees.c">

 			</File>

 			<File

-				RelativePath=".\ioapi.c">

+				RelativePath="..\..\minizip\ioapi.c">

 			</File>

 			<File

-				RelativePath=".\iowin32.c">

+				RelativePath="..\..\minizip\iowin32.c">

 			</File>

 			<File

-				RelativePath=".\trees.c">

+				RelativePath="..\..\..\trees.c">

 			</File>

 			<File

-				RelativePath=".\uncompr.c">

+				RelativePath="..\..\..\uncompr.c">

 			</File>

 			<File

-				RelativePath=".\unzip.c">

+				RelativePath="..\..\minizip\unzip.c">

 				<FileConfiguration

 					Name="Release|Win32">

 					<Tool

@@ -376,7 +385,7 @@
 				</FileConfiguration>

 			</File>

 			<File

-				RelativePath=".\zip.c">

+				RelativePath="..\..\minizip\zip.c">

 				<FileConfiguration

 					Name="Release|Win32">

 					<Tool

@@ -392,38 +401,38 @@
 				RelativePath=".\zlibvc.def">

 			</File>

 			<File

-				RelativePath=".\zutil.c">

+				RelativePath="..\..\..\zutil.c">

 			</File>

 		</Filter>

 		<Filter

 			Name="Header Files"

 			Filter="h;hpp;hxx;hm;inl;fi;fd">

 			<File

-				RelativePath=".\deflate.h">

+				RelativePath="..\..\..\deflate.h">

 			</File>

 			<File

-				RelativePath=".\infblock.h">

+				RelativePath="..\..\..\infblock.h">

 			</File>

 			<File

-				RelativePath=".\infcodes.h">

+				RelativePath="..\..\..\infcodes.h">

 			</File>

 			<File

-				RelativePath=".\inffast.h">

+				RelativePath="..\..\..\inffast.h">

 			</File>

 			<File

-				RelativePath=".\inftrees.h">

+				RelativePath="..\..\..\inftrees.h">

 			</File>

 			<File

-				RelativePath=".\infutil.h">

+				RelativePath="..\..\..\infutil.h">

 			</File>

 			<File

-				RelativePath=".\zconf.h">

+				RelativePath="..\..\..\zconf.h">

 			</File>

 			<File

-				RelativePath=".\zlib.h">

+				RelativePath="..\..\..\zlib.h">

 			</File>

 			<File

-				RelativePath=".\zutil.h">

+				RelativePath="..\..\..\zutil.h">

 			</File>

 		</Filter>

 		<Filter