# Arm

Arm is a computing technology company that develops processor architectures, CPUs, GPUs, and related tools and licenses its intellectual property for software and hardware development.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Nvidia Approaches Arm Boss Rene Haas In Search For New CEO

DevFeed: [Nvidia Approaches Arm Boss Rene Haas In Search For New CEO](<https://devfeed.tech/articles/nvidia-approaches-arm-boss-rene-haas-in-search-for-new-ceo-144612.md>)

Original publisher: [Read original article](<https://slashdot.org/story/26/11/19/2212215/nvidia-approaches-arm-boss-rene-haas-in-search-for-new-ceo>)

Author: BeauHD

Published: 2026-11-19T23:00:00Z

Content type: news

Language: en

Sources: [Slashdot](<https://devfeed.tech/sources/slashdot.md>)

Topics: [Arm](<https://devfeed.tech/topics/arm.md>), [Nvidia](<https://devfeed.tech/topics/nvidia.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-chip](<https://devfeed.tech/tags/ai-chip.md>), [amd](<https://devfeed.tech/tags/amd.md>), [apple](<https://devfeed.tech/tags/apple.md>), [arm](<https://devfeed.tech/tags/arm.md>), [bloomberg](<https://devfeed.tech/tags/bloomberg.md>), [board](<https://devfeed.tech/tags/board.md>), [business](<https://devfeed.tech/tags/business.md>), [cambridge](<https://devfeed.tech/tags/cambridge.md>), [ceo](<https://devfeed.tech/tags/ceo.md>), [chip](<https://devfeed.tech/tags/chip.md>), [co-founder](<https://devfeed.tech/tags/co-founder.md>), [company](<https://devfeed.tech/tags/company.md>), [computing](<https://devfeed.tech/tags/computing.md>), [conference](<https://devfeed.tech/tags/conference.md>), [designs](<https://devfeed.tech/tags/designs.md>), [executive](<https://devfeed.tech/tags/executive.md>), [ian-buck](<https://devfeed.tech/tags/ian-buck.md>), [jensen-huang](<https://devfeed.tech/tags/jensen-huang.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [search](<https://devfeed.tech/tags/search.md>)

### AI overview

Nvidia has reportedly approached Arm CEO Rene Haas as a leading contender to replace co-founder Jensen Huang, who the excerpt says resigned last week amid a personal scandal. Heidrick & Struggles, hired by Nvidia's board, has begun contacting candidates. Haas joined Arm in 2013 and became CEO in 2022; before that, he spent seven years at Nvidia leading its computing products business. Other reported candidates are Nvidia vice-president Ian Buck, AMD CEO Lisa Su, and Apple hardware chief Johny Srouji. The excerpt also notes Arm's broad customer base for its chip designs, which includes Nvidia, Apple, Samsung, and Qualcomm.

### Source excerpt

Nvidia has reportedly approached Arm CEO Rene Haas as it searches for a replacement for co-founder Jensen Huang, who resigned last week amid a personal scandal. According to Bloomberg, Haas is emerging as a leading contender for the job. The 64-year-old previously worked at Nvidia as general manager of its computing products business before joining Arm, giving him firsthand experience with the AI chip giant. The Guardian reports: Heidrick & Struggles, the recruiting firm hired by the company's board, has started contacting potential candidates, according to Bloomberg. It reported that Rene Haas, who joined Arm in 2013 and became chief executive in 2022, is among those approached. [...] Haas, 64, is viewed as the leading contender for the top job at Nvidia, having previously worked at the $3.6tn company for seven years as the general manager of its computing products. Reports suggest that other potential candidates include: Ian Buck, an Nvidia vice-president; Lisa Su, AMD's chief executive; and Johny Srouji, Apple's chief hardware officer. Arm, which is listed in New York but retains its global headquarters in Cambridge, has about 500 users of its chip designs worldwide, including Nvidia, Apple, Samsung and Qualcomm. The company employs more than 7,000 staff, including more than 3,000 in the UK. It is the biggest tech firm headquartered in Britain, now valued at $196bn. Haas told a tech conference in Austin on Wednesday that Huang was "a legend." "What he built at Nvidia is historic," he said. "You don't have many champions like that." Read more of this story at Slashdot.

## Microsoft thinks it can make agentic AI work for the whole company, not just you

DevFeed: [Microsoft thinks it can make agentic AI work for the whole company, not just you](<https://devfeed.tech/articles/microsoft-thinks-it-can-make-agentic-ai-work-for-the-whole-company-not-just-you-143167.md>)

Original publisher: [Read original article](<https://www.techspot.com/news/114611-microsoft-thinks-can-make-agentic-ai-work-whole.html>)

Author: Bob O'Donnell

Published: 2026-11-19T12:32:00Z

Content type: article

Language: en

Sources: [TechSpot](<https://devfeed.tech/sources/techspot.md>)

Topics: [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [workflow automation](<https://devfeed.tech/topics/workflow-automation.md>), [microsoft 365](<https://devfeed.tech/topics/microsoft-365.md>), [Frontier AI](<https://devfeed.tech/topics/frontier-ai.md>), [Arm](<https://devfeed.tech/topics/arm.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [agentic-workloads](<https://devfeed.tech/tags/agentic-workloads.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [ai-investments](<https://devfeed.tech/tags/ai-investments.md>), [ai-scaling](<https://devfeed.tech/tags/ai-scaling.md>), [ai-tools](<https://devfeed.tech/tags/ai-tools.md>), [ai-transparency](<https://devfeed.tech/tags/ai-transparency.md>), [arm](<https://devfeed.tech/tags/arm.md>), [autopilot](<https://devfeed.tech/tags/autopilot.md>), [cobalt-200](<https://devfeed.tech/tags/cobalt-200.md>), [coding](<https://devfeed.tech/tags/coding.md>), [company](<https://devfeed.tech/tags/company.md>), [connectors](<https://devfeed.tech/tags/connectors.md>), [context](<https://devfeed.tech/tags/context.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [ignite](<https://devfeed.tech/tags/ignite.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [opinion](<https://devfeed.tech/tags/opinion.md>), [work](<https://devfeed.tech/tags/work.md>)

### AI overview

Microsoft is assembling tools to extend agentic AI from individual use to organization-wide workflows, though the article says scaling will take time. Copilot Workspaces lets teams build and edit ongoing projects using shared Office documents and Teams threads; Copilot's Today mode offers individual task reminders and is in private preview. Microsoft IQ adds a contextual layer above Microsoft Graph, combining several IQ services and more than 350 connectors intended to link and prepare organizational data for agents. A Salesforce partnership, Copilotforce, would connect Salesforce data and skills through MCP. For cost and deployment flexibility, Microsoft says its MAI-Code-2 offers 90% of current frontier models' coding capability at smaller size, while Microsoft-Decision-1.1 routes task components to suitable, cost-effective models across cloud, on-premises and edge environments. The article notes competing routing efforts and that more work remains. Security and infrastructure announcements accompany the software, but the transition to enterprise-scale use is not immediate.

### Source excerpt

While there's been a tremendous amount of excitement surrounding agentic AI over the last year or two, the vast majority of the attention has focused on individual use of these tools. Everywhere you look, it seems, you can find stories of people who have done amazing work on their own... Read Entire Article

## Nvidia approaches Arm boss Rene Haas in search for new CEO

DevFeed: [Nvidia approaches Arm boss Rene Haas in search for new CEO](<https://devfeed.tech/articles/nvidia-approaches-arm-boss-rene-haas-in-search-for-new-ceo-143173.md>)

Original publisher: [Read original article](<https://www.theguardian.com/technology/2026/nov/19/nvidia-new-ceo-search-jensen-huang-arm-rene-haas>)

Author: Lauren Almeida

Published: 2026-11-19T11:29:01Z

Content type: news

Language: en

Sources: [The Guardian | Technology](<https://devfeed.tech/sources/the-guardian-technology.md>)

Topics: [Nvidia](<https://devfeed.tech/topics/nvidia.md>), [Arm](<https://devfeed.tech/topics/arm.md>)

Tags: [arm](<https://devfeed.tech/tags/arm.md>), [bloomberg](<https://devfeed.tech/tags/bloomberg.md>), [board](<https://devfeed.tech/tags/board.md>), [business](<https://devfeed.tech/tags/business.md>), [cambridge](<https://devfeed.tech/tags/cambridge.md>), [ceo](<https://devfeed.tech/tags/ceo.md>), [chip](<https://devfeed.tech/tags/chip.md>), [co-founder](<https://devfeed.tech/tags/co-founder.md>), [company](<https://devfeed.tech/tags/company.md>), [computing](<https://devfeed.tech/tags/computing.md>), [corporate-governance](<https://devfeed.tech/tags/corporate-governance.md>), [executive](<https://devfeed.tech/tags/executive.md>), [exit](<https://devfeed.tech/tags/exit.md>), [jensen-huang](<https://devfeed.tech/tags/jensen-huang.md>), [leader](<https://devfeed.tech/tags/leader.md>), [leading](<https://devfeed.tech/tags/leading.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [nvidia-technology-sector-corporate-governance-jensen-huang-business-technology-arm-computing-world-n](<https://devfeed.tech/tags/nvidia-technology-sector-corporate-governance-jensen-huang-business-technology-arm-computing-world-n.md>), [recruiting](<https://devfeed.tech/tags/recruiting.md>), [reports](<https://devfeed.tech/tags/reports.md>), [search](<https://devfeed.tech/tags/search.md>), [technology](<https://devfeed.tech/tags/technology.md>), [technology-sector](<https://devfeed.tech/tags/technology-sector.md>), [world-news](<https://devfeed.tech/tags/world-news.md>)

### AI overview

Nvidia's board says it does not intend to reinstate co-founder Jensen Huang, and its recruiter has reportedly approached Arm CEO Rene Haas as a possible successor. Bloomberg reported Haas is viewed as the leading contender; other reported possibilities include Nvidia vice-president Ian Buck, AMD CEO Lisa Su and Apple hardware chief Johny Srouji. Haas previously spent seven years at Nvidia and joined Arm in 2013, becoming its CEO in 2022. Colette Kress is interim CEO. The excerpt also reports Huang's planned congressional interviews and an SEC investigation into Nvidia's China business.

### Source excerpt

CEO of Cambridge-based firm viewed as leading contender to replace co-founder Jensen Huang according to reports Business live - latest updates Nvidia's headhunters have reportedly approached the chief executive of the Cambridge-based chip company Arm, in its search for a new leader after Jensen Huang's dramatic exit. Heidrick & Struggles, the recruiting firm hired by the company's board, has started contacting potential candidates, according to Bloomberg. Continue reading...

## Flipper One - a portable Arm Linux computer and networking multi-tool

DevFeed: [Flipper One - a portable Arm Linux computer and networking multi-tool](<https://devfeed.tech/articles/flipper-one-a-portable-arm-linux-computer-and-networking-multi-tool-140779.md>)

Original publisher: [Read original article](<https://blog.adafruit.com/2026/11/18/flipper-one-a-portable-arm-linux-computer-and-networking-multi-tool/>)

Author: Anne Barela

Published: 2026-11-18T16:01:05Z

Content type: news

Language: en

Sources: [Adafruit Industries](<https://devfeed.tech/sources/adafruit-industries-makers-hackers-artists-designers-and-engineers.md>)

Topics: [Linux](<https://devfeed.tech/topics/linux.md>), [Raspberry Pi RP2350](<https://devfeed.tech/topics/raspberry-pi-rp2350.md>), [Arm](<https://devfeed.tech/topics/arm.md>), [Raspberry Pi](<https://devfeed.tech/topics/raspberry-pi.md>)

Tags: [arm](<https://devfeed.tech/tags/arm.md>), [chip](<https://devfeed.tech/tags/chip.md>), [computer](<https://devfeed.tech/tags/computer.md>), [computers](<https://devfeed.tech/tags/computers.md>), [cortex](<https://devfeed.tech/tags/cortex.md>), [devices](<https://devfeed.tech/tags/devices.md>), [electronics](<https://devfeed.tech/tags/electronics.md>), [ethernet](<https://devfeed.tech/tags/ethernet.md>), [flipper](<https://devfeed.tech/tags/flipper.md>), [flipper-devices](<https://devfeed.tech/tags/flipper-devices.md>), [flipper-one](<https://devfeed.tech/tags/flipper-one.md>), [gigabit-ethernet](<https://devfeed.tech/tags/gigabit-ethernet.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [hdmi](<https://devfeed.tech/tags/hdmi.md>), [linux](<https://devfeed.tech/tags/linux.md>), [microcontrollers](<https://devfeed.tech/tags/microcontrollers.md>), [networking](<https://devfeed.tech/tags/networking.md>), [open-source-hardware](<https://devfeed.tech/tags/open-source-hardware.md>), [portable](<https://devfeed.tech/tags/portable.md>), [raspberry-pi](<https://devfeed.tech/tags/raspberry-pi.md>), [raspberry-pi-rp2350](<https://devfeed.tech/tags/raspberry-pi-rp2350.md>), [rk3576](<https://devfeed.tech/tags/rk3576.md>), [tool](<https://devfeed.tech/tags/tool.md>), [wifi](<https://devfeed.tech/tags/wifi.md>), [wireless](<https://devfeed.tech/tags/wireless.md>)

### AI overview

Flipper One is an open-source portable Arm Linux computer and networking multi-tool built around a Rockchip RK3576, with an RP2350 microcontroller for low-level control. It adds dual Gigabit Ethernet, WiFi 6E, HDMI 2.1, USB-C, a nano SIM slot, GPIO, and an M.2 slot for an optional cellular modem. Unlike the STM32-based Flipper Zero, Flipper Devices says it operates at different levels of networking and wireless stacks. The Debian-based Flipper OS uses a mainline Linux kernel, with RK3576 support developed with Collabora; wireless and cellular may still require binary blobs for regulatory reasons. Kickstarter rewards start at $399, with shipping planned for July 2027.

### Source excerpt

Jean-Luc Aufranc wrote at CNX Software about the Flipper One, an open-source hardware portable Arm Linux computer and networking multi-tool from Flipper Devices. It runs on a Rockchip RK3576 octa-core Cortex-A72/A53 chip, with a Raspberry Pi RP2350 microcontroller handling low-level control. Ports and radios include dual Gigabit Ethernet, WiFi 6E, HDMI 2.1, USB-C OTG and [...]

## MSI EdgeMesa N AI+ Review: RTX Spark N1X and 128GB in a 1.18-Liter Mini PC

DevFeed: [MSI EdgeMesa N AI+ Review: RTX Spark N1X and 128GB in a 1.18-Liter Mini PC](<https://devfeed.tech/articles/msi-edgemesa-n-ai-review-rtx-spark-n1x-and-128gb-in-a-1-18-liter-mini-pc-141149.md>)

Original publisher: [Read original article](<https://www.storagereview.com/review/msi-edgemesa-n-ai-plus-review>)

Author: Brian Beeler

Published: 2026-11-18T14:40:38Z

Content type: article

Language: en

Sources: [StorageReview.com](<https://devfeed.tech/sources/storagereview-com.md>)

Topics: [NVIDIA RTX](<https://devfeed.tech/topics/nvidia-rtx.md>), [NVIDIA Blackwell](<https://devfeed.tech/topics/nvidia-blackwell.md>), [NVMe](<https://devfeed.tech/topics/nvme.md>), [Arm](<https://devfeed.tech/topics/arm.md>), [DGX Spark](<https://devfeed.tech/topics/dgx-spark.md>), [Image](<https://devfeed.tech/topics/image.md>), [3D](<https://devfeed.tech/topics/3d.md>)

Tags: [10gbe](<https://devfeed.tech/tags/10gbe.md>), [aluminum](<https://devfeed.tech/tags/aluminum.md>), [arm](<https://devfeed.tech/tags/arm.md>), [blackwell](<https://devfeed.tech/tags/blackwell.md>), [end-user](<https://devfeed.tech/tags/end-user.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [memory](<https://devfeed.tech/tags/memory.md>), [mini-pc](<https://devfeed.tech/tags/mini-pc.md>), [msi](<https://devfeed.tech/tags/msi.md>), [n1x](<https://devfeed.tech/tags/n1x.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [pcie-gen5](<https://devfeed.tech/tags/pcie-gen5.md>), [review](<https://devfeed.tech/tags/review.md>), [rtx](<https://devfeed.tech/tags/rtx.md>), [rtx-spark](<https://devfeed.tech/tags/rtx-spark.md>), [ssd](<https://devfeed.tech/tags/ssd.md>), [unified-memory](<https://devfeed.tech/tags/unified-memory.md>), [windows](<https://devfeed.tech/tags/windows.md>), [windows-11](<https://devfeed.tech/tags/windows-11.md>), [windows-11-pro](<https://devfeed.tech/tags/windows-11-pro.md>), [workstation](<https://devfeed.tech/tags/workstation.md>)

### AI overview

The MSI EdgeMesa N AI+ delivers higher sustained performance and lower average CPU temperatures than tested RTX Spark laptops, while matching the ASUS ProArt GR1X mini PC in most workloads. In a 30-minute Cinebench loop it scored 7,276, 4-11% ahead of the laptops; with eight concurrent requests on Qwen3.8 27B it reached 39.8 tokens/s versus 31.9-33.8 on the laptops. Single-request AI performance was similar across systems. Its 128GB unified memory let the review run Qwen-Image 20B at Q8 and a 35B coding-agent model that the 64GB systems did not run. The tested configuration also includes a 4TB Gen5 SSD and 10GbE. Tradeoffs include fixed, non-upgradeable memory, one M.2 2242 slot, no USB-A or audio jack, and some CPU peak readings above 100°C. The advertised 120B model support was not tested; the Windows suite tested models up to 35B.

### Source excerpt

The MSI EdgeMesa N AI+ is a 1.18-liter aluminum mini PC built on NVIDIA's RTX Spark N1X, the 20-core Arm processor with a 6,144-core Blackwell RTX GPU that we had previously tested only in laptops. Our review unit carries 128GB of unified memory, a 4TB PCIe Gen5 SSD, 10GbE, and Windows 11 Pro. We ran The post MSI EdgeMesa N AI+ Review: RTX Spark N1X and 128GB in a 1.18-Liter Mini PC appeared first on StorageReview.com.

## Microsoft's ARM-based Cobalt 200 chips go GA. Why it matters for AI agents.

DevFeed: [Microsoft's ARM-based Cobalt 200 chips go GA. Why it matters for AI agents.](<https://devfeed.tech/articles/microsoft-s-arm-based-cobalt-200-chips-go-ga-why-it-matters-for-ai-agents-138247.md>)

Original publisher: [Read original article](<https://thenewstack.io/microsoft-cobalt-200-ga/>)

Author: Frederic Lardinois

Published: 2026-11-17T18:42:11Z

Content type: news

Language: en

Sources: [The New Stack](<https://devfeed.tech/sources/the-new-stack.md>)

Topics: [virtualization](<https://devfeed.tech/topics/virtualization.md>), [Arm](<https://devfeed.tech/topics/arm.md>), [Microsoft](<https://devfeed.tech/topics/microsoft.md>)

Tags: [1-5](<https://devfeed.tech/tags/1-5.md>), [3nm](<https://devfeed.tech/tags/3nm.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent-tool-execution](<https://devfeed.tech/tags/ai-agent-tool-execution.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [amadeus](<https://devfeed.tech/tags/amadeus.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [api](<https://devfeed.tech/tags/api.md>), [arm](<https://devfeed.tech/tags/arm.md>), [azure](<https://devfeed.tech/tags/azure.md>), [azure-devops](<https://devfeed.tech/tags/azure-devops.md>), [azure-kubernetes-service](<https://devfeed.tech/tags/azure-kubernetes-service.md>), [azure-sql](<https://devfeed.tech/tags/azure-sql.md>), [chips](<https://devfeed.tech/tags/chips.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [sandboxes](<https://devfeed.tech/tags/sandboxes.md>), [tools](<https://devfeed.tech/tags/tools.md>), [virtual-machines](<https://devfeed.tech/tags/virtual-machines.md>)

### AI overview

Microsoft's Cobalt 200 Arm-based VMs are generally available in 14 Azure regions, with expansion to 23 planned by year-end. Microsoft reports up to 50% better overall performance and up to 1.5x faster AI-agent tool execution than Cobalt 100, including file searches, code compilation, and sandbox tasks. Developers can choose deterministic 3.2 GHz operation for consistent performance or opportunistic operation up to 3.6 GHz, which Microsoft says can add up to 12% performance when power and thermal headroom permit. The excerpt recommends deterministic mode for distributed analytics and services with tight performance targets; web, API, transaction-processing, and media workloads may benefit from opportunistic mode. Cobalt 200 VMs include Azure Boost; Microsoft reports up to 15% more network bandwidth and 20% more remote-storage IOPS than Cobalt 100. They can be deployed with Azure tools, Virtual Machine Scale Sets, or as Azure Kubernetes Service node pools.

### Source excerpt

Microsoft is making its Cobalt 200 virtual machines generally available, with CPU improvements aimed at the sandboxes, tools, and code The post Microsoft's ARM-based Cobalt 200 chips go GA. Why it matters for AI agents. appeared first on The New Stack.

## Arm enables the world's fastest and most energy-efficient supercomputers

DevFeed: [Arm enables the world's fastest and most energy-efficient supercomputers](<https://devfeed.tech/articles/arm-enables-the-world-s-fastest-and-most-energy-efficient-supercomputers-137165.md>)

Original publisher: [Read original article](<https://newsroom.arm.com/blog/arm-worlds-fastest-energy-efficient-supercomputers>)

Author: Arm Editorial Team

Published: 2026-11-17T00:48:18Z

Content type: article

Language: en

Sources: [Arm Newsroom](<https://devfeed.tech/sources/arm-newsroom.md>)

Topics: [High-Performance Computing](<https://devfeed.tech/topics/high-performance-computing.md>), [Supercomputing](<https://devfeed.tech/topics/supercomputing.md>), [Arm](<https://devfeed.tech/topics/arm.md>), [Sustainable Computing](<https://devfeed.tech/topics/sustainable-computing.md>)

Tags: [arm](<https://devfeed.tech/tags/arm.md>), [computing](<https://devfeed.tech/tags/computing.md>), [ecosystem](<https://devfeed.tech/tags/ecosystem.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [energy](<https://devfeed.tech/tags/energy.md>), [high-performance-computing](<https://devfeed.tech/tags/high-performance-computing.md>), [high-performance-computing-hpc](<https://devfeed.tech/tags/high-performance-computing-hpc.md>), [hpc](<https://devfeed.tech/tags/hpc.md>), [november-2026](<https://devfeed.tech/tags/november-2026.md>), [performance](<https://devfeed.tech/tags/performance.md>), [rankings](<https://devfeed.tech/tags/rankings.md>), [supercomputers](<https://devfeed.tech/tags/supercomputers.md>)

### AI overview

The supplied text says Arm-based systems hold the top positions in the November 2026 TOP500 and Green500 rankings, with four of the 10 fastest and five of the 10 most energy-efficient supercomputers using Arm technology. It distinguishes Arm-compatible custom processors, including those in LineShine and Fugaku, from Arm Neoverse-based NVIDIA Grace Hopper systems in JUPITER, Alps, and the Green500 leaders. It attributes HPC performance and efficiency to flexible hardware and software tuning: high-bandwidth memory and CPU-GPU connectivity for data movement; vector and matrix extensions, compilers, and math libraries for numerical work; parallel execution and data-locality tuning; and power tuning to balance throughput with power limits.

### Source excerpt

The November 2026 TOP500 and Green500 rankings showcase the breadth of the Arm high-performance computing (HPC) ecosystem, and how it combines performance, efficiency, and the freedom to innovate. Highlights include: Arm technology across the world's leading supercomputers From the world's most powerful supercomputers to the most energy-efficient systems, Arm technology is helping advance HPC through [...] The post Arm enables the world's fastest and most energy-efficient supercomputers appeared first on Arm Newsroom.

## Rockchip RK3668 switches to Cortex-A725 and Cortex-A520 cores, engineering samples planned for Q1 2027

DevFeed: [Rockchip RK3668 switches to Cortex-A725 and Cortex-A520 cores, engineering samples planned for Q1 2027](<https://devfeed.tech/articles/rockchip-rk3668-switches-to-cortex-a725-and-cortex-a520-cores-engineering-samples-planned-for-q1-2027-136389.md>)

Original publisher: [Read original article](<https://www.cnx-software.com/2026/11/17/rockchip-rk3668-switches-to-cortex-a725-and-cortex-a520-cores-engineering-samples-planned-for-q1-2027/>)

Author: Jean-Luc Aufranc (CNXSoft)

Published: 2026-11-17T00:00:50Z

Content type: news

Language: en

Sources: [CNX Software - Embedded Systems News](<https://devfeed.tech/sources/cnx-software-embedded-systems-news.md>)

Topics: [armv9](<https://devfeed.tech/topics/armv9.md>), [Arm](<https://devfeed.tech/topics/arm.md>), [USB](<https://devfeed.tech/topics/usb.md>)

Tags: [10gbe](<https://devfeed.tech/tags/10gbe.md>), [android](<https://devfeed.tech/tags/android.md>), [armsom](<https://devfeed.tech/tags/armsom.md>), [armv9](<https://devfeed.tech/tags/armv9.md>), [artificial-intelligence-ai](<https://devfeed.tech/tags/artificial-intelligence-ai.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [board](<https://devfeed.tech/tags/board.md>), [computers](<https://devfeed.tech/tags/computers.md>), [core](<https://devfeed.tech/tags/core.md>), [cortex](<https://devfeed.tech/tags/cortex.md>), [cortex-a520](<https://devfeed.tech/tags/cortex-a520.md>), [cortex-a725](<https://devfeed.tech/tags/cortex-a725.md>), [cortex-m52](<https://devfeed.tech/tags/cortex-m52.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [edge-ai](<https://devfeed.tech/tags/edge-ai.md>), [embedded-systems](<https://devfeed.tech/tags/embedded-systems.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [geekbench](<https://devfeed.tech/tags/geekbench.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [nvr](<https://devfeed.tech/tags/nvr.md>), [pcie](<https://devfeed.tech/tags/pcie.md>), [processor](<https://devfeed.tech/tags/processor.md>), [prototypes](<https://devfeed.tech/tags/prototypes.md>), [q1](<https://devfeed.tech/tags/q1.md>), [radxa](<https://devfeed.tech/tags/radxa.md>), [roadmap](<https://devfeed.tech/tags/roadmap.md>), [rockchip](<https://devfeed.tech/tags/rockchip.md>), [rockchip-rk36xx](<https://devfeed.tech/tags/rockchip-rk36xx.md>), [sata](<https://devfeed.tech/tags/sata.md>), [scheduled](<https://devfeed.tech/tags/scheduled.md>), [single-board-computers](<https://devfeed.tech/tags/single-board-computers.md>), [soc](<https://devfeed.tech/tags/soc.md>), [specifications](<https://devfeed.tech/tags/specifications.md>), [switches](<https://devfeed.tech/tags/switches.md>)

### AI overview

The preliminary RK3668 specifications describe an 8-core Armv9 processor with six Cortex-A725 cores and two Cortex-A520 cores, replacing the 10-core configuration announced in 2025. Rockchip estimates clock speeds up to 2.5 GHz and 2.2 GHz, respectively. The excerpt reports up to 44 TOPS for its sparse NPU, LPDDR6 support with up to 90 GB/s usable bandwidth, UFS 4.0 storage, and support for up to two 8Kp60 displays. Rockchip's cited comparisons claim roughly twice the RK3588's multicore CPU performance and GPU frame rate, plus a 49% single-core gain; the article cautions that NPU TOPS figures are not workload benchmarks. Some interface and bandwidth details remain unclear, and no block diagram was available for cross-checking. Engineering samples are scheduled for Q1 2027, with early single-board-computer prototypes expected in the first half of 2027.

### Source excerpt

More details have surfaced about the Rockchip RK3668 processor. The biggest change is that the Armv9 SoC will feature eight cores (6x Cortex-A725 and 2x Cortex-A520), rather than ten cores in a 4x Cortex-A730 + 6x Cortex-A530 configuration announced at its initial unveiling in July 2025. Mostly because the A730 and A530 cores have never been launched... We also have more detailed specifications thanks to posts from Radxa and ArmSoM, who shared the "RK3668 Application" document. That document also includes a roadmap showing that the 6nm Rockchip RK3668 processor is now scheduled for Q1 2027 (engineering samples), and the flagship RK3688 processor should probably be available at the end of 2027 or in 2028, although the time scale in the roadmap may be deceiving... Early prototypes of RK3668 single board computers should come in H1 2027. Rockchip RK3668 specifications: Octa-core CPU - 6x Cortex-A725 cores @ up to 2.5 [...] The post Rockchip RK3668 switches to Cortex-A725 and Cortex-A520 cores, engineering samples planned for Q1 2027 appeared first on CNX Software - Embedded Systems News.

## How Two First-Timers Created the World's Most Popular Processor | Steve Furber

DevFeed: [How Two First-Timers Created the World's Most Popular Processor | Steve Furber](<https://devfeed.tech/articles/how-two-first-timers-created-the-world-s-most-popular-processor-steve-furber-135928.md>)

Original publisher: [Read original article](<https://www.developing.dev/p/e075-steve-furber>)

Author: Ryan Peterman

Published: 2026-11-16T14:05:41Z

Content type: article

Language: en

Sources: [The Developing Dev](<https://devfeed.tech/sources/the-developing-dev.md>)

Topics: [cpu](<https://devfeed.tech/topics/cpu.md>), [Arm](<https://devfeed.tech/topics/arm.md>)

Tags: [arm](<https://devfeed.tech/tags/arm.md>), [chip](<https://devfeed.tech/tags/chip.md>), [created](<https://devfeed.tech/tags/created.md>), [designers](<https://devfeed.tech/tags/designers.md>), [first](<https://devfeed.tech/tags/first.md>), [popular](<https://devfeed.tech/tags/popular.md>), [processor](<https://devfeed.tech/tags/processor.md>), [world](<https://devfeed.tech/tags/world.md>)

### AI overview

Steve Furber describes how he and Sophie Wilson helped create ARM at Acorn despite having no prior processor-design experience. After testing 16-bit processors that handled real-time interrupts poorly and underused memory bandwidth, they drew on Berkeley and Stanford RISC research. Wilson designed the instruction set; Furber translated it into a microarchitecture and modeled it in 808 lines of BBC BASIC. Acorn's chip team turned that reference model into silicon about 18 months after work began. ARM's simple, pipelined, load-store design enabled faster memory use and a small, low-power processor. The interview also distinguishes the detailed microarchitecture model, useful for checking hardware behavior, from faster instruction-level emulators used to test larger programs and instruction functions. Furber credits Acorn's prior hardware experience and confidence, while noting that RISC's advantages were not widely adopted by industry for years.

### Source excerpt

In 1984, two first-time chip designers, Steve Furber and Sophie Wilson, created what would become the most popular processor in the world (ARM).

## User-Schedulable Approximations for Quantized Tensor Programs

DevFeed: [User-Schedulable Approximations for Quantized Tensor Programs](<https://devfeed.tech/articles/user-schedulable-approximations-for-quantized-tensor-programs-135792.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.17526>)

Author: Alex Reinking

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [ggml](<https://devfeed.tech/topics/ggml.md>), [LLM optimization](<https://devfeed.tech/topics/llm-optimization.md>), [Functional programming](<https://devfeed.tech/topics/functional-programming.md>), [Arm](<https://devfeed.tech/topics/arm.md>), [x86](<https://devfeed.tech/topics/x86.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [activation](<https://devfeed.tech/tags/activation.md>), [algorithm](<https://devfeed.tech/tags/algorithm.md>), [apple](<https://devfeed.tech/tags/apple.md>), [approximation](<https://devfeed.tech/tags/approximation.md>), [arm](<https://devfeed.tech/tags/arm.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [block](<https://devfeed.tech/tags/block.md>), [but](<https://devfeed.tech/tags/but.md>), [can](<https://devfeed.tech/tags/can.md>), [cases](<https://devfeed.tech/tags/cases.md>), [code](<https://devfeed.tech/tags/code.md>), [codec](<https://devfeed.tech/tags/codec.md>), [contracts](<https://devfeed.tech/tags/contracts.md>), [covering](<https://devfeed.tech/tags/covering.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [cpus](<https://devfeed.tech/tags/cpus.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-pf](<https://devfeed.tech/tags/cs-pf.md>), [cs-pl](<https://devfeed.tech/tags/cs-pl.md>), [decoder](<https://devfeed.tech/tags/decoder.md>), [devices](<https://devfeed.tech/tags/devices.md>), [user](<https://devfeed.tech/tags/user.md>)

### AI overview

The work extends Halide so quantization codecs--paired encoders and decoders built from reusable quantizers, integer representations, bit packers, and layouts--can be applied to program stages and scheduled like ordinary computation. Property-tested contracts can catch representation errors; a round-trip law exposed an inconsistent block sum in GGML's q8_1. One algorithm and schedule library generates 347 kernels for 31 GGML and KleidiAI formats on Arm CPUs and Apple GPUs, covering 38 weight-activation pairs without GGML kernels, using 3.7x less code than GGML and KleidiAI. On Apple M3 Max, the kernels reach at least 95% of GGML's format-specific kernel speed in 91.0% of comparable cases, with 1.13x median speedup; including Apple BLAS lowers the threshold share to 86.9% of CPU cases. An x86 port with Intel AMX adds 793 lines and matches GGML in 83.5% of its cases.

### Source excerpt

arXiv:2611.17526v1 Announce Type: cross Abstract: Quantization lets language models run on edge devices, but it sharply increases the number of tensor kernels a library must maintain: every weight format must be paired with every activation format on every instruction set and GPU, with an encoder and a decoder that agree on the stored bytes. In GGML, the tensor library used by llama.cpp, these kernels are written by hand, and only 8 of the 54 weight-activation pairs it runs on our Arm CPU have a tiled matrix-multiplication kernel. We extend Halide's separation of algorithm and schedule to the representation of values. Each approximation is a codec, an encoder paired with a decoder, composed from reusable units: quantizers, integer representations, bit packers and layouts. A new directive, approximate_by, applies a codec to one stage of a program and returns the encoder and decoder as ordinary stages that Halide can schedule, so both decoders fuse into the register tiles of a matrix product. Optional contracts, such as a round-trip law, are checked by property tests; the law exposed an inconsistent block sum in GGML's q8_1. One algorithm and one schedule library generate 347 kernels for 31 of GGML's and KleidiAI's formats on Arm CPUs and Apple GPUs, covering 38 weight-activation pairs for which GGML has no kernel, in 3.7x less code than GGML and KleidiAI. On an Apple M3 Max, our kernels reach at least 95% of the speed of GGML's format-specific kernels in 91.0% of the cases that have one, with a median speedup of 1.13x, and are faster still where GGML falls back to blocked dot products. Counting Apple's BLAS library, which is usually faster for larger f32 products, we still reach that threshold in 86.9% of CPU cases. A port to x86 with Intel's AMX adds 793 lines of code and matches GGML in 83.5% of its cases.

## Without Jensen Huang, is it game over for GeForce?

DevFeed: [Without Jensen Huang, is it game over for GeForce?](<https://devfeed.tech/articles/without-jensen-huang-is-it-game-over-for-geforce-130834.md>)

Original publisher: [Read original article](<https://www.techspot.com/news/114538-without-jensen-huang-game-over-geforce.html>)

Author: Julio Franco

Published: 2026-11-12T19:16:00Z

Content type: news

Language: en

Sources: [TechSpot](<https://devfeed.tech/sources/techspot.md>)

Topics: [GeForce](<https://devfeed.tech/topics/geforce.md>), [Arm](<https://devfeed.tech/topics/arm.md>), [groq](<https://devfeed.tech/topics/groq.md>)

Tags: [17](<https://devfeed.tech/tags/17.md>), [2](<https://devfeed.tech/tags/2.md>), [2013](<https://devfeed.tech/tags/2013.md>), [big-tech](<https://devfeed.tech/tags/big-tech.md>), [board](<https://devfeed.tech/tags/board.md>), [ceo](<https://devfeed.tech/tags/ceo.md>), [chair](<https://devfeed.tech/tags/chair.md>), [company](<https://devfeed.tech/tags/company.md>), [data-center](<https://devfeed.tech/tags/data-center.md>), [employees](<https://devfeed.tech/tags/employees.md>), [first](<https://devfeed.tech/tags/first.md>), [game](<https://devfeed.tech/tags/game.md>), [geforce](<https://devfeed.tech/tags/geforce.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [graphics-card](<https://devfeed.tech/tags/graphics-card.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [harvey](<https://devfeed.tech/tags/harvey.md>), [industry](<https://devfeed.tech/tags/industry.md>), [jensen-huang](<https://devfeed.tech/tags/jensen-huang.md>), [leadership](<https://devfeed.tech/tags/leadership.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [nvidia-ceo](<https://devfeed.tech/tags/nvidia-ceo.md>), [opinion](<https://devfeed.tech/tags/opinion.md>), [over](<https://devfeed.tech/tags/over.md>), [pc-gaming](<https://devfeed.tech/tags/pc-gaming.md>), [project](<https://devfeed.tech/tags/project.md>), [quickly](<https://devfeed.tech/tags/quickly.md>), [separate](<https://devfeed.tech/tags/separate.md>), [serve](<https://devfeed.tech/tags/serve.md>), [synopsys](<https://devfeed.tech/tags/synopsys.md>)

### AI overview

After Jensen Huang's resignation, CFO Colette Kress is running Nvidia on an interim basis while the company searches for a successor; longtime director Harvey Jones has become board chair. The article says there is no clear successor: candidates discussed range from Nvidia executives to leaders at Arm, Intel, Apple, and AMD, with differing strengths and gaps in operating experience. It argues GeForce faces pressure because gaming is small beside data center revenue and competes for scarce memory and manufacturing capacity. A successor less attached to Nvidia's gaming roots could let the business fade through fewer launches and longer gaps. Yet GeForce also brings developers into CUDA, shares GPU research with data center products, and supplies Nintendo Switch 2, making a sale or spin-off complicated. The piece also describes Nvidia's extensive AI-industry financing and reports that its product roadmap and demand remain strong.

### Source excerpt

Nvidia moved quickly to project continuity. In an internal memo, longtime director Harvey Jones told employees he would serve as the company's first-ever board chair. Jones, a former Synopsys CEO, has sat on Nvidia's board since its founding in 1993. The fact that Nvidia never had a separate chair until... Read Entire Article

## AMD Tunes Up CPUs For Agentic AI With "Venice" Epyc Processors

DevFeed: [AMD Tunes Up CPUs For Agentic AI With "Venice" Epyc Processors](<https://devfeed.tech/articles/amd-tunes-up-cpus-for-agentic-ai-with-venice-epyc-processors-126819.md>)

Original publisher: [Read original article](<https://www.nextplatform.com/compute/2026/11/10/amd-tunes-up-cpus-for-agentic-ai-with-venice-epyc-processors/5308850>)

Author: Jeff Burt

Published: 2026-11-10T17:06:06Z

Content type: news

Language: en

Sources: [The Next Platform: In-depth coverage of high end computing](<https://devfeed.tech/sources/the-next-platform-in-depth-coverage-of-high-end-computing.md>)

Topics: [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [x86](<https://devfeed.tech/topics/x86.md>), [Arm](<https://devfeed.tech/topics/arm.md>), [Graviton](<https://devfeed.tech/topics/graviton.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [1-5](<https://devfeed.tech/tags/1-5.md>), [1-6](<https://devfeed.tech/tags/1-6.md>), [2018](<https://devfeed.tech/tags/2018.md>), [2022](<https://devfeed.tech/tags/2022.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [amd](<https://devfeed.tech/tags/amd.md>), [chatbot](<https://devfeed.tech/tags/chatbot.md>), [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [chatgpt-chatbot](<https://devfeed.tech/tags/chatgpt-chatbot.md>), [compute](<https://devfeed.tech/tags/compute.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [cpus](<https://devfeed.tech/tags/cpus.md>), [epyc](<https://devfeed.tech/tags/epyc.md>), [introduction](<https://devfeed.tech/tags/introduction.md>), [launch](<https://devfeed.tech/tags/launch.md>), [openai](<https://devfeed.tech/tags/openai.md>), [processors](<https://devfeed.tech/tags/processors.md>), [up](<https://devfeed.tech/tags/up.md>), [venice](<https://devfeed.tech/tags/venice.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

AMD presents its 6th Gen Epyc "Venice" CPUs as a fit for agentic AI, whose multi-step workflows involve orchestration, databases, APIs, enterprise tools and isolated code execution. The article says agentic AI could increase CPU demand relative to GPUs, though AMD did not design Venice specifically for it. AMD reports 1.9x throughput versus prior Turin processors; Venice scales to 96 cores at 5.3 GHz, with 16 DDR5 channels delivering 1.6 TB/s and PCIe Gen 6. AMD also claims a 256-core, 400-watt model achieves 3.3x Vera's agents per watt and higher agents per dollar than Intel's 6th Gen Xeons. These are company comparisons; the article notes ephemeral agent tools lack a well-defined benchmark and describes AMD's selected workloads as representative samples.

### Source excerpt

The introduction of the ChatGPT chatbot by OpenAI in late 2022 supercharged the launch of of the Gen ...

## Seeed Studio XIAO STM32C5 development board features dual CAN FD and a 6-axis IMU with programmable heating

DevFeed: [Seeed Studio XIAO STM32C5 development board features dual CAN FD and a 6-axis IMU with programmable heating](<https://devfeed.tech/articles/seeed-studio-xiao-stm32c5-development-board-features-dual-can-fd-and-a-6-axis-imu-with-programmable-heating-123536.md>)

Original publisher: [Read original article](<https://www.cnx-software.com/2026/11/09/seeed-studio-xiao-stm32c5-development-board-features-dual-can-fd-and-a-6-axis-imu-with-programmable-heating/>)

Author: Debashis Das

Published: 2026-11-09T12:00:41Z

Content type: news

Language: en

Sources: [CNX Software - Embedded Systems News](<https://devfeed.tech/sources/cnx-software-embedded-systems-news.md>)

Topics: [Embedded Systems](<https://devfeed.tech/topics/embedded-systems.md>), [seeed studio](<https://devfeed.tech/topics/seeed-studio.md>), [Arm](<https://devfeed.tech/topics/arm.md>), [Robotics](<https://devfeed.tech/topics/robotics.md>), [USB](<https://devfeed.tech/topics/usb.md>)

Tags: [automation](<https://devfeed.tech/tags/automation.md>), [battery](<https://devfeed.tech/tags/battery.md>), [can](<https://devfeed.tech/tags/can.md>), [can-bus](<https://devfeed.tech/tags/can-bus.md>), [cortex-m33](<https://devfeed.tech/tags/cortex-m33.md>), [development-board](<https://devfeed.tech/tags/development-board.md>), [firmware](<https://devfeed.tech/tags/firmware.md>), [flash](<https://devfeed.tech/tags/flash.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [imu](<https://devfeed.tech/tags/imu.md>), [industrial](<https://devfeed.tech/tags/industrial.md>), [micropython](<https://devfeed.tech/tags/micropython.md>), [motion-sensing](<https://devfeed.tech/tags/motion-sensing.md>), [robotics](<https://devfeed.tech/tags/robotics.md>), [rtos](<https://devfeed.tech/tags/rtos.md>), [seeed-studio](<https://devfeed.tech/tags/seeed-studio.md>), [sensors](<https://devfeed.tech/tags/sensors.md>), [stm32](<https://devfeed.tech/tags/stm32.md>), [stmicro-stm32](<https://devfeed.tech/tags/stmicro-stm32.md>), [stmicroelectronics](<https://devfeed.tech/tags/stmicroelectronics.md>), [usb-c](<https://devfeed.tech/tags/usb-c.md>), [zephyr](<https://devfeed.tech/tags/zephyr.md>)

### AI overview

The XIAO STM32C5 pairs a 144 MHz STM32C5A3CG Arm Cortex-M33 with two CAN FD controllers and a 6-axis LSM6DS3TR-C IMU whose temperature can be regulated by PWM-controlled heating resistors to help reduce temperature-related motion-measurement drift. FDCAN2 connects to an onboard CAN FD transceiver and CANH/CANL pads; FDCAN1 exposes TX/RX for an external transceiver. The onboard 120 Ω termination is enabled by default and can be disconnected. The board also has 256 KB SRAM, 1 MB internal and 16 MB external flash, USB-C, battery charging, and XIAO-format expansion headers. Documentation and examples are listed for STM32CubeIDE, PlatformIO with Zephyr, and MicroPython. The text lists prices of $18.85 on AliExpress and $9.90 at Seeed Studio, or $10.90 for the pre-soldered version, before taxes and shipping.

### Source excerpt

Seeed Studio XIAO STM32C5 is the company's first XIAO development board based on an STMicroelectronics MCU, namely a 144 MHz STM32C5A3CG Arm Cortex-M33 microcontroller. It features two CAN FD controllers and a 6-axis IMU with programmable heating for robotics, industrial control, and motion-sensing applications. The board also includes 16MB of external flash, a 48 MHz external crystal, a USB-C port, and battery charging circuitry. One CAN FD channel is connected to an onboard transceiver, while the second requires an external transceiver. The integrated IMU heater allows firmware to control sensor temperature and reduce measurement drift from temperature changes. XIAO STM32C5 specifications: MCU - STMicroelectronics STM32C5A3CG CPU - 144 MHz Arm Cortex-M33 with FPU and DSP instructions Memory - 256KB SRAM Storage - 1MB internal flash Storage - 16MB external flash USB - USB Type-C port with USB 2.0 Full-Speed support (12 Mbps) CAN Bus 2x CAN FD controllers (FDCAN1 and [...] The post Seeed Studio XIAO STM32C5 development board features dual CAN FD and a 6-axis IMU with programmable heating appeared first on CNX Software - Embedded Systems News.

## HP's next CEO loves confrontation

DevFeed: [HP's next CEO loves confrontation](<https://devfeed.tech/articles/hp-s-next-ceo-loves-confrontation-119309.md>)

Original publisher: [Read original article](<https://www.cio.com/article/4245262/hps-next-ceo-loves-confrontation-2.html>)

Author: Lynn Greiner

Published: 2026-11-05T17:33:55Z

Content type: news

Language: en

Sources: [CIO](<https://devfeed.tech/sources/cio.md>)

Topics: [Arm](<https://devfeed.tech/topics/arm.md>), [engineering-leadership](<https://devfeed.tech/topics/engineering-leadership.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [board](<https://devfeed.tech/tags/board.md>), [boardroom](<https://devfeed.tech/tags/boardroom.md>), [business](<https://devfeed.tech/tags/business.md>), [ceo](<https://devfeed.tech/tags/ceo.md>), [commercial-providers](<https://devfeed.tech/tags/commercial-providers.md>), [commercial-providers-hp-industry-markets-technology-industry-vendors-and-providers](<https://devfeed.tech/tags/commercial-providers-hp-industry-markets-technology-industry-vendors-and-providers.md>), [company](<https://devfeed.tech/tags/company.md>), [components](<https://devfeed.tech/tags/components.md>), [customer](<https://devfeed.tech/tags/customer.md>), [demand](<https://devfeed.tech/tags/demand.md>), [edition-us](<https://devfeed.tech/tags/edition-us.md>), [experience](<https://devfeed.tech/tags/experience.md>), [growth](<https://devfeed.tech/tags/growth.md>), [healthcare](<https://devfeed.tech/tags/healthcare.md>), [hp](<https://devfeed.tech/tags/hp.md>), [industry](<https://devfeed.tech/tags/industry.md>), [innovation](<https://devfeed.tech/tags/innovation.md>), [insights](<https://devfeed.tech/tags/insights.md>), [language-en](<https://devfeed.tech/tags/language-en.md>), [lead](<https://devfeed.tech/tags/lead.md>), [leadership](<https://devfeed.tech/tags/leadership.md>), [leading](<https://devfeed.tech/tags/leading.md>), [linkedin](<https://devfeed.tech/tags/linkedin.md>), [markets](<https://devfeed.tech/tags/markets.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [storytype-news](<https://devfeed.tech/tags/storytype-news.md>), [technology-industry](<https://devfeed.tech/tags/technology-industry.md>), [vendors-and-providers](<https://devfeed.tech/tags/vendors-and-providers.md>)

### AI overview

HP has appointed former GSK CEO Emma Walmsley to lead the company starting January 4, 2027, as declining printing revenue and AI-related component demand that is raising PC prices press for a business shake-up. At GSK, she turned around finances and spun off consumer healthcare as Haleon; she also spent 17 years at L'Oréal and served on Microsoft's board, though this will be her first tech CEO role. The article describes her as willing to invite confrontation in the boardroom. HP leaders highlighted her cross-industry experience, strategic thinking, customer insight, and people-first approach. Interim CEO Bruce Broussard will become board chair; former CEO Enrique Lores left for PayPal.

### Source excerpt

The new year will see a new CEO for HP, which after a nine-month search has named Emma Walmsley to lead the company from January 4, 2027. Walmsley was previously CEO of drug company GSK, where she turned around its finances and spun off its consumer healthcare business into a new company, Haleon. She has a reputation for courting confrontation rather than yes-men in the boardroom. HP needs a shake-up as revenue from printing declines and AI-driven demand for components is forcing up PC prices. She will take over from HP's interim CEO Bruce Broussard, who stepped in in February when former CEO Enrique Lores left the company after more than 25 years to become president and CEO at PayPal. There's a consolation prize for Broussard, who will become chair of HP's board, succeeding Chip Bergh who remains a board member. Although Walmsley has been on Microsoft's board for seven years (she is stepping down in December), this is her first foray into leading a tech company. Her almost 16-year tenure at GSK included more than eight years as CEO, and earlier in her career, she spent 17 years at L'Oréal. Bergh said that during the executive search, she stood out "for the strength of her leadership experience across multiple industries, the clarity of her strategic thinking and her ability to translate customer insights into new growth." He particularly cited her people-first leadership approach. Walmsley reiterated her commitment to the philosophy in a post on LinkedIn. "HP has an extraordinary innovation heritage, an inspiring purpose and an incredible opportunity ahead as AI reshapes technology and what customers need from it. I'm excited to build on those strengths and help translate innovation into impact," she wrote. "Behind every innovation are the people who work to make someone's day a little easier, their work more productive, their ideas possible. In an age of AI, I believe human leadership has never mattered more. It's a privilege to be joining this team." Announcing W

## Qualcomm's stock falls on revenue miss and weak guidance; Arm and GlobalFoundries do little better

DevFeed: [Qualcomm's stock falls on revenue miss and weak guidance; Arm and GlobalFoundries do little better](<https://devfeed.tech/articles/qualcomm-s-stock-falls-on-revenue-miss-and-weak-guidance-arm-and-globalfoundries-do-little-better-117839.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/11/04/qualcomms-stock-falls-on-revenue-miss-and-weak-guidance-arm-and-globalfoundries-do-little-better/>)

Author: Mike Wheatley

Published: 2026-11-04T23:42:09Z

Content type: news

Language: en

Sources: [SiliconANGLE](<https://devfeed.tech/sources/siliconangle.md>)

Topics: [Qualcomm](<https://devfeed.tech/topics/qualcomm.md>), [Arm](<https://devfeed.tech/topics/arm.md>)

Tags: [advanced](<https://devfeed.tech/tags/advanced.md>), [advanced-micro-devices](<https://devfeed.tech/tags/advanced-micro-devices.md>), [ai-chips](<https://devfeed.tech/tags/ai-chips.md>), [ai-data-center](<https://devfeed.tech/tags/ai-data-center.md>), [arm](<https://devfeed.tech/tags/arm.md>), [arm-stock](<https://devfeed.tech/tags/arm-stock.md>), [better](<https://devfeed.tech/tags/better.md>), [but](<https://devfeed.tech/tags/but.md>), [chip-revenue](<https://devfeed.tech/tags/chip-revenue.md>), [chip-sales](<https://devfeed.tech/tags/chip-sales.md>), [chipmakers](<https://devfeed.tech/tags/chipmakers.md>), [cristiano-amon](<https://devfeed.tech/tags/cristiano-amon.md>), [data-center-chips](<https://devfeed.tech/tags/data-center-chips.md>), [devices](<https://devfeed.tech/tags/devices.md>), [earnings](<https://devfeed.tech/tags/earnings.md>), [falls](<https://devfeed.tech/tags/falls.md>), [financial](<https://devfeed.tech/tags/financial.md>), [financial-results](<https://devfeed.tech/tags/financial-results.md>), [globalfoundries](<https://devfeed.tech/tags/globalfoundries.md>), [globalfoundries-stock](<https://devfeed.tech/tags/globalfoundries-stock.md>), [guidance](<https://devfeed.tech/tags/guidance.md>), [inc](<https://devfeed.tech/tags/inc.md>), [infra](<https://devfeed.tech/tags/infra.md>), [investors](<https://devfeed.tech/tags/investors.md>), [just](<https://devfeed.tech/tags/just.md>), [little](<https://devfeed.tech/tags/little.md>), [news](<https://devfeed.tech/tags/news.md>), [qualcomm](<https://devfeed.tech/tags/qualcomm.md>), [qualcomm-shares](<https://devfeed.tech/tags/qualcomm-shares.md>), [qualcomm-stock](<https://devfeed.tech/tags/qualcomm-stock.md>), [revenue](<https://devfeed.tech/tags/revenue.md>), [stock](<https://devfeed.tech/tags/stock.md>), [the-latest](<https://devfeed.tech/tags/the-latest.md>), [top-story-3](<https://devfeed.tech/tags/top-story-3.md>), [top-story-6](<https://devfeed.tech/tags/top-story-6.md>)

### AI overview

Qualcomm's revenue miss and below-consensus guidance weighed on its shares despite a slight earnings beat: smartphone chip sales fell 26% amid pressure on handset demand, while automotive sales rose 89% and data center revenue reached $650 million. CEO Cristiano Amon said growth was constrained by supply and targeted more than $5 billion in data center revenue by fiscal 2027. Arm beat quarterly estimates, with revenue up 27% and data center royalties doubling, but its guidance was only modestly above forecasts; its shares fell 2% after-hours. GlobalFoundries slightly beat estimates and forecast, with sales up 12% on demand from AI and data center customers, but its shares were flat. The excerpt distinguishes Qualcomm's chip and modem sales, Arm's processor design licensing, and GlobalFoundries' contract manufacturing.

### Source excerpt

Chipmakers Qualcomm Inc., Arm Holdings Ltd. and GlobalFoundries Ltd. struggled to move the needle today after reporting financial results that clearly left investors wanting more. After an impressive earnings beat from Advanced Micro Devices Inc. just 24 hours earlier, investors may have had heightened expectations, but if they did, they were clearly let down by [...] The post Qualcomm's stock falls on revenue miss and weak guidance; Arm and GlobalFoundries do little better appeared first on SiliconANGLE.

## RGB Photo Enhancement with Deep Learning on Smartphone GPUs: Mobile AI 2026 Challenge Report

DevFeed: [RGB Photo Enhancement with Deep Learning on Smartphone GPUs: Mobile AI 2026 Challenge Report](<https://devfeed.tech/articles/rgb-photo-enhancement-with-deep-learning-on-smartphone-gpus-mobile-ai-2026-challenge-report-117554.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.05024>)

Author: Andrey Ignatov, Georgy Perevozchikov, Radu Timofte, Dong Zhang, Zhao Ran, Yang Zhang, Xiaochen Li, Shichang Ju, Yiqin Cao, Yang Lu, Nguyen Nhu Tinh Anh, To Thanh Dat, Nguyen Ngoc Ky Duyen, Nguyen Tron

Published: 2026-11-04T05:00:00Z

Content type: news

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Deep learning](<https://devfeed.tech/topics/deep-learning.md>), [Image](<https://devfeed.tech/topics/image.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Adreno](<https://devfeed.tech/topics/adreno.md>), [Arm](<https://devfeed.tech/topics/arm.md>), [Qualcomm](<https://devfeed.tech/topics/qualcomm.md>), [iphone](<https://devfeed.tech/topics/iphone.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [adreno](<https://devfeed.tech/tags/adreno.md>), [ai](<https://devfeed.tech/tags/ai.md>), [arm](<https://devfeed.tech/tags/arm.md>), [camera](<https://devfeed.tech/tags/camera.md>), [challenge](<https://devfeed.tech/tags/challenge.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [design](<https://devfeed.tech/tags/design.md>), [device](<https://devfeed.tech/tags/device.md>), [enhancement](<https://devfeed.tech/tags/enhancement.md>), [fast](<https://devfeed.tech/tags/fast.md>), [gpus](<https://devfeed.tech/tags/gpus.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [mobile](<https://devfeed.tech/tags/mobile.md>), [mobile-ai](<https://devfeed.tech/tags/mobile-ai.md>), [photo](<https://devfeed.tech/tags/photo.md>), [report](<https://devfeed.tech/tags/report.md>), [rgb](<https://devfeed.tech/tags/rgb.md>), [smartphone](<https://devfeed.tech/tags/smartphone.md>)

### AI overview

The Mobile AI 2026 challenge focused on deep learning models that enhance RGB photos directly on smartphone GPUs. Participants used the DPED dataset, which pairs images from an iPhone 3GS with photos from a Canon 70D DSLR. Runtime was measured on Qualcomm's Snapdragon 8 Elite Gen 5 with an Adreno GPU and MediaTek's Dimensity 9500 with a Mali GPU. The report says top solutions enhanced Full HD images on both platforms in under 300 milliseconds; the excerpt does not provide model-level comparisons or image-quality results.

### Source excerpt

arXiv:2611.05024v1 Announce Type: cross Abstract: On-device RGB photo enhancement is a popular task that is needed for quality improvement of photos captured with mobile devices as well as for retouching of images acquired through other sources. This creates a need for efficient deep learning models for this problem that are not only performant but can also be deployed on constrained mobile hardware. In this Mobile AI challenge, we address this problem and propose participants to design fast solutions that can perform comprehensive enhancement of RGB photos while running on popular smartphone GPUs from Qualcomm and Arm. For this, the participants were provided with a large-scale DPED dataset consisting of RGB image pairs captured with an old iPhone 3GS smartphone and a professional Canon 70D DSLR camera. The runtime of all models was evaluated on the Snapdragon 8 Elite Gen 5 and Dimensity 9500 chipsets with the Adreno and Mali GPUs, respectively. Top solutions proposed in this challenge are able to enhance Full HD resolution RGB images on both platforms under 300 milliseconds. A comprehensive description of the models developed in the challenge is provided in this paper.

## Andes Waits For Market Momentum For Cuzco CPU

DevFeed: [Andes Waits For Market Momentum For Cuzco CPU](<https://devfeed.tech/articles/andes-waits-for-market-momentum-for-cuzco-cpu-112532.md>)

Original publisher: [Read original article](<https://www.eetimes.com/andes-waits-for-market-momentum-for-cuzco-cpu/>)

Author: Sally Ward-Foxton

Published: 2026-11-02T12:00:00Z

Content type: news

Language: en

Sources: [EE Times](<https://devfeed.tech/sources/ee-times.md>)

Topics: [rv32i](<https://devfeed.tech/topics/rv32i.md>), [Arm](<https://devfeed.tech/topics/arm.md>), [Advanced AI workflows](<https://devfeed.tech/topics/advanced-ai-workflows.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-chip](<https://devfeed.tech/tags/ai-chip.md>), [analog](<https://devfeed.tech/tags/analog.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [business](<https://devfeed.tech/tags/business.md>), [community](<https://devfeed.tech/tags/community.md>), [compiler](<https://devfeed.tech/tags/compiler.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [cto](<https://devfeed.tech/tags/cto.md>), [data-center](<https://devfeed.tech/tags/data-center.md>), [data-movement](<https://devfeed.tech/tags/data-movement.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [designline](<https://devfeed.tech/tags/designline.md>), [development](<https://devfeed.tech/tags/development.md>), [digital](<https://devfeed.tech/tags/digital.md>), [education](<https://devfeed.tech/tags/education.md>), [ee-times](<https://devfeed.tech/tags/ee-times.md>), [ee-times-university](<https://devfeed.tech/tags/ee-times-university.md>), [eelife](<https://devfeed.tech/tags/eelife.md>), [eelive-electronic-design](<https://devfeed.tech/tags/eelive-electronic-design.md>), [eet](<https://devfeed.tech/tags/eet.md>), [electrical-engineering](<https://devfeed.tech/tags/electrical-engineering.md>), [electronic-components](<https://devfeed.tech/tags/electronic-components.md>), [electronic-engineering-times](<https://devfeed.tech/tags/electronic-engineering-times.md>), [electronics](<https://devfeed.tech/tags/electronics.md>), [embedded](<https://devfeed.tech/tags/embedded.md>), [embedded-systems](<https://devfeed.tech/tags/embedded-systems.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [fundamentals-courses](<https://devfeed.tech/tags/fundamentals-courses.md>), [hit](<https://devfeed.tech/tags/hit.md>), [ip](<https://devfeed.tech/tags/ip.md>), [ip-intellectual-property](<https://devfeed.tech/tags/ip-intellectual-property.md>), [learning](<https://devfeed.tech/tags/learning.md>), [mixed-signal](<https://devfeed.tech/tags/mixed-signal.md>), [news](<https://devfeed.tech/tags/news.md>), [opinion](<https://devfeed.tech/tags/opinion.md>), [part-search](<https://devfeed.tech/tags/part-search.md>), [product-search](<https://devfeed.tech/tags/product-search.md>), [risc-v](<https://devfeed.tech/tags/risc-v.md>), [semiconductors](<https://devfeed.tech/tags/semiconductors.md>), [software](<https://devfeed.tech/tags/software.md>), [tech-papers](<https://devfeed.tech/tags/tech-papers.md>), [technology](<https://devfeed.tech/tags/technology.md>), [video](<https://devfeed.tech/tags/video.md>)

### AI overview

Andes has slowed development of its Cuzco high-end RISC-V CPU IP and brought the Condor effort back in-house, shifting engineering resources toward its faster-growing AI business. CTO Charlie Su said AI contributes half of revenue and is driving demanding custom-core delivery schedules; inquiries about Cuzco have not yet converted into enough licenses to justify prioritizing completion. Andes still intends to productize Cuzco, potentially under another name, but will wait for stronger market momentum and focus on making the design reusable. Meanwhile, it is prioritizing a storage-market main processor core, alongside automotive and robotics. The excerpt says Andes uses AI agents across engineering with human review, and reports Su's view that changes to Arm's business model have improved competitors' prospects at the high end.

### Source excerpt

Andes CTO Charlie Su said the company put its high-end RISC-V CPU on the back burner for commercial reasons. The post Andes Waits For Market Momentum For Cuzco CPU appeared first on EE Times.

## How Arm is redefining the PC ecosystem

DevFeed: [How Arm is redefining the PC ecosystem](<https://devfeed.tech/articles/how-arm-is-redefining-the-pc-ecosystem-112941.md>)

Original publisher: [Read original article](<https://newsroom.arm.com/blog/arm-based-pcs-future-personal-computing>)

Author: Arm Editorial Team

Published: 2026-11-02T11:10:25Z

Content type: article

Language: en

Sources: [Arm Newsroom](<https://devfeed.tech/sources/arm-newsroom.md>)

Topics: [Arm](<https://devfeed.tech/topics/arm.md>), [pc](<https://devfeed.tech/topics/pc.md>), [Claude](<https://devfeed.tech/topics/claude.md>)

Tags: [applications](<https://devfeed.tech/tags/applications.md>), [arm](<https://devfeed.tech/tags/arm.md>), [ecosystem](<https://devfeed.tech/tags/ecosystem.md>), [pc](<https://devfeed.tech/tags/pc.md>), [silicon](<https://devfeed.tech/tags/silicon.md>)

### AI overview

Arm-based PCs now span ultra-portable laptops and AI workstations, with platforms for Windows and Googlebooks. The text highlights NVIDIA's Arm-based RTX Spark, which is intended to bring local AI capabilities to Windows PCs from several manufacturers, and Arm and Google's work on efficient, portable Googlebook systems for on-device AI. Emerging agentic workloads may run across personal devices and cloud infrastructure, using hybrid intelligence to match tasks to compute resources. Windows on Arm has thousands of verified applications and games; Arm AppReady for Windows offers resources and engineering expertise for building, porting, and optimizing native apps. The text also says Python 3.15 runs natively on Windows on Arm and describes tools for assessing dependencies, build settings, architecture-specific code, and performance paths, with access to Arm experts for complex migration issues.

### Source excerpt

From new Arm-based silicon and PCs to thousands of applications, Arm is reshaping the next era of personal computing. The post How Arm is redefining the PC ecosystem appeared first on Arm Newsroom.

## Top Arm-based innovations advancing on-device AI, cloud infrastructure, and physical AI in October 2026

DevFeed: [Top Arm-based innovations advancing on-device AI, cloud infrastructure, and physical AI in October 2026](<https://devfeed.tech/articles/top-arm-based-innovations-advancing-on-device-ai-cloud-infrastructure-and-physical-ai-in-october-2026-112942.md>)

Original publisher: [Read original article](<https://newsroom.arm.com/blog/top-arm-based-innovations-in-october-2026>)

Author: Arm Editorial Team

Published: 2026-11-02T11:05:25Z

Content type: article

Language: en

Sources: [Arm Newsroom](<https://devfeed.tech/sources/arm-newsroom.md>)

Topics: [Physical AI](<https://devfeed.tech/topics/physical-ai.md>), [On-device AI](<https://devfeed.tech/topics/on-device-ai.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [Arm](<https://devfeed.tech/topics/arm.md>), [Azure](<https://devfeed.tech/topics/azure.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [ai-performance](<https://devfeed.tech/tags/ai-performance.md>), [ai-powered-wearables](<https://devfeed.tech/tags/ai-powered-wearables.md>), [ai-workloads](<https://devfeed.tech/tags/ai-workloads.md>), [arm](<https://devfeed.tech/tags/arm.md>), [autonomous-vehicles](<https://devfeed.tech/tags/autonomous-vehicles.md>), [azure](<https://devfeed.tech/tags/azure.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [cloud-infrastructure](<https://devfeed.tech/tags/cloud-infrastructure.md>), [device](<https://devfeed.tech/tags/device.md>), [on-device-ai](<https://devfeed.tech/tags/on-device-ai.md>), [physical-ai](<https://devfeed.tech/tags/physical-ai.md>)

### AI overview

October's Arm ecosystem examples show AI deployment across vehicles, wearables, robotics, mobile devices and cloud infrastructure, with distinct approaches to sensing, compute and model optimization. Tensor's RoboCar distributes 433 Arm-based cores across centralized AI, sensing and vehicle control; PSYONIC's Ability Hand uses 12 microcontrollers for touch, motor control and feedback, and can provide human grip data for robotics research. For local inference, Liquid AI reports provisional LFM3-1.7B benchmarks on Arm CPUs: SME2 enabled 3.1x faster prefill and 1.5x faster decoding using two threads. Arm AI Model Optimizer, available through an Early Access Program, showed up to 5.9x faster inference and 74% less memory for one Raspberry Pi 5 image-classification model, with a small reported accuracy change. Arm and Tencent reduced a neural image decoder module's latency from 61 ms to 30 ms for a 2K image on a reference smartphone using two threads. In cloud search, Elastic reports up to 44% better price-performance on Azure Cobalt instances versus tested Fsv2 instances. These reported results are specific to the stated models, workloads and test setups.

### Source excerpt

From AI-powered wearables to autonomous vehicles, October highlighted the strength of the Arm ecosystem in bringing more intelligence into devices, infrastructure, and the physical world. The post Top Arm-based innovations advancing on-device AI, cloud infrastructure, and physical AI in October 2026 appeared first on Arm Newsroom.

## Why wearables are the next frontier of AI-first personal computing

DevFeed: [Why wearables are the next frontier of AI-first personal computing](<https://devfeed.tech/articles/why-wearables-are-the-next-frontier-of-ai-first-personal-computing-109897.md>)

Original publisher: [Read original article](<https://newsroom.arm.com/blog/ai-wearables-smart-glasses-arm>)

Author: Arm Editorial Team

Published: 2026-10-30T16:00:00Z

Content type: article

Language: en

Sources: [Arm Newsroom](<https://devfeed.tech/sources/arm-newsroom.md>)

Topics: [Arm](<https://devfeed.tech/topics/arm.md>), [smartdevices](<https://devfeed.tech/topics/smartdevices.md>), [Local AI](<https://devfeed.tech/topics/local-ai.md>), [Computing](<https://devfeed.tech/topics/computing.md>), [Distributed Systems & Parallel Computing](<https://devfeed.tech/topics/distributed-systems-parallel-computing.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-wearables](<https://devfeed.tech/tags/ai-wearables.md>), [ai-workloads](<https://devfeed.tech/tags/ai-workloads.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [arm](<https://devfeed.tech/tags/arm.md>), [awareness](<https://devfeed.tech/tags/awareness.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [cloud-infrastructure](<https://devfeed.tech/tags/cloud-infrastructure.md>), [compute](<https://devfeed.tech/tags/compute.md>), [compute-platform](<https://devfeed.tech/tags/compute-platform.md>), [computing](<https://devfeed.tech/tags/computing.md>), [connectivity](<https://devfeed.tech/tags/connectivity.md>), [cpus](<https://devfeed.tech/tags/cpus.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [environment](<https://devfeed.tech/tags/environment.md>), [everyday](<https://devfeed.tech/tags/everyday.md>), [glasses](<https://devfeed.tech/tags/glasses.md>), [has](<https://devfeed.tech/tags/has.md>), [smart-glasses](<https://devfeed.tech/tags/smart-glasses.md>), [wearables](<https://devfeed.tech/tags/wearables.md>)

### AI overview

AI wearables must balance useful, responsive computing with tight limits on power, heat, battery life, weight and size. The article describes a hybrid approach: run sensor processing, gesture recognition and other time-sensitive tasks on the wearable for lower latency, better privacy and some offline capability, while using a connected phone or cloud for more complex reasoning or information retrieval. Everysight's glasses are cited as an example: an Alif E4 platform with an Arm Ethos-U85 NPU performs eye-tracking inference locally, avoiding transfer of raw sensor data to a phone while meeting device constraints. Arm CPUs, Mali GPUs and Ethos-U NPUs support different wearable workloads; the article also presents Arm's shared architecture and software ecosystem as a basis for connecting wearables with phones and cloud systems. It estimates Arm technology is used in 99 percent of smart glasses.

### Source excerpt

From smart glasses to emerging AI wearables, a new generation of Arm-based devices is bringing intelligence closer to users. The post Why wearables are the next frontier of AI-first personal computing appeared first on Arm Newsroom.

## Build, test and optimize faster: Arm and GitHub accelerate agentic AI development

DevFeed: [Build, test and optimize faster: Arm and GitHub accelerate agentic AI development](<https://devfeed.tech/articles/build-test-and-optimize-faster-arm-and-github-accelerate-agentic-ai-development-108332.md>)

Original publisher: [Read original article](<https://newsroom.arm.com/blog/arm-github-accelerate-agentic-ai-development>)

Author: Shantu Roy

Published: 2026-10-29T16:02:31Z

Content type: article

Language: en

Sources: [Arm Newsroom](<https://devfeed.tech/sources/arm-newsroom.md>)

Topics: [GitHub Copilot CLI](<https://devfeed.tech/topics/github-copilot-cli.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>), [GitHub Actions](<https://devfeed.tech/topics/github-actions.md>), [GitHub](<https://devfeed.tech/topics/github.md>), [Arm](<https://devfeed.tech/topics/arm.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [Architecture & optimization](<https://devfeed.tech/topics/architecture-optimization.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-ai-development](<https://devfeed.tech/tags/agentic-ai-development.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [ai-development](<https://devfeed.tech/tags/ai-development.md>), [arm](<https://devfeed.tech/tags/arm.md>), [build](<https://devfeed.tech/tags/build.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [development](<https://devfeed.tech/tags/development.md>), [faster](<https://devfeed.tech/tags/faster.md>), [github](<https://devfeed.tech/tags/github.md>), [iteration](<https://devfeed.tech/tags/iteration.md>), [native](<https://devfeed.tech/tags/native.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [optimize](<https://devfeed.tech/tags/optimize.md>), [test](<https://devfeed.tech/tags/test.md>)

### AI overview

The workflow runs GitHub Copilot CLI on organization-controlled Arm compute so agents can edit code, build, test, and investigate failures natively, giving earlier feedback on Arm-specific dependencies and runtime behavior without emulation. Developers can use measurements such as execution time, latency, memory behavior, and throughput to guide optimization. GitHub pull requests support review, while GitHub Actions on Arm64 runners provide a separate, repeatable build and test stage. The approach reduces architecture switching and handoffs; developers remain responsible for reviewing agent changes and validating correctness.

### Source excerpt

Through ongoing collaboration with GitHub, Arm is bringing AI coding agents into native Arm development workflows, enabling earlier testing, faster iteration, and greater optimization using real performance data. The post Build, test and optimize faster: Arm and GitHub accelerate agentic AI development appeared first on Arm Newsroom.

## Combinatorial Lock for Trojan-Resilient AI Engines via Hash-Assisted Spectral Filtering

DevFeed: [Combinatorial Lock for Trojan-Resilient AI Engines via Hash-Assisted Spectral Filtering](<https://devfeed.tech/articles/combinatorial-lock-for-trojan-resilient-ai-engines-via-hash-assisted-spectral-filtering-101396.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.33437>)

Author: Soumita Chatterjee, Sudip Ghosh, Tamal Ghosh, Bhargab B. Bhattacharya, Hafizur Rahaman

Published: 2026-10-27T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [AI software supply chain security](<https://devfeed.tech/topics/ai-software-supply-chain-security.md>), [Mixture of Experts (MoE)](<https://devfeed.tech/topics/mixture-of-experts-moe.md>), [Arm](<https://devfeed.tech/topics/arm.md>)

Tags: [activation](<https://devfeed.tech/tags/activation.md>), [ai](<https://devfeed.tech/tags/ai.md>), [asic](<https://devfeed.tech/tags/asic.md>), [asr](<https://devfeed.tech/tags/asr.md>), [attack](<https://devfeed.tech/tags/attack.md>), [backdoor](<https://devfeed.tech/tags/backdoor.md>), [cs-ar](<https://devfeed.tech/tags/cs-ar.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [defense](<https://devfeed.tech/tags/defense.md>), [detection](<https://devfeed.tech/tags/detection.md>), [fpga](<https://devfeed.tech/tags/fpga.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [hash](<https://devfeed.tech/tags/hash.md>), [latency](<https://devfeed.tech/tags/latency.md>), [logic](<https://devfeed.tech/tags/logic.md>), [mitigation](<https://devfeed.tech/tags/mitigation.md>), [model](<https://devfeed.tech/tags/model.md>), [models](<https://devfeed.tech/tags/models.md>), [operations](<https://devfeed.tech/tags/operations.md>), [training](<https://devfeed.tech/tags/training.md>), [trigger](<https://devfeed.tech/tags/trigger.md>), [trojan](<https://devfeed.tech/tags/trojan.md>)

### AI overview

Combinatorial Lock targets models poisoned with multiple trigger types using a training-free, reference-calibrated defense. It pairs anomaly-gated spectral scrubbing, applied only to inputs flagged as anomalous, with hash-compressed binary activation signatures checked by detection experts, including one for compound attacks. The authors report reducing near-100% attack success to single digits across six models, poisoning rates of 1-10%, and 1-9 simultaneous triggers; one tuned operating point reaches 0.1% attack success while retaining 97.8% clean accuracy. ASIC and FPGA implementations add 19-20% latency overhead. These are reported results from the supplied abstract.

### Source excerpt

arXiv:2610.33437v1 Announce Type: new Abstract: Multi-trigger backdoor attacks, in which heterogeneous trigger mechanisms (e.g., patch, blend, warping, and the latent-domain Spy-Watermark) coexist within a single poisoned model, cannot be addressed by existing shortcut-based defenses that assume a single, static attack mechanism. Current multi-trigger remedies (BU+FT, BU+ANP, and BU+ABL) rely on backdoor unlearning, which incurs high training costs and loses effectiveness at low poisoning ratios. This paper proposes Combinatorial Lock, a training-free, reference-calibrated defense that reduces multi-trigger identification to a combinatorial problem over binary activation signatures. This formulation is the key novelty: it yields a multi-trigger defense that is training-free, trigger-oblivious, and directly implementable in hardware, since its decision rules can be evaluated with integer and logic operations. The framework combines anomaly-gated spectral scrubbing, which removes the malicious subspace only from inputs identified as anomalous, with a hash-compressed combinatorial signature verified by an ensemble of detection experts, including a compound-attack-aware expert for multi-trigger inputs. A joint threshold-shrinkage search identifies an operating point ($\tau$ at the 97.1st percentile, $\gamma = 0.78$) that reduces the attack success rate (ASR) to as low as 0.1% while preserving 97.8% clean accuracy. Evaluation on six models (ResNet18, VGG16, MobileNet, AlexNet, ViT-Small, ViT-Base) shows strong generalization: near-100% ASR drops to single digits across poisoning rates of 1-10% and 1-9 simultaneous triggers, with only gradual degradation in clean accuracy. ASIC and FPGA implementations confirm practicality, adding a consistent 19-20% latency overhead across all evaluated architectures and establishing Combinatorial Lock as a hardware-native approach to multi-trigger backdoor mitigation.

## Rockchip RK3576-powered SMARC 2.2 system-on-module and development board target Edge AI applications

DevFeed: [Rockchip RK3576-powered SMARC 2.2 system-on-module and development board target Edge AI applications](<https://devfeed.tech/articles/rockchip-rk3576-powered-smarc-2-2-system-on-module-and-development-board-target-edge-ai-applications-100986.md>)

Original publisher: [Read original article](<https://www.cnx-software.com/2026/10/27/rockchip-rk3576-powered-smarc-2-2-system-on-module-and-development-board-target-edge-ai-applications/>)

Author: Jean-Luc Aufranc (CNXSoft)

Published: 2026-10-27T00:00:25Z

Content type: news

Language: en

Sources: [CNX Software - Embedded Systems News](<https://devfeed.tech/sources/cnx-software-embedded-systems-news.md>)

Topics: [AI tools for developers](<https://devfeed.tech/topics/ai-tools-for-developers.md>), [Arm](<https://devfeed.tech/topics/arm.md>), [Bluetooth](<https://devfeed.tech/topics/bluetooth.md>)

Tags: [4g-lte](<https://devfeed.tech/tags/4g-lte.md>), [5g](<https://devfeed.tech/tags/5g.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-applications](<https://devfeed.tech/tags/ai-applications.md>), [android](<https://devfeed.tech/tags/android.md>), [board](<https://devfeed.tech/tags/board.md>), [cortex](<https://devfeed.tech/tags/cortex.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [debian](<https://devfeed.tech/tags/debian.md>), [development-board](<https://devfeed.tech/tags/development-board.md>), [edge](<https://devfeed.tech/tags/edge.md>), [edge-ai](<https://devfeed.tech/tags/edge-ai.md>), [emmc](<https://devfeed.tech/tags/emmc.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [industrial](<https://devfeed.tech/tags/industrial.md>), [linux](<https://devfeed.tech/tags/linux.md>), [linux-6-x](<https://devfeed.tech/tags/linux-6-x.md>), [lpddr5](<https://devfeed.tech/tags/lpddr5.md>), [module](<https://devfeed.tech/tags/module.md>), [myir](<https://devfeed.tech/tags/myir.md>), [npu](<https://devfeed.tech/tags/npu.md>), [rk3576](<https://devfeed.tech/tags/rk3576.md>), [rockchip](<https://devfeed.tech/tags/rockchip.md>), [rockchip-rk35xx](<https://devfeed.tech/tags/rockchip-rk35xx.md>), [smarc](<https://devfeed.tech/tags/smarc.md>), [soc](<https://devfeed.tech/tags/soc.md>), [software](<https://devfeed.tech/tags/software.md>), [som](<https://devfeed.tech/tags/som.md>), [support](<https://devfeed.tech/tags/support.md>), [yocto](<https://devfeed.tech/tags/yocto.md>)

### AI overview

MYIR's MYC-JR3576 is a 314-pin SMARC 2.2 module built around the Rockchip RK3576 (commercial) or RK3576J (industrial), with eight Cortex-A72/A53 CPU cores and a 6 TOPS NPU. Options include 4GB or 8GB LPDDR5, 32GB or 64GB eMMC, and Wi-Fi 6E/Bluetooth 5.4. Its listed interfaces include dual Gigabit Ethernet, multiple display and camera connections, USB, and PCIe 2.1 multiplexed with SATA III. MYIR offers a carrier-board development platform with storage, display, camera, cellular, and isolated serial/CAN interfaces. Linux 6.1 (Debian/Yocto) and Android 15 are supported, but the BSP is provided only to customers. The excerpt lists module prices of $192 and $209, development kits at $279 or $293, and says they are shipping; sample pricing applies to the first two units. Carrier-board ports marked N/A are not supported by this module, and the optional Wi-Fi module is rated for -20 to 70°C.

### Source excerpt

MYIR MYC-JR3576 is a SMARC 2.2 system-on-module (SoM) powered by a Rockchip RK3576/RK3576J octa-core Cortex-A72/A53 SoC with a 6 TOPS NPU designed for Edge AI applications. It features up to 8GB LPDDR5, up to 64GB eMMC flash, an optional WiFI 6E and Bluetooth 5.4 module, and exposes all I/Os through a 314-pin MXM connector as defined in the SMARC 2.2 standard. The company says it's the socketed counterpart to its LGA-packaged MYC-LR3576 (43 x 45 mm) module introduced in 2024, so the same processor is now available in both solder-down and standard form factors from MYiR. MYC-JR3576 - Rockchip RK3576 SMARC 2.2 module MYIR MYC-JR3576 specifications: SoC - Rockchip RK3576 (commercial) or RK3576J (industrial) CPU 4x Cortex-A72 cores @ 2.2GHz, four Cortex-A53 cores @ 1.8GHz Arm Cortex-M0 MCU at 400MHz GPU - ARM Mali-G52 MC3 GPU with support for OpenGL ES 1.1, 2.0 and 3.2, OpenCL up to 2.0 and [...] The post Rockchip RK3576-powered SMARC 2.2 system-on-module and development board target Edge AI applications appeared first on CNX Software - Embedded Systems News.

## Optimizing Streaming Speech Recognition on Arm® Edge Devices with ExecuTorch

DevFeed: [Optimizing Streaming Speech Recognition on Arm® Edge Devices with ExecuTorch](<https://devfeed.tech/articles/optimizing-streaming-speech-recognition-on-arm-edge-devices-with-executorch-102395.md>)

Original publisher: [Read original article](<https://pytorch.org/blog/optimizing-streaming-speech-recognition-on-arm-edge-devices-with-executorch/>)

Author: Josiah Davis, Principal AI Engineer, Arm and Kshitij Sisodia, Principal Software Engineer, Arm

Published: 2026-10-26T18:27:27Z

Content type: article

Language: en

Sources: [PyTorch](<https://devfeed.tech/sources/blog-pytorch.md>)

Topics: [asr](<https://devfeed.tech/topics/asr.md>), [Streaming](<https://devfeed.tech/topics/streaming.md>), [Speech Processing](<https://devfeed.tech/topics/speech-processing.md>), [quantization](<https://devfeed.tech/topics/quantization.md>), [Arm](<https://devfeed.tech/topics/arm.md>), [performance-engineering](<https://devfeed.tech/topics/performance-engineering.md>), [Local AI](<https://devfeed.tech/topics/local-ai.md>)

Tags: [arm](<https://devfeed.tech/tags/arm.md>), [asr](<https://devfeed.tech/tags/asr.md>), [automatic](<https://devfeed.tech/tags/automatic.md>), [batch](<https://devfeed.tech/tags/batch.md>), [blog](<https://devfeed.tech/tags/blog.md>), [challenge](<https://devfeed.tech/tags/challenge.md>), [device](<https://devfeed.tech/tags/device.md>), [devices](<https://devfeed.tech/tags/devices.md>), [edge](<https://devfeed.tech/tags/edge.md>), [executorch](<https://devfeed.tech/tags/executorch.md>), [first](<https://devfeed.tech/tags/first.md>), [model](<https://devfeed.tech/tags/model.md>), [optimizing](<https://devfeed.tech/tags/optimizing.md>), [post](<https://devfeed.tech/tags/post.md>), [pytorch](<https://devfeed.tech/tags/pytorch.md>), [recognition](<https://devfeed.tech/tags/recognition.md>), [speech](<https://devfeed.tech/tags/speech.md>), [speech-recognition](<https://devfeed.tech/tags/speech-recognition.md>), [streaming](<https://devfeed.tech/tags/streaming.md>), [streaming-speech-recognition](<https://devfeed.tech/tags/streaming-speech-recognition.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

Streaming ASR accuracy and response delay depend on chunk size, so evaluate both at the intended deployment cadence. In host tests across four corpora, longer chunks improved Nemotron 3.5 WER: FP16 fell from 15.2% at 80 ms to 11.5% at 1,120 ms; QC8W reached 11.7%, with a modest WER increase over FP32. On a Google Pixel 11, enabling SME2 reduced whole-recording processing time for 24.9 seconds of audio from 9.79 to 4.61 seconds for FP16 and from 5.20 to 3.24 seconds for QC8W, using one mid-core inference thread. The gains mainly came from faster GEMM, while data movement became a larger share of runtime. ETDump exposed operator timings and Arm Streamline sampled native kernels, but the tools did not link individual model layers to kernel functions. Example operating points show the tradeoff: at 560 ms, FP16 had 12.01% WER and an estimated 691 ms first-token delay; QC8W had 12.26% and 660 ms. These latency estimates assume the first output emits text.

### Source excerpt

When you're speaking to a device, you expect text to appear as you talk. That makes streaming automatic speech recognition (ASR) a different challenge from batch transcription, where the model... The post Optimizing Streaming Speech Recognition on Arm® Edge Devices with ExecuTorch appeared first on PyTorch.

[Next page](<https://devfeed.tech/topics/arm.md?cursor=WyIyMDI2LTEwLTI2VDE4OjI3OjI3KzAwOjAwIiwgImNiNDgwNzgyLWQ1Y2MtNDVjMi05M2JmLTc4OWY4Y2EyNTNhNiJd>)