Search Results for author:
Found 7 papers, 0 papers with code
Accelerating Neural Network Inference with Processing-in-DRAM: From the Edge to the Cloud
Our analysis reveals that PIM greatly benefits memory-bound NNs: (1) UPMEM provides 23x the performance of a high-end GPU when the GPU requires memory oversubscription for a general matrix-vector multiplication kernel; (2) Mensa improves energy efficiency and throughput by 3. 0x and 3. 1x over the Google Edge TPU for 24 Google edge NN models; and (3) SIMDRAM outperforms a CPU/GPU by 16. 7x/1. 4x for three binary NNs.
An Experimental Evaluation of Machine Learning Training on a Real Processing-in-Memory System
Our K-Means clustering on PIM is $2. 8\times$ and $3. 2\times$ than state-of-the-art CPU and GPU versions, respectively.
Machine Learning Training on a Real Processing-in-Memory System
Our goal is to understand the potential of modern general-purpose PIM architectures to accelerate machine learning training.
Heterogeneous Data-Centric Architectures for Modern Data-Intensive Applications: Case Studies in Machine Learning and Databases
One promising execution paradigm that alleviates the data movement bottleneck in modern and emerging applications is processing-in-memory (PIM), where the cost of data movement to/from main memory is reduced by placing computation capabilities close to memory.
Google Neural Network Models for Edge Devices: Analyzing and Mitigating Machine Learning Inference Bottlenecks
To understand how edge ML accelerators perform, we characterize the performance of a commercial Google Edge TPU, using 24 Google edge NN models (which span a wide range of NN model types) and analyzing each NN layer within each model.
Mitigating Edge Machine Learning Inference Bottlenecks: An Empirical Study on Accelerating Google Edge Models
We comprehensively study the characteristics of each NN layer in all of the Google edge models, and find that these shortcomings arise from the one-size-fits-all approach of the accelerator, as there is a high amount of heterogeneity in key layer characteristics both across different models and across different layers in the same model.
SIMDRAM: A Framework for Bit-Serial SIMD Processing Using DRAM
Compared to a CPU and a high-end GPU, SIMDRAM is 257x and 31x more energy-efficient, while providing 93x and 6x higher operation throughput, respectively.
Hardware Architecture Distributed, Parallel, and Cluster Computing Emerging Technologies
