COMPUTER ARCHITECTURE & SOFTWARE-DEFINED RADIO NEBU JOHN - - PowerPoint PPT Presentation

NEBU JOHN MATHAI DIRECTOR, ENGINEERING AND ARCHITECTURE

COMPUTER ARCHITECTURE & SOFTWARE-DEFINED RADIO

INTRODUCTION

Communications System Architects Increased Algorithm Complexity More Performance Hardware Architects Higher Performance Substrates

COMPUTER ARCHITECTURE  SDR

New standards, New uses Higher SDR performance Novel Computer Architectures

TRENDS

• Communications standards complexity
• Algorithmic diversity
• Large parameter spaces
• Cross-stack communication
• Processing power
• Flexibility
• Better Language/Compilers
• Express complex ideas correctly
• Efficient mapping

TRENDS

• IOT: Boldly going where no radio has gone before
• Power consumption
• Flexibility
• Malleability
• High Performance Computing
• Scaling: both directions
• Power efficiency
• Architectural diversity

Edge Computing Edge Computing Big Compute Big Compute

HPC

OVERVIEW

• Quick look at history
• Computer architecture  SDR

HISTORY

• C.E. Shannon
• Digital Hardware Engineering
• Information Theory
• A. N. Kolmogorov
• Algorithmic Information Theory
• N. Wiener, W.R. Ashby, …
• systems { convey, store, process } information for control

Computation Communications Control

HOW DID WE GET HERE?

• Constraints and Requirements
• New standards and interfaces
• IOT: malleability, performance, power economy
• Cognitive radio: same
• Advanced sensing: high-performance

Analog to Digital Hard Digital to Soft Digital Canonical to exotic HPC

COMPUTATION

• Map: math -> physical substrate
• Analog
• Variables analogous to physical quantities
• Transistors in linear region
• Digital
• Variables are analogous to abstractions
• Transistors in discrete on/off states

• 1. (A2D) ANALOG COMPLEXITY
• Design Complexity
• Verification Complexity
• Simulation
• Mismatch: ODE and digital computers
• Simplifications
• Validation Complexity
• Smaller-scale vital systems

• 1. (A2D) DIGITAL SOLUTIONS
• Arbitrary precision, dynamic range
• H(z) => hardware implementation
• Control flow
• Scalability
• Tractable Verification + Validation
• Discrete-time simulation directly maps to digital computers
• Integration with software stack

• 1. (A2D) REPERCUSSIONS
• Verification Complexity
• State space explosion
• Adequate stimulation requires lots of time
• Simulation: orders of magnitude slower than real time
• How to practically ensure you’ve covered all cases?

Analog Analog Hard digital Hard digital Soft digital Soft digital

complexity

• 2. (H2S) MAKE IT SOFTWARE’S PROBLEM

Digital Front End Digital Front End Control Knobs Control Processor Control Processor

• Add knobs to the digital front end
• When it becomes impractical to control the knobs …
• … develop schemes to control them via a processor

• 2. (H2S) MAKE IT SOFTWARE’S PROBLEM
• Solves the Design + Verification problem:
• Processors are well-known systems
• Adding features: easy
• Achieving performance: hard
• Innovative architectures to address this

• 3. ARCHITECTURES: BASIC

… Instruction RAM Instruction RAM Data Input RAM Data Input RAM Data Output RAM Data Output RAM Functional Units

• 3. ARCHITECTURES: DSP

… Instruction RAM Instruction RAM Data Input RAM Data Input RAM Data Output RAM Data Output RAM More Functional Units

• 3. ARCHITECTURES: SIMD

… Instruction RAM Instruction RAM Data Input RAM Data Input RAM Data Output RAM Data Output RAM Parallel Functional Units

• 3. ARCHITECTURES: MIMD

… Instruction RAM Instruction RAM Data Input RAM Data Input RAM Data Output RAM Data Output RAM Parallel Independent Functional Units

• 3. ARCHITECTURES: VLIW

Instruction RAM Instruction RAM Data Input RAM Data Input RAM Data Output RAM Data Output RAM

• 3. ARCHITECTURES: GRID

• 3. HETEROGENEOUS SYSTEMS
• Demanding
• Hardware architecture, design and verification
• Software engineering
• Worthwhile
• Ideal performance characteristics