Rewriting Strategies and Strategic Rewrite Programs

Kirchner, Hélène

doi:10.1007/978-3-319-23165-5_18

Cited by 11 publications

(8 citation statements)

References 58 publications

(83 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach is generally fast, but complicates support for cyclic or expansive rules, and makes both rewriting performance and output quality dependent on fine-grained rule orderings. Past work has extensively investigated how to mitigate these challenges by scheduling rules [Barendregt et al 1987;Borovanskỳ et al 1998;Dershowitz 1982;Knuth and Bendix 1983], special casing cyclic and expansive rules [Bachmair et al 2000;Dershowitz 1987;Eker 2003;Lucas 2001], and efficiently implementing rewrite rule-based search [Clavel et al 2007;Kirchner 2015;Visser 2001a,b]. Many systems still rely on ad hoc rule orderings and heuristic mitigations developed through trial and error, though recent work [Newcomb et al 2020] has demonstrated how reduction orders [Baader and Nipkow 1998] can be automatically synthesized and then used to effectively guide destructive term rewriting systems.…”

Section: Implementing Rewrite Systemsmentioning

confidence: 99%

Rewrite Rule Inference Using Equality Saturation

Nandi¹,

Willsey²,

Zhu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Many compilers, synthesizers, and theorem provers rely on rewrite rules to simplify expressions or prove equivalences. Developing rewrite rules can be difficult: rules may be subtly incorrect, profitable rules are easy to miss, and rulesets must be rechecked or extended whenever semantics are tweaked. Large rulesets can also be challenging to apply: redundant rules slow down rule-based search and frustrate debugging.This paper explores how equality saturation, a promising technique that uses e-graphs to apply rewrite rules, can also be used to infer rewrite rules. E-graphs can compactly represent the exponentially large sets of enumerated terms and potential rewrite rules. We show that equality saturation efficiently shrinks both sets, leading to faster synthesis of smaller, more general rulesets.We prototyped these strategies in a tool dubbed Ruler. Compared to a similar tool built on CVC4, Ruler synthesizes 5.8× smaller rulesets 25× faster without compromising on proving power. In an end-to-end case study, we show Ruler-synthesized rules which perform as well as those crafted by domain experts, and addressed a longstanding issue in a popular open source tool.

show abstract

Section: Implementing Rewrite Systemsmentioning

confidence: 99%

Rewrite Rule Inference Using Equality Saturation

Nandi¹,

Willsey²,

Zhu³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Program transformations using rewrite rules and strategy languages have since been used in different domains including reverse engineering [Chikofsky and II 1990], refactoring [Fowler 1999], and obfuscation [Collberg et al 1998]. Visser [Visser 2001b[Visser , 2005 and Kirchner [Kirchner 2015] provide surveys covering term rewriting, strategy languages and their application domains. Tactic languages including [Delahaye 2000] and [Felty 1993] are related to strategy languages but are designed for specifying proofs in theorem provers.…”

Section: Related Workmentioning

confidence: 99%

“…ELEVATE is inspired by strategy languages for rewrite systems ś mainly unknown to the high-performance community ś such as Stratego by Visser [2001a]. Kirchner [2015] provides a recent overview of the rewriting community's research. Figure 1 shows an overview of our approach showing the compilation flow from a high-level program and an optimization strategy to high-performance code.…”

Section: Introductionmentioning

confidence: 99%

Achieving high-performance the functional way: a functional pearl on expressing high-performance optimizations as rewrite strategies

Hagedorn

Lenfers

Kœhler

et al. 2020

Proc. ACM Program. Lang.

View full text Add to dashboard Cite

Optimizing programs to run efficiently on modern parallel hardware is hard but crucial for many applications. The predominantly used imperative languages-like C or OpenCL-force the programmer to intertwine the code describing functionality and optimizations. This results in a portability nightmare that is particularly problematic given the accelerating trend towards specialized hardware devices to further increase efficiency. Many emerging DSLs used in performance demanding domains such as deep learning or high-performance image processing attempt to simplify or even fully automate the optimization process. Using a high-level-often functional-language, programmers focus on describing functionality in a declarative way. In some systems such as Halide or TVM, a separate schedule specifies how the program should be optimized. Unfortunately, these schedules are not written in well-defined programming languages. Instead, they are implemented as a set of ad-hoc predefined APIs that the compiler writers have exposed. In this functional pearl, we show how to employ functional programming techniques to solve this challenge with elegance. We present two functional languages that work together-each addressing a separate concern. RISE is a functional language for expressing computations using well known functional data-parallel patterns. ELEVATE is a functional language for describing optimization strategies. A high-level RISE program is transformed into a low-level form using optimization strategies written in ELEVATE. From the rewritten low-level program high-performance parallel code is automatically generated. In contrast to existing high-performance domain-specific systems with scheduling APIs, in our approach programmers are not restricted to a set of built-in operations and optimizations but freely define their own computational patterns in RISE and optimization strategies in ELEVATE in a composable and reusable way. We show how our holistic functional approach achieves competitive performance with the state-of-the-art imperative systems Halide and TVM. CCS Concepts: • Software and its engineering → Functional languages; Compilers; • Theory of computation → Rewrite systems.

show abstract

“…While rewrite rules are a straightforward choice for encoding single program transformation, it might be required to apply a rule only to a subpart of a program, multiple rules in a specific order, or en-/disable rules during a specific phase. To control the application of rewrite rules, strategy languages such as Stratego [3,38] have been proposed -Kirchner [21] provides a recent overview of the field. These strategy languages enable strategic rewriting by composing individual rewrite rules into larger rewrite strategies that encode the transformation of an entire program.…”

Section: Introductionmentioning

confidence: 99%

Row-Polymorphic Types for Strategic Rewriting

Fu¹,

Qin²,

Dardha³

et al. 2021

Preprint

View full text Add to dashboard Cite

We present a type system for strategy languages that express program transformations as compositions of rewrite rules. Our row-polymorphic type system assists compiler engineers to write correct strategies by statically rejecting non meaningful compositions of rewrites that otherwise would fail during rewriting at runtime. Furthermore, our type system enables reasoning about how rewriting transforms the shape of the computational program. We present a formalization of our language at its type system and demonstrate its practical use for expressing compiler optimization strategies.Our type system builds the foundation for many interesting future applications, including verifying the correctness of program transformations and synthesizing program transformations from specifications encoded as types.

show abstract

Rewriting Strategies and Strategic Rewrite Programs

Cited by 11 publications

References 58 publications

Rewrite Rule Inference Using Equality Saturation

Rewrite Rule Inference Using Equality Saturation

Achieving high-performance the functional way: a functional pearl on expressing high-performance optimizations as rewrite strategies

Row-Polymorphic Types for Strategic Rewriting

Contact Info

Product

Resources

About