A computer server that contains a graphics processing unit (GPU). GPU servers are used for mathematical and AI processing and work in tandem with CPUs that orchestrate the data in and out of the GPU.

High bandwidth memory (HBM) major client Nvidia is said to have visited Samsung Electronics' advanced packaging plant again, ...

High tech companies always have roadmaps. Whether or not they show them to the public, they are always showing them to key ...

Interestingly, sales of traditional servers – meaning those not used in HPC and AI settings and including GPU accelerators – were up by 15.2 percent to $3.39 billion in the quarter, and representing ...

In a blog post, Microsoft said the new Windows Server 2025 feature is called GPU Partitioning, or GPU-P. In summary, admins can use this feature with the OS to set up several virtual machines that ...

More than 70% of TSMC’s CoWoS-L advanced packaging capacity has already been booked, fueled by strong demand for Nvidia’s Blackwell GPUs. This surge is also driving orders to major backend ...

The company also disclosed plans to use "X3D" chip packaging for future ... powers Ryzen client and EPYC server processors, CDNA will have a multi-generational GPU roadmap. "What you can expect ...

By separating the CPU and GPU, Apple can take advantage of TSMC's latest chip-packaging technology, known as SoIC-mH (System-on-Integrated-Chips-Molding-Horizontal). This advanced method of ...

The reason for this is that many professional-grade GPU accelerators are installed in rack-mounted server cases, and are therefore equipped with heat sinks but no fans: the case is meant to ...

TL;DR: NVIDIA's next-gen B300 AI GPU is set to launch in Q4 2025 ... and network cards has also been upgraded on GB300 AI server platforms, with the optical module improved again from 800G ...