Efficient Algorithms for Stream Compaction on GPUs

Author:

Bakunas-Milanowski Darius1,Rego Vernon2,Sang Janche3,Chansu Yu3

Affiliation:

1. IBM Corporation

2. Purdue University

3. Cleveland State University

Publisher

IJNC Editorial Committee

Reference15 articles.

1. [1] A. V. Adinetz. CUDA Pro Tip: Optimized Filtering With Warp-Aggregated Atomics, PARALLEL FORALL. http://devblogs.nvidia.com/parallelforall/ cuda-pro-tip-optimized-filtering-warp-aggregated-atomics/, 2015.

2. [2] M. Billeter, O. Olsson, and U. Assarsson. Ecient Stream Compaction on Wide SIMD Many- Core Architectures. In Proceedings of the Conference on High Performance Graphics, 2009.

3. [3] G. Diamos, H.Wu, A. Lele, J.Wang, and S. Yalamanchili. Ecient relational algebra algorithms and data structures for GPU. Technical report, Technical Report GIT-CERCS-12-01, CERCS, Georgia Institute of Technology, 2012.

4. [4] K. Garanzha, S. Premoze, A. Bely, and V. Galaktionov. Grid-based SAH BVH construction on a GPU. The Visual Computer, 27(6-8):697{706, 2011.

5. [5] M. Harris and M. Garland. Optimizing Parallel Prex Operations for the Fermi Architecture. Chapter 3 of the book GPU Computing Gems - Jade Edition, Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, 2011.

Cited by 5 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Redzone stream compaction: removing k items from a list in parallel O(k) time;ACM Transactions on Parallel Computing;2024-08-27

2. Accelerating k-Core Decomposition by a GPU;2023 IEEE 39th International Conference on Data Engineering (ICDE);2023-04

3. Accelerating Parallel Operation for Compacting Selected Elements on GPUs;Journal of Open Source Software;2022-07-22

4. Post-training Piecewise Linear Quantization for Deep Neural Networks;Computer Vision – ECCV 2020;2020

5. Value-Aware Quantization for Training and Inference of Neural Networks;Computer Vision – ECCV 2018;2018

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3