Branch Optimisation Techniques for Hardware Compilation

نویسندگان

  • Henry Styles
  • Wayne Luk
چکیده

This paper explores using information about program branch probabilities to optimise reconfigurable designs. The basic premise is to promote utilization by dedicating more resources to branches which execute more frequently. A hardware compilation system has been developed for producing designs which are optimised for different branch probabilities. We propose an analytical queueing network performance model to determine the best design from observed branch probability information. The branch optimisation space is characterized in an experimental study for Xilinx Virtex FPGAs of two complex applications: video feature extraction and progressive refinement radiosity. For designs of equal performance, branch-optimised designs require 24% and 27.5% less area. For designs of equal area, branch optimised designs run upto 3 times faster. Our analytical performance model is shown to be highly accurate with relative error between 0.12 and .

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Compiling Policy Descriptions into Reconfigurable Firewall Processors

We describe a framework for capturing firewall requirements as high-level descriptions based on the policy specification language Ponder. The framework provides abstraction from hardware implementation while allowing performance control through constraints. Our hardware compilation strategy for such descriptions involves a rule reduction step to produce a hardware firewall rule representation. ...

متن کامل

Area Optimisation in SystemC Hardware Compilation

Hardware compilation translates a program written in a high-level language into a description of a hardware circuit. Hardware compilation shortens development time compared to traditional hardware design. However, currently it often produces less efficient hardware, measured in speed and logic area. This report describes three methods to improve logic area of a design. The first method is resou...

متن کامل

Provably Correct Hardware Compilation using Timing Diagrams

In this article we present a framework within which hardware implementations are proven correct from speciications given in an OCCAM-like language called Handel by the use of a robust set of mathematical trans-formational laws. The semantical basis for Handel and its hardware implementations are simple functions of time which are called timing diagrams. This basis allows to denote the abstract ...

متن کامل

Research Proposal : Michael O ’ Boyle

This project aims to develop a new framework which enables compilers to adapt with and exploit the exponential growth in hardware performance. This is achieved by systematically describing the program optimisation space and by developing new approaches to explore this space in a manner independent of application or underlying architecture. Furthermore, by transcending the distinction between co...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2003