检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Lin, Rui Li, Jason Chun Lok Zhou, Jiajun Huang, Binxiao Ran, Jie Wong, Ngai Distributed and Parallel Software Lab Huawei China Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong

Most deep neural networks (DNNs) consist fundamentally of convolutional and/or fully connected layers, wherein the linear transform can be cast as the product between a filter matrix and a data matrix obtained by arranging feature tensors into columns. The lately proposed deformable butterfly (DeBut) decomposes the filter matrix into generalized, butterfly-like factors, thus achieving network compression orthogonal to the traditional ways of pruning or low-rank decomposition. This work reveals an intimate link between DeBut and a systematic hierarchy of depthwise and pointwise convolutions, which explains the empirically good performance of DeBut layers. By developing an automated DeBut chain generator, we show for the first time the viability of homogenizing a DNN into all DeBut layers, thus achieving an extreme sparsity and compression. Various examples and hardware benchmarks verify the advantages of All-DeBut networks. In particular, we show it is possible to compress a PointNet to Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Flora: Dual-Frequency LOss-Compensated ReAl-Time Monocular 3D Video Reconstruction 37

Flora: Dual-Frequency LOss-Compensated ReAl-Time Monocular 3...

引用

37th AAAI Conference on Artificial Intelligence (AAAI) / 35th Conference on Innovative Applications of Artificial Intelligence / 13th Symposium on Educational Advances in Artificial Intelligence

作者： Wang, Likang Gong, Yue Wang, Qirui Zhou, Kaixuan Chen, Lei Hong Kong Univ Sci & Technol Dept Comp Sci & Engn Hong Kong Peoples R China Hong Kong Univ Sci & Technol Data Sci & Analyt Thrust Guangzhou Peoples R China Huawei Technol Distributed & Parallel Software Lab Shenzhen Peoples R China Huawei Technol Riemann Lab Shenzhen Peoples R China Huawei Technol Fundamental Software Innovat Lab Shenzhen Peoples R China

ISBN: (纸本)9781577358800

In this work, we propose a real-time monocular 3D video reconstruction approach named Flora for reconstructing delicate and complete 3D scenes from RGB video sequences in an end-to-end manner. Specifically, we introduce a novel method with two main contributions. Firstly, the proposed feature aggregation module retains both color and reliability in a dual-frequency form. Secondly, the loss compensation module solves missing structure by correcting losses for falsely pruned voxels. The dual-frequency feature aggregation module enhances reconstruction quality in both precision and recall, and the loss compensation module benefits the recall. Notably, both proposed contributions achieve great results with negligible inferencing overhead. Our state-of-the-art experimental results on real-world datasets demonstrate Flora's leading performance in both effectiveness and efficiency. The code is available at https://***/NoOneUST/Flora.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Research on application of heterogeneous resonance Integral for double heterogeneous system

引用

ANNALS OF NUCLEAR ENERGY 2025年 212卷

作者： Qin, Shuai Zhang, Qian Wang, Kai Huang, Dong Li, Song Liang, Yuechao Zhejiang Univ Zhejiang Inst Modern Phys Sch Phys Lab Adv Nucl Energy Theory & Applicat Hangzhou 310027 Zhejiang Peoples R China Xi An Jiao Tong Univ Sch Elect Engn 28 Xianning West Rd Xian 710049 Shaanxi Peoples R China Naval Univ Engn Coll Nucl Sci & Technol Wuhan Peoples R China Natl Univ Def Technol Lab Digitizing Software Frontier Equipment Changsha 410073 Hunan Peoples R China Natl Univ Def Technol Key Lab Parallel & Distributed Comp Changsha 410073 Hunan Peoples R China

The Double Heterogeneous (DH) system, where fuel particles are randomly dispersed in the non-fissile matrix, is challenging for the reactor physics calculation. The Sanchez-Pomraning method accurately handles the DH system, but integrating it into existing reactor physics code requires code development. This study adopts the Sanchez-Pomraning coupled Ultra-Fine-Group (SP-UFG) slowing-down calculation to generate the heterogeneous Resonance Integral (RI) for DH system treatment with simple volume homogenization. Fully Ceramic Microencapsulated (FCM) fuel pin-cells and plates with varying configurations are calculated for verification. Effective cross-sections (XSs) and keff calculated by the heterogeneous RI are compared with SP-UFG results. Results show that the maximum bias of XSs and keff caused by the XS biases are less than 5% and 200 pcm, respectively. The maximum bias of keff when compared with Monte Carlo calculated results is -213 pcm, demonstrating that only considering the DH effect in the resonance energy region is acceptable.

关键词： Double heterogeneous Heterogeneous resonance integral Sanchez-Pomraning method Ultra-fine-group Subgroup parameter

来源：评论

学校读者我要写书评

暂无评论

Optimizing All-to-All Collective Communication on Tianhe Supercomputer 20

Optimizing All-to-All Collective Communication on Tianhe Sup...

引用

20th IEEE Int Symposium on parallel and distributed Processing with Applicat / 15th IEEE Int Conf on Social Comp and Networking / 12th IEEE Int Conf on Big Data and Cloud Comp / 12th IEEE Int Conf on Sustainable Comp and Commun

作者： Peng, Jintao Liu, Jie Dai, Yi Xie, Min Gong, Chunye Natl Univ Def Technol Changsha Peoples R China NUDT Sci & Technol Parallel & Distributed Proc Lab Changsha 410073 Peoples R China NUDT Changsha & Lab Software Engn Complex Syst Changsha 410073 Peoples R China

ISBN: (纸本)9781665464970

All-to-all communication has a wide range of applications in parallel applications like FFT. On most supercomputers, there are multiple cores in a node. Message aggregation is an efficient method for smaller messages. Using multi-leader to aggregate message show significant improvement in intranode overhead. However, compared to one-leader aggregation, existing multi-leader design incurs more message count and less aggregated message size. This paper proposes an Overlapped Multi-worker Multi-port all-to-all (OVALL) to scale the message size and parallelism of the aggregation algorithm. The algorithm exploits the all-to-all multi-core parallelism, concurrent communication, and overlapping capabilities. Experiment results show that, compared to systems built-in MPI, OVALL'implementation achieves up to 5.9x or 18x speedup compared to MPI on different HPC systems. For the Fast Fourier Transform (FFT) application, OVALL is up to 2.7x (8192 cores, system A) or 5.6x (4800 cores, system B) faster compared to built-in MPI on peak performance.

关键词： All to all Message Aggratation MPI Multi core Concurrency

来源：评论

学校读者我要写书评

暂无评论

sNPU: Trusted Execution Environments on Integrated NPUs 51

sNPU: Trusted Execution Environments on Integrated NPUs

引用

ACM/IEEE 51st Annual International Symposium on Computer Architecture (ISCA)

作者： Feng, Erhu Feng, Dahu Du, Dong Xia, Yubin Chen, Haibo Shanghai Jiao Tong Univ Inst Parallel & Distributed Syst SEIEE Shanghai Peoples R China Tsinghua Univ Dept Precis Instrument Beijing Peoples R China Minist Educ Engn Res Ctr Domain Specif Operating Syst Beijing Peoples R China Chinese Acad Sci Key Lab Syst Software Beijing Peoples R China

ISBN: (纸本)9798350326598;9798350326581

Trusted execution environment (TEE) promises strong security guarantee with hardware extensions for security-sensitive tasks. Due to its numerous benefits, TEE has gained widespread adoption, and extended from CPU-only TEEs to FPGA and GPU TEE systems. However, existing TEE systems exhibit inadequate and inefficient support for an emerging (and significant) processing unit, NPU. For instance, commercial TEE systems resort to coarse-grained and static protection approaches for NPUs, resulting in notable performance degradation (10%-20%), limited (or no) multitasking capabilities, and suboptimal resource utilization. In this paper, we present a secure NPU architecture, known as sNPU, which aims to mitigate vulnerabilities inherent to the design of NPU architectures. First, sNPU proposes NPU Guarder to enhance the NPU's access control. Second, sNPU defines new attack surfaces leveraging in-NPU structures like scratchpad and NoC, and designs NPU Isolator to guarantee the isolation of scratchpad and NoC routing. Third, our system introduces a trusted software module called NPU Monitor to minimize the software TCB. Our prototype, evaluated on FPGA, demonstrates that sNPU significantly mitigates the runtime costs associated with security checking (from upto 20% to 0%) while incurring less than 1% resource costs.

关键词： Accelerator Machine learning Security

来源：评论

学校读者我要写书评

暂无评论

TFS: Revisiting Temporal Language Grounding from Frequency Spiking Perspective

TFS: Revisiting Temporal Language Grounding from Frequency S...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yifan Lyu Hongzhou Wu Lixiang Liu Chuxiong Sun Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China Parallel and Distributed Processing Lab National University of Defense Technology Changsha China Institute of Software Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Temporal Language Grounding (TLG) aims to localize moments in untrimmed videos that are most relevant to natural language queries. While existing weakly-supervised methods have achieved significant success in exploring cross-modal relationships, they still face a critical bottleneck: the interference of task-irrelevant information in query embeddings. To address this issue, we propose TLG Frequency Spiking (TFS), a dimensional mask derived from the frequency domain that models the varying importance specific to different queries. By enhancing the understanding of queries, TFS effectively optimizes the cross-modal alignment of visual and textual modalities. Experimental results show that TFS significantly outperforms state-of-the-art baselines on both the Charades-STA and ActivityNet-Captions datasets.

关键词： Visualization Grounding Frequency-domain analysis Neural networks Natural languages Interference Signal processing Speech processing Faces Videos

来源：评论

学校读者我要写书评

暂无评论

Enhancing Code Representation Learning for Code Search with Abstract Code Semantics

Enhancing Code Representation Learning for Code Search with ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Shaojie Zhang Yiwei Ding Enrui Hu Yue Yu Yu Zhang Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Peng Cheng Laboratory Shenzhen China Distributed and Parallel Software Lab Huawei Shenzhen China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Code representation learning is an important way to encode the semantics of source code through pre-training. The learned representation supports a variety of downstream tasks, such as natural language code search and code defect detection. Inspired by pre-trained models for natural language representation learning, existing approaches often treat the source code or its structural information (e.g., Abstract Syntax Tree or AST) as a plain token sequence. Unlike natural language, programming language has its unique code unit information (e.g., identifiers and expressions) and logic information (e.g., the functionality of a code snippet). To further explore those properties, we propose Abstract Code Embedding (AbCE), a self-supervised learning method that considers the abstract semantics of code logic. Instead of scattered tokens, AbCE treats an entire node or a subtree in an AST as a basic code unit during pre-training, which preserves the entirety of a coding unit. Moreover, AbCE learns the abstract semantics of AST nodes via a self-distillation way. Experimental results show that it achieves significant improvements over state-of-the-art baselines on code search tasks and comparable performance on code clone detection and defect detection tasks even without using contrastive learning or curriculum learning.

关键词： Representation learning Codes Source coding Semantics Natural languages Cloning Syntactics

来源：评论

学校读者我要写书评

暂无评论

Fast and Scalable In-network Lock Management Using Lock Fission 18

Fast and Scalable In-network Lock Management Using Lock Fiss...

引用

18th USENIX Symposium on Operating Systems Design and Implementation (OSDI)

作者： Zhang, Hanze Cheng, Ke Chen, Rong Chen, Haibo Shanghai Jiao Tong Univ Inst Parallel & Distributed Syst SEIEE Shanghai Peoples R China Shanghai AI Lab Shanghai Peoples R China Minist Educ Engn Res Ctr Domain Specif Operating Syst Beijing Peoples R China Shanghai Jiao Tong Univ AI Inst MoE Key Lab Artificial Intelligence Shanghai Peoples R China Chinese Acad Sci Key Lab Syst Software Beijing Peoples R China

ISBN: (纸本)9781939133403

distributed lock services are extensively utilized in distributed systems to serialize concurrent accesses to shared resources. The need for fast and scalable lock services has become more pronounced with decreasing task execution times and expanding dataset scales. However, traditional lock managers, reliant on server CPUs to handle lock requests, experience significant queuing delays in lock grant latency. Advanced network hardware (e.g. programmable switches) presents an avenue to manage locks without queuing delays due to their high packet processing power. Nevertheless, their constrained memory capacity restricts the manageable lock scale, thereby limiting their effect in large-scale workloads. This paper presents FISSLOCK, a fast and scalable distributed lock service that exploits the programmable switch to improve (tail) latency and peak throughput for millions of locks. The key idea behind FISSLOCK is the concept of lock fission, which decouples lock management into grant decision and participant maintenance. FISSLOCK leverages the programmable switch to decide lock grants synchronously and relies on servers to maintain participants (i.e., holders and waiters) asynchronously. By using the programmable switch for routing, FISSLOCK enables on-demand fine-grained lock migration, thereby reducing the lock grant and release delays. FISSLOCK carefully designs and implements grant decision procedure on the programmable switch, supporting over one million locks. Evaluation using various benchmarks and a real-world application shows the efficiency of FISSLOCK. Compared to the state-of-the-art switch-based approach (NetLock), FISSLOCK cuts up to 79.1% (from 43.0%) of median lock grant time in the microbenchmark and improves transaction throughput for TATP and TPC-C by 1.76x and 2.28x, respectively.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

NEDORT: a novel and efficient approach to the data overlap problem in relational triples

引用

COMPLEX & INTELLIGENT SYSTEMS 2023年第5期9卷 5235-5250页

作者： Zhang, Zhanjun Hu, Xiaoru Zhang, Haoyu Liu, Jie Natl Univ Def Technol Coll Comp Changsha Peoples R China Cent South Univ Xiangya Hosp 2 Dept Nephrol Hunan Key Lab Kidney Dis & Blood Purificat Changsha Peoples R China Def Innovat Inst Beijing Peoples R China Natl Univ Def Technol Sci & Technol Parallel & Distributed Proc Lab Changsha Peoples R China Natl Univ Def Technol Lab Software Engn Complex Syst Changsha Peoples R China

Relation triple extraction is a combination of named entity recognition and relation prediction. Early works ignore the problem of data overlap when extracting triples, resulting in poor extraction performance. Subsequent works improve the capability of the model to extract overlapping triples through generative and extractive methods. These works achieve considerable performance but still suffer from some defects, such as poor extraction capability for individual triplets and inappropriate spatial distribution of the data. To solve the above problems, we perform sequence-to-matrix transformation and propose the NEDORT model. NEDORT predicts all subjects in the sentence and then completes the extraction of relation-object pairs. There are overlapping parts between relation-object pairs, so we conduct the conversion of sequence to matrix. We design the Differential Amplified Multi-head Attention method to extract subjects. This method highlights the locations of entities and captures sequence features from multiple dimensions. When performing the extraction of relation-object pairs, we fuse subject and sequence information through the Biaffine method and generate relation-sequence matrices. In addition, we design a multi-layer U-Net network to optimize the matrix representation and improve the extraction performance of the model. Experimental results on two public datasets show that our model outperforms other baseline models on triples of all categories

关键词： Relation triple extraction Overlapping data Differential amplified Multi-head attention Biaffine U-Net network

来源：评论

学校读者我要写书评

暂无评论

Open source oriented cross-platform survey

引用

INFORMATION AND software TECHNOLOGY 2025年 182卷

作者： Yao, Simeng Zhang, Xunhui Zhang, Yang Wang, Tao Natl Univ Def Technol Coll Comp Sci & Technol Changsha 410073 Peoples R China State Key Lab Complex & Crit Software Environm Changsha 410073 Peoples R China Natl Key Lab Parallel & Distributed Comp Changsha 410073 Peoples R China

Context: Open-source software development has become a widely adopted approach to software creation. However, developers' activities extend beyond social coding platforms (e.g., GitHub), encompassing social Q&A platforms (e.g., StackOverflow) and social media platforms (e.g., Twitter). Therefore, cross-platform research is essential for a deeper understanding of the nature of software development activities. Objective: This paper focuses on open-source platforms and systematically summarizes relevant cross-platform research. It aims to assess the current state of cross-platform research and provide insights into the challenges and future developments in this field. Method: This paper reviews 69 cross-platform research papers related to open-source software from 2013 to 2024, with a focus on several key areas, including platform interconnections, research themes, experimental design methods, challenges and research opportunities. Results: Through the analysis of 69 papers, we found that cross-platform research primarily involves platforms such as social coding, social Q&A, and social media. Researchers typically rely on information traces, including user personal info, technical info, project/post/bug report metadata, interaction info, to facilitate connections between platforms. Cross-platform research in the open-source domain mainly focuses on problem classification and feature extraction. The predominant research methods include data-driven approaches, qualitative studies, modeling and machine learning, and tool development and implementation. Despite these advancements, common challenges remain, such as subjective evaluation bias in manual data classification, insufficient data source coverage, and inaccurate data recognition. Future research opportunities may focus on increasing the diversity of data sources, improving data recognition accuracy, optimizing data classification methods, and clarifying user skill requirements. Conclusions: Based on our findings, w

关键词： Open source Cross-platform Systematic literature review GitHub StackOverflow Twitter

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：