检索结果-内蒙古大学图书馆

Proceedings of the 18th USENIX Conference on File and Storage Technologies

作者： Miryeong Kwon Donghyun Gouk Changrim Lee Byounggeun Kim Jooyoung Hwang Myoungsoo Jung Computer Architecture and Memory Systems Laboratory Korea Advanced Institute of Science and Technology Computer Architecture and Memory Systems Laboratory Samsung

ISBN: (纸本)9781939133120

We propose DC-store, a storage framework that offers deterministic I/O performance for a multi-container execution environment. DC-store's hardware-level design implements multiple NVM sets on a shared storage pool, each providing a deterministic SSD access time by removing internal resource conflicts. In parallel, software support of DC-Store is aware of the NVM sets and enlightens Linux kernel to isolate noisy neighbor containers, performing page frame reclaiming, from peers. We prototype both hardware and software counterparts of DC-Store and evaluate them in a real system. The evaluation results demonstrate that containerized data-intensive applications on DC-Store exhibit 31% shorter average execution time, on average, compared to those on a baseline system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Aware: Adaptive Distributed Training with Computation, Communication and Position Awareness for Deep Learning Model 24

Aware: Adaptive Distributed Training with Computation, Commu...

引用

24th IEEE International Conference on High Performance Computing and Communications, 8th IEEE International Conference on Data science and Systems, 20th IEEE International Conference on Smart City and 8th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Application, HPCC/DSS/SmartCity/DependSys 2022

作者： Zeng, Yan Yi, Guangzheng Yin, Yuyu Wu, Jiyang Xue, Meiting Zhang, Jilin Wan, Jian Zhang, Yunquan School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China School of Cyberspace Hangzhou Dianzi University Hangzhou China Institute of Computing Technology Chinese Academy of Sciences State Key Laboratory of Computer Architecture Beijing China

ISBN: (纸本)9798350319934

The accuracy of the neural networks can usually be improved by increasing the size of the dataset and the layers or operators of the network, as it has strong composability. But, it makes a challenge to train these models efficiently, due to the limited resources of a single device, such as memory, computational resource and so on. For this challenge, it has become an inevitable trend to automatically implement model parallelism across multiple devices. This paper proposes Aware, an adaptive distributed parallel training method, to search distributed parallel strategy automatically for deep learning model. It firstly proposes an operator fusion strategy with computation and communication awareness to simplify the computational graph of deep learning model. And then, it introduces position-aware graph embedding algorithm to extract the structural features of models, which can make the searched parallel strategies to transplant to other networks with similar structures. On this basis, we use reinforcement learning algorithm to search distributed parallel strategy automatically. This paper makes experiments with neural networks such as Inception V3, NMT, GNM, NasNet and ResNet, and uses CIFAR10 and PTB datasets to compare the two methods of Hierarchical and Placeto. The results show that compared with Placeto, Aware achieves up to 5% reductions in runtime. Aware achieves more than 8% reductions in runtime compared with Hierarchical. Moreover, it has better transplantation and generalization capabilities, and supports pre-training for large-scale network parallel strategy search and accelerates convergence. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Fast assembling of neuron fragments in serial 3D sections

引用

Brain Informatics 2017年第3期4卷 183-186页

作者： Chen, Hanbo Iascone, Daniel Maxim da Costa, Nuno Maçarico Lein, Ed S. Liu, Tianming Peng, Hanchuan Allen Institute for Brain Science SeattleWA United States Cortical Architecture Imaging and Discovery Laboratory Department of Computer Science and Bioimaging Research Center The University of Georgia AthensGA United States Department of Neuroscience Columbia University New YorkNY United States

Reconstructing neurons from 3D image-stacks of serial sections of thick brain tissue is very time-consuming and often becomes a bottleneck in high-throughput brain mapping projects. We developed NeuronStitcher, a software suite for stitching non-overlapping neuron fragments reconstructed in serial 3D image sections. With its efficient algorithm and user-friendly interface, NeuronStitcher has been used successfully to reconstruct very large and complex human and mouse neurons. © 2017, The Author(s).

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Multiple TCP connections in iSCSI

Performance Evaluation of Multiple TCP connections in iSCSI

引用

IEEE/NASA Goddard Conference on Mass Storage Systems and Technologies, (MSST)

作者： Bhargava K. Kancherla Ganesh M. Narayan K. Gopinath Computer Architecture and Systems Laboratory Department of Computer Science and Automation Indian Institute of Science Bangalore India

Storage area networks (SANs) based on fibre channel have been used extensively in the last decade while iSCSI is fast becoming a serious contender due to its reduced costs and unified infrastructure. This work examines the performance of iSCSI with multiple TCP connections. Multiple TCP connections are often used to realize higher bandwidth but there may be no fairness in how bandwidth is distributed. We propose a mechanism to share congestion information across multiple flows in "Fair-TCP" for improved performance. Our results show that Fair-TCP significantly improves the performance for I/O intensive workloads.

关键词： Throughput TCPIP Wide area networks Storage area networks Encapsulation Storage automation Bandwidth Transport protocols Optical fiber cables computer architecture

来源：评论

学校读者我要写书评

暂无评论

A Benchmark of Ocular Disease Intelligent Recognition: One Shot for Multi-disease Detection 3rd

A Benchmark of Ocular Disease Intelligent Recognition: One S...

引用

3rd BenchCouncil International Symposium on Benchmarking, Measuring, and Optimizing, Bench 2020

作者： Li, Ning Li, Tao Hu, Chunyu Wang, Kai Kang, Hong College of Computer Science Nankai university Tianjin300350 China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Science Beijing100190 China Beijing Shanggong Medical Technology Co. Ltd. Beijing100176 China

ISBN: (纸本)9783030710576

In ophthalmology, early fundus screening is an economic and effective way to prevent blindness caused by ophthalmic diseases. Clinically, due to the lack of medical resources, manual diagnosis is time-consuming and may delay the condition. With the development of deep learning, some researches on ophthalmic diseases have achieved good results, however, most of them are just based on one disease. During fundus screening, ophthalmologists usually give diagnoses of multi-disease on binocular fundus image, so we release a dataset with 8 diseases to meet the real medical scene, which contains 10,000 fundus images from both eyes of 5,000 patients. We did some benchmark experiments on it through some state-of-the-art deep neural networks. We found simply increasing the scale of network cannot bring good results for multi-disease classification, and a well-structured feature fusion method combines characteristics of multi-disease is needed. Through this work, we hope to advance the research of related fields. © 2021, Springer Nature Switzerland AG.

关键词： computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Testable critical path selection considering process variation

Testable critical path selection considering process variati...

引用

作者： Fu, Xiang Li, Huawei Li, Xiaowei Key Laboratory of Computer System and Architecture Institute of Computing Technology Chinese Academic of Science Beijing 100190 China Graduate University of Chinese Academic of Sciences Beijing 100039 China

Critical path selection is very important in delay testing. Critical paths found by conventional static timing analysis (STA) tools are inadequate to represent the real timing of the circuit, since neither the testability of paths nor the statistical variation of cell delays caused by process variation is considered. This paper proposed a novel path selection method considering process variation. The circuit is firstly simplified by eliminating non-critical edges under statistical timing model, and then divided into sub-circuits, while each sub-circuit has only one prime input (PI) and one prime output (PO). Critical paths are selected only in critical sub-circuits. The concept of partially critical edges (PCEs) and completely critical edges (CCEs) are introduced to speed up the path selection procedure. Two path selection strategies are also presented to search for a testable critical path set to cover all the critical edges. The experimental results showed that the proposed circuit division approach is efficient in path number reduction, and PCEs and CCEs play an important role as a guideline during path selection. Copyright © 2010 The institute of Electronics.

关键词： Delay circuits

来源：评论

学校读者我要写书评

暂无评论

LONGHEADS: Multi-Head Attention is Secretly a Long Context Processor

LONGHEADS: Multi-Head Attention is Secretly a Long Context P...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Lu, Yi Zhou, Xin He, Wei Zhao, Jun Ji, Tao Gui, Tao Zhang, Qi Huang, Xuanjing School of Computer Science Fudan University Shanghai China Institute of Modern Languages and Linguistics Fudan University Shanghai China Key Laboratory of Intelligent Information Processing Fudan University Shanghai China

ISBN: (纸本)9798891761681

Large language models (LLMs) have achieved impressive performance in numerous domains but often struggle to process lengthy inputs effectively and efficiently due to limited length generalization and attention's quadratic computational demands. Many sought to mitigate this by restricting the attention window within the pre-trained length. However, these methods introduce new issues such as ignoring the middle context and requiring additional training. To address these problems, we propose LONGHEADS, a training-free framework that enhances LLM's long context ability by unlocking multi-head attention's untapped potential. Instead of allowing each head to attend to the full sentence, which struggles with generalizing to longer sequences, we allow each head to process in-distribution length by selecting and attending to important context chunks. To this end, we propose a chunk selection strategy that relies on the inherent correlation between the query and the key representations, efficiently distributing context chunks to different heads. In this way, each head ensures it can effectively process attended tokens within the trained length, while different heads in different layers can collectively process longer contexts. LONGHEADS works efficiently and fits seamlessly with many LLMs that use relative positional encoding. LONGHEADS achieves 100% accuracy at the 128k length on passkey retrieval task, verifying LONGHEADS's efficacy in extending the usable context window for existing models. We release our code at https://***/LuLuLuyi/LongHeads. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Adaptive weighting for neural machine translation 27

Adaptive weighting for neural machine translation

引用

27th International Conference on Computational Linguistics, COLING 2018

作者： Li, Yachao Li, Junhui Zhang, Min Institute of Artificial Intelligence School of Computer Science and Technology Soochow University China Key Laboratory of China’s Ethnic Languages and Information Technology of Ministry of Education Northwest Minzu University China

ISBN: (纸本)9781948087506

In the popular sequence to sequence (seq2seq) neural machine translation (NMT), there exist many weighted sum models (WSMs), each of which takes a set of input and generates one output. However, the weights in a WSM are independent of each other and fixed for all inputs, suggesting that by ignoring different needs of inputs, the WSM lacks effective control on the influence of each input. In this paper, we propose adaptive weighting for WSMs to control the contribution of each input. Specifically, we apply adaptive weighting for both GRU and the output state in NMT. Experimentation on Chinese-to-English translation and English-to-German translation demonstrates that the proposed adaptive weighting is able to much improve translation accuracy by achieving significant improvement of 1.49 and 0.92 BLEU points for the two translation tasks. Moreover, we discuss in-depth on what type of information is encoded in the encoder and how information influences the generation of target words in the decoder. © 2018 COLING 2018 - 27th International Conference on Computational Linguistics, Proceedings. All rights reserved.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Providing fairness on shared-memory multiprocessors via process scheduling 12

Providing fairness on shared-memory multiprocessors via proc...

引用

12th Joint International Conference on Measurement and Modeling of computer Systems, ACM SIGMETRICS/Performance 2012

作者： Xu, Di Wu, Chenggang Yew, Pen-Chung Li, Jianjun Wang, Zhenjiang State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing China Graduate University Chinese Academy of Sciences Beijing China Department of Computer Science and Engineering University of Minnesota at Twin-Cities MN United States Institute of Information Science Academia Sinica Taiwan

ISBN: (纸本)9781450310970

Competition for shared memory resources on multiprocessors is the most dominant cause for slowing down applications and makes their performance varies unpredictably. It exacerbates the need for Quality of Service (QoS) on such systems. In this paper, we propose a fair-progress process scheduling (FPS) policy to improve system fairness. Its strategy is to force the equally-weighted applications to have the same amount of slowdown when they run concurrently. The basic approach is to monitor the progress of all applications at runtime. When we find an application suffered more slowdown and accumulated less effective work than others, we allocate more CPU time to give it a better parity. Our policy also allows different weights to different threads, and provides an effective and robust tuner that allows the OS to freely make tradeoffs between system fairness and higher throughput. Evaluation results show that FPS can significantly improve system fairness by an average of 53.5% and 65.0% on a 4-core processor with a private cache and a 4-core processor with a shared cache, respectively. The penalty is about 1.1% and 1.6% of the system throughput. For memory-intensive workloads, FPS also improves system fairness by an average of 45.2% and 21.1% on 4-core and 8-core system respectively at the expense of a throughput loss of about 2%. © 2012 ACM.

关键词： Throughput

来源：评论

学校读者我要写书评

暂无评论

Block-gram: Mining Knowledgeable Features for Smart Contract Vulnerability Detection 7th

Block-gram: Mining Knowledgeable Features for Smart Contrac...

引用

7th International Conference on Smart Computing and Communication, SmartCom 2022

作者： Li, Tao Wang, Haolong Fang, Yaozheng Jian, Zhaolong Wang, Zichun Xie, Xueshuo Tianjin Key Laboratory of Network and Data Security Technology Tianjin China College of Computer Science Nankai University Tianjin China Key Laboratory of Blockchain and Cyberspace Governance of Zhejiang Province Hangzhou China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783031281235

Effective vulnerability detection of large-scale smart contracts is critical because smart contract attacks frequently bring about tremendous economic loss. However, code analysis requiring traversal paths and learning methods requiring many features training is too time-consuming to detect large-scale on-chain contracts. This paper focuses on improving detection efficiency by reducing the dimension of the features, combined with expert knowledge. We propose a feature extraction method Block-gram to form low-dimensional knowledgeable features from the bytecode. We first separate the metadata and convert the runtime code to opcode sequence, dividing the opcode sequence into segments according to some instructions (jump, etc.). Then, we mine extensible Block-gram features for learning-based model training, consisting of 4-dimensional block features and 8-dimensional attribute features. We evaluate these knowledge-based features using seven state-of-the-art learning algorithms to show that the average detection latency speeds up 25 to 650 times, compared with the features extracted by N-gram. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Smart contract

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：