Electrical engineering

Physics

Chip

Inefficiency

Application-specific integrated circuit

Operating system

Algorithm

Encoder

Computer architecture

Encoding (memory)

Engineering

Parallel computing

Embedded system

SIMD

Artificial intelligence

Economics

Microeconomics

Volume (thermodynamics)

Efficient energy use

General purpose

Computer science

Computation

Quantum mechanics

Computer hardware

Telecommunications

Due to their high volume, general-purpose processors, and now chip multiprocessors (CMPs), are much more cost effective than ASICs, but lag significantly in terms of performance and energy efficiency. This paper explores the sources of these performance and energy overheads in general-purpose processing systems by quantifying the overheads of a 720p HD H.264 encoder running on a general-purpose CMP system. It then explores methods to eliminate these overheads by transforming the CPU into a specialized system for H.264 encoding. We evaluate the gains from customizations useful to broad classes of algorithms, such as SIMD units, as well as those specific to particular computation, such as customized storage and functional units.

Understanding sources of inefficiency in general-purpose chips