Saved in:
Bibliographic Details
Main Authors: Li, Tangrui, Shi, Justin Y., Spatola, Matteo, Wang, Hongzheng
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.08381
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912702224400384
author Li, Tangrui
Shi, Justin Y.
Spatola, Matteo
Wang, Hongzheng
author_facet Li, Tangrui
Shi, Justin Y.
Spatola, Matteo
Wang, Hongzheng
contents This paper reports three computational experiments for a von Neumann inspired reconfigurable fault tolerant multiprocessor for neural network (NN) training workflows. The experiments are intended to prove the feasibility of the proposed reconfigurable multiprocessor architecture for non-regular workflows on robustness of adaptability. A potential integration with MLIR compilers is also discussed for integrating diverse accelerator hardware for existing practical applications.
format Preprint
id arxiv_https___arxiv_org_abs_2511_08381
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Fault Tolerant Reconfigurable ML Multiprocessor
Li, Tangrui
Shi, Justin Y.
Spatola, Matteo
Wang, Hongzheng
Networking and Internet Architecture
This paper reports three computational experiments for a von Neumann inspired reconfigurable fault tolerant multiprocessor for neural network (NN) training workflows. The experiments are intended to prove the feasibility of the proposed reconfigurable multiprocessor architecture for non-regular workflows on robustness of adaptability. A potential integration with MLIR compilers is also discussed for integrating diverse accelerator hardware for existing practical applications.
title Fault Tolerant Reconfigurable ML Multiprocessor
topic Networking and Internet Architecture
url https://arxiv.org/abs/2511.08381