• Home
  • Search
  • Integer linear programming vs. graph-based methods in code generation
  • Cite Icon12
  • https://doi.org/10.22028/d291-25801Copy DOI Icon

Integer linear programming vs. graph-based methods in code generation

Show More
  • Abstract
  • Literature Map
  • Citations
  • Similar Papers
Abstract

A common characterictic of many applications is that they are aimed at the high-volume consumer market, which is extremely cost-sensitive. However many of them impose stringent performance demands on the underlying system. Therefore the code generation must take into account the restrictions and features given by the target architecture while satisfying these performance demands. High-level language compilers often are unable to generate code meeting these requirements. One reason is the phase coupling problem between instruction scheduling and register allocation. Many compilers perform these tasks separately with each phase ignorant of the require- ments of the other. Commonly, each task is accomplished by using heuristic methods. As the goals of the two phases often conflict, whichever phase is performed first imposes constraints on the other, sometimes producing inefficient code. Integer linear programming (ILP) provides an integrated approach to the combined instruction scheduling and register allocation problem. This way, optimal solutions can be found - albeit at the cost of high compilation times. In our experiments, we considered as target processor the 32-bit DSP ADSP-2106x. We have examined two different ILP formulations and compared them with conventional approaches including list scheduling and the critical path method. Moreover, we have investigated approximations based on the ILP formulations; this way, compilation time can be reduced considerably while still producing near-optimal results. From the results of our implementation, we have concluded that integrating ILP formulations in conventional global algorithms is a promising method for generating high-quality code.

Similar Papers
  • Book Chapter
  • Citations23

Optimal Integrated VLIW Code Generation with Integer Linear Programming

  • Jan 01, 2006
  • Andrzej Bednarski +1
  • Research Article
  • Citations50

Using integer linear programming for instruction scheduling and register allocation in multi-issue processors

  • Nov 01, 1997
  • Computers & Mathematics with Applications
  • Chia-Ming Chang +2
  • Research Article
  • Citations9

An Efficient WCET-Aware Instruction Scheduling and Register Allocation Approach for Clustered VLIW Processors

  • Sep 27, 2017
  • ACM Transactions on Embedded Computing Systems
  • Xuesong Su +2
  • Book Chapter
  • Citations23

Register Allocation and Optimal Spill Code Scheduling in Software Pipelined Loops Using 0-1 Integer Linear Programming Formulation

  • Mar 26, 2007
  • Santosh G Nagarakatte +1
  • Research Article
  • Citations11

Evolutionary Algorithms for Instruction Scheduling, Operation Merging, and Register Allocation in VLIW Compilers

  • Jan 17, 2020
  • Journal of Signal Processing Systems
  • Florian Giesemann +2
  • Book Chapter
  • Citations21

Code Optimization by Integer Linear Programming

  • Jan 01, 1999
  • Daniel Kästner +1
  • Research Article
  • Citations11

A Dynamic Programming Approach to Optimal Integrated Code Generation

  • Aug 01, 2001
  • ACM SIGPLAN Notices
  • Christoph Keßler +1
  • Conference Article
  • Citations11

A Dynamic Programming Approach to Optimal Integrated Code Generation

  • Aug 01, 2001
  • Christoph Keßler +1
  • Conference Article
  • Citations22

New Techniques for Efficient Traffic Grooming in WDM Mesh Networks

  • Aug 01, 2007
  • Arunita Jaekel +3
  • Research Article
  • Citations6

Taming the Duplication-Loss-Coalescence Model with Integer Linear Programming.

  • Apr 16, 2021
  • Journal of Computational Biology
  • Jarosław Paszek +3
  • Book Chapter
  • Citations2

Integer Linear Programming Formulation for the Unified Duplication-Loss-Coalescence Model

  • Jan 01, 2020
  • Javad Ansarifar +3
  • Research Article
  • Citations2

Fast, frequency‐based, integrated register allocation and instruction scheduling

  • Nov 06, 2007
  • Software: Practice and Experience
  • Ioana Cutcutache +1
  • Conference Article
  • Citations3

Survivable traffic grooming for scheduled demands

  • Sep 01, 2008
  • Arunita Jaekel +2
  • Conference Article
  • Citations9

Reducing the complexity of ILP formulations for synthesis

  • Nov 22, 2002
  • A Mignotte +1
  • Research Article
  • Citations18

Survey on Combinatorial Register Allocation and Instruction Scheduling

  • Jun 18, 2019
  • ACM Computing Surveys
  • Roberto Castañeda Lozano +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.