Silicon Feeds
From coding agents to personal assistants and physical systems, agentic workloads are creating new demands across the full computing paradigm. The post Agentic AI explained: How agentic AI changes computing from cloud to edge appeared first on Arm Newsroom.
In development for a number of months now has been Kraid as a modern graphics compiler for recent Arm Mali GPUs. Kraid was merged for Mesa 26.2 back in June while in Mesa 27.0 due out in Q1 it will be switching to this new shader compiler by default...
NVIDIA has released version 1.9.0 of RTX Path Tracing (RTXPT), its open-source reference path tracer on GitHub, claiming roughly 20% better performance than the previous 1.8.1 release, with comparable or better image quality. RTXPT is a code sample for developers, meant as a starting point for building a path tracer…
Arm's Ami Badani cites the $2 nominal damages award as validation, while chip design experts point to open architectures such as RISC-V as the long-term alternative for AI workload flexibility. The post Arm Comments on Jury Decision in Qualcomm Trial appeared first on EE Times.
RISC-V is emerging as a candidate architecture for high-performance computing (HPC), but its competitiveness against established x86 and Arm processors remains difficult to assess because existing studies use different platforms, workloads, and methodologies, and rarely consider energy efficiency. Our work provides an…
The $2 damages award grabbed headlines, but the Arm-Qualcomm verdict’s bigger implication concerns who controls the compliance tests that custom chips must pass before shipping. The post Two Dollars and a Test Suite appeared first on EE Times.
This dashboard has weekly and nightly performance regressions for those interested. On nightly build, Kunminghu v3 has hit GEOMEAN(INT) of 21.706 with gcc, which keeps going up as the platform nears validation and release phase in Q1 2027. SPECint06/GHz on xscc is 21.924. SPECint17/GHz is 2.321, which also compares…
TrendForce's latest AI server industry research indicates that demand for server CPUs has grown steadily since the second half of 2025 as AI server providers actively introduce AI agent applications. Server CPU shipments are projected to increase 31% YoY in 2026. In 2027, continued growth in AI inference demand and…
The open-source and commercial software building blocks for agentic AI already span the Arm64 ecosystem. Here is how they come together. The post Powering agentic AI with the Arm AGI CPU software ecosystem appeared first on Arm Newsroom.
Microsoft might be working on a cheaper 12-inch Surface, and Apple's MacBook Neo looks like the reason. DigiTimes reports, citing supply chain sources, that Microsoft is reviewing the specifications of its entry-level 12-inch Surface to bring costs down, and is also rethinking which processor goes inside. The report's…
Arm claims its AGI CPU delivers nearly 2X the modeled rack performance of AMD’s EPYC 9755 across seven agentic AI workloads, using a new evaluation methodology developed with Fujitsu, Meta, and OpenAI
IBM's next-generation Z processor doesn't just run Z; it runs Arm natively too, and at 5.7 GHz that makes it the fastest Arm chip ever made. At Hot Chips 2026, IBM opened day one by unveiling a dual-ISA core that switches between z/Architecture and Armv9.3 on a per-thread basis, alongside 11 cores on Samsung 2nm, 36…
At OCP Global Summit 2026, Arm AGI CPU and a growing partner ecosystem show how open infrastructure can bring CPUs, accelerators, memory, software and rack design together for scale The post Arm at OCP Global Summit 2026: How Arm AGI CPU is scaling agentic AI infrastructure from CPU to rack appeared first on Arm…
Russian semiconductor players shows off bespoke CPU and SoC designs — Arm and Elbrus architectures on display
SK hynix detailed H-TPU, tiny in-house cores that offload routine I/O from the Arm CPUs in its next enterprise SSD controllers.
A federal jury sides with Arm on select issues, rules in favor of Qualcomm in other cases. The legal battle set to continue.
As confidential AI systems bring together more components, suppliers and stakeholders, attestation is becoming an ecosystem-wide challenge. Open standards and open-source collaboration can help make trust scalable. The post Scaling trust in confidential AI requires a common language appeared first on Arm Newsroom.
As AI moves closer to devices and physical systems, developers need to build applications that can sense, reason, and act locally while balancing latency, privacy, power, connectivity, and software complexity. The post How Arm is helping developers build local AI systems for the intelligent edge appeared first on Arm…
How Arm enables countries to build AI capability around national priorities while preserving flexibility as technology evolves The post Sovereign AI: Building national capability while preserving choice appeared first on Arm Newsroom.
A decade after Arm co-founded the Micro:bit Educational Foundation, the pocket-sized computer has grown into a global platform for creativity, digital skills, and AI literacy. The post Ten years of Arm and micro:bit: Building the next generation of technology innovators appeared first on Arm Newsroom.
Agentic AI runs its tools on the CPU, and no vendor tells you how many cores an agent needs. In this keynote at the Design Automation Conference, I compare AMD Venice, Intel Xeon 6, the Arm AGI CPU and Nvidia Vera, then follow the problem down into advanced packaging, CFETs and thermals. You also hear what EDA tools…
OpenAI chose to pair rack-scale deployments of its Jalapeño ASIC with AMD EPYC Turin CPUs, not the wave of high-performance agentic chips like Arm’s AGI or Nvidia’s Vera.
Forget the data center - the real AI action might be happening in microwatts. Sally Ward-Foxton and Ian Cutress dig into the tiniest AI chips on the market, from analog compute upstarts to ARM's revived Ethos NPU line, and debate why an "AI ASIC" isn't really an ASIC at all. Plus: a mysterious defense-linked startup…
Part 1 of an extended discussion, covering the Softbank takeover of Arm in 2016
Arm’s new Neoverse CSS N4 platform can pack up to 128 cores per die and 256 MB of L3 cache, representing a large increase in support over the previous Neoverse CSS N2 platform.
Editor’s Note (9/8/2026): Arm has reached out to clarify that the maximum IPC increase of the C2-Ultra core over the C1-Ultra core using the parameters shown in the endnotes is 7% along with the memory bandwidth improvement not factoring into the IPC improvement.
Fujitsu gave us a detailed look at its 144-core Monaka server CPU at Hot Chips 2026 on August 24, confirming for the first time that the Arm chip runs dual 256-bit SVE2 vector units, down from the 512-bit SVE in its A64FX predecessor.
Arm reveals more details about its AGI processors with up to 136 cores, but fails to disclose performance.
IBM is vastly expanding softwarte support on its mainframes with its first dual-ISA CPU core that natively supports z/Architecture and ARM instructions.
Arm-based servers accounted for nearly half of server revenue in Q1 2026, challenging x86. But in the coming years, they might catch up unit wise as well.
My take on the Nvidia RTX Spark and the GB10 die that powers it. Can Nvidia challenge Qualcomm and conquer Windows on Arm laptops? Become a supporter on Patreon: https://www.patreon.com/c/u46978634 Follow me on X: https://x.com/highyieldYT Follow me on Bsky: https://bsky.app/profile/highyield.bsky.social
The Softbank takeover and ISA transitions
Cloud-native AI and data intensive workloads coming to IBM Z and LinuxONE systems as IBM wants to make its machines more relevant for today's workloads.
Is Arm getting its hands on its customers' business?
The global server market soared 134% to $95.2 billion in Q1 2025 as hyperscalers ramped up AI infrastructure, with Arm-based Nvidia GB200 systems driving growth and annual spending projected to exceed $366 billion.
Fujitsu and server-giant Supermicro have partnered up to create liquid cooled servers based on Fujitsu's Monaka ARM datacenter processors, which are slated to arrive in 2027.
Elon Musk shared new video footage of the inside of the Cortex supercluster today, the new name for the recent expansion of Tesla’s “Giga Texas” plant. The X video showcases over 2,000 AI-accelerator servers, a small portion of the expected 70,000.
AMD's EPYC outperforms Nvidia's Grace CPU in all major server benchmarks, according to tests conducted by AMD.
Samsung Electronics, a world leader in advanced semiconductor technology, today announced that it will deliver the next generation Arm® Cortex™-X CPU optimized on Samsung Foundry’s latest Gate-All-Around (GAA) process technology. This initiative is built on years of partnership with millions of devices shipped with…