# Difference between revisions of "Mapping Networks on Reconfigurable Binary Engine Accelerator"

### From iis-projects

(→Status: Available) |
|||

Line 3: | Line 3: | ||

---> | ---> | ||

==Short Description== | ==Short Description== | ||

− | We have recently designed an accelerator called Reconfigurable Binary Engine (RBE). The RBE architecture uses these two innovations to emulate quantized NNs by choosing the binary weights to correspond to each bit of the quantized weights. One quantized NN can therefore be emulated by a superposition of power-of-2 weighted Q) × Q+ binary NN, whereas Q+ corresponds to the quantization level of the weights and Q) quantization level of the activations. We call this concept from now on Binary Based Quantization (BBQ) which allows the RBE to perform convolutions with configurable arithmetic precisions in a flexible and power-scalable way. In this project we make use of our in-house developed frameworks NEMO and DORY to map networks onto the RBE accelerator and evaluate its performance and energy-efficiency for real networks. | + | We have recently designed an accelerator called Reconfigurable Binary Engine (RBE)[1]. The RBE architecture uses these two innovations to emulate quantized NNs by choosing the binary weights to correspond to each bit of the quantized weights. One quantized NN can therefore be emulated by a superposition of power-of-2 weighted Q) × Q+ binary NN, whereas Q+ corresponds to the quantization level of the weights and Q) quantization level of the activations. We call this concept from now on Binary Based Quantization (BBQ) which allows the RBE to perform convolutions with configurable arithmetic precisions in a flexible and power-scalable way. In this project, we make use of our in-house developed frameworks NEMO [2] (or Quantlab [3]) and DORY [4] to map networks onto the RBE accelerator and evaluate its performance and energy-efficiency for real networks. |

+ | |||

+ | ===Literature=== | ||

+ | * [https://github.com/pulp-platform/rbe] RBE Github | ||

+ | * [https://github.com/pulp-platform/dory] Dory Github | ||

+ | * [https://github.com/pulp-platform/dory_examples] Dory Examples Github | ||

+ | * [https://github.com/pulp-platform/nemo] Nemo Github | ||

+ | * [https://github.com/pulp-platform/quantlab] Quantlab Github | ||

===Status: Available === | ===Status: Available === | ||

Line 33: | Line 40: | ||

===Professor=== | ===Professor=== | ||

[http://www.iis.ee.ethz.ch/people/person-detail.html?persid=194234 Luca Benini] | [http://www.iis.ee.ethz.ch/people/person-detail.html?persid=194234 Luca Benini] | ||

− | |||

− | |||

− | |||

− | |||

− | |||

[[#top|↑ top]] | [[#top|↑ top]] | ||

Line 59: | Line 61: | ||

At the end of the project, the outcome of the thesis will be presented in a 15 (SA) or 20-minutes (MA) talk and 5 minutes of discussion in front of interested people of the Integrated Systems Laboratory. The presentation is open to the public, so you are welcome to invite interested friends. The exact date will be determined towards the end of the work. | At the end of the project, the outcome of the thesis will be presented in a 15 (SA) or 20-minutes (MA) talk and 5 minutes of discussion in front of interested people of the Integrated Systems Laboratory. The presentation is open to the public, so you are welcome to invite interested friends. The exact date will be determined towards the end of the work. | ||

− | |||

− | |||

==Links== | ==Links== |

## Revision as of 17:00, 19 November 2021

## Contents

## Short Description

We have recently designed an accelerator called Reconfigurable Binary Engine (RBE)[1]. The RBE architecture uses these two innovations to emulate quantized NNs by choosing the binary weights to correspond to each bit of the quantized weights. One quantized NN can therefore be emulated by a superposition of power-of-2 weighted Q) × Q+ binary NN, whereas Q+ corresponds to the quantization level of the weights and Q) quantization level of the activations. We call this concept from now on Binary Based Quantization (BBQ) which allows the RBE to perform convolutions with configurable arithmetic precisions in a flexible and power-scalable way. In this project, we make use of our in-house developed frameworks NEMO [2] (or Quantlab [3]) and DORY [4] to map networks onto the RBE accelerator and evaluate its performance and energy-efficiency for real networks.

### Literature

### Status: Available

- Looking for 1-2 Semester/Master students
- Contact: Gianna Paulin, Thorir Mar Ingolfsson

### Prerequisites

- VLSI I
- C coding
- python coding (optimal: Pytorch)

### Character

- 20% Theory
- 20% HW understanding
- 40% ML Tools: Nemo, Dory, Pytorch
- 20% Embedded C programming

### Professor

## Project Organization

#### Weekly Meetings

The student shall meet with the advisor(s) every week in order to discuss any issues/problems that may have persisted during the previous week and with a suggestion of next steps. These meetings are meant to provide a guaranteed time slot for mutual exchange of information on how to proceed, clear out any questions from either side and to ensure the student’s progress.

#### Report / Presentation

Documentation is an important and often overlooked aspect of engineering. One final report has to be completed within this project. Any form of word processing software is allowed for writing the reports, nevertheless, the use of LaTeX with Tgif, drawoio (See: http://bourbon.usc.edu:8001/tgif/index.html and http://www.dz.ee.ethz.ch/en/information/how-to/drawing-schematics.html) or any other vector drawing software (for block diagrams) is strongly encouraged by the IIS staff.

###### Final Report

A digital copy of the report, the presentation, the developed software, build script/project files, drawings/illustrations, acquired data, etc. needs to be handed in at the end of the project. Note that this task description is part of your report and has to be attached to your final report.

###### Presentation

At the end of the project, the outcome of the thesis will be presented in a 15 (SA) or 20-minutes (MA) talk and 5 minutes of discussion in front of interested people of the Integrated Systems Laboratory. The presentation is open to the public, so you are welcome to invite interested friends. The exact date will be determined towards the end of the work.