Heterogeneous System Modeling and Optimization

This paper presents GoldenEye, a functional simulator with fault injection capabilities for common and emerging numerical formats, implemented for the PyTorch deep learning framework. Gold- enEye provides a unified framework for numerical format...

Specialized accelerators are increasingly used to meet the power-performance goals of emerging applications such as machine learning, image processing, and graph analysis. Existing accelerator programming methodologies using APIs have several limitations...

This paper presents the many-accelerator architecture, a design approach combining the scalability of homogeneous multi-core architectures and system-on-chip’s high performance and power-efficient hardware accelerators. In preparation for systems...

Hardware specialization, in the form of accelerators that provide custom datapath and control for specific algorithms and applications, promises impressive performance and energy advantages compared to traditional architectures. Current research in...

In this paper we propose using machine learning to improve the design of deep neural network hardware accelerators. We show how to adapt multi-objective Bayesian optimization to overcome a challenging design problem: optimizing deep neural network...

Increasing demand for power-efficient, high- performance computing has spurred a growing number and diversity of hardware accelerators in mobile and server Systems on Chip (SoCs). This paper makes the case that the co-design of the accelerator...