Register allocation for predicated code

Current compilers for VLIW and superscalar machines increase the instruction level parallelism of an application by merging several basic blocks into an enlarged predicated block, resulting in higher performance code but increased register requirements. We present a framework that computes precisely...

Full description

Saved in:
Bibliographic Details
Main Authors: Eichenberger, A.E., Davidson, E.S.
Format: Conference Proceeding
Language:English
Subjects:
Application software
Computer architecture
Interference
Kernel
Laboratories
Merging
Parallel processing
Pipeline processing
Registers
VLIW
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Current compilers for VLIW and superscalar machines increase the instruction level parallelism of an application by merging several basic blocks into an enlarged predicated block, resulting in higher performance code but increased register requirements. We present a framework that computes precisely the interferences among virtual registers in the presence of predicated operations. Graph-coloring biased register allocators can directly use the resulting interference graph. For interval-graph based register allocators, and others, we propose a technique that reduces the register requirements by allowing non-interfering virtual registers that overlap in time to share a common virtual register. Preliminary measurements on a benchmark of loops from the Perfect Club, SPEC-89, and the Livermore Fortran Kernels indicate the effectiveness of this technique.
ISSN:1072-4451
DOI:10.1109/MICRO.1995.476825