On February 26-March 2, 2018, Brookhaven National Laboratory (BNL) hosted a hackathon targeting the Intel Xeon Phi (formerly code-named Knights Landing, or KNL) processors for scientists to come together to optimize their application code performance on the KNL-based supercomputers. Out of the five teams who participated, two teams came from the high energy physics community:
- APES (Accelerator Particle Energy Simulator): A code for tracking particle-device and particle-particle interactions that has the potential to be used as the design platform for future particle accelerators. Team members all came from BNL.
- ART: a code for simulating the formation of structures in the universe, particularly galaxy clusters. Team members came from Yale University and University of Miami.
Each team was paired with a mentor with similar scientific background. They also had access to four floating mentors from Intel who brought expertise in OpenMP, Intel hardware architectures, compilers and performance profiling tools. The teams worked with their mentors for five days in a hands-on setting. By the end of the week, all teams achieved significant performance improvements for their codes, with ART and APES achieving >2X and >5X speedup, respectively.
Held at the ALCF from May 15–17, our intensive three-day workshop is aimed at experienced HPC users with goals of applying for a major allocation award.
Carnegie Mellon University (CMU) and Georgia Tech (GT) will be hosting a
3-day conference on “Machine Learning in Science and Engineering” on
CMU’s campus in Pittsburgh on June 6-8, 2018. The purpose of the
conference is to bring together researchers across the disciplines to
present the latest ideas on the applications of ML methods in their
fields as well as providing a forum for work on the development of new
algorithms designed for challenges in science and engineering. More
information on the conference can be found at the website
Together with Deirdre Shoemaker from Georgia Tech, I am co-chairing the
Physics Track of the conference. We invite you all to submit abstracts
for 15+5 minute contributed talks through your respective collaborations
that have received information about abstract contributions to our ML
In case of any questions, please contact email@example.com
Two days of KNL training and optimization sessions being held at NERSC March 6 and 7th.
The training will be presented by Intel experts covering Intel compilers, optimization tools, and libraries and will take place on Tuesday, March 6, 2018.
The following day, there will be a KNL hack-a-thon, with Intel and NERSC experts on hand to help you evaluate the performance of your application and develop an optimization strategy.
The events will be held at LBL’s Shyh Wang Hall (Building 59, CRT) in Room 3101. All sessions will presented online using Zoom but we highly recommend attending in-person if you can.
See https://www.nersc.gov/users/training/events/intel-compilers-tools-and-libraries-training-march-6-2018/ and https://www.nersc.gov/users/training/events/cori-knl-hackathon-march-7-2018/ for details and registration.
Please register for both days if you plan to attend either in person or remotely.
From February 27–March 1, 2018, we will host the ALCF Simulation, Data, and Learning Workshop to help attendees improve their applications on Theta. To register, visit: https://www.alcf.anl.gov/workshops/simulation-data-learning-workshop
The Quantum Computing Summer School at Los Alamos National Laboratory is an immersive 10-week curriculum that includes tutorials from world-leading experts in quantum computation as well as one-on-one mentoring from LANL staff scientists who are conducting cutting-edge quantum computing research. Summer school fellowship recipients will be exposed to the theoretical foundations of quantum computation and will become skilled at programming commercial quantum computers, such as those developed by D-Wave Systems and IBM. Ten students will be awarded a fellowship from LANL that covers travel, living expenses in Los Alamos, and salary, with a fellowship value ranging from $7,500 to $13,000, based on academic rank (junior, senior, 1st year graduate student, etc.).
For more details on applications, see http://quantumcomputing.lanl.gov
The Computational Science Initiative Division at Brookhaven National Laboratory, in partnership with the HEP Center for Computational Excellence (CCE) and the ECP SOLLVE project, will host the first KNL Hackathon on February 26-March 2, 2018. All current and potential users of the Intel Knights Landing-based systems are encouraged to submit an application to participate.
To participate, please submit a team application at www.bnl.gov/knlhackathon2018. Deadline for application is January 5, 2018. All applications will be peer-reviewed, and notification of acceptance will be sent out by January 14, 2018.
For more information, visit www.bnl.gov/knlhackathon2018.
OpenACC, NVIDIA, and the Pittsburgh Supercomputing Center will
provide a three-part online OpenACC course beginning Thursday,
October 19 and continuing on Thursday, October 26 and Thursday,
November 2. The course will consist of lectures and hands-on
exercises. For more information or to register, visit
OLCF users are invited to participate in webinar presented by Michael Wolfe
of NVIDIA titled “Scalable Node Programming with OpenACC” on Wednesday,
September 20, at 1:00 pm ET. For more information and/or to register,
Registration is now open for the Scaling to Petascale Institute, which will be held June 26-30, 2017. The petascale institute is a collaboration between multiple institutions. The purpose of the institute is for people who are developing, modifying, and supporting research projects to enhance their knowledge and skills to scale software to petascale and emerging extreme-scale computing systems. Basic familiarity with Linux, programming, and MPI are recommended. The agenda includes introductory and advanced MPI, OpenMP, scaling, profiling, and debugging, GPU programming, OpenACC, Phi programming, scientific libraries, Parallel I/O, HDF5, Globus, and software engineering.
Continue reading SCALING TO PETASCALE Institute