Redefining Mobile Experiences with AI-Optimized Arm CSS for Client and New Arm Kleidi Software
News highlights
- New compute solution, Arm Compute Subsystems (CSS) for Client, brings together Armv9 benefits with validated and verified production ready implementations of new Arm CPUs and GPUs on 3nm process nodes to enable silicon partners to rapidly innovate and speed time to market
- AI-optimized Arm CSS for Client with next generation Cortex-X CPU, delivering highest year-on-year IPC uplift resulting in a 36% increase in performance; new Immortalis GPU brings a 37% uplift in graphics performance
- New KleidiAI software integrates with popular AI frameworks for seamless developer experiences; KleidiAI with Arm CSS dramatically improves performance of computing applications by leveraging a wide range of Arm’s acceleration technologies (NEON, SVE2 and SME2)
With power efficiency in our DNA, the Arm platform is providing the foundation for the next wave of computing demands as the AI era accelerates. As AI models continue to rapidly evolve, we’re seeing that software begins to outpace hardware which means additional innovation is required at all levels of the compute stack. To meet these growing demands, we’re evolving our solution offering to gain the maximum benefits of leading process nodes and announcing the newest Arm compute solution for AI smartphones and PCs – Arm Compute Subsystems (CSS) for Client.
Arm CSS for Client provides the performance, efficiency and accessibility to deliver leading AI-based experiences and makes it easier and faster for our silicon partners to build Arm-based solutions and get to market quickly. CSS for Client provides the foundational computing elements for flagship SoCs and features the latest Armv9.2 CPUs and Immortalis GPUs, as well as production ready physical implementations for CPU and GPU on 3nm and the latest Corelink System Interconnect and System Memory Management Units (SMMUs).
Unprecedented CPU and GPU performance and efficiency
CSS for Client delivers a step change in platform capabilities to continue pushing the boundaries of premium mobile experiences. This is the fastest Arm compute platform addressing demanding real-life Android workloads with greater than 30 percent increase on compute and graphics performance and 59 percent faster AI inference for broader AI/ML and computer vision (CV) workloads.
At the heart of CSS for Client is Arm’s most performant, efficient and versatile CPU cluster ever for maximum performance and power efficiency. The new Arm Cortex-X925 delivers the highest year-on-year performance uplift in the history of Cortex-X. Taking advantage of the leading edge 3nm process nodes, assuming a 3.8GHz clock rate and maximum cache size, the result is a massive 36 percent increase in single-thread performance when comparing to 2023 smartphone flagship 4nm SoCs. For AI, Cortex-X925 provides an incredible 41 percent performance uplift to dramatically improve the responsiveness of on-device generative AI, like large language models (LLMs).
The push for leading-edge performance is combined with leading-edge efficiency through our new Arm Cortex-A725 CPU, which delivers a 35 percent improvement in performance efficiency to target AI and mobile gaming use cases. This is supported by a refreshed Arm Cortex-A520 CPU and an updated DSU-120 that provide power efficiency and scalability improvements for consumer devices that adopt the latest Armv9 CPU clusters. Learn more about the new Armv9 CPUs in this blog.
The new Arm Immortalis-G925 GPU, which is our most performant and efficient GPU to date, delivers 37 percent more performance across a wide range of leading mobile gaming applications, as well as 34 percent more performance when measured over multiple AI and ML networks. While Immortalis-G925 is for the flagship smartphone market, the highly scalable new GPU family, including Arm Mali-G725 and Mali-G625 GPUs, targets a broad range of consumer device markets, from premium mobile handsets to smartwatches and XR wearables. Learn more about Arm’s new GPUs in this blog.
Optimizing software for outstanding developer innovation
We are relentlessly focused on millions of developers worldwide, ensuring they have access to the performance, tools and software libraries required to create the next wave of AI-enabled applications. To enable developers to land these innovations quickly at the highest performance, we’re introducing Arm Kleidi, which includes KleidiAI for AI workloads and KleidiCV for computer vision applications. KleidiAI is a set of compute kernels for developers of AI frameworks, providing them with frictionless access to the best performance possible on Arm CPUs, across a wide range of devices, with support for key Arm architectural features such as NEON, SVE2 and SME2. KleidiAI integrates with popular AI frameworks, such as PyTorch, Tensorflow and MediaPipe, with a view to accelerating the performance of key models including Meta Llama 3 and Phi-3. It is also backwards and forwards compatible to ensure Arm is future fit as we bring additional technologies to market. Learn more about Arm Kleidi in this blog.
The compute platform for the future of AI
Through the unique combination of leading-edge CPU and GPU technologies, production ready physical implementations and continuous software optimizations, CSS for Client combined with Kleidi software will provide the compute platform for the future of AI, a future that is built on Arm.
Supporting partner quotes
Intel Foundry Services:
“Intel Foundry is deeply engaged with Arm, and this announcement demonstrates progress on the Arm Client. We are collaborating closely on leading-edge technology nodes, including Intel 18A, to provide best-in-class power, performance, and area metrics and enable next-generation mobile SoC products based on Arm’s new Compute Subsystems (CSS) for Client.” – Suk Lee, Vice President and General Manager of the Ecosystem Technology Office, Intel Foundry Services
MediaTek:
“MediaTek is committed to supporting the latest Armv9 Cortex-X925 CPU and Immortalis-G925 GPU Client solution in our next generation flagship chipset, Dimensity 9400, later this year. As part of our longstanding relationship with Arm, we will continue to work together to enable the future of Computing technology as it accelerates in features and capabilities.” – JC Hsu, Corporate Senior Vice President at MediaTek
Samsung Electronics:
“GenAI capabilities embedded in mobile devices are in major demand amongst customers, requiring top-tier silicon technologies integrated with leading computing solutions. Combining Arm’s Cortex-X925 CPU solutions with Samsung Foundry’s latest 3nm GAA process node delivers on this demand. Our long-standing partnership with Arm allowed for early and tight collaboration in the areas of DTCO and PPA maximization for an on-time silicon delivery that hit performance and efficiency demands.” – Jongwook Kye, Executive Vice President and Head of Foundry Design Platform Development, Samsung Electronics
Samsung Electronics:
“Samsung and Arm have consistently challenged the status quo and pushed the boundaries of what is possible in mobile. As the proliferation of AI transforms the entire industry and society, we will continue to develop the leading-edge technologies to advance and enrich people’s lives. We are excited to be working with Arm to open a new chapter of mobile AI to empower people around the world with more AI computing performance on their devices.” – TM Roh, President and Head of Mobile eXperience (MX) Business, Samsung Electronics
TSMC:
“The AI-optimized Arm CSS is a prime example of the collaboration between Arm and TSMC in helping designers achieve unprecedented levels of performance and power efficiency, pushing the boundaries of semiconductor innovation for AI. Together with Arm and our Open Innovation Platform® (OIP) ecosystem partners, we empower our customers to accelerate their AI innovation using the most advanced process technologies and design solutions.” – Dan Kochpatcharin, Head of the Ecosystem and Alliance Management Division, TSMC
vivo:
“vivo pays great attention to the user experience and is fueled by Arm technology and the collaboration in the developer ecosystem to bring to life cutting-edge AI experiences on-device. We are excited to see the new direction with Arm CSS for Client and how this will enable the next generation GenAI on devices with Armv9 CPUs paired with Arm GPU for an immersive and intelligent mobile solution.” – Xiaofei Xia, Chief Chipset Planning Expert, vivo
Additional resources:
Any re-use permitted for informational and non-commercial or personal use only.
Media Contacts
Latest on Twitter
For #WorldRefugeeDay, we're celebrating our partnership with @Refugees & @UNRefugeesUK to ensure AI tools for humanitarian efforts are used responsibly.
By supporting @UNHCRinnovation, we can ensure diversity is built into tools from the ground up:
We're putting the foundations in place for a thriving, diverse, chiplet ecosystem in Automotive.
From participation in @imec_int's Automotive Chiplet Program, to our role in SOAFEE, here's how we're ensuring interoperability and performance for chiplets: https://okt.to/eBfYgd
Here's to our fantastic, award-winning Internal Comms team. 👏
At the #ICEAwards, the team took home 3️⃣ awards for:
⭐ Best event
⭐ Best Internal Comms from the tech, media and telecommunications sector
⭐ Best Internal Comms Campaign in a large business under 10,000 employees
Rene Haas joined the Samsung Foundry Forum to discuss our almost 30-year partnership and the possibilities of Arm CSS.
By removing the complexity from SoC development, Arm CSS enables our partners to move faster in the age of AI, with the support of partners like Samsung.
Sentiment analysis is a vital AI technique that figures out emotions and opinions from written text.
With @HuggingFace's pipeline running on Arm Neoverse CPUs, we're making sentiment analysis quicker, with more impactful insights.
👉 See for yourself:
The next generation of Windows on Arm is here. ✨
We caught up with @sinclairinat0r at Microsoft Build to get his take on the latest Windows on Arm AI capabilities and how they are making AI approachable and easy to use.
From the moment he saw his first computer, Samuel fell in love with technology.
Now, it extends to his work at @Simprints, where their biometric solution built #onArm is enabling faster patient tracking and healthcare interventions.
This is how technology can change lives.
🆕 Slack is Windows on Arm ready! 🥳
Available now in beta, the ARM64 version of @SlackHQ lets you maximize performance on Arm-based hardware.
This creates the opportunity for new AI experiences running efficiently on Windows on Arm devices.
More: https://okt.to/oqMg25
Congrats to the winner of the 2024 Arm Flexible Access for Startups Contest, Agate Sensors! 👏
Chosen for its spectral imaging technology that paves the way for edge tech, the team will receive up to $250K of Arm credit to build next-gen SoC solutions: https://okt.to/Fbqrph
No other ecosystem has Arm's level of diversity & collaboration in its supply chain.
It's why Arm Neoverse is best suited to drive the transformation of AI-ready cloud data centers, together with our partners.
Eddie Ramirez shares more at #COMPUTEX2024: https://okt.to/WFqu7R
"We are at a magical time in our industry relative to the growth potential"
Following the biggest IPO of 2023, Rene Haas speaks to the @FT on the AI opportunity for Arm, discussing why the CPU is crucial, sustainable development & what's next for Arm CSS.
Rene Haas: ‘Arm has the most ubiquitous computer architecture on the planet’
Chip designer’s chief executive talks about diversification and how AI is changing the devices we use
okt.to
Our Architecture Formal Team has won the @RAEngNews Colin Campbell Mitchell Award, paving the way for more reliable computing systems.
Their ground-breaking approach to formal specifications enables efficient & secure Arm-based computing systems. https://okt.to/m8y1Qp
Introducing @GitHub-hosted runners for Arm! 🌟
Announced this week, the Arm-based Linux and Windows runners for Git Hub Actions let you build and test cycles directly on Arm Neoverse processors.
Get started and simplify the development process 👉 https://okt.to/7BXgNQ
For AI to scale it needs a mix of computing options.
Small language models, which can run on Arm Neoverse-based server processors, offer tailored solutions with reduced costs.
This sets the stage for generative AI in the cloud running on Arm CPUs:
At #COMPUTEX2024, @CTBergey shared more about Arm CSS for Client, our latest platform for AI smartphones and PCs.
With a TON of updates, it’s been designed to help developers create better, faster, and more secure AI experiences.
Details at 44:00 here: https://okt.to/UwdZa8
@MediaTek We're also thrilled to celebrate @MediaTek joining Arm Total Design, announced today at #COMPUTEX2024.
As an Arm Total Design partner, MediaTek brings its world class expertise to infrastructure as we rapidly deliver sustainable, AI-powered cloud data centers on Neoverse CSS.
Following 20+ years of partnership, we're thrilled to continue our close collaboration with @MediaTek to enable AI innovation.
At #COMPUTEX2024, Rene Haas joined Dr. Rick Tsai to discuss how together we're enabling leading AI products from cloud to edge: https://okt.to/3yMdQR
We're back at #COMPUTEX2024! Arm CEO Rene Haas kicked things off with a keynote address exploring:
⚡ Arm's history in power efficiency
🏅 Why Arm's the de facto choice for every major OS
🆕 How KleidiAI helps developers unlock AI performance on the CPU
https://okt.to/u4VGcY
Get ready for #COMPUTEX2024!
The conference brings together some of the biggest technology and AI leaders of today and we’re thrilled to be a part of it.
Keep an eye on our socials for the latest. https://okt.to/n9cHgy
Heading to #COMPUTEX2024?
Join Rene Haas' keynote for insights into Arm's role in the AI revolution across the world's compute touchpoints - from cloud to edge. https://okt.to/Rb5D1n
We hope to see you there!
📆 Monday June 3, 11:30am
📍 Grand Hilai Taipei
@computex_taipei
Heading to #COMPUTEX2024?
Join Rene Haas' keynote for insights into Arm's role in the AI revolution across the world's compute touchpoints - from cloud to edge: https://okt.to/RhtQpx
We hope to see you there!
📆 Monday June 3, 11:30am
📍 Grand Hilai Taipei
@computex_taipei
You can find our technology in everything from mobile phones to data centers.
But we're only just getting started.
Join our team and help shape the future of computing: https://okt.to/cRQnPt
Our CCO, Will Abbey, recently spoke at #DubTechSummit about the importance of power efficiency in the age of AI.
He highlighted our commitment to addressing growing energy demands and discussed how our history of efficient compute solutions can help realize AI's full potential.
Transformer models are the next big innovation in AI, translating text and speech in near real-time.
With the Ethos-U85, we're offering support for transformer-based models at the edge - the foundation for newer language and vision models.
@PNWilliamson shares how.
