The September 2017 OpenACC Monthly Highlights document covers the latest developments in OpenACC, a portable programming model for high-performance computing (HPC), detailing upcoming courses, events, and a new book aimed at helping programmers utilize OpenACC effectively. It includes performance benchmarks, information about compilers and architectures, and encourages the use of OpenACC to enhance legacy codes with accelerated computing. Notable events are listed, including a hackathon and a workshop at SC17 in Denver.

1. September 2017
OPENACC MONTHLY
HIGHLIGHTS

2. OpenACC.org Members
main()
{
<serial code>
#pragma acc kernels
{
<parallel code>
}
}
Add Simple Compiler Directive
OpenACC Directives

3. SINGLE CODE FOR MULTIPLE PLATFORMS
POWER
Sunway
x86 CPU
x86 Xeon Phi
NVIDIA GPU
PEZY-SC
9x 10x 11x
52x
9x 10x 11x
77x
0x
20x
40x
60x
80x
SpeedupvsSingleHaswellCore
PGI OpenACC
Intel OpenMP
IBM OpenMP
Dual Haswell Dual Broadwell Dual POWER8 1 Tesla
P100
OpenACC - Performance Portable Programming Model for HPC
1 Tesla
V100
AWE Hydrodynamics CloverLeaf mini-App, bm32 data set
Systems: Haswell: 2x16 core Haswell server, four K80s, CentOS 7.2 (perf-hsw10), Broadwell: 2x20 core Broadwell server, eight P100s (dgx1-prd-01), Minsky: POWER8+NVLINK, four P100s,
RHEL 7.3 (gsn1).
Compilers: Intel 17.0, IBM XL 13.1.3, PGI 16.10.
Benchmark: CloverLeaf v1.3 downloaded from http://uk-mac.github.io/CloverLeaf the week of November 7 2016; CloverlLeaf_Serial; CloverLeaf_ref (MPI+OpenMP); CloverLeaf_OpenACC
(MPI+OpenACC)
Data compiled by PGI November 2016, Volta data collected June 2017

4. Learn what’s new with OpenACC

5. INTRODUCTION TO OPENACC COURSE
Free course to start accelerating codes on CPUs and GPUs
Lectures
Hands-on labs
Time with experts
Starts
October 19, 2017
John Urbanic
Parallel Computing Specialist
Pittsburgh Supercomputing Center
Jeff Larkin
Developer Technology Software Engineer
NVIDIA
REGISTER NOW https://webinars.on24.com/NVIDIA/openacc

6. NEW BOOK: OPENACC FOR PROGRAMMERS
• Discover how OpenACC makes scalable
parallel programming easier and more practical
• Get productive with OpenACC code editors,
compilers, debuggers, and performance
analysis tools
• Build your first real-world OpenACC programs
• Overcome common performance, portability,
and interoperability challenges
• Efficiently distribute tasks across multiple
processors READ MORE
Edited by: By Sunita Chandrasekaran, Guido Juckeland

7. RESOURCES
Paper: From MPI to MPI+OpenACC: Conversion of a legacy FORTRAN PCG
solver for the spherical Laplace equation
“Overall, adding OpenACC to POT3D to add multi-GPU capabilities
did not involve overly extensive development time, and for PC1 only
required a 3% change in the source code. This, combined with the
positive GPU performance results, encourages us to move forward
in implementing OpenACC in our global MHD code MAS.
The lessons learned in the POT3D implementation will be of great
assistance in that venture, and we hope they will also be of assistance
to other researchers considering adding accelerated computing to their
legacy code using OpenACC.“
READ NOW

8. UPCOMING EVENTS
EVENT & LOCATION DATE LINK
ORNL Hackathon
Knoxville, Tennessee, USA
Oct 9 - 13, 2017
https://www.olcf.ornl.gov/training-
event/2017-gpu-hackathons
SBAC-PAD 2017
Campinas, Brazil
Oct 17-20, 2017 http://www2.sbc.org.br/sbac/2017/
OpenACC Online Course Oct 19 - Nov 2,
2017
https://webinars.on24.com/NVIDIA/openacc
WACCPD Workshop,
SC17, Denver, USA
Nov 13, 2017 http://waccpd.org/
Scalable Parallel Programming
Using OpenACC for Multicore,
GPUs, and Manycore
SC17, Denver, USA
Nov 13, 2017
http://sc17.supercomputing.org/presentati
on/?id=tut135&sess=sess224
User Group Meeting,
SC17, Denver, USA
Nov 14, 2017 https://www.eventbrite.com/e/fourth-
openacc-user-group-meeting-sc17-tag-
restaurant-tickets-37930132046?ref=estw
COMPLETE LIST OF EVENTS

9. FOR MORE INFORMATION
Visit OpenACC.org
EXPLORE NOW