#hardware

Samsung and ASML expanded their deal to use High-NA machines to print sub-2nm computer chips. Standard machines require multiple printing passes, which slows manufacturing and raises defect rates.

AMD showed Threadripper Halo Station at IFA 2026, combining 96 CPU cores and 576GB of HBM3E memory to run trillion-parameter models locally. Run large models on local liquid-cooled workstations to avoid cloud rental fees.

Lattice added hardware FPGA chips to robot joints to inspect electronic commands and physically cut motor power if commands are unsafe. Put hardware chips on motor joints to block bad commands before machines move.

Broadcom’s AI chip revenue rose to $11.5 B, tripling. Tech giants moved from standard GPUs to custom ASICs. Generic GPUs waste power on unused hardware blocks. Custom chips lower inference costs by 40% and reduce electricity use for high‑volume queries.

Chipmakers are running full software stacks on hardware emulation clusters before manufacturing 2nm AI chips. Fixing a flawed chip mask costs $50M and causes a 12-month delay. Pre-silicon hardware emulation catches design errors before physical fabrication begins.