Texas Instruments TMS320C67 DSP Series Programmer's Reference Manual page 56

Special Requirements
Implementation Notes
xl1_1 = x7 - x3;
if (radix == 2)
{
xl0_0 = x4;
xl1_0 = x5;
xl1_1 = x6;
xl0_1 = x7;
}
yt2 = xl0_0 + xl1_1;
yt3 = xl1_0 + xl0_1;
yt6 = xl0_0 - xl1_1;
yt7 = xl1_0 - xl0_1;
y0[k] = yt0/n_max; y0[k+1] = yt1/n_max;
k += n_max>>1;
y0[k] = yt2/n_max; y0[k+1] = yt3/n_max;
k += n_max>>1;
y0[k] = yt4/n_max; y0[k+1] = yt5/n_max;
k += n_max>>1;
y0[k] = yt6/n_max; y0[k+1] = yt7/n_max;
}
}
N must be a power of 2 and N ≥ 8, N ≤ 16384 points.
-
-
Complex time data x and twiddle facotrs w are aligned on double-word
boundares. Real values are stored in even word positions and imaginary
values in odd positions.
-
All data is in single-precision floating-point format. The complex frequency
data will be returned in linear order.
-
x must be padded with 16 words at the end.
-
A special sequence of coeffs. used as generated above produces the ifft.
This collapses the inner 2 loops in the traditional Burrus and Parks imple-
mentation Fortran code.
-
The revised FFT uses a redundant sequence of twiddle factors to allow a
linear access through the data. This linear access enables data and in-
struction level parallelism.
DSPF_sp_ifftSPxSP
DSPLIB Reference 4-31