5 ExaFlop/s HPL-MxP Benchmark with Linear Scalability on the 40-Million-Core Sunway Supercomputer-Reference-Cited by-同舟云学术

5 ExaFlop/s HPL-MxP Benchmark with Linear Scalability on the 40-Million-Core Sunway Supercomputer

Published:2023-11-11 Issue: Volume: Page:
ISSN:
Container-title:Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis
language:
Short-container-title:

Author:

Lin Rongfen¹^ORCID,Yuan Xinhui¹^ORCID,Xue Wei²³^ORCID,Yin Wanwang¹^ORCID,Yao Jienan²^ORCID,Shi Junda¹^ORCID,Sun Qiang¹^ORCID,Song Chaobo¹^ORCID,Wang Fei²^ORCID

Affiliation:

1. National Research Center of Parallel Computer Engineering & Technology, Beijing, China

2. Tsinghua University, Beijing, China

3. Qinghai University, Xining, Qinghai, China

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3581784.3607030

Reference36 articles.

1. A parallel implementation of matrix multiplication and LU factorization on the IBM 3090;Agarwal Ramesh C;Proceedings of the IFIP WG,1988

2. LU factorization for accelerator-based systems

3. AMD. 2022. AMD cdna2 white-paper. https://www.amd.com/system/files/documents/amd-cdna2-white-paper.pdf AMD. 2022. AMD cdna2 white-paper. https://www.amd.com/system/files/documents/amd-cdna2-white-paper.pdf

4. Optimized HPL for AMD GPU and multi-core CPU usage

5. Sebastien Bubeck , Varun Chandrasekaran , Ronen Eldan , Johannes Gehrke , Eric Horvitz , Ece Kamar , Peter Lee , Yin Tat Lee , Yuanzhi Li, Scott Lundberg, Harsha Nori, Hamid Palangi, Marco Tulio Ribeiro, and Yi Zhang. 2023 . Sparks of Artificial General Intelligence: Early experiments with GPT- 4. arXiv:2303.12712v2 Sebastien Bubeck, Varun Chandrasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin Tat Lee, Yuanzhi Li, Scott Lundberg, Harsha Nori, Hamid Palangi, Marco Tulio Ribeiro, and Yi Zhang. 2023. Sparks of Artificial General Intelligence: Early experiments with GPT-4. arXiv:2303.12712v2