The architectural design-space exploration (or DSE) process-whether manual or automated-
benefits greatly from knowing the limits of the metrics of interest in advance. Data movement …

A spatial accelerator's efficiency depends heavily on both its mapper and cost models to
generate optimized map**s for various operators of DNN models. However, existing cost …

Map Space Exploration is the problem of finding optimized map**s of a Deep Neural
Network (DNN) model on an accelerator. It is known to be extremely computationally …

Applications of machine learning (ML) increasingly penetrate into our daily routines, our
work, and our living environments. In this way, more complex machine intelligence …

To achieve high accuracy, convolutional neural networks (CNNs) are increasingly growing
in complexity and diversity in layer types and topologies. This makes it very challenging to …

Deep neural network (DNN) hardware accelerators enable the execution of complex DNN
inferences on resource-constrained IoT devices. Inference performance and energy figures …

High-performance computing and deep learning domains have been motivating the design
of domain-specific processors. Although these processors can provide promising …

Sparse Tensor Algebra (STA) applications are limited by data movement and can benefit
from better data reuse. Prior research has focused on intra-operator data reuse, such as …

Workload scheduling strategy, referred to as map**, plays a vital role in exploring
hardware spatial accelerator performance. Evaluating all possible map**s experimentally …

Hypergraphs are recently emerging as a robust set-theoretical mathematical tool that can
faithfully model higher-order relationships among the entities in a dataset. To design efficient …