Digital Signal Processor Romain Rogister MS T&M

Contents Digital Signal Processing : definition and explanation The typical characteristics of Digital Signal Processors (DSPs) Review of the five generations of DSPs What are the biggest DSPs manufacturers today ?

Digital Signal Processing : definition and explanation

The typical characteristics of Digital Signal Processors (DSPs)

Review of the five generations of DSPs

What are the biggest DSPs manufacturers today ?

Part One Digital Signal Processing

Definition of Digital Signal Processing Signal processing is the analysis, interpretation, and manipulation of signals. Signals can be either analog or digital. Digital signal processing is the study of signals in a digital representation and the processing methods of these signals.

Signal processing is the analysis, interpretation, and manipulation of signals.

Signals can be either analog or digital.

Digital signal processing is the study of signals in a digital representation and the processing methods of these signals.

From analog to digital / From digital to analog The Nyquist-Shannon sampling theorem 16 bits : 65 535 values 24 bits : 16 777 215 values

The Nyquist-Shannon sampling theorem

Engineers study digital signals in the following domains : Time domain Spatial domain Method called Filtering Linear or non-linear filter Causal or non-causal filter Time-invariant or adaptive-filter Stable or unstable filter FIR or IIR Frequency domain Fourier transform

Time domain

Spatial domain

Method called Filtering

Linear or non-linear filter

Causal or non-causal filter

Time-invariant or adaptive-filter

Stable or unstable filter

FIR or IIR

Frequency domain

Fourier transform

Part Two Digital Signal Processors (DSPs)

MAC Operations In computing, especially digital signal processing, multiply-accumulate is a common operation that computes the product of two numbers and adds that product to an accumulator DSPs contain architectural optimizations to speed up processing

Real-Time Computing (RTC) In computer science, real-time computing (RTC) is the study of hardware and software systems which are subject to a "real-time constraint“. The needs of real-time software are often addressed in the context of real-time operating systems, and synchronous programming languages, which provide frameworks on which to build real-time application software.

Fixed -point Arithmetic Most DSPs use fixed-point arithmetic, because in real world signal processing, the additional range provided by floating point is not needed, and there is a large speed benefit and cost benefit due to reduced hardware complexity. However, some versions are available which use floating point arithmetic and are more powerful. Specific applications Cost of Software

However, some versions are available which use floating point arithmetic and are more powerful.

Specific applications

Cost of Software

Sigle Instruction, Multiple Data SIMD (Single Instruction, Multiple Data) is a technique employed to achieve data level parallelism. With a SIMD processor there are two improvements to this process. For one the data is understood to be in blocks, and a number of values can be loaded all at once.

Harvard Architecture Harvard architecture is a computer architecture with physically separate storage and signal pathways for instructions and data.

Pipeline Architecture In computing, a pipeline is a set of data processing elements connected in series, so that the output of one element is the input of the next one. The elements of a pipeline are often executed in parallel.

Part Three From 1980 to 2008: 5 generations of DSPs

Five generations of DSPs

Part Four The Four Biggest Manufacturers

Texas Instrument Founded 1930 (as GSI), 1951 (as TI) Headquarters Dallas, Texas, USA Industry Semiconductors, Electronics Revenue ▲ $14.26 billion USD (2006) Employees ▲ 30,986

Freescale Founded Spin-off from Motorola in 2004 Headquarters Austin, Texas, USA Industry Semiconductors Revenue ▲ $6.4 billion USD (2006) Employees ▲ 24,000

Lucent Technologies Founded Spin-off from AT&T in 1996 Headquarters Murray Hill, New Jersey, USA Industry Telecommunications Revenue ▲ $9.4 billion USD (2005) Employees ▲ 30,500

Analog Devices Founded 1965 Headquarters Norwood, Massachusetts, USA Industry Semiconductors Revenue ▲ $2.6 billion USD (2006) Employees ▲ 8,800

Conclusion The best way to understand the impact of DSP technology on design is to take a detailed look at some of the applications where DSP has established a clear advantage over alternative technologies. Digital Video Audio Biometric Security Telecom Radar or Sonar Control Biomedical Going digital enables developers to exceed their own expectations and provide functionality far beyond that which is possible through analog processing.

What is Digital Signal Processing ? Page  There are two ways to process a signal ? Analog signal processing is any signal processing conducted on analog signals by analog means. "Analog" indicates something that is mathematically represented as a set of continuous values. This differs from "digital" which uses a series of discrete quantities to represent signal. Digital signal processing ( DSP ) is the study of signals in a digital representation and the processing methods of these signals. It includes subfields like: audio and speech signal processing, sonar and radar signal processing, sensor array processing, spectral estimation, statistical signal processing, digital image processing, signal processing for communications, biomedical signal processing, seismic data processing, etc.

There are two ways to process a signal ?

Analog signal processing is any signal processing conducted on analog signals by analog means.

"Analog" indicates something that is mathematically represented as a set of continuous values. This differs from "digital" which uses a series of discrete quantities to represent signal.

Digital signal processing ( DSP ) is the study of signals in a digital representation and the processing methods of these signals.

It includes subfields like: audio and speech signal processing, sonar and radar signal processing, sensor array processing, spectral estimation, statistical signal processing, digital image processing, signal processing for communications, biomedical signal processing, seismic data processing, etc.