Several techniques for analysis and transformations are used in compilers. Among them, the peeling of loops for hoisting quasi-invariants can be used to optimize generated code, or simply ease developers' lives. In this paper, we introduce a new concept of dependency analysis borrowed from the field of Implicit Computational Complexity (ICC), allowing to work with composed statements called "Chunks" to detect more quasi-invariants. Based on an optimization idea given on a WHILE language, we provide a transformation method -reusing ICC concepts and techniques [9, 10] -to compilers. This new analysis computes an invariance degree for each statement or chunks of statements by building a new kind of dependency graph, finds the "maximum" or "worst" dependency graph for loops, and recognizes if an entire block is Quasi-Invariant or not. This block could be an inner loop, and in that case the computational complexity of the overall program can be decreased. We already implemented a proof of concept on a toy C parser 1 analysing and transforming the AST representation.In this paper, we introduce the theory around this concept and present a prototype analysis pass implemented on LLVM. In a very near future, we will implement the corresponding transformation and provide benchmarks comparisons.
This work leverages an original dependency analysis to parallelize loops regardless of their form in imperative programs. Our algorithm distributes a loop into multiple parallelizable loops, resulting in gains in execution time comparable to state-of-the-art automatic source-to-source code transformers when both are applicable. Our graph-based algorithm is intuitive, language-agnostic, proven correct, and applicable to all types of loops. Importantly, it can be applied even if the loop iteration space is unknown statically or at compile time, or more generally if the loop is not in canonical form or contains loop-carried dependency. As contributions we deliver the computational technique, proof of its preservation of semantic correctness, and experimental results to quantify the expected performance gains. We also show that many comparable tools cannot distribute the loops we optimize, and that our technique can be seamlessly integrated into compiler passes or other automatic parallelization suites.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.