Loading…
FRCRC HPC 2013 has ended

Sign up or log in to bookmark your favorites and sync them to your phone or calendar.

Tutorial- Intermediate [clear filter]
Tuesday, August 13
 

3:00pm

3:00pm

 
Thursday, August 15
 

8:30am

Intro to Open ACC

Audience: A bit of C or Fortran experience is helpful, no GPU Computing experience required.

Abstract:

Using OpenACC directives, developers can create high-level applications to execute on modern heterogeneous systems, combining CPUs and accelerators. In this tutorial you will learn about GPUs and how their high performance can be used to accelerate applications by adding simple OpenACC directives to familiar programming languages.

After an introduction to GPU programming, you will write your first OpenACC program to understand the concepts of how directives are structured and how to use the OpenACC compiler, building and running your program in the cloud on Amazon’s AWS. Building upon this first example, you will create a parallel program using the “parallel” directive. We will then have a closer look at the OpenACC memory model, learning how to manage data transfers both implicitly and explicitly. Particular focus will be on using compiler feedback and performance analysis to guide development, understanding how to manage data, especially in cases with a nested call graph.  This is a “bring your own computer” hands-on tutorial.


Speakers
ME

Mark Ebersole

As CUDA Educator at NVIDIA, Mark Ebersole teaches developers the benefits of GPU computing using the NVIDIA CUDA parallel computing platform and programming model, and the benefits of GPU computing. With more than ten years of experience as a systems programmer, Mark has spent much... Read More →


Thursday August 15, 2013 8:30am - 10:15am
College of Business Room 8

8:30am

10:30am

HPC in the Cloud
Speakers
EW

Eric Wang

Liqiang (Eric) Wang has been an associate professor (2012-present) and an assistant professor (2006-2012) in the Department of Computer Science at the University of Wyoming. He received Ph.D. in Computer Science from Stony Brook University in 2006. His research interest is the design and analysis of parallel systems. For analysis, he is mainly working on concurrency/security-related error detection. For design, he is currently working on data-intensive parallel computing on multicore CPU, GPU, and Cloud Computing... Read More →


Thursday August 15, 2013 10:30am - 12:30pm
College of Business Room 9

10:30am

Intro to GPU Computing with Python

Audience: A little bit of Python experience is helpful, no GPU Computing experience required.

Abstract:

Until recently, the ability to directly program for an NVIDIA GPU has been restricted to languages such as C/C++ or Fortran.  With the release of Anaconda Accelerate from Continuum Analystics, is now possible to write GPU code directly in Python and have it execute natively on an NVIDIA GPU.

This tutorial will briefly cover an introduction to GPU programming, after which we will move to hands-on exercises using Python, hosted on systems in the cloud with Amazon’s AWS.  The exercises will cover concepts such as memory management, easily launching kernels with thousands of threads, and profiling the created GPU code.  We will also look at simpler methods to accelerate Python functions using Accelerate’s built-in @vectorize decorator.  This is a “bring your own computer” hands-on tutorial.


Speakers
ME

Mark Ebersole

As CUDA Educator at NVIDIA, Mark Ebersole teaches developers the benefits of GPU computing using the NVIDIA CUDA parallel computing platform and programming model, and the benefits of GPU computing. With more than ten years of experience as a systems programmer, Mark has spent much... Read More →


Thursday August 15, 2013 10:30am - 12:30pm
College of Business Room 8