Log In Sign Up

Apollo: Transferable Architecture Exploration

by   Amir Yazdanbakhsh, et al.

The looming end of Moore's Law and ascending use of deep learning drives the design of custom accelerators that are optimized for specific neural architectures. Architecture exploration for such accelerators forms a challenging constrained optimization problem over a complex, high-dimensional, and structured input space with a costly to evaluate objective function. Existing approaches for accelerator design are sample-inefficient and do not transfer knowledge between related optimizations tasks with different design constraints, such as area and/or latency budget, or neural architecture configurations. In this work, we propose a transferable architecture exploration framework, dubbed Apollo, that leverages recent advances in black-box function optimization for sample-efficient accelerator design. We use this framework to optimize accelerator configurations of a diverse set of neural architectures with alternative design constraints. We show that our framework finds high reward design configurations (up to 24.6 sample-efficiently than a baseline black-box optimization approach. We further show that by transferring knowledge between target architectures with different design constraints, Apollo is able to find optimal configurations faster and often with better objective value (up to 25 outcome portrays a promising path forward to facilitate generating higher quality accelerators.


page 1

page 2

page 3

page 4


Rethinking Co-design of Neural Architectures and Hardware Accelerators

Neural architectures and hardware accelerators have been two driving for...

AIRCHITECT: Learning Custom Architecture Design and Mapping Space

Design space exploration is an important but costly step involved in the...

GANDSE: Generative Adversarial Network based Design Space Exploration for Neural Network Accelerator Design

With the popularity of deep learning, the hardware implementation platfo...

AutoAccel: Automated Accelerator Generation and Optimization with Composable, Parallel and Pipeline Architecture

CPU-FPGA heterogeneous architectures are attracting ever-increasing atte...

Domain-specific Genetic Algorithm for Multi-tenant DNNAccelerator Scheduling

As Deep Learning continues to drive a variety of applications in datacen...

Fast Design Space Exploration of Nonlinear Systems: Part II

Nonlinear system design is often a multi-objective optimization problem ...

Design Space Exploration of SABER in 65nm ASIC

This paper presents a design space exploration for SABER, one of the fin...