TensorWave just deployed the largest AMD GPU training cluster in North America — features 8,192 MI325X AI accelerators tamed by direct liquid-cooling

TensorWave has built North America's largest AMD AI cluster with 8,192 liquid-cooled MI325X GPUs, delivering 21 exaFLOPS of FP8 throughput. It’s a bold move against NVIDIA’s dominance and marks ROCm’s first major public cloud-scale deployment for general-purpose AI training.

https://www.tomshardware.com/pc-components/gpus/tensorwave-just-deployed-the-largest

 Enthusiast builds a fully functional CPU from old memory chips — hand-solders every wire, writes 1800 lines of assembler code, and makes it play The Matrix on a VFD display

Someone just built a fully functional CPU from scratch using old memory chips and logic parts from the 8-bit era. Spanning four perfboards and over a kilometer of wire, it runs real code, handles interrupts, and even plays The Matrix—all using logic simulated entirely through EPROMs.

https://www.tomshardware.com/pc-components/cpus/passionate-enthusiast-build


Buscar