检索结果-内蒙古大学图书馆

32nd ACM SIGPLAN International Conference on Compiler Construction (CC)

作者： Lim, HeuiChan Debray, Saumya Univ Arizona Dept Comp Sci Tucson AZ 85721 USA

ISBN: (纸本)9798400700880

Just-in-Time (JIT) compilers are ubiquitous in modern computing systems and are used in a wide variety of software. dynamic code generation bugs, where the JIT compiler silently emits incorrect code, can result in exploitable vulnerabilities. They, therefore, pose serious security concerns and make quick mitigation essential. However, due to the size and complexity of JIT compilers, quickly locating and fixing bugs is often challenging. In addition, the unique characteristics of JIT compilers make existing bug localization approaches inapplicable. Therefore, this paper proposes a new approach to automatic bug localization, explicitly targeting the JIT compiler back-end. The approach is based on explicitly modeling architecture-independent back-end representation and architecture-specific code-generation. Experiments using a prototype implementation on a widely used JIT compiler (Turbofan) indicate that it can successfully localize dynamic code generation bugs in the back-end with high accuracy.

关键词： JIT Compiler Back-End dynamic Program Analysis dynamic code generation Automatic Bug Localization

来源：评论

学校读者我要写书评

暂无评论

Robust Practical Binary Optimization at Run-time using LLVM 6

Robust Practical Binary Optimization at Run-time using LLVM

引用

IEEE/ACM 6th Workshop on the LLVM Compiler Infrastructure in HPC / Workshop on Hierarchical Parallelism for Exascale Computing (LLVM-HPC and HiPar)

作者： Engelke, Alexis Schulz, Martin Tech Univ Munich Munich Germany

ISBN: (纸本)9780738110424

In High Performance Computing (HPC) the performance of applications is paramount, which is has led to a wide body of work on optimizing compilers. However, compilers alone are naturally limited in their potential, as they cannot exploit run-time information to specialize generated code. For this reason, run-time components to perform such specializations are gaining traction. In particular, application or use-case driven specializations have a high potential for optimizations, as they can benefit from explicit guidance from the application or the user, which allows for targeted changes incorporating specific knowledge. Because full compilers and sources are usually unavailable during computation, specializations have to be done at machine code level. However, existing libraries for binary specialization face structural limitations of separating optimization and code generation, in addition to numerous implementation gaps. In this paper, we describe BinOpt, a novel and robust library for performing application-driven binary optimization and specialization using LLVM. A machine code function is lifted directly to LLVM-IR, optimized in LLVM while making use of application-specified information, used to generate a new specialization for a function, and integrated back to the original code. We apply this technique to existing optimized code and show that significant performance improvements can be observed with only a small optimization time overhead.

关键词： High Performance Computing dynamic code generation Run-Time Optimization Binary Translation LLVM

来源：评论

学校读者我要写书评

暂无评论

Using dynamic Compilation to Achieve Ninja Performance for CNN Training on Many-Core Processors 24th

Using Dynamic Compilation to Achieve Ninja Performance for C...

引用

24th International European Conference on Parallel and Distributed Computing (Euro-Par)

作者： Mandal, Ankush Barik, Rajkishore Sarkar, Vivek Georgia Inst Technol Atlanta GA 30332 USA Uber Technol Inc San Francisco CA USA

ISBN: (纸本)9783319969831;9783319969824

Convolutional Neural Networks (CNNs) represent a class of Deep Neural Networks that is growing in importance due to their state-of-the-art performance in pattern recognition tasks in various domains, including image recognition, speech recognition, and natural language processing. However, CNNs are very time consuming to train due to the computationally intensive nature of their convolution operations. Typically, a convolution operation is exposed as a library API that duplicates and reorganizes input tensors under-the-hood in order to leverage existing matrix-matrix multiplication (GEMM) BLAS routines. Unfortunately, this widely-used approach suffers not only from memory expansion but also from memory bandwidth limitations. Moreover, although there has been a significant amount of past work on optimizing CNNs on GPUs, those approaches are not directly applicable to many-core CPU platforms such as Intel Xeon Phi. In this paper, we show how a novel dynamic code generation approach can be used to implement convolution on Intel Knights Landing systems with AVX-512 support, so as to obtain order-of-magnitude performance improvements compared to the GEMM-based approach. Moreover, our approach gives robust performance across different convolution layers of the state-of-the-art CNNs, such as AlexNet, GoogleNetV1, Overfeat, and Vgga. The methods in this paper should be applicable to future many-core CPU platforms with vector lengths of 512 bits or larger.

关键词： Direct convolution KNL dynamic code generation

来源：评论

学校读者我要写书评

暂无评论

Using LLVM for Optimized Lightweight Binary Re-Writing at Runtime 31

Using LLVM for Optimized Lightweight Binary Re-Writing at Ru...

引用

31st IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPS)

作者： Engelke, Alexis Weidendorfer, Josef Tech Univ Munich Dept Informat Munich Germany

ISBN: (纸本)9780769561493

Providing new parallel programming models/abstractions as a set of library functions has the huge advantage that it allows for an relatively easy incremental porting path for legacy HPC applications, in contrast to the huge effort needed when novel concepts are only provided in new programming languages or language extensions. However, performance issues are to be expected with fine granular usage of library functions. In previous work, we argued that binary rewriting can bridge the gap by tightly coupling application and library functions at runtime. We showed that runtime specialization at the binary level, starting from a compiled, generic stencil code can help in approaching performance of manually written, statically compiled version. In this paper, we analyze the benefits of post-processing the re-written binary code using standard compiler optimizations as provided by LLVM. To this end, we present our approach for efficiently converting x86-64 binary code to LLVM-IR. Using the mentioned generic code for arbitrary 2d stencils, we present performance numbers with and without LLVM post-processing. We find that we can now achieve the performance of variants specialized by hand.

关键词： High Performance Computing dynamic code generation dynamic Optimization Binary Transformation

来源：评论

学校读者我要写书评

暂无评论

BlackBox: Lightweight Security Monitoring for COTS Binaries 16

BlackBox: Lightweight Security Monitoring for COTS Binaries

引用

14th International Symposium on code generation and Optimization (CGO)

作者： Hawkins, Byron Demsky, Brian Taylor, Michael B. Univ Calif Irvine Irvine CA 92717 USA Univ Calif San Diego La Jolla CA 92093 USA

ISBN: (纸本)9781450337786

After a software system is compromised, it can be difficult to understand what vulnerabilities attackers exploited. Any information residing on that machine cannot be trusted as attackers may have tampered with it to cover their tracks. Moreover, even after an exploit is known, it can be difficult to determine whether it has been used to compromise a given machine. Aviation has long-used black boxes to better understand the causes of accidents, enabling improvements that reduce the likelihood of future accidents. Many attacks introduce abnormal control flows to compromise systems. In this paper, we present BLACKBOX, a monitoring system for COTS software. Our techniques enable BLACKBOX to efficiently monitor unexpected and potentially harmful control flow in COTS binaries. BLACKBOX constructs dynamic profiles of an application's typical control flows to filter the vast majority of expected control flow behavior, leaving us with a manageable amount of data that can be logged across the network to remote devices. Modern applications make extensive use of dynamically generated code, some of which varies greatly between executions. We introduce support for code generators that can detect security-sensitive behaviors while allowing BLACKBOX to avoid logging the majority of ordinary behaviors. We have implemented BLACKBOX in DynamoRIO. We evaluate the runtime overhead of BLACKBOX, and show that it can effectively monitor recent versions of Microsoft Office and Google Chrome. We show that in ROP, COOP, and state-of-the-art JIT injection attacks, BLACKBOX logs the pivotal actions by which the attacker takes control, and can also blacklist those actions to prevent repeated exploits.

关键词： Software Security Program Monitoring Control Flow Integrity Binary Rewriting dynamic code generation

来源：评论

学校读者我要写书评

暂无评论

C++ EDSL for parallel code generation

C++ EDSL for parallel code generation

引用

Romania Tier 2 Federation Grid, Cloud & High Performance Computing in Science Conference

作者： Daniel Berenyi GPU Lab Institute for Particle and Nuclear Physics Wigner RCP

ISBN: (纸本)9781479989171

code generation is ubiquitous for modern high-performance computing (HPC) to provide efficient but highly parametrizable program development. Many times functional dependencies should be made available for the user to manipulate, and such arbitrary functions should be efficiently parallelized over multiple levels. We propose an embedded domain specific language inside C++ for manipulating abstract syntax trees (ASTs) that can represent arbitrary computation, and that such language can be extended with constructs for parallelism and functional programming.

关键词： C++ EDSLs GPUs Functional programming dynamic code generation

来源：评论

学校读者我要写书评

暂无评论

Using standards to build the DIMAG connected mobile applications framework

引用

COMPUTER STANDARDS & INTERFACES 2014年第2期36卷 354-367页

作者： Miravet, Patricia Ortin, Francisco Mann, Ignacio Rionda, Abel CTIC Fdn Dept Res & Dev Gijon 33203 Spain Univ Oviedo Dept Comp Sci Oviedo 33007 Spain

The development of connected mobile applications is a complex task due to device diversity. Therefore, device-independent approaches are aimed at hiding the differences among the distinct mobile devices in the market. This work proposes DIMAG, a software framework to generate connected mobile applications for multiple software platforms, following a declarative approach. DIMAG provides transparent data and state synchronization between the server and the client side applications. The proposed platform has been designed making use of existing standards, extending them when a required functionality is not provided. (C) 2013 Elsevier B.V. All rights reserved.

关键词： Device fragmentation Mobile applications Data and state synchronization Partially connected architectures dynamic code generation

来源：评论

学校读者我要写书评

暂无评论

The Fastest Fourier Transform in the South

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2013年第19期61卷 4707-4716页

作者： Blake, Anthony M. Witten, Ian H. Cree, Michael J. Univ Waikato Dept Comp Sci Hamilton 3240 New Zealand Univ Waikato Sch Engn Hamilton 3240 New Zealand

This paper describes FFTS, a discrete Fourier transform (DFT) library that achieves state-of-the-art performance using a new cache-oblivious algorithm implemented with run-time specialization. During initialization the transform parameters, such as sign and direction, are fixed, allowing sequencing and data access information to be precomputed and specialized machine code to be generated. The resulting code may be executed any number of times on different input data. In contrast to FFTW, FFTS does not use large base cases at the leaves of recursion, nor a substantial library of codelets, and does not require time-consuming machine-specific calibration. The code presented in this paper has been benchmarked on recent Intel x86 and ARM machines, and is, in almost all cases, faster than self-tuning libraries such as FFTW, and even vendor-tuned libraries such as Intel IPP and Apple vDSP.

关键词： dynamic code generation FFT Fourier transform run-time specialization

来源：评论

学校读者我要写书评

暂无评论

A Java Expression Evaluator for Nonlinear Programming

A Java Expression Evaluator for Nonlinear Programming

引用

World Congress on Engineering (WCE 2013)

作者： Matias, J. Correia, A. Serodio, C. Teixeira, C. Mestre, P. Univ Tras Os Montes & Alto Douro CM UTAD Ctr Math Vila Real Portugal ESTGF IPP Porto Portugal UTAD CITAB Vila Real Portugal UTAD Vila Real Portugal

ISBN: (纸本)9789881925107

Finding the optimal value for a problem is usual in many areas of knowledge where in many cases it is needed to solve Nonlinear Optimization Problems. For some of those problems it is not possible to determine the expression for its objective function and/or its constraints, they are the result of experimental procedures, might be non-smooth, among other reasons. To solve such problems it was implemented an API contained methods to solve both constrained and unconstrained problems. This API was developed to be used either locally on the computer where the application is being executed or remotely on a server. To obtain the maximum flexibility both from the programmers' and users' points of view, problems can be defined as a Java class (because this API was developed in Java) or as a simple text input that is sent to the API. For this last one to be possible it was also implemented on the API an expression evaluator. One of the drawbacks of this expression evaluator is that it is slower than the Java native code. In this paper it is presented a solution that combines both options: the problem can be expressed at run-time as a string of chars that are converted to Java code, compiled and loaded dynamically. To wide the target audience of the API, this new expression evaluator is also compatible with the AMPL format.

关键词： Nonlinear Prograrruning Java API AMPL dynamic code generation

来源：评论

学校读者我要写书评

暂无评论

Performance Optimization by dynamic code Transformation 11

Performance Optimization by Dynamic Code Transformation

引用

8th ACM International Conference on Computing Frontiers (CF)

作者： Weidendorfer, Josef Kuestner, Tilman Mckee, Sally A. Tech Univ Munich Dept Informat Munich Germany Chalmers Comp Sci & Engn Gothenburg Sweden

ISBN: (纸本)9781450306980

Even parts of a program that are sequential or just inherently difficult to parallelize can be optimized for ILP. For instance, eliminating loop overheads and potential pipeline stalls from control flow can alleviate performance bottle-necks. Unfortunately, static compilation is limited in the extent to which it can identify opportunities to apply such optimizations. Generating code dynamically at run time, however, create much more efficient applications by usin information not available at compile time. We demonstrate our approach on a sparse-matrix PET scan code by aggressive unrolling loops and specializing code via dynamic code generation. We leverage task-level parallelism by having an auxiliary processor core concurrently generate code and feed it to the core executing the application. Our approach to fast code generation leverages patching and concatenating prepared code skeletons.

关键词： dynamic code generation performance optimizati

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：