Optimized Hybrid Scaled Neural Analog Predictor - PowerPoint PPT Presentation

Loading...

PPT – Optimized Hybrid Scaled Neural Analog Predictor PowerPoint presentation | free to view - id: 6f5f26-OTg4M



Loading


The Adobe Flash plugin is needed to view this content

Get the plugin now

View by Category
About This Presentation
Title:

Optimized Hybrid Scaled Neural Analog Predictor

Description:

Optimized Hybrid Scaled Neural Analog Predictor Daniel A. Jim nez Department of Computer Science The University of Texas at San Antonio Branch Prediction with ... – PowerPoint PPT presentation

Number of Views:20
Avg rating:3.0/5.0
Slides: 16
Provided by: Danie507
Category:

less

Write a Comment
User Comments (0)
Transcript and Presenter's Notes

Title: Optimized Hybrid Scaled Neural Analog Predictor


1
Optimized Hybrid Scaled Neural Analog Predictor
Daniel A. Jiménez Department of Computer
Science The University of Texas at San Antonio
2
Branch Prediction with Perceptrons
3
Branch Prediction with Perceptrons cont.
4
SNP/SNAP St. Amant et al. 2008
  • A version of piecewise linear neural prediction
    Jiménez 2005
  • Based on perceptron prediction
  • SNAP is a mixed digital/analog version of SNP
  • Uses analog circuit for costly dot-product
    operation
  • Enables interesting tricks e.g. scaling

5
Weight Scaling
  • Scaling weights by coefficients

Different history positions have different
importance!
6
The Algorithm Parameters and Variables
  • C array of scaling coefficients
  • h the global history length
  • H a global history shift register
  • A a global array of previous branch addresses
  • W an n (GHL 1) array of small integers
  • ? a threshold to decide when to train

7
The Algorithm Making a Prediction
Weights are selected based on the current branch
and the ith most recent branch
8
The Algorithm Training
  • If the prediction is wrong or output ? then
  • For the ith correlating weight used to predict
    this branch
  • Increment it if the branch outcome outcome of
    ith in history
  • Decrement it otherwise
  • Increment the bias weight if branch is taken
  • Decrement otherwise

9
SNP/SNAP Datapath
10
Tricks
  • Use alloyed Skadron 2000 global and per-branch
    history
  • Separate table of local perceptrons
  • Output from this stage multiplied by empircally
    determined coefficient
  • Training coefficients vector(s)
  • Multiple vectors initialized to f(i) 1 / (A B
    i)
  • Minimum coefficient value determined empircally
  • Indexed by branch PC
  • Each vector trained with perceptron-like learning
    on-line

11
Tricks(2)
  • Branch cache
  • Highly associative cache with entries for branch
    information
  • Each entry contains
  • A partial tag for this branch PC
  • The bias weight for this branch
  • An ever taken bit
  • A never taken bit
  • The ever/never bits avoid needless use of
    weight resources
  • The bias weight is protected from destructive
    interference
  • LRU replacement
  • gt99 hit rate

12
Tricks(3)
  • Hybrid predictor
  • When perceptron output is below some threshold
  • If a 2-bit counter gshare predictor has high
    confidence, use it
  • Else use a 1-bit counter PAs predictor
  • Multiple ?s indexed by branch PC
  • Each trained adaptively Seznec 2005
  • Ragged array
  • Not all rows of the matrix are the same size

13
Benefit of Tricks
  • Graph shows effect of one trick in isolation
  • Training coefficients yields most benefit

14
References
  • Jiménez Lin, HPCA 2001 (perceptron predictor)
  • Jiménez Lin, TOCS 2002 (global/local
    perceptron)
  • Jiménez ISCA 2005 (piecewise linear branch
    predictor)
  • Skadron, Martonosi Clark, PACT 2000 (alloyed
    history)
  • Seznec 2005 (adaptively trained threshold)
  • St. Amant, Jiménez Burger, MICRO 2008
    (SNP/SNAP)
  • McFarling 1993, gshare
  • Yeh Patt 1991, PAs

15
The End
About PowerShow.com