DeepAI AI Chat
Log In Sign Up

Data-Driven Offline Optimization For Architecting Hardware Accelerators

10/20/2021
by   Aviral Kumar, et al.
Google
berkeley college
7

Industry has gradually moved towards application-specific hardware accelerators in order to attain higher efficiency. While such a paradigm shift is already starting to show promising results, designers need to spend considerable manual effort and perform a large number of time-consuming simulations to find accelerators that can accelerate multiple target applications while obeying design constraints. Moreover, such a "simulation-driven" approach must be re-run from scratch every time the set of target applications or design constraints change. An alternative paradigm is to use a "data-driven", offline approach that utilizes logged simulation data, to architect hardware accelerators, without needing any form of simulations. Such an approach not only alleviates the need to run time-consuming simulation, but also enables data reuse and applies even when set of target applications changes. In this paper, we develop such a data-driven offline optimization method for designing hardware accelerators, dubbed PRIME, that enjoys all of these properties. Our approach learns a conservative, robust estimate of the desired cost function, utilizes infeasible points, and optimizes the design against this estimate without any additional simulator queries during optimization. PRIME architects accelerators – tailored towards both single and multiple applications – improving performance upon state-of-the-art simulation-driven methods by about 1.54x and 1.20x, while considerably reducing the required total simulation time by 93 PRIME also architects effective accelerators for unseen applications in a zero-shot setting, outperforming simulation-based methods by 1.26x.

READ FULL TEXT

page 1

page 2

page 3

page 4

06/29/2019

HTS: A Hardware Task Scheduler for Heterogeneous Systems

As the Moore's scaling era comes to an end, application specific hardwar...
02/01/2022

Compiler-Driven Simulation of Reconfigurable Hardware Accelerators

As customized accelerator design has become increasingly popular to keep...
09/21/2022

Review of Time Series Forecasting Methods and Their Applications to Particle Accelerators

Particle accelerators are complex facilities that produce large amounts ...
09/14/2022

C^2:Co-design of Robots via Concurrent Networks Coupling Online and Offline Reinforcement Learning

With the rise of computing power, using data-driven approaches for co-de...
03/26/2022

Tuning Particle Accelerators with Safety Constraints using Bayesian Optimization

Tuning machine parameters of particle accelerators is a repetitive and t...
11/29/2021

A Graph Deep Learning Framework for High-Level Synthesis Design Space Exploration

The design of efficient hardware accelerators for high-throughput data-p...
12/29/2022

TensorFHE: Achieving Practical Computation on Encrypted Data Using GPGPU

In this paper, we propose TensorFHE, an FHE acceleration solution based ...