Argonne Researchers Win Lusk Best Paper Award at EuroMPI Conference

Five researchers from Argonne National Laboratory have won the Ewing ​“Rusty” Lusk Best Paper award at EuroMPI/USA 2025, held at the University of North Carolina in October. EuroMPI is an event for discussion of new developments and applications of the Message Passing Interface (MPI) standard for high performance parallel computing. The award-winning paper, ​“Implementing True MPI Sessions and […]

HPC News Bytes 20251103: 4 Exascale HPC’s Coming to National Labs; NVIDIA, Nokia and 6G; Intel Said to Be in SambaNova Talks

Good November morning to you! It was a hefty HPC-AI news week last week, here’s a rapid ….

Achieving AI Scale-Up Supremacy with Co-Packaged Optics

AI architectures are approaching an inflection point, and that is why a new generation of scale-up architectures is needed. Enabling thousands of XPUs to operate as one massive chip for trillion-parameter AI models ….

Ayar Labs Appoints Vivek Gupta Chief Strategy Officer

SAN JOSE – Oct. 9, 2025 – Ayar Labs, a co-packaged optics (CPO) company, today announced that Vivek Gupta has joined as the company’s first Chief Strategy Officer (CSO). “This is a momentous time for the company, as we scale to commercial production and strengthen customer partnerships,” said Mark Wade, CEO and co-founder of Ayar Labs. […]

Scintil Photonics Raises $58M

GRENOBLE, France, Sept. 09, 2025 — Scintil Photonics today announced the completion of a $58 million (€50M) Series B funding round led by Yotta Capital Partners and NGP Capital, with participation from NVIDIA. The round includes new participation from BNP Paribas Développement, alongside existing investors including Supernova Invest, Bpifrance Digital Venture, Innovacom, Bosch Ventures, Applied […]

Ayar Labs and Alchip in Co-Packaged Optics Partnership

SAN JOSE – Sept. 7, 2025 – Co-packaged optics (CPO) company Ayar Labs, and ASICS company Alchip Technologies announced a strategic partnership to accelerate AI scale-up infrastructure. The collaboration fulfills hyperscaler demands for advanced AI accelerators and platforms that deliver enhanced performance, efficiency, and scalability. The partnership brings together Ayar Labs’ CPO technology, Alchip’s packaging […]

Building Jupiter: An Exascale Supercomputer, and a Room to Put It In

Connecting 24,000 GPUs mounted in 125 racks, with 36,000 high performance network cables for a machine which uses 17MW running full tilt – and getting it all running smoothly as a single system is hard – but doing all that ….

OpenLight Raises $34M for AI Data Center Photonics

SANTA CLARA, Calif., Aug. 26, 2025 — OpenLight, a Photonic Application-Specific Integrated Circuit (PASIC) chip design and manufacturing company, today announced the close of its oversubscribed $34M Series A. The round is co-led by Xora Innovation and Capricorn Investment Group. Other participants include Mayfield; Juniper Networks, now part of HPE; Lam Capital, the corporate venture […]

The AI Superfactory: NVIDIA’s Multi-Data Center ‘Scale Across’ Ethernet

Ahead of Hot Chips 2025, NVIDIA today announced Spectrum-XGS Ethernet, a scale-across technology for combining multiple, distributed data centers into “unified, giga-scale AI super-factories.”

Terabit Ethernet: Rambus Launches Multi-Channel Engine MACsec-IP-364 (+363)

Aug. 21, 2025 — Rambus has introduced the Multi-Channel Engine MACsec-IP-364 (+363), built for next-generation Ethernet. The company said it delivers full line-rate MACsec and optional IPsec support for 1.6T and 3.2T Ethernet ports, offering a scalable and configurable solution for securing high-speed data traffic. Capabilities Full Line-Rate Throughput: Supports 1.6T in 3nm and 3.2T […]