Story image

NVIDIA adds CUDA support for Arm

19 Jun 2019
Twitter
Facebook

NVIDIA has released support for Arm CPUs, providing the high-performance computing industry with a new path to building energy-efficient, AI-enabled exascale supercomputers.

The full stack of its AI and HPC software, which accelerates more than 600 HPC applications and all AI frameworks, will be available to the Arm ecosystem by year’s end. 

The stack includes all NVIDIA CUDA-X AITM and HPC libraries, GPU-accelerated AI frameworks and software development tools such as PGI compilers with OpenACC support and profilers.

Once stack optimisation is complete, NVIDIA will accelerate all major CPU architectures, including x86, POWER and Arm.

“Supercomputers are the essential instruments of scientific discovery, and achieving exascale supercomputing will dramatically expand the frontier of human knowledge,” says NVIDIA founder and CEO Jensen Huang. 

“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.”

Arm CEO Simon Segars adds, “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.”

According to the Green500 list released today, NVIDIA powers 22 of the world’s 25 most energy-efficient supercomputers.

Key factors making this possible are: 

  • the ability of NVIDIA GPU-powered supercomputers to offload heavy processing jobs to more energy-efficient parallel processing CUDA GPUs;
     
  • NVIDIA’s collaboration with Mellanox to optimize processing across entire supercomputing clusters; and
     
  • NVIDIA’s invention of SXM 3D-packaging and NVIDIA NVLink interconnect technology, which allows for extremely dense scale-up nodes.

NVIDIA’s support for Arm-based HPC systems builds on more than 10 years of collaboration.

NVIDIA uses Arm for several of its system-on-a-chip products available for portable gaming, autonomous vehicles, robotics and embedded AI computing.

World leaders of the HPC industry and Arm ecosystem, including supercomputing centres and systems providers and system-on-a-chip manufacturers, have voiced their support.

“Both NVIDIA and Arm leverage technologies that offer high performance computing customers greater levels of energy efficiency,” says HPE vice president and HPC and AI general manager Bill Mannel. 

“NVIDIA’s support for Arm complements our latest developments on the HPE Apollo 70, an Arm-based, purpose-built HPC system, and now, NVIDIA GPU-enabled. With the HPE Apollo 70 supporting a 2U GPU tray and multiple energy-efficient cooling options, we can further help the HPC industry address increasingly unsustainable levels of power consumption.”

Marvell president and CEO Matt Murphy adds,  “We are excited to work with NVIDIA and server OEMs to couple the CUDA-X platform and NVIDIA GPUs with the Marvell ThunderX2 family of server processors. The combination of ThunderX2’s best-in-class 64-bit Armv8 performance and NVIDIA GPUs offers breakthrough levels of energy efficiency and application performance, enabling world-class HPC and AI solutions for exascale computing.”

Story image
11 Nov
Unpopular opinion: The software monolith is wrongly maligned
We’re led to believe microservices are modern and monoliths are legacy - but it’s not that easy, writes Segment’s Alexandra Noonan and Calvin-French Owen.More
Story image
14 Nov
DXC Technology & VMware team up on IaC cloud platform
“By combining VMware’s hybrid cloud offerings with DXC cloud services and industry expertise, DXC Managed Multi-Cloud Services powered by VMware gives IT the ability to rapidly deploy a universal management experience across all cloud environments."More
Story image
16 Oct
Mellanox takes NVMe/TCP and RoCE fabrics to new heights
ConnectX SmartNICs and BlueField I/O processing units (IPUs) are first 200Gb/s adapters to support NVMe-oF over TCP and RoCE as well as IPsec and TLS security acceleration.More
Story image
22 Oct
Microsoft & SAP to accelerate SAP S/4HANA adoption on Azure
The two companies will work alongside each other and a global network of system integrators to offer bundles that provide unified reference architectures, road maps and market-approved journeys so that customers have a clearer path to cloud.More
Story image
07 Nov
SoftwareONE completes strategic acquisition of BNW Consulting
SoftwareONE Holding AG has announced that it has acquired BNW Consulting, and states the strategic decision will enable the company to extend its SAP capabilities on public cloud hyperscalers. More
Story image
31 Oct
AI capabilities power global IoT adoption
Artificial intelligence is the key to realising value from internet of things (IoT) initiatives, according to a recent survey of global business leaders.More