📄 simple_idct_mmx.asm
字号:
%define src1 %3%define src5 %4%define dst %5%define rounder_op %6%define rounder_arg %7%define shift %8 movq mm0,[src0] ; R4 R0 r4 r0 movq mm1,[src4] ; R6 R2 r6 r2 movq mm3,[src5] ; R7 R5 r7 r5 movq mm4,[coeffs+16] ; C4 C4 C4 C4 pmaddwd mm4,mm0 ; C4R4+C4R0 C4r4+C4r0 movq mm5,[coeffs+24] ; -C4 C4 -C4 C4 pmaddwd mm0,mm5 ; -C4R4+C4R0 -C4r4+C4r0 movq mm5,[coeffs+32] ; C6 C2 C6 C2 pmaddwd mm5,mm1 ; C6R6+C2R2 C6r6+C2r2 movq mm6,[coeffs+40] ; -C2 C6 -C2 C6 pmaddwd mm1,mm6 ; -C2R6+C6R2 -C2r6+C6r2 ; rounder_op mm4, rounder_arg movq mm6,mm4 ; C4R4+C4R0 C4r4+C4r0 ; rounder_op mm0, rounder_arg paddd mm4,mm5 ; A0 a0 psubd mm6,mm5 ; A3 a3 movq mm5,mm0 ; -C4R4+C4R0 -C4r4+C4r0 paddd mm0,mm1 ; A1 a1 psubd mm5,mm1 ; A2 a2 movq mm1,[coeffs+56] ; C7 C5 C7 C5 pmaddwd mm1,mm3 ; C7R7+C5R5 C7r7+C5r5 movq mm7,[coeffs+72] ; -C5 -C1 -C5 -C1 pmaddwd mm7,mm3 ; -C5R7-C1R5 -C5r7-C1r5 paddd mm1,mm4 ; A0+B0 a0+b0 paddd mm4,mm4 ; 2A0 2a0 psubd mm4,mm1 ; A0-B0 a0-b0 psrad mm1,shift psrad mm4,shift movq mm2,mm0 ; A1 a1 paddd mm0,mm7 ; A1+B1 a1+b1 psubd mm2,mm7 ; A1-B1 a1-b1 psrad mm0,shift psrad mm2,shift packssdw mm1,mm1 ; A0+B0 a0+b0 movd [ dst ],mm1 packssdw mm0,mm0 ; A1+B1 a1+b1 movd [ dst + 16 ],mm0 packssdw mm2,mm2 ; A1-B1 a1-b1 movd [ dst + 96 ],mm2 packssdw mm4,mm4 ; A0-B0 a0-b0 movd [ dst + 112 ],mm4 movq mm1,[coeffs+88] ; C3 C7 C3 C7 pmaddwd mm1,mm3 ; C3R7+C7R5 C3r7+C7r5 movq mm2,mm5 ; A2 a2 pmaddwd mm3,[coeffs+104] ; -C1R7+C3R5 -C1r7+C3r5 paddd mm2,mm1 ; A2+B2 a2+b2 psubd mm5,mm1 ; a2-B2 a2-b2 psrad mm2,shift psrad mm5,shift movq mm1,mm6 ; A3 a3 paddd mm6,mm3 ; A3+B3 a3+b3 psubd mm1,mm3 ; a3-B3 a3-b3 psrad mm6,shift psrad mm1,shift packssdw mm2,mm2 ; A2+B2 a2+b2 packssdw mm6,mm6 ; A3+B3 a3+b3 movd [dst + 32],mm2 packssdw mm1,mm1 ; A3-B3 a3-b3 packssdw mm5,mm5 ; A2-B2 a2-b2 movd [dst + 48],mm6 movd [dst + 64],mm1 movd [dst + 80],mm5%undef src0%undef src4%undef src1%undef src5%undef dst%undef rounder_op%undef rounder_arg%undef shift%endmacro;---------------------------------------------------------------------------; IDCT6;---------------------------------------------------------------------------%macro IDCT6 8%define src0 %1%define src4 %2%define src1 %3%define src5 %4%define dst %5%define rounder_op %6%define rounder_arg %7%define shift %8 movq mm0,[src0] ; R4 R0 r4 r0 movq mm3,[src5] ; R7 R5 r7 r5 movq mm4,[coeffs+16] ; C4 C4 C4 C4 pmaddwd mm4,mm0 ; C4R4+C4R0 C4r4+C4r0 movq mm5,[coeffs+24] ; -C4 C4 -C4 C4 pmaddwd mm0,mm5 ; -C4R4+C4R0 -C4r4+C4r0 ; rounder_op mm4, rounder_arg movq mm6,mm4 ; C4R4+C4R0 C4r4+C4r0 ; rounder_op mm0, rounder_arg movq mm5,mm0 ; -C4R4+C4R0 -C4r4+C4r0 movq mm1,[coeffs+56] ; C7 C5 C7 C5 pmaddwd mm1,mm3 ; C7R7+C5R5 C7r7+C5r5 movq mm7,[coeffs+72] ; -C5 -C1 -C5 -C1 pmaddwd mm7,mm3 ; -C5R7-C1R5 -C5r7-C1r5 paddd mm1,mm4 ; A0+B0 a0+b0 paddd mm4,mm4 ; 2A0 2a0 psubd mm4,mm1 ; A0-B0 a0-b0 psrad mm1,shift psrad mm4,shift movq mm2,mm0 ; A1 a1 paddd mm0,mm7 ; A1+B1 a1+b1 psubd mm2,mm7 ; A1-B1 a1-b1 psrad mm0,shift psrad mm2,shift packssdw mm1,mm1 ; A0+B0 a0+b0 movd [ dst ],mm1 packssdw mm0,mm0 ; A1+B1 a1+b1 movd [ dst + 16 ],mm0 packssdw mm2,mm2 ; A1-B1 a1-b1 movd [ dst + 96 ],mm2 packssdw mm4,mm4 ; A0-B0 a0-b0 movd [ dst + 112 ],mm4 movq mm1,[coeffs+88] ; C3 C7 C3 C7 pmaddwd mm1,mm3 ; C3R7+C7R5 C3r7+C7r5 movq mm2,mm5 ; A2 a2 pmaddwd mm3,[coeffs+104] ; -C1R7+C3R5 -C1r7+C3r5 paddd mm2,mm1 ; A2+B2 a2+b2 psubd mm5,mm1 ; a2-B2 a2-b2 psrad mm2,shift psrad mm5,shift movq mm1,mm6 ; A3 a3 paddd mm6,mm3 ; A3+B3 a3+b3 psubd mm1,mm3 ; a3-B3 a3-b3 psrad mm6,shift psrad mm1,shift packssdw mm2,mm2 ; A2+B2 a2+b2 packssdw mm6,mm6 ; A3+B3 a3+b3 movd [dst + 32],mm2 packssdw mm1,mm1 ; A3-B3 a3-b3 packssdw mm5,mm5 ; A2-B2 a2-b2 movd [dst + 48],mm6 movd [dst + 64],mm1 movd [dst + 80],mm5%undef src0%undef src4%undef src1%undef src5%undef dst%undef rounder_op%undef rounder_arg%undef shift%endmacro;---------------------------------------------------------------------------; IDCT2;---------------------------------------------------------------------------%macro IDCT2 8%define src0 %1%define src4 %2%define src1 %3%define src5 %4%define dst %5%define rounder_op %6%define rounder_arg %7%define shift %8 movq mm0,[src0] ; R4 R0 r4 r0 movq mm2,[src1] ; R3 R1 r3 r1 movq mm3,[src5] ; R7 R5 r7 r5 movq mm4,[coeffs+16] ; C4 C4 C4 C4 pmaddwd mm4,mm0 ; C4R4+C4R0 C4r4+C4r0 movq mm5,[coeffs+24] ; -C4 C4 -C4 C4 pmaddwd mm0,mm5 ; -C4R4+C4R0 -C4r4+C4r0 ; rounder_op mm4, rounder_arg movq mm6,mm4 ; C4R4+C4R0 C4r4+C4r0 movq mm7,[coeffs+48] ; C3 C1 C3 C1 ; rounder_op mm0, rounder_arg pmaddwd mm7,mm2 ; C3R3+C1R1 C3r3+C1r1 movq mm5,mm0 ; -C4R4+C4R0 -C4r4+C4r0 movq mm1,[coeffs+56] ; C7 C5 C7 C5 pmaddwd mm1,mm3 ; C7R7+C5R5 C7r7+C5r5 pmaddwd mm2,[coeffs+64] ; -C7R3+C3R1 -C7r3+C3r1 paddd mm7,mm1 ; B0 b0 movq mm1,[coeffs+72] ; -C5 -C1 -C5 -C1 pmaddwd mm1,mm3 ; -C5R7-C1R5 -C5r7-C1r5 paddd mm7,mm4 ; A0+B0 a0+b0 paddd mm4,mm4 ; 2A0 2a0 psubd mm4,mm7 ; A0-B0 a0-b0 paddd mm1,mm2 ; B1 b1 psrad mm7,shift psrad mm4,shift movq mm2,mm0 ; A1 a1 paddd mm0,mm1 ; A1+B1 a1+b1 psubd mm2,mm1 ; A1-B1 a1-b1 psrad mm0,shift psrad mm2,shift packssdw mm7,mm7 ; A0+B0 a0+b0 movd [dst],mm7 packssdw mm0,mm0 ; A1+B1 a1+b1 movd [dst + 16],mm0 packssdw mm2,mm2 ; A1-B1 a1-b1 movd [dst + 96],mm2 packssdw mm4,mm4 ; A0-B0 a0-b0 movd [dst + 112],mm4 movq mm0,[src1] ; R3 R1 r3 r1 movq mm4,[coeffs+80] ; -C1 C5 -C1 C5 pmaddwd mm4,mm0 ; -C1R3+C5R1 -C1r3+C5r1 movq mm7,[coeffs+88] ; C3 C7 C3 C7 pmaddwd mm0,[coeffs+96] ; -C5R3+C7R1 -C5r3+C7r1 pmaddwd mm7,mm3 ; C3R7+C7R5 C3r7+C7r5 movq mm2,mm5 ; A2 a2 pmaddwd mm3,[coeffs+104] ; -C1R7+C3R5 -C1r7+C3r5 paddd mm4,mm7 ; B2 b2 paddd mm2,mm4 ; A2+B2 a2+b2 psubd mm5,mm4 ; a2-B2 a2-b2 psrad mm2,shift psrad mm5,shift movq mm4,mm6 ; A3 a3 paddd mm3,mm0 ; B3 b3 paddd mm6,mm3 ; A3+B3 a3+b3 psubd mm4,mm3 ; a3-B3 a3-b3 psrad mm6,shift psrad mm4,shift packssdw mm2,mm2 ; A2+B2 a2+b2 packssdw mm6,mm6 ; A3+B3 a3+b3 movd [dst + 32],mm2 packssdw mm4,mm4 ; A3-B3 a3-b3 packssdw mm5,mm5 ; A2-B2 a2-b2 movd [dst + 48],mm6 movd [dst + 64],mm4 movd [dst + 80],mm5%undef src0%undef src4%undef src1%undef src5%undef dst%undef rounder_op%undef rounder_arg%undef shift%endmacro;---------------------------------------------------------------------------; IDCT3;---------------------------------------------------------------------------%macro IDCT3 8%define src0 %1%define src4 %2%define src1 %3%define src5 %4%define dst %5%define rounder_op %6%define rounder_arg %7%define shift %8 movq mm0,[src0] ; R4 R0 r4 r0 movq mm2,[src1] ; R3 R1 r3 r1 movq mm4,[coeffs+16] ; C4 C4 C4 C4 pmaddwd mm4,mm0 ; C4R4+C4R0 C4r4+C4r0 movq mm5,[coeffs+24] ; -C4 C4 -C4 C4 pmaddwd mm0,mm5 ; -C4R4+C4R0 -C4r4+C4r0 ; rounder_op mm4, rounder_arg movq mm6,mm4 ; C4R4+C4R0 C4r4+C4r0 movq mm7,[coeffs+48] ; C3 C1 C3 C1 ; rounder_op mm0, rounder_arg pmaddwd mm7,mm2 ; C3R3+C1R1 C3r3+C1r1 movq mm5,mm0 ; -C4R4+C4R0 -C4r4+C4r0 movq mm3,[coeffs+64] pmaddwd mm3,mm2 ; -C7R3+C3R1 -C7r3+C3r1 paddd mm7,mm4 ; A0+B0 a0+b0 paddd mm4,mm4 ; 2A0 2a0 psubd mm4,mm7 ; A0-B0 a0-b0 psrad mm7,shift psrad mm4,shift movq mm1,mm0 ; A1 a1 paddd mm0,mm3 ; A1+B1 a1+b1 psubd mm1,mm3 ; A1-B1 a1-b1 psrad mm0,shift psrad mm1,shift packssdw mm7,mm7 ; A0+B0 a0+b0 movd [dst],mm7 packssdw mm0,mm0 ; A1+B1 a1+b1 movd [dst + 16],mm0 packssdw mm1,mm1 ; A1-B1 a1-b1 movd [dst + 96],mm1 packssdw mm4,mm4 ; A0-B0 a0-b0 movd [dst + 112],mm4 movq mm4,[coeffs+80] ; -C1 C5 -C1 C5 pmaddwd mm4,mm2 ; -C1R3+C5R1 -C1r3+C5r1 pmaddwd mm2,[coeffs+96] ; -C5R3+C7R1 -C5r3+C7r1 movq mm1,mm5 ; A2 a2 paddd mm1,mm4 ; A2+B2 a2+b2 psubd mm5,mm4 ; a2-B2 a2-b2 psrad mm1,shift psrad mm5,shift movq mm4,mm6 ; A3 a3 paddd mm6,mm2 ; A3+B3 a3+b3 psubd mm4,mm2 ; a3-B3 a3-b3 psrad mm6,shift psrad mm4,shift packssdw mm1,mm1 ; A2+B2 a2+b2 packssdw mm6,mm6 ; A3+B3 a3+b3 movd [dst + 32],mm1 packssdw mm4,mm4 ; A3-B3 a3-b3 packssdw mm5,mm5 ; A2-B2 a2-b2 movd [dst + 48],mm6 movd [dst + 64],mm4 movd [dst + 80],mm5%undef src0%undef src4%undef src1%undef src5%undef dst%undef rounder_op%undef rounder_arg%undef shift%endmacro;---------------------------------------------------------------------------; IDCT5;---------------------------------------------------------------------------%macro IDCT5 8%define src0 %1%define src4 %2%define src1 %3%define src5 %4%define dst %5%define rounder_op %6%define rounder_arg %7%define shift %8 movq mm0,[src0] ; R4 R0 r4 r0 movq mm1,[src4] ; R6 R2 r6 r2 movq mm4,[coeffs+16] ; C4 C4 C4 C4 pmaddwd mm4,mm0 ; C4R4+C4R0 C4r4+C4r0 movq mm5,[coeffs+24] ; -C4 C4 -C4 C4 pmaddwd mm0,mm5 ; -C4R4+C4R0 -C4r4+C4r0 movq mm5,[coeffs+32] ; C6 C2 C6 C2 pmaddwd mm5,mm1 ; C6R6+C2R2 C6r6+C2r2 movq mm6,[coeffs+40] ; -C2 C6 -C2 C6 pmaddwd mm1,mm6 ; -C2R6+C6R2 -C2r6+C6r2 ; rounder_op mm4, rounder_arg movq mm6,mm4 ; C4R4+C4R0 C4r4+C4r0 paddd mm4,mm5 ; A0 a0 ; rounder_op mm0, rounder_arg psubd mm6,mm5 ; A3 a3 movq mm5,mm0 ; -C4R4+C4R0 -C4r4+C4r0 paddd mm0,mm1 ; A1 a1 psubd mm5,mm1 ; A2 a2 movq mm2,[src0 + 8] ; R4 R0 r4 r0 movq mm3,[src4 + 8] ; R6 R2 r6 r2 movq mm1,[coeffs+16] ; C4 C4 C4 C4 pmaddwd mm1,mm2 ; C4R4+C4R0 C4r4+C4r0 movq mm7,[coeffs+24] ; -C4 C4 -C4 C4 pmaddwd mm2,mm7 ; -C4R4+C4R0 -C4r4+C4r0 movq mm7,[coeffs+32] ; C6 C2 C6 C2 pmaddwd mm7,mm3 ; C6R6+C2R2 C6r6+C2r2 pmaddwd mm3,[coeffs+40] ; -C2R6+C6R2 -C2r6+C6r2 ; rounder_op mm1, rounder_arg paddd mm7,mm1 ; A0 a0 paddd mm1,mm1 ; 2C0 2c0 ; rounder_op mm2, rounder_arg psubd mm1,mm7 ; A3 a3 paddd mm3,mm2 ; A1 a1 paddd mm2,mm2 ; 2C1 2c1 psubd mm2,mm3 ; A2 a2 psrad mm4,shift psrad mm7,shift psrad mm3,shift packssdw mm4,mm7 ; A0 a0 movq [dst],mm4 psrad mm0,shift packssdw mm0,mm3 ; A1 a1 movq [dst + 16],mm0 movq [dst + 96],mm0 movq [dst + 112],mm4 psrad mm5,shift psrad mm6,shift psrad mm2,shift packssdw mm5,mm2 ; A2-B2 a2-b2 movq [dst + 32],mm5 psrad mm1,shift packssdw mm6,mm1 ; A3+B3 a3+b3 movq [dst + 48],mm6 movq [dst + 64],mm6 movq [dst + 80],mm5%undef src0%undef src4%undef src1%undef src5%undef dst%undef rounder_op%undef rounder_arg%undef shift%endmacro;---------------------------------------------------------------------------; IDCT1;---------------------------------------------------------------------------%macro IDCT1 8%define src0 %1%define src4 %2%define src1 %3%define src5 %4%define dst %5%define rounder_op %6%define rounder_arg %7%define shift %8 movq mm0,[src0] ; R4 R0 r4 r0 movq mm1,[src4] ; R6 R2 r6 r2 movq mm2,[src1] ; R3 R1 r3 r1 movq mm4,[coeffs+16] ; C4 C4 C4 C4 pmaddwd mm4,mm0 ; C4R4+C4R0 C4r4+C4r0 movq mm5,[coeffs+24] ; -C4 C4 -C4 C4 pmaddwd mm0,mm5 ; -C4R4+C4R0 -C4r4+C4r0 movq mm5,[coeffs+32] ; C6 C2 C6 C2 pmaddwd mm5,mm1 ; C6R6+C2R2 C6r6+C2r2 movq mm6,[coeffs+40] ; -C2 C6 -C2 C6
⌨️ 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 + -