Files in this item

FilesDescriptionFormat

application/pdf

application/pdfUMENTHUM-THESIS-2019.pdf (316kB)
(no description provided)PDF

Description

Title:Open-source high-level synthesis of tensorflow dataflow graphs using LegUp
Author(s):Umenthum, Kenneth Richard
Advisor(s):Chen, Deming
Department / Program:Electrical & Computer Eng
Discipline:Electrical & Computer Engr
Degree Granting Institution:University of Illinois at Urbana-Champaign
Degree:M.S.
Genre:Thesis
Subject(s):high level synthesis
machine learning
tensorflow
legup
Abstract:A flow is presented for synthesizing Tensorflow computation graphs into FPGA accelerators using the open-source high-level synthesis (HLS) tool LegUp. The Tensorflow computation graph is represented translated from an intermediate representation in Tensorflow's Accelerated Linear Algebra (XLA) compiler called High Level Optimizer (HLO). This is translated into LLVM intermediate representation (IR) using a modified version of XLA's CPU backend. These modifications enable users to leverage IP modules for computation-intensive operations. For a simple instance of matrix multiply, using even a naively implemented IP is shown to give a 1.7x speedup over baseline accelerators synthesized from the original CPU backend.
Issue Date:2019-04-26
Type:Text
URI:http://hdl.handle.net/2142/104949
Rights Information:Copyright 2019 Kenneth Richard Umenthum
Date Available in IDEALS:2019-08-23
Date Deposited:2019-05


This item appears in the following Collection(s)

Item Statistics