Proceedings of the 27th International Conference on Compiler Construction最新文献_第2页

Parallel sparse flow-sensitive points-to analysis 并行稀疏流敏感点分析

Proceedings of the 27th International Conference on Compiler Construction Pub Date : 2018-02-24 DOI: 10.1145/3178372.3179517

Jisheng Zhao, M. Burke, Vivek Sarkar

{"title":"Parallel sparse flow-sensitive points-to analysis","authors":"Jisheng Zhao, M. Burke, Vivek Sarkar","doi":"10.1145/3178372.3179517","DOIUrl":"https://doi.org/10.1145/3178372.3179517","url":null,"abstract":"This paper aims to contribute to further advances in pointer (or points-to) analysis algorithms along the combined dimen- sions of precision, scalability, and performance. For precision, we aim to support interprocedural ow-sensitive analysis. For scalability, we aim to show that our approach scales to large applications with reasonable memory requirements. For performance, we aim to design a points-to analysis algo- rithm that is amenable to parallel execution. The algorithm introduced in this paper achieves all these goals. As an ex- ample, our experimental results show that our algorithm can analyze the 2.2MLOC Tizen OS framework with < 16GB of memory while delivering an average analysis rate of > 10KLOC/second. Our points-to analysis algorithm, PSEGPT, is based on the Pointer Sparse Evaluation Graph (PSEG) form, a new analysis representation that combines both points-to and heap def-use information. PSEGPT is a scalable interprocedural flow-sensitive context-insensitive points-to analy- sis that is amenable to efficient task-parallel implementa- tions, even though points-to analysis is usually viewed as a challenge problem for parallelization. Our experimental results with 6 real-world applications on a 12-core machine show an average parallel speedup of 4.45× and maximum speedup of 7.35×. The evaluation also includes precision results by demonstrating that our algorithm identifies significantly more inlinable indirect calls (IICs) than SUPT and SS, two states of the art SSA-based points-to analyses implemented in LLVM.","PeriodicalId":117615,"journal":{"name":"Proceedings of the 27th International Conference on Compiler Construction","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123872250","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 10

PAYJIT: space-optimal JIT compilation and its practical implementation PAYJIT:空间最优JIT编译及其实际实现

Proceedings of the 27th International Conference on Compiler Construction Pub Date : 2018-02-24 DOI: 10.1145/3178372.3179523

Jacob Brock, C. Ding, Xiaoran Xu, Yan Zhang

{"title":"PAYJIT: space-optimal JIT compilation and its practical implementation","authors":"Jacob Brock, C. Ding, Xiaoran Xu, Yan Zhang","doi":"10.1145/3178372.3179523","DOIUrl":"https://doi.org/10.1145/3178372.3179523","url":null,"abstract":"Just-in-time (JIT) compilation in dynamic programming languages can improve execution speed in code with hot sections. However, that comes at the cost of increased memory usage for the storage of compiled code and associated bookkeeping data, as well as up-front compilation time for the hot code. The current standard JIT compilation policy (used in both Android's JIT compiler and the HotSpot Java compiler) is simplistic; any method that has reached a certain hotness, as counted by invocations and loop iterations, is scheduled for compilation. This would be fine if the cost/benefit of compilation was the same for every method of a given hotness, but that is not the case. In fact, compiling a large method will likely result in less overall speedup than compiling a smaller, equally hot method. This exposes an opportunity for improvement. We propose the PAYJIT compilation policy for method-based JIT compilers, which scales compilation hotness thresholds with method sizes, and includes two-point tuning, a mechanism for determining those hotness thresholds. In this way, PAYJIT compiles more small methods, it compiles them sooner, and it nearly eliminates the compilation of large methods that contribute little to overall speedup. Among 10 popular Android apps tested across 16 experiments, the PAYJIT compilation policy decreases compilation time by a maximum of 49.2%, with an average of 18.7%; execution time by a maximum of 10.9%, with an average of 1.34% (for a geometric mean speedup of 1.46%); and code cache size by a maximum of 41.1%, with an average of 15.6%.","PeriodicalId":117615,"journal":{"name":"Proceedings of the 27th International Conference on Compiler Construction","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124352014","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Rethinking compilers in the rise of machine learning and AI (keynote) 在机器学习和人工智能的兴起中重新思考编译器(主题演讲)

Proceedings of the 27th International Conference on Compiler Construction Pub Date : 2018-02-24 DOI: 10.1145/3178372.3183634

Xipeng Shen

{"title":"Rethinking compilers in the rise of machine learning and AI (keynote)","authors":"Xipeng Shen","doi":"10.1145/3178372.3183634","DOIUrl":"https://doi.org/10.1145/3178372.3183634","url":null,"abstract":"Recent years have witnessed some influential progresses in Machine Learning (ML) and Artificial Intelligence (AI). The progresses may lead to some significant changes to future programming. Many programs, for instance, may be not code written in some specially designed programming languages, but high-level user intentions expressed in natural languages. Deep Learning-based software, despite the difficulties in interpreting their results, may continue its rapid growth in the software market and its influence in people's everyday life. This talk will first examine the implications of these changes to compiler research, and then discuss the potential opportunities that ML and AI could bring to possibly transform the field of compiler research. Specifically, the talk will focus on the possibilities for ML and AI to help reveal the high-level semantics and attributes of software components that traditional compiler technology cannot do, and hence, open important opportunities for high-level large-scoped code reasoning and optimizations---a direction that has some tremendous potential but has been beyond the reach of traditional compiler technology. The talk will discuss how ML and AI may help break the \"abstraction wall\"---barriers formed by layers of abstractions in modern software---for program analysis and optimizations, and how ML and AI may transform the way in which high-level user intentions get translated into low-level code implementations. The talk will conclude with a list of grand challenges and possible research directions for future compiler constructions.","PeriodicalId":117615,"journal":{"name":"Proceedings of the 27th International Conference on Compiler Construction","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125115669","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fast and flexible instruction selection with constraints 具有约束的快速灵活的指令选择

Proceedings of the 27th International Conference on Compiler Construction Pub Date : 2018-02-24 DOI: 10.1145/3178372.3179501

Patrick Thier, M. Ertl, A. Krall

引用次数: 2

A polyhedral compilation framework for loops with dynamic data-dependent bounds 具有动态数据依赖边界的循环的多面体编译框架

Proceedings of the 27th International Conference on Compiler Construction Pub Date : 2018-02-24 DOI: 10.1145/3178372.3179509

Jie Zhao, Michael Kruse, Albert Cohen

{"title":"A polyhedral compilation framework for loops with dynamic data-dependent bounds","authors":"Jie Zhao, Michael Kruse, Albert Cohen","doi":"10.1145/3178372.3179509","DOIUrl":"https://doi.org/10.1145/3178372.3179509","url":null,"abstract":"We study the parallelizing compilation and loop nest optimization of an important class of programs where counted loops have a dynamic data-dependent upper bound. Such loops are amenable to a wider set of transformations than general while loops with inductively defined termination conditions: for example, the substitution of closed forms for induction variables remains applicable, removing the loop-carried data dependences induced by termination conditions. We propose an automatic compilation approach to parallelize and optimize dynamic counted loops. Our approach relies on affine relations only, as implemented in state-of-the-art polyhedral libraries. Revisiting a state-of-the-art framework to parallelize arbitrary while loops, we introduce additional control dependences on data-dependent predicates. Our method goes beyond the state of the art in fully automating the process, specializing the code generation algorithm to the case of dynamic counted loops and avoiding the introduction of spurious loop-carried dependences. We conduct experiments on representative irregular computations, from dynamic programming, computer vision and finite element methods to sparse matrix linear algebra. We validate that the method is applicable to general affine transformations for locality optimization, vectorization and parallelization.","PeriodicalId":117615,"journal":{"name":"Proceedings of the 27th International Conference on Compiler Construction","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115574485","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 11

Termination checking and task decomposition for task-based intermittent programs 基于任务的间歇程序的终止检查和任务分解

Proceedings of the 27th International Conference on Compiler Construction Pub Date : 2018-02-24 DOI: 10.1145/3178372.3179525

A. Colin, Brandon Lucia

{"title":"Termination checking and task decomposition for task-based intermittent programs","authors":"A. Colin, Brandon Lucia","doi":"10.1145/3178372.3179525","DOIUrl":"https://doi.org/10.1145/3178372.3179525","url":null,"abstract":"Emerging energy-harvesting computer systems extract energy from their environment to compute, sense, and communicate with no battery or tethered power supply. Building software for energy-harvesting devices is a challenge, because they operate only intermittently as energy is available. Programs frequently reboot due to power loss, which can corrupt program state and prevent forward progress. Task-based programming models allow intermittent execution of long-running applications, but require the programmer to decompose code into tasks that will eventually complete between two power failures. Task decomposition is challenging and no tools exist to aid in task decomposition. We propose CleanCut, a tool that can check for and report non-terminating tasks in existing code, as well as automatically decompose code into efficient, terminating tasks. CleanCut is based on a statistical model for energy of paths through the program. We applied a prototype of CleanCut to four applications, including pattern-recognition, encryption, compression, and data filtering. Our experiments demonstrated the risk of non-termination in existing code and showed that CleanCut finds efficient task decompositions that execute 2.45x faster on average than manually placed boundaries.","PeriodicalId":117615,"journal":{"name":"Proceedings of the 27th International Conference on Compiler Construction","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125060573","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 72

Towards a compiler analysis for parallel algorithmic skeletons 对并行算法骨架的编译器分析

Proceedings of the 27th International Conference on Compiler Construction Pub Date : 2018-02-24 DOI: 10.1145/3178372.3179513

T. Koch, Stanislav Manilov, Christos Vasiladiotis, M. Cole, Björn Franke

{"title":"Towards a compiler analysis for parallel algorithmic skeletons","authors":"T. Koch, Stanislav Manilov, Christos Vasiladiotis, M. Cole, Björn Franke","doi":"10.1145/3178372.3179513","DOIUrl":"https://doi.org/10.1145/3178372.3179513","url":null,"abstract":"Parallelizing compilers aim to detect data-parallel loops in sequential programs, which -- after suitable transformation -- can be safely and profitably executed in parallel. However, in the traditional model safe parallelization requires provable absence of dependences. At the same time, several well-known parallel algorithmic skeletons cannot be easily expressed in a data dependence framework due to spurious depedences, which prevent parallel execution. In this paper we argue that commutativity is a more suitable concept supporting formal characterization of parallel algorithmic skeletons. We show that existing commutativity definitions cannot be easily adapted for practical use, and develop a new concept of commutativity based on liveness, which readily integrates with existing compiler analyses. This enables us to develop formal definitions of parallel algorithmic skeletons such as task farms, MapReduce and Divide&Conquer. We show that existing informal characterizations of various parallel algorithmic skeletons are captured by our abstract formalizations. In this way we provide the urgently needed formal characterization of widely used parallel constructs allowing their immediate use in novel parallelizing compilers.","PeriodicalId":117615,"journal":{"name":"Proceedings of the 27th International Conference on Compiler Construction","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134222694","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Polyhedral expression propagation 多面体表达传播

Proceedings of the 27th International Conference on Compiler Construction Pub Date : 2018-02-24 DOI: 10.1145/3178372.3179529

J. Doerfert, Shrey Sharma, Sebastian Hack

{"title":"Polyhedral expression propagation","authors":"J. Doerfert, Shrey Sharma, Sebastian Hack","doi":"10.1145/3178372.3179529","DOIUrl":"https://doi.org/10.1145/3178372.3179529","url":null,"abstract":"Polyhedral techniques have proven to be powerful for various optimizations, from automatic parallelization to accelerator programming. At their core, these techniques compute accurate dependences among statement instances in order to apply complex program transformations. Such transformations comprise memory layout or program order modifications by optimizing memory access functions or scheduling functions. However, these approaches treat statements as opaque entities and do not consider changing the structure of the contained expressions or the memory accesses involved. In this paper we present a technique that statically propagates expressions in order to avoid communicating their result via memory. While orthogonal to other polyhedral optimizations, this transformation can be used to enable them. Applied separately, expression propagation can increase parallelism, eliminate temporary arrays, create independent computations and improve cache utilization. It is especially useful for streaming codes that involve temporary arrays and scalar variables. For multiple image processing pipelines we achieve portable speedups of up to 21.3× as well as a significant memory reduction compared to a naive parallel implementation. In 6 out of 7 cases, expression propagation outperforms a state-of-the-art polyhedral optimization especially designed for this kind of programs by a factor of up to 2.03×.","PeriodicalId":117615,"journal":{"name":"Proceedings of the 27th International Conference on Compiler Construction","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122753454","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Computing partially path-sensitive MFP solutions in data flow analyses 数据流分析中部分路径敏感MFP解的计算

Proceedings of the 27th International Conference on Compiler Construction Pub Date : 2018-02-24 DOI: 10.1145/3178372.3179497

K. Pathade, Uday P. Khedker

{"title":"Computing partially path-sensitive MFP solutions in data flow analyses","authors":"K. Pathade, Uday P. Khedker","doi":"10.1145/3178372.3179497","DOIUrl":"https://doi.org/10.1145/3178372.3179497","url":null,"abstract":"Data flow analysis traverses paths in a control flow graph (CFG) representation of programs to compute useful information. Many of these paths are infeasible, i.e. they cannot arise in any possible execution. The information computed along these paths adds imprecision to the conventional Maximal Fixed Point (MFP) solution of a data flow analysis. Existing approaches for removing this imprecision are either specific to a data flow problem or involve control flow graph restructuring which has exponential complexity. We introduce partial path-sensitivity to the MFP solution by identifying clusters of minimal infeasible path segments to distinguish between the data flowing along feasible and infeasible control flow paths. This allows us to lift any data flow analysis to an analysis over k+1 tuples where k is the number of clusters. Our flow function for a k+1 tuple shifts the values of the underlying analysis from an element in the tuple to other element(s) at the start and end of a cluster as appropriate. This allows us to maintain the distinctions where they are beneficial. Since k is linear in the number of conditional edges in the CFG, the effort is multiplied by a factor that is linear in the number of conditional edges (and is not exponential, unlike conventional approaches of achieving path sensitivity.) We have implemented our method of computing partially path sensitive MFP for reaching definitions analysis and value range analysis of variables. Our measurements on benchmark programs show up to 9% reduction in the number of reaching definitions and up to 14% cases where the value range of a variable is smaller.","PeriodicalId":117615,"journal":{"name":"Proceedings of the 27th International Conference on Compiler Construction","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128709416","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 6

A session type provider: compile-time API generation of distributed protocols with refinements in F# 会话类型提供者:在f#中进行改进的分布式协议的编译时API生成

Proceedings of the 27th International Conference on Compiler Construction Pub Date : 2018-02-24 DOI: 10.1145/3178372.3179495

R. Neykova, Raymond Hu, N. Yoshida, Fahd Abdeljallal

{"title":"A session type provider: compile-time API generation of distributed protocols with refinements in F#","authors":"R. Neykova, Raymond Hu, N. Yoshida, Fahd Abdeljallal","doi":"10.1145/3178372.3179495","DOIUrl":"https://doi.org/10.1145/3178372.3179495","url":null,"abstract":"We present a library for the specification and implementation of distributed protocols in native F# (and other .NET languages) based on multiparty session types (MPST). There are two main contributions. Our library is the first practical development of MPST to support what we refer to as interaction refinements: a collection of features related to the refinement of protocols, such as message-type refinements (value constraints) and message value dependent control flow. A well-typed endpoint program using our library is guaranteed to perform only compliant session I/O actions w.r.t. to the refined protocol, up to premature termination. Second, our library is developed as a session type provider, that performs on-demand compile-time protocol validation and generation of protocol-specific .NET types for users writing the distributed endpoint programs. It is implemented by extending and integrating Scribble (a toolchain for MPST) with an SMT solver into the type providers framework. The safety guarantees are achieved by a combination of static type checking of the generated types for messages and I/O operations, correctness by construction from code generation, and automated inlining of assertions.","PeriodicalId":117615,"journal":{"name":"Proceedings of the 27th International Conference on Compiler Construction","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127026277","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 46