Emerging applications such as deep neural network demand high off-chip memory
bandwidth. However, under stringent physical constraints of chip packages and system …

Training machine learning (ML) algorithms is a computationally intensive process, which is
frequently memory-bound due to repeatedly accessing large training datasets. As a result …

In this paper, we present GradPIM, a processingin-memory architecture which accelerates
parameter updates of deep neural networks training. As one of processing-in-memory …

As its core computation, a self-attention mechanism gauges pairwise correlations across the
entire input sequence. Despite favorable performance, calculating pairwise correlations is …

Near-memory processing has been extensively studied to optimize memory intensive
workloads. However, none of the proposed designs address sparse matrix transposition, an …

Data movement between memory and processors is a major bottleneck in modern
computing systems. The processing-in-memory (PIM) paradigm aims to alleviate this …

Matrix-matrix multiplication operations (GEMMs) are important in many HPC and machine-
learning applications. They are often mapped to discrete accelerators (eg, GPUs) to improve …

Training machine learning (ML) algorithms is a computationally intensive process, which is
frequently memory-bound due to repeatedly accessing large training datasets. As a result …

In today's data-centric world, where data fuels numerous application domains, with machine
learning at the forefront, handling the enormous volume of data efficiently in terms of time …

Modern Machine Learning (ML) training on large-scale datasets is a very time-consuming
workload. It relies on the optimization algorithm Stochastic Gradient Descent (SGD) due to …