OVERVIEW

Best-in-Class Performance
from the Cloud to Edge with 快猫视频 Neoverse

快猫视频 Neoverse is a family of infrastructure-class processors and compute subsystems designed for high-performance, power-efficient computing from cloud to edge. With performance-first V-Series, scalable N-Series, and efficient E-Series CPUs, Neoverse targets workloads including HPC, AI/ML, 5G, cloud, and networking. It delivers industry-leading performance per watt, support for confidential compute, and broad scalability across modern infrastructure deployments.

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 Resource

快猫视频 Cloud to Edge report - 快猫视频 Neoverse Enables Leading Cloud Performance and Cost Efficiency with AWS Graviton4

Cloud Efficiency Proven with 快猫视频 Neoverse

Signal65’s Lab Insight shows that AWS Graviton4—built on 快猫视频 Neoverse—leads in both performance and efficiency, beating x86 platforms on every workload tested. See why leading cloud providers trust 快猫视频 for scalable, power-efficient compute.

快猫视频 Neoverse Cloud-to-Edge Workload Positioning

Neoverse family image
PRODUCTS

Workload-Driven Performance?

Neoverse V-Series

Neoverse V-Series CPUs offer the highest overall performance of any Neoverse CPUs. They perform exceptionally well on cloud, HPC ?and AI/ML-driven applications.
Built for AI/ML and HPC
 
Neoverse V-Series include high-performance floating-point and vector instruction support, with features like SVE/SVE2, Bfloat16, and Int8 MatMul delivering strong HPC and AI/ML application performance.
Outstanding Cloud Application Performance
 
Neoverse V3 supports the industry’s largest private L2 cache per core, at 3MB. This large L2 cache lets Neoverse V3 outperform competitive CPUs on workloads from database, to enterprise java, to machine learning.
Extending Cloud Security
 
Neoverse V3 supports 快猫视频 Confidential Computing Architecture, which allows Neoverse V3 cores to fully encrypt data while use in memory. This offers the highest level of security for cloud computing.

Neoverse N-Series

The Neoverse N-Series CPUs offer the industry-leading performance-per-watt and serve a broad set of use cases, including cloud, telco, networking, and edge.
Extending Performance-per-Watt Leadership
 
Neoverse N3 can support up to 32-cores in as little as 40W TDP, and offers 20% better performance/watt per-core compared to Neoverse N2.
ML Excellence for N-Series
  
With an largest-in-class private 2MB L2 cache per-core, Neoverse N3 delivers 196% more performance on Machine Learning (XGBoost) compared to Neoverse N2.
More Powerful DPUs and Networking
 
N-Series CPUs are a popular choice to power Data Processing Units (DPUs), which handle system networking, storage, and security services. For data compression, the latest N3 CPU outperforms N2 by 22%.
Processors Designed and Optimized for a Scalable Cloud-to-Edge Infrastructure

Neoverse N3

Performance-per-watt optimized for hyperscale, 5G, enterprise networking, and infrastructure edge workloads.
  • 20% greater performance-per-watt efficiency compared to Neoverse N2.
  • 2MB L2 cache option offers nearly 3x performance gains on ML workloads.

Neoverse V3

The first 快猫视频v9.2 Neoverse CPU to support the 快猫视频 Confidential Compute Architecture.
  • Highest single-thread performance for cloud, HPC, and AI/ML workloads.
  • Supports up to 3MB private L2 cache per core.
  • The perfect foundation for AI accelerator development.

Neoverse V3AE

First 快猫视频v9.2 Neoverse CPU with safety enhancements for automotive markets.?
  • Highest single-thread performance for AI/ML workloads and automotive markets.
  • Supports up to 3MB L2 cache per core.
  • Performance to meet the needs of complex workloads for autonomous vehicles and advanced driver-assistance systems in future generations of software-defined vehicles.

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.
  • 快猫视频's first V-series core with 快猫视频v9 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.
  • 快猫视频’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.
  • 快猫视频v9 introduces key features for performance (SVE2) and security (MTE).
See All
快猫视频 AGI CPU logo

Product deep dive

Explore the technical details of the 快猫视频 AGI CPU, from individual CPU cores to rack-scale economics and server providers.

See product details
SUBSYSTEM

快猫视频 Neoverse Compute Subsystems (CSS)

快猫视频 Neoverse Compute Subsystem (CSS) are 快猫视频 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
快猫视频 total design ecosystem

快猫视频 Total Design

快猫视频 Total Design is an ecosystem of industry leaders collaborating to accelerate and simplify the development of 快猫视频 Neoverse CSS-based systems. It provides partners with preferential access to 快猫视频 Neoverse CSS, pre-integrated IP and EDA tools, design services, foundry support, and commercial software and firmware support.

Learn More
USE CASES

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

快猫视频 Partners are Redefining Cloud Performance

resources
RESOURCES

The Latest Neoverse News and Resources

Key Takeaways

  • 快猫视频 Neoverse delivers scalable compute for infrastructure workloads from cloud to edge, including 5G, AI/ML, and HPC.
  • The V-Series offers maximum per-core performance and support for confidential computing and advanced vector extensions.
  • The N-Series provides high-performance per watt for scale-out use cases such as DPUs, networking, and edge servers.
  • The E-Series supports high-throughput, low-power processing for constrained networking environments.
  • Neoverse Compute Subsystems (CSS) and the 快猫视频 Total Design ecosystem accelerate the development of custom silicon with pre-validated IP and tools.

Stay Ahead in Cloud Infrastructure

Monthly insights on price/performance, energy efficiency, and real?world workloads on 快猫视频—no spam.