simple_idct_mmx.c

来自「这是著名的TCPMP播放器在WINDWOWS,和WINCE下编译通过的源程序.笔」· C语言 代码 · 共 1,315 行 · 第 1/4 页

C
1,315 行
字号
1234
	"pmaddwd 104(%2), %%mm3			\n\t" /* -C1R7+C3R5	-C1r7+C3r5 */\
	"paddd %%mm7, %%mm4			\n\t" /* B2		b2 */\
	"paddd %%mm4, %%mm2			\n\t" /* A2+B2		a2+b2 */\
	"psubd %%mm4, %%mm5			\n\t" /* a2-B2		a2-b2 */\
	"psrad $" #shift ", %%mm2		\n\t"\
	"psrad $" #shift ", %%mm5		\n\t"\
	"movq %%mm6, %%mm4			\n\t" /* A3		a3 */\
	"paddd %%mm0, %%mm3			\n\t" /* B3		b3 */\
	"paddd %%mm3, %%mm6			\n\t" /* A3+B3		a3+b3 */\
	"psubd %%mm3, %%mm4			\n\t" /* a3-B3		a3-b3 */\
	"psrad $" #shift ", %%mm6		\n\t"\
	"psrad $" #shift ", %%mm4		\n\t"\
	"packssdw %%mm2, %%mm2			\n\t" /* A2+B2	a2+b2 */\
	"packssdw %%mm6, %%mm6			\n\t" /* A3+B3	a3+b3 */\
	"movd %%mm2, 32+" #dst "		\n\t"\
	"packssdw %%mm4, %%mm4			\n\t" /* A3-B3	a3-b3 */\
	"packssdw %%mm5, %%mm5			\n\t" /* A2-B2	a2-b2 */\
	"movd %%mm6, 48+" #dst "		\n\t"\
	"movd %%mm4, 64+" #dst "		\n\t"\
	"movd %%mm5, 80+" #dst "		\n\t"

//IDCT(  src0,   src4,   src1,    src5,    dst, rounder, shift)
IDCT(    (%1), 64(%1), 32(%1),  96(%1),  0(%0),/nop, 20)
IDCT(   8(%1), 72(%1), 40(%1), 104(%1),  4(%0),/nop, 20)
IDCT(  16(%1), 80(%1), 48(%1), 112(%1),  8(%0),/nop, 20)
IDCT(  24(%1), 88(%1), 56(%1), 120(%1), 12(%0),/nop, 20)
	"jmp 9f					\n\t"

	"#.balign 16				\n\t"\
	"3:					\n\t"
#undef IDCT
#define IDCT(src0, src4, src1, src5, dst, rounder, shift) \
	"movq " #src0 ", %%mm0			\n\t" /* R4	R0	r4	r0 */\
	"movq " #src1 ", %%mm2			\n\t" /* R3	R1	r3	r1 */\
	"movq 16(%2), %%mm4			\n\t" /* C4	C4	C4	C4 */\
	"pmaddwd %%mm0, %%mm4			\n\t" /* C4R4+C4R0	C4r4+C4r0 */\
	"movq 24(%2), %%mm5			\n\t" /* -C4	C4	-C4	C4 */\
	"pmaddwd %%mm5, %%mm0			\n\t" /* -C4R4+C4R0	-C4r4+C4r0 */\
	#rounder ", %%mm4			\n\t"\
	"movq %%mm4, %%mm6			\n\t" /* C4R4+C4R0	C4r4+C4r0 */\
	"movq 48(%2), %%mm7			\n\t" /* C3	C1	C3	C1 */\
	#rounder ", %%mm0			\n\t"\
	"pmaddwd %%mm2, %%mm7			\n\t" /* C3R3+C1R1	C3r3+C1r1 */\
	"movq %%mm0, %%mm5			\n\t" /* -C4R4+C4R0	-C4r4+C4r0 */\
	"movq 64(%2), %%mm3			\n\t"\
	"pmaddwd %%mm2, %%mm3			\n\t" /* -C7R3+C3R1	-C7r3+C3r1 */\
	"paddd %%mm4, %%mm7			\n\t" /* A0+B0		a0+b0 */\
	"paddd %%mm4, %%mm4			\n\t" /* 2A0		2a0 */\
	"psubd %%mm7, %%mm4			\n\t" /* A0-B0		a0-b0 */\
	"psrad $" #shift ", %%mm7		\n\t"\
	"psrad $" #shift ", %%mm4		\n\t"\
	"movq %%mm0, %%mm1			\n\t" /* A1		a1 */\
	"paddd %%mm3, %%mm0			\n\t" /* A1+B1		a1+b1 */\
	"psubd %%mm3, %%mm1			\n\t" /* A1-B1		a1-b1 */\
	"psrad $" #shift ", %%mm0		\n\t"\
	"psrad $" #shift ", %%mm1		\n\t"\
	"packssdw %%mm7, %%mm7			\n\t" /* A0+B0	a0+b0 */\
	"movd %%mm7, " #dst "			\n\t"\
	"packssdw %%mm0, %%mm0			\n\t" /* A1+B1	a1+b1 */\
	"movd %%mm0, 16+" #dst "		\n\t"\
	"packssdw %%mm1, %%mm1			\n\t" /* A1-B1	a1-b1 */\
	"movd %%mm1, 96+" #dst "		\n\t"\
	"packssdw %%mm4, %%mm4			\n\t" /* A0-B0	a0-b0 */\
	"movd %%mm4, 112+" #dst "		\n\t"\
	"movq 80(%2), %%mm4			\n\t" /* -C1	C5	-C1 	C5 */\
	"pmaddwd %%mm2, %%mm4			\n\t" /* -C1R3+C5R1	-C1r3+C5r1 */\
	"pmaddwd 96(%2), %%mm2			\n\t" /* -C5R3+C7R1	-C5r3+C7r1 */\
	"movq %%mm5, %%mm1			\n\t" /* A2		a2 */\
	"paddd %%mm4, %%mm1			\n\t" /* A2+B2		a2+b2 */\
	"psubd %%mm4, %%mm5			\n\t" /* a2-B2		a2-b2 */\
	"psrad $" #shift ", %%mm1		\n\t"\
	"psrad $" #shift ", %%mm5		\n\t"\
	"movq %%mm6, %%mm4			\n\t" /* A3		a3 */\
	"paddd %%mm2, %%mm6			\n\t" /* A3+B3		a3+b3 */\
	"psubd %%mm2, %%mm4			\n\t" /* a3-B3		a3-b3 */\
	"psrad $" #shift ", %%mm6		\n\t"\
	"psrad $" #shift ", %%mm4		\n\t"\
	"packssdw %%mm1, %%mm1			\n\t" /* A2+B2	a2+b2 */\
	"packssdw %%mm6, %%mm6			\n\t" /* A3+B3	a3+b3 */\
	"movd %%mm1, 32+" #dst "		\n\t"\
	"packssdw %%mm4, %%mm4			\n\t" /* A3-B3	a3-b3 */\
	"packssdw %%mm5, %%mm5			\n\t" /* A2-B2	a2-b2 */\
	"movd %%mm6, 48+" #dst "		\n\t"\
	"movd %%mm4, 64+" #dst "		\n\t"\
	"movd %%mm5, 80+" #dst "		\n\t"


//IDCT(  src0,   src4,   src1,    src5,    dst, rounder, shift)
IDCT(    (%1), 64(%1), 32(%1),  96(%1),  0(%0),/nop, 20)
IDCT(   8(%1), 72(%1), 40(%1), 104(%1),  4(%0),/nop, 20)
IDCT(  16(%1), 80(%1), 48(%1), 112(%1),  8(%0),/nop, 20)
IDCT(  24(%1), 88(%1), 56(%1), 120(%1), 12(%0),/nop, 20)
	"jmp 9f					\n\t"

	"#.balign 16				\n\t"\
	"5:					\n\t"
#undef IDCT
#define IDCT(src0, src4, src1, src5, dst, rounder, shift) \
	"movq " #src0 ", %%mm0			\n\t" /* R4	R0	r4	r0 */\
	"movq " #src4 ", %%mm1			\n\t" /* R6	R2	r6	r2 */\
	"movq 16(%2), %%mm4			\n\t" /* C4	C4	C4	C4 */\
	"pmaddwd %%mm0, %%mm4			\n\t" /* C4R4+C4R0	C4r4+C4r0 */\
	"movq 24(%2), %%mm5			\n\t" /* -C4	C4	-C4	C4 */\
	"pmaddwd %%mm5, %%mm0			\n\t" /* -C4R4+C4R0	-C4r4+C4r0 */\
	"movq 32(%2), %%mm5			\n\t" /* C6	C2	C6	C2 */\
	"pmaddwd %%mm1, %%mm5			\n\t" /* C6R6+C2R2	C6r6+C2r2 */\
	"movq 40(%2), %%mm6			\n\t" /* -C2	C6	-C2	C6 */\
	"pmaddwd %%mm6, %%mm1			\n\t" /* -C2R6+C6R2	-C2r6+C6r2 */\
	#rounder ", %%mm4			\n\t"\
	"movq %%mm4, %%mm6			\n\t" /* C4R4+C4R0	C4r4+C4r0 */\
	"paddd %%mm5, %%mm4			\n\t" /* A0		a0 */\
	#rounder ", %%mm0			\n\t"\
	"psubd %%mm5, %%mm6			\n\t" /* A3		a3 */\
	"movq %%mm0, %%mm5			\n\t" /* -C4R4+C4R0	-C4r4+C4r0 */\
	"paddd %%mm1, %%mm0			\n\t" /* A1		a1 */\
	"psubd %%mm1, %%mm5			\n\t" /* A2		a2 */\
	"movq 8+" #src0 ", %%mm2		\n\t" /* R4	R0	r4	r0 */\
	"movq 8+" #src4 ", %%mm3		\n\t" /* R6	R2	r6	r2 */\
	"movq 16(%2), %%mm1			\n\t" /* C4	C4	C4	C4 */\
	"pmaddwd %%mm2, %%mm1			\n\t" /* C4R4+C4R0	C4r4+C4r0 */\
	"movq 24(%2), %%mm7			\n\t" /* -C4	C4	-C4	C4 */\
	"pmaddwd %%mm7, %%mm2			\n\t" /* -C4R4+C4R0	-C4r4+C4r0 */\
	"movq 32(%2), %%mm7			\n\t" /* C6	C2	C6	C2 */\
	"pmaddwd %%mm3, %%mm7			\n\t" /* C6R6+C2R2	C6r6+C2r2 */\
	"pmaddwd 40(%2), %%mm3			\n\t" /* -C2R6+C6R2	-C2r6+C6r2 */\
	#rounder ", %%mm1			\n\t"\
	"paddd %%mm1, %%mm7			\n\t" /* A0		a0 */\
	"paddd %%mm1, %%mm1			\n\t" /* 2C0		2c0 */\
	#rounder ", %%mm2			\n\t"\
	"psubd %%mm7, %%mm1			\n\t" /* A3		a3 */\
	"paddd %%mm2, %%mm3			\n\t" /* A1		a1 */\
	"paddd %%mm2, %%mm2			\n\t" /* 2C1		2c1 */\
	"psubd %%mm3, %%mm2			\n\t" /* A2		a2 */\
	"psrad $" #shift ", %%mm4		\n\t"\
	"psrad $" #shift ", %%mm7		\n\t"\
	"psrad $" #shift ", %%mm3		\n\t"\
	"packssdw %%mm7, %%mm4			\n\t" /* A0	a0 */\
	"movq %%mm4, " #dst "			\n\t"\
	"psrad $" #shift ", %%mm0		\n\t"\
	"packssdw %%mm3, %%mm0			\n\t" /* A1	a1 */\
	"movq %%mm0, 16+" #dst "		\n\t"\
	"movq %%mm0, 96+" #dst "		\n\t"\
	"movq %%mm4, 112+" #dst "		\n\t"\
	"psrad $" #shift ", %%mm5		\n\t"\
	"psrad $" #shift ", %%mm6		\n\t"\
	"psrad $" #shift ", %%mm2		\n\t"\
	"packssdw %%mm2, %%mm5			\n\t" /* A2-B2	a2-b2 */\
	"movq %%mm5, 32+" #dst "		\n\t"\
	"psrad $" #shift ", %%mm1		\n\t"\
	"packssdw %%mm1, %%mm6			\n\t" /* A3+B3	a3+b3 */\
	"movq %%mm6, 48+" #dst "		\n\t"\
	"movq %%mm6, 64+" #dst "		\n\t"\
	"movq %%mm5, 80+" #dst "		\n\t"	
	

//IDCT(  src0,   src4,   src1,    src5,    dst, rounder, shift)
IDCT(    0(%1), 64(%1), 32(%1),  96(%1),  0(%0),/nop, 20)
//IDCT(   8(%1), 72(%1), 40(%1), 104(%1),  4(%0),/nop, 20)
IDCT(  16(%1), 80(%1), 48(%1), 112(%1),  8(%0),/nop, 20)
//IDCT(  24(%1), 88(%1), 56(%1), 120(%1), 12(%0),/nop, 20)
	"jmp 9f					\n\t"


	"#.balign 16				\n\t"\
	"1:					\n\t"
#undef IDCT
#define IDCT(src0, src4, src1, src5, dst, rounder, shift) \
	"movq " #src0 ", %%mm0			\n\t" /* R4	R0	r4	r0 */\
	"movq " #src4 ", %%mm1			\n\t" /* R6	R2	r6	r2 */\
	"movq " #src1 ", %%mm2			\n\t" /* R3	R1	r3	r1 */\
	"movq 16(%2), %%mm4			\n\t" /* C4	C4	C4	C4 */\
	"pmaddwd %%mm0, %%mm4			\n\t" /* C4R4+C4R0	C4r4+C4r0 */\
	"movq 24(%2), %%mm5			\n\t" /* -C4	C4	-C4	C4 */\
	"pmaddwd %%mm5, %%mm0			\n\t" /* -C4R4+C4R0	-C4r4+C4r0 */\
	"movq 32(%2), %%mm5			\n\t" /* C6	C2	C6	C2 */\
	"pmaddwd %%mm1, %%mm5			\n\t" /* C6R6+C2R2	C6r6+C2r2 */\
	"movq 40(%2), %%mm6			\n\t" /* -C2	C6	-C2	C6 */\
	"pmaddwd %%mm6, %%mm1			\n\t" /* -C2R6+C6R2	-C2r6+C6r2 */\
	#rounder ", %%mm4			\n\t"\
	"movq %%mm4, %%mm6			\n\t" /* C4R4+C4R0	C4r4+C4r0 */\
	"movq 48(%2), %%mm7			\n\t" /* C3	C1	C3	C1 */\
	#rounder ", %%mm0			\n\t"\
	"pmaddwd %%mm2, %%mm7			\n\t" /* C3R3+C1R1	C3r3+C1r1 */\
	"paddd %%mm5, %%mm4			\n\t" /* A0		a0 */\
	"psubd %%mm5, %%mm6			\n\t" /* A3		a3 */\
	"movq %%mm0, %%mm5			\n\t" /* -C4R4+C4R0	-C4r4+C4r0 */\
	"paddd %%mm1, %%mm0			\n\t" /* A1		a1 */\
	"psubd %%mm1, %%mm5			\n\t" /* A2		a2 */\
	"movq 64(%2), %%mm1			\n\t"\
	"pmaddwd %%mm2, %%mm1			\n\t" /* -C7R3+C3R1	-C7r3+C3r1 */\
	"paddd %%mm4, %%mm7			\n\t" /* A0+B0		a0+b0 */\
	"paddd %%mm4, %%mm4			\n\t" /* 2A0		2a0 */\
	"psubd %%mm7, %%mm4			\n\t" /* A0-B0		a0-b0 */\
	"psrad $" #shift ", %%mm7		\n\t"\
	"psrad $" #shift ", %%mm4		\n\t"\
	"movq %%mm0, %%mm3			\n\t" /* A1		a1 */\
	"paddd %%mm1, %%mm0			\n\t" /* A1+B1		a1+b1 */\
	"psubd %%mm1, %%mm3			\n\t" /* A1-B1		a1-b1 */\
	"psrad $" #shift ", %%mm0		\n\t"\
	"psrad $" #shift ", %%mm3		\n\t"\
	"packssdw %%mm7, %%mm7			\n\t" /* A0+B0	a0+b0 */\
	"movd %%mm7, " #dst "			\n\t"\
	"packssdw %%mm0, %%mm0			\n\t" /* A1+B1	a1+b1 */\
	"movd %%mm0, 16+" #dst "		\n\t"\
	"packssdw %%mm3, %%mm3			\n\t" /* A1-B1	a1-b1 */\
	"movd %%mm3, 96+" #dst "		\n\t"\
	"packssdw %%mm4, %%mm4			\n\t" /* A0-B0	a0-b0 */\
	"movd %%mm4, 112+" #dst "		\n\t"\
	"movq 80(%2), %%mm4			\n\t" /* -C1	C5	-C1 	C5 */\
	"pmaddwd %%mm2, %%mm4			\n\t" /* -C1R3+C5R1	-C1r3+C5r1 */\
	"pmaddwd 96(%2), %%mm2			\n\t" /* -C5R3+C7R1	-C5r3+C7r1 */\
	"movq %%mm5, %%mm3			\n\t" /* A2		a2 */\
	"paddd %%mm4, %%mm3			\n\t" /* A2+B2		a2+b2 */\
	"psubd %%mm4, %%mm5			\n\t" /* a2-B2		a2-b2 */\
	"psrad $" #shift ", %%mm3		\n\t"\
	"psrad $" #shift ", %%mm5		\n\t"\
	"movq %%mm6, %%mm4			\n\t" /* A3		a3 */\
	"paddd %%mm2, %%mm6			\n\t" /* A3+B3		a3+b3 */\
	"psubd %%mm2, %%mm4			\n\t" /* a3-B3		a3-b3 */\
	"psrad $" #shift ", %%mm6		\n\t"\
	"packssdw %%mm3, %%mm3			\n\t" /* A2+B2	a2+b2 */\
	"movd %%mm3, 32+" #dst "		\n\t"\
	"psrad $" #shift ", %%mm4		\n\t"\
	"packssdw %%mm6, %%mm6			\n\t" /* A3+B3	a3+b3 */\
	"movd %%mm6, 48+" #dst "		\n\t"\
	"packssdw %%mm4, %%mm4			\n\t" /* A3-B3	a3-b3 */\
	"packssdw %%mm5, %%mm5			\n\t" /* A2-B2	a2-b2 */\
	"movd %%mm4, 64+" #dst "		\n\t"\
	"movd %%mm5, 80+" #dst "		\n\t"
	

//IDCT(  src0,   src4,   src1,    src5,    dst, rounder, shift)
IDCT(    (%1), 64(%1), 32(%1),  96(%1),  0(%0),/nop, 20)
IDCT(   8(%1), 72(%1), 40(%1), 104(%1),  4(%0),/nop, 20)
IDCT(  16(%1), 80(%1), 48(%1), 112(%1),  8(%0),/nop, 20)
IDCT(  24(%1), 88(%1), 56(%1), 120(%1), 12(%0),/nop, 20)
	"jmp 9f					\n\t"


	"#.balign 16				\n\t"
	"7:					\n\t"
#undef IDCT
#define IDCT(src0, src4, src1, src5, dst, rounder, shift) \
	"movq " #src0 ", %%mm0			\n\t" /* R4	R0	r4	r0 */\
	"movq 16(%2), %%mm4			\n\t" /* C4	C4	C4	C4 */\
	"pmaddwd %%mm0, %%mm4			\n\t" /* C4R4+C4R0	C4r4+C4r0 */\
	"movq 24(%2), %%mm5			\n\t" /* -C4	C4	-C4	C4 */\
	"pmaddwd %%mm5, %%mm0			\n\t" /* -C4R4+C4R0	-C4r4+C4r0 */\
	#rounder ", %%mm4			\n\t"\
	#rounder ", %%mm0			\n\t"\
	"psrad $" #shift ", %%mm4		\n\t"\
	"psrad $" #shift ", %%mm0		\n\t"\
	"movq 8+" #src0 ", %%mm2		\n\t" /* R4	R0	r4	r0 */\
	"movq 16(%2), %%mm1			\n\t" /* C4	C4	C4	C4 */\
	"pmaddwd %%mm2, %%mm1			\n\t" /* C4R4+C4R0	C4r4+C4r0 */\
	"movq 24(%2), %%mm7			\n\t" /* -C4	C4	-C4	C4 */\
	"pmaddwd %%mm7, %%mm2			\n\t" /* -C4R4+C4R0	-C4r4+C4r0 */\
	"movq 32(%2), %%mm7			\n\t" /* C6	C2	C6	C2 */\
	#rounder ", %%mm1			\n\t"\
	#rounder ", %%mm2			\n\t"\
	"psrad $" #shift ", %%mm1		\n\t"\
	"packssdw %%mm1, %%mm4			\n\t" /* A0	a0 */\
	"movq %%mm4, " #dst "			\n\t"\
	"psrad $" #shift ", %%mm2		\n\t"\
	"packssdw %%mm2, %%mm0			\n\t" /* A1	a1 */\
	"movq %%mm0, 16+" #dst "		\n\t"\
	"movq %%mm0, 96+" #dst "		\n\t"\
	"movq %%mm4, 112+" #dst "		\n\t"\
	"movq %%mm0, 32+" #dst "		\n\t"\
	"movq %%mm4, 48+" #dst "		\n\t"\
	"movq %%mm4, 64+" #dst "		\n\t"\
	"movq %%mm0, 80+" #dst "		\n\t"	

//IDCT(  src0,   src4,   src1,    src5,    dst, rounder, shift)
IDCT(   0(%1), 64(%1), 32(%1),  96(%1),  0(%0),/nop, 20)
//IDCT(   8(%1), 72(%1), 40(%1), 104(%1),  4(%0),/nop, 20)
IDCT(  16(%1), 80(%1), 48(%1), 112(%1),  8(%0),/nop, 20)
//IDCT(  24(%1), 88(%1), 56(%1), 120(%1), 12(%0),/nop, 20)


#endif

/*
Input
 00 40 04 44 20 60 24 64
 10 30 14 34 50 70 54 74
 01 41 03 43 21 61 23 63
 11 31 13 33 51 71 53 73
 02 42 06 46 22 62 26 66
 12 32 16 36 52 72 56 76
 05 45 07 47 25 65 27 67
 15 35 17 37 55 75 57 77
  
Temp
 00 04 10 14 20 24 30 34
 40 44 50 54 60 64 70 74
 01 03 11 13 21 23 31 33
 41 43 51 53 61 63 71 73
 02 06 12 16 22 26 32 36
 42 46 52 56 62 66 72 76
 05 07 15 17 25 27 35 37
 45 47 55 57 65 67 75 77
*/

"9: \n\t"
		:: "r" (block), "r" (temp), "r" (coeffs)
		: "%eax"
	);
}

void ff_simple_idct_mmx(int16_t *block)
{
    idct(block);
}

//FIXME merge add/put into the idct

void ff_simple_idct_put_mmx(uint8_t *dest, int line_size, DCTELEM *block)
{
    idct(block);
    put_pixels_clamped_mmx(block, dest, line_size);
}
void ff_simple_idct_add_mmx(uint8_t *dest, int line_size, DCTELEM *block)
{
    idct(block);
    add_pixels_clamped_mmx(block, dest, line_size);
}
1234

simple_idct_mmx.c - 源码说明

本页面展示了「这是著名的TCPMP播放器在WINDWOWS,和WINCE下编译通过的源程序.笔者对其中的LIBMAD库做了针对ARM MPU的优化. 并增加了词幕功能.」中的 simple_idct_mmx.c 源码文件，采用 C语言 编程语言编写，共 1,315 行代码。您可以在线阅读完整代码内容，也可以返回资源详情页下载完整源码包进行本地学习和开发。

虫虫开发者社区收录了大量与TCPMP播放器相关的技术资源，包括源代码、技术文档、电路图等，是电子工程师和嵌入式开发者的专业学习平台。

⌨️ 快捷键说明

复制代码Ctrl + C
搜索代码Ctrl + F
全屏模式F11
增大字号Ctrl + =
减小字号Ctrl + -
显示快捷键?