Code Translation with Compiler Representations

Szafraniec, Marc; Rozière, Baptiste; Leather, Hugh; Charton, François; Labatut, Patrick; Synnaeve, Gabriel

doi:10.48550/arxiv.2207.03578

Cited by 5 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural Machine Translation. Since the advent of sequence to sequence models [64], neural machine translation has been applied to programming language translation tasks [11,12,26], including unsupervised settings [13,55,65]. Training data is often extracted from coding websites [42].…”

Section: Other Approachesmentioning

confidence: 99%

C2TACO: Lifting Tensor Code to TACO

Magalhães,

Woodruff,

Polgreen

et al. 2023

Proceedings of the 22nd ACM SIGPLAN International Conference on Generative Programming: Concepts and Experiences

View full text Add to dashboard Cite

Domain-specific languages (DSLs) promise a significant performance and portability advantage over traditional languages. DSLs are designed to be high-level and platformindependent, allowing an optimizing compiler significant leeway when targeting a particular device. Such languages are particularly popular with emerging tensor algebra workloads. However, DSLs present their own challenge: they require programmers to learn new programming languages and put in significant effort to migrate legacy code.We present C2TACO, a synthesis tool for synthesizing TACO, a well-known tensor DSL, from C code. We develop a guided enumerative synthesizer that uses automatically generated IO examples and source-code analysis to efficiently generate dense tensor algebra code. C2TACO is able to synthesize 95% benchmarks from a tensor benchmark suite, outperforming an alternative neural machine translation technique, and demonstrates substantially higher levels of accuracy when evaluated against two state-of-the-art existing schemes, TF-Coder and ChatGPT. Our synthesized TACO programs are, by design, portable achieving significant performance improvement when evaluated on a multi-core and GPU platform.

show abstract

Section: Other Approachesmentioning

confidence: 99%

C2TACO: Lifting Tensor Code to TACO

Magalhães,

Woodruff,

Polgreen

et al. 2023

Proceedings of the 22nd ACM SIGPLAN International Conference on Generative Programming: Concepts and Experiences

View full text Add to dashboard Cite

show abstract

“…It compiles source code from different languages into distilled code representation firstly and then decompile this intermediate representation into the target language. Szafraniec et al [31] proposed a method with low-level compiler intermediate representations to improve the effect of program translation. Ahmad et al [32] proposed a new approach by using code summary on directional model.…”

Section: Unsupervised Program Translationmentioning

confidence: 99%

Human-Machine Cooperative Program Translation Based on Abstract Syntax Tree

Zhang,

Liu,

et al. 2023

Preprint

View full text Add to dashboard Cite

Program translation involves converting one programming language into another, which can modernize and migrate applications across platforms. Most of the current program translation methods are sequence-based, which cannot capture the semantic information of the code. To overcome this, abstract syntax tree-based program translation rises up. However, even the state-of-the-art machine translation methods can not guarantee error-free translation results. Consequently, software engineers need to make corrections on the machine's results before using, which is labor-intensive. To solve this problem, we propose the Human-Machine Cooperative Program Translation Based on Abstract Syntax Tree (HMPT-AST), which feeds the human's modification into the model in each iteration and the model updates the result based on human's feedback. It enables two patterns of human participation: First-error-based and Layer-based HMPT-AST. In the former one, the software engineer corrects one error node in each iteration. In the latter one, all error nodes within the same layer are corrected. In addition, the proposed method can also reduce the interactive response time from two aspects: avoiding generating the correct AST subtree repeatedly with parameter cache module, as well as reducing the generation of unnecessary AST subtree with early termination module. We conducted experiments on multiple dataset. The results show that compared with baselines, our method reduces the human effort up to 94.44\% and reduces the response time up to 94.32\%. We have made the code publicly available.\footnote{https://drive.google.com/drive/folders/1878Or6cEsW21fu_cpdpnv_dGevfFr9mB?usp=sharing}

show abstract

“…To build neural style transfer models for code, we rely on extensive work in code language modeling, where large numbers of programs from open source repositories are used to pre-train models over code (Ahmad et al (2021), Wang et al (2021), Feng et al (2020)), and these models have in turn, been used in a variety of downstream tasks such as code translation, or generation of code from natural language (Szafraniec et al (2022), Chen et al ( 2021)). To our knowledge, CodeStylist is the only system that exploits these language models to perform the rather complex task of code style transfer.…”

Section: Introductionmentioning

confidence: 99%

CodeStylist: A System for Performing Code Style Transfer Using Neural Networks

Ting

Karl

Serenity

et al. 2023

AAAI

View full text Add to dashboard Cite

Code style refers to attributes of computer programs that affect their readability, maintainability, and performance. Enterprises consider code style as important and enforce style requirements during code commits. Tools that assist in coding style compliance and transformations are highly valuable. However, many key aspects of programming style transfer are difficult to automate, as it can be challenging to specify the patterns required to perform the transfer algorithmically. In this paper, we describe a system called CodeStylist which uses neural methods to perform style transfer on code.

show abstract

Code Translation with Compiler Representations

Cited by 5 publications

References 12 publications

C2TACO: Lifting Tensor Code to TACO

C2TACO: Lifting Tensor Code to TACO

Human-Machine Cooperative Program Translation Based on Abstract Syntax Tree

CodeStylist: A System for Performing Code Style Transfer Using Neural Networks

Contact Info

Product

Resources

About