Best-in-Class Performance from the Cloud to Edge with Arm Neoverse

Global infrastructure is changing rapidly to accommodate growing workloads and increasing performance demands. Optimizable for the cloud, edge, and 5G networks, Arm Neoverse delivers the speeds, energy efficiency, performance per watt and performance per dollar needed for tomorrow’s infrastructure and its customers.

 

The Arm Neoverse family is designed to target the full breadth of the Infrastructure market.

Neoverse V-Series: Maximum Performance

Based around a performance-first CPU, Neoverse V-series delivers maximum per core performance for systems running demanding compute- and memory-intensive applications.

Use Cases Include:
High performance computing (HPC), HPC in the cloud and AI/ML-accelerated workloads.
Neoverse N-Series: Scale Out Performance

Provides a balanced CPU design optimized to deliver both performance per watt and performance per dollar.

Use Cases Include:
Scale-out cloud, enterprise networking, smartNICs/DPUs and custom ASIC accelerators, 5G infrastructure and power and space-constrained edge locations.
Neoverse E-Series: Efficient Throughput

Supports high data throughput with minimal power consumption

Use Cases Include:
Networking data plane processor, 5G deployments for low power gateways.
Featured News

NVIDIA announces details behind its plans for the Arm Neoverse-based NVIDIA Grace CPU Superchip.

Read Blog

Arm Neoverse Cloud-to-Edge Workload Positioning

Neoverse

Workload-Driven Performance 

Neoverse V-Series

Neoverse V1 offers the highest overall performance of any Neoverse CPUs. It performs exceptionally well on floating-point and vector-driven workloads commonly found in HPC and AI/ML-driven applications.
1.8x More Vector Workloads
 
Neoverse V1 with SVE delivers 1.8x more vector performance across a range of HPC kernels compared to Neoverse N1.
2x Better Floating-point Performance
 
Neoverse V1 with SVE delivers 512bits of vector processing per core, doubling the capability over Neoverse N1 with NEON.
4x Better Machine Learning Performance
 
New Int8 Matrix Multiplication instruction on Neoverse V1 offers up to 4x the ML processing capability of Neoverse N1.

Neoverse N-Series

The Neoverse N1 and N2 offer the broadest range of workload performance flexibility. Neoverse N2 performs well on cloud-based workloads like NGINX but is also very effective for 5G-edge applications, such as DPDK L3 forwarding.
1.4x More IPC on the SPECint®2006 Benchmark
 
On an unloaded system with all CPU resources available to a single thread, Neoverse N2 delivers +40% more IPC than Neoverse N1 on the SPECint2006 benchmark.
1.3x Higher Throughput on NGINIX Application
 
When configured as a web server or a reverse proxy server, Neoverse N2 delivers 30% higher transaction throughput over Neoverse N1 on the popular NGINIX application.
1.2x More Throughput on DPDK L3 Fwd
 

On DPDK L3 forward packet processing the Neoverse N2 core delivers 20% more throughput than Neoverse N1.

Processors Designed and Optimized for a Scalable Cloud-to-Edge Infrastructure

Neoverse V2

A New Benchmark for Cloud Computing, HPC, and ML Performance.
  • With an enhanced pipeline and up to 2MB L2 cache per core, Neoverse V2 can deliver 2x the performance of Neoverse V1 on cloud and ML applications.
  • Arm's first V-series core with Armv9 features like memory tagging extension (MTE) and performance defined power (PDP).

Neoverse V1

A performance-first tier targeting HPC, HPC in the Cloud and AI/ML-accelerated applications.
  • Arm’s first SVE implementation for the HPC market, with 2x floating and 4x ML uplift over Neoverse N1.
  • Expands market-leading performance with 50% IPC uplift over Neoverse N1.

Neoverse N2

Leading performance efficiency for cloud-to-edge infrastructure.
  • Market leading scalability and versatility.
  • Significant 40% IPC performance improvement over Neoverse N1.
  • Armv9 introduces key features for performance (SVE2) and security (MTE).

Neoverse N1

Accelerating the transformation to a scalable cloud to edge infrastructure.
  • Revolutionary compute performance.
  • Platform features specific to infrastructure.
  • Designed for extreme range of scale and diversity of compute.

Neoverse E1

Empowering the infrastructure to meet next-generation throughput demands.
  • Intelligent design for highly efficient throughput. 
  • Fully leverages diverse Arm software ecosystem. 
  • Highly scalable throughput for edge-to-core data transport.

Arm Neoverse Compute Subsystems (CSS)

Arm Neoverse Compute Subsystem (CSS) are Arm Neoverse platforms delivered to partners as fully validated, PPA-optimized, customizable subsystems. Neoverse CSS lets partners focus their design resources on developing market-differentiated specialized silicon, offering them an accelerated path to production silicon with leading-edge performance and technology.

Learn More
Industry Solutions

Support for a Broad Range of Infrastructure Workloads

Cloud Computing

Cloud customers are experiencing up to 40% improved price performance over comparable traditional architecture-based instances on a broad range of workload.

Learn More

High-Performance Computing (HPC)

HPC researchers are exploring the scale-out performance of Neoverse on computational fluid dynamics, medical research, oil & gas exploration and other computationally demanding workloads.

Learn More

5G

To deliver on performance and versatility, 5G requires a more complex and robust infrastructure. Arm delivers technology for building faster, low-latency 5G networks.

Learn More

Arm Partners are Redefining Cloud Performance