Code reordering and speculation support for dynamic optimization systems

E. M. Nystrom, R. D. Barnes, M. C. Merten, Wen-Mei W Hwu

Research output: Contribution to journalConference article

Abstract

For dynamic optimization systems, success is limited by two difficult problems arising from instruction reordering. Following optimization within and across basic block boundaries, both the ordering of exceptions and the observed processor register contents at each exception point must be consistent with the original code. While compilers traditionally utilize global data-flow analysis to determine which registers require preservation, this analysis is often infeasible in dynamic optimization systems due to both strict time/space constraints and incomplete code discovery. This paper presents an approach called Precise Speculation that addresses these problems. The proposed mechanism is a component of our vision for Run-time Optimization ARchitecture, or ROAR, to support aggressive dynamic optimization of programs. It utilizes a hardware mechanism to automatically recover the precise register states when a deferred exception is reported, utilizing the original unoptimized code to perform all recovery. We observe that Precise Speculation enables a dynamic optimization system to achieve a large performance gain over aggressively optimized base code, while preserving precise exceptions. For an 8-issue EPIC processor, the dynamic optimizer achieves between 3.6% and 57% speedup over a full-strength optimizing compiler that employs profile-guided optimization.

Original languageEnglish (US)
Pages (from-to)163-174
Number of pages12
JournalParallel Architectures and Compilation Techniques - Conference Proceedings, PACT
StatePublished - Jan 1 2001
EventInternatinal Conference on Parallel Architectures and Compilation Techniques PACT 2001 - Barcelona, Spain
Duration: Sep 8 2001Sep 12 2001

Fingerprint

Speculation
Dynamic Optimization
Reordering
Exception
Optimization
Optimizing Compilers
Data Flow
Compiler
Preservation
Speedup
Data flow analysis
Recovery
Hardware

ASJC Scopus subject areas

  • Software
  • Theoretical Computer Science
  • Hardware and Architecture

Cite this

Code reordering and speculation support for dynamic optimization systems. / Nystrom, E. M.; Barnes, R. D.; Merten, M. C.; Hwu, Wen-Mei W.

In: Parallel Architectures and Compilation Techniques - Conference Proceedings, PACT, 01.01.2001, p. 163-174.

Research output: Contribution to journalConference article

@article{98e61cd79e2a400e9e91641f70d389c1,
title = "Code reordering and speculation support for dynamic optimization systems",
abstract = "For dynamic optimization systems, success is limited by two difficult problems arising from instruction reordering. Following optimization within and across basic block boundaries, both the ordering of exceptions and the observed processor register contents at each exception point must be consistent with the original code. While compilers traditionally utilize global data-flow analysis to determine which registers require preservation, this analysis is often infeasible in dynamic optimization systems due to both strict time/space constraints and incomplete code discovery. This paper presents an approach called Precise Speculation that addresses these problems. The proposed mechanism is a component of our vision for Run-time Optimization ARchitecture, or ROAR, to support aggressive dynamic optimization of programs. It utilizes a hardware mechanism to automatically recover the precise register states when a deferred exception is reported, utilizing the original unoptimized code to perform all recovery. We observe that Precise Speculation enables a dynamic optimization system to achieve a large performance gain over aggressively optimized base code, while preserving precise exceptions. For an 8-issue EPIC processor, the dynamic optimizer achieves between 3.6{\%} and 57{\%} speedup over a full-strength optimizing compiler that employs profile-guided optimization.",
author = "Nystrom, {E. M.} and Barnes, {R. D.} and Merten, {M. C.} and Hwu, {Wen-Mei W}",
year = "2001",
month = "1",
day = "1",
language = "English (US)",
pages = "163--174",
journal = "Parallel Architectures and Compilation Techniques - Conference Proceedings, PACT",
issn = "1089-795X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Code reordering and speculation support for dynamic optimization systems

AU - Nystrom, E. M.

AU - Barnes, R. D.

AU - Merten, M. C.

AU - Hwu, Wen-Mei W

PY - 2001/1/1

Y1 - 2001/1/1

N2 - For dynamic optimization systems, success is limited by two difficult problems arising from instruction reordering. Following optimization within and across basic block boundaries, both the ordering of exceptions and the observed processor register contents at each exception point must be consistent with the original code. While compilers traditionally utilize global data-flow analysis to determine which registers require preservation, this analysis is often infeasible in dynamic optimization systems due to both strict time/space constraints and incomplete code discovery. This paper presents an approach called Precise Speculation that addresses these problems. The proposed mechanism is a component of our vision for Run-time Optimization ARchitecture, or ROAR, to support aggressive dynamic optimization of programs. It utilizes a hardware mechanism to automatically recover the precise register states when a deferred exception is reported, utilizing the original unoptimized code to perform all recovery. We observe that Precise Speculation enables a dynamic optimization system to achieve a large performance gain over aggressively optimized base code, while preserving precise exceptions. For an 8-issue EPIC processor, the dynamic optimizer achieves between 3.6% and 57% speedup over a full-strength optimizing compiler that employs profile-guided optimization.

AB - For dynamic optimization systems, success is limited by two difficult problems arising from instruction reordering. Following optimization within and across basic block boundaries, both the ordering of exceptions and the observed processor register contents at each exception point must be consistent with the original code. While compilers traditionally utilize global data-flow analysis to determine which registers require preservation, this analysis is often infeasible in dynamic optimization systems due to both strict time/space constraints and incomplete code discovery. This paper presents an approach called Precise Speculation that addresses these problems. The proposed mechanism is a component of our vision for Run-time Optimization ARchitecture, or ROAR, to support aggressive dynamic optimization of programs. It utilizes a hardware mechanism to automatically recover the precise register states when a deferred exception is reported, utilizing the original unoptimized code to perform all recovery. We observe that Precise Speculation enables a dynamic optimization system to achieve a large performance gain over aggressively optimized base code, while preserving precise exceptions. For an 8-issue EPIC processor, the dynamic optimizer achieves between 3.6% and 57% speedup over a full-strength optimizing compiler that employs profile-guided optimization.

UR - http://www.scopus.com/inward/record.url?scp=0035177608&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035177608&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0035177608

SP - 163

EP - 174

JO - Parallel Architectures and Compilation Techniques - Conference Proceedings, PACT

JF - Parallel Architectures and Compilation Techniques - Conference Proceedings, PACT

SN - 1089-795X

ER -