The Magnificent Seven Challenges and Opportunities in Domain-Specific Accelerator Design for Autonomous Systems

Abstract

The end of Moore's Law and Dennard Scaling has combined with advances in agile hardware design to foster a golden age of domain-specific acceleration. However, this new frontier of computing opportunities is not without pitfalls. As computer architects approach unfamiliar domains, we have seen common themes emerge in the challenges that can hinder progress in the development of useful acceleration. In this work, we present the Magnificent Seven Challenges in domain-specific accelerator design that can guide adventurous architects to contribute meaningfully to novel application domains. Although these challenges appear across domains ranging from ML to genomics, we examine them through the lens of autonomous systems as a motivating example in this work. To that end, we identify opportunities for the path forward in a successful domain-specific accelerator design from these challenges.

Presented at DAC 2024

References in corpus (9)

• Hardware Acceleration of Sparse and Irregular Tensor Computations of ML Models: A Survey and Insights
• A Compiler Infrastructure for Accelerator Generators
• SeGraM: A Universal Hardware Accelerator for Genomic Sequence-to-Graph and Sequence-to-Sequence Mapping
• GRiD: GPU-Accelerated Rigid Body Dynamics with Analytical Gradients
• A Survey on Active Simultaneous Localization and Mapping: State of the Art and New Frontiers
• Tiny Robot Learning: Challenges and Directions for Machine Learning in Resource-Constrained Robots
• Hardware Acceleration of Monte-Carlo Sampling for Energy Efficient Robust Robot Manipulation
• Motions in Microseconds via Vectorized Sampling-Based Planning
• GreenFPGA: Evaluating FPGAs as Environmentally Sustainable Computing Solutions