Leading the Way in High Performance Computing
Developing scientific applications for global issues, such as drug discovery, climate forecasts, and grid management, requires diverse, complex, and often urgent exascale workloads. National laboratories such as SiPearl (Europe), ETRI (Republic of Korea) and MEITY/C-DAC (India) have adopted Arm Neoverse V1 for HPC because it delivers the AI performance, energy efficiency, and design flexibility needed to achieve their goals in a sustainable, economic manner.
Featured News
At AWS Re:Invent 2022, AWS announced the Graviton3E CPU and HPC7g instances targeted at high-performance cloud workloads. HPC7g instances are now in preview and you can request access today.
Nvidia's Grace CPU Superchips are the first Arm Neoverse-based devices designed specifically for HPC, hyperscale and AI workloads, showing what is possible through the tight coupling of Neoverse CPUs as well as high-performance accelerators and memory systems.
Innovations Ignited by Neoverse
Industry leaders share their thoughts and experiences on the advantages of Arm-based technology.
HPC Leaders ETRI and SiPearl Build on Arm
Experts from ETRI and SiPearl describe how Arm Neoverse V1 supports their goal of building exascale-class CPUs for AI and other HPC projects, with state-of-the-art power and performance efficiency.
Arm Powers the World’s Fastest Supercomputer
As HPC enters a new era of technological capabilities, RIKEN and Fujitsu based the Fugaku Supercomputer in Japan on Arm, for performance, efficiency, and scalability.
Arm Neoverse Wins Four 2022 HPCwire Readers' and Editors' Choice Awards
Neoverse V1 CPU
Designed for Performance, Parallelism and Compatibility
Neoverse V1 was designed with two goals in mind: to provide designers with a platform for achieving the impossible while minimizing the time, cost and independent development needed to get there. Features such as Scalable Vector Extension and CMN-700 mesh interconnect, deliver extreme performance while giving designers the flexibility and freedom to experiment. Neoverse V1 designs can be customized, but remain compatible with mainstream OSes, libraries, compilers, middleware and debug and profiling tools.
HPC Use Cases Around the World
National Labs
These national laboratories are pushing the limits of supercomputing in a quest for scientific discovery.
Engineering
Arm-based HPC delivers accelerated CFD and crash-simulations with improved performance for more detailed experimentation and increased accuracy.
Electronic Design Automation
From design to simulation and verification to functional safety, Arm-based HPC provides the performance and efficiency needed in the EDA process.
Energy
Simulation models can be finetuned and iterated upon quickly thanks to reliable software stacks and ecosystems, including compilers, toolchains and math libraries optimized for Arm Neoverse.
Biosciences
Arm-based HPC helps researchers develop therapies to improve the heath of humans, animals and agriculture.
University Research
Arm-based HPC clusters lets universities pursue both computer-science and pure science research.
A Proven Range of Powerful HPC Capabilities
Learn more about Arm’s portfolio of HPC products and solutions and foundational technologies.
Neoverse V1
A revolution in high-performance computing, the Neoverse V1 CPU delivers leading per-core execution and vector performance with SVE.
Corelink CMN-700
Improved system capability, scalability, and bandwidth, and the ability to add high-bandwidth DDR5 and HBM memory sub-systems, and right-size PCIe Gen5 and multi-chip interfaces.
Scalable Vector Extensions
Arm’s Scalable Vector Extensions (SVE) deliver vector-length agnostic performance and programming to HPC. Write once, compile once, deploy forever.
Arm Allinea Studio
A complete suite of high-performance tools for developing Arm-based server and HPC applications.
Armv8-A Architecture
The latest-generation Arm architecture is optimized for rich applications and high-performance operating systems required in complex HPC solutions.
NVIDIA CUDA Support for Arm Neoverse
Optimize a NVIDIA CUDA ML inference application with Arm Forge.
Build Your Future on Arm
Arm DevSummit 2022
Interested in understanding why 48 out of 50 top AWS EC2 customers chose Arm Neoverse-powered Graviton instance? Perhaps it’s our performance gains, cost savings, power efficiency, or world-class security. Or all of the above, and more. See how the experts are developing innovative, scalable solutions faster than ever with frictionless development on Arm.
Resources
Technical White Papers
- Arm Scalable Vector Extensions and application to Machine Learning
- A sneak peek into SVE and VLA programming
- Delivering Superior Throughput for EDA Verification Workloads
News
- AWS Announces Three Amazon EC2 Instances Powered by New AWS-Designed Chips
- Arm recognized among winners of 2022 Gordon Bell Prize
- NVIDIA Unveils Grace ARM-based CPU for giant-scale AI and HPC apps
- Fujitsu selected to deliver Arm Supercharger for World-class research capabilities in Portugal
- SiPearls teams for 6nm HPC chip
- Nimbix announces first multi-cloud HPC platform with support for Arm
Blogs
- Evaluating Applications Using the NVIDIA Arm HPC Developer Kit
- AWS Graviton3 improves Cadence EDA tools performance for Arm
- A case study in vectorizing HACCmk using SVE
- HPC Cloud hackathon summary
- Neoverse V1: A New Approach to HPC
- China’s UCloud expands HPC in the Cloud offerings with Arm Neoverse
- NVIDIA, Ampere Computing Raise Arm 26x in Supercomputing
- Trends to Watch in HPC
- October 18 – 10^18 – Exascale Day, a reason for optimism
- Why Arm’s SVE will bring Vector Computing from HPC to the Edge
- Is the Cloud Ready for HPC Workloads?
Sign up to receive the latest Arm Neoverse and ecosystem news.
Loading...
We will process your information in accordance with our privacy policy.
Take a look at a past Arm Infrastructure newsletter.