OpenCL Training Courses for Intel Xeon Phi coprocessor

AccelerEyes has been working with Intel to develop premium training courses for the Intel Xeon Phi coprocessor. These training courses are the fastest way for developers to become proficient at programming Intel Xeon Phi.

AccelerEyes is uniquely equipped to provide training for Xeon Phi due to our extensive experience programming ArrayFire support for Xeon Phi. In our training courses, we are able to share important first-hand experience that will greatly benefit your development efforts.

The Intel Xeon Phi is capable of performing over a teraflop of floating point calculations. Contact us today to schedule a training course for your organization.

Attendees will receive the latest industry knowledge and techniques for computing with OpenCL and accelerator devices. We have helped thousands of organizations speedup their code and our primary objective is to help you increase productivity while maximizing the return on your hardware. AccelerEyes training will empower you with the knowledge your organization needs in order to achieve success in accelerated computing.

Upcoming Training Courses and Locations

OpenCL

• Apr 24-25, OpenCL Training, Seattle, WA
• May 8-9, OpenCL Training, Austin, TX
• May 30-31, OpenCL Training, Atlanta, GA
• Jun 12-13, OpenCL Training, Baltimore/Washington D.C.
• Jul 10-11, OpenCL Training, San Jose, CA
• Sep 4-5, OpenCL Training, Boston, MA

• Sep 25-26, OpenCL Training, Baltimore/Washington, D.C.
• Oct 9-10, OpenCL Training, Houston, TX
• Oct 23-24, OpenCL Training, Atlanta, GA
• Nov 6-7, OpenCL Training, Baltimore/Washington, D.C.
• Dec 4-5, OpenCL Training, New York, NY

OpenCL Training Course Syllabus

• Day 1: Introduction to OpenCL
• Lectures:
• OpenCL Computing Overview
• The OpenCL Programming Model
• Architectures Supported
• Basic Dataset Mapping Techniques
• OpenCL Libraries, ArrayFire
• Asychronos Operation
• Portability


• Practice:
• A Simple OpenCL Kernel
• Equivalent ArrayFire Example
• Monte Carlo Pi Estimation
• Using OpenCL Libraries
• Timing OpenCL and ArrayFire
• Porting Code for Multiple Devices

• Day 3: Scaling Across Multiple Devices
• Lectures:
• Multi-Device Use Cases
• Heterogeneous Computing
• Scaling Across Multiple Devices


• Practice:
• Out of Core Problems: Matrix Multiply
• Task Level Parallelism: Optimization
• ArrayFire Multi-Device

• Day 2: OpenCL Optimization
• Lectures:
• OpenCL Architecture: Work Groups, Work-Items, WaveFronts
• OpenCL Memory Model: Global, Local and Constant Memory
• OpenCL Command Queues: Asynchronos Launches and Concurrent Execution
• Advanced Mapping Techniques
• Architecture Specific Limitations and Optimizations
• ArrayFire: Lazy Evaluation and Code Vectorization


• Practice:
• Matrix Transpose
• Median Filter
• Optimization Using Constant Memory
• Command Queues Example
• ArrayFire Example: Nearest Neighbor Algorithm
•  

• Day 4: OpenCL Algorithm Problems
• Lectures and Practice:
• Reductions
• Scan Algorithms
• Sort
• Convolution
• Customer-Specific Problem