打印编程

开发平台：

Visual C++

pngvcrd.c：源码内容

/* pngvcrd.c - mixed C/assembler version of utilities to read a PNG file
*
* For Intel x86 CPU and Microsoft Visual C++ compiler
*
* Last changed in libpng 1.2.6 - August 15, 2004
* For conditions of distribution and use, see copyright notice in png.h
*
* Contributed by Nirav Chhatrapati, Intel Corporation, 1998
* Interface to libpng contributed by Gilles Vollant, 1999
*
*
* In png_do_read_interlace() in libpng versions 1.0.3a through 1.0.4d,
* a sign error in the post-MMX cleanup code for each pixel_depth resulted
* in bad pixels at the beginning of some rows of some images, and also
* (due to out-of-range memory reads and writes) caused heap corruption
* when compiled with MSVC 6.0. The error was fixed in version 1.0.4e.
*
* [png_read_filter_row_mmx_avg() bpp == 2 bugfix, GRR 20000916]
*
* [runtime MMX configuration, GRR 20010102]
*
*/
#define PNG_INTERNAL
#include "png.h"
#if defined(PNG_ASSEMBLER_CODE_SUPPORTED) && defined(PNG_USE_PNGVCRD)
static int mmx_supported=2;
int PNGAPI
png_mmx_support(void)
{
int mmx_supported_local = 0;
_asm {
push ebx //CPUID will trash these
push ecx
push edx
pushfd //Save Eflag to stack
pop eax //Get Eflag from stack into eax
mov ecx, eax //Make another copy of Eflag in ecx
xor eax, 0x200000 //Toggle ID bit in Eflag [i.e. bit(21)]
push eax //Save modified Eflag back to stack
popfd //Restored modified value back to Eflag reg
pushfd //Save Eflag to stack
pop eax //Get Eflag from stack
push ecx // save original Eflag to stack
popfd // restore original Eflag
xor eax, ecx //Compare the new Eflag with the original Eflag
jz NOT_SUPPORTED //If the same, CPUID instruction is not supported,
//skip following instructions and jump to
//NOT_SUPPORTED label
xor eax, eax //Set eax to zero
_asm _emit 0x0f //CPUID instruction (two bytes opcode)
_asm _emit 0xa2
cmp eax, 1 //make sure eax return non-zero value
jl NOT_SUPPORTED //If eax is zero, mmx not supported
xor eax, eax //set eax to zero
inc eax //Now increment eax to 1. This instruction is
//faster than the instruction "mov eax, 1"
_asm _emit 0x0f //CPUID instruction
_asm _emit 0xa2
and edx, 0x00800000 //mask out all bits but mmx bit(24)
cmp edx, 0 // 0 = mmx not supported
jz NOT_SUPPORTED // non-zero = Yes, mmx IS supported
mov mmx_supported_local, 1 //set return value to 1
NOT_SUPPORTED:
mov eax, mmx_supported_local //move return value to eax
pop edx //CPUID trashed these
pop ecx
pop ebx
}
//mmx_supported_local=0; // test code for force don't support MMX
//printf("MMX : %u (1=MMX supported)n",mmx_supported_local);
mmx_supported = mmx_supported_local;
return mmx_supported_local;
}
/* Combines the row recently read in with the previous row.
This routine takes care of alpha and transparency if requested.
This routine also handles the two methods of progressive display
of interlaced images, depending on the mask value.
The mask value describes which pixels are to be combined with
the row. The pattern always repeats every 8 pixels, so just 8
bits are needed. A one indicates the pixel is to be combined; a
zero indicates the pixel is to be skipped. This is in addition
to any alpha or transparency value associated with the pixel. If
you want all pixels to be combined, pass 0xff (255) in mask. */
/* Use this routine for x86 platform - uses faster MMX routine if machine
supports MMX */
void /* PRIVATE */
png_combine_row(png_structp png_ptr, png_bytep row, int mask)
{
#ifdef PNG_USE_LOCAL_ARRAYS
const int png_pass_inc[7] = {8, 8, 4, 4, 2, 2, 1};
#endif
png_debug(1,"in png_combine_row_asmn");
if (mmx_supported == 2) {
#if !defined(PNG_1_0_X)
/* this should have happened in png_init_mmx_flags() already */
png_warning(png_ptr, "asm_flags may not have been initialized");
#endif
png_mmx_support();
}
if (mask == 0xff)
{
png_memcpy(row, png_ptr->row_buf + 1,
(png_size_t)PNG_ROWBYTES(png_ptr->row_info.pixel_depth,
png_ptr->width));
}
/* GRR: add "else if (mask == 0)" case?
* or does png_combine_row() not even get called in that case? */
else
{
switch (png_ptr->row_info.pixel_depth)
{
case 1:
{
png_bytep sp;
png_bytep dp;
int s_inc, s_start, s_end;
int m;
int shift;
png_uint_32 i;
sp = png_ptr->row_buf + 1;
dp = row;
m = 0x80;
#if defined(PNG_READ_PACKSWAP_SUPPORTED)
if (png_ptr->transformations & PNG_PACKSWAP)
{
s_start = 0;
s_end = 7;
s_inc = 1;
}
else
#endif
{
s_start = 7;
s_end = 0;
s_inc = -1;
}
shift = s_start;
for (i = 0; i < png_ptr->width; i++)
{
if (m & mask)
{
int value;
value = (*sp >> shift) & 0x1;
*dp &= (png_byte)((0x7f7f >> (7 - shift)) & 0xff);
*dp |= (png_byte)(value << shift);
}
if (shift == s_end)
{
shift = s_start;
sp++;
dp++;
}
else
shift += s_inc;
if (m == 1)
m = 0x80;
else
m >>= 1;
}
break;
}
case 2:
{
png_bytep sp;
png_bytep dp;
int s_start, s_end, s_inc;
int m;
int shift;
png_uint_32 i;
int value;
sp = png_ptr->row_buf + 1;
dp = row;
m = 0x80;
#if defined(PNG_READ_PACKSWAP_SUPPORTED)
if (png_ptr->transformations & PNG_PACKSWAP)
{
s_start = 0;
s_end = 6;
s_inc = 2;
}
else
#endif
{
s_start = 6;
s_end = 0;
s_inc = -2;
}
shift = s_start;
for (i = 0; i < png_ptr->width; i++)
{
if (m & mask)
{
value = (*sp >> shift) & 0x3;
*dp &= (png_byte)((0x3f3f >> (6 - shift)) & 0xff);
*dp |= (png_byte)(value << shift);
}
if (shift == s_end)
{
shift = s_start;
sp++;
dp++;
}
else
shift += s_inc;
if (m == 1)
m = 0x80;
else
m >>= 1;
}
break;
}
case 4:
{
png_bytep sp;
png_bytep dp;
int s_start, s_end, s_inc;
int m;
int shift;
png_uint_32 i;
int value;
sp = png_ptr->row_buf + 1;
dp = row;
m = 0x80;
#if defined(PNG_READ_PACKSWAP_SUPPORTED)
if (png_ptr->transformations & PNG_PACKSWAP)
{
s_start = 0;
s_end = 4;
s_inc = 4;
}
else
#endif
{
s_start = 4;
s_end = 0;
s_inc = -4;
}
shift = s_start;
for (i = 0; i < png_ptr->width; i++)
{
if (m & mask)
{
value = (*sp >> shift) & 0xf;
*dp &= (png_byte)((0xf0f >> (4 - shift)) & 0xff);
*dp |= (png_byte)(value << shift);
}
if (shift == s_end)
{
shift = s_start;
sp++;
dp++;
}
else
shift += s_inc;
if (m == 1)
m = 0x80;
else
m >>= 1;
}
break;
}
case 8:
{
png_bytep srcptr;
png_bytep dstptr;
png_uint_32 len;
int m;
int diff, unmask;
__int64 mask0=0x0102040810204080;
#if !defined(PNG_1_0_X)
if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_COMBINE_ROW)
/* && mmx_supported */ )
#else
if (mmx_supported)
#endif
{
srcptr = png_ptr->row_buf + 1;
dstptr = row;
m = 0x80;
unmask = ~mask;
len = png_ptr->width &~7; //reduce to multiple of 8
diff = png_ptr->width & 7; //amount lost
_asm
{
movd mm7, unmask //load bit pattern
psubb mm6,mm6 //zero mm6
punpcklbw mm7,mm7
punpcklwd mm7,mm7
punpckldq mm7,mm7 //fill register with 8 masks
movq mm0,mask0
pand mm0,mm7 //nonzero if keep byte
pcmpeqb mm0,mm6 //zeros->1s, v versa
mov ecx,len //load length of line (pixels)
mov esi,srcptr //load source
mov ebx,dstptr //load dest
cmp ecx,0 //lcr
je mainloop8end
mainloop8:
movq mm4,[esi]
pand mm4,mm0
movq mm6,mm0
pandn mm6,[ebx]
por mm4,mm6
movq [ebx],mm4
add esi,8 //inc by 8 bytes processed
add ebx,8
sub ecx,8 //dec by 8 pixels processed
ja mainloop8
mainloop8end:
mov ecx,diff
cmp ecx,0
jz end8
mov edx,mask
sal edx,24 //make low byte the high byte
secondloop8:
sal edx,1 //move high bit to CF
jnc skip8 //if CF = 0
mov al,[esi]
mov [ebx],al
skip8:
inc esi
inc ebx
dec ecx
jnz secondloop8
end8:
emms
}
}
else /* mmx not supported - use modified C routine */
{
register unsigned int incr1, initial_val, final_val;
png_size_t pixel_bytes;
png_uint_32 i;
register int disp = png_pass_inc[png_ptr->pass];
int offset_table[7] = {0, 4, 0, 2, 0, 1, 0};
pixel_bytes = (png_ptr->row_info.pixel_depth >> 3);
srcptr = png_ptr->row_buf + 1 + offset_table[png_ptr->pass]*
pixel_bytes;
dstptr = row + offset_table[png_ptr->pass]*pixel_bytes;
initial_val = offset_table[png_ptr->pass]*pixel_bytes;
final_val = png_ptr->width*pixel_bytes;
incr1 = (disp)*pixel_bytes;
for (i = initial_val; i < final_val; i += incr1)
{
png_memcpy(dstptr, srcptr, pixel_bytes);
srcptr += incr1;
dstptr += incr1;
}
} /* end of else */
break;
} // end 8 bpp
case 16:
{
png_bytep srcptr;
png_bytep dstptr;
png_uint_32 len;
int unmask, diff;
__int64 mask1=0x0101020204040808,
mask0=0x1010202040408080;
#if !defined(PNG_1_0_X)
if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_COMBINE_ROW)
/* && mmx_supported */ )
#else
if (mmx_supported)
#endif
{
srcptr = png_ptr->row_buf + 1;
dstptr = row;
unmask = ~mask;
len = (png_ptr->width)&~7;
diff = (png_ptr->width)&7;
_asm
{
movd mm7, unmask //load bit pattern
psubb mm6,mm6 //zero mm6
punpcklbw mm7,mm7
punpcklwd mm7,mm7
punpckldq mm7,mm7 //fill register with 8 masks
movq mm0,mask0
movq mm1,mask1
pand mm0,mm7
pand mm1,mm7
pcmpeqb mm0,mm6
pcmpeqb mm1,mm6
mov ecx,len //load length of line
mov esi,srcptr //load source
mov ebx,dstptr //load dest
cmp ecx,0 //lcr
jz mainloop16end
mainloop16:
movq mm4,[esi]
pand mm4,mm0
movq mm6,mm0
movq mm7,[ebx]
pandn mm6,mm7
por mm4,mm6
movq [ebx],mm4
movq mm5,[esi+8]
pand mm5,mm1
movq mm7,mm1
movq mm6,[ebx+8]
pandn mm7,mm6
por mm5,mm7
movq [ebx+8],mm5
add esi,16 //inc by 16 bytes processed
add ebx,16
sub ecx,8 //dec by 8 pixels processed
ja mainloop16
mainloop16end:
mov ecx,diff
cmp ecx,0
jz end16
mov edx,mask
sal edx,24 //make low byte the high byte
secondloop16:
sal edx,1 //move high bit to CF
jnc skip16 //if CF = 0
mov ax,[esi]
mov [ebx],ax
skip16:
add esi,2
add ebx,2
dec ecx
jnz secondloop16
end16:
emms
}
}
else /* mmx not supported - use modified C routine */
{
register unsigned int incr1, initial_val, final_val;
png_size_t pixel_bytes;
png_uint_32 i;
register int disp = png_pass_inc[png_ptr->pass];
int offset_table[7] = {0, 4, 0, 2, 0, 1, 0};
pixel_bytes = (png_ptr->row_info.pixel_depth >> 3);
srcptr = png_ptr->row_buf + 1 + offset_table[png_ptr->pass]*
pixel_bytes;
dstptr = row + offset_table[png_ptr->pass]*pixel_bytes;
initial_val = offset_table[png_ptr->pass]*pixel_bytes;
final_val = png_ptr->width*pixel_bytes;
incr1 = (disp)*pixel_bytes;
for (i = initial_val; i < final_val; i += incr1)
{
png_memcpy(dstptr, srcptr, pixel_bytes);
srcptr += incr1;
dstptr += incr1;
}
} /* end of else */
break;
} // end 16 bpp
case 24:
{
png_bytep srcptr;
png_bytep dstptr;
png_uint_32 len;
int unmask, diff;
__int64 mask2=0x0101010202020404, //24bpp
mask1=0x0408080810101020,
mask0=0x2020404040808080;
srcptr = png_ptr->row_buf + 1;
dstptr = row;
unmask = ~mask;
len = (png_ptr->width)&~7;
diff = (png_ptr->width)&7;
#if !defined(PNG_1_0_X)
if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_COMBINE_ROW)
/* && mmx_supported */ )
#else
if (mmx_supported)
#endif
{
_asm
{
movd mm7, unmask //load bit pattern
psubb mm6,mm6 //zero mm6
punpcklbw mm7,mm7
punpcklwd mm7,mm7
punpckldq mm7,mm7 //fill register with 8 masks
movq mm0,mask0
movq mm1,mask1
movq mm2,mask2
pand mm0,mm7
pand mm1,mm7
pand mm2,mm7
pcmpeqb mm0,mm6
pcmpeqb mm1,mm6
pcmpeqb mm2,mm6
mov ecx,len //load length of line
mov esi,srcptr //load source
mov ebx,dstptr //load dest
cmp ecx,0
jz mainloop24end
mainloop24:
movq mm4,[esi]
pand mm4,mm0
movq mm6,mm0
movq mm7,[ebx]
pandn mm6,mm7
por mm4,mm6
movq [ebx],mm4
movq mm5,[esi+8]
pand mm5,mm1
movq mm7,mm1
movq mm6,[ebx+8]
pandn mm7,mm6
por mm5,mm7
movq [ebx+8],mm5
movq mm6,[esi+16]
pand mm6,mm2
movq mm4,mm2
movq mm7,[ebx+16]
pandn mm4,mm7
por mm6,mm4
movq [ebx+16],mm6
add esi,24 //inc by 24 bytes processed
add ebx,24
sub ecx,8 //dec by 8 pixels processed
ja mainloop24
mainloop24end:
mov ecx,diff
cmp ecx,0
jz end24
mov edx,mask
sal edx,24 //make low byte the high byte
secondloop24:
sal edx,1 //move high bit to CF
jnc skip24 //if CF = 0
mov ax,[esi]
mov [ebx],ax
xor eax,eax
mov al,[esi+2]
mov [ebx+2],al
skip24:
add esi,3
add ebx,3
dec ecx
jnz secondloop24
end24:
emms
}
}
else /* mmx not supported - use modified C routine */
{
register unsigned int incr1, initial_val, final_val;
png_size_t pixel_bytes;
png_uint_32 i;
register int disp = png_pass_inc[png_ptr->pass];
int offset_table[7] = {0, 4, 0, 2, 0, 1, 0};
pixel_bytes = (png_ptr->row_info.pixel_depth >> 3);
srcptr = png_ptr->row_buf + 1 + offset_table[png_ptr->pass]*
pixel_bytes;
dstptr = row + offset_table[png_ptr->pass]*pixel_bytes;
initial_val = offset_table[png_ptr->pass]*pixel_bytes;
final_val = png_ptr->width*pixel_bytes;
incr1 = (disp)*pixel_bytes;
for (i = initial_val; i < final_val; i += incr1)
{
png_memcpy(dstptr, srcptr, pixel_bytes);
srcptr += incr1;
dstptr += incr1;
}
} /* end of else */
break;
} // end 24 bpp
case 32:
{
png_bytep srcptr;
png_bytep dstptr;
png_uint_32 len;
int unmask, diff;
__int64 mask3=0x0101010102020202, //32bpp
mask2=0x0404040408080808,
mask1=0x1010101020202020,
mask0=0x4040404080808080;
srcptr = png_ptr->row_buf + 1;
dstptr = row;
unmask = ~mask;
len = (png_ptr->width)&~7;
diff = (png_ptr->width)&7;
#if !defined(PNG_1_0_X)
if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_COMBINE_ROW)
/* && mmx_supported */ )
#else
if (mmx_supported)
#endif
{
_asm
{
movd mm7, unmask //load bit pattern
psubb mm6,mm6 //zero mm6
punpcklbw mm7,mm7
punpcklwd mm7,mm7
punpckldq mm7,mm7 //fill register with 8 masks
movq mm0,mask0
movq mm1,mask1
movq mm2,mask2
movq mm3,mask3
pand mm0,mm7
pand mm1,mm7
pand mm2,mm7
pand mm3,mm7
pcmpeqb mm0,mm6
pcmpeqb mm1,mm6
pcmpeqb mm2,mm6
pcmpeqb mm3,mm6
mov ecx,len //load length of line
mov esi,srcptr //load source
mov ebx,dstptr //load dest
cmp ecx,0 //lcr
jz mainloop32end
mainloop32:
movq mm4,[esi]
pand mm4,mm0
movq mm6,mm0
movq mm7,[ebx]
pandn mm6,mm7
por mm4,mm6
movq [ebx],mm4
movq mm5,[esi+8]
pand mm5,mm1
movq mm7,mm1
movq mm6,[ebx+8]
pandn mm7,mm6
por mm5,mm7
movq [ebx+8],mm5
movq mm6,[esi+16]
pand mm6,mm2
movq mm4,mm2
movq mm7,[ebx+16]
pandn mm4,mm7
por mm6,mm4
movq [ebx+16],mm6
movq mm7,[esi+24]
pand mm7,mm3
movq mm5,mm3
movq mm4,[ebx+24]
pandn mm5,mm4
por mm7,mm5
movq [ebx+24],mm7
add esi,32 //inc by 32 bytes processed
add ebx,32
sub ecx,8 //dec by 8 pixels processed
ja mainloop32
mainloop32end:
mov ecx,diff
cmp ecx,0
jz end32
mov edx,mask
sal edx,24 //make low byte the high byte
secondloop32:
sal edx,1 //move high bit to CF
jnc skip32 //if CF = 0
mov eax,[esi]
mov [ebx],eax
skip32:
add esi,4
add ebx,4
dec ecx
jnz secondloop32
end32:
emms
}
}
else /* mmx _not supported - Use modified C routine */
{
register unsigned int incr1, initial_val, final_val;
png_size_t pixel_bytes;
png_uint_32 i;
register int disp = png_pass_inc[png_ptr->pass];
int offset_table[7] = {0, 4, 0, 2, 0, 1, 0};
pixel_bytes = (png_ptr->row_info.pixel_depth >> 3);
srcptr = png_ptr->row_buf + 1 + offset_table[png_ptr->pass]*
pixel_bytes;
dstptr = row + offset_table[png_ptr->pass]*pixel_bytes;
initial_val = offset_table[png_ptr->pass]*pixel_bytes;
final_val = png_ptr->width*pixel_bytes;
incr1 = (disp)*pixel_bytes;
for (i = initial_val; i < final_val; i += incr1)
{
png_memcpy(dstptr, srcptr, pixel_bytes);
srcptr += incr1;
dstptr += incr1;
}
} /* end of else */
break;
} // end 32 bpp
case 48:
{
png_bytep srcptr;
png_bytep dstptr;
png_uint_32 len;
int unmask, diff;
__int64 mask5=0x0101010101010202,
mask4=0x0202020204040404,
mask3=0x0404080808080808,
mask2=0x1010101010102020,
mask1=0x2020202040404040,
mask0=0x4040808080808080;
#if !defined(PNG_1_0_X)
if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_COMBINE_ROW)
/* && mmx_supported */ )
#else
if (mmx_supported)
#endif
{
srcptr = png_ptr->row_buf + 1;
dstptr = row;
unmask = ~mask;
len = (png_ptr->width)&~7;
diff = (png_ptr->width)&7;
_asm
{
movd mm7, unmask //load bit pattern
psubb mm6,mm6 //zero mm6
punpcklbw mm7,mm7
punpcklwd mm7,mm7
punpckldq mm7,mm7 //fill register with 8 masks
movq mm0,mask0
movq mm1,mask1
movq mm2,mask2
movq mm3,mask3
movq mm4,mask4
movq mm5,mask5
pand mm0,mm7
pand mm1,mm7
pand mm2,mm7
pand mm3,mm7
pand mm4,mm7
pand mm5,mm7
pcmpeqb mm0,mm6
pcmpeqb mm1,mm6
pcmpeqb mm2,mm6
pcmpeqb mm3,mm6
pcmpeqb mm4,mm6
pcmpeqb mm5,mm6
mov ecx,len //load length of line
mov esi,srcptr //load source
mov ebx,dstptr //load dest
cmp ecx,0
jz mainloop48end
mainloop48:
movq mm7,[esi]
pand mm7,mm0
movq mm6,mm0
pandn mm6,[ebx]
por mm7,mm6
movq [ebx],mm7
movq mm6,[esi+8]
pand mm6,mm1
movq mm7,mm1
pandn mm7,[ebx+8]
por mm6,mm7
movq [ebx+8],mm6
movq mm6,[esi+16]
pand mm6,mm2
movq mm7,mm2
pandn mm7,[ebx+16]
por mm6,mm7
movq [ebx+16],mm6
movq mm7,[esi+24]
pand mm7,mm3
movq mm6,mm3
pandn mm6,[ebx+24]
por mm7,mm6
movq [ebx+24],mm7
movq mm6,[esi+32]
pand mm6,mm4
movq mm7,mm4
pandn mm7,[ebx+32]
por mm6,mm7
movq [ebx+32],mm6
movq mm7,[esi+40]
pand mm7,mm5
movq mm6,mm5
pandn mm6,[ebx+40]
por mm7,mm6
movq [ebx+40],mm7
add esi,48 //inc by 32 bytes processed
add ebx,48
sub ecx,8 //dec by 8 pixels processed
ja mainloop48
mainloop48end:
mov ecx,diff
cmp ecx,0
jz end48
mov edx,mask
sal edx,24 //make low byte the high byte
secondloop48:
sal edx,1 //move high bit to CF
jnc skip48 //if CF = 0
mov eax,[esi]
mov [ebx],eax
skip48:
add esi,4
add ebx,4
dec ecx
jnz secondloop48
end48:
emms
}
}
else /* mmx _not supported - Use modified C routine */
{
register unsigned int incr1, initial_val, final_val;
png_size_t pixel_bytes;
png_uint_32 i;
register int disp = png_pass_inc[png_ptr->pass];
int offset_table[7] = {0, 4, 0, 2, 0, 1, 0};
pixel_bytes = (png_ptr->row_info.pixel_depth >> 3);
srcptr = png_ptr->row_buf + 1 + offset_table[png_ptr->pass]*
pixel_bytes;
dstptr = row + offset_table[png_ptr->pass]*pixel_bytes;
initial_val = offset_table[png_ptr->pass]*pixel_bytes;
final_val = png_ptr->width*pixel_bytes;
incr1 = (disp)*pixel_bytes;
for (i = initial_val; i < final_val; i += incr1)
{
png_memcpy(dstptr, srcptr, pixel_bytes);
srcptr += incr1;
dstptr += incr1;
}
} /* end of else */
break;
} // end 48 bpp
default:
{
png_bytep sptr;
png_bytep dp;
png_size_t pixel_bytes;
int offset_table[7] = {0, 4, 0, 2, 0, 1, 0};
unsigned int i;
register int disp = png_pass_inc[png_ptr->pass]; // get the offset
register unsigned int incr1, initial_val, final_val;
pixel_bytes = (png_ptr->row_info.pixel_depth >> 3);
sptr = png_ptr->row_buf + 1 + offset_table[png_ptr->pass]*
pixel_bytes;
dp = row + offset_table[png_ptr->pass]*pixel_bytes;
initial_val = offset_table[png_ptr->pass]*pixel_bytes;
final_val = png_ptr->width*pixel_bytes;
incr1 = (disp)*pixel_bytes;
for (i = initial_val; i < final_val; i += incr1)
{
png_memcpy(dp, sptr, pixel_bytes);
sptr += incr1;
dp += incr1;
}
break;
}
} /* end switch (png_ptr->row_info.pixel_depth) */
} /* end if (non-trivial mask) */
} /* end png_combine_row() */
#if defined(PNG_READ_INTERLACING_SUPPORTED)
void /* PRIVATE */
png_do_read_interlace(png_structp png_ptr)
{
png_row_infop row_info = &(png_ptr->row_info);
png_bytep row = png_ptr->row_buf + 1;
int pass = png_ptr->pass;
png_uint_32 transformations = png_ptr->transformations;
#ifdef PNG_USE_LOCAL_ARRAYS
const int png_pass_inc[7] = {8, 8, 4, 4, 2, 2, 1};
#endif
png_debug(1,"in png_do_read_interlacen");
if (mmx_supported == 2) {
#if !defined(PNG_1_0_X)
/* this should have happened in png_init_mmx_flags() already */
png_warning(png_ptr, "asm_flags may not have been initialized");
#endif
png_mmx_support();
}
if (row != NULL && row_info != NULL)
{
png_uint_32 final_width;
final_width = row_info->width * png_pass_inc[pass];
switch (row_info->pixel_depth)
{
case 1:
{
png_bytep sp, dp;
int sshift, dshift;
int s_start, s_end, s_inc;
png_byte v;
png_uint_32 i;
int j;
sp = row + (png_size_t)((row_info->width - 1) >> 3);
dp = row + (png_size_t)((final_width - 1) >> 3);
#if defined(PNG_READ_PACKSWAP_SUPPORTED)
if (transformations & PNG_PACKSWAP)
{
sshift = (int)((row_info->width + 7) & 7);
dshift = (int)((final_width + 7) & 7);
s_start = 7;
s_end = 0;
s_inc = -1;
}
else
#endif
{
sshift = 7 - (int)((row_info->width + 7) & 7);
dshift = 7 - (int)((final_width + 7) & 7);
s_start = 0;
s_end = 7;
s_inc = 1;
}
for (i = row_info->width; i; i--)
{
v = (png_byte)((*sp >> sshift) & 0x1);
for (j = 0; j < png_pass_inc[pass]; j++)
{
*dp &= (png_byte)((0x7f7f >> (7 - dshift)) & 0xff);
*dp |= (png_byte)(v << dshift);
if (dshift == s_end)
{
dshift = s_start;
dp--;
}
else
dshift += s_inc;
}
if (sshift == s_end)
{
sshift = s_start;
sp--;
}
else
sshift += s_inc;
}
break;
}
case 2:
{
png_bytep sp, dp;
int sshift, dshift;
int s_start, s_end, s_inc;
png_uint_32 i;
sp = row + (png_size_t)((row_info->width - 1) >> 2);
dp = row + (png_size_t)((final_width - 1) >> 2);
#if defined(PNG_READ_PACKSWAP_SUPPORTED)
if (transformations & PNG_PACKSWAP)
{
sshift = (png_size_t)(((row_info->width + 3) & 3) << 1);
dshift = (png_size_t)(((final_width + 3) & 3) << 1);
s_start = 6;
s_end = 0;
s_inc = -2;
}
else
#endif
{
sshift = (png_size_t)((3 - ((row_info->width + 3) & 3)) << 1);
dshift = (png_size_t)((3 - ((final_width + 3) & 3)) << 1);
s_start = 0;
s_end = 6;
s_inc = 2;
}
for (i = row_info->width; i; i--)
{
png_byte v;
int j;
v = (png_byte)((*sp >> sshift) & 0x3);
for (j = 0; j < png_pass_inc[pass]; j++)
{
*dp &= (png_byte)((0x3f3f >> (6 - dshift)) & 0xff);
*dp |= (png_byte)(v << dshift);
if (dshift == s_end)
{
dshift = s_start;
dp--;
}
else
dshift += s_inc;
}
if (sshift == s_end)
{
sshift = s_start;
sp--;
}
else
sshift += s_inc;
}
break;
}
case 4:
{
png_bytep sp, dp;
int sshift, dshift;
int s_start, s_end, s_inc;
png_uint_32 i;
sp = row + (png_size_t)((row_info->width - 1) >> 1);
dp = row + (png_size_t)((final_width - 1) >> 1);
#if defined(PNG_READ_PACKSWAP_SUPPORTED)
if (transformations & PNG_PACKSWAP)
{
sshift = (png_size_t)(((row_info->width + 1) & 1) << 2);
dshift = (png_size_t)(((final_width + 1) & 1) << 2);
s_start = 4;
s_end = 0;
s_inc = -4;
}
else
#endif
{
sshift = (png_size_t)((1 - ((row_info->width + 1) & 1)) << 2);
dshift = (png_size_t)((1 - ((final_width + 1) & 1)) << 2);
s_start = 0;
s_end = 4;
s_inc = 4;
}
for (i = row_info->width; i; i--)
{
png_byte v;
int j;
v = (png_byte)((*sp >> sshift) & 0xf);
for (j = 0; j < png_pass_inc[pass]; j++)
{
*dp &= (png_byte)((0xf0f >> (4 - dshift)) & 0xff);
*dp |= (png_byte)(v << dshift);
if (dshift == s_end)
{
dshift = s_start;
dp--;
}
else
dshift += s_inc;
}
if (sshift == s_end)
{
sshift = s_start;
sp--;
}
else
sshift += s_inc;
}
break;
}
default: // This is the place where the routine is modified
{
__int64 const4 = 0x0000000000FFFFFF;
// __int64 const5 = 0x000000FFFFFF0000; // unused...
__int64 const6 = 0x00000000000000FF;
png_bytep sptr, dp;
png_uint_32 i;
png_size_t pixel_bytes;
int width = row_info->width;
pixel_bytes = (row_info->pixel_depth >> 3);
sptr = row + (width - 1) * pixel_bytes;
dp = row + (final_width - 1) * pixel_bytes;
// New code by Nirav Chhatrapati - Intel Corporation
// sign fix by GRR
// NOTE: there is NO MMX code for 48-bit and 64-bit images
// use MMX routine if machine supports it
#if !defined(PNG_1_0_X)
if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_INTERLACE)
/* && mmx_supported */ )
#else
if (mmx_supported)
#endif
{
if (pixel_bytes == 3)
{
if (((pass == 0) || (pass == 1)) && width)
{
_asm
{
mov esi, sptr
mov edi, dp
mov ecx, width
sub edi, 21 // (png_pass_inc[pass] - 1)*pixel_bytes
loop_pass0:
movd mm0, [esi] ; X X X X X v2 v1 v0
pand mm0, const4 ; 0 0 0 0 0 v2 v1 v0
movq mm1, mm0 ; 0 0 0 0 0 v2 v1 v0
psllq mm0, 16 ; 0 0 0 v2 v1 v0 0 0
movq mm2, mm0 ; 0 0 0 v2 v1 v0 0 0
psllq mm0, 24 ; v2 v1 v0 0 0 0 0 0
psrlq mm1, 8 ; 0 0 0 0 0 0 v2 v1
por mm0, mm2 ; v2 v1 v0 v2 v1 v0 0 0
por mm0, mm1 ; v2 v1 v0 v2 v1 v0 v2 v1
movq mm3, mm0 ; v2 v1 v0 v2 v1 v0 v2 v1
psllq mm0, 16 ; v0 v2 v1 v0 v2 v1 0 0
movq mm4, mm3 ; v2 v1 v0 v2 v1 v0 v2 v1
punpckhdq mm3, mm0 ; v0 v2 v1 v0 v2 v1 v0 v2
movq [edi+16] , mm4
psrlq mm0, 32 ; 0 0 0 0 v0 v2 v1 v0
movq [edi+8] , mm3
punpckldq mm0, mm4 ; v1 v0 v2 v1 v0 v2 v1 v0
sub esi, 3
movq [edi], mm0
sub edi, 24
//sub esi, 3
dec ecx
jnz loop_pass0
EMMS
}
}
else if (((pass == 2) || (pass == 3)) && width)
{
_asm
{
mov esi, sptr
mov edi, dp
mov ecx, width
sub edi, 9 // (png_pass_inc[pass] - 1)*pixel_bytes
loop_pass2:
movd mm0, [esi] ; X X X X X v2 v1 v0
pand mm0, const4 ; 0 0 0 0 0 v2 v1 v0
movq mm1, mm0 ; 0 0 0 0 0 v2 v1 v0
psllq mm0, 16 ; 0 0 0 v2 v1 v0 0 0
movq mm2, mm0 ; 0 0 0 v2 v1 v0 0 0
psllq mm0, 24 ; v2 v1 v0 0 0 0 0 0
psrlq mm1, 8 ; 0 0 0 0 0 0 v2 v1
por mm0, mm2 ; v2 v1 v0 v2 v1 v0 0 0
por mm0, mm1 ; v2 v1 v0 v2 v1 v0 v2 v1
movq [edi+4], mm0 ; move to memory
psrlq mm0, 16 ; 0 0 v2 v1 v0 v2 v1 v0
movd [edi], mm0 ; move to memory
sub esi, 3
sub edi, 12
dec ecx
jnz loop_pass2
EMMS
}
}
else if (width) /* && ((pass == 4) || (pass == 5)) */
{
int width_mmx = ((width >> 1) << 1) - 8;
if (width_mmx < 0)
width_mmx = 0;
width -= width_mmx; // 8 or 9 pix, 24 or 27 bytes
if (width_mmx)
{
_asm
{
mov esi, sptr
mov edi, dp
mov ecx, width_mmx
sub esi, 3
sub edi, 9
loop_pass4:
movq mm0, [esi] ; X X v2 v1 v0 v5 v4 v3
movq mm7, mm0 ; X X v2 v1 v0 v5 v4 v3
movq mm6, mm0 ; X X v2 v1 v0 v5 v4 v3
psllq mm0, 24 ; v1 v0 v5 v4 v3 0 0 0
pand mm7, const4 ; 0 0 0 0 0 v5 v4 v3
psrlq mm6, 24 ; 0 0 0 X X v2 v1 v0
por mm0, mm7 ; v1 v0 v5 v4 v3 v5 v4 v3
movq mm5, mm6 ; 0 0 0 X X v2 v1 v0
psllq mm6, 8 ; 0 0 X X v2 v1 v0 0
movq [edi], mm0 ; move quad to memory
psrlq mm5, 16 ; 0 0 0 0 0 X X v2
pand mm5, const6 ; 0 0 0 0 0 0 0 v2
por mm6, mm5 ; 0 0 X X v2 v1 v0 v2
movd [edi+8], mm6 ; move double to memory
sub esi, 6
sub edi, 12
sub ecx, 2
jnz loop_pass4
EMMS
}
}
sptr -= width_mmx*3;
dp -= width_mmx*6;
for (i = width; i; i--)
{
png_byte v[8];
int j;
png_memcpy(v, sptr, 3);
for (j = 0; j < png_pass_inc[pass]; j++)
{
png_memcpy(dp, v, 3);
dp -= 3;
}
sptr -= 3;
}
}
} /* end of pixel_bytes == 3 */
else if (pixel_bytes == 1)
{
if (((pass == 0) || (pass == 1)) && width)
{
int width_mmx = ((width >> 2) << 2);
width -= width_mmx;
if (width_mmx)
{
_asm
{
mov esi, sptr
mov edi, dp
mov ecx, width_mmx
sub edi, 31
sub esi, 3
loop1_pass0:
movd mm0, [esi] ; X X X X v0 v1 v2 v3
movq mm1, mm0 ; X X X X v0 v1 v2 v3
punpcklbw mm0, mm0 ; v0 v0 v1 v1 v2 v2 v3 v3
movq mm2, mm0 ; v0 v0 v1 v1 v2 v2 v3 v3
punpcklwd mm0, mm0 ; v2 v2 v2 v2 v3 v3 v3 v3
movq mm3, mm0 ; v2 v2 v2 v2 v3 v3 v3 v3
punpckldq mm0, mm0 ; v3 v3 v3 v3 v3 v3 v3 v3
punpckhdq mm3, mm3 ; v2 v2 v2 v2 v2 v2 v2 v2
movq [edi], mm0 ; move to memory v3
punpckhwd mm2, mm2 ; v0 v0 v0 v0 v1 v1 v1 v1
movq [edi+8], mm3 ; move to memory v2
movq mm4, mm2 ; v0 v0 v0 v0 v1 v1 v1 v1
punpckldq mm2, mm2 ; v1 v1 v1 v1 v1 v1 v1 v1
punpckhdq mm4, mm4 ; v0 v0 v0 v0 v0 v0 v0 v0
movq [edi+16], mm2 ; move to memory v1
movq [edi+24], mm4 ; move to memory v0
sub esi, 4
sub edi, 32
sub ecx, 4
jnz loop1_pass0
EMMS
}
}
sptr -= width_mmx;
dp -= width_mmx*8;
for (i = width; i; i--)
{
int j;
/* I simplified this part in version 1.0.4e
* here and in several other instances where
* pixel_bytes == 1 -- GR-P
*
* Original code:
*
* png_byte v[8];
* png_memcpy(v, sptr, pixel_bytes);
* for (j = 0; j < png_pass_inc[pass]; j++)
* {
* png_memcpy(dp, v, pixel_bytes);
* dp -= pixel_bytes;
* }
* sptr -= pixel_bytes;
*
* Replacement code is in the next three lines:
*/
for (j = 0; j < png_pass_inc[pass]; j++)
*dp-- = *sptr;
sptr--;
}
}
else if (((pass == 2) || (pass == 3)) && width)
{
int width_mmx = ((width >> 2) << 2);
width -= width_mmx;
if (width_mmx)
{
_asm
{
mov esi, sptr
mov edi, dp
mov ecx, width_mmx
sub edi, 15
sub esi, 3
loop1_pass2:
movd mm0, [esi] ; X X X X v0 v1 v2 v3
punpcklbw mm0, mm0 ; v0 v0 v1 v1 v2 v2 v3 v3
movq mm1, mm0 ; v0 v0 v1 v1 v2 v2 v3 v3
punpcklwd mm0, mm0 ; v2 v2 v2 v2 v3 v3 v3 v3
punpckhwd mm1, mm1 ; v0 v0 v0 v0 v1 v1 v1 v1
movq [edi], mm0 ; move to memory v2 and v3
sub esi, 4
movq [edi+8], mm1 ; move to memory v1 and v0
sub edi, 16
sub ecx, 4
jnz loop1_pass2
EMMS
}
}
sptr -= width_mmx;
dp -= width_mmx*4;
for (i = width; i; i--)
{
int j;
for (j = 0; j < png_pass_inc[pass]; j++)
{
*dp-- = *sptr;
}
sptr --;
}
}
else if (width) /* && ((pass == 4) || (pass == 5))) */
{
int width_mmx = ((width >> 3) << 3);
width -= width_mmx;
if (width_mmx)
{
_asm
{
mov esi, sptr
mov edi, dp
mov ecx, width_mmx
sub edi, 15
sub esi, 7
loop1_pass4:
movq mm0, [esi] ; v0 v1 v2 v3 v4 v5 v6 v7
movq mm1, mm0 ; v0 v1 v2 v3 v4 v5 v6 v7
punpcklbw mm0, mm0 ; v4 v4 v5 v5 v6 v6 v7 v7
//movq mm1, mm0 ; v0 v0 v1 v1 v2 v2 v3 v3
punpckhbw mm1, mm1 ;v0 v0 v1 v1 v2 v2 v3 v3
movq [edi+8], mm1 ; move to memory v0 v1 v2 and v3
sub esi, 8
movq [edi], mm0 ; move to memory v4 v5 v6 and v7
//sub esi, 4
sub edi, 16
sub ecx, 8
jnz loop1_pass4
EMMS
}
}
sptr -= width_mmx;
dp -= width_mmx*2;
for (i = width; i; i--)
{
int j;
for (j = 0; j < png_pass_inc[pass]; j++)
{
*dp-- = *sptr;
}
sptr --;
}
}
} /* end of pixel_bytes == 1 */
else if (pixel_bytes == 2)
{
if (((pass == 0) || (pass == 1)) && width)
{
int width_mmx = ((width >> 1) << 1);
width -= width_mmx;
if (width_mmx)
{
_asm
{
mov esi, sptr
mov edi, dp
mov ecx, width_mmx
sub esi, 2
sub edi, 30
loop2_pass0:
movd mm0, [esi] ; X X X X v1 v0 v3 v2
punpcklwd mm0, mm0 ; v1 v0 v1 v0 v3 v2 v3 v2
movq mm1, mm0 ; v1 v0 v1 v0 v3 v2 v3 v2
punpckldq mm0, mm0 ; v3 v2 v3 v2 v3 v2 v3 v2
punpckhdq mm1, mm1 ; v1 v0 v1 v0 v1 v0 v1 v0
movq [edi], mm0
movq [edi + 8], mm0
movq [edi + 16], mm1
movq [edi + 24], mm1
sub esi, 4
sub edi, 32
sub ecx, 2
jnz loop2_pass0
EMMS
}
}
sptr -= (width_mmx*2 - 2); // sign fixed
dp -= (width_mmx*16 - 2); // sign fixed
for (i = width; i; i--)
{
png_byte v[8];
int j;
sptr -= 2;
png_memcpy(v, sptr, 2);
for (j = 0; j < png_pass_inc[pass]; j++)
{
dp -= 2;
png_memcpy(dp, v, 2);
}
}
}
else if (((pass == 2) || (pass == 3)) && width)
{
int width_mmx = ((width >> 1) << 1) ;
width -= width_mmx;
if (width_mmx)
{
_asm
{
mov esi, sptr
mov edi, dp
mov ecx, width_mmx
sub esi, 2
sub edi, 14
loop2_pass2:
movd mm0, [esi] ; X X X X v1 v0 v3 v2
punpcklwd mm0, mm0 ; v1 v0 v1 v0 v3 v2 v3 v2
movq mm1, mm0 ; v1 v0 v1 v0 v3 v2 v3 v2
punpckldq mm0, mm0 ; v3 v2 v3 v2 v3 v2 v3 v2
punpckhdq mm1, mm1 ; v1 v0 v1 v0 v1 v0 v1 v0
movq [edi], mm0
sub esi, 4
movq [edi + 8], mm1
//sub esi, 4
sub edi, 16
sub ecx, 2
jnz loop2_pass2
EMMS
}
}
sptr -= (width_mmx*2 - 2); // sign fixed
dp -= (width_mmx*8 - 2); // sign fixed
for (i = width; i; i--)
{
png_byte v[8];
int j;
sptr -= 2;
png_memcpy(v, sptr, 2);
for (j = 0; j < png_pass_inc[pass]; j++)
{
dp -= 2;
png_memcpy(dp, v, 2);
}
}
}
else if (width) // pass == 4 or 5
{
int width_mmx = ((width >> 1) << 1) ;
width -= width_mmx;
if (width_mmx)
{
_asm
{
mov esi, sptr
mov edi, dp
mov ecx, width_mmx
sub esi, 2
sub edi, 6
loop2_pass4:
movd mm0, [esi] ; X X X X v1 v0 v3 v2
punpcklwd mm0, mm0 ; v1 v0 v1 v0 v3 v2 v3 v2
sub esi, 4
movq [edi], mm0
sub edi, 8
sub ecx, 2
jnz loop2_pass4
EMMS
}
}
sptr -= (width_mmx*2 - 2); // sign fixed
dp -= (width_mmx*4 - 2); // sign fixed
for (i = width; i; i--)
{
png_byte v[8];
int j;
sptr -= 2;
png_memcpy(v, sptr, 2);
for (j = 0; j < png_pass_inc[pass]; j++)
{
dp -= 2;
png_memcpy(dp, v, 2);
}
}
}
} /* end of pixel_bytes == 2 */
else if (pixel_bytes == 4)
{
if (((pass == 0) || (pass == 1)) && width)
{
int width_mmx = ((width >> 1) << 1) ;
width -= width_mmx;
if (width_mmx)
{
_asm
{
mov esi, sptr
mov edi, dp
mov ecx, width_mmx
sub esi, 4
sub edi, 60
loop4_pass0:
movq mm0, [esi] ; v3 v2 v1 v0 v7 v6 v5 v4
movq mm1, mm0 ; v3 v2 v1 v0 v7 v6 v5 v4
punpckldq mm0, mm0 ; v7 v6 v5 v4 v7 v6 v5 v4
punpckhdq mm1, mm1 ; v3 v2 v1 v0 v3 v2 v1 v0
movq [edi], mm0
movq [edi + 8], mm0
movq [edi + 16], mm0
movq [edi + 24], mm0
movq [edi+32], mm1
movq [edi + 40], mm1
movq [edi+ 48], mm1
sub esi, 8
movq [edi + 56], mm1
sub edi, 64
sub ecx, 2
jnz loop4_pass0
EMMS
}
}
sptr -= (width_mmx*4 - 4); // sign fixed
dp -= (width_mmx*32 - 4); // sign fixed
for (i = width; i; i--)
{
png_byte v[8];
int j;
sptr -= 4;
png_memcpy(v, sptr, 4);
for (j = 0; j < png_pass_inc[pass]; j++)
{
dp -= 4;
png_memcpy(dp, v, 4);
}
}
}
else if (((pass == 2) || (pass == 3)) && width)
{
int width_mmx = ((width >> 1) << 1) ;
width -= width_mmx;
if (width_mmx)
{
_asm
{
mov esi, sptr
mov edi, dp
mov ecx, width_mmx
sub esi, 4
sub edi, 28
loop4_pass2:
movq mm0, [esi] ; v3 v2 v1 v0 v7 v6 v5 v4
movq mm1, mm0 ; v3 v2 v1 v0 v7 v6 v5 v4
punpckldq mm0, mm0 ; v7 v6 v5 v4 v7 v6 v5 v4
punpckhdq mm1, mm1 ; v3 v2 v1 v0 v3 v2 v1 v0
movq [edi], mm0
movq [edi + 8], mm0
movq [edi+16], mm1
movq [edi + 24], mm1
sub esi, 8
sub edi, 32
sub ecx, 2
jnz loop4_pass2
EMMS
}
}
sptr -= (width_mmx*4 - 4); // sign fixed
dp -= (width_mmx*16 - 4); // sign fixed
for (i = width; i; i--)
{
png_byte v[8];
int j;
sptr -= 4;
png_memcpy(v, sptr, 4);
for (j = 0; j < png_pass_inc[pass]; j++)
{
dp -= 4;
png_memcpy(dp, v, 4);
}
}
}
else if (width) // pass == 4 or 5
{
int width_mmx = ((width >> 1) << 1) ;
width -= width_mmx;
if (width_mmx)
{
_asm
{
mov esi, sptr
mov edi, dp
mov ecx, width_mmx
sub esi, 4
sub edi, 12
loop4_pass4:
movq mm0, [esi] ; v3 v2 v1 v0 v7 v6 v5 v4
movq mm1, mm0 ; v3 v2 v1 v0 v7 v6 v5 v4
punpckldq mm0, mm0 ; v7 v6 v5 v4 v7 v6 v5 v4
punpckhdq mm1, mm1 ; v3 v2 v1 v0 v3 v2 v1 v0
movq [edi], mm0
sub esi, 8
movq [edi + 8], mm1
sub edi, 16
sub ecx, 2
jnz loop4_pass4
EMMS
}
}
sptr -= (width_mmx*4 - 4); // sign fixed
dp -= (width_mmx*8 - 4); // sign fixed
for (i = width; i; i--)
{
png_byte v[8];
int j;
sptr -= 4;
png_memcpy(v, sptr, 4);
for (j = 0; j < png_pass_inc[pass]; j++)
{
dp -= 4;
png_memcpy(dp, v, 4);
}
}
}
} /* end of pixel_bytes == 4 */
else if (pixel_bytes == 6)
{
for (i = width; i; i--)
{
png_byte v[8];
int j;
png_memcpy(v, sptr, 6);
for (j = 0; j < png_pass_inc[pass]; j++)
{
png_memcpy(dp, v, 6);
dp -= 6;
}
sptr -= 6;
}
} /* end of pixel_bytes == 6 */
else
{
for (i = width; i; i--)
{
png_byte v[8];
int j;
png_memcpy(v, sptr, pixel_bytes);
for (j = 0; j < png_pass_inc[pass]; j++)
{
png_memcpy(dp, v, pixel_bytes);
dp -= pixel_bytes;
}
sptr-= pixel_bytes;
}
}
} /* end of mmx_supported */
else /* MMX not supported: use modified C code - takes advantage
* of inlining of memcpy for a constant */
{
if (pixel_bytes == 1)
{
for (i = width; i; i--)
{
int j;
for (j = 0; j < png_pass_inc[pass]; j++)
*dp-- = *sptr;
sptr--;
}
}
else if (pixel_bytes == 3)
{
for (i = width; i; i--)
{
png_byte v[8];
int j;
png_memcpy(v, sptr, pixel_bytes);
for (j = 0; j < png_pass_inc[pass]; j++)
{
png_memcpy(dp, v, pixel_bytes);
dp -= pixel_bytes;
}
sptr -= pixel_bytes;
}
}
else if (pixel_bytes == 2)
{
for (i = width; i; i--)
{
png_byte v[8];
int j;
png_memcpy(v, sptr, pixel_bytes);
for (j = 0; j < png_pass_inc[pass]; j++)
{
png_memcpy(dp, v, pixel_bytes);
dp -= pixel_bytes;
}
sptr -= pixel_bytes;
}
}
else if (pixel_bytes == 4)
{
for (i = width; i; i--)
{
png_byte v[8];
int j;
png_memcpy(v, sptr, pixel_bytes);
for (j = 0; j < png_pass_inc[pass]; j++)
{
png_memcpy(dp, v, pixel_bytes);
dp -= pixel_bytes;
}
sptr -= pixel_bytes;
}
}
else if (pixel_bytes == 6)
{
for (i = width; i; i--)
{
png_byte v[8];
int j;
png_memcpy(v, sptr, pixel_bytes);
for (j = 0; j < png_pass_inc[pass]; j++)
{
png_memcpy(dp, v, pixel_bytes);
dp -= pixel_bytes;
}
sptr -= pixel_bytes;
}
}
else
{
for (i = width; i; i--)
{
png_byte v[8];
int j;
png_memcpy(v, sptr, pixel_bytes);
for (j = 0; j < png_pass_inc[pass]; j++)
{
png_memcpy(dp, v, pixel_bytes);
dp -= pixel_bytes;
}
sptr -= pixel_bytes;
}
}
} /* end of MMX not supported */
break;
}
} /* end switch (row_info->pixel_depth) */
row_info->width = final_width;
row_info->rowbytes = PNG_ROWBYTES(row_info->pixel_depth,final_width);
}
}
#endif /* PNG_READ_INTERLACING_SUPPORTED */
// These variables are utilized in the functions below. They are declared
// globally here to ensure alignment on 8-byte boundaries.
union uAll {
__int64 use;
double align;
} LBCarryMask = {0x0101010101010101},
HBClearMask = {0x7f7f7f7f7f7f7f7f},
ActiveMask, ActiveMask2, ActiveMaskEnd, ShiftBpp, ShiftRem;
// Optimized code for PNG Average filter decoder
void /* PRIVATE */
png_read_filter_row_mmx_avg(png_row_infop row_info, png_bytep row
, png_bytep prev_row)
{
int bpp;
png_uint_32 FullLength;
png_uint_32 MMXLength;
//png_uint_32 len;
int diff;
bpp = (row_info->pixel_depth + 7) >> 3; // Get # bytes per pixel
FullLength = row_info->rowbytes; // # of bytes to filter
_asm {
// Init address pointers and offset
mov edi, row // edi ==> Avg(x)
xor ebx, ebx // ebx ==> x
mov edx, edi
mov esi, prev_row // esi ==> Prior(x)
sub edx, bpp // edx ==> Raw(x-bpp)
xor eax, eax
// Compute the Raw value for the first bpp bytes
// Raw(x) = Avg(x) + (Prior(x)/2)
davgrlp:
mov al, [esi + ebx] // Load al with Prior(x)