AI Chips news and analysis on Web Pulse: 7109 curated articles tracking the latest AI Chips developments, tools, and research, updated continuously from vetted sources.
Google's Tensor Processing Units (TPUs) are specialized chips designed for neural network matrix multiplications, differing fundamentally from GPUs. Unlike GPUs, which evolved from graphics rendering, TPUs use a systolic…
A group of companies backing the Chip Security Act is urging Congress to mandate location-tracking for advanced AI chips to prevent them from reaching China and other adversaries. The bill would require stronger security…
A team of kernel engineers developed a bf16 forward attention kernel for AMD MI300X GPUs using HIP, outperforming AMD's own AITER v3 library by up to 1.26× across various token lengths and rounding modes. The kernel achi…
Micron Technology is expected to report fiscal third-quarter 2026 earnings on June 24 with adjusted EPS between $19.95 and $20.98, representing roughly 1,000% year-over-year profit growth driven by surging AI memory dema…
VLIW architecture is experiencing a resurgence driven by machine learning workloads, which rely on regular, statically analyzable computation that VLIW exploits efficiently. Unlike out-of-order designs, VLIW shifts depen…
Tesla filed a trademark for 'Megapod,' a modular AI data center hardware system, signaling plans to enter a market dominated by Nvidia's GB200 NVL72 and DGX SuperPOD. The product would bundle servers, networking, power, …
Micron Technology has received 57 buy ratings from analysts, with price targets approaching $1,500, driven by the AI memory boom that has quadrupled the stock in 2026. The company's fiscal Q3 2026 earnings report on June…
Google is adopting Nvidia's business strategies to develop its own AI chip business, aiming to compete with Nvidia's dominant position in the AI hardware market. The move signals Google's intent to reduce reliance on ext…
AMD released ATOM and ATOMesh, a ROCm-native LLM serving stack for Instinct GPUs on June 16, 2026, that disaggregates prefill and decode phases to eliminate head-of-line blocking. The open-source stack splits inference i…
A merger of SpaceX and Tesla could create a single entity rivaling Nvidia's market cap, potentially making Elon Musk controller of the world's most valuable listed firm.
Leaked audited financials show OpenAI lost $20.92 billion on $13 billion in revenue in 2025, with losses projected to reach $63 billion by 2027. The real beneficiaries are Microsoft and Nvidia, which received $17.2 billi…
Japan's semiconductor equipment makers Tokyo Electron, Screen Holdings, and Advantest are losing China revenue due to export controls, with Tokyo Electron's China sales dropping from 47.4% to 26.8% of revenue. The compan…
Kazakhstan signed agreements with U.S.-based Firebird Inc. for AI infrastructure projects worth up to $10 billion, supported by Nvidia chips, aiming to generate $3 billion in annual export revenue. Iran offered Kazakhsta…
Samsung Electronics reviewed plans to expand high-bandwidth memory shipments and secure long-term supply agreements with major AI customers at its global strategy meeting last week, as tightening memory supply and soarin…
Samsung Electronics reviewed strategies to expand sales of high-bandwidth memory (HBM) chips and discussed long-term supply agreements with major customers at a global strategy meeting, amid surging demand for AI semicon…
Japan's semiconductor equipment makers reported a 10% drop in China sales as export restrictions on advanced chipmaking technology take effect. Tokyo Electron's China revenue fell from 279.4 billion yen to 175.5 billion …
A developer detailed the architectural differences between NVIDIA's Ampere and Hopper GPU architectures, focusing on tensor core and memory bandwidth improvements. The Hopper architecture introduces Tensor Core 2.0 with …
MicroPhase Technology announced the AntSDR T510 AI, a single-board platform combining an AMD Zynq UltraScale+ RFSoC with an NVIDIA Jetson module for RF capture and GPU-accelerated AI inference. The board, listed as comin…
The information technology sector now accounts for 38.33% of the MSCI USA Index and 44% of the MSCI Emerging Markets Index as of mid-2026, driven by surging demand for AI infrastructure. This historic concentration raise…
A developer used Gemini Flash Lite to transcribe a video explaining High Bandwidth Memory (HBM) technology. The video details how HBM achieves high bandwidth through an extremely wide bus width, contrasting with traditio…