Copper's reach is shrinking so Broadcom is strapping optics directly to GPUs

What good is going fast if you can't get past the next rack?

In modern AI systems, using PCIe to stitch together accelerators is already too slow. Nvidia and AMD use specialized interconnects like NVLink and Infinity Fabric for this reason – but at the 900-plus GB/sec these links push, copper will only carry you so far.…