| ??? 08/02/10 08:01 Modified: 08/02/10 10:23 Read: times |
#177565 - Digitial signal processing is mainly math. Responding to: ???'s previous message |
Joseph Hebert said:
But strictly speaking, a UART stream is an analog signal in a time domain. Think of one on an oscilloscope. And when you read it into the receiving unit it's turned back into a digital sequence. Is that not digital signal processing? Not quite yet. Digital signal processing describes the application of mathematical algorithms to signals that time-discrete (i.e. "sampled") and value-discrete (i.e. "digital"). How those signals are generated isn't the concern of DSP. In real-world applications, they're usually the result of some form of analog-to-digital conversion, but it's perfectly possible to perform DSP on signals that have never seen the analog world (e.g. the output of a pseudo-RNG). Similarly, what is the defining characteristic or property that would make a piece of hardware a DSP (as in a noun). Does adding a MAC make an otherwise µ-processor/controller a DSP? I'd consider a MAC unit a necessary, but not sufficient feature to call a piece of hardware a "DSP". Most ARM cores come with MAC units, but they still usually lack things like sophisticated DMA, bit-reversed addressing, specialized instructions for things like polynomial evaluation, FIR filters, zero-overhead loops, etc, that a "true" DSP would have. DSPs are supposed to be the "swiss army knife" for all tasks that involve signal processing. Conversely, does the absence of a MAC then preclude a piece of hardware from being considered a DSP? I'd say so. (A "DSP" without a MAC unit would correspond to a Swiss Army Knife without a blade). |
| Topic | Author | Date |
| µ-controllers, µ-processors and DSPs | 01/01/70 00:00 | |
| No-on last question. | 01/01/70 00:00 | |
| early DSP's had no converters | 01/01/70 00:00 | |
| Signal Processing | 01/01/70 00:00 | |
Digitial signal processing is mainly math. | 01/01/70 00:00 | |
| it's all marketing | 01/01/70 00:00 | |
| There really isn't a true distinction anymore. | 01/01/70 00:00 | |
| 8051 + MAC | 01/01/70 00:00 | |
| I know. | 01/01/70 00:00 | |
| There is some confusion.... | 01/01/70 00:00 | |
| DSP designed for concurrency of simple operations | 01/01/70 00:00 | |
| Still some confusion... | 01/01/70 00:00 | |
| processor/processing, and absolute time contra clock cycles | 01/01/70 00:00 | |
| You're being too practical | 01/01/70 00:00 | |
| No magic ISR advantage for uC in relation to uP | 01/01/70 00:00 |