HIGH PERFORMANCE COMPUTING
HPC innovation in Frankfurt
ROBERT ROE REPORTS ON ANNOUNCEMENTS AND NEW TECHNOLOGY FROM THE ISC HIGH PERFORMANCE CONFERENCE
More than 3,500 people and 164 exhibitors attended the recent ISC High Performance conference in
Frankfurt, a slight increase on the previous year. Artificial intelligence (AI), machine learning (ML) and deep learning (DL) continue to play a big role in the technologies and discussion at the show but there is also excitement about HPC, particularly, with the rise of AMD and Arm in recent months. Both companies were the focus of a lot of the excitement at the conference, as they begin to increase their foothold on the HPC CPU market. At the show Nvidia announced that
it would bring the CUDA programming language to Arm. The company is making available to the Arm ecosystem its full stack of AI and HPC software –
4 Scientific Computing World August/September 2019
which accelerates more than 600 HPC applications and all AI frameworks – by the end the year. Jensen Huang, founder and CEO of Nvidia, said: ‘Supercomputers are the essential instruments of scientific discovery, and achieving exascale supercomputing will dramatically expand the frontier of human knowledge. As traditional compute scaling ends, power will limit all supercomputers. The combination of Nvidia’s CUDA-accelerated computing and Arm’s energy-efficient CPU architecture will give the HPC community a boost to exascale.’ Simon Segars, CEO of Arm, added: ‘Arm
is working with our ecosystem to deliver unprecedented compute performance gains and exascale-class capabilities to Arm-based SoCs. Collaborating with Nvidia to bring CUDA acceleration to the Arm architecture is a key milestone for the HPC community, which is already deploying Arm technology to address some of the world’s most complex research challenges.’ AMD gave several presentations at its booth, including ‘Experience the Exascale Era with AMD at ISC’19’ from AMD’s HPC segment manager for AMD EPYC server processors, Andy Parma. The talk highlighted its HPC architecture and
ecosystem technologies that will be used to power the exascale era of HPC. The company also pushed the partnerships it has formed with many well-known HPC companies including; Dell EMC, HPE, Broadcom, Mellanox, Samsung and Xilinx. Arm was showcasing its new toolset, which was acquired at the end of 2016. Arm is now delivering a full set of debugging and performance tools including Arm DDT, a parallel debugging tool and Arm MAP, a low-overhead profiler, to simplify the task of debugging, profiling and optimising applications running on the Armv8-A architecture. Users can also use Arms C/C++
compiler which is compatible with Arm Forge and Arm Performance Libraries. The Arm C/C++ Compiler includes
support for the C++ 14 standard to improve the speed of server and HPC workloads on a wide range of Arm-based platforms. The company also includes a Fortran
compiler, which has been designed to get the most performance on any 64-bit Arm hardware used for scientific computing and high performance applications.
Storage innovation Storage was another area of developments at ISC this year. Excelero and ThinkParQ announced it was bringing Integrated NVMesh and BeeGFS solution to market in order to boost the efficiency of data centre I/O. The companies announced that they had successfully integrated Excelero’s NVMesh software-defined block storage solution for shared NVMe at local latency, along with ThinkParQ’s leading parallel cluster file system BeeGFS. The companies stressed that early
@scwmagazine |
www.scientific-computing.com
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32
