Home > Active Components > Ampere

Ampere Computing

Ampere Ampere is a semiconductor design company for a new era, leading the future of computing with an innovative approach to CPU design focused on high-performance, energy efficient, sustainable cloud computing. As a pioneer in the new frontier of energy efficient high-performance computing, Ampere is in a leading position driving sustainable computing for the Cloud, AI inferencing, and edge applications.

Ampere Computing brought to market the first credible, merchant Arm-based silicon for general compute. Azure, Google Cloud (GCP), Oracle Cloud Infrastructure (OCI) and others have adopted Ampere's CPUs to deliver Arm-based cloud instances. The one notable exception is AWS, which developed its own Arm chip, called Graviton.

Technology startup Ampere launched AmpereOne microprocessor for data centers, aiming to win a piece of that increasingly competitive market with chips designed to draw less electricity. AmpereOne microprocessors have 192 computing cores. AmpereOnes double the number of cores in rival products from AMD, and triple what Intel offers in its Sapphire Rapids chips.

As Ampere has become so popular in the cloud, it is easy to overlook the architecture of its CPUs and the value they bring to high-performance computing and AI. More AI workloads are run on the CPU versus the GPU. In many AI training deployments, the acceleration capabilities built into the CPU are more than capable of delivering the required performance. For example, In the x86 market, Intel has designed several accelerators to boost training performance significantly. Advanced Matrix Engines (AMX) and Advanced Vector Engines 512 (AVX-512) work with other acceleration engines to remove the requirement for discrete accelerators. Ampere has employed a similar strategy in the Arm ecosystem, designing its CPUs for AI workloads from the ground up. When considering the two elements that drive the need for acceleration – the amount of data and complexity of the model – Ampere has designed a CPU that pushes the need for a GPU further to the right, if you will, on the CPU – GPU continuum. Its native support for the FP16 data format can double the speed of some AI workloads, making it a strong candidate for many mainstream AI use cases.

Ampere Computing is a modern semiconductor company delivering the first cloud native processors built for the sustainable cloud. Ampere designed the industry’s first Cloud Native Processors based on the ARM Aarch64 instruction set architecture (ISA). The Ampere Altra Family delivers up to 128 single threaded, power-optimized computing cores per CPU, each with large dedicated caches for superior performance of cloud native workloads.

Optimized for Cloud

By providing a new level of predictable scale-out performance and efficiency, Ampere is working with leading cloud service providers, OEMs, and an expansive partner ecosystem to deliver Cloud Native Processors that can handle the compute demands of today and tomorrow.

Optimized for AI

Ampere® Altra® Max processors deliver exceptional performance and power efficiency for AI workloads.

Ampere Altra Max is the only cloud processor that currently supports the fp16 data format while supporting fp32, and int8 data formats.

Ampere AltraFinally, Ampere Altra Family CPUs support leading NVIDIA GPUs for heavy workload training or inferencing.

Energy-efficiency

Climate change, government policies, and ethical imperatives are prompting organizations to drive sustainability through their supply chains and data centers.

Environmental, social, and governance (ESG) goals have taken on greater urgency with accelerated global climate change and increasingly limited natural resources.

Scalable and efficient, Cloud Native Processors reduce data center power consumption and physical space requirements—a foundation for rack level efficiency and the means of a truly sustainable future. 

Cloud Native Processors deliver better efficiency at scale than legacy x86 processors, without sacrificing performance.

Ampere and its New Generation of Cloud Datacenter Processors

In 2020, Ampere launched its new generation 80-core Ampere® Altra® processors and in 2021 extended that product family with the 128-core Ampere® Altra® Max processors. 

AmpereOneIn 2023, the company introduced AmpereOne™ processor family with up to 192 cores and support for 128x PCIe Gen5 lanes and 8 channels of DDR5 memory.

 

Ampere® Altra® VS AmpereOne™ Processors

With the addition of AmpereOne to the portfolio, Ampere is transitioning to its own custom CPU core design while remaining ARM ISA compliant. The new product line will provide more options to customers with more cores, higher bandwidth DDR5 memory support, and support for PCIe Gen5 devices.

AmpereOne also introduces new scalability, security, and performance management features. The higher processor count translates to a higher TDP ranging from 250-400W per socket. Ampere will continue to offer the family of Ampere Altra processors, providing customers with plenty of options to suit their workloads and applications.

 

  Ampere ® Altra ® Family AmpereOne ™ Family
Cores From 32 to 128 cores From 136 to 192 cores
L2 Private Cache 1MB/Core 2MB/Core
Memory 8 Channel DDR4 8 Channel DDR5
IO 128 Lanes PCIe Gen4 128 Lanes PCIe Gen5
Usage Power 40-180W 200-350W
Cloud Native Features
  • Single Threaded Cores
  • Consistent Frequency
  • Large Private L2 Cache
  • 2x128b Vector Units, FP16, int16, int8
  • Interrupt & IO Virtualization
  • Bfloat16
  • Performance Consistency
    • Mesh Congestion Management
    • Memory & SLC QoS Enforcement
    • Nested Virtualization
  • Scalable Management
    • Fine Grained Power Management
    • Advanced Droop Detection
    • Process Aging Monitors
  • Security
    • Secure Virtualization
    • Single-Key Memory Encryption
    • Memory Tagging