2018 · 55 citations · 52 references
EngineeringComputer EngineeringComputer ScienceCompilersComputer ArchitectureMachine LearningAccelerator ArchitectureField-programmable Gate Array ArchitectureHardware AccelerationInstruction Set ArchitectureMixed-signal IntegrationProcessor MicroarchitectureAccelerator MicroarchitectureAcceleratorsCompiler DesignCompiler SupportEnergy-efficient Hardware AccelerationInstruction Set DesignInstruction Set MicroarchitectureProgrammable Accelerators
Analog/mixed-signal machine learning (ML) accelerators exploit the unique computing capability of analog/mixed-signal circuits and inherent error tolerance of ML algorithms to obtain higher energy efficiencies than digital ML accelerators. Unfortunately, these analog/mixed-signal ML accelerators lack programmability, and even instruction set interfaces, to support diverse ML algorithms or to enable essential software control over the energy-vs-accuracy tradeoffs. We propose PROMISE, the first end-to-end design of a PROgrammable MIxed-Signal accElerator from Instruction Set Architecture (ISA) to high-level language compiler for acceleration of diverse ML algorithms. We first identify prevalent operations in widely-used ML algorithms and key constraints in supporting these operations for a programmable mixed-signal accelerator. Second, based on that analysis, we propose an ISA with a PROMISE architecture built with silicon-validated components for mixed-signal operations. Third, we develop a compiler that can take a ML algorithm described in a high-level programming language (Julia) and generate PROMISE code, with an IR design that is both language-neutral and abstracts away unnecessary hardware details. Fourth, we show how the compiler can map an application-level error tolerance specification for neural network applications down to low-level hardware parameters (swing voltages for each application Task) to minimize energy consumption. Our experiments show that PROMISE can accelerate diverse ML algorithms with energy efficiency competitive even with fixed-function digital ASICs for specific ML algorithms, and the compiler optimization achieves significant additional energy savings even for only 1% extra errors.
52
Corinna Cortes, Vladimir Vapnik · Machine Learning · 1995 · 40.5K citations · Full text
Corinna Cortes, Vladimir Vapnik · Machine Learning · 1995 · 33K citations · Full text
Mastering the game of Go with deep neural networks and tree search
David Silver, Aja Huang, Chris J. Maddison et al. · Nature · 2016 · 15.8K citations
TensorFlow: a system for large-scale machine learning
Martı́n Abadi, Paul Barham, Jianmin Chen et al. · Operating Systems Design and Implementation · 2016 · 6.4K citations