OpenACC Monthly Highlights February 2019
Download as PPTX, PDF10 likes4,173 views
The February 2019 OpenACC monthly highlights document provides an overview of the OpenACC programming model, which enables parallel computing on CPUs and GPUs through simple directives. It emphasizes the model's growing adoption across various high-performance computing applications, offers details on upcoming events and bootcamps, and includes educational resources such as video tutorials and research papers. The document underscores OpenACC's advantages in performance and portability, especially in collaboration with GPU technologies.
OpenACC Monthly Highlights February 2019
- 2. 2 WHAT IS OPENACC? main() { <serial code> #pragma acc kernels { <parallel code> } } Add Simple Compiler Directive POWERFUL & PORTABLE Directives-based programming model for parallel computing Designed for performance and portability on CPUs and GPUs SIMPLE Open Specification Developed by OpenACC.org Consortium
- 3. 3 silica IFPEN, RMM-DIIS on P100 OPENACC GROWING MOMENTUM Wide Adoption Across Key HPC Codes ANSYS Fluent Gaussian VASP LSDalton MPAS GAMERA GTC XGC ACME FLASH COSMO Numeca OVER 100 APPS* USING OpenACC Prof. Georg Kresse Computational Materials Physics University of Vienna For VASP, OpenACC is the way forward for GPU acceleration. Performance is similar to CUDA, and OpenACC dramatically decreases GPU development and maintenance efforts. We’re excited to collaborate with NVIDIA and PGI as an early adopter of Unified Memory. “ “ VASP Top Quantum Chemistry and Material Science Code * Applications in production and development
- 4. 4 DON’T MISS THESE UPCOMING EVENTS COMPLETE LIST OF EVENTS Event Call Closes Event Date GTC Bootcamp at GTC 2019, San Jose, California, USA March 4, 2019 March 17, 2019 CAS GPU Hackathon March 1, 2019 April 15-19, 2019 JGI GPU Hackathon March 1, 2019 May 6-10, 2019 MIT GPU Hackathon April 5, 2019 June 3-7, 2019 Colombia GPU Hackathon April 19, 2019 June 17-21, 2019 Princeton GPU Hackathon April 26, 2019 June 24-28, 2019
- 5. 5 OPENACC AT GTC 2019 – MARCH 18-21ST Talks, Tutorials, Labs and More! VIEW ALL EVENTS Explore and engage with the latest research, resources and technology. Learn from thought leaders across academia, research and supercomputing centers such as University of Delaware, University of Illinois at Urbana-Champaign, NCAR, Jülich Supercomputing Centre, Helmholtz-Zentrum Dresden-Rossendorf, and more. With sessions covering topics from scientific disciplines to the most current developments in accelerator programming, there is something for everyone. Attend the GPU Bootcamp, take a hands-on lab or tutorial, connect with experts, and network with peers at this seminal event.
- 6. 6 GPU BOOTCAMP AT GTC Sunday March 17th | 8:30 AM - 6:00 PM APPLY NOW Want to start learning how to accelerate your code quickly and efficiently? GPU Bootcamp is the place to go! Designed for scientists and researchers, this free one-day event will introduce you to a variety of tools for GPU-accelerated computing where you can master key acceleration techniques with the OpenACC programming model, then apply your knowledge to a real code. Registration to GTC is not required.
- 7. 7 10TH ANNUAL USER GROUP MEETING Tuesday March 19th at 7:30PM RSVP NOW Enjoy an evening of colleagues, conversations and cocktails at the OpenACC 10th Annual User Group Meeting. The event will provide a great platform to discuss training, discover the latest resources, give feedback on the specification, collaborate on OpenACC-related research and activities, and share experiences and best practices
- 8. 8 RESOURCES Video Tutorial: OpenACC Selected Topics Michael Wolfe, NVIDIA/PGI Compilers and Tools These engaging video tutorials cover a wide range of topics including: pool allocator using OpenACC, managed memory msing OpenACC, implicit deep copy, true deep copy, the future of data management, multicore execution, and pinned memory. VIEW NOW
- 9. 9 RESOURCES Paper: Parallelization of a Denoising Algorithm for Tonal Bioacoustic Signals using OpenACC Directives Jorge Castro, Advanced Computing Laboratory, Costa Rica National High Technology Center Esteban Meneses, School of Computing, Costa Rica Institute of Technology Automatic segmentation and classification methods for bioacoustic signals enable real- time monitoring, population estimation, as well as other important tasks for the conservation, management, and study of wildlife. These methods normally require a filter or a denoising strategy to enhance relevant information in the input signal and avoid false positive detections. This denoising stage is usually the performance bottleneck of such methods. This paper discusses parallelizing a denoising algorithm for tonal bioacoustic signals using mainly OpenACC directives. The implemented program was executed in both multicore and GPU architectures. The proposed parallelized algorithm achieves a higher speedup on GPU than CPU, leading to a 10.67 speedup compared to the original sequential algorithm in C++. READ NOW
- 10. 10 RESOURCES Blog: Optimizing an OpenACC Weather Simulation Kernel Alan Gray, NVIDIA This blog article describes recent work to optimize an OpenACC code provided by the Met Office in the United Kingdom. This relatively small computational section has been developed as part of preparations to move to the new LFRic Weather Simulation Model. LFRic will be developed using an automated system called PSyclone which itself is currently under development at The Hartree Centre to generate performance-portable parallel code, including OpenACC-augmented Fortran for execution on GPUs. The hand-tuning of the code described in this blog provides a “gold standard” for PSyclone, to ensure that it is developed in a way that permits good performance on the GPU architecture. READ NOW