Verified lifting of stencil computations
Open accessThe DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
This paper demonstrates a novel combination of program synthesis and verification to lift stencil computations from low-level Fortran code to a high-level summary expressed using a predicate language. The technique is sound and mostly automated, and leverages counter-example guided inductive synthesis (CEGIS) to find provably correct translations. Lifting existing code to a high-performance description language has a number of benefits, including maintainability and performance portability. For example, our experiments show that the lifted summaries can enable domain specific compilers to do a better job of parallelization as compared to an off-the-shelf compiler working on the original code, and can even support fully automatic migration to hardware accelerators such as GPUs. We have implemented verified lifting in a system called STNG and have evaluated it using microbenchmarks, mini-apps, and real-world applications. We demonstrate the benefits of verified lifting by first automatically summarizing Fortran source code into a high-level predicate language, and subsequently translating the lifted summaries into Halide, with the translated code achieving median performance speedups of 4.1X and up to 24X for non-trivial stencils as compared to the original implementation.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
(2013) · doi:10.1145/2491956.2462176 · Cited by 885
Alur, R., Bodik, R., Juniwal, G., Martin, M. M. K., Raghothaman, M., Seshia, S. A., Singh, R., Solar-Lezama, A., Torlak, E., & Udupa, A. (2013) · 2013 Formal Methods in Computer-Aided Design · doi:10.1109/fmcad.2013.6679385 · Cited by 656
Self-citationAn auto-tuning framework for parallel multicore stencil computations
Kamil, S., Chan, C., Oliker, L., Shalf, J., & Williams, S. (2010) · 2010 IEEE International Symposium on Parallel & Distributed Processing (IPDPS) · doi:10.1109/ipdps.2010.5470421 · Cited by 209 · cited 3×
“We manually constructed Challenge Problems, a set of 27-point 3D stencils based on optimizations used in realworld stencils found in prior work [18, 37].”
BackgroundMethodSelf-citationSuperoptimizer: a look at the smallest program
Massalin, H. (1987) · Proceedings of the second international conference on Architectual support for programming languages and operating systems · doi:10.1145/36206.36194 · Cited by 154
Solar-Lezama, A., Arnold, G., Tancau, L., Bodik, R., Saraswat, V., & Seshia, S. (2007) · Proceedings of the 28th ACM SIGPLAN Conference on Programming Language Design and Implementation · doi:10.1145/1250734.1250754 · Cited by 149 · cited 1×
“[53] describes a reduction algorithm that transforms stencils written in SKETCH, which usually have unbounded input sizes, into bounded circuits, which can then be used in the synthesis algorithm to fill any holes in the reduced program.”
MethodSelf-citationSchkufza, E., Sharma, R., & Aiken, A. (2013) · ACM SIGARCH Computer Architecture News · doi:10.1145/2490301.2451150 · Cited by 57
Cited by
Synthesis of divide and conquer parallelism for loops
Farzan, A., & Nicolet, V. (2017) · Proceedings of the 38th ACM SIGPLAN Conference on Programming Language Design and Implementation · doi:10.1145/3062341.3062355 · Cited by 25
“We lay the theoretical 1 Not to be confused with lambda lifting or the informal use of it in [24]. foundations to answer these questions, and in Section 6, we present an algorithm for producing this lifting automatically that satisfies all aforementioned criteria.”
BackgroundMethodHow statically-typed functional programmers write code
Lubin, J., & Chasins, S. E. (2021) · Proceedings of the ACM on Programming Languages · doi:10.1145/3485532 · Cited by 18
“We can frame the low-workload code to high-workload code transformation task as a synthesis problem similar to verified lifting (Kamil et al., 2016): given an opportunistically-constructed (possibly partial) program 𝑃 and a set of subjectively desirable or streamlined components 𝐶 , find a…”
MethodModular divide-and-conquer parallelization of nested loops
Farzan, A., & Nicolet, V. (2019) · Proceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation · doi:10.1145/3314221.3314612 · Cited by 16
“Synthesis techniques have been leveraged for parallel programs before, instances of which include synthesis of distributed map/reduce programs from input/output examples [38] and optimization and parallelization of stencils [24].”
Method
Metadata
- Authors
- Kamil, S., Cheung, A., Itzhaky, S., & Solar-Lezama, A.
- Venue
- Proceedings of the 37th ACM SIGPLAN Conference on Programming Language Design and Implementation
- Publisher
- ACM
- Published
- 2016-06-02
- Pages
- 711-726
- ISSN
- 1531-7102 (ISSN-L)
- OpenAlex
- W2412440871
- Cited by
- 53
- References
- 6
- FWCI
- 4.94
- Type
- conference paper
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Verified lifting of stencil computations. https://app.cochat.ai/papers/10.1145/2908080.2908117
- The paper
- Kamil, S., Cheung, A., Itzhaky, S., & Solar-Lezama, A. (2016). Verified lifting of stencil computations. Proceedings of the 37th ACM SIGPLAN Conference on Programming Language Design and Implementation. https://doi.org/10.1145/2908080.2908117
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.