AccelerEyes has been working closely with AMD and Intel to develop premium OpenCL training courses for AMD devices and the Intel Xeon Phi coprocessor. This comprehensive two day course will enable you to become proficient in writing and optimizing applications for AMD and Intel hardware using OpenCL.
Partnering closely with AMD and Intel, AccelerEyes training courses are the fastest way for developers to become proficient at OpenCL programming. AccelerEyes is uniquely equipped to provide training for AMD and Intel accelerator devices due to our extensive experience programming ArrayFire. 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.
Course Goodie BagAll training courses include the following:
Instruction by an excellent and interesting expert. Many hands-on exercises.Use of a laptop with OpenCL deviceChoice of Linux or Windows operating systemPrinted manual of lecture materialElectronic copy of programming exercisesCertificate of Completion OpenCL Training Course Syllabus
Day 1: Introduction to OpenCL
Lectures:OpenCL Computing OverviewThe OpenCL Programming ModelArchitectures SupportedBasic Dataset Mapping TechniquesOpenCL Libraries, ArrayFireAsynchronous OperationPortability
A Simple OpenCL KernelEquivalent ArrayFire ExampleMonte Carlo Pi EstimationUsing OpenCL LibrariesTiming OpenCL and ArrayFirePorting Code for Multiple DevicesLectures:
Day 2: OpenCL Optimization
Lectures:OpenCL Architecture: Work Groups, Work-Items, WaveFrontsOpenCL Memory Model: Global, Local and Constant MemoryOpenCL Command Queues: Asynchronos Launches and Concurrent ExecutionAdvanced Mapping TechniquesArchitecture Specific Limitations and OptimizationsArrayFire: Lazy Evaluation and Code Vectorization
Matrix TransposeOptimization Using Local MemoryMedian FilterOptimization Using Constant MemoryCommand Queues ExampleExample: Nearest Neighbor AlgorithmExample: Finite-difference time-domain (FDTD) Example