News highlights
- Arm extends its platform breadth to embrace manufacturing silicon products for the first time, providing the broadest alternative of compute throughout IP, Arm Compute Subsystems (CSS) and silicon
- Introducing the first Arm-designed information heart CPU, the Arm AGI CPU, for agentic AI infrastructure, delivering greater than 2x efficiency per rack in contrast with x86 platforms*
- Developed with lead associate Meta, with different prospects and main ODMs dedicated for manufacturing, the Arm AGI CPU is backed by robust assist from the worldwide ecosystem
Cambridge, England – Mar. 24, 2026 – Arm Holdings plc (NASDAQ: ARM) in the present day announced the subsequent evolution of the Arm compute platform, extending into manufacturing silicon products for the first time in the company’s historical past. This begins with the launch of the Arm AGI CPU, an Arm-designed CPU for AI information facilities, constructed to deal with a rising class of agentic AI workloads.
For greater than three a long time, the {industry} has innovated on the Arm compute platform to ship scalable, power-efficient computing throughout tons of of billions of units. As AI transforms world computing infrastructure, companions throughout the ecosystem are asking for tactics to deploy Arm expertise at scale. In response, Arm is increasing its platform technique past IP and Compute Subsystems (CSS) to embrace Arm-designed silicon products – giving companions the broadest set of choices to construct on Arm and enabling quicker innovation throughout the AI ecosystem.
“AI has fundamentally redefined how computing is built and deployed. Agentic computing is accelerating that change,” stated Rene Haas, CEO, Arm. “Today marks the next phase of the Arm compute platform and a defining moment for our company. With the expansion into delivering production silicon with our Arm AGI CPU, we are giving partners more choices all built on Arm’s foundation of high-performance, power-efficient computing, to support agentic AI infrastructure at global scale.”
Agentic AI is reshaping AI infrastructure, driving extra demand for CPUs
The rise of AI brokers is driving a serious inflection level in world computing. As AI shifts from coaching fashions to deploying constantly operating brokers that motive, plan and act, the quantity of tokens generated throughout AI programs is quickly growing and requires considerably extra CPUs to deal with reasoning, coordination and information motion.
As organizations scale agent-driven purposes, information facilities are anticipated to require greater than 4x the present CPU capability per GW* — driving the necessity for considerably extra compute inside the similar energy envelope. This is driving demand for a brand new class of CPUs designed for AI-scale infrastructure — delivering the efficiency wanted to maintain excessive token throughput, the effectivity required to function inside real-world energy constraints and a simplified structure constructed with out the overhead and complexity of x86 processors.
Extending the Arm platform into manufacturing silicon
To assist companions transfer quicker in this new surroundings, Arm is introducing the Arm AGI CPU, which is anticipated to be the muse for agentic information facilities. The enlargement into silicon products offers the ecosystem with larger flexibility in how they construct and deploy Arm-based infrastructure — whether or not licensing Arm IP, adopting Arm CSS, or deploying Arm-designed silicon.
The Arm AGI CPU delivers:
- Performance: Up to 136 Arm Neoverse V3 cores per CPU, delivering main efficiency per core, SoC, blade and rack*, with 6GB/s reminiscence bandwidth per core at sub-100ns latency.
- Scale: 300-watt TDP with a devoted core per program thread allows deterministic efficiency underneath sustained load, eliminating throttling and idle threads.
- Efficiency: Supports high-density 1U server chassis that helps air-cooled deployments with up to 8,160 cores per rack, and liquid-cooled programs delivering 45,000+ cores per rack.
These capabilities translate into larger workload density, improved accelerator utilization and extra usable compute inside present energy envelopes — vital benefits as AI infrastructure scales. The Arm AGI CPU delivers greater than 2x efficiency per rack versus x86 CPUs, enabling up to $10B in CAPEX financial savings per GW of AI information heart capability*.
Broad ecosystem assist for Arm AGI CPU
Meta serves as the lead partner and co-developer, leveraging Arm AGI CPU to optimize infrastructure for its household of apps and dealing alongside Meta’s personal customized silicon, known as Meta Training and Inference Accelerator (MTIA), enabling extra environment friendly orchestration in large-scale AI programs. Arm and Meta are dedicated to collaborating throughout a number of generations of the Arm AGI CPU roadmap.
“Delivering AI experiences at global scale demands a robust and adaptable portfolio of custom silicon solutions, purpose-built to accelerate AI workloads and optimize performance across Meta’s platforms,” stated Santosh Janardhan, head of infrastructure, Meta. “We worked alongside Arm to develop the Arm AGI CPU to deploy an efficient compute platform that significantly improves our data center performance density and supports a multi-generation roadmap for our evolving AI systems.”
Alongside Meta, Arm has confirmed extra industrial momentum with companions together with Cerebras, Cloudflare, F5, OpenAI, Positron, Rebellions, SAP, and SK Telecom. These prospects will deploy the Arm AGI CPU for key agentic CPU use-cases together with accelerator administration, management aircraft processing, and cloud and enterprise-based API, process and utility internet hosting.
To speed up this ramp, Arm is partnering with lead OEMs and ODMs together with ASRock Rack, Lenovo, Quanta Computer, and Supermicro, with early programs accessible now and broader availability anticipated in the second half of the 12 months.
More than 50 main corporations throughout hyperscale, cloud, silicon, reminiscence, networking, software program, system design and manufacturing are supporting the enlargement of the Arm compute platform into silicon. That momentum contains {industry} leaders reminiscent of AWS, Broadcom, Google, Marvell, Micron, Microsoft, NVIDIA, Samsung, SK hynix and TSMC, alongside many others.
A brand new period for the Arm compute platform
For a long time, the {industry} has constructed on the Arm compute platform by means of its industry-leading IP and, extra lately, Arm CSS, grounded in a basis of high-performance, power-efficient computing. The enlargement into manufacturing silicon with the Arm AGI CPU marks the subsequent part of that evolution, extending Arm into information heart silicon and bringing its power-efficient structure to AI infrastructure at scale.
Ecosystem assist:
Click here to view supporting quotes from greater than 50 main ecosystem gamers:
Advantest, Altera, AMI, Amazon Web Services, Amkor, Arista, ASRock Rack, ASE Holdings, Broadcom, Bristol Centre for Supercomputing, Cadence, Canonical, Cerebras, Cisco, Cloudflare, Databricks, F5, Furiosa, GitHub, Google Cloud, Hugging Face, Intel Foundry, Lenovo, Marvell, MediaTek, Meta, Micron, Microsoft Azure, MongoDB, Nutanix, NVIDIA, NXP, OpenAI (OAI), Open Compute Project, Oracle Cloud Infrastructure (OCI), Positron, Red Hat, Rebellions, Redis, Samsung, SAP, Siemens, SK hynix, SK Telecom, Snowflake, Socionext (SNI), ST Micro, StatsChipPac, SUSE, Supermicro, Synopsys, TSMC, VMWare.
Supporting quotes embrace:
AWS
“Back in 2009, I first wrote about Arm becoming the next generation general purpose server CPU. Over the last decade, we’ve partnered closely with Arm in building Graviton here at AWS, and it’s been a remarkable success – the majority of compute capacity AWS added to our fleet in 2025 was powered by Graviton. This collaboration has been great for both companies, and Graviton continues to deliver better price/performance for our customers. Here’s to celebrating with Arm and to our continued partnership delivering big for customers.” – James Hamilton, SVP and Distinguished Engineer, Amazon
Broadcom
“As Broadcom builds the world’s most capable XPU and networking solutions for hyperscalers at the heart of the AI transformation, our partnership with Arm has enabled us to move with unmatched intent and speed. By building on Arm’s power-efficient technology leadership, we continue to deliver market-leading innovations that scale the most complex AI infrastructure. The new Arm AGI CPU will further unlock the Arm ecosystem for a broad range of customers, creating significant new opportunities for everyone building the future of intelligence on Arm.” – Charlie Kawwas, Ph. D., President, Semiconductor Solutions Group, Broadcom Inc.
“At Google Cloud, we are committed to delivering compute infrastructure that allows customers to maximize performance, reduce costs, and meet sustainability goals. Google’s custom Axion CPUs, built on the Arm architecture, provide organizations with the energy efficiency and scalability required to support modern cloud-native and AI-driven workloads. CPU innovation with Arm’s new AGI CPU can unlock a new generation of purpose-built compute capabilities across the industry.” – Amin Vahdat, SVP & Chief Technologist, AI Infrastructure, Google
Marvell
“As AI workloads grow in scale and complexity, advances in compute, connectivity, and data center infrastructure must evolve to support the insatiable demand for AI. The new AGI CPU provides more options for the Arm ecosystem and broadens the accessibility of compute to a new set of customers. Marvell brings leadership in custom compute, end-to-end connectivity, and accelerated infrastructure technologies that power modern data centers, and we are proud to partner with Arm to enable the next generation of AI infrastructure.” – Matt Murphy, Chairman and CEO, Marvell
Micron
“As AI systems become more autonomous and data‑intensive, performance is no longer defined by compute alone, but by how efficiently compute and memory work together. That’s why our longstanding partnership with Arm is so important. Today’s announcement of the Arm AGI CPU is a significant milestone, opening new opportunities for system‑level innovation when paired with Micron’s leading memory and storage portfolio.” –Sanjay Mehrotra, Chairman, President and CEO, Micron Technology
Microsoft Azure
“Arm’s AGI CPU and ongoing CSS investments strengthen the Arm ecosystem for the next wave of AI and cloud workloads. Microsoft’s Azure Cobalt family of CPUs, built on Neoverse CSS, is a key part of how we optimize every layer of our stack to deliver high performance and efficient infrastructure for our customers.” –Rani Borkar, President, Azure Hardware Systems and Infrastructure, Microsoft
NVIDIA
“Our partnership began nearly two decades ago and since then, Arm’s adaptability has made it possible for us to integrate Arm across all of our platforms and for all different phases of AI. Together we’re creating one seamless platform, from cloud to edge to AI factories. We look forward to building the future with Arm.” – Jensen Huang, Founder and CEO of NVIDIA.
Samsung
“As AI workloads rise, performance gains will increasingly depend on tight co-optimization across logic, memory, and advanced packaging technologies. Samsung’s broad semiconductor capabilities and long-term collaboration with compute leaders like Arm position us to support next-generation AI platforms at scale. Purpose-built AI compute platforms like the Arm AGI CPU create new opportunities for deeper collaboration across silicon design, memory integration, and manufacturing innovation with cutting-edge process technology, making this an important milestone for the ecosystem.” – Young Hyun Jun, Vice Chairman and CEO of Samsung Electronics
SK hynix
“SK hynix has a long history of collaborating with industry leaders to support high-performance computing and accelerate innovation for global customers. As AI datacenters evolve, platforms designed for AI workloads must be supported by advanced memory technologies that deliver the capacity and bandwidth required for modern applications. The introduction of purpose-built AI compute with the Arm AGI CPU is an important milestone for the ecosystem, and we look forward to continued partnership with Arm to advance the next generation of AI-driven infrastructure.”- Noh-Jung Kwak, CEO, SK hynix
TSMC
“Datacenter AI workloads are evolving, and we are seeing more demand than ever for efficient, scalable compute, driving deeper collaboration across every layer of the ecosystem—from silicon design to manufacturing innovation. As the Arm AGI CPU manufacturer, we are excited to support this breakthrough platform. By leveraging our advanced 3nm process technology, the new Arm AGI CPU delivers significant performance and energy efficiency and is expected to play an important role in enabling the next generation of AI infrastructure across the datacenter ecosystem.” – Dr. Kevin Zhang, SVP and Deputy Co-COO at TSMC
About Arm
Arm is the {industry}’s highest-performing and most power-efficient compute platform with unmatched scale that touches 100% of the linked world inhabitants. To meet the insatiable demand for compute, Arm is delivering superior options that enable the world’s main expertise corporations to unleash the unprecedented experiences and capabilities of AI. Together with the world’s largest computing ecosystem and 22 million software program builders, we’re constructing the way forward for AI on Arm.
All data is supplied “as is” and with out guarantee or illustration. This doc could also be shared freely, attributed and unmodified. Arm is a registered trademark of Arm Limited (or its subsidiaries or associates). All manufacturers or product names are the property of their respective holders. © 1995-2026 Arm Limited.
Forward-looking statements
This press launch comprises forward-looking statements inside the that means of Section 27A of the Securities Act of 1933, as amended, and Section 21E of the Securities Exchange Act of 1934, as amended, and as outlined in the Private Securities Litigation Reform Act of 1995. All statements aside from statements of historic truth could possibly be deemed forward-looking statements, together with with out limitation, statements relating to our progress alternatives and platform enlargement, alternatives arising from the continued adoption of synthetic intelligence (AI) applied sciences, together with the expansion of AI information facilities and agentic AI; market and {industry} traits; our TAM expectation, enlargement and our being effectively positioned to deal with such expanded alternative; and our expectations for brand spanking new AI information heart capability. In some instances, you’ll be able to determine forward-looking statements as a result of they comprise phrases reminiscent of “may,” “might,” “will,” “could,” “would,” “should,” “expect,” “is/are likely to,” “intend,” “plan,” “objective,” “anticipate,” “believe,” “estimate,” “predict,” “potential,” “target,” “continue,” “ongoing” or comparable phrases or phrases, or the destructive of those phrases or phrases. These statements contain identified and unknown dangers, uncertainties and different essential elements which will trigger Arm’s precise outcomes, ranges of exercise, efficiency or achievements to be materially totally different from the knowledge expressed or implied by these forward-looking statements. There are many elements that would trigger or contribute to such variations, together with, however not restricted to, any of the next: Arm’s dependence on the semiconductor and electronics industries and the demand for the products of its prospects; Arm’s dependence on the compatibility of its products with the manufacturing and design processes of its prospects; Arm’s improvement of compute subsystems, chiplets, or full System-on-a-Chip (SoC) options in addition to different extra built-in compute products; Arm’s reliance on third events to market and promote chips and finish products incorporating its products, in addition to add worth to its licensed products; Arm’s dependence on a restricted variety of prospects for a good portion of its income; the lack of any of Arm’s senior administration personnel or a number of key staff or Arm’s incapacity to entice and retain certified personnel; Arm’s capability to adequately fund its analysis and improvement efforts; dangers associated to the provision of improvement instruments, programs software program, digital design automation instruments and working programs appropriate with its structure; Arm’s capability to defend its proprietary products and its model, and the prices of defending such mental property rights, notably because of litigation; Arm’s capability to confirm royalty quantities owed to it underneath its licensing agreements; dangers associated to overseas change fluctuations; modifications in Arm’s efficient tax charge; dangers related to natural progress or progress from strategic investments or acquisitions Arm makes, and the chance of failing to successfully handle its progress; dangers related to the gradual improvement of the marketplace for Arm’s connectivity, system and information administration platform; the opportunity of cyberattacks, breaches of Arm’s safety controls and unauthorized entry to its information or a buyer’s information; Arm’s capability to fulfill information safety, safety, privateness or different government- and industry-specific necessities; dangers related to the pursuits of SoftBank Group Corp., Arm’s controlling shareholder, conflicting with the pursuits of different holders of Arm’s atypical shares and American depositary shares; and results of worldwide basic financial circumstances, political elements, battle or hostility, pandemics and different occasions exterior of Arm’s management and people mentioned in Arm’s Annual Report on Form 20-F for the fiscal 12 months ended March 31, 2025, filed with the Securities and Exchange Commission on May 28, 2025. Any forward-looking assertion in this press launch speaks solely as of the date hereof, and Arm doesn’t undertake any obligation to replace any forward-looking assertion to replicate occasions or circumstances after the date of this press launch besides as required by relevant legislation. Arm cautions that you shouldn’t place undue reliance on any of Arm’s forward-looking statements.
*Based on estimates.
Media
Arm External Communications
Global-PRteam@arm.com
Investors
Arm Investor Relations
Investor.Relations@arm.com
