CURRENT ISSUE
Contests
Feature Article
|
|
Issue #204 June 2007
Are You Up for 16 Bits?
A look at Microchip's Family of 16 -Bit Microcontrollers
by Jeff Bachiochi
Start | Microchip's 16-Bit Family |Eeny, Meeny, Miny, Moe | PIC24F | PIC24H | Need DSP? | dsPIC30/33 | Standard Features | Peripheral Pin Select | DSP | DMA | Jump-Start PCBs | SMPS for $750 | Think, Enter, Win | Sources & PDF
|
Function execution times |
|||||||
| Function | Cycle count equation | Conditions | Number of cycles | Execution time at 40 MIPS | |||
| Complex FFT** | — | N = 64 | 3,739 | 93.4 µs | |||
| Complex FFT** | — | N = 128 | 8,485 | 212.1 µs | |||
| Complex FFT** | — | N = 256 | 19,055 | 476.4 µs | |||
| Block FIR | 53 + N (4 + M) | N = 32, M = 32 | 1,205 | 30.1 µs | |||
| Block FIR lattice | 41 + N (4 + 7 M) | N = 32, M = 32 | 7,337 | 183.4 µs | |||
| Block IIR canonic | 36 + N (8 + 7 S) | N = 32, S = 4 | 1,188 | 29.7 µs | |||
| Block IIR lattice | 46 + N (16 + 7 M) | N = 32, M = 8 | 2,350 | 58.7 µs | |||
| Matrix add | 20 + 3 (C × R) | C = 8, R = 8 | 212 | 5.3 µs | |||
| Matrix transpose | 16 + C (6 + 3 (R – 1)) | C = 8, R = 8 | 232 | 5.8 µs | |||
| Vector dot product | 17 + 3N | N = 32 | 113 | 2.9 µ | |||
| Vector max | 19 + 7 (N – 2) | N = 32 | 229 | 5.7 µs | |||
| Vector multiply | 17 + 4 N | N = 32 | 145 | 3.6 µs | |||
| Vector power | 16 + 2 N | N = 32 | 80 | 2 µs | |||
| Proportional integral derivative (PID) | 30 | N = 1 | 30 | 0.75 µs | |||
| *C = #columns, N = # samples, M = #taps, S = #sections, R = #rows | |||||||
| **Complex FFT routine inherently prevents overflow | |||||||
| Table 2—This table will give you a feel for the execution times you can expect when using the DSP algorithm library. The PID function is the latest to be included in this free library. | |||||||
|