
Fifth generation ARM Cortex-X for 3nm AI chip designs
ARM has launched its fifth generation Cortex-X core for smartphones along with a compute sub-system (CSS) with the latest high performance graphics unit.
The smartphone compute sub-system (CSS) combines the ARM Cortex-X925, the successor the X4, and the Immortalis G925 GPU core. These are combined with refreshed ARM A-class cores, the A725 and A520 for big.LITTLE architectures ready designed for chip makers. These have a system management wrapper, the Dynamiq DS-120, that manages the data flow between up to 14 cores.
The CSS is aimed squarely at adding AI to Android smartphones through chips such as the Mediatek Dimensity 9400 as well as Windows and Linux PCs, with chips designed for the 3nm process at TSMC and Samsung and the 1.8nm 18A process at Intel Foundry Services (IFS).
ARM has also launched library software that runs popular generative AI frameworks such as Llama 3 and
There are two versions of the Kleidi library to support generative AI and computer vision that support the ARMv9.2 instruction set to use the X925 CPU cores.
KleidiAI integrates with popular AI frameworks such as PyTorch, Tensorflow, MediaPipe Microsoft Phi-3 and Meta Llama 3, and is also backwards and forwards compatible.
KleidiCV accelerates CV pipelines that are used for many camera use cases. OpenCV, the world’s largest CV library containing over 2500 algorithms and supporting hundreds of thousands of developers, has already identified a typical performance uplift of 75 percent for a variety of image processing tasks based on KleidiCV integrations.
The Cortex-X95 provides a 36% increase in performance through an increase in frequency from 3.6GHz to 3.8GHz as well as a higher instruction per cycle (IPC) rate and a larger private L2 cache that is 2MB 8-way set associative with 4 banks or 3MB 12-way set associative with 4 banks.
The Immortalis GPU brings a 37% increase in graphics performance with between 10 processing units and 24, up from 16, along with the ray tracing capability that was introduced with the previous version.
The integrated system-level cache (SLC) enables best system power efficiency by reducing DRAM bandwidth and accesses. The System Memory Management Unit (SMMU) provides enhanced security through stage-2 translation to support virtualized security frameworks, such as the Android Virtualization Framework (AVF).
“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,” said Chris Bergey, SVP and GM, Client Line of Business.
MediaTek has been the lead customer for the Cortex-X cores in smartphones. “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,” said JC Hsu, Corporate Senior Vice President at MediaTek
The CSS has support from the major foundries with leading edge process technologies.
“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,” said Suk Lee, Vice President and General Manager of the Ecosystem Technology Office, Intel Foundry Services.
“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 longstanding 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,” said Jongwook Kye, Executive Vice President and Head of Foundry Design Platform Development, Samsung Electronics.
3nm AI chips and 6nm microcontrollers will be key to TSMC Dresden fab
“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,” said Dan Kochpatcharin, Head of the Ecosystem and Alliance Management Division at TSMC.
