检索结果-内蒙古大学图书馆

Modeling the Interplay between Loop Tiling and Fusion in optimizing compilers Using Affine Relations

ACM TRANSACTIONS ON COMPUTER SYSTEMS 2023年第1-4期41卷 1-45页

作者： Zhao, Jie Xu, Jinchen Di, Peng Nie, Wang Hu, Jiahui Yi, Yanzhi Yang, Sijia Geng, Zhen Zhang, Renwei Li, Bojie Gan, Zhiliang Jin, Xuefeng Hunan Univ Coll Comp Sci & Elect Engn Changsha 410082 Peoples R China Informat Engn Univ Zhengzhou 450001 Peoples R China Huawei Technol Co Ltd Beijing 100085 Peoples R China

Loop tiling and fusion are two essential transformations in optimizing compilers to enhance the data locality of programs. Existing heuristics either perform loop tiling and fusion in a particular order, missing some of their profitable compositions, or execute ad-hoc implementations for domain-specific applications, calling for a generalized and systematic solution in optimizing compilers. In this article, we present a so-called basteln (an abbreviation for backward slicing of tiled loop nests) strategy in polyhedral compilation to better model the interplay between loop tiling and fusion. The basteln strategy first groups loop nests by preserving their parallelism/tilability and next performs rectangular/parallelogram tiling to the output groups that produce data consumed outside the considered program fragment. The memory footprints required by each tile are then computed, from which the upward exposed data are extracted to determine the tile shapes of the remaining fusion groups. Such a tiling mechanism can construct complex tile shapes imposed by the dependences between these groups, which are further merged by a post-tiling fusion algorithm for enhancing data locality without losing the parallelism/tilability of the output groups. The basteln strategy also takes into account the amount of redundant computations and the fusion of independent groups, exhibiting a general applicability. We integrate the basteln strategy into two optimizing compilers, with one a general-purpose optimizer and the other a domain-specific compiler for deploying deep learning models. The experiments are conducted on CPU, GPU, and a deep learning accelerator to demonstrate the effectiveness of the approach for a wide class of application domains, including deep learning, image processing, sparse matrix computation, and linear algebra. In particular, the basteln strategy achieves a mean speedup of 1.8x over cuBLAS/cuDNN and 1.1x over TVM on GPU when used to optimize deep learning models

关键词： Tiling fusion data locality parallelism redundant computation memory hierarchy polyhedral model optimizing compilers

来源：评论

学校读者我要写书评

暂无评论

Computer algebra systems as mathematical optimizing compilers

引用

SCIENCE OF COMPUTER PROGRAMMING 2006年第3期59卷 250-273页

作者： Dall'Osso, A 9 Ave Parthenay F-92400 Courbevoie France

The role of computer algebra systems (CASs) is not limited to analyzing and solving mathematical and physical problems. They have also been used as tools in the development process of computer programs, starting from the specification and ending with the coding and testing phases. In this way one can exploit their powerful mathematical capacity during the development phases and, by the other way, take advantage of the speed performance of languages such as FORTRAN or C in the implementation. Among the mathematical features of CASs there are transformations allowing one to optimize the final code instructions. In this paper we show some kind of optimizations that can be done on new or existing algorithms, by extending some techniques that compilers apply currently to optimize the machine code. The results show that the CPU time taken by the optimized code is reduced by a factor that can reach 5. The optimizations are performed with a package built on a well known CAS: Mathematica. (c) 2005 Elsevier B.V. All rights reserved.

关键词： computer algebra systems optimizing compilers problem-solving environments scientific software development code synthesis

来源：评论

学校读者我要写书评

暂无评论

PERFORMANCE CHARACTERIZATION OF optimizing compilers

引用

IEEE TRANSACTIONS ON SOFTWARE ENGINEERING 1995年第7期21卷 615-628页

作者： SAAVEDRA, RH SMITH, AJ UNIV CALIF BERKELEY DEPT EECSBERKELEYCA 94720

optimizing compilers have become an essential component in achieving high levels of performance. Various simple and sophisticated optimizations are implemented at different stages of compilation to yield significant improvements, but little work has been done in characterizing the effectiveness of optimizers, or in understanding where most of this improvement comes from. In this paper we study the performance impact of optimization in the context of our methodology for CPU performance characterization based on the abstract machine model. The model considers all machines to be different implementations of the same high level language abstract machine;in previous research, the model has been used as a basis to analyze machine and benchmark performance. In this paper, we show that our model can be extended to characterize the performance improvement provided by optimizers and to predict the run time of optimized programs, and measure the effectiveness of several compilers in implementing different optimization techniques.

关键词： PERFORMANCE EVALUATION optimizing compilers BENCHMARKING CPU PERFORMANCE CHARACTERIZATION

来源：评论

学校读者我要写书评

暂无评论

Adaptive optimizing compilers for the 21st century

引用

JOURNAL OF SUPERCOMPUTING 2002年第1期23卷 7-22页

作者： Cooper, KD Subramanian, D Torczon, L Rice Univ Dept Comp Sci Houston TX 77005 USA

Historically, compilers have operated by applying a fixed set of optimizations in a predetermined order. We call such an ordered list of optimizations a compilation sequence. This paper describes a prototype system that uses biased random search to discover a program-specific compilation sequence that minimizes an explicit, external objective function. The result is a compiler framework that adapts its behavior to the application being compiled, to the pool of available transformations, to the objective function, and to the target machine. This paper describes experiments that attempt to characterize the space that the adaptive compiler must search. The preliminary results suggest that optimal solutions are rare and that local minima are frequent. If this holds true, biased random searches, such as a genetic algorithm, should find good solutions more quickly than simpler strategies, such as hill climbing.

关键词： configurable compilers order of optimization biased random search optimizing compilers

来源：评论

学校读者我要写书评

暂无评论

OptiScope: Performance Accountability for optimizing compilers 09

OptiScope: Performance Accountability for Optimizing Compile...

引用

7th International Symposium on Code Generation and Optimization

作者： Moseley, Tipp Grunwald, Dirk Peri, Ramesh Univ Colorado Dept Comp Sci Boulder CO 80309 USA Intel Corp Hillsboro OR 97124 USA

ISBN: (纸本)9780769535760

compilers employ many aggressive code transformations to achieve highly optimized code. However, because of complex target architectures and unpredictable optimization interactions, these transformations may not always be beneficial. Current analysis methods measure performance at the application level and ignore optimization effects at the function and loop level. To better measure and understand these effects, we present OptiScope, a compiler independent tool to identify performance opportunities by comparing programs built with different compilers or optimization fags. The analysis includes hundreds of different metrics and uses a novel loop correlation technique for binary programs (produced from the same source by different compilers) to isolate measurements to specific regions. We present several case studies using OptiScope to identify key differences between different compiler suites, versions, and target architectures. The examples demonstrate performance improvement opportunities between 32.5% to 893% on select regions of SPEC 2006 benchmarks.

关键词： optimizing compilers Program processors Testing Hardware Computer science Computer architecture Performance analysis Current measurement Optimization methods Out of order

来源：评论

学校读者我要写书评

暂无评论

Adaptive optimizing compilers for the 21st century

Adaptive optimizing compilers for the 21st century

引用

2nd Symposium of the Los Alamos-Computer-Science-Institute

作者： Cooper, KD Subramanian, D Torczon, L Rice Univ Dept Comp Sci Houston TX 77005 USA

关键词： configurable compilers order of optimization biased random search optimizing compilers

来源：评论

学校读者我要写书评

暂无评论

optimizing compilers for the SPARC architecture-an overview

Optimizing compilers for the SPARC architecture-an overview

引用

IEEE Compcon

作者： S.S. Muchnick C. Aoki V. Ghodssi M. Helft M. Lee R. Tuck D. Weaver A. Wu Sun Microsystems Inc. Mountain View CA USA

The authors discuss the user programming model for the scalable processor architecture (SPARC) and the optimizing compilers for the SPARC-based Sun-4 workstations. They are concerned with two broad areas: how the compilers use the architecture and the design of the compilers themselves. They discuss the registers, synthesized instructions, tagged data support, the compilers, the global and peephole optimizers, and compiler performance analysis.< >

关键词： optimizing compilers Sun Reduced instruction set computing Hardware Delay Program processors Process design Design optimization Workstations Coprocessors

来源：评论

学校读者我要写书评

暂无评论

The effect of optimizing compilers on architecture and programs

引用

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS 1997年第4期E80D卷 403-408页

作者： Wolfe, M OREGON GRAD INST PORTLANDOR 97291

The first optimizing compiler was developed at IBM in order to prove that high level language programming could be as efficient as hand-coded machine language. Computer architecture and compiler optimization interacted through a feedback loop, from the high-level language computer architectures of the 1970s to the RISC machines of the 1980s. In the supercomputing community, the availability of effective vectorizing compilers delivered easy-to-use performance in the 1980s to the present. These compilers were successful at least in part because they could predict poor performance spots in the program and report these to users. This fostered a feedback loop between programmers and compilers to develop high performance programs. Future optimizing compilers for high performance computers and supercomputers will have to take advantage of both feedback loops.

关键词： optimizing compilers parallel computers

来源：评论

学校读者我要写书评

暂无评论

optimizing NET compilers for improved Java performance

引用

COMPUTER 1997年第6期30卷 67-+页

作者： Hsieh, CHA Conte, MT Johnson, TL Gyllenhaal, JC Hwu, WMW Univ of Illinois Urbana IL USA

Because they are interpreted, Java executables run slower than their compiled counterparts. The native executable translation (NET) compiler's objective is to optimize the translation of Java bytecode to native machine code so that it runs nearly as fast as native code generated directly from a source. The article presents some preliminary results for several large application programs and standard benchmarks. It compares the NET-compiled code performance with Sun's Java VM, Microsoft's Java just-in-time compiler, and equivalent C and C++ programs directly compiled. The results show that the optimizing NET compiler is capable of achieving better performance than the two other bytecode execution methods, in some cases achieving speeds comparable to directly compiled native code.

关键词： optimizing compilers Java Software performance Virtual manufacturing Program processors Standards development Costs Computational modeling Hardware Software standards

来源：评论

学校读者我要写书评

暂无评论

Concept-based component libraries and optimizing compilers

Concept-based component libraries and optimizing compilers

引用

International Symposium on Parallel and Distributed Processing (IPDPS)

作者： S.D.P. Gregor B. Osman D.R. Musser J.G. Siek L.-Q. Lee A. Lumsdaine Rensselaer Polytechnic Institute Indiana University

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：