Monthly Subscription Starting at AED 99 + VAT

Developing FPGA-accelerated cloud applications with SDAccel: Practice
  • Level Professional
  • Duration 13 hours
  • Course by Politecnico di Milano
  • Offered by

About

This course is for anyone passionate about learning how to develop FPGA-accelerated applications with SDAccel! The more general purpose you are, the more flexible you are and the more kinds of programs and algorithms you can execute on your underlying computing infrastructure. All of this is terrific, but there is no free food and this is happening, quite often, by losing in efficiency. This course will present several scenarios where the workloads require more performance than can be obtained even by using the fastest CPUs. This scenario is turning cloud and data center architectures toward accelerated computing. Within this course, we are going to show you how to gain benefits by using Xilinx SDAccel to program Amazon EC2 F1 instances. We are going to do this through a working example of an algorithm used in computational biology. The huge amount of data the algorithms need to process and their complexity raised the problem of increasing the amount of computational power needed to perform the computation. In this scenario, hardware accelerators revealed to be effective in achieving a speed-up in the computation while, at the same time, saving power consumption. Among the algorithms used in computational biology, the Smith-Waterman algorithm is a dynamic programming algorithm, guaranteed to find the optimal local alignment between two strings that could be nucleotides or proteins. In the following classes, we present an analysis and successive FPGA-based hardware acceleration of the Smith-Waterman algorithm used to perform pairwise alignment of DNA sequences. Within this context, this course is focusing on distributed, heterogeneous cloud infrastructures, providing you details on how to use Xilinx SDAccel, through working examples, to bring your solutions to life by using the Amazon EC2 F1 instances.

Modules

Rationale behind FPGA in the Cloud

    • 3 Videos
    • 1 Assignment
Show info about module content

1 Assignment

  • QUIZ 1

3 Videos

  • Course introduction
  • An overview of cloud infrastructure
  • Cloud Computing: few definitions

Reconfigurable acceleration in the Cloud

    • 4 Videos
    • 1 Assignment
Show info about module content

1 Assignment

  • QUIZ 2

4 Videos

  • Reconfigurable acceleration in the Cloud
  • Reconfigurable acceleration in the Cloud: Intel FPGA-based solutions
  • Reconfigurable acceleration in the Cloud: Xilinx FPGA-based solutions
  • Reconfigurable acceleration in the Cloud: from the past, to the future

An introduction to the AWS EC2 F1 instances

    • 1 Videos
    • 1 Assignment
Show info about module content

1 Assignment

  • QUIZ 3

1 Videos

  • An introduction to the AWS EC2 F1 instances

Applicative domains and Victor's story

    • 1 Videos
    • 1 Assignment
Show info about module content

1 Assignment

  • QUIZ 4

1 Videos

  • Applicative domains and Victor's story

Understanding the AWS F1 HW and SW stacks

    • 3 Videos
    • 1 Assignment
Show info about module content

1 Assignment

  • QUIZ 5

3 Videos

  • F1: instances and FPGA description
  • How FPGA Acceleration Works on AWS
  • AWS F1 Platform Model

AFI Creation Flow Overview

    • 5 Videos
    • 1 Assignment
Show info about module content

1 Assignment

  • QUIZ 6

5 Videos

  • Creating Kernels from RTL IP, C/C++, OpenCL
  • Compiling the Platform
  • Creating an Amazon FPGA Image
  • Developing and Executing a Host Application on F1
  • Start Accelerating

An overview to the Smith-Waterman problem

    • 8 Videos
    • 1 Readings
    • 1 Assignment
Show info about module content

1 Assignment

  • QUIZ 7

8 Videos

  • Problem description
  • Algorithm and code analysis
  • Roofline model 1/2
  • Roofline model 2/2
  • Code profiling
  • Static Code Analysis 1/2
  • Static Code Analysis 2/2
  • Performance Prediction via Roofline Model

1 Readings

  • SDAccel Environment Profiling and Optimisation Guide

On how to optimize the Smith-Waterman solution

    • 9 Videos
    • 1 Readings
    • 1 Assignment
Show info about module content

1 Assignment

  • QUIZ 8

9 Videos

  • A first implementation 1/3
  • A first implementation 2/3
  • A first implementation 3/3
  • Parallelism in the Smith-Waterman Algorithm
  • Systolic Array Architecture 1/2
  • Systolic Array Architecture 2/2
  • Input Compression
  • Shift Register
  • Dual Physical Ports

1 Readings

  • Sources Codes

SDAccel on F1

    • 3 Videos
    • 1 Readings
    • 1 Assignment
Show info about module content

1 Assignment

  • QUIZ 9

3 Videos

  • Smith-Waterman accelerated on the Amazon EC2 F1 instances 1/3
  • Smith-Waterman accelerated on the Amazon EC2 F1 instances 2/3
  • Smith-Waterman accelerated on the Amazon EC2 F1 instances 3/3

1 Readings

  • Source Codes

Concluding notes

    • 1 Videos
    • 1 Readings
Show info about module content

1 Videos

  • Closing remarks and future directions

1 Readings

  • Architectural optimizations for high performance and energy efficient Smith-Waterman implementation on FPGAs using OpenCL

Auto Summary

Develop FPGA-accelerated cloud applications with SDAccel in this professional course designed for enthusiasts in computational efficiency. Guided by Coursera, learn to harness Xilinx SDAccel on Amazon EC2 F1 instances through practical examples, including the Smith-Waterman algorithm for DNA sequence alignment. Perfect for those looking to excel in distributed, heterogeneous cloud infrastructures, the course spans 780 minutes and offers a Starter subscription option. Ideal for professionals seeking to boost their cloud application performance.

Marco Domenico Santambrogio
Instructor

Marco Domenico Santambrogio