1 / 9

OpenACC Month Highlights- October

Check out OpenACC Monthly Highlights for updates on SC17 activities, sessions, and more.

nvidia
Download Presentation

OpenACC Month Highlights- October

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. OPENACC MONTHLY HIGHLIGHTS October 2017

  2. OpenACC is a directives- based programming approach to parallel computing designed for performance and portability on CPUs and GPUs.

  3. TOP HPC APPS ADOPTING OPENACC ANSYS Fluent ● Gaussian ● VASP ● GTC ● XGC ● ACME ● FLASH ● LSDalton ● COSMO ● ELEPHANT ● RAMSES ● ICON ● ORB5 Gaussian 16 ANSYS Fluent ANSYS Fluent R18.0 Radiation Solver Valinomycin wB97xD/6-311+(2d,p) Freq 30000 Fluent Native Solver Fluent HTC Solver K80 GPU 22500 5.15X speedup 2.25X speedup Time (S) 15000 7500 0 T4 T8 T14 T28 CPU (cores) Hardware: HPE server with dual Intel Xeon E5-2698 v3 CPUs (2.30GHz ; 16 cores/chip), 256GB memory and 4 Tesla K80 dual GPU boards (boost clocks: MEM 2505 and SM 875). Gaussian source code compiled with PGI Accelerator Compilers (16.5) with OpenACC (2.5 standard). CPU: (Haswell EP) Intel(R) Xeon(R) CPU E5-2695 v3 @2.30GHz, 2 sockets, 28 cores GPU: Tesla K80 12+12 GB, Driver 346.46

  4. Join OpenACC at #SC17 for a user group meeting, talks, workshops, BoF and labs

  5. JOIN OPENACC USERS AT SC17 Forth OpenACC User Group Meeting, Nov 14, Tag Restaurant REGISTER NOW Network and Discuss Invited Speakers OpenACC-related research Feedback on the Specification OpenACC Trainings Have a Great Time! Experiences and Best Practices Raghu Raj Prasanna Kumar National Center for Atmospheric Research (NCAR) Lin Gan Jack Wells Oak Ridge National Laboratory Wuxi Supercomputing Center

  6. OPENACC TALKS AT SC 2017 COMPLETE SCHEDULE Activity BoF: OpenACC API User Experience, Vendor Reaction, Relevance, and Roadmap Talk: Application Readiness Projects for the Summit Architecture Talk: Unstructured-Grid CFD Algorithms on the NVIDIA Pascal and Volta Architectures Talk: Accelerating HPC Programmer Productivity with OpenACC and CUDA Unified Memory Talk: An Approach to Developing MPAS on GPUs Date Nov 14, 2017 5:15 - 6:45PM Location Room 210 - 212 Nov 14, 2017 2:00 - 2:20PM NVIDIA Booth Nov 14, 2017 12:30 - 12:50PM NVIDIA Booth Nov 15, 2017 10:30 - 10:50AM NVIDIA Booth Nov 15, 2017 3:00 - 3:20PM NVIDIA Booth

  7. WORKSHOPS AND TUTORIALS AT SC 2017 Activity Tutorial: Scalable Parallel Programming Using OpenACC for Multicore, GPUs, and Manycore Tutorial: Application Porting and Optimization on GPU- Accelerated POWER Architectures Workshop: Fourth Workshop on Accelerator Programming Using Directives (WACCPD) Workshop: EduHPC-17: Workshop on Education for High- Performance Computing Hands-on Labs: OpenACC labs at NVIDIA Booth at SC17 Date Nov 13, 2017 8:30AM - 5:00PM Nov 13, 2017 8:30AM - 5:00PM Nov 13, 2017 9:00AM - 5:30PM Nov 13, 2017 9:00AM - 5:30PM Nov 13 - 16, 2017 Show hours Location Room 302 Room 405 Room 710 - 712 Room 505 NVIDIA Booth COMPLETE SCHEDULE

  8. RESOURCES  Paper: Accelerating lattice QCD simulations with 2 flavours of staggered fermions on multiple GPUs using OpenACC - a first attempt “We present the results of an effort to accelerate a Rational Hybrid Monte Carlo (RHMC) program for lattice quantum chromodynamics (QCD) simulation for 2 flavours of staggered fermions on multiple Kepler K20X GPUs distributed on different nodes of a Cray XC30. We do not use CUDA but adopt a higher level directive based programming approach using the OpenACC platform. The lattice QCD algorithm is known to be bandwidth bound; our timing results illustrate this clearly, and we discuss how this limits the parallelization gains. We achieve more than a factor three speed-up compared to the CPU only MPI program.” READ NOW

  9. FOR MORE INFORMATION Visit OpenACC.org EXPLORE NOW

More Related