检索结果-内蒙古大学图书馆

39th ACM SIGPLAN Conference on programming Language Design and Implementation (PLDI)

作者： Acar, Umut A. Chargueraud, Arthur Guatto, Adrien Rainey, Mike Sieczkowski, Filip Carnegie Mellon Univ Pittsburgh PA 15213 USA INRIA Rocquencourt France Univ Strasbourg ICube Strasbourg France CREST Bloomington IN USA

ISBN: (纸本)9781450356985

A classic problem in parallel computing is to take a high-level parallel program written, for example, in nested-parallel style with fork-join constructs and run it efficiently on a real machine. The problem could be considered solved in theory, but not in practice, because the overheads of creating and managing parallel threads can overwhelm their benefits. Developing efficient parallel codes therefore usually requires extensive tuning and optimizations to reduce parallelism just to a point where the overheads become acceptable. In this paper, we present a scheduling technique that delivers provably efficient results for arbitrary nested-parallel programs, without the tuning needed for controlling parallelism overheads. The basic idea behind our technique is to create threads only at a beat (which we refer to as the "heartbeat") and make sure to do useful work in between. We specify our heartbeat scheduler using an abstract-machine semantics and provide mechanized proofs that the scheduler guarantees low overheads for all nested parallel programs. We present a prototype C++ implementation and an evaluation that shows that Heartbeat competes well with manually optimized Cilk Plus codes, without requiring manual tuning.

关键词： parallel programming languages granularity control

来源：评论

学校读者我要写书评

暂无评论

On Demand Specialization of SYCL Kernels with Specialization Constant Length Allocations (SCLA) 24

On Demand Specialization of SYCL Kernels with Specialization...

引用

12th International Workshop on OpenCL and SYCL, IWOCL 2024

作者： Pérez, Víctor Lomüller, Victor Sommer, Lukas Oppermann, Julian Biessy, Romain Ciglarič, Tadej Goli, Mehdi Codeplay Software Ltd United Kingdom

No abstract available.

ISBN: (纸本)9798400717901

No abstract available.

关键词： Just-in-time compilers parallel programming languages SPIR-V SYCL Specialization constants

来源：评论

学校读者我要写书评

暂无评论

IMPLEMENTING OBJECT-BASED DISTRIBUTED SHARED MEMORY ON TRANSPUTERS

IMPLEMENTING OBJECT-BASED DISTRIBUTED SHARED MEMORY ON TRANS...

引用

1994 World Transputer Congress (WTC 94) - Transputer Applications and Systems 94

作者： HEINZLE, HP BAL, HE LANGENDOEN, K FREE UNIV AMSTERDAM DEPT MATH & COMP SCI1007 MC AMSTERDAMNETHERLANDS

来源：评论

学校读者我要写书评

暂无评论

Networked workstations and parallel processing utilizing functional languages

Networked workstations and parallel processing utilizing fun...

引用

作者： Fox, Stanley L. Naval Postgraduate School

学位级别：硕士

Alternative computer architectures are necessary to replace the traditional 'von Neumann' computer organization in order to obtain large increases in performance. The traditional 'von Neumann' architecture uses a timer based (e. g., the program counter), sequentially programmed, single processor approach to problem solving. Today's new hardware technology allows for the utilization of multiple processors. By programming and operating these processors in parallel, this alternative architecture will provide for greater computing speed, improved system reliability, enhanced software manageability, and a more cost-effective approach than our present computing practices.

关键词： parallel processing distributed computing functional languages parallel programming languages

来源：评论

学校读者我要写书评

暂无评论

Safe Nondeterminism in a Deterministic-by-Default parallel Language 11

Safe Nondeterminism in a Deterministic-by-Default Parallel L...

引用

38th Symposium on Principles of programming languages

作者： Bocchino, Robert L., Jr. Heumann, Stephen Honarmand, Nima Adve, Sarita V. Adve, Vikram S. Welc, Adam Shpeisman, Tatiana Carnegie Mellon Univ Pittsburgh PA 15213 USA

ISBN: (纸本)9781450304900

A number of deterministic parallel programming models with strong safety guarantees are emerging, but similar support for non-deterministic algorithms, such as branch and bound search, remains an open question. We present a language together with a type and effect system that supports nondeterministic computations with a deterministic-by-default guarantee: nondeterminism must be explicitly requested via special parallel constructs (marked nd), and any deterministic construct that does not execute any nd construct has deterministic input-output behavior. Moreover, deterministic parallel constructs are always equivalent to a sequential composition of their constituent tasks, even if they enclose, or are enclosed by, nd constructs. Finally, in the execution of nd constructs, interference may occur only between pairs of accesses guarded by atomic statements, so then;are no data races, either between atomic statements and unguarded accesses (strong isolation) or between pairs of unguarded access (stronger than strong isolation alone). We enforce the guarantees at compile time with modular checking using novel,extensions to a previously described effect system. Our effect system extensions also enable the compiler to remove unnecessary transactional synchronization. We provide a static semantics, dynamic semantics, and a complete proof of soundness for the language;both with, and without the barrier removal feature. An experimental evaluation shows that our language can achieve good scalability for realistic parallel algorithms, and that the barrier removal techniques provide significant performance gains.

关键词： strong isolation transactional memory determinism atomicity effects parallel programming languages data race freedom tranasctions effect systems nondeterminism atomic sections

来源：评论

学校读者我要写书评

暂无评论

User-driven Online Kernel Fusion for SYCL

引用

ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION 2023年第2期20卷 21-21页

作者： Perez, Victor Sommer, Lukas Lomuller, Victor Narasimhan, Kumudha Goli, Mehdi Codeplay Software Ltd Level C Argyle House3 Lady Lawson St Edinburgh EH3 9DR Scotland

Heterogeneous programming models are becoming increasingly popular to support the ever-evolving hardware architectures, especially for new and emerging specialized accelerators optimizing specific tasks. While such programs provide performance portability of the existing applications across various heterogeneous architectures to some extent, short-running device kernels can affect an application performance due to overheads of data transfer, synchronization, and kernel launch. While in applications with one or two short-running kernels the overhead can be negligible, it can be noticeable when these short-running kernels dominate the overall number of kernels in an application, as it is the case in graph-based neural network models, where there are several small memory-bound nodes alongside few large compute-bound nodes. To reduce the overhead, combining several kernels into a single, more optimized kernel is an active area of research. However, this task can be time-consuming and error-prone given the huge set of potential combinations. This can push programmers to seek a tradeoffbetween (a) task-specific kernels with low overhead but hard to maintain and (b) smaller modular kernels with higher overhead but easier to maintain. While there are DSL-based approaches, such as those provided for machine learning frameworks, which offer the possibility of such a fusion, they are limited to a particular domain and exploit specific knowledge of that domain and, as a consequence, are hard to port elsewhere. This study explores the feasibility of a user-driven kernel fusion through an extension to the SYCL API to address the automation of kernel fusion. The proposed solution requires programmers to define the subgraph regions that are potentially suitable for fusion without any modification to the kernel code or the function signature. We evaluate the performance benefit of our approach on common neural networks and study the performance improvement in detail.

关键词： Just-in-time compilers runtime environments parallel programming languages

来源：评论

学校读者我要写书评

暂无评论

parallel programming WITH CONTROL ABSTRACTION

引用

ACM TRANSACTIONS ON programming languages AND SYSTEMS 1994年第3期16卷 524-576页

作者： CROWL, LA LEBLANC, TJ UNIV ROCHESTER DEPT COMP SCIROCHESTERNY 14627

parallel programming involves finding the potential parallelism in an application and mapping it to the architecture at hand. Since a typical application has more potential parallelism than any single architecture can exploit effectively, programmers usually limit their focus to the parallelism that the available control constructs express easily and that the given architecture exploits efficiently. This approach produces programs that exhibit much less parallelism than exists in the application, and whose performance depends critically on the underlying hardware and software. We argue for an alternative approach based on control abstraction. Control abstraction is the process by which programmers define new control constructs, specifying constraints on statement ordering separately from an implementation of that ordering. With control abstraction programmers can define and use a rich variety of control constructs to represent an algorithm's potential parallelism. Since control abstraction separates the definition of a construct from its implementation, a construct may have several different implementations, each exploiting a different subset of the parallelism admitted by the construct. By selecting an implementation for each control construct using annotations, a programmer can vary the parallelism in a program to best exploit the underlying hardware without otherwise changing the source code. This approach produces programs that exhibit most of the potential parallelism in an algorithm, and whose performance can be tuned simply by choosing among the various implementations for the control constructs in use. We use several example applications to illustrate the use of control abstraction in parallel programming and performance tuning and describe our implementation of a prototype programming language based on these ideas on the BBN Butterfly.

关键词： ALGORITHMS DESIGN languages ARCHITECTURAL ADAPTABILITY CLOSURES CONTROL ABSTRACTION DATA ABSTRACTION EARLY REPLY MULTIPROCESSORS parallel programming languages PERFORMANCE TUNING

来源：评论

学校读者我要写书评

暂无评论

MODELS AND TRENDS IN parallel programming

引用

parallel Algorithms and Applications 2001年第2期16卷 145-180页

作者： Domenico Talia

This paper introduces and discusses programming models for parallel processing and recent trends in the area of parallel programming. The paper discusses different parallel programming languages and tools that reflect various parallel computation models. These language differ in expressiveness, portability and performance. Software design and implementation largely varies by using different languages that make the programmer task easy or complex. We describe here the design goals and the main issues of parallel programming models and languages belonging to the following categories: shared-space based languages, message-based languages, parallel toolkits, data-parallel languages, parallel declarative languages, parallel object-oriented languages, and parallel composition-based languages. Tools and languages such as HPF, Linda, Java, OpenMP, PVM, MPI, parallel C+ +, Sisal, Orca, Mentat, SkieCL, BSP and others are described in some detail. Their main features for design and implementation of high performance applications are discussed. Finally, we outline directions of research and development in the parallel programming area with a special attention to novel approaches based on high-level programming structures that make transparent to the users the architectural details of parallel computing machines.

关键词： parallel processing parallel programming languages Software tools Multicomputers Multiprocessors

来源：评论

学校读者我要写书评

暂无评论

MINIME-GPU: Multicore Benchmark Synthesizer for GPUs

引用

ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION 2016年第4期12卷 34-34页

作者： Deniz, Etem Sen, Alper Bogazici Univ Dept Comp Engn TR-34342 Istanbul Turkey

We introduce MINIME-GPU, a novel automated benchmark synthesis framework for graphics processing units (GPUs) that serves to speed up architectural simulation of modern GPU architectures. Our framework captures important characteristics of original GPU applications and generates synthetic GPU benchmarks using the Open Computing Language (OpenCL) library from those applications. To the best of our knowledge, this is the first time synthetic OpenCL benchmarks for GPUs are generated from existing applications. We use several characteristics, including instruction throughput, compute unit occupancy, and memory efficiency, to compare the similarity of original applications and their corresponding synthetic benchmarks. The experimental results show that our synthetic benchmark generation framework is capable of generating synthetic benchmarks that have similar characteristics with the original applications from which they are generated. On average, the similarity (accuracy) is 96% and the speedup is 541x. In addition, our synthetic benchmarks use the OpenCL library, which allows us to obtain portable human readable benchmarks as opposed to using assembly-level code, and they are faster and smaller than the original applications from which they are generated. We experimentally validated that our synthetic benchmarks preserve the characteristics of the original applications across different architectures.

关键词： Performance Experimentation parallel programming languages Heterogeneous Architectures GPU OpenCL synthetic benchmarks benchmark characterization benchmark generation

来源：评论

学校读者我要写书评

暂无评论

Selecting and using a parallel programming language (abstract only) 13

Selecting and using a parallel programming language (abstrac...

引用

Proceeding of the 44th ACM technical symposium on Computer science education

作者： Michael Graf David Bunde David Ely David Lucas Jens Mache Chris Mitchell Andrei Papancea Miriam Robinson Ben White Knox College Galesburg IL USA The Ohio State University Columbus OH USA Lewis & Clark College Portland OR USA CloudBolt Software Rockville MD USA Lewis & Clark College Portland OR Uae

ISBN: (纸本)9781450318686

One promising approach to teaching parallel programming is to use high-level parallel programming languages, which handle some of the more mundane details of parallel programming and allow both instructors and students to focus on the main ideas. How does one go about selecting the language to use? We present short descriptions of a variety of languages (Chapel, Cilk, CUDA, Habanero Java, Hadoop, OpenACC, OpenMP and Scala), including our assessment of their strengths and weaknesses, plus some general considerations to keep in mind when teaching parallel programming.

关键词： teaching parallel programming high-level languages parallel programming languages

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：