CONNECT WITH US
NEWS TAGGED ACCELERATOR
Thursday 17 September 2026
Huawei Connect 2026: Ascend 960 puts industry-first NPO supernode at heart of Huawei's AI scale-up bet
Huawei has unveiled its next-generation Ascend 960 supernode, positioning near-packaged optics (NPO) at the centre of its effort to scale AI computing beyond the limits of individual...
Wednesday 16 September 2026
Samsung backs Dutch AI chip startup Euclyd in US$230M funding round
Samsung Electronics is investing in Dutch AI chip startup Euclyd as part of a more than EUR200 million (about US$230.9 million) Series A funding round, highlighting growing efforts...
Wednesday 16 September 2026
Astera says customers are rethinking HBM needs for AI accelerators

AI infrastructure customers are starting to reconsider how much high-bandwidth memory (HBM) needs to be placed alongside accelerators...

Tuesday 15 September 2026
Beyond H100: China's GPU makers chase scale, not just parity

China's domestic GPU industry is entering a tougher phase: matching high-end accelerator performance is no longer enough. Vendors must...

Friday 11 September 2026
Enflame enters public markets with Nvidia alternatives in its sights

Chinese AI chipmaker Enflame Technology made a striking debut on Shanghai's STAR Market on Friday, with its shares opening 188% above...

Friday 11 September 2026
More memory won't fix AI's bottleneck, says Microsoft's Azure hardware chief
Microsoft's AI accelerator was never designed to compete with Nvidia. It was designed to run Microsoft's own inference workloads across its own fleet, and that scoping decision —...
Wednesday 9 September 2026
SEMIFIVE begins HyperAccel chip production on Samsung 4nm as capacity tightens
SEMIFIVE has begun mass production of HyperAccel's data center inference accelerator using Samsung Foundry's 4nm process, marking the Korean custom-silicon company's first large-scale...
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 1 September 2026
SK Hynix explores Intel as second source for HBM base dies
SK Hynix is reportedly considering adding Intel Foundry as a second manufacturing source for high-bandwidth memory (HBM) base dies, a move that could reduce its reliance on TSMC as...
Monday 31 August 2026
MetaX posts first-half profit while China's AI GPU rivals split
MetaX posted its first half-year profit since listing, with rising GPU shipments and the mass production of its C600 accelerator strengthening its commercial position while China's...
Thursday 27 August 2026
Rebellions targets 100-plus NPU racks as UK steps up chip spending
Rebellions is pursuing deployment of more than 100 NPU-based computing racks in the UK through a partnership with British AI infrastructure startup Callosum, giving the South Korean...
Thursday 27 August 2026
Nvidia reportedly shifts HBM4 mix toward 8-high as memory supply stays tight

Nvidia has reportedly asked Samsung Electronics and SK Hynix to increase the share of 8-high products...

Wednesday 26 August 2026
Taiwan Photon Source boosts domestic accelerator supply chain, challenges cutting-edge technology limits
The Taiwan-based National Synchrotron Radiation Research Center (NSRRC), supported by top scientists including Nobel chemistry laureate Yuan-tseh Lee, held a celebration event on August...
Wednesday 26 August 2026
China GPU race, Part 2: Moore Threads, MetaX, Biren and Enflame pursue four formulas for breaking Nvidia's grip
Enflame's planned US$893 million STAR Market IPO, examined in Part 1 of this series, highlights both the opportunity and the financial strain facing China's emerging AI chip suppliers,...