R2D2: Removing ReDunDancy Utilizing Linearity of Address Generation in GPUs-Reference-Cited by-同舟云学术

R2D2: Removing ReDunDancy Utilizing Linearity of Address Generation in GPUs

Published:2023-06-17 Issue: Volume: Page:
ISSN:
Container-title:Proceedings of the 50th Annual International Symposium on Computer Architecture
language:
Short-container-title:

Author:

Ha Dongho¹^ORCID,Oh Yunho²^ORCID,Ro Won Woo¹^ORCID

Affiliation:

1. Yonsei University, Seoul, Republic of Korea

2. Korea University, Seoul, Republic of Korea

Publisher

ACM

Reference54 articles.

1. General-Purpose Graphics Processor Architectures

2. Convergence and scalarization for data-parallel architectures

3. Analyzing CUDA workloads using a detailed GPU simulator

4. Saisanthosh Balakrishnan and Gurindar S. Sohi . 2003. Exploiting Value Locality in Physical Register Files . In Proceedings of the 36th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO 36) . IEEE Computer Society, USA, 265. Saisanthosh Balakrishnan and Gurindar S. Sohi. 2003. Exploiting Value Locality in Physical Register Files. In Proceedings of the 36th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO 36). IEEE Computer Society, USA, 265.

5. Dynamic dead-instruction detection and elimination

Cited by 3 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. VitBit: Enhancing Embedded GPU Performance for AI Workloads through Register Operand Packing;Proceedings of the 53rd International Conference on Parallel Processing;2024-08-12

2. Photon: A Fine-grained Sampled Simulation Methodology for GPU Workloads;56th Annual IEEE/ACM International Symposium on Microarchitecture;2023-10-28

3. MAD MAcce: Supporting Multiply-Add Operations for Democratizing Matrix-Multiplication Accelerators;56th Annual IEEE/ACM International Symposium on Microarchitecture;2023-10-28