cfbblt.c

远程桌面连接工具

		    /* you'd think this would be faster --
		     * a single instruction instead of 6
		     * but measurements show it to be ~15% slower
		     */
		    while ((nl -= 6) >= 0)
		    {
			asm ("moveml %1+,#0x0c0f;moveml#0x0c0f,%0"
			     : "=m" (*(char *)pdst)
			     : "m" (*(char *)psrc)
			     : "d0", "d1", "d2", "d3",
			       "a2", "a3");
			pdst += 6;
		    }
		    nl += 6;
		    while (nl--)
			*pdst++ = *psrc++;
#endif
		    DuffL(nl, label1,
			    *pdst = MROP_SOLID (*psrc, *pdst);
			    pdst++; psrc++;)
#endif

		    if (endmask)
			*pdst = MROP_MASK(*psrc, *pdst, endmask);
		}
	    }
#ifndef DO_UNALIGNED_BITBLT
	    else
	    {
		if (xoffSrc > xoffDst)
		{
#if PSZ == 24
		    leftShift = (xoffSrc - xoffDst) << 3;
#else
#if PGSZ == 32
		    leftShift = (xoffSrc - xoffDst) << (5 - PWSH);
#else /* PGSZ == 64 */
		    leftShift = (xoffSrc - xoffDst) << (6 - PWSH);
#endif /* PGSZ */
#endif
		    rightShift = PGSZ - leftShift;
		}
		else
		{
#if PSZ == 24
		    rightShift = (xoffDst - xoffSrc) << 3;
#else
#if PGSZ == 32
		    rightShift = (xoffDst - xoffSrc) << (5 - PWSH);
#else /* PGSZ == 64 */
		    rightShift = (xoffDst - xoffSrc) << (6 - PWSH);
#endif /* PGSZ */
#endif
		    leftShift = PGSZ - rightShift;
		}
		while (h--)
		{
		    psrc = psrcLine;
		    pdst = pdstLine;
		    pdstLine += widthDst;
		    psrcLine += widthSrc;
		    bits = 0;
		    if (xoffSrc > xoffDst)
			bits = *psrc++;
		    if (startmask)
		    {
			bits1 = BitLeft(bits,leftShift);
			bits = *psrc++;
			bits1 |= BitRight(bits,rightShift);
			*pdst = MROP_MASK(bits1, *pdst, startmask);
			pdst++;
		    }
		    nl = nlMiddle;

#ifdef LARGE_INSTRUCTION_CACHE
		    bits1 = bits;

#ifdef FAST_CONSTANT_OFFSET_MODE

		    psrc += nl & (UNROLL-1);
		    pdst += nl & (UNROLL-1);

#define BodyOdd(n) \
bits = psrc[-n]; \
pdst[-n] = MROP_SOLID(BitLeft(bits1, leftShift) | BitRight(bits, rightShift), pdst[-n]);

#define BodyEven(n) \
bits1 = psrc[-n]; \
pdst[-n] = MROP_SOLID(BitLeft(bits, leftShift) | BitRight(bits1, rightShift), pdst[-n]);

#define LoopReset \
pdst += UNROLL; \
psrc += UNROLL;

#else

#define BodyOdd(n) \
bits = *psrc++; \
*pdst = MROP_SOLID(BitLeft(bits1, leftShift) | BitRight(bits, rightShift), *pdst); \
pdst++;
		   
#define BodyEven(n) \
bits1 = *psrc++; \
*pdst = MROP_SOLID(BitLeft(bits, leftShift) | BitRight(bits1, rightShift), *pdst); \
pdst++;

#define LoopReset   ;

#endif	/* !FAST_CONSTANT_OFFSET_MODE */

		    PackedLoop

#undef BodyOdd
#undef BodyEven
#undef LoopReset

#else
		    DuffL (nl,label2,
			bits1 = BitLeft(bits, leftShift);
			bits = *psrc++;
			*pdst = MROP_SOLID (bits1 | BitRight(bits, rightShift), *pdst);
			pdst++;
		    )
#endif

		    if (endmask)
		    {
			bits1 = BitLeft(bits, leftShift);
			if (BitLeft(endmask, rightShift))
			{
			    bits = *psrc;
			    bits1 |= BitRight(bits, rightShift);
			}
			*pdst = MROP_MASK (bits1, *pdst, endmask);
		    }
		}
	    }
#endif /* DO_UNALIGNED_BITBLT */
	}
#endif /* ! DO_MEMCPY */
	else	/* xdir == -1 */
	{
#if PSZ == 24
	    xoffSrc = (pptSrc->x + w) & 3;
	    xoffDst = pbox->x2 & 3;
	    pdstLine += ((pbox->x2 * 3 - 1) >> 2) + 1;
	    psrcLine += (((pptSrc->x+w) * 3 - 1) >> 2) + 1;
#else
	    xoffSrc = (pptSrc->x + w - 1) & PIM;
	    xoffDst = (pbox->x2 - 1) & PIM;
	    pdstLine += ((pbox->x2-1) >> PWSH) + 1;
	    psrcLine += ((pptSrc->x+w - 1) >> PWSH) + 1;
#endif
#ifdef DO_UNALIGNED_BITBLT
#if PSZ == 24
	    nl = xoffDst - xoffSrc;
#else
	    nl = xoffSrc - xoffDst;
#endif
	    psrcLine = (unsigned long *)
			(((unsigned char *) psrcLine) + nl);
#else
	    if (xoffSrc == xoffDst)
#endif
	    {
		while (h--)
		{
		    psrc = psrcLine;
		    pdst = pdstLine;
		    pdstLine += widthDst;
		    psrcLine += widthSrc;
		    if (endmask)
		    {
			pdst--;
			psrc--;
			*pdst = MROP_MASK (*psrc, *pdst, endmask);
		    }
		    nl = nlMiddle;

#ifdef LARGE_INSTRUCTION_CACHE
#ifdef FAST_CONSTANT_OFFSET_MODE
		    psrc -= nl & (UNROLL - 1);
		    pdst -= nl & (UNROLL - 1);

#define BodyOdd(n) pdst[n-1] = MROP_SOLID (psrc[n-1], pdst[n-1]);

#define BodyEven(n) BodyOdd(n)

#define LoopReset \
pdst -= UNROLL;\
psrc -= UNROLL;

#else

#define BodyOdd(n)  --pdst; --psrc; *pdst = MROP_SOLID(*psrc, *pdst);
#define BodyEven(n) BodyOdd(n)
#define LoopReset   ;

#endif
		    PackedLoop

#undef BodyOdd
#undef BodyEven
#undef LoopReset

#else
		    DuffL(nl,label3,
			 --pdst; --psrc; *pdst = MROP_SOLID (*psrc, *pdst);)
#endif

		    if (startmask)
		    {
			--pdst;
			--psrc;
			*pdst = MROP_MASK(*psrc, *pdst, startmask);
		    }
		}
	    }
#ifndef DO_UNALIGNED_BITBLT
	    else
	    {
		if (xoffDst > xoffSrc)
		{
#if PSZ == 24
		    leftShift = (xoffDst - xoffSrc) << 3;
		    rightShift = PGSZ - leftShift;
#else
#if PGSZ == 32
		    rightShift = (xoffDst - xoffSrc) << (5 - PWSH);
#else /* PGSZ == 64 */
		    rightShift = (xoffDst - xoffSrc) << (6 - PWSH);
#endif /* PGSZ */
		    leftShift = PGSZ - rightShift;
#endif
		}
		else
		{
#if PSZ == 24
		    rightShift = (xoffSrc - xoffDst) << 3;
		    leftShift = PGSZ - rightShift;
#else
#if PGSZ == 32
		    leftShift = (xoffSrc - xoffDst) << (5 - PWSH);
#else /* PGSZ == 64 */
		    leftShift = (xoffSrc - xoffDst) << (6 - PWSH);
#endif /* PGSZ */
		    rightShift = PGSZ - leftShift;
#endif
		}
		while (h--)
		{
		    psrc = psrcLine;
		    pdst = pdstLine;
		    pdstLine += widthDst;
		    psrcLine += widthSrc;
		    bits = 0;
#if PSZ == 24
		    if (xoffSrc > xoffDst)
#else
		    if (xoffDst > xoffSrc)
#endif
			bits = *--psrc;
		    if (endmask)
		    {
			bits1 = BitRight(bits, rightShift);
			bits = *--psrc;
			bits1 |= BitLeft(bits, leftShift);
			pdst--;
			*pdst = MROP_MASK(bits1, *pdst, endmask);
		    }
		    nl = nlMiddle;

#ifdef LARGE_INSTRUCTION_CACHE
		    bits1 = bits;
#ifdef FAST_CONSTANT_OFFSET_MODE
		    psrc -= nl & (UNROLL - 1);
		    pdst -= nl & (UNROLL - 1);

#define BodyOdd(n) \
bits = psrc[n-1]; \
pdst[n-1] = MROP_SOLID(BitRight(bits1, rightShift) | BitLeft(bits, leftShift),pdst[n-1]);

#define BodyEven(n) \
bits1 = psrc[n-1]; \
pdst[n-1] = MROP_SOLID(BitRight(bits, rightShift) | BitLeft(bits1, leftShift),pdst[n-1]);

#define LoopReset \
pdst -= UNROLL; \
psrc -= UNROLL;

#else

#define BodyOdd(n) \
bits = *--psrc; --pdst; \
*pdst = MROP_SOLID(BitRight(bits1, rightShift) | BitLeft(bits, leftShift),*pdst);

#define BodyEven(n) \
bits1 = *--psrc; --pdst; \
*pdst = MROP_SOLID(BitRight(bits, rightShift) | BitLeft(bits1, leftShift),*pdst);

#define LoopReset   ;

#endif

		    PackedLoop

#undef BodyOdd
#undef BodyEven
#undef LoopReset

#else
		    DuffL (nl, label4,
			bits1 = BitRight(bits, rightShift);
			bits = *--psrc;
			--pdst;
			*pdst = MROP_SOLID(bits1 | BitLeft(bits, leftShift),*pdst);
		    )
#endif

		    if (startmask)
		    {
			bits1 = BitRight(bits, rightShift);
			if (BitRight (startmask, leftShift))
			{
			    bits = *--psrc;
			    bits1 |= BitLeft(bits, leftShift);
			}
			--pdst;
			*pdst = MROP_MASK(bits1, *pdst, startmask);
		    }
		}
	    }
#endif
	}
	pbox++;
	pptSrc++;
    }
    if (pboxNew2)
    {
	DEALLOCATE_LOCAL(pptNew2);
	DEALLOCATE_LOCAL(pboxNew2);
    }
    if (pboxNew1)
    {
	DEALLOCATE_LOCAL(pptNew1);
	DEALLOCATE_LOCAL(pboxNew1);
    }
}