CONNECT WITH US
NEWS TAGGED BANDWIDTH
Saturday 19 September 2026
CXL adds memory capacity, but HBM retains its bandwidth edge

Growing memory requirements are increasing interest in Compute Express Link (CXL) as a way to add capacity beyond locally attached memory...

Friday 18 September 2026
GlobalFoundries, Marvell expand SiGe capacity deal for AI optical connectivity

GlobalFoundries (GF) and Marvell Technology have expanded a multi-year agreement to increase production capacity for silicon germanium...

Friday 18 September 2026
Apple and MediaTek's latest SoCs address overkill performance by reserving space for agentic AI
Apple unveiled its iPhone 18 Pro series featuring its inaugural 2nm smartphone silicon, the A20 Pro, which was followed by MediaTek's announcement of its own 2nm Dimensity 9600 Pro...
Thursday 17 September 2026
SK Hynix looks beyond HBM as inference workloads diversify
SK Hynix is expanding its memory strategy beyond the conventional GPU-HBM pairing as inference workloads split between latency-sensitive services and capacity-heavy, long-context a...
Thursday 17 September 2026
Samsung bets on zHBM as 2.5D memory nears its limits
Samsung Electronics is betting on vertically stacked zHBM to move memory beyond the physical constraints of conventional 2.5D architectures, setting a system-level target of raising...
Monday 14 September 2026
CPO nears mass production — next battle about interfaces, yield and maintenance
As AI computing bandwidth keeps rising, optical interconnect architectures are moving beyond pluggable optical modules toward near-packaged optics (NPO) and co-packaged optics (CPO)...
Friday 11 September 2026
Huawei stakes out the AI optics rulebook with 7.2Tbps NPO
Huawei Technologies has unveiled a 7.2-terabit-per-second near-packaged optics (NPO) module for AI data centres, coupling a high-bandwidth product launch with an effort to shape emerging...
Friday 11 September 2026
Apple's new chip packaging boosts A20 Pro AI power, pushing MediaTek, Qualcomm to follow suit
Apple has unveiled its latest iPhone 18 Pro and the A20 Pro, its first 2nm chip. According to Apple's official specifications, the A20 Pro features a six-core CPU, seven-core GPU,...
Thursday 10 September 2026
Compute-in-memory returns to the spotlight with edge AI's power, memory squeeze
AI is shifting from data centers to PCs, personal AI systems, robots, and other edge devices, renewing a core semiconductor challenge: delivering enough compute and memory bandwidth...
Wednesday 9 September 2026
Backed by Nanya partnership, PieceMakers eyes AI memory upgrade boom
As AI compute requirements scale, memory bandwidth has become a primary bottleneck governing system performance. PieceMakers Technology, which maintains a strategic partnership with...
Tuesday 8 September 2026
Nvidia reportedly shifts Rubin Ultra toward 8-high HBM as memory costs rise

Nvidia is reportedly shifting its Rubin Ultra AI accelerator toward an eight-high high-bandwidth memory (HBM) configuration, down from...

Tuesday 8 September 2026
Corning targets AI bottlenecks with glass substrates, optics for high-speed data transmission
As AI processors advance toward higher compute density, larger package footprints, and increased bandwidth demands, advanced packaging and high-speed data transmission have emerged...
Friday 4 September 2026
Ennostar accelerates AI optical communications with micro LED
Ennostar is pushing into AI high-speed optical communications and says Taiwan's full supply-chain ecosystem could bring micro LED into commercial use sooner than expected. Andrew Tsai,...
Thursday 3 September 2026
SanDisk pushes HBF ecosystem as AI inference reshapes token economics
The rapid rise of AI inference, multimodal inputs, and AI agents is giving NAND flash a new strategic role.