LeFlow: Enabling Flexible FPGA High-Level Synthesis of Tensorflow Deep Neural Networks

07/14/2018
by   Daniel H. Noronha, et al.
0

Recent work has shown that Field-Programmable Gate Arrays (FPGAs) play an important role in the acceleration of Machine Learning applications. Initial specification of machine learning applications are often done using a high-level Python-oriented framework such as Tensorflow, followed by a manual translation to either C or RTL for synthesis using vendor tools. This manual translation step is time-consuming and requires expertise that limit the applicability of FPGAs in this important domain. In this paper, we present an open-source tool-flow that maps numerical computation models written in Tensorflow to synthesizable hardware. Unlike other tools, which are often constrained by a small number of inflexible templates, our flow uses Google's XLA compiler which emits LLVM code directly from a Tensorflow specification. This LLVM code can then be used with a high-level synthesis tool to automatically generate hardware. We show that our flow allows users to generate Deep Neural Networks with very few lines of Python code.

READ FULL TEXT

page 4

page 6

research
02/27/2019

TensorFlow Eager: A Multi-Stage, Python-Embedded DSL for Machine Learning

TensorFlow Eager is a multi-stage, Python-embedded domain-specific langu...
research
01/27/2022

High-level Synthesis using the Julia Language

The growing proliferation of FPGAs and High-level Synthesis (HLS) tools ...
research
03/24/2021

De-specializing an HLS library for Deep Neural Networks: improvements upon hls4ml

Custom hardware accelerators for Deep Neural Networks are increasingly p...
research
03/20/2019

TATi-Thermodynamic Analytics ToolkIt: TensorFlow-based software for posterior sampling in machine learning applications

We describe a TensorFlow-based library for posterior sampling and explor...
research
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...
research
03/15/2023

IMPACT: A Toolchain for Nonlinear Model Predictive Control Specification, Prototyping, and Deployment

We present IMPACT, a flexible toolchain for nonlinear model predictive c...
research
05/30/2023

Implementation of a framework for deploying AI inference engines in FPGAs

The LCLS2 Free Electron Laser FEL will generate xray pulses to beamline ...

Please sign up or login with your details

Forgot password? Click here to reset