MAFIA: Machine Learning Acceleration on FPGAs for IoT Applications

Recent breakthroughs in ML have produced new classes of models that allow ML inference to run directly on milliwatt-powered IoT devices. On one hand, existing ML-to-FPGA compilers are designed for deep neural-networks on large FPGAs. On the other hand, general-purpose HLS tools fail to exploit prope...

Full description

Saved in:
Bibliographic Details
Main Authors: Ghanathe, Nikhil P, Seshadri, Vivek, Sharma, Rahul, Wilton, Steve, Kumar, Aayan
Format: Conference Proceeding
Language:English
Subjects:
Compiler
FPGA
Hardware Acceleration
High level synthesis
Internet of Things
Linear algebra
Machine learning
Machine learning algorithms
Machine learning Inference
Neural networks
Performance evaluation
Program processors
Resource constrained devices
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recent breakthroughs in ML have produced new classes of models that allow ML inference to run directly on milliwatt-powered IoT devices. On one hand, existing ML-to-FPGA compilers are designed for deep neural-networks on large FPGAs. On the other hand, general-purpose HLS tools fail to exploit properties specific to ML inference, thereby resulting in suboptimal performance. We propose MAFIA, a tool to compile ML inference on small form-factor FPGAs for IoT applications. MAFIA provides native support for linear algebra operations and can express a variety of ML algorithms, including state-of-the-art models. We show that MAFIA-generated programs outperform best-performing variant of a commercial HLS compiler by 2.5 × on average.
ISSN:1946-1488
DOI:10.1109/FPL53798.2021.00067