A survey of compute nodes with 100 TFLOPS and beyond for supercomputers
J Chang, K Lu, Y Guo, Y Wang, Z Zhao… - CCF Transactions on …, 2024 - Springer
With the Frontier supercomputer ranked first on the Top500 list, it marks the era of exascale
computing power for supercomputers, employing the compute nodes with double-precision …
computing power for supercomputers, employing the compute nodes with double-precision …
[PDF][PDF] In-depth survey of processing-in-memory architectures for deep neural networks
Processing-in-Memory (PIM) is an emerging computing architecture that has gained
significant attention in recent times. It aims to maximize data movement efficiency by moving …
significant attention in recent times. It aims to maximize data movement efficiency by moving …
An Architecture-Level Framework for Enabling Processing-Using-Memory Simulations in Deep Neural Networks
The emulation or layout in the study of processing-in-memory (PIM) is a highly time-
consuming process. Especially, the processing-using-memory (PUM), a subset of PIM, is …
consuming process. Especially, the processing-using-memory (PUM), a subset of PIM, is …
A Spatio-Temporal Switchable Data Prefetcher for Convolutional Neural Networks
In this paper, we propose a spatio-temporal switchable data prefetcher that can adapt to the
locality characteristics of CNN models. The proposed prefetcher records the recent delta …
locality characteristics of CNN models. The proposed prefetcher records the recent delta …