检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Hunhold, Laslo Parallel and Distributed Systems Group University of Cologne Cologne Germany

Recent evaluations have highlighted the tapered posit number format as a promising alternative to the uniform precision IEEE 754 floating-point numbers, which suffer from various deficiencies. Although the posit encoding scheme offers superior coding efficiency at values close to unity, its efficiency markedly diminishes with deviation from unity. This reduction in efficiency leads to suboptimal encodings and a consequent diminution in dynamic range, thereby rendering posits suboptimal for general-purpose computer arithmetic. This paper introduces and formally proves ‘takum’ as a novel general-purpose logarithmic tapered-precision number format, synthesising the advantages of posits in low-bit applications with high encoding efficiency for numbers distant from unity. Takums exhibit an asymptotically constant dynamic range in terms of bit string length, which is delineated in the paper to be suitable for a general-purpose number format. It is demonstrated that takums either match or surpass existing alternatives. Moreover, takums address several issues previously identified in posits while unveiling novel and beneficial arithmetic *** Codes 68M07 (Primary), 65G30, 65Y04 (Secondary) © 2024, CC BY.

关键词： General purpose computers

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a Takum Arithmetic Hardware Codec in VHDL

arXiv

引用

arXiv 2024年

作者： Hunhold, Laslo Parallel and Distributed Systems Group University of Cologne Cologne Germany

The takum machine number format has been recently proposed as an enhancement over the posit number format, which is considered a promising alternative to the IEEE 754 floating-point standard. Takums retain the useful posit properties, but feature a novel exponent coding scheme that yields more precision for small and large magnitude numbers and a much higher and bounded dynamic range. This paper presents the design and implementation of a hardware codec for both takums (logarithmic number system, LNS) and linear takums (floating-point format). The codec design is emphasised, as it constitutes the primary distinguishing feature compared to logarithmic posits (LNS) and posits (floating-point format), which otherwise share similar internal representations. Furthermore, a novel internal representation for LNS is proposed. The proposed takum codec, implemented in VHDL, demonstrates near-optimal scalability and performance on an FPGA. It achieves latency reductions of up to 38% and reduces LUT utilisation up to 50% compared to state-of-the-art posit *** Codes 68M07 © 2024, CC BY.

关键词： Intellectual property core

来源：评论

学校读者我要写书评

暂无评论

Integer Representations in IEEE 754, Posit, and Takum Arithmetics

arXiv

引用

arXiv 2024年

作者： Hunhold, Laslo Parallel and Distributed Systems Group University of Cologne Cologne Germany

The posit and takum machine number formats have been proposed as alternatives to the IEEE 754 floating-point standard. As floating-point numbers are frequently employed to represent integral values, with certain applications explicitly relying on this capability, it is pertinent to evaluate how effectively these new formats fulfil this function compared to the standard they seek to replace. While empirical results are known for posits, this aspect has yet to be formally investigated. This paper provides rigorous derivations and proofs of the integral representation capabilities of posits and takums, examining both the exact number of bits required to represent a given integer and the largest consecutive integer that can be represented with a specified number of bits. The findings indicate that, while posits are generally less effective than IEEE 754 floating-point numbers in this regard, takums demonstrate overall superior representational strength compared to both IEEE 754 and posits. © 2024, CC BY.

关键词： Integer linear programming

来源：评论

学校读者我要写书评

暂无评论

Player-customized puzzle instance generation for Massively Multiplayer Online Games 09

Player-customized puzzle instance generation for Massively M...

引用

Annual Workshop on Network and systems Support for Games (NetGames)

作者： A. Iosup Parallel and Distributed Systems Group Delft University of Technnology Netherlands

ISBN: (纸本)9781424456055

Massively Multiplayer Online Games (MMOGs) have emerged as a new type of interactive application simultaneously played by millions around the world. Besides social interaction, players are entertained by content such as virtual world objects and logical challenges. Thus, developing content of good quality and in sufficient quantity is key for a successful MMOG. Currently, the content is generated exclusively by teams of human content designers, but the growth of the player population, the lack of scalability of the production pipeline, and the increase in the price ratio between human work and computation make this situation undesirable for the future. The paper investigates the problem of fully automated content generation for MMOGs, such that customized content that matches taste and previous game experience is available for each player. We take as a motivating example of content instances of puzzle games, that is, games in which the player is entertained by solving a logical challenge; for example, different players may each spend hours to solve different instances of chess puzzles to open the gates to the Labyrinth.

关键词： Humans Mesh generation Cloud computing Grid computing Runtime Databases Scalability Pipelines Flow production systems Large-scale systems

来源：评论

学校读者我要写书评

暂无评论

ELMO: A User-Friendly API to Enable Local Memory in OpenCL Kernels

ELMO: A User-Friendly API to Enable Local Memory in OpenCL K...

引用

Euromicro Conference on parallel, distributed and Network-Based Processing

作者： Jianbin Fang Ana Lucia Varbanescu Jie Shen Henk Sips Parallel and Distributed Systems Group Delft University of Technology Delft Netherlands

Recent parallel architectures are equipped with local memory, which simplifies hardware design at the cost of increased program complexity due to explicit management. To simplify this extra-burden that programmers have, we introduce an easy-to-use API, ELMO, that improves productivity while preserving high performance of local memory operations. Specifically, ELMO is a generic API that covers different local memory use-cases. We also present prototype implementations for these APIs and perform multiple GPU-inspired optimizations to maximize their performance. Experimental results on the NVIDIA Quadro5000 GPU show that performance is significantly improved by using ELMO on native implementations: the achieved speedup ranges from 1.3x to 3.7x. Furthermore, using ELMO we still achieve performance comparable (if not better) with that of hand-tuned applications, while the code is shorter, clearer, and safer.

关键词： Memory management Registers Kernel Indexes Bandwidth Optimization Geometry

来源：评论

学校读者我要写书评

暂无评论

A resource based framework for planning and replanning

A resource based framework for planning and replanning

引用

IEEE/WIC/ACM International Conference on Intelligent Agent Technology (IAT)

作者： R. van der Krogt M. de Weerdt C. Witteveen Parallel and Distributed Systems Group Delft University of Technnology Delft Netherlands

We discuss a rigorous unifying framework for both planning and replanning, extending an existing logic-based approach to resource-based planning. The primitive concepts in this action resource framework (ARF) are actions and resources. Actions consume and produce resources. Plans are structures composed of actions, resource facts and an explicit dependency function specifying their interrelationships. In this framework, both planning and replanning are conceived as plan transformation processes accomplished by applying sequences of operations on plans. For this, we introduce operators for plan transformation and define the concept of a plan library. Using a refinement planning template, we show how some existing (re)planning methods and heuristics can be described as special cases of this framework. The advantage of the framework is that it offers a unifying view on planning and replanning.

关键词： Technology planning Process planning Libraries Humans Databases Heuristic algorithms Intelligent agent

来源：评论

学校读者我要写书评

暂无评论

Performance Traps in OpenCL for CPUs

Performance Traps in OpenCL for CPUs

引用

Euromicro Conference on parallel, distributed and Network-Based Processing

作者： Jie Shen Jianbin Fang Henk Sips Ana Lucia Varbanescu Parallel and Distributed Systems Group Delft University of Technology Delft Netherlands

With its design concept of cross-platform portability, OpenCL can be used not only on GPUs (for which it is quite popular), but also on CPUs. Whether porting GPU programs to CPUs, or simply writing new code for CPUs, using OpenCL brings up the performance issue, usually raised in one of two forms: "OpenCL is not performance portable!" or "Why using OpenCL for CPUs after all?!". We argue that both issues can be addressed by a thorough study of the factors that impact the performance of OpenCL on CPUs. This analysis is the focus of this paper. Specifically, starting from the two main architectural mismatches between many-core CPUs and the OpenCL platform-parallelism granularity and the memory model-we identify eight such performance "traps" that lead to performance degradation in OpenCL for CPUs. Using multiple code examples, from both synthetic and real-life benchmarks, we quantify the impact of these traps, showing how avoiding them can give up to 10 times better performance. Furthermore, we point out that the solutions we provide for avoiding these traps are simple and generic code transformations, which can be easily adopted by either programmers or automated tools. Therefore, we conclude that a certain degree of OpenCL inter-platform performance portability, while indeed not a given, can be achieved by simple and generic code transformations.

关键词： Kernel Graphics processing units Benchmark testing parallel processing Data transfer Hardware Performance evaluation

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Performance Comparison of CUDA and OpenCL

A Comprehensive Performance Comparison of CUDA and OpenCL

引用

International Conference on parallel Processing (ICPP)

作者： Jianbin Fang Ana Lucia Varbanescu Henk Sips Parallel and Distributed Systems Group Delft University of Technology Delft Netherlands

This paper presents a comprehensive performance comparison between CUDA and OpenCL. We have selected 16 benchmarks ranging from synthetic applications to real-world ones. We make an extensive analysis of the performance gaps taking into account programming models, ptimization strategies, architectural details, and underlying compilers. Our results show that, for most applications, CUDA performs at most 30% better than OpenCL. We also show that this difference is due to unfair comparisons: in fact, OpenCL can achieve similar performance to CUDA under a fair comparison. Therefore, we define a fair comparison of the two types of applications, providing guidelines for more potential analyses. We also investigate OpenCL's portability by running the benchmarks on other prevailing platforms with minor modifications. Overall, we conclude that OpenCL's portability does not fundamentally affect its performance, and OpenCL can be a good alternative to CUDA.

关键词： Graphics processing unit Benchmark testing Programming Performance evaluation Computational modeling Kernel

来源：评论

学校读者我要写书评

暂无评论

An Auto-tuning Solution to Data Streams Clustering in OpenCL

An Auto-tuning Solution to Data Streams Clustering in OpenCL

引用

IEEE International Conference on Computational Science and Engineering, CSE

作者： Jianbin Fang Ana Lucia Varbanescu Henk Sips Parallel and Distributed Systems Group Delft University of Technology Delft Netherlands

Due to its applicability to numerous types of data, including telephone records, web documents, and click streams, the data stream model has recently attracted attention. For analysis of such data, it is crucial to process the data in a single pass, or a small number of passes, using little memory. This paper provides an OpenCL implementation for data streams clustering, and then presents several optimizations for it, which make it more efficient in terms of memory usage. In order to maximize performance for different problem sizes and architectures, we also propose an auto-tuning solution. Experimental results show that our fully optimized implementation can perform 2.1x and 1.4x faster than the native OpenCL implementation on NVIDIA GTX480 and AMD HD5870, respectively, it can also achieve 1.4x to 3.3x speedup relative to the original CUDA implementation solution on GTX480.

关键词： Optimization Graphics processing unit Mathematical model Equations Bandwidth Memory management Analytical models

来源：评论

学校读者我要写书评

暂无评论

Glinda: A framework for accelerating imbalanced applications on heterogeneous platforms 13

Glinda: A framework for accelerating imbalanced applications...

引用

2013 ACM International Conference on Computing Frontiers, CF 2013

作者： Shen, Jie Varbanescu, Ana Lucia Arntzen, Michael Simons, Dick G. Henk Sips Parallel and Distributed Systems Group Delft University of Technology Netherlands Air Transport and Operations Aerospace Engineering Delft University of Technology Netherlands Dutch National Aerospace Laboratory Netherlands

ISBN: (纸本)9781450320535

Heterogeneous platforms integrating different processors like GPUs and multi-core CPUs become popular in high performance computing. While most applications are currently using the homogeneous parts of these platforms, we argue that there is a large class of applications that can benefit from their heterogeneity: massively parallel imbalanced applications. Such applications emerge, for example, from variable time step based numerical methods and simulations. In this paper, we present Glinda, a framework for accelerating imbalanced applications on heterogeneous computing platforms. Our framework is able to correctly detect the application workload characteristics, make choices based on the available parallel solutions and hardware configuration, and automatically obtain the optimal workload decomposition and distribution. Our experiments on parallelizing a heavily imbalanced acoustic ray tracing application show that Glinda improves application performance in multiple scenarios, achieving up to 12× speedup against manually configured parallel solutions. Copyright 2013 ACM.

关键词： Ray tracing

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：