Zur Webseite der Uni Stuttgart

How good is good enough? The Approximate Computing Paradigm in Hardware, Software and Algorithms

Approximate computing is an emerging paradigm in computer science which spans the whole system stack from the hardware up to the software and the algorithms.

The goal of approximate computing is to exploit the error tolerance and robustness of certain applications in order to trade off precision against power, energy, storage, bandwidth and performance. This goal is achieved by both relaxing strict requirements on accuracy and precision, and by allowing a deviating behavior from exact (e.g. Boolean) specifications to some extent.

Besides the development of innovative new approximate hardware structures, research currently focuses on appropriate error metrics, as well as on new algorithms for approximate computing. In addition, the application of fault tolerance measures is investigated to enable a broadened spectrum of applications and to assure the quality of computational results.

This seminar approaches approximate computing at all levels - hardware, software and algorithm - and covers some of the most important challenges in the context of:

  • Architecture and hardware design

  • Technology and hardware implementation

  • Approximate software techniques

  • New algorithms for approximate computing

  • Error metrics and characterization

  • Fault tolerance for approximate computing

Schedule

 

Preliminary schedule (subject to changes):

Date

Room

Topic

17.10.2016
15:45-17:15

0.363

Introduction, topic overview and assignment (Slides)
Presenter: Claus Braun

24.10.2016
15:45-17:15

0.363

Session 0: Introduction to Approximate Computing
Presenter: Claus Braun

05.12.2016
15:45-17:15

0.363

Session 1: Metrics and Characterization in Approximate Computing

Topic 1: "Metrics and techniques for quality evaluation of approximate computations"
Presenter:

Topic 2: "Error resilience characterization"
Presenter:

12.12.2016
15:45-17:15

0.363

Session 2: Programming and Software Techniques in Approximate Computing

Topic 3: "Programming languages and compiler support for approximate computing"
Presenter:

Topic 4: "Approximation techniques in software"
Presenter:

19.12.2016
15:45-17:15

0.363

Session 3: Software Applications in Approximate Computing

Topic 5: "Use of multiple inexact program versions"
Presenter:

Topic 6: "Approximate computing for scientific applications"
Presenter:

09.01.2017
15:45-17:15

0.363

Session 4: Design and Synthesis / Neural Approximate Computing

Topic 7: "High-level synthesis of approximate computing hardware"
Presenter:

Topic 8: "Neural network-based approximate computing "
Presenter:

16.01.2017
15:45-17:15

0.363

Session 5: Approximate and Precision-configurable Arithmetic Hardware

Topic 9: "Approximate full adders"
Presenter:

Topic 10: "Precision-configurable approximate hardware"
Presenter:

23.01.2017
15:45-17:15

0.363

Session 6: Memory in Approximate Computing

Topic 11: "Approximate memory technologies"
Presenter:

Topic 12: "Approximate computing in the memory hierarchy"
Presenter:

30.01.2017
15:45-17:15

0.363

––

06.02.2017
15:45-17:15

0.363

––

Akzeptieren

Diese Webseite verwendet Cookies. Durch die Nutzung dieser Webseite erklären Sie sich damit einverstanden, dass Cookies gesetzt werden. Mehr erfahren, zum Datenschutz