Hardware & Semiconductors
187 articles RSS
Kioxia and SanDisk Begin Sampling 332-Layer BiCS10 NAND, Claiming a 59 Percent Bit-Density Gain for AI Data-Center SSDs
The flash-memory partners started sampling their 10th-generation 3D NAND on July 3, targeting enterprise SSDs, with mass production reportedly slated for 2027.
SK hynix Commits 100 Trillion Won to Cheongju, Anchored by an 80 Trillion Won M17 NAND Fab, as Korea Doubles Down on AI Memory
SK hynix will spend 100 trillion won ($64.38 billion) on a new NAND fab and advanced packaging plant in Cheongju, part of a 392 trillion won Chungcheong buildout with Samsung.
Nvidia Becomes the Top Data Center Ethernet Switch Vendor by Revenue for the First Time, IDC Says, on $2.1 Billion of Spectrum-X Sales
IDC says Nvidia took the No. 1 revenue spot in data center Ethernet switching in Q1 2026 with $2.1 billion and a 21.5% share, edging Arista.
Nokia to Invest $30 Million Expanding Its Allentown Photonic-Chip Packaging Plant to Feed AI Data Centers
Nokia will spend about $30 million to grow its Allentown, Pennsylvania test and packaging site up to tenfold, backed by state aid and a federal CHIPS tax credit.
XCENA Raises $135 Million Series B for CXL Computational Memory Packing Thousands of RISC-V Cores Beside DRAM
South Korean startup XCENA raised a $135M Series B at a $570M valuation for its MX1 CXL memory device, betting AI's real bottleneck is memory, not compute.
Qualcomm Unveils Dragonfly Data Center Roadmap: A 250-Core C1000 Server CPU and AI300 Accelerator, With Meta Signed as a CPU Customer
At its June 24 Investor Day, Qualcomm detailed a multi-generation data center chip line built for agentic AI inference, anchored by the Dragonfly C1000 CPU and AI300 accelerator, and named Meta as a server-CPU customer.
Intel's Enhanced 18A-P Process Enters Risk Production, Claiming 9% More Performance and 20-40% Lower Thermal Resistance Than 18A
At the 2026 VLSI Symposium, Intel said 18A-P, a drop-in upgrade to its 18A node, reached risk production with 9% higher performance at iso-power.
OpenAI and Broadcom Unveil 'Jalapeño,' a Custom LLM-Inference Chip Designed in Nine Months and Targeting Deployment by the End of 2026
OpenAI's first custom silicon, the Broadcom-built Jalapeño inference accelerator, went from design to tape-out in nine months and targets deployment by the end of 2026.
ASML, TSMC, and imec Fabricate Complementary 2D-Material Transistors at 50nm Pitch on a Full 300mm Wafer
At the 2026 VLSI Symposium, imec and partners reported MoS2 and WS2/WSe2 transistors at a 50nm contacted poly pitch with 94% of devices operational, a step toward post-silicon logic.
Micron's 9650 Becomes the First PCIe Gen6 Data Center SSD to Reach Mass Production, Hitting 28 GB/s Reads and 5.5 Million IOPS
Micron's 9650 NVMe SSD has entered mass production as the first PCIe Gen6 data center drive to ship at scale, with up to 28 GB/s reads and 5.5 million random read IOPS.
Alibaba's T-Head Unveils Zhenwu M890 AI Accelerator With 144GB Memory and a 128-Chip Supernode, Claiming 3x Its Prior Generation
Alibaba's chip unit T-Head detailed the Zhenwu M890, a 144GB AI accelerator it says triples the prior 810E, alongside a 128-chip supernode server.
Tim Cook Calls Apple Price Increases 'Unavoidable' as a Memory Shortage Pushes iPhone 18 Pro Costs Higher
Cook told the WSJ that AI-driven memory shortages make price hikes unavoidable. TechInsights estimates the iPhone 18 Pro needs a $270 increase to hold margins.