检索结果-内蒙古大学图书馆

approximate computing: Making Mobile Systems More Efficient

IEEE PERVASIVE computing 2015年第2期14卷 9-13页

作者： Moreau, Thierry Sampson, Adrian Ceze, Luis Univ Washington Seattle WA 98195 USA Univ Washington Comp Sci & Engn Seattle WA 98195 USA

approximate systems can reclaim energy that's currently lost to the "correctness tax" imposed by traditional safety margins designed to prevent worst-case scenarios. Researchers at the University of Washington have co-designed programming language extensions, a compiler, and a hardware co-processor to support approximate acceleration. Their end-to-end system includes two building blocks. First, a new programmer-guided compiler framework transforms programs to use approximation in a controlled way. An approximate C Compiler for Energy and Performance Tradeoffs (Accept) uses programmer annotations, static analysis, and dynamic profiling to find parts of a program that are amenable to approximation. Second, the compiler targets a system on a chip (SoC) augmented with a co-processor that can efficiently evaluate coarse regions of approximate code. A Systolic Neural Network Accelerator in Programmable logic (Snnap) is a hardware accelerator prototype that can efficiently evaluate approximate regions of code in a general-purpose program.

关键词： Approximation Methods Mobile Communication Neural Networks Benchmark Testing Program Processors Field Programmable Gate Arrays Energy Efficiency SNNAP approximate computing Mobile Pervasive computing Energy Efficiency Green computing ACCEPT

来源：评论

学校读者我要写书评

暂无评论

approximate computing using frequency upscaling

引用

IET CIRCUITS DEVICES & SYSTEMS 2019年第7期13卷 1018-1026页

作者： Huang, Junqi Kumar, T. Nandha Abbas, Haider Lombardi, Fabrizio Univ Nottingham Dept Elect & Elect Engn Selangor Malaysia Northeastern Univ Dept Elect & Comp Engn Boston MA 02115 USA

This study presents frequency upscaling as a technique for developing error resilient arithmetic designs in approximate computing whereby the input signal frequency of the circuit is upscaled beyond its largest operating value in generating errors in the arithmetic operation while speeding up the computational throughput. This study initially presents the mathematical modelling of frequency upscaling for both exact and inexact full adders. An exhaustive simulation and evaluation of 4 and 8 bits subtraction followed by addition of two images and approximate discrete cosine transform (DCT) is pursued using exact and inexact circuits when subjected to the proposed technique. The results estimated using the proposed model show good agreement with the simulation results. The normalised mean error distance of subtraction using an inexact circuit is close to the exact value for different technology nodes. The peak signal-to-noise ratio (PSNR) results for the addition of two images show that the inexact full adder achieves a higher output image quality than the exact circuit when the frequency is scaled up. Also, in an approximate DCT, the input frequency of an inexact full adder can be scaled up significantly higher than an exact full adder without a significant decrease in PSNR value.

关键词： discrete cosine transforms logic design adders approximation theory digital arithmetic approximate computing frequency upscaling error resilient arithmetic designs adder cell arithmetic operation computational throughput exact adders exhaustive simulation inexact circuit inexact full adder exact circuit approximate DCT input frequency exact full adder peak signal-to-noise ratio mathematical modelling approximate discrete cosine transform technology nodes PSNR word length 4 0 bit word length 8 0 bit

来源：评论

学校读者我要写书评

暂无评论

approximate computing Techniques for Iterative Graph Algorithms 24

Approximate Computing Techniques for Iterative Graph Algorit...

引用

IEEE 24th International Conference on High Performance computing Workshops (HiPCW)

作者： Panyala, Ajay Subasi, Omer Halappanavar, Mahantesh Kalyanaraman, Ananth Chavarria-Miranda, Daniel Krishnamoorthy, Sriram Pacific Northwest Natl Lab Richland WA 99352 USA Washington State Univ Pullman WA 99164 USA Trovares Inc Seattle WA USA

ISBN: (纸本)9781538622933

approximate computing enables processing of large-scale graphs by trading off quality for performance. approximate computing techniques have become critical not only due to the emergence of parallel architectures but also due to the availability of large scale datasets enabling data-driven discovery. Using two prototypical graph algorithms, PageRank and community detection, we present several approximate computing heuristics to scale the performance with minimal loss of accuracy. We present several heuristics including loop perforation, data caching, incomplete graph coloring and synchronization, and evaluate their efficiency. We demonstrate performance improvements of up to 83% for PageRank and up to 450x for community detection, with low impact on accuracy for both the algorithms. We expect the proposed approximate techniques will enable scalable graph analytics on data of importance to several applications in science and their subsequent adoption to scale similar graph algorithms.

关键词： Approximation algorithms approximate computing Iterative algorithms Color Convergence Algorithm design and analysis Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

approximate computing for onboard anomaly detection from hyperspectral images

引用

JOURNAL OF REAL-TIME IMAGE PROCESSING 2019年第1期16卷 99-114页

作者： Wu, Yuanfeng Lopez, Sebastian Zhang, Bing Qiao, Fei Gao, Lianru Chinese Acad Sci Inst Remote Sensing & Digital Earth Key Lab Digital Earth Sci Beijing Peoples R China Univ Las Palmas Gran Canaria Inst Appl Microelect Campus Tafira Las Palmas Gran Canaria Spain Tsinghua Univ Dept Elect Engn Beijing Peoples R China

Interest on anomaly detection for hyperspectral images has increasingly grown during the last decades due to the diversity of applications that benefit from this technique. However, the high computational cost inherent to this detection procedure seriously limits its processing efficiency, especially for onboard application scenarios. In this paper, a novel spectral and spatial approximate computing approach, named SSAC is proposed for onboard anomaly detection from hyperspectral images. To efficiently design the proposed approach, two preliminary aspects have been deeply analyzed in this work. First, data correlation in hyperspectral images in both spectral and spatial dimensions has been analyzed. The high data correlation in both spectral and spatial dimensions is considered to be one of the cornerstones of the SSAC approach. Second, the error resilience of a popular hyperspectral anomaly detection algorithm in both data level and algorithm level has been analyzed, which is considered to be another cornerstone of the SSAC approach. Based on the outcomes of this analysis, the processing of spectrally and spatially degraded images has been employed for reducing computation complexity in onboard hyperspectral anomaly detection scenarios in this work. Performance assessment tools such as ROC curves, Cost curves, and computing times have been used for evaluating the computing accuracy and efficiency of our proposal. The results obtained with a nonlinear anomaly detector for hyperspectral imagery, such as the well-known kernel RX-algorithm, show that the proposed SSAC approach greatly improves anomaly detection efficiency compared to the traditional method with negligible degeneration in accuracy. This is an important achievement to meet the restrictions of onboard hyperspectral anomaly detection scenarios.

关键词： Anomaly detection approximate computing Hyperspectral image Spectral spatial degradation Onboard applications

来源：评论

学校读者我要写书评

暂无评论

approximate computing for complexity reduction in timing synchronization

引用

EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING 2014年第1期2014卷 1-7页

作者： Airoldi, Roberto Campi, Fabio Nurmi, Jari Tampere Univ Technol Dept Elect & Commun Engn FI-33720 Tampere Finland Simon Fraser Univ Sch Engn Sci Burnaby BC V5A 1S6 Canada

This paper presents the design and performance evaluation of a reduced complexity algorithm for timing synchronization. The complexity reduction is obtained via the introduction of approximate computing, which lightens the computational load of the algorithm with a minimal loss in precision. Timing synchronization for wideband-code division multiple access (W-CDMA) systems is utilized as the case study and experimental results show that the proposed approach is able to deliver performance similar to traditional approaches. At the same time, the proposed algorithm is able to cut the computational complexity of the traditional algorithm by a 20% factor. Furthermore, the estimation of power consumption on a reference architecture, showed that a 20% complexity reduction, corresponds to a total power saving of 45%.

关键词： Timing synchronization approximate computing W-CDMA

来源：评论

学校读者我要写书评

暂无评论

approximate computing for Multithreaded Programs in Shared Memory Architectures 19

Approximate Computing for Multithreaded Programs in Shared M...

引用

17th ACM-IEEE Inter- national Conference on Formal Methods and Models for System Design (MEMOCODE)

作者： Nongpoh, Bernard Ray, Rajarshi Banerjee, Ansuman Natl Inst Technol Meghalaya Dept Comp Sci & Engn Shillong Meghalaya India Indian Assoc Cultivat Sci Sch Math & Computat Sci Kolkata W Bengal India Indian Stat Inst Adv Comp & Microelect Unit Kolkata W Bengal India

ISBN: (纸本)9781450369978

In multicore and multicached architectures, cache coherence is ensured with a coherence protocol. However, the performance benefits of caching diminishes due to the cost associated with the protocol implementation. In this paper, we propose a novel technique to improve the performance of multithreaded programs running on shared-memory multicore processors by embracing approximate computing. Our idea is to relax the coherence requirement selectively in order to reduce the cost associated with a cache-coherence protocol, and at the same time, ensure a bounded QoS degradation with probabilistic reliability. In particular, we detect instructions in a multithreaded program that write to shared data, we call them Shared-Write-Access-Points (SWAPs), and propose an automated statistical analysis to identify those which can tolerate coherence faults. We call such SWAPs approximable. Our experiments on 9 applications from the SPLASH 3.0 benchmarks suite reveal that an average of 57% of the tested SWAPs are approximable. To leverage this observation, we propose an adapted cache-coherence protocol that relaxes the coherence requirement on stores from approximable SWAPs. Additionally, our protocol uses stale values for load misses due to coherence, the stale value being the version at the time of invalidation. We observe an average of 15% reduction in CPU cycles and 11% reduction in energy footprint from architectural simulation of the 9 applications using our approximate execution scheme.

关键词： Hypothesis testing Cache-Coherence approximate computing

来源：评论

学校读者我要写书评

暂无评论

approximate computing for Spiking Neural Networks 20

Approximate Computing for Spiking Neural Networks

引用

20th Conference and Exhibition on Design, Automation and Test in Europe (DATE)

作者： Sen, Sanchari Venkataramani, Swagath Raghunathan, Anand Purdue Univ Sch Elect & Comp Engn W Lafayette IN 47907 USA IBM TJ Watson Res Ctr Yorktown Hts NY USA

ISBN: (纸本)9783981537093

Spiking Neural Networks (SNNs) are widely regarded as the third generation of artificial neural networks, and are expected to drive new classes of recognition, data analytics and computer vision applications. However, large-scale SNNs (e.g., of the scale of the human visual cortex) are highly compute and data intensive, requiring new approaches to improve their efficiency. Complementary to prior efforts that focus on parallel software and the design of specialized hardware, we propose AxSNN, the first effort to apply approximate computing to improve the computational efficiency of evaluating SNNs. In SNNs, the inputs and outputs of neurons are encoded as a time series of spikes. A spike at a neuron's output triggers updates to the potentials (internal states) of neurons to which it is connected. AxSNN determines spike-triggered neuron updates that can be skipped with little or no impact on output quality and selectively skips them to improve both compute and memory energy. Neurons that can be approximated are identified by utilizing various static and dynamic parameters such as the average spiking rates and current potentials of neurons, and the weights of synaptic connections. Such a neuron is placed into one of many approximation modes, wherein the neuron is sensitive only to a subset of its inputs and sends spikes only to a subset of its outputs. A controller periodically updates the approximation modes of neurons in the network to achieve energy savings with minimal loss in quality. We apply AxSNN to both hardware and software implementations of SNNs. For hardware evaluation, we designed SNNAP, a Spiking Neural Network approximate Processor that embodies the proposed approximation strategy, and synthesized it to 45nm technology. The software implementation of AxSNN was evaluated on a 2.7 GHz Intel Xeon server with 128 GB memory. Across a suite of 6 image recognition benchmarks, AxSNN, achieves 1.4-5.5x reduction in scalar operations for network evaluation, which

关键词： approximate computing Spiking Neural Networks approximate Neural Networks

来源：评论

学校读者我要写书评

暂无评论

approximate computing in Chrominance Cache for Image/Video Processing 1

Approximate Computing in Chrominance Cache for Image/Video P...

引用

IEEE First International Conference on Multimedia Big Data

作者： Qiao, Fei Zhou, Ni Chen, Yuanchang Yang, Huazhong Tsinghua Univ Inst Circuit & Syst Dept Elect Engn Tsinghua Natl Lab Informat Sci & Technol Beijing 100084 Peoples R China

ISBN: (纸本)9781479986880

An approximate computing method for chrominance data of the video/image sequences is proposed in this paper, which is implemented in one hybrid cache architecture. This approach fully exploits the fact that the sensitivity of chrominance is much lower than that of luminance to reduce off-chip memory access of chrominance data. For the 4: 2: 0 image format, the proposed approximate computing method can achieve 25% reduction in off-chip memory access with the 2x2 basic approximate unit. Moreover, for the image formats of 4: 2: 2 and 4: 4: 4, it has about 37.5% and 50% access reduction of off-chip memory, respectively, with acceptable degradation of image quality to human visual system.

关键词： approximate computing chrominace hybrid cache image/video processing

来源：评论

学校读者我要写书评

暂无评论

approximate computing based on Latest-result Reuse for Image Edge Detection 35

Approximate Computing based on Latest-result Reuse for Image...

引用

35th International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC)

作者： Usami, Kimiyoshi Ochi, Hajime Ono, Yoshinori Shibaura Inst Technol Dept Comp Sci & Engn Koto Ku Tokyo 1358548 Japan Shibaura Inst Technol Grad Sch Engn & Sci Koto Ku Tokyo 1358548 Japan

ISBN: (纸本)9784885523281

This paper describes a memo-table-free approximate computing technique for an image edge detector to reuse the computed result only in the closest past. Decision of reuse is made based on tolerance-level controllable similarity checking for two consecutive 3x3 input pixels. We designed and implemented the proposed approximate edge detector in an FPGA and evaluated with 6 benchmark images. Results have demonstrated that by controlling the tolerance level the execution time is reduced by 15% and the energy dissipation is saved by 3-12% compared with the precise computation at acceptable quality in edge detected images.

关键词： approximate computing reuse image edge detector FPGA energy savings

来源：评论

学校读者我要写书评

暂无评论

approximate computing: From Circuits to Applications

引用

PROCEEDINGS OF THE IEEE 2020年第12期108卷 2103-2107页

作者： Liu, Weiqiang Lombardi, Fabrizio Schulte, Michael NUAA Coll Elect & Informat Engn Nanjing Jiangsu Peoples R China Northeastern Univ Boston MA USA Univ Wisconsin Madison WI 53706 USA Lehigh Univ Bethlehem PA 18015 USA AMD Res Austin TX USA

This special issue explores the technological contributions and developments of approximate computing at disparate levels and provides insight into exciting directions for the future.

关键词： Special issues and sections approximate computing Computer architecture Artificial intelligence Approximation algorithms

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：