检索结果-内蒙古大学图书馆

Radiance Caching with On-Surface Caches for Real-Time Global Illumination

PROCEEDINGS OF THE ACM ON COMPUTER GRAPHICS AND INTERACTIVE TECHNIQUES 2024年第3期7卷 1-17页

作者： Tatzgern, Wolfgang Weinrauch, Alexander Stadlbauer, Pascal Mueller, Joerg H. Winter, Martin Steinberger, Markus Graz Univ Technol Graz Austria Huawei Technol Graz Austria

Achieving global illumination is crucial for delivering realistic lighting in real-time rendering applications. Despite recent advancements in hardware ray tracing, the computational demands of full path tracing remain largely impractical for real-world production scenarios. We introduce a novel two-level radiance caching system that exclusively utilizes on-surface caches, diverging from conventional approaches that combine screen-space and world-space caches. Unlike previous texture space techniques, which mostly prioritize closely matching the resolution to screen space to minimize artifacts, our focus is on achieving optimal visual quality with minimal texture space resolutions. By caching directional radiance information on both primary and secondary hits, our approach delivers high-quality renderings of global illumination while being computationally efficient. Overall, this leads to an up to 5% to 10% improvement in both speed and quality compared to other state-of-the-art approaches. Our proposed method is versatile, handling not only diffuse global illumination but also addressing (glossy) reflections. Furthermore, our approach is well-suited for multi-viewer rendering, as the utilization of on-surface caches enables information sharing among different viewers, making it applicable to cloud-native rendering environments.

关键词： Computing methodologies -> Ray tracing Rendering parallel algorithms Dis- tributed algorithms.

来源：评论

学校读者我要写书评

暂无评论

parallel Minimum Spanning Tree algorithms via Lattice Linear Predicate Detection

Parallel Minimum Spanning Tree Algorithms via Lattice Linear...

引用

IEEE International Symposium on parallel and Distributed Processing Workshops and Phd Forum (IPDPSW)

作者： David R. Alves Vijay K. Garg Department of Electrical and Computer Engineering The University of Texas at Austin Austin TX USA

ISBN: (数字)9781665497473

ISBN: (纸本)9781665497480

We show that the problem of computing the minimum spanning tree can be formulated as special case of detecting Lattice Linear Predicate (LLP). In general, formulating problems as LLP presents two main advantages: 1) Different problems are formulated under a single, general framework, which defines the problem in terms of simple local predicates that must hold for the all the elements of a lattice, making the problem (and the solution) compact and easy to understand. 2) improvements on one set of problems can be transferable to other sets of problems; 3 $\bigcirc\!\!\!\!\!{6}$ since the problems are stated as a set of local predicates, which can be often tested with little or no synchronization it is often the case that new opportunities for parallelism present themselves. In this paper we introduce two parallel algorithms LLP-Prim and LLP-Boruvka that improve on the non-LLP counterparts in several ways. LLP-Prim reduces the number of heap operations required by Prim by allowing edges to be selected without entering the heap thus allowing for parallelism. LLP-Boruvka improves on Boruvka by reducing synchronization and thus once more improving parallelism opportunities. Our experimental evaluation shows that LLP-Prim is faster than Prim's algorithm in both single threaded and multithreaded scenarios and that it provides a good tradeoff between parallelism and efficiency at low core counts. For higher core count scenarios we show how LLP-Boruvka improves on an efficient implementation of a parallel version of Boruvka.

关键词： Distributed processing Instruction sets Conferences Lattices Synchronization parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

Risk Prediction and Treatment in Enterprise Management Based on Ant Colony parallel Algorithm

Lecture Notes on Data Engineering and Communications Technol...

引用

Lecture Notes on Data Engineering and Communications Technologies 2022年 129卷 99-106页

作者： Shi, Kaixin TOJOY Wisdom Enterprise Service Co. Ltd. Shanghai China

As the global economy continues to grow, the business scope of enterprises is further expanded, the environment will become more complex, the risks they face will increase, and the uncertainty will gradually increase. If an enterprise fails to manage risks properly, it will not only affect the normal operation of the enterprise, but may even lead to bankruptcy. This paper aims to study the risk prediction and processing in enterprise management based on the ant colony parallel algorithm. Based on the analysis of the current situation of risk prediction research at home and abroad, combined with the function of risk prediction and the principle of risk prediction index selection, a risk prediction system is established and reused. The parallel and distributed characteristics of ant colony algorithm establish a risk prediction model to predict enterprise management risks. The prediction results show that the relative error value of all samples is controlled below 3%, and the minimum error value is only 0.86%. Therefore, the ant parallel algorithm model can meet the accuracy requirements of enterprise management risk prediction. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

Saliency detection for large-scale mesh decimation

引用

COMPUTERS & GRAPHICS-UK 2023年 111卷 63-76页

作者： dos Anjos, Rafael Kuffner Roberts, Richard Andrew Allen, Benjamin Jorge, Joaquim Anjyo, Ken Univ Leeds Leeds England Victoria Univ Wellington CMIC Wellington New Zealand IMAG Grp Tokyo Japan INESC ID Lisbon Portugal

Highly complex and dense models of 3D objects have recently become indispensable in digital industries. Mesh decimation then plays a crucial role in the production pipeline to efficiently get visually convincing yet compact expressions of complex meshes. However, the current pipeline typically does not allow artists control the decimation process, just a simplification rate. Thus a preferred approach in production settings splits the process into a first pass of saliency detection highlighting areas of greater detail, and allowing artists to iterate until satisfied before simplifying the model. We propose a novel, efficient multi-scale method to compute mesh saliency at coarse and finer scales, based on fast mesh entropy of local surface measurements. Unlike previous approaches, we ensure a robust and straightforward calculation of mesh saliency even for densely tessellated models with millions of polygons. Moreover, we introduce a new adaptive subsampling and interpolation algorithm for saliency estimation. Our implementation achieves speedups of up to three orders of magnitude over prior approaches. Experimental results showcase its resilience to problem scenarios that efficiently scales up to process multi-million vertex meshes. Our evaluation with artists in the entertainment industry also demonstrates its applicability to real use-case scenarios. (c) 2023 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY license (http://***/licenses/by/4.0/).

关键词： Geometric processing Mesh saliency Mesh decimation parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

Efficient deterministic MapReduce algorithms for parallelizable problems

引用

JOURNAL OF parallel AND DISTRIBUTED COMPUTING 2023年 177卷 28-38页

作者： Frei, Fabian Wada, Koichi Swiss Fed Inst Technol Dept Comp Sci Zurich Switzerland Hosei Univ Dept Appl Informat Chiyoda City Tokyo Japan

The MapReduce framework has firmly established itself as one of the most widely used parallel computing platforms for processing big data on tera-and peta-byte scale. Approaching it from a theoretical standpoint has proved to be notoriously difficult, however. In continuation of Goodrich et al.'s early efforts, explicitly espousing the goal of putting the MapReduce framework on footing equal to that of long-established models such as the PRAM, we investigate the obvious complexity question of how the computational power of MapReduce algorithms compares to that of combinational Boolean circuits commonly used for parallel computations. Relying on the standard MapReduce model introduced by Karloff et al. a decade ago, we develop an intricate simulation technique to show that any problem in NC (i.e., a problem solved by a logspace-uniform family of Boolean circuits of polynomial size and a depth polylogarithmic in the input size) can be solved by a MapReduce computation in O(T(n)/ log n) rounds, where n is the input size and T(n) is the depth of the witnessing circuit family. Thus, we are able to closely relate the standard, uniform NC hierarchy modeling parallel computations to the deterministic MapReduce hierarchy DM R C by proving that NCi+1 subset of DM R Ci for all i is an element of N. Besides the theoretical significance, this result has important applied aspects as well. In particular, we show for all problems in NC1-many practically relevant ones, such as integer multiplication and division, the parity function, and recognizing balanced strings of parentheses being among these-how to solve them in a constant number of deterministic MapReduce rounds.(c) 2023 The Author(s). Published by Elsevier Inc. This is an open access article under the CC BY license (http://creativecommons .org /licenses /by /4 .0/).

关键词： MapReduce Circuit complexity parallel algorithms Nick?s class Complexity theory

来源：评论

学校读者我要写书评

暂无评论

A Novel Compute-Efficient Tridiagonal Solver for Many-Core Architectures

引用

IEEE TRANSACTIONS ON parallel AND DISTRIBUTED SYSTEMS 2023年第1期34卷 195-206页

作者： Liu, Kan Xue, Wei Tsinghua Univ Dept Comp Sci & Technol Beijing 100084 Peoples R China

The tridiagonal solver is an important kernel and is widely supported in mainstream numerical libraries. While parallel algorithms have been studied for many-core architectures, the performance of current algorithms and implementations is still hindered by input size sensitivity and cross-platform portability. In this paper, we propose a novel algorithm WM-pGE for the batched solution of diagonally dominant tridiagonal systems. The algorithm balances the key design objectives, including computation complexity, memory complexity, parallelism, and input size sensitivity, better than existing algorithms. Moreover, an elegant formulation is presented to show the implementation and cross-platform optimization without loss of efficiency and generality, by extracting the platform-dependent works into only four vector operators. The results from our batched tridiagonal experiments show that the proposed algorithm outperforms the prior work PCR-pThomas by 25% and 12% on NVIDIA Tesla V100 in single and double precision, respectively. On Intel KNL, our method achieves a 10% improvement in performance over PCR-pThomas in double precision.

关键词： Computer architecture Layout Sensitivity parallel algorithms Heuristic algorithms Graphics processing units Computational complexity parallel numerical algorithm Tridiagonal solver batched Tridiagonal solver many-core architectures

来源：评论

学校读者我要写书评

暂无评论

A parallel Algorithm for Updating a Multi-objective Shortest Path in Large Dynamic Networks

A Parallel Algorithm for Updating a Multi-objective Shortest...

引用

2023 International Conference on High Performance Computing, Network, Storage, and Analysis, SC Workshops 2023

作者： Khanda, Arindam Shovan, S.M. Das, Sajal K. Missouri University of Science and Technology RollaMO United States

ISBN: (纸本)9798400707858

In dynamic networks, where continuous topological changes are prevalent, it becomes paramount to find and update different graph properties without the computational burden of recalculating from the ground up. However finding or updating a multi-objective shortest path (MOSP) in such a network is challenging, as it involves simultaneously optimizing multiple (conflicting) objectives. In light of this, our paper focuses on shortest path search and proposes parallel algorithms tailored specifically for large incremental graphs. We first present an efficient algorithm that updates the single-objective shortest path (SOSP) whenever a new set of edges are introduced. Leveraging this SOSP update algorithm, we also devise a novel heuristic approach to adaptively update a MOSP in large networks. Empirical evaluations on both real and synthetic incremental networks with shared memory implementations attest to the scalability and efficacy of the proposed algorithms. © 2023 ACM.

关键词： parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

Efficient Adaptive Monte Carlo Uncertainty Forecasting for High Dimensional Nonlinear Dynamic Systems

引用

IEEE ACCESS 2023年 11卷 12119-12138页

作者： Vanfossen, Andrew W. Kumar, Mrinal Ohio State Univ Dept Mech & Aerosp Engn Columbus OH 43210 USA

The problem of uncertainty forecasting for complex dynamical systems in the framework of particle methods can be effectively addressed through the solution methodology known as adaptive Monte Carlo (AMC). Monte Carlo (MC) methods involve discretizing the initial probability density function (pdf) followed by forward propagation of particles through system dynamics to obtain an approximate particle representation of the evolved state uncertainty. While simple to implement, MC faces questions surrounding transient statistical consistency and rate of convergence. AMC (adopted here) addresses these issues on-the-fly using defined bounds on estimation accuracy alongside ensemble enrichment routines. This paper presents several improvements in the ensemble enrichment module of AMC. The AMC platform is re-engineered to include the novel implementation of a parallel global stochastic optimization routine in conjunction with additional module enhancements that work together towards the goal of efficient forecasting. Moreover, the efficacy of algorithms utilized within every submodule of AMC are detailed and improved upon under the framework of arithmetic minimization and parallelization. Each submodule is profiled to determine computational bottlenecks, optimized or replaced with more efficient methods such as simulated annealing (SA), and parallelized ultimately leading to a clock time reduction of 200 - 400% for benchmark entry descent and landing, Lorenz-96, and Lotka-Volterra models.

关键词： Uncertainty Numerical models Forecasting Mathematical models Biological system modeling Monte Carlo methods Data models Simulated annealing Adaptive Monte Carlo arithmetic minimization parallel algorithms nonconvex optimization simulated annealing uncertainty quantification

来源：评论

学校读者我要写书评

暂无评论

ezLDA: Efficient and Scalable LDA on GPUs

引用

IEEE ACCESS 2023年 11卷 100165-100179页

作者： Wang, Shilong Liu, Hang Gaihre, Anil Yu, Hengyong Univ Massachusetts Lowell Dept Elect & Comp Engn Lowell MA 01854 USA Stevens Inst Technol Dept Elect & Comp Engn Hoboken NJ 07030 USA

Latent Dirichlet Allocation (LDA) is a statistical approach for topic modeling with a wide range of applications. Attracted by the exceptional computing and memory throughput capabilities, this work introduces ezLDA which achieves efficient and scalable LDA training on GPUs with the following three contributions: First, ezLDA introduces three-branch sampling method which takes advantage of the convergence heterogeneity of various tokens to reduce the redundant sampling task. Second, to enable sparsity-aware format for both D and W on GPUs with fast sampling and updating, we introduce hybrid format for W along with corresponding token partition to T and inverted index designs. Third, we design a hierarchical workload balancing solution to address the extremely skewed workload imbalance problem on GPU and scale ezLDA across multiple GPUs. Taken together, ezLDA achieves superior performance over the state-of-the-art attempts with lower memory consumption.

关键词： Bayes method GPU high performance computin latent dirichlet allocation LDA parallel algorithms parallel programming machine learning unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Exploring Scalable parallelization for Edit Distance-Based Motif Search

引用

IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2023年第2期20卷 1587-1593页

作者： Qiu, Junqiao Ebnenasir, Ali City Univ Hong Kong Dept Comp Sci Kowloon Tong Hong Kong Peoples R China Michigan Technol Univ Dept Comp Sci Houghton MI 49931 USA

Motif Searching is an important problem that can reveal crucial information from biological data. Since the general motif searching is NP-hard and the volume of biological data is growing exponentially in recent years, there is a pressing need for developing time and space-efficient algorithms to find motifs. In this paper, we explore scalable parallelization for Edit Distance-Based Motif Search (EMS). We introduce two parallel designs, recursEMS which integrates the existing EMS solver into a parallel recursion tree running in multiple processes, and parEMS that presents a novel thread-based method which avoids the storage of redundant motif candidates. To make the parallel designs practical, we implement SPEMS, a Scalability-sensitive parallel solver for EMS. For any given biological dataset and search instance, SPEMS can provide an EMS parallelization towards the optimal performance, or a sub-optimal performance but being more space efficient. Evaluations on two real-world DNA dataset TRANSFAC and ChIP-seq show that SPEMS can obtain 10x geometric mean speedup over the state-of-the-art at the expense of no less than 74.7% memory overheads, or provide 2.2x geometric mean speedup with the possibility of consuming less memory, when running on a 48-core machine.

关键词： Biology Proteins parallel algorithms DNA Costs Time complexity Search problems Edit-distance motif search parallelism

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：