Merge 8.6

2 files changed, 461 insertions, 461 deletions

diff --git a/compat/zlib/contrib/masmx64/inffas8664.c b/compat/zlib/contrib/masmx64/inffas8664.c
index e8af06f..aa861a3 100644
--- a/compat/zlib/contrib/masmx64/inffas8664.c
+++ b/compat/zlib/contrib/masmx64/inffas8664.c
@@ -1,186 +1,186 @@
-/* inffas8664.c is a hand tuned assembler version of inffast.c - fast decoding

- * version for AMD64 on Windows using Microsoft C compiler

- *

- * 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.

- *

- * 2005 - Adaptation to Microsoft C Compiler for AMD64 by Gilles Vollant

- *

- * inffas8664.c call function inffas8664fnc in inffasx64.asm

- *  inffasx64.asm is automatically convert from AMD64 portion of inffas86.c

- *

- * 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,

- * 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/

- *

- */

-

-#include <stdio.h>

-#include "zutil.h"

-#include "inftrees.h"

-#include "inflate.h"

-#include "inffast.h"

-

-/* Mark Adler's comments from inffast.c: */

-

-/*

-   Decode literal, length, and distance codes and write out the resulting

-   literal and match bytes until either not enough input or output is

-   available, an end-of-block is encountered, or a data error is encountered.

-   When large enough input and output buffers are supplied to inflate(), for

-   example, a 16K input buffer and a 64K output buffer, more than 95% of the

-   inflate execution time is spent in this routine.

-

-   Entry assumptions:

-

-        state->mode == LEN

-        strm->avail_in >= 6

-        strm->avail_out >= 258

-        start >= strm->avail_out

-        state->bits < 8

-

-   On return, state->mode is one of:

-

-        LEN -- ran out of enough output space or enough available input

-        TYPE -- reached end of block code, inflate() to interpret next block

-        BAD -- error in block data

-

-   Notes:

-

-    - The maximum input bits used by a length/distance pair is 15 bits for the

-      length code, 5 bits for the length extra, 15 bits for the distance code,

-      and 13 bits for the distance extra.  This totals 48 bits, or six bytes.

-      Therefore if strm->avail_in >= 6, then there is enough input to avoid

-      checking for available input while decoding.

-

-    - The maximum bytes that a single length/distance pair can output is 258

-      bytes, which is the maximum length that can be coded.  inflate_fast()

-      requires strm->avail_out >= 258 for each loop to avoid checking for

-      output space.

- */

-

-

-

-    typedef struct inffast_ar {

-/* 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 */ size_t /*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*/

-    } type_ar;

-#ifdef ASMINF

-

-void inflate_fast(strm, start)

-z_streamp strm;

-unsigned start;         /* inflate()'s starting value for strm->avail_out */

-{

-    struct inflate_state FAR *state;

-    type_ar ar;

-    void inffas8664fnc(struct inffast_ar * par);

-

-

-

-#if (defined( __GNUC__ ) && defined( __amd64__ ) && ! defined( __i386 )) || (defined(_MSC_VER) && defined(_M_AMD64))

-#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 - PAD_AVAIL_IN);

-    ar.out = strm->next_out;

-    ar.beg = ar.out - (start - strm->avail_out);

-    ar.end = ar.out + (strm->avail_out - PAD_AVAIL_OUT);

-    ar.wsize = state->wsize;

-    ar.write = state->wnext;

-    ar.window = state->window;

-    ar.hold = state->hold;

-    ar.bits = state->bits;

-    ar.lcode = state->lencode;

-    ar.dcode = state->distcode;

-    ar.lmask = (1U << state->lenbits) - 1;

-    ar.dmask = (1U << state->distbits) - 1;

-

-    /* decode literals and length/distances until end-of-block or not enough

-       input data or output space */

-

-    /* align in on 1/2 hold size boundary */

-    while (((size_t)(void *)ar.in & (sizeof(ar.hold) / 2 - 1)) != 0) {

-        ar.hold += (unsigned long)*ar.in++ << ar.bits;

-        ar.bits += 8;

-    }

-

-    inffas8664fnc(&ar);

-

-    if (ar.status > 1) {

-        if (ar.status == 2)

-            strm->msg = "invalid literal/length code";

-        else if (ar.status == 3)

-            strm->msg = "invalid distance code";

-        else

-            strm->msg = "invalid distance too far back";

-        state->mode = BAD;

-    }

-    else if ( ar.status == 1 ) {

-        state->mode = TYPE;

-    }

-

-    /* return unused bytes (on entry, bits < 8, so in won't go too far back) */

-    ar.len = ar.bits >> 3;

-    ar.in -= ar.len;

-    ar.bits -= ar.len << 3;

-    ar.hold &= (1U << ar.bits) - 1;

-

-    /* update state and return */

-    strm->next_in = ar.in;

-    strm->next_out = ar.out;

-    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 = (unsigned long)ar.hold;

-    state->bits = ar.bits;

-    return;

-}

-

-#endif

+/* inffas8664.c is a hand tuned assembler version of inffast.c - fast decoding
+ * version for AMD64 on Windows using Microsoft C compiler
+ *
+ * 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.
+ *
+ * 2005 - Adaptation to Microsoft C Compiler for AMD64 by Gilles Vollant
+ *
+ * inffas8664.c call function inffas8664fnc in inffasx64.asm
+ *  inffasx64.asm is automatically convert from AMD64 portion of inffas86.c
+ *
+ * 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,
+ * 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/
+ *
+ */
+
+#include <stdio.h>
+#include "zutil.h"
+#include "inftrees.h"
+#include "inflate.h"
+#include "inffast.h"
+
+/* Mark Adler's comments from inffast.c: */
+
+/*
+   Decode literal, length, and distance codes and write out the resulting
+   literal and match bytes until either not enough input or output is
+   available, an end-of-block is encountered, or a data error is encountered.
+   When large enough input and output buffers are supplied to inflate(), for
+   example, a 16K input buffer and a 64K output buffer, more than 95% of the
+   inflate execution time is spent in this routine.
+
+   Entry assumptions:
+
+        state->mode == LEN
+        strm->avail_in >= 6
+        strm->avail_out >= 258
+        start >= strm->avail_out
+        state->bits < 8
+
+   On return, state->mode is one of:
+
+        LEN -- ran out of enough output space or enough available input
+        TYPE -- reached end of block code, inflate() to interpret next block
+        BAD -- error in block data
+
+   Notes:
+
+    - The maximum input bits used by a length/distance pair is 15 bits for the
+      length code, 5 bits for the length extra, 15 bits for the distance code,
+      and 13 bits for the distance extra.  This totals 48 bits, or six bytes.
+      Therefore if strm->avail_in >= 6, then there is enough input to avoid
+      checking for available input while decoding.
+
+    - The maximum bytes that a single length/distance pair can output is 258
+      bytes, which is the maximum length that can be coded.  inflate_fast()
+      requires strm->avail_out >= 258 for each loop to avoid checking for
+      output space.
+ */
+
+
+
+    typedef struct inffast_ar {
+/* 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 */ size_t /*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*/
+    } type_ar;
+#ifdef ASMINF
+
+void inflate_fast(strm, start)
+z_streamp strm;
+unsigned start;         /* inflate()'s starting value for strm->avail_out */
+{
+    struct inflate_state FAR *state;
+    type_ar ar;
+    void inffas8664fnc(struct inffast_ar * par);
+
+
+
+#if (defined( __GNUC__ ) && defined( __amd64__ ) && ! defined( __i386 )) || (defined(_MSC_VER) && defined(_M_AMD64))
+#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 - PAD_AVAIL_IN);
+    ar.out = strm->next_out;
+    ar.beg = ar.out - (start - strm->avail_out);
+    ar.end = ar.out + (strm->avail_out - PAD_AVAIL_OUT);
+    ar.wsize = state->wsize;
+    ar.write = state->wnext;
+    ar.window = state->window;
+    ar.hold = state->hold;
+    ar.bits = state->bits;
+    ar.lcode = state->lencode;
+    ar.dcode = state->distcode;
+    ar.lmask = (1U << state->lenbits) - 1;
+    ar.dmask = (1U << state->distbits) - 1;
+
+    /* decode literals and length/distances until end-of-block or not enough
+       input data or output space */
+
+    /* align in on 1/2 hold size boundary */
+    while (((size_t)(void *)ar.in & (sizeof(ar.hold) / 2 - 1)) != 0) {
+        ar.hold += (unsigned long)*ar.in++ << ar.bits;
+        ar.bits += 8;
+    }
+
+    inffas8664fnc(&ar);
+
+    if (ar.status > 1) {
+        if (ar.status == 2)
+            strm->msg = "invalid literal/length code";
+        else if (ar.status == 3)
+            strm->msg = "invalid distance code";
+        else
+            strm->msg = "invalid distance too far back";
+        state->mode = BAD;
+    }
+    else if ( ar.status == 1 ) {
+        state->mode = TYPE;
+    }
+
+    /* return unused bytes (on entry, bits < 8, so in won't go too far back) */
+    ar.len = ar.bits >> 3;
+    ar.in -= ar.len;
+    ar.bits -= ar.len << 3;
+    ar.hold &= (1U << ar.bits) - 1;
+
+    /* update state and return */
+    strm->next_in = ar.in;
+    strm->next_out = ar.out;
+    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 = (unsigned long)ar.hold;
+    state->bits = ar.bits;
+    return;
+}
+
+#endif
diff --git a/compat/zlib/contrib/testzlib/testzlib.c b/compat/zlib/contrib/testzlib/testzlib.c
index 5f659de..8626c92 100644
--- a/compat/zlib/contrib/testzlib/testzlib.c
+++ b/compat/zlib/contrib/testzlib/testzlib.c
@@ -1,275 +1,275 @@
-#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,unsigned char** pFilePtr)

-{

-    FILE* stream;

-    unsigned char* 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;

-}

+#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,unsigned char** pFilePtr)
+{
+    FILE* stream;
+    unsigned char* 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;
+}