Programming Workshop is Based on Use of PGI Accelerator with OpenACC Directives
nCore Design, a leading provider of embedded HPC solutions and multicore training courses, today announced plans to present its popular multicore programming course, NCT-500, in Houston, Texas June 11-12, 2012.
The course titled “NCT-500 PGI Accelerator with OpenACC Directives” was developed by nCore in collaboration with The Portland Group (PGI). This course covers concepts and approaches related to programming GPU accelerators using OpenACC directives and the PGI Accelerator™ programming model. Structured as an interactive workshop, students learn from in-depth, hands-on lectures and laboratories, gaining a keen understanding of how to capitalize on low-cost, high performance GPU computing hardware to improve application performance while reducing maintenance and porting requirements.
NCT-500 is ideal for software architects, developers, team leaders and managers seeking to improve their GPU software skills. As mandatory pre-requisites, students should have knowledge of computer architecture and intermediate C or Fortran software development experience.
By attending this course, students will learn to correctly identify concurrency opportunities and the steps necessary to parallelize algorithms to run on GPUs, understand the OpenACC command set and its application to C and Fortran codes, and receive practical advice on GPU programming using OpenACC directives and PGI Accelerator Workstation.
“This is a comprehensive two-day workshop that thoroughly prepares students to be successful with OpenACC and PGI tools,” said Ian Lintault, Managing Director of nCore. “We are thrilled to be able to offer this program in close cooperation with The Portland Group and NVIDIA as the demand for GPU programming increases at a steady pace.”
The two-day course, NCT-500 PGI Accelerator with OpenACC Directives, will be held at the Microtek Training Facility, 11200 Richmond Avenue, Suite 100, in Houston, Texas. Registration is now available at: http://ncoredesign.com/training/registration/
OpenACC is an open parallel programming standard designed to enable scientific and technical programmers to easily take advantage of the transformative power of heterogeneous CPU/GPU computing systems. OpenACC allows parallel programmers to provide simple hints, known as “directives,” to the compiler, identifying which areas of code to accelerate, without requiring programmers to modify or adapt the underlying code itself. By exposing parallelism to the compiler, directives allow the compiler to do the detailed work of mapping the computation onto the accelerator.