Automatic Parallelization and Optimization of Programs by Proof Rewriting

Hurlin, Clément

doi:10.1007/978-3-642-03237-0_6

Cited by 9 publications

(5 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These internal dependencies can be used to inject safe parallelism. This insight is due to Raza et al [2009], Cook et al [2010], and Hurlin [2009], both of which propose parallelization analyses based on separation logic. The analyses proposed in these papers are much more conservative than ours, in that they discover independence which already exists between commands of the program.…”

Section: Related Work In Detailmentioning

confidence: 93%

“…They do not insert synchronization constructs, and consequently cannot enforce sequential dependencies among concurrent computations that share and modify state. Indeed, Raza et al [2009] do not consider any program transformations, since the goal of that work is to identify memory separation of different commands, while Hurlin [2009] expresses optimizations as reordering rewrites on proof trees. Bell et al [2009] construct a proof of an already-transformed multithreaded program parallelized by the DSWP transformation [Ottoni et al 2005].…”

Section: Related Work In Detailmentioning

confidence: 99%

See 1 more Smart Citation

Proof-Directed Parallelization Synthesis by Separation Logic

Botinčan

Dodds

Jagannathan

2013

ACM Trans. Program. Lang. Syst.

View full text Add to dashboard Cite

We present an analysis which takes as its input a sequential program, augmented with annotations indicating potential parallelization opportunities, and a sequential proof, written in separation logic, and produces a correctly synchronized parallelized program and proof of that program. Unlike previous work, ours is not a simple independence analysis that admits parallelization only when threads do not interfere; rather, we insert synchronization to preserve dependencies in the sequential program that might be violated by a naïve translation. Separation logic allows us to parallelize fine-grained patterns of resource usage, moving beyond straightforward points-to analysis. The sequential proof need only represent shape properties, meaning we can handle complex algorithms without verifying every aspect of their behavior.Our analysis works by using the sequential proof to discover dependencies between different parts of the program. It leverages these discovered dependencies to guide the insertion of synchronization primitives into the parallelized program, and to ensure that the resulting parallelized program satisfies the same specification as the original sequential program, and exhibits the same sequential behavior. Our analysis is built using frame inference and abduction, two techniques supported by an increasing number of separation logic tools. ACM Reference Format:Botinčan, M., Dodds, M., and Jagannathan, S. 2013. Proof-directed parallelization synthesis by separation logic.

show abstract

Section: Related Work In Detailmentioning

confidence: 93%

Section: Related Work In Detailmentioning

confidence: 99%

Proof-Directed Parallelization Synthesis by Separation Logic

Botinčan

Dodds

Jagannathan

2013

ACM Trans. Program. Lang. Syst.

View full text Add to dashboard Cite

show abstract

“…These internal dependencies can be used to inject safe parallelism. This insight is due to [13,31] and [24], both of which propose parallelization analyses based on separation logic. The analyses proposed in these papers are much more conservative than ours, in that they discover independence which already exists between commands of the program.…”

Section: Related Workmentioning

confidence: 99%

“…They do not insert synchronization constructs, and consequently cannot enforce sequential dependencies among concurrent computations that share and modify state. Indeed, [31] does not consider any program transformations, since the goal of that work is to identify memory separation of different commands, while [24] expresses optimizations as reordering rewrites on proof trees.…”

Section: Related Workmentioning

confidence: 99%

Resource-sensitive synchronization inference by abduction

2012

View full text Add to dashboard Cite

We present an analysis which takes as its input a sequential program, augmented with annotations indicating potential parallelization opportunities, and a sequential proof, written in separation logic, and produces a correctly-synchronized parallelized program and proof of that program. Unlike previous work, ours is not an independence analysis; we insert synchronization constructs to preserve relevant dependencies found in the sequential program that may otherwise be violated by a naïve translation. Separation logic allows us to parallelize fine-grained patterns of resource-usage, moving beyond straightforward points-to analysis.Our analysis works by using the sequential proof to discover dependencies between different parts of the program. It leverages these discovered dependencies to guide the insertion of synchronization primitives into the parallelized program, and to ensure that the resulting parallelized program satisfies the same specification as the original sequential program, and exhibits the same sequential behaviour. Our analysis is built using frame inference and abduction, two techniques supported by an increasing number of separation logic tools.

show abstract

“…Hurlin shows how to parallelize a sequential program's proof, using rewrite rules on its derivation tree, for the DOALL optimization [7]. We demonstrate how to prove a DSWP-parallelized program without using the proof's derivation tree, but we assume a proof structure that may not characterize all proofs.…”

Section: Related Workmentioning

confidence: 99%

Concurrent Separation Logic for Pipelined Parallelization

2010

View full text Add to dashboard Cite

Abstract. Recent innovations in automatic parallelizing compilers are showing impressive speedups on multicore processors using shared memory with asynchronous channels. We have formulated an operational semantics and proved sound a concurrent separation logic to reason about multithreaded programs that communicate asynchronously through channels and share memory. Our logic supports shared channel endpoints (multiple producers and consumers) and introduces histories to overcome limitations with local reasoning. We demonstrate how to transform a sequential proof into a parallelized proof that targets the output of the parallelizing optimization DSWP (Decoupled Software Pipelining).

show abstract

Automatic Parallelization and Optimization of Programs by Proof Rewriting

Cited by 9 publications

References 31 publications

Proof-Directed Parallelization Synthesis by Separation Logic

Proof-Directed Parallelization Synthesis by Separation Logic

Resource-sensitive synchronization inference by abduction

Concurrent Separation Logic for Pipelined Parallelization

Contact Info

Product

Resources

About