ARM details 2nm Neoverse V3 chiplets for the data centre
Cette publication existe aussi en Français
ARM has announced several 2nm chiplet designs by customers using its Neoverse V3 compute subsystem (CSS).
ADTechnology and Rebellions are working on a 2nm AI CPU chiplet platform to be based by Samsung Foundry. This is based on the ARM Neoverse CSS V3 for cloud, HPC, and AI/ML training and inference. This follows hints this time last year on a 2nm chiplet project.
Egis Group collaborates with Arm to Drive AI HPC chiplet technology
“We introduced ARM Total Design a year ago to address these challenges by creating an ecosystem of partners to accelerate the development of custom silicon, bringing together key industry players to build solutions for the datacenters of the future with Arm Compute Subsystems (CSS),” said Eddie Ramirez, Vice President of Go-To-Market, Infrastructure Line of Business at ARM.
ARM Total Design has 30 participating companies, with Alcor Micro, Egis, PUF Security and SEMIFIVE as the latest companies to join the ecosystem. AMD and Intel today launched an x86 ecosystem partnership in response.
The ADTechnology chiplet platform uses the Rebellions’ REBEL AI accelerator built with a Neoverse CSS V3-powered compute chiplet from ADTechnology to be implemented with Samsung Foundry 2nm Gate-All-Around (GAA) advanced process technology.
“AI and HPC designs require technology solutions that deliver maximum performance, high transistor density, and energy efficiency,” said Taejoong Song, Vice President and Head of Foundry Business Development at Samsung Electronics. “Samsung Foundry’s 2nm GAA process is designed precisely to satisfy the most stringent HPC and AI design requirements, and we’re excited to leverage the flexibility of Arm CSS and the power of the Arm Total Design ecosystem to deliver an AI CPU chiplet platform, which will further accelerate adoption of our leading-edge technology and design solutions for hyperscalers and cloud service providers.”
The rapid evolution of AI workloads means tightly coupled CPU compute is essential for supporting the complete AI stack, says Ramirez. “Data pre-processing, orchestration, database augmentation techniques, such as Retrieval-augmented Generation (RAG), and more all benefit from performance-efficiency of Arm Neoverse CPUs. We’ve baked support for these requirements into our CSS and through Arm Total Design, the ecosystem is already benefitting from these innovations,” he said.
Alphawave, Cadence, and proteanTecs, are validating their third-party IP products with CSS on advanced nodes to ensure compliance with ARM specifications and standards. This means partners can build CSS-based custom silicon on leading edge nodes.
The ARM Kleidi software technology is also key. This optimizes CPU-based inference on Arm to open source projects like PyTorch and Llama.cpp for CSS-based chiplets for edge AI computing without the need for an accelerator.
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
