_algorithm.asm

在ADSP-2126x上编写的优化过的IIR滤波器程序（用c和汇编编写）。

/////////////////////////////////////////////////////////////
//                                                         //
//     Process the audio stream                            //
//                                                         //
/////////////////////////////////////////////////////////////

#include <def21262.h>
#define SECTIONS 3    /* Number of second-order sections (biquads) */

.section /pm seg_pmco;
.global _Cascaded_IIR_Filter_SIMD;
.extern inbuf;
.extern outbuf;
.extern delaybuf;
.extern coefficients;


_Cascaded_IIR_Filter_SIMD:

/*****************************************************************************
 The algorithm:

 IIR Second order sections - The cannonic second-order section implemented as
 "Direct Form II" biquads.  Note that the SIMD architecture of the 2126x SHARC
 family enables the two parallel execution units to filter the left and right
 channel simultaneously.  All register moves and memory reads implicitly apply
 to the shadow processing element (PEy) as well as the primary computational
 unit (PEx).
 *****************************************************************************

  Given the most general biquadratic (second order rational polynomial)

                b0 + b1'*z^-1 + b2'*z^-2
        H(z) = -------------------------- ,
                a0 + a1'*z^-1 + a2'*z^-2

  we may factor out the gain of the transfer function,

                b0     (b1'/a0)*z^-1 + (b2'/a0)*z^-2
        H(z) = ---- * -------------------------------
                a0     (a1'/b0)*z^-1 + (a2'/b0)*z^-2

  and normalize the coefficients, such that

                    a1*z^-1 + a2*z^-2
        H(z) = A * -------------------
                    b1*z^-1 + b2*z^-2

  where A = gain = b1'/a0

        a1 = a1'/b0,  a2 = a2'/b0,  b1 = b1'/a0,  b2 = b2'/a0

  This leaves only four true filter coefficients.  The gain values from
  all of the sections may be combined into a single channel gain applied
  apart from the inner computational loop.  With the simplified coefficients,
  the cannonic direct form II may be written as a pair of difference
  equations:

          w[n] = x[n] + a1*w[n-1] + a2*w[n-2]
          y[n] = w[n] + b1*w[n-1] + b2*w[n-2]

 which leads to the following pseudocode:

 read(x[n])
 f12=0,                                            f2=w[n-1],         read(a1)
 --- Loop --------------------------------------------------------------------
 f12=a1*w[n-1], f8=f8 + f12,                       f3=w[n-2],         read(a2)
 f12=a2*w[n-2], f8=x[n] + a1*w[n-2],               w[n-1] -> w[n-2]', read(b1)
 f12=b1*w[n-2], w[n]=x[n] + a1*w[n-2] + a2*w[n-1], f2=w[n-1],         read(b2)
 f12=b2*w[n-1], f8=w[n] + b1*w[n-2],               w[n] -> w[n-1]',   read(a1)
 -----------------------------------------------------------------------------
                y[n]=f8 + f12

 **************************************************************************/

  /*  Subroutine that implements the pseudocode above */

cascaded_biquad:
	bit set mode1 CBUFEN | PEYEN ;			// Enable SIMD mode
    b0 = delaybuf;
    b1 = b0;
    b3 = inbuf;
    b4 = outbuf;
    b9 = coefficients;
    r0 = SECTIONS;

	f8=dm(i3,m1);                               // read inbuf
	r12=r12 xor r12,    f2=dm(i0,m1),  f4=pm(i8,m8);
   	lcntr=r0, do quads until lce;
            f12=f2*f4, 		f8=f8+f12, 	  f3=dm(i0,m1), 	f4=pm(i8,m8);
            f12=f3*f4, 		f8=f8+f12,	  dm(i1,m1)=f3, 	f4=pm(i8,m8);
            f12=f2*f4, 		f8=f8+f12, 	  f2=dm(i0,m1), 	f4=pm(i8,m8);
quads:      f12=f3*f4, 	    f8=f8+f12, 	  dm(i1,m1)=f8, 	f4=pm(i8,m8);
    f8=f8+f12;
    rts (db);
	dm(i4,m1)=f8;
	bit clr mode1 CBUFEN | PEYEN;				  // disable SIMD mode

_Cascaded_IIR_Filter_SIMD.end:


//--------------------------------------------

/*

_processLeft:
	f8=dm(inbuf);
	dm(outbuf)=f8;


_processRight:
	f8=dm(inbuf+1);
	dm(outbuf+1)=f8;

	rts;
*/