Cerebras Architecture Deep Dive: First Look Inside the Hardware/Software Co-Design for Deep Learning-Reference-Cited by-同舟云学术

Cerebras Architecture Deep Dive: First Look Inside the Hardware/Software Co-Design for Deep Learning

Author:

Lie Sean¹^ORCID

Affiliation:

1. Cerebras Systems, Sunnyvale, CA, USA

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Electrical and Electronic Engineering,Hardware and Architecture,Software

Link

Reference13 articles.

1. Using DeepSpeed and Megatron to train Megatron-Turing NLG 530B, a large-scale generative language model;smith,2022

2. PanGu-?: Large-scale autoregressive pretrained Chinese language models with auto-parallel computation;zeng,2021

4. Language models are few-shot learners;brown,2020

Cited by 8 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. Near-Optimal Wafer-Scale Reduce;Proceedings of the 33rd International Symposium on High-Performance Parallel and Distributed Computing;2024-06-03

3. Language Modeling on a SpiNNaker2 Neuromorphic Chip;2024 IEEE 6th International Conference on AI Circuits and Systems (AICAS);2024-04-22

4. The CMOS 2.0 revolution;Nature Reviews Electrical Engineering;2024-01-16

5. Interconnect Fabrics for Multi-Core Quantum Processors;Proceedings of the 16th International Workshop on Network on Chip Architectures;2023-10-28