Expanding Support for Arm Developers
Opportunities for ARM Developers
NVIDIA’s accelerated computing platform is used to help solve the world’s most challenging computational problems. Today, NVIDIA GPUs not only power some of the world’s largest supercomputers and cloud data centers; they also power edge devices across industries. NVIDIA is expanding support for longtime partner Arm to open new opportunities for developers across an already vibrant ecosystem.
The entire set of NVIDIA tools, libraries, and frameworks will be compatible with the new Arm CPUs and scalable vector extensions (SVE) where applicable.
Software Application Developers
Arm compatibility will be built into the entire set of NVIDIA tools, libraries, and frameworks.
NVIDIA is collaborating with an increasing number of hardware developers to design and validate Arm-based systems with NVIDIA GPUs.
We’re opening up new opportunities in AI by working with system-on-chip (SoC) designers to add GPU compatibility to their products.
NVIDIA Arm HPC Developer Kit
The NVIDIA Arm HPC Developer Kit is an integrated hardware and software platform for creating, evaluating, and benchmarking HPC, AI, and scientific computing applications on a heterogeneous GPU- and CPU-accelerated computing system. The kit includes an Arm CPU, an NVIDIA Ampere A100 Tensor Core GPU, two NVIDIA Bluefield-2 E-Series DPUs, and the NVIDIA HPC SDK suite of tools.
NVIDIA’s HPC solutions feature everything you need to create on the Arm platform.
Comprehensive Suite of Compilers, Libraries, and Tools for HPC Developers
The NVIDIA HPC SDK includes compilers that are optimized for performance on Arm CPUs with vectorization and multi-core support.HPC SDK
Optimized Implementations of Industry-Standard and Domain-Specific Algorithms
Built on top of NVIDIA CUDA®, CUDA-X™ is a collection of libraries that are optimized and available on Arm systems.CUDA-X
CUDA Development Environment for Creating Apps on Arm
The CUDA Toolkit for Arm provides a development environment for creating high-performance, GPU-accelerated applications on Arm.CUDA Toolkit
Debug, Profile, and Develop Applications for NVIDIA GPUs
NVIDIA Nsight™ is a powerful suite of tools that help developers build, debug, profile, and optimize applications on NVIDIA GPUs. These tools are compatible with a wide range of NVIDIA platforms, from multi-GPU workstations and laptops, to embedded devices with a variety of Arm CPUs.Developer Tools
NVIDIA InfiniBand and Ethernet Networking for Arm
NVIDIA® InfiniBand™ and Ethernet networking delivers the highest productivity, enabling Arm-based compute clusters and converged data centers to operate at any scale, while reducing operational costs and infrastructure complexity.NVIDIA Networking
Cloud and Data Center
Optimize your network with industry-leading NVIDIA hardware and software solutions.
Kubernetes on NVIDIA GPUs lets you automate the deployment, maintenance, scheduling, and operation of multiple GPU-accelerated application containers across clusters of nodes with Arm CPUs.NVIDIA BlueField Data Processing Unit
Manage and Monitor GPUs in Cluster Environments
NVIDIA Data Center GPU Manager (DCGM) simplifies GPU administration in the cloud and data center to improve resource reliability and uptime, automate administrative tasks, and drive overall infrastructure efficiency.Data Center GPU Manager
Create Applications and Services on NVIDIA BlueField DPUs
The NVIDIA DOCA SDK for Arm integrates industry-standard open APIs, drivers, libraries, services and prepackaged containers to accelerate development of software-defined networking, storage, and security applications and services for NVIDIA BlueField DPUs.Data Center GPU Manager
Maximize Storage and Network IO
NVIDIA Magnum IO uses Arm-compatible libraries and technologies such as GPUDirect® RDMA, SNAP™, SHARP™, and NCCL to maximize storage and network input/output (IO) performance for multi-GPU, multi-node acceleration.Magnum IO
Data Processing and Analytics Software
RAPIDS™ suite of open-source software libraries and APIs accelerates end-to-end data science and analytics pipelines. An early access version of Server Base System Architecture (SBSA) is planned for RAPIDS release 21.10 for servers based on 64-bit ARM processors.RAPIDS for Data Science
Edge AI and Robotics
High-Performance, Low-Power Computing at the Edge
NVIDIA Jetson™ is the world’s leading embedded AI computing platform with an integrated Arm CPU.Jetson for Edge
Streaming Video, Audio, and Multi-Sensor AI Applications
With NVIDIA’s DeepStream SDK, developers can build seamless streaming pipelines for AI-based data streaming analytics. DeepStream is optimized for video, audio, and image understanding. Its plugins fully support the hardware accelerators found on NVIDIA's Arm-based Jetson platforms.DeepStream SDK
Accelerating Robotic Application Development
NVIDIA Isaac™ accelerates robot development by making it easier to add AI to ROS-based robotics applications. The Isaac GEMs for ROS are hardware accelerated image processing and AI packages that run on and are optimized for Arm-based NVIDIA Jetson AGX Xavier™ systems.Isaac for Robotics
Linux Personal Computer with RTX and AI
Combine Arm CPUs with NVIDIA GeForce® GPUs and Linux for a powerful, RTX and AI enabled personal computer.Get Linux Driver
Real-time AI and imaging for medical devices.
The NVIDIA Clara AGX™ is an AI computer powered by ARM-based NVIDIA Xavier™ and RTX GPUs.Clara AGX
RTX ON, Real-Time Ray Tracing
Simulate the physical behavior of light for immersive experiences with real time global illumination and DLSS. RTX SDKs are now available for Arm.RTX SDK
Join the NVIDIA Developer Program to learn more.Learn More