Giter VIP home page Giter VIP logo

chandranil2606 / learning-io-access-patterns-to-improve-prefetching-in-ssds- Goto Github PK

View Code? Open in Web Editor NEW
8.0 3.0 2.0 85.25 MB

In this project, we discuss the challenges of prefetching in SSDs, explain why prior approaches fail to achieve high accuracy, and present a neural network based prefetching approach that significantly outperforms the state-of the-art.

Jupyter Notebook 99.42% Shell 0.58%

learning-io-access-patterns-to-improve-prefetching-in-ssds-'s Introduction

Author: Chandranil Chakraborttii and Heiner Litz

My website: https://people.ucsc.edu/~cchakrab/

Project Description: In this project, we collect I/O trace files from several real-world applications running on cloudservers and show that our proposed approach consistently outperforms existing stride prefetchers by up to 800ร— and prior approaches based on Markov chains by up to 8ร—. Furthermore, we propose an address map-ping learning technique to demonstrate the applicability of our approach to previously unseen SSD workloads and perform an hyperparameter sensitivity study.

You will need the following packages installed for the code to work:

  • python 3.8.6
  • tensorflow-gpu 1.15
  • nvidia-driver-430
  • cuda 10.1
  • cudnn 9.0
  • pandas
  • matplotlib
  • pillow
  • requests
  • sklearn
  • keras multi-head
  • jupyter notebook

Please use the following steps to recreate the project.

  1. Download the trace data using the shell scripts
  2. Run the data through the data filtering step
  3. Use the Multihead-train-model_ipynb to train the model
  4. Use generate predictions.ipynb to generate predictions
  5. Use simulator.ipynb to check the performance of the model
  6. Use the baselines.ipynb to get information about predictions
  7. Use transfer learning to test applicabilty in other traces (Required training first. Trained model included)

P.S: You need to update the path and GPU variables before running.

learning-io-access-patterns-to-improve-prefetching-in-ssds-'s People

Contributors

chandranil2606 avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar

learning-io-access-patterns-to-improve-prefetching-in-ssds-'s Issues

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.