可能是最快的算法alpha blend汇编源代码，Intel官方提供

51testing

Intel官方网站有一个ablend_565的快速汇编算法，理论上是是把一块32bit RGBA渲染到16bit的buffer上，我的机器是PIII800,函数在system menory中进行，640*480的256级alpha blending，达到100fps，我想可以满足绝大部分的要求了，在这里，我提供了这个算法的应用，希望可以对大家有所帮助。
ablend_565函数，源代码可以直接编译使用，无需其他库函数，感谢intel提供这么好的东西。
首先，我提供一些本人编写的把32bit tga文件读入pRGBABuffer的函数
文件尺寸保存在 width,height
//-----------------------------------------------------------------------
// Name: LoadTgaFile( TCHAR* strPathname, DWORD** pRGBABuffer, long* width, long* height )
// Desc: 读取32bit tga文件到DWORD缓冲里，返回其尺寸
// Time: 2002.06.22 00:36
// Author: RealRender
// Para:
// Return:
// Note: 这段代码来自directx 7.0 sample中的d3dtextr.cpp，我把他提取了出来
// 方便使用
//-----------------------------------------------------------------------
BOOL LoadTgaFile( TCHAR* strPathname, DWORD** pRGBABuffer, long* width, long* height )
{
    FILE* file = fopen( strPathname, "rb" );
    if( NULL == file )
    return false;
    struct TargaHeader
    {
        BYTE IDLength;
        BYTE ColormapType;
        BYTE ImageType;
        BYTE ColormapSpecification[5];
        WORD XOrigin;
        WORD YOrigin;
        WORD ImageWidth;
        WORD ImageHeight;
        BYTE PixelDepth;
        BYTE ImageDescriptor;
    } tga;
    fread( &tga, sizeof(TargaHeader), 1, file );
    // Only true color, non-mapped images are supported
    if( ( 0 != tga.ColormapType ) ||
        ( tga.ImageType != 10 && tga.ImageType != 2 ) )
    {
        fclose( file );
        return false;
    }
    // Skip the ID field. The first byte of the header is the length of this field
    if( tga.IDLength )
        fseek( file, tga.IDLength, SEEK_CUR );
    DWORD m_dwWidth = tga.ImageWidth;
    DWORD m_dwHeight = tga.ImageHeight;
    DWORD m_dwBPP = tga.PixelDepth;
    DWORD *m_pRGBAData = new DWORD[m_dwWidth*m_dwHeight];
    if( m_pRGBAData == NULL )
    {
        fclose(file);
        return false;
    }
    for( DWORD y=0; y<m_dwHeight; y++ )
    {
        DWORD dwOffset = y*m_dwWidth;
        if( 0 == ( tga.ImageDescriptor & 0x0010 ) )
            dwOffset = (m_dwHeight-y-1)*m_dwWidth;
        for( DWORD x=0; x<m_dwWidth; x )
        {
            if( tga.ImageType == 10 )
            {
                BYTE PacketInfo = getc( file );
                WORD PacketType = 0x80 & PacketInfo;
                WORD PixelCount = ( 0x007f & PacketInfo ) + 1;
                if( PacketType )
                {
                    DWORD b = getc( file );
                    DWORD g = getc( file );
                    DWORD r = getc( file );
                    DWORD a = 0xff;
                    if( m_dwBPP == 32 )
                        a = getc( file );
                    while( PixelCount-- )
                    {
                        m_pRGBAData[dwOffset+x] = (r<<24L)+(g<<16L)+(b<<8L)+(a);
                        x++;
                    }
                }
                else
                {
                    while( PixelCount-- )
                    {
                        BYTE b = getc( file );
                        BYTE g = getc( file );
                        BYTE r = getc( file );
                        BYTE a = 0xff;
                        if( m_dwBPP == 32 )
                        a = getc( file );
                        m_pRGBAData[dwOffset+x] = (r<<24L)+(g<<16L)+(b<<8L)+(a);
                        x++;
                    }
                }
            }
            else
            {
                BYTE b = getc( file );
                BYTE g = getc( file );
                BYTE r = getc( file );
                BYTE a = 0xff;
                if( m_dwBPP == 32 )
                    a = getc( file );
                m_pRGBAData[dwOffset+x] = (r<<24L)+(g<<16L)+(b<<8L)+(a);
                x++;
            }
        }
    }
    fclose( file );
    // Check for alpha content
    for( DWORD i=0; i<(m_dwWidth*m_dwHeight); i++ )
    {
        if( m_pRGBAData & 0x000000ff != 0xff )
        {
            //m_bHasAlpha = TRUE;
            break;
        }
    }
    *pRGBABuffer = m_pRGBAData;
    *width = m_dwWidth;
    *height = m_dwHeight;
    return true;
}
把32bit buffer分割为rgb和alpha的代码。
注意，分割后的pBitmap一定要是8字节对齐，这是优化的一个重要条件，所以，我的算法中：
BYTE* p = new BYTE[lSize*2+8];
BYTE* pOrig = p;
p += (DWORD)p%8;
WORD* color = (WORD*)p;
这是不规范的写法，把指针强行改变为8位对齐，实际使用的时候，要记住释放的原始指针不是p，而是pOrig，在这里，我没有释放分配的内存，请谅解。
//-----------------------------------------------------------------------
// Name: SplitRGBA( DWORD* pRGBABuffer, LPBYTE* pAlpha, LPWORD* pBitmap, long lWidth, long lHeight )
// Desc:
// Time: 2002.06.22 00:36
// Author: RealRender
// Para:
// Return:
// Note: 把从32bit的缓冲建立16bit的565缓冲和8bit的alpha通道
//-----------------------------------------------------------------------
void SplitRGBA( DWORD* pRGBABuffer, LPBYTE* pAlpha, LPWORD* pBitmap, long lWidth, long lHeight )
{
    long lSize = lWidth*lHeight;
    BYTE* alpha = new BYTE[lSize];
    BYTE* p = new BYTE[lSize*2+8];
    // 强行转换为8字节对齐
    p += (DWORD)p%8;
    WORD* color = (WORD*)p;
    DWORD dwPixel;
    DWORD r, g, b, a;
    for( int i = 0; i < lSize; i++ )
    {
        dwPixel = pRGBABuffer;
        r = ((dwPixel>>24)&0x000000ff);
        g = ((dwPixel>>16)&0x000000ff);
        b = ((dwPixel>> 8)&0x000000ff);
        a = ((dwPixel>> 0)&0x000000ff);
        alpha = a;
        // 888i转化为565
        color = RGBTo16( r, g, b );
    }
    *pAlpha = alpha;
    *pBitmap = color;
}
//
这个视intel官方提供的函数，函数的描述，用我的话来说就是把一个带有256级alpha通道的565颜色数据绘制到16位目标页面。
函数说明：
unsigned char *lpAlpha, // 256 级alpha通道
unsigned int iAlpPitch, // alpha通道的pitch
unsigned char *lpSrc, // 原色彩缓冲
unsigned int iSrcX, //
unsigned int iSrcY, // 原色彩位置
unsigned int iSrcPitch, // 原色彩pitch
unsigned char *lpDst, // 目标缓冲
unsigned int iDstX,
unsigned int iDstY, // 目标位置
unsigned int iDstW,
unsigned int iDstH, // 目标缓冲的尺寸
unsigned int iDstPitch // 目标缓冲的pitch
void ablend_565(unsigned char *lpAlpha,unsigned int iAlpPitch,
unsigned char *lpSrc,unsigned int iSrcX, unsigned int iSrcY,
unsigned int iSrcPitch, unsigned char *lpDst,
unsigned int iDstX, unsigned int iDstY,
unsigned int iDstW, unsigned int iDstH,
unsigned int iDstPitch)
{
//Mask for isolating the red,green, and blue components
static __int64 MASKB=0x001F001F001F001F;
static __int64 MASKG=0x07E007E007E007E0;
static __int64 MASKSHIFTG=0x03F003F003F003F0;
static __int64 MASKR=0xF800F800F800F800;
//constants used by the integer alpha blending equation
static __int64 SIXTEEN=0x0010001000100010;
static __int64 FIVETWELVE=0x0200020002000200;
static __int64 SIXONES=0x003F003F003F003F;
unsigned char *lpLinearDstBp=(iDstX<<1)+(iDstY*iDstPitch)+lpDst; //base pointer for linear destination
unsigned char *lpLinearSrcBp=(iSrcX<<1)+(iSrcY*iSrcPitch)+lpSrc; //base pointer for linear source
unsigned char *lpLinearAlpBp=iSrcX+(iSrcY*iAlpPitch)+lpAlpha; //base pointer for linear alpha
_asm{
mov esi,lpLinearSrcBp; //src
mov edi,lpLinearDstBp; //dst
mov eax,lpLinearAlpBp; //alpha
mov ecx,iDstH; //ecx=number of lines to copy
mov ebx,iDstW; //ebx=span width to copy
test esi,6; //check if source address is qword aligned
//since addr coming in is always word aligned(16bit)
jnz done; //if not qword aligned we don't do anything
primeloop:
movd mm1,[eax]; //mm1=00 00 00 00 a3 a2 a1 a0
pxor mm2,mm2; //mm2=0;
movq mm4,[esi]; //g1: mm4=src3 src2 src1 src0
punpcklbw mm1,mm2; //mm1=00a3 00a2 00a1 00a0
loopqword:
mov edx,[eax];
test ebx,0xFFFFFFFC; //check if only 3 pixels left
jz checkback; //3 or less pixels left
//early out tests
cmp edx,0xffffffff; //test for alpha value of 1
je copyback; //if 1's copy the source pixels to the destination
test edx,0xffffffff; //test for alpha value of 0
jz leavefront; //if so go to the next 4 pixels
//the alpha blend starts
//green
//i=a*sg+(63-a)*dg;
//i=(i+32)+((i+32)>>6)>>6;
//red
//i=a*sr+(31-a)*dr;
//i=(i+16)+((i+16)>>5)>>5;
movq mm5,[edi]; //g2: mm5=dst3 dst2 dst1 dst0
psrlw mm1,2; //mm1=a?>>2 nuke out lower 2 bits
movq mm7,MASKSHIFTG; //g3: mm7=1 bit shifted green mask
psrlw mm4,1; //g3a: move src green down by 1 so that we won't overflow
movq mm0,mm1; //mm0=00a3 00a2 00a1 00a0
psrlw mm5,1; //g3b: move dst green down by 1 so that we won't overflow
psrlw mm1,1; //mm1=a?>>1 nuke out lower 1 bits
pand mm4,mm7; //g5: mm4=sg3 sg2 sg1 sg0
movq mm2,SIXONES;//g4: mm2=63
pand mm5,mm7; //g7: mm5=dg3 dg2 dg1 dg0
movq mm3,[esi]; //b1: mm3=src3 src2 src1 src0
psubsb mm2,mm0; //g6: mm2=63-a3 63-a2 63-a1 63-a0
movq mm7,MASKB; //b2: mm7=BLUE MASK
pmullw mm4,mm0; //g8: mm4=sg?*a?
movq mm0,[edi]; //b3: mm0=dst3 dst2 dst1 dst0
pmullw mm5,mm2; //g9: mm5=dg?*(1-a?)
movq mm2,mm7; //b4: mm2=fiveones
pand mm3,mm7; //b4: mm3=sb3 sb2 sb1 sb0
pmullw mm3,mm1; //b6: mm3=sb?*a?
pand mm0,mm7; //b5: mm0=db3 db2 db1 db0
movq mm7,[esi]; //r1: mm7=src3 src2 src1 src0
paddw mm4,mm5; //g10: mm4=sg?*a?+dg?*(1-a?)
pand mm7,MASKR; //r2: mm7=sr3 sr2 sr1 sr0　
psubsb mm2,mm1; //b5a: mm2=31-a3 31-a2 31-a1 31-a0
paddw mm4,FIVETWELVE; //g11: mm4=(mm4+512) green
pmullw mm0,mm2; //b7: mm0=db?*(1-a?)
movq mm5,mm4; //g12: mm5=mm4 green
psrlw mm7,11; //r4: shift src red down to position 0
psrlw mm4,6; //g13: mm4=mm4>>6
paddw mm4,mm5; //g14: mm4=mm4+mm5 green
paddw mm0,mm3; //b8: mm0=sb?*a?+db?*(1-a?)
movq mm5,[edi]; //r3: mm5=dst3 dst2 dst1 dst0
paddw mm0,SIXTEEN; //b9: mm0=(mm0+16) blue
pand mm5,MASKR; //r5: mm5=dr3 dr2 dr1 dr0
psrlw mm4,5; //g15: mm4=0?g0 0?g0 0?g0 0?g0 green
movq mm3,mm0; //b10: mm3=mm0 blue
psrlw mm0,5; //b11: mm0=mm0>>5 blue
psrlw mm5,11; //r6: shift dst red down to position 0
paddw mm0,mm3; //b12: mm0=mm3+mm0 blue
psrlw mm0,5; //b13: mm0=000b 000b 000b 000b blue
pmullw mm7,mm1; //mm7=sr?*a?
pand mm4,MASKG; //g16: mm4=00g0 00g0 00g0 00g0 green
pmullw mm5,mm2; //r7: mm5=dr?*(31-a?)
por mm0,mm4; //mm0=00gb 00gb 00gb 00gb
add eax,4; //move to next 4 alphas
add esi,8; //move to next 4 pixels in src
add edi,8; //move to next 4 pixels in dst
movd mm1,[eax]; //mm1=00 00 00 00 a3 a2 a1 a0
paddw mm5,mm7; //r8: mm5=sr?*a?+dr?*(31-a?)
paddw mm5,SIXTEEN; //r9: mm5=(mm5+16) red
pxor mm2,mm2; //mm2=0;
movq mm7,mm5; //r10: mm7=mm5 red
psrlw mm5,5; //r11: mm5=mm5>>5 red
movq mm4,[esi]; //g1: mm4=src3 src2 src1 src0
paddw mm5,mm7; //r12: mm5=mm7+mm5 red
punpcklbw mm1,mm2; //mm1=00a3 00a2 00a1 00a0
psrlw mm5,5; //r13: mm5=mm5>>5 red
psllw mm5,11; //r14: mm5=mm5<<10 red
por mm0,mm5; //mm0=0rgb 0rgb 0rgb 0rgb
sub ebx,4; //polished off 4 pixels
movq [edi-8],mm0; //dst=0rgb 0rgb 0rgb 0rgb
jmp loopqword; //go back to start
copyback:
movq [edi],mm4; //copy source to destination
leavefront:
add edi,8; //advance destination by 4 pixels
add eax,4; //advance alpha by 4
add esi,8; //advance source by 4 pixels
sub ebx,4; //decrease pixel count by 4
jmp primeloop;
checkback:
test ebx,0xFF; //check if 0 pixels left
jz nextline; //done with this span
//backalign: //work out back end pixels
movq mm5,[edi]; //g2: mm5=dst3 dst2 dst1 dst0
psrlw mm1,2; //mm1=a?>>2 nuke out lower 2 bits
movq mm7,MASKSHIFTG; //g3: mm7=shift 1 bit green mask
psrlw mm4,1; //g3a: move src green down by 1 so that we won't overflow
movq mm0,mm1; //mm0=00a3 00a2 00a1 00a0
psrlw mm5,1; //g3b: move dst green down by 1 so that we won't overflow
psrlw mm1,1; //mm1=a?>>1 nuke out lower 1 bits
pand mm4,mm7; //g5: mm4=sg3 sg2 sg1 sg0
movq mm2,SIXONES;//g4: mm2=63
pand mm5,mm7; //g7: mm5=dg3 dg2 dg1 dg0
movq mm3,[esi]; //b1: mm3=src3 src2 src1 src0
psubsb mm2,mm0; //g6: mm2=63-a3 63-a2 63-a1 63-a0
movq mm7,MASKB; //b2: mm7=BLUE MASK
pmullw mm4,mm0; //g8: mm4=sg?*a?
movq mm0,[edi]; //b3: mm0=dst3 dst2 dst1 dst0
pmullw mm5,mm2; //g9: mm5=dg?*(1-a?)
movq mm2,mm7; //b4: mm2=fiveones
pand mm3,mm7; //b4: mm3=sr3 sr2 sr1 sr0
pmullw mm3,mm1; //b6: mm3=sb?*a?
pand mm0,mm7; //b5: mm0=db3 db2 db1 db0
movq mm7,[esi]; //r1: mm7=src3 src2 src1 src0
paddw mm4,mm5; //g10: mm4=sg?*a?+dg?*(1-a?)
pand mm7,MASKR; //r2: mm7=sr3 sr2 sr1 sr0
psubsb mm2,mm1; //b5a: mm2=31-a3 31-a2 31-a1 31-a0
paddw mm4,FIVETWELVE; //g11: mm4=(i+512) green
pmullw mm0,mm2; //b7: mm0=db?*(1-a?)
movq mm5,mm4; //g12: mm5=(i+512) green
psrlw mm7,11; //r4: shift src red down to position 0
psrlw mm4,6; //g13: mm4=(i+512)>>6
paddw mm4,mm5; //g14: mm4=(i+512)+((i+512)>>6) green
paddw mm0,mm3; //b8: mm0=sb?*a?+db?*(1-a?)
movq mm5,[edi]; //r3: mm5=dst3 dst2 dst1 dst0
paddw mm0,SIXTEEN; //b9: mm0=(i+16) blue
pand mm5,MASKR; //r5: mm5=dr3 dr2 dr1 dr0
psrlw mm4,5; //g15: mm4=0?g0 0?g0 0?g0 0?g0 green
movq mm3,mm0; //b10: mm3=(i+16) blue
psrlw mm0,5; //b11: mm0=(i+16)>>5 blue
psrlw mm5,11; //r6: shift dst red down to position 0
paddw mm0,mm3; //b12: mm0=(i+16)+(i+16)>>5 blue
psrlw mm0,5; //b13: mm0=000r 000r 000r 000r blue
pmullw mm7,mm1; //mm7=sr?*a?
pand mm4,MASKG; //g16: mm4=00g0 00g0 00g0 00g0 green
pmullw mm5,mm2; //r7: mm5=dr?*(31-a?)
por mm0,mm4; //mm0=00gb 00gb 00gb 00gb
add eax,4; //move to next 4 alphas
//stall
paddw mm5,mm7; //r8: mm5=sr?*a?+dr?*(31-a?)
paddw mm5,SIXTEEN; //r9: mm5=(i+16) red
movq mm7,mm5; //r10: mm7=(i+16) red
psrlw mm5,5; //r11: mm5=(i+16)>>5 red
paddw mm5,mm7; //r12: mm5=(i+16)+((i+16)>>5) red
psrlw mm5,5; //r13: mm5=(i+16)+((i+16)>>5)>>5 red
psllw mm5,11; //r14: mm5=mm5<<10 red
por mm0,mm5; //mm0=0rgb 0rgb 0rgb 0rgb
test ebx,2; //check if there are 2 pixels
jz oneendpixel; //goto one pixel if that's it
movd [edi],mm0; //dst=0000 0000 0rgb 0rgb
psrlq mm0,32; //mm0>>32
add edi,4; //edi=edi+4
sub ebx,2; //saved 2 pixels
jz nextline; //all done goto next line
oneendpixel: //work on last pixel
movd edx,mm0; //edx=0rgb
mov [edi],dx; //dst=0rgb
nextline: //goto next line
dec ecx; //nuke one line
jz done; //all done
mov eax,lpLinearAlpBp; //alpha
mov esi,lpLinearSrcBp; //src
mov edi,lpLinearDstBp; //dst
add eax,iAlpPitch; //inc alpha ptr by 1 line
add esi,iSrcPitch; //inc src ptr by 1 line
add edi,iDstPitch; //inc dst ptr by 1 line
mov lpLinearAlpBp,eax; //save new alpha base ptr
mov ebx,iDstW; //ebx=span width to copy
mov lpLinearSrcBp,esi; //save new src base ptr
mov lpLinearDstBp,edi; //save new dst base ptr
jmp primeloop; //start the next span
done:
emms
}
}