📄 simple_idct_mmx.c
字号:
"packssdw %%mm1, %%mm1 \n\t" /* A3-B3 a3-b3 */\ "packssdw %%mm5, %%mm5 \n\t" /* A2-B2 a2-b2 */\ "movd %%mm6, 48+" #dst " \n\t"\ "movd %%mm1, 64+" #dst " \n\t"\ "movd %%mm5, 80+" #dst " \n\t"//IDCT( src0, src4, src1, src5, dst, shift)IDCT( (%1), 64(%1), 32(%1), 96(%1), 0(%0), 20)IDCT( 8(%1), 72(%1), 40(%1), 104(%1), 4(%0), 20)IDCT( 16(%1), 80(%1), 48(%1), 112(%1), 8(%0), 20)IDCT( 24(%1), 88(%1), 56(%1), 120(%1), 12(%0), 20) "jmp 9f \n\t" "#" ASMALIGN(4) \ "2: \n\t"Z_COND_IDCT( 96(%0),104(%0),112(%0),120(%0), 96(%1),paddd (%2), 11, 3f)#undef IDCT#define IDCT(src0, src4, src1, src5, dst, shift) \ "movq " #src0 ", %%mm0 \n\t" /* R4 R0 r4 r0 */\ "movq " #src1 ", %%mm2 \n\t" /* R3 R1 r3 r1 */\ "movq " #src5 ", %%mm3 \n\t" /* R7 R5 r7 r5 */\ "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 %%mm4, %%mm6 \n\t" /* C4R4+C4R0 C4r4+C4r0 */\ "movq 48(%2), %%mm7 \n\t" /* C3 C1 C3 C1 */\ "pmaddwd %%mm2, %%mm7 \n\t" /* C3R3+C1R1 C3r3+C1r1 */\ "movq %%mm0, %%mm5 \n\t" /* -C4R4+C4R0 -C4r4+C4r0 */\ "movq 56(%2), %%mm1 \n\t" /* C7 C5 C7 C5 */\ "pmaddwd %%mm3, %%mm1 \n\t" /* C7R7+C5R5 C7r7+C5r5 */\ "pmaddwd 64(%2), %%mm2 \n\t" /* -C7R3+C3R1 -C7r3+C3r1 */\ "paddd %%mm1, %%mm7 \n\t" /* B0 b0 */\ "movq 72(%2), %%mm1 \n\t" /* -C5 -C1 -C5 -C1 */\ "pmaddwd %%mm3, %%mm1 \n\t" /* -C5R7-C1R5 -C5r7-C1r5 */\ "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 */\ "paddd %%mm2, %%mm1 \n\t" /* B1 b1 */\ "psrad $" #shift ", %%mm7 \n\t"\ "psrad $" #shift ", %%mm4 \n\t"\ "movq %%mm0, %%mm2 \n\t" /* A1 a1 */\ "paddd %%mm1, %%mm0 \n\t" /* A1+B1 a1+b1 */\ "psubd %%mm1, %%mm2 \n\t" /* A1-B1 a1-b1 */\ "psrad $" #shift ", %%mm0 \n\t"\ "psrad $" #shift ", %%mm2 \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 %%mm2, %%mm2 \n\t" /* A1-B1 a1-b1 */\ "movd %%mm2, 96+" #dst " \n\t"\ "packssdw %%mm4, %%mm4 \n\t" /* A0-B0 a0-b0 */\ "movd %%mm4, 112+" #dst " \n\t"\ "movq " #src1 ", %%mm0 \n\t" /* R3 R1 r3 r1 */\ "movq 80(%2), %%mm4 \n\t" /* -C1 C5 -C1 C5 */\ "pmaddwd %%mm0, %%mm4 \n\t" /* -C1R3+C5R1 -C1r3+C5r1 */\ "movq 88(%2), %%mm7 \n\t" /* C3 C7 C3 C7 */\ "pmaddwd 96(%2), %%mm0 \n\t" /* -C5R3+C7R1 -C5r3+C7r1 */\ "pmaddwd %%mm3, %%mm7 \n\t" /* C3R7+C7R5 C3r7+C7r5 */\ "movq %%mm5, %%mm2 \n\t" /* A2 a2 */\ "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, shift)IDCT( (%1), 64(%1), 32(%1), 96(%1), 0(%0), 20)IDCT( 8(%1), 72(%1), 40(%1), 104(%1), 4(%0), 20)IDCT( 16(%1), 80(%1), 48(%1), 112(%1), 8(%0), 20)IDCT( 24(%1), 88(%1), 56(%1), 120(%1), 12(%0), 20) "jmp 9f \n\t" "#" ASMALIGN(4) \ "3: \n\t"#undef IDCT#define IDCT(src0, src4, src1, src5, dst, 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 */\ "movq %%mm4, %%mm6 \n\t" /* C4R4+C4R0 C4r4+C4r0 */\ "movq 48(%2), %%mm7 \n\t" /* C3 C1 C3 C1 */\ "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, shift)IDCT( (%1), 64(%1), 32(%1), 96(%1), 0(%0), 20)IDCT( 8(%1), 72(%1), 40(%1), 104(%1), 4(%0), 20)IDCT( 16(%1), 80(%1), 48(%1), 112(%1), 8(%0), 20)IDCT( 24(%1), 88(%1), 56(%1), 120(%1), 12(%0), 20) "jmp 9f \n\t" "#" ASMALIGN(4) \ "5: \n\t"#undef IDCT#define IDCT(src0, src4, src1, src5, dst, 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 */\ "movq %%mm4, %%mm6 \n\t" /* C4R4+C4R0 C4r4+C4r0 */\ "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 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 */\ "paddd %%mm1, %%mm7 \n\t" /* A0 a0 */\ "paddd %%mm1, %%mm1 \n\t" /* 2C0 2c0 */\ "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, shift)IDCT( 0(%1), 64(%1), 32(%1), 96(%1), 0(%0), 20)//IDCT( 8(%1), 72(%1), 40(%1), 104(%1), 4(%0), 20)IDCT( 16(%1), 80(%1), 48(%1), 112(%1), 8(%0), 20)//IDCT( 24(%1), 88(%1), 56(%1), 120(%1), 12(%0), 20) "jmp 9f \n\t" "#" ASMALIGN(4) \ "1: \n\t"#undef IDCT#define IDCT(src0, src4, src1, src5, dst, shift) \ "movq " #src0 ", %%mm0 ⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -