Personal tools

Big Data Analytics Benchmarks for Ara

From iis-projects

Revision as of 15:20, 6 November 2022 by Chizhang (talk | contribs)
Jump to: navigation, search


Introduction

Ara big data analytics Ara lack these benchmarks goal:


Tasks

  • Familiarize yourself with vector processor Ara
    • Try to run Ara RTL simulation
    • Executing existing benchmarks
    • Understand how vector processor works and the chaining techneque
  • Familiarize yourself with a bunch of popular big data analytics worksloads, including:
    • Naive Bayes
    • SVM
    • K-means clustering
    • Breadth-first search
    • Depth-first search
    • Multilayer perceptron,
    • Graph neural network
  • Coding for big data analytics benchmarks for Ara, while think about:
    • How to vectorize these workloads
    • How to schedule memory access and computation to make best advantage of vector chaining and reach to high function unit utilization
  • Evaluating big data analytics benchmarks
    • Run you benchmarks on Ara and count performance metrics, function unit utilization, bandwidth, bus utilization, etc.
    • Make roofline model, while varing data set size and Ara lane counts
  • Write a report and prepare a presentation.
  • Possible BONUS goals.


Requirements

  • Strong interest and basic knowledge in computer architecture and operating systems, both on the HW and SW sides
  • Experience with SystemVerilog HDL, such as taught in VLSI I
  • Knowledge of bare-metal C and assembly programming
  • Bonus: being familiar with vector processors, RISC-V RVV

Character

  • 25% Literature / Architecture review
  • 50% Bare-metal C and Assembly programming
  • 25% Performance evaluation

Project Supervisors

References

[1] Ara: https://arxiv.org/pdf/1906.00478.pdf

[2] Ara source code: https://github.com/pulp-platform/ara

[3] Cray-Processor: http://www.edwardbosworth.com/My5155_Slides/Chapter13/Cray_Supercomputers.htm

[4] RVV: https://github.com/riscv/riscv-v-spec/releases/tag/v1.0