Near-Optimal Instruction Selection on DAGs

Near-Optimal Instruction Selection on DAGs (2008)

by David Ryan Koes , Seth Copen Goldstein

Citations:

2 - 2 self

User correction supplied by mph

Datum	Value	Source
TITLE	Near-Optimal Instruction Selection on DAGs	user correction
AUTHOR NAME	David Ryan Koes	user correction
AUTHOR AFFIL	School of Computer Science; Carnegie Mellon University	user correction
AUTHOR ADDR	Pittsburgh, PA 15213	user correction
AUTHOR NAME	Seth Copen Goldstein	user correction
ABSTRACT	Instruction selection is a key component of code generation. High quality instruction selection is of particular importance in the embedded space where complex instruction sets are common and code size is a prime concern. Although instruction selection on tree expressions is a well understood and easily solved problem, instruction selection on directed acyclic graphs is NP-complete. In this paper we present NOLTIS, a near-optimal, linear time instruction selection algorithm for DAG expressions. NOLTIS is easy to implement, fast, and effective with a demonstrated average code size improvement of 5.1 % compared to the traditional tree decomposition and tiling approach.	SVM HeaderParse 0.2
YEAR	2008	user correction
CITATIONS	36 found	ParsCit 1.0