Semantical interprocedural parallelization

Irigoin, François; Jouvelot, Pierre; Triolet, Rémi

doi:10.1145/2591635.2667163

Cited by 29 publications

(12 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, their detection is of relevance in compilation for hybrid MPC. Due to the availability and maturity of automated parallelization tools, e.g., [29,50], we rely on these for the detection of parallel loops, i.e., loops that have independent loop iterations. These tools are able to detect parallelism and to annotate parallelism using source-to-source compilation techniques, independent of the HyCC compilation chain.…”

Section: Automated Parallelizationmentioning

confidence: 99%

HyCC

Büscher

Demmler

Katzenbeisser

et al. 2018

Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security

View full text Add to dashboard Cite

While secure multi-party computation (MPC) is a vibrant research topic and a multitude of practical MPC applications have been presented recently, their development is still a tedious task that requires expert knowledge. Previous works have made first steps in compiling high-level descriptions from various source descriptions into MPC protocols, but only looked at a limited set of protocols. In this work we present HyCC, a tool-chain for automated compilation of ANSI C programs into hybrid protocols that efficiently and securely combine multiple MPC protocols with optimizing compilation, scheduling, and partitioning. As a result, our compiled protocols are able to achieve performance numbers that are comparable to hand-built solutions. For the MiniONN neural network (Liu et al., CCS 2017), our compiler improves performance of the resulting protocol by more than a factor of 3. Thus, for the first time, highly efficient hybrid MPC becomes accessible for developers without cryptographic background.

show abstract

Section: Automated Parallelizationmentioning

confidence: 99%

HyCC

Büscher

Demmler

Katzenbeisser

et al. 2018

Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security

View full text Add to dashboard Cite

show abstract

“…We have based our work on some code transformation passes of the PIPS compiler [10][11] and on its highlevel intermediate representation. Aiming at automatic interprocedural code parallelization, optimization and offloading, it features a wide range of analyses and transformations over Fortran and C code.…”

Section: Background and Notationsmentioning

confidence: 99%

Effects Dependence Graph: A Key Data Concept for C Source-to-Source Compilers

Lossing¹,

Guillou²,

Irigoin³

2016

2016 IEEE 16th International Working Conference on Source Code Analysis and Manipulation (SCAM)

View full text Add to dashboard Cite

International audienceOptimizations, transformations and analyses are applied to programs by compilers at the intermediate representation level, which usually does not include explicit variable declarations. This description level is fine for middle-ends and for source-to-source optimizers of simple languages. Meanwhile, the C language has become much more flexible since the C99standard, and let variable and type declarations appear almost anywhere in source code.We present in this paper a new concept to manage C99 declarations in a source-to-source compiler: the Effects Dependence Graph, which is an extension of the classical Data Dependence Graph. It deals particularly efficiently with user-defined type declarations or dependent types like Variable-Length Array. It is also interesting because no legal scheduling transformationis hindered and because existing algorithms are either not or slightly modified. Finally it reduces the need for variable, struct and array privatization or live range analyses in automatic parallelizers.To the best of our knowledge, the declaration issue is ignored in the literature: existing C source-to-source compilers either do not support C99, or accept only restricted portions of code, and production compilers use low-level intermediate representations, possibly with annotations. In this way our solution addresses a wider range of compiler analysis issues

show abstract

“…This idea of using LRA to synthesize input-output relations is quite straightforward and not new. In particular, it is systematically applied in the tool PIPS [3,23], which considers each basic statement as an elementary relation, and synthesizes the input-output relation of a full program by composing these relations bottom-up. In this paper, we specialize the approach to the synthesis of procedure summaries.…”

Section: Introductionmentioning

confidence: 99%

Disjunctive Relational Abstract Interpretation for Interprocedural Program Analysis

Boutonnet

Halbwachs

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Program analysis by abstract interpretation using relational abstract domains-like polyhedra or octagons-easily extends from state analysis (construction of reachable states) to relational analysis (construction of input-output relations). In this paper, we exploit this extension to enable interprocedural program analysis, by constructing relational summaries of procedures. In order to improve the accuracy of procedure summaries, we propose a method to refine them into disjunctions of relations, these disjunctions being directed by preconditions on input parameters.

show abstract

Semantical interprocedural parallelization

Cited by 29 publications

References 24 publications

HyCC

HyCC

Effects Dependence Graph: A Key Data Concept for C Source-to-Source Compilers

Disjunctive Relational Abstract Interpretation for Interprocedural Program Analysis

Contact Info

Product

Resources

About