AI Chips news and analysis on Web Pulse: 6919 curated articles tracking the latest AI Chips developments, tools, and research, updated continuously from vetted sources.
Arm debuted its CSS for Mobile 2 technology, featuring the Mali G2-Ultra NX GPU, which the company says is its first AI-native GPU, designed to boost gaming graphics and AI tasks in premium Android phones arriving in 202…
Arm has unveiled the Mali G2-Ultra NX GPU with AI-powered 'neural graphics' features, debuting in Xiaomi's 18 Fold phone in China, which Arm claims can deliver up to four times the framerate and extend gaming battery lif…
Arm Holdings plc unveiled Arm CSS for Mobile 2, an AI-native compute platform for mobile featuring the Arm C2 Ultra CPU with Arm Scalable Matrix Extension 2 (SME2) and the Arm Mali G2-Ultra NX GPU with dedicated neural a…
Arm has unveiled the Mali G2-Ultra NX GPU, its first AI-native Mali GPU, integrating neural accelerators into the shader cores to enable neural graphics techniques such as Neural Super Sampling and Neural Frame Rate Upsc…
Arm Holdings CEO Rene Haas said in a BBC interview on September 7, 2026, that AI could help cure cancer 'in our lifetime,' but current computational capacity is insufficient because the semiconductor industry remains 'ab…
Arm Holdings CEO Rene Haas told the BBC that AI could eventually solve cancer research but is currently held back by a shortage of chips needed for data centers, with SK Hynix, Samsung, and Micron having preallocated ess…
Rene Haas, CEO of Arm, said the global chip shortage is slowing the development of AI-driven cancer cures, as modelling how a DNA marker is impacted by cancer cannot currently be done, though computers are 'going to solv…
At IFA 2026, AMD unveiled new AI-focused hardware including Strix Halo and Gorgon Halo chips, the Threadripper Halo Station with 96 cores, and announced Project Zenith with Microsoft's Pavan Davuluri, enabling local exec…
D-Matrix CEO Sid Sheth said in an interview on Eye on AI that low-latency demands are splitting the AI chip market into two tiers, with d-Matrix using digital in-memory compute on legacy fabrication nodes to challenge GP…
SemiAnalysis published the first third-party inference results for Google's TPUv7 Ironwood, showing up to 50% better performance per dollar than NVIDIA's B200/B300 in apples-to-apples comparisons. The analysis, based on …
Preferred Networks, the Tokyo AI startup valued at roughly $2 billion, is opening its books to foreign investors for the first time and eyeing an IPO in three to five years to fund mass production of its own AI chips, CE…
NVIDIA CEO Jensen Huang declared on X on September 6, 2026 that 'AGI has arrived,' citing OpenAI's GPT-6 Astra model trained on over 100,000 NVIDIA Grace Blackwell NVLink72 GPUs, and said 400,000 more GPUs are coming onl…
China's AI infrastructure buildout is shifting focus from chips to electricity, memory, and data centers, with Ulanqab's computing capacity jumping from 3.3GW to 12.5GW in under a year, and CXMT's LPDDR6 memory debuting …
Apple's M5 Max Mac Studio with 128GB of memory at 1TB storage is priced at $5,399, about $100 less than the base M5 Ultra Studio's 96GB configuration at $5,499, according to Apple's live configurator cited by Vetted Cons…
Taiwan's Ministry of Economic Affairs said the island is well-positioned to develop copackaged optics (CPO) and manufacture precision silicon photonics chips, a technology seen as key to overcoming AI computing bottlenec…
Google's Pixel 11 series, powered by the Tensor G6 processor, trails rival flagships by significant margins, with Apple's iPhone 17 Pro scoring up to 43% faster in single-core and 73% faster in GPU benchmarks, and Samsun…
Malaysia is seriously evaluating Huawei Technologies' Ascend 910C AI chips for a RM2 billion (US$494 million) sovereign AI initiative, which would mark the first known instance of a foreign government officially opting f…
Kioxia presented a Compute Express Link (CXL) module at a Tokyo briefing that uses its XL-Flash NAND to replace some DRAM in AI workloads, claiming it can double memory capacity at the same cost while improving performan…
Malaysia is advancing sovereign AI initiatives with Huawei's Ascend chips, planning to deploy roughly 3,000 chips by 2026, despite initial government distancing. Huawei inaugurated its first AI Lab outside China in Kuala…
DeepSeek plans to deploy at least 160,000 Huawei Ascend 950DT accelerators at a new data center in Inner Mongolia, according to sources familiar with the matter. The cluster, earmarked for inference workloads, would be a…