Presentation is loading. Please wait.

Presentation is loading. Please wait.

Imprecise Computing Yavuz Yetim. Overview Motivation Background Definition and Causes of Imprecision Solution Approaches Discussion of Two Methods Future.

Similar presentations


Presentation on theme: "Imprecise Computing Yavuz Yetim. Overview Motivation Background Definition and Causes of Imprecision Solution Approaches Discussion of Two Methods Future."— Presentation transcript:

1 Imprecise Computing Yavuz Yetim

2 Overview Motivation Background Definition and Causes of Imprecision Solution Approaches Discussion of Two Methods Future Work

3 Motivation Precision = Overkill Applications inherently imprecision tolerant Cosmic Rays Perfect timing, High V dd, ECC, CRC, checker circuits Power Performance

4 Background Vulnerability Factor [Mukherjee, Weaver, Emer, Reinhardt, Austin, 2003] – Not all bits are important (Architectural) – The important bits are not always important (Timing) Evaluation Method

5 Background Algorithmic Noise Tolerance [Hegde, Shanbhag, 1999] – Reduce noise in predictable signals DSP Applications

6 Background Error Resilient System Architecture Inflexible, Suboptimal

7 Definition of Imprecise Data Stochastic Process – Probabilistic Issues – Time Issues Imprecision Time PDF Google Page Rank Or MIS Memory bit: Reverse time

8 Causes of Imprecision Unit: Hardware Faults Input: Data From Noisy Channel Operation: Software Bugs Unit InputOutput Operation

9 Solution Approaches Decrease imprecision by estimation – ANT approach in software Tolerate imprecision by controlling it – ERSA only handles exceptions – Numerical control Input: 10 -3, Output: 10 -2

10 Software Support Information flow – Hardware-Software – Data-Data Ease of use Efficiency Resource Management

11 Two Analysis Methods Probabilistic Method Heuristic Method

12 Probabilistic Method int b, c; imp int a, d, e;. // some code modifying b, c a = b + c;. // some code modifying e. d = a + e; # bc ae d

13 Heuristic Method Keep performance metric for variables Update all with info from hardware Feedback for adjusting imprecision

14 Comparison Probabilistic – Probabilistic – Operational Overhead – Both online and offline optimization Heuristic – Definite – Hardware Overhead – Only online optimization

15 Future Work Combine two methods Better evaluation for different methods Compiler, architecture and hardware support Power and Performance evaluations

16 Thank you…


Download ppt "Imprecise Computing Yavuz Yetim. Overview Motivation Background Definition and Causes of Imprecision Solution Approaches Discussion of Two Methods Future."

Similar presentations


Ads by Google