Bravo
If ARM was an arm, BRN would be its biceps💪!
Not on my PC ATM and can’t drive my i-Pad very well.
Could we be involved in the new Arm Cortex-A320???
Check out the Arm blog - the link at the bottom of the post. It reads like does everything Pico can do???
The Ethos-U85 driver has now been updated so that Ethos-U85 can be driven directly by a Cortex-A320, without the need for a Cortex-M based ML island. This update improves latency and allows Arm partners to remove the cost and complexity of using a Cortex-M to drive the NPU.
Arm to support more intelligent applications at the edge with Armv9 Edge AI Platform
![]()
BY MIKE WHEATLEY
FEBRUARY 26 2025
Chipmaker Arm Holdings Plc is looking to strengthen its grip on artificial intelligence at the network edge with the debut of a powerful new lightweight processor designed to sit at the heart of intelligent internet of things applications.
????
The company unveiled the Arm Cortex-A320 central processing unit today, saying it’s the centerpiece of its all-new Armv9 Edge AI Platform, which provides all of the hardware needed to run lightweight AI workloads independently of the cloud.
???
In its pitch, Arm says the increasingly connected world we live in means that we cannot just rely on the cloud to continue processing AI workloads anymore. Use cases such as smart cities and industrial automation demand that AI applications live at the edge, and there’s an urgent need for them to process data locally to eliminate latency, but to do that we need to have the right infrastructure to run them, the company says.
That’s what it’s providing with the Armv9 Edge AI Platform, which combines the Cortex-A320 CPU with a new AI accelerator chip, the Arm Ethos-U85 neural processing unit, to run powerful AI models with up to 1 billion parameters locally on any device.
Arm said the edge platform is equipped to handle workloads such as autonomous vehicles that can navigate busy factory floors, smart cameras that must be able to process what they’re seeing, drones that carry out autonomous operations, and human-machine interfaces that drive natural, conversational interactions.
The Cortex-A320 is based on the company’s most advanced CPU architecture, Armv9, and delivers key features such as SVE2 for enhanced machine learning performance of up to 10 times its predecessor edge CPU, the Cortex-A35. It also benefits from improved security, with new capabilities such as Pointer Authentication, Branch Target Identification and Memory Tagging Extension, which enable edge devices to handle sensitive data in the most exposed locations, the company said. At the same time, Armv9 provides greater efficiency, meaning lower running costs for edge AI workloads.
Arm KleidiAI comes to the network edge
It’s one thing to provide the infrastructure for edge AI applications, and another thing to build them, but Arm has this covered too. Alongside the Armv9 Edge AI Platform, it’s also extending its Arm KleidiAI software development platform to the edge. It provides a powerful set of compute libraries to support the development of AI frameworks that can optimize AI and machine learning workloads to run on the new Armv9 Edge AI Platform, the company said.
KleidiAI is a popular platform that has already been widely integrated into IoT AI software frameworks such as Llama.cpp and ExecuTorch to accelerate the performance of lightweight large language models such as Meta Platform’s Llama 3 and Microsoft Corp.’s Phi-3. According to Arm, KleidiAI can help to boost the performance of the new Cortex-A320 CPUs by up to 70% in some scenarios.
By using KleidiAI, developers can also accelerate the time-to-market for new edge AI applications, meaning they can quickly build new solutions that grow and adapt as their requirements evolve.
The launch of the Armv9 Edge AI Platform has been warmly welcomed by customers including Amazon Web Services Inc. and the edge server manufacturer Eurotech S.p.A. For instance, AWS has already integrated the hardware into the nucleus lite runtime environment within its AWS IoT Greengrass platform for edge devices.
“This seamless integration between the two technologies provides an optimized solution for developers to build modern edge AI applications, like anomaly detection in precision agriculture, smart manufacturing and autonomous vehicles,” said AWS Vice President of IoT Yasser Alsaied.
Meanwhile, Eurotech has been quick to install Arm’s new hardware at the foundation of its latest edge computing hardware.
“Arm’s new edge AI platform provides us with the foundation to build the next generation of rich IoT devices, with Armv9 giving us access to new levels of secure performance, energy-efficiency and software flexibility,” said Eurotech Chief Technology Officer Marco Carrer.
Introducing Cortex-A320: Ultra-efficient Armv9 CPU Optimized for IoT
Unlock ultra-efficient performance, advanced AI processing, and robust security with the Cortex-A320—designed to power the future of IoT and edge AI innovation.
![]()
Introducing Cortex-A320: Ultra-efficient Armv9 CPU Optimized for IoT
Arm Cortex-A320, the first ultra-efficient Armv9 CPU, delivers advanced AI, security, and efficiency to power-constrained devices in the evolving IoT and edge AI landscape.newsroom.arm.com
Building on the points above, it seems like quite the "coincidence" that Arm has just announced its new ArmV9 edge AI platform—featuring the Cortex A320—in Korea.
Meanwhile, BrainChip just happened to post a job listing for a Regional Sales Manager in… you guessed it—Korea!
Arm eyes expansion in Korea with AI chip designs for IoT devices
Posted : 2025-02-27 17:00
Updated : 2025-02-27 17:10

Arm Korea President Hwang Seon-wook speaks during a press conference at the Plaza Seoul hotel in Jung District, Thursday. Korea Times photo by Nam Hyun-woo
By Nam Hyun-woo
Chip architecture giant Arm announced its latest platform for edge artificial intelligence (AI) for Internet of Things (IoT) devices in Korea on Thursday, expressing hopes that the new solution will empower various AI-powered IT devices and home appliances developed by client companies here.
During a press conference in Seoul, Arm Korea President Hwang Seon-wook revealed the Armv9 Edge AI platform, which includes the Cortex-A320 CPU and the Ethos-U85 neural processing unit designs and related architecture and software tools to help developers produce their chips and other solutions.
Edge AI refers to processing AI tasks directly on devices such as smartphones, autonomous vehicles, home appliances and sensors without relying on remote servers. The importance of Edge AI is growing as more IoT devices are powered by AI, and the increasing workloads for AI in the cloud are pushing such devices to handle AI tasks locally.
“In the areas of smart homes, smart cities and industrial automation, the importance of edge AI has grown, and device makers are expecting Arm to drive the entire ecosystem,” Hwang said. “To meet industry expectations and maximize Edge AI, the new Armv9 platform will be introduced.”
According to Arm, the Armv9 platform delivers an eight-fold improvement in machine learning performance compared to the Cortex-M85-based platform the company launched last year. The new platform comes with the latest Cortex-A320 CPU design, which is specifically optimized for IoT applications due to its power efficiency.
The Cortex-A320 takes advantage of Armv9 architectural features to deliver a 10-fold improvement in machine learning performance and a 30 percent scalar performance uplift compared to its predecessor, the Cortex-A35.
Arm said the Cortex-A320 CPU completes the company's CPU portfolio, which spans from ultra-efficient models for IoT devices to performance-oriented ones for servers, offering a wide range of options for partner companies.
Hwang said he expects client companies will begin making physical chips using Cortex-A320 from 2026, but they will not likely require the most advanced fabrication processes such as 2 nanometers. Also, a number of clients are now evaluating the Cortex-A320 and the Ethos-U85 designs, with possible applications for various appliances and chips.
Read More
Regarding questions about Arm's plan for a license fee hike, Hwang said he is not in a position to answer but added that Arm aims to support the success of its Korean partner companies.“We have many customers in Korea using our Arm solutions — the proportion of users in Korea is probably the highest in the world. Startups are building and validating their solutions and products on this foundation, developing competitive products, and using that as a stepping stone to enter the global market,” Hwang said. “Our goal is to ensure the success of our partners.”
In January, Reuters reported that Arm is developing a long-term strategy to hike prices by as much as 300 percent, potentially affecting chips and smartphone makers, including Samsung Electronics.

Arm eyes expansion in Korea with AI chip designs for IoT devices
Chip architecture giant Arm announced its latest platform for edge artificial intelligence (AI) for Internet of Things (IoT) devices in Korea on Thursday, expressing hopes that the new solution will empower various AI-powered IT devices and home appliances developed by client companies here.
