Differences Between the C64x and C64x+ DSPLIBs
3.4 Differences Between the C64x and C64x+ DSPLIBs
The C64x+ DSPLIB was developed by optimizing some of the functions of the C64x DSPLIB to take advantage of the C64x+ architecture.
Table 3−10 shows the optimized functions for the C64x+ DSPLIB.
There are two optimization types:
-SPLOOP conversion: Optimized code uses SPLOOP to provide interruptibility and decrease power consumption. The new C64x+ instructions do not increase algorithm performance, and thus, are not used.
-Kernel redesign, SPLOOP: Kernel of algorithm rewritten to take advantage of the new C64x+ instructions and of the SPLOOP feature.
Table 3−10. Functions Optimized in the C64x+ DSPLIB
Function | C64x+ Optimized | Optimization Type |
DSP_firlms2 | No |
|
DSP_autocor | No |
|
DSP_autocor_rA8 | Yes | Kernel re−design, SPLOOP |
|
| Optimization resulted in new |
|
| requirements. New name is used. |
DSP_fft16x16 | Yes | New Function Optimized C64x+ |
DSP_fft16x16_imre | Yes | New Function Optimized C64x+ |
DSP_fft16x16r | Yes | Kernel re−design, SPLOOP |
DSP_fft16x32 | Yes | Kernel re−design, SPLOOP |
DSP_fft32x32 | Yes | Kernel re−design, SPLOOP |
DSP_fft32x32s | Yes | Kernel re−design, SPLOOP |
DSP_ifft16x16 | Yes | New Function Optimized C64x+ |
DSP_ifft16x16_imre | Yes | New Function Optimized C64x+ |
DSP_ifft16x32 | Yes | Kernel re−design, SPLOOP |
DSP_ifft32x32 | Yes | Kernel re−design, SPLOOP |
DSP_fir_cplx | No |
|
|
|
|
