检索结果-内蒙古大学图书馆

31st ieee international symposium on high performance computer architecture, HPCA 2025

作者： Liu, Zihan Luo, Xinhao Guo, Junxian Ni, Wentao Zhou, Yangjie Guan, Yue Guo, Cong Cui, Weihao Feng, Yu Guo, Minyi Zhu, Yuhao Zhang, Minjia Jin, Chen Leng, Jingwen Shanghai Jiao Tong University China Shanghai Qi Zhi Institute China Duke University United States National University of Singapore Singapore University of Rochester United States University of Illinois Urbana-Champaign United States Magik Compute

ISBN: (纸本)9798331506476

Vector quantization (VQ), which treats a vector as a compression unit, gains increasing research interests for its potential to accelerate large language models (LLMs). Compared to conventional element-wise quantization methods, VQ algorithms can compress weight and KV cache tensors in LLMs with a greater ratio while maintaining the high model accuracy. However, translating a VQ algorithm's memory reduction into the actual latency improvement is challenging. We profile and analyze the current approach of integrating VQ into computation kernels and show that its major inefficiency lies in the poor access efficiency of codebooks in VQ algorithms and uncoordinated computation dataflow. Meanwhile, the diversity of VQ algorithms (e.g., different vector sizes and entry counts) and LLMs, computation kernels (e.g matrix-matrix/vector multiplication and attention computation) makes it impractical to manually craft efficient kernel implementations for each specific case. In this work, we design and implement VQ-LLM, an efficient fused VQ kernel generation framework. We first introduce a software abstraction called codebook cache to optimize codebook access efficiency and support the integration of VQ with various computations. The codebook cache adaptively stores different entries across the GPU's memory hierarchy, including off-chip global memory, on-chip shared memory, and registers. Centered around the codebook cache, we design an efficient computation engine that optimizes memory traffic during computations involving codebooks. This compute engine adopts the codebook-centric dataflow and fusion optimizations. Additionally, we provide adaptive heuristics to tailor parameter selection in our optimizations to diverse VQ configurations. Our optimizations achieve the latency reduction of {6 4. 3 6%} to {9 9. 1%} compared to existing open-source implementations. A final comparison with state-of-the-art element-wise quantization methods like AWQ and QoQ shows that our VQ-LLM is

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

From Theory to Practice of Multidimensional Big Data Analytics over Big Healthcare Data: A Real-Life Case Study 28th

From Theory to Practice of Multidimensional Big Data Analyti...

引用

28th international symposium on Database Engineered Applications, IDEAS 2024

作者： Cuzzocrea, Alfredo Hafsaoui, Abderraouf Gallo, Carmine iDEA Lab University of Calabria Rende Italy Department of Computer Science University of Paris City Paris France

ISBN: (纸本)9783031834714

This paper provides practical and experimental results coming from the real-life research project that focuses on Big Data Analytics over Big Healthcare Data about chronical pain of patients in real-life hospitals and medical centers of North Italy (Region Lombardy), named as Pain-RELife. In this context, we devise innovative Multidimensional Big Data Analytics tools and a reference Cloud-based architecture that implements our analytics paradigm. Finally, we provide our analytical results based on advanced tools such as Multidimensional Clustering and Multidimensional Regression. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Advanced Big Data Systems Healthcare Data Science Multidimensional Big Data Analytics Tools

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning-Based Voting for Feature Drift-Aware Intrusion Detection: An Incremental Learning Framework

引用

ieee Access 2025年 13卷 37872-37903页

作者： Shyaa, Methaq A. Ibrahim, Noor Farizah Zainol, Zurinahni Binti Abdullah, Rosni Anbar, Mohammed School of Computer Sciences Penang11800 Malaysia Albukhary International University School of Computing and Informatics Alor Setar05200 Malaysia Penang11800 Malaysia

In Intrusion Detection Systems (IDS), stream data classification faces significant challenges due to concept drifts and feature evolution, where traditional methods struggle to maintain accuracy over time. One critical challenge is feature drift, which refers to changes in the relevance of features over time, directly impacting the model’s classification accuracy. This paper introduces the Incremental Feature Drift-Aware Genetic Programming Combiner (IFDA-GPC), which integrates a Voting Enhanced Deep Q-Network Multi-Agent Feature Selection (VE-DQN-MAFS) mechanism to address these challenges. The framework extends the existing IGPC architecture by incorporating dynamic feature selection and employing a multi-agent system with voting-based aggregation. This approach enhances feature selection decisions, especially in cases where agents provide conflicting assessments of feature relevance. By reconciling these variations, the framework ensures consistency and reliability in real-time classification tasks. The framework was evaluated using benchmark datasets, including KDD Cup ’99, CICIDS-2017, HIKARI-2021, and ISCX2012, under both evolving and non-evolving scenarios. Results demonstrate that GPC-KOS-DFS, derived from IFDA-GPC, significantly outperformed existing methods in accuracy, F1-score, recall, and AUC metrics. Notably, it achieved an accuracy of 93% on the CICIDS-2017 dataset, showcasing its effectiveness in handling feature drifts while maintaining high classification performance. These findings establish IFDA-GPC as a robust solution for managing evolving data streams in intrusion detection systems. © 2025 The Authors.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

HeterSim: Enable Flexible Simulation for Heterogeneous Distributed Deep Learning Platform

HeterSim: Enable Flexible Simulation for Heterogeneous Distr...

引用

2024 international Conference on Mechatronics and Intelligent Control, ICMIC 2024

作者： Tang, Yinan Zhang, Hongwei Wang, Li Guo, Zhenhua Zhao, Yaqian Li, Rengang IEIT SYSTEM Co. Ltd. Beijing China

ISBN: (数字)9781510686847

ISBN: (纸本)9781510686830

Distributed deep learning has become an essential technique for accelerating deep learning, but its performance is often influenced by the heterogeneous computing nodes and heterogeneous communication networks within the distributed deep learning platform. Due to the high costs of practical deployment and running of distributed deep learning, it is almost impossible for researchers to optimize the training strategy of distributed deep learning tasks in real-world environments. In this paper, we propose HeterSim, a simulator specifically designed for heterogeneous distributed deep learning platforms. HeterSim enables flexible configuration of computing node performance and network connections, and supports to define and simulate distributed deep learning workloads using graph-based representations. HeterSim also allows for the modification of communication strategies in the distributed deep learning process, thereby assisting researchers in validating their designs for distributed deep learning. We verify the feasibility and flexibility of HeterSim, by generating a simulation platform at the scale of millions of nodes, and successfully simulate the distributed deep learning process of Resnet50. We aim to provide HeterSim as a flexible and user-friendly simulator for researchers, targeting heterogeneous distributed deep learning platforms, and helping researchers evaluate and optimize the strategy of distributed deep learning tasks at a lower cost. © 2025 SPIE.

关键词： computer simulations Switches Deep learning Education and training Data modeling Modeling Computation time computer architecture Manufacturing Mathematical modeling

来源：评论

学校读者我要写书评

暂无评论

REMNA: Variation-Resilient and Energy-Efficient MLC FeFET computing-in-Memory Using NAND Flash-Like Read and Adaptive Control 24

REMNA: Variation-Resilient and Energy-Efficient MLC FeFET Co...

引用

43rd international Conference on computer-Aided Design, ICCAD 2024

作者： Li, Taixin Zhong, Hongtao Xu, Yixin Narayanan, Vijaykrishnan Ni, Kai Yang, Huazhong Kämpfe, Thomas Li, Xueqing Electronic Engineering LFET/BNRist Tsinghua University China The Pennsylvania State University United States University of Notre Dame United States Fraunhofer IPMS Germany

ISBN: (纸本)9798400710773

Nonvolatile memory (NVM)-based computing-in-memory (CiM) has shown promising prospects in deep neural network (DNN) inference at the edge thanks to its nonvolatility and high density. Moreover, most NVMs support multi-level cell (MLC) storage, which can further boost energy efficiency and storage density. However, MLC NVM-based CiMs suffer from degraded accuracy due to device nonidealities, including large variations, nonlinear current distribution, and state drifts. Although prior works have explored various mitigation measures, such as hybrid SLC/MLC, write-and-verify, and local recovery units, the substantial costs from software support, energy, latency, and area still limit the performance. Therefore, the tradeoff between inference accuracy, storage density and compute density has become a vital challenge in NVM-based CiMs. To break the inevitable tradeoff, this work proposes REMNA, a variation-resilient and energy-efficient CiM based on MLC ferroelectric field-effect transistors (FeFETs). For the first time, a NAND flash-like read scheme is introduced in MLC CiMs, enabling REMNA with reliable computing, efficient storage, and high scalability. To further enhance resilience against variations and drifts, an adaptive bias voltage control method is explored. Furthermore, an adaptive sparsity-aware input control is proposed to improve throughput and energy efficiency in the segmented REMNA architecture. Results show that REMNA achieves 1.39-18.12× storage density and 1.34-20.90× compute density with 26.72TOPS/W energy efficiency and © 2024 Copyright is held by the owner/author(s).

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Investigating the Automotive HPC Safety architecture for Software Defined Vehicle

Investigating the Automotive HPC Safety Architecture for Sof...

引用

Annual international symposium on Reliability Physics

作者： Jingu Park Jongil Jeong Byungju Kim Sehwan Park Myungmin Lee Donghwa Yun Namyong Park CTO Division / LG Electronics Seoul Republic of Korea VS Division / LG Electronics Seoul Republic of Korea

ISBN: (数字)9798331504779

ISBN: (纸本)9798331504786

This paper presents a robust safety architecture for high performance computing (HPC) in Software Defined Vehicle (SDV). In Zonal architecture, the centralized HPC plays a critical role in processing and controlling massive amounts of real-time data, demanding stringent safety measures. We rigorously validated LG's first HPC, incorporating designs that account for dependent failures, power and mechanical fault-tolerant systems, and failure detection techniques. Furthermore, this paper discusses future directions for enhancing safety in automotive HPC.

关键词： high performance computing Fault tolerant systems Process control computer architecture Software Real-time systems Safety Software reliability Physics Automotive engineering

来源：评论

学校读者我要写书评

暂无评论

Rethinking Dead Block Prediction for Intermittent computing

Rethinking Dead Block Prediction for Intermittent Computing

引用

ieee symposium on high-performance computer architecture

作者： Gan Fang Changhee Jung Department of Computer Science Purdue University

ISBN: (数字)9798331506476

ISBN: (纸本)9798331506483

Existing dead block predictors have proven to be effective in reducing cache leakage power of conventional systems. However, prior work is significantly less effective in energy harvesting systems in that it does not take into account their unique characteristic, i.e., frequent power failure during program execution. Even if some cache blocks are predicted to be live, they may not be used due to their loss upon power failure. In response, this paper introduces EDBP, an extension to existing dead block predictors, to enhance their performance in various energy harvesting environments. EDBP can identify and deactivate those cache blocks that are not reused before upcoming power failure-though they are considered live by the existing predictor-thereby lowering cache leakage and preserving more energy for forward execution progress. Experimental results show that for 20 applications from Mediabench and MiBench, EDBP alone reduces total energy consumption by 6.5% and improves performance by 6.9% compared to the baseline with no dead block predictor. When combined with a conventional dead block predictor (Cache Decay), EDBP achieves 9.8% reduction in total energy consumption—approaching the theoretical minimum—and 11.9% performance improvement.

关键词： Energy consumption computer architecture Energy efficiency Energy harvesting

来源：评论

学校读者我要写书评

暂无评论

Optimized Dense Neural Network architecture for Bone Marrow Cancer Classification Using Custom Callbacks

Optimized Dense Neural Network Architecture for Bone Marrow ...

引用

2025 international Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Deepa, G. Kalpana, Y. Department of Computer Science Chennai India Department of Computer Application and It Chennai India

ISBN: (纸本)9798331509828

Classification of bone marrow cancer is a crucial step in the analysis of several hematological cancers, such as multiple myeloma and leukemia. This study shows better dense neural network (DNN) architecture for significant the variation among the five main types of bone marrow cells includes lymphocytes, myelocytes, band neutrophils, and plasma cells. To find and diagnose bone marrow cancers like multiple myeloma, acute myeloid leukemia (AML), and acute lymphoblastic leukemia (ALL) early on, it is important to be able to accurately identify these cell types. The suggested DNN model uses unique callbacks to optimize training, avoid overfitting, and guarantee faster convergence. These callbacks include learning rate scheduling, early pausing, and dynamic weight modifications. The system preprocesses the high-resolution bone marrow image database to enhance contrast, adapt to fluctuations in illumination, and utilize dense layers for cell classification and convolutional layers for feature extraction. After extensive hyperparameter tuning, a model that classified these five categories of bone marrow cells obtained an overall accuracy rate of 95%. In terms of accuracy, recall, and F1 scores, the model performs better than conventional machine learning techniques while retaining computing economy. The model is able to increase training times without sacrificing classification performance by incorporating custom callbacks. With its enormous clinical application potential, our improved DNN architecture offers pathologists a dependable and effective tool for accurately classifying bone marrow cells. By improving bone marrow cancer diagnosis accuracy, this approach can improve patient care and treatment results. © 2025 ieee.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Architecting Space Microdatacenters: A System-level Approach

Architecting Space Microdatacenters: A System-level Approach

引用

ieee symposium on high-performance computer architecture

作者： Nathan Bleier Rick Eason Michael Lembeck Rakesh Kumar Department of Electrical Engineering & Computer Science University of Michigan Ann Arbor MI Department of Electrical and Computer Engineering University of Illinois Urbana IL Department of Aerospace Engineering University of Illinois Urbana IL

ISBN: (数字)9798331506476

ISBN: (纸本)9798331506483

Server-based computing in space has been recently proposed due to potential benefits in terms of capability, latency, security, sustainability, and cost. Despite this, there has been no work asking the question: how should we architect systems for server-based computing in space when considering overall cost. This paper presents a Total Cost of Ownership (TCO)-based approach to architecture of server-based computing systems for space (Space Microdatacenters - SμDC) for processing data produced by low Earth orbit (LEO)-based Earth observation (EO) satellites. We show that power of compute is the primary factor in determining SμDC TCO, though the dependence is sublinear. Second, the impact of compute mass, monetary cost, and communication on TCO is relatively insignificant. Third, architectures with the highest $\frac{\text { FLOPs }}{{\mathrm {W}}}$ provide much higher performance per TCO ${\$}$ even if they have poor $\frac{\mathrm{FLOPs}}{\$}$. We leverage these insights to advocate extreme heterogeneity designs for SμDCs. These designs reduce SμDC TCO by 116× in spite of poor $\frac{\mathrm{FLOPs}}{\$}$ characteristics. We also show that (a) collaborative compute constellations — constellations in which EO satellites are also equipped with compute hardware — further improve SμDC TCO by 1.31 to 1.74×, (b) a distributed architecture reduces TCO by 10% over a monolithic architecture, and (c) low monetary cost of compute can be leveraged to provide near zero cost compute overprovisioning which improves an SμDC’s availability significantly and supports graceful degradation. Overall, this is the first paper on cost-aware architecture and optimization of a SμDC.

关键词： Space vehicles Earth Costs Satellites Low earth orbit satellites computer architecture Hardware Security Sustainable development Optimization

来源：评论

学校读者我要写书评

暂无评论

Efficient Optimization with Encoded Ising Models

Efficient Optimization with Encoded Ising Models

引用

ieee symposium on high-performance computer architecture

作者： Devrath Iyer Sara Achour Stanford University

ISBN: (数字)9798331506476

ISBN: (纸本)9798331506483

Many promising computing substrates, including quantum computers, oscillator-based computers, and p computers solve constrained combinatorial optimization problems by minimizing energy functions called Ising models. Because Ising solvers explore an unconstrained search space, Ising models for many popular optimization problems must include penalty terms to raise the energy of infeasible solutions that would appear optimal otherwise. We observe that for some problems, Ising solvers spend the majority of computation time exploring this invalid state and often never find a feasible solution. We introduce the encoded Ising model (E-I model), an extension to the Ising model that uses a digital encoding circuit to vastly reduce the proportion of time a solver spends exploring invalid states. We present Fuse, a software framework that enables the description of such functions and automatically lowers them to a p-computer. Our formulation reduces the number of iterations to a solution by a factor of $7.2-52000 \mathrm{x}$ and achieves up to $\mathbf{1 0 0. 0 \%}$ higher estimated success probability over baseline formulations.

关键词： computers Quantum computing Computational modeling Search problems Encoding Software Logic Integrated circuit modeling Optimization Substrates

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：