Chip giant ships first 2nm custom compute SoC to power Fujitsu's next-gen supercomputer project

Jensen Huang declares ‘compute equals revenues’ as the big green giant continues to defy AI market skeptics

Cisco veteran Stephen Patak joins firm following recent Nokia win

New BCM49438 APU and Trident X3+ switch target enterprise edge AI and high-density Wi-Fi 8 deployments – despite the final standard being years away

Hyperscaler leverages a two-tier Ethernet-based topology, custom AI Transport Layer & software tools to deliver a tightly integrated, low-latency platform

The Japanese giant’s ExpEther tech separates and distributes CPUs and GPUs to maximize resource utilization

Seeking proposals to scale up circuits for transceivers, accelerators, and other chip types

Next-gen Rubin platform will see DPUs help control all network I/O to and from the compute node

First memory chips. Then lasers. Now, copper looks to be the next commodity to pose ‘systemic risk’ to the digital infrastructure space

Giant’s CES 2026 showcase sees BlueField reinvent storage while Rubin marches toward production

AWS doubles down on custom silicon and the looming memory crisis to come

And a new unnamed XPU customer is teased

The likes of OpenAI, AMD, and Cornelis Networks are taking part in what is really a modernization effort – and that's okay

Powered by hardware-accelerated RoCEv2, the CN6000 SuperNIC doubles the performance of its predecessor

Demand for its Ethernet products now ‘on par’ with that of InfiniBand

New generation offers double the bandwidth compared to prior version

Custom hardware delivers 73% more bandwidth while cutting power consumption by 35%

Singaporean firm builds photonic hardware for use in telecoms and networks

Neoverse integration means custom hardware from AWS, Google, and Microsoft can integrate with Nvidia GPUs

Move brings AI-SuperNIC technology in-house as Arm looks to capitalize on surging data center demand

Research also points to success beyond Nvidia on AWS architecture

Effort builds collab with chipmakers to provide a consistent management platform for distributed compute across accelerators

CXL has big beneficial implications for a wide range of industries, including high-performance computing and hyperscalers like Google, Amazon, and Microsoft

Both new groups formed just days before the granddaddy of open source hardware groups, Open Compute Project (OCP), holds its annual summit. All three focus on “fundamentally different areas”