Graphics processing units (GPUs) are designed in a way that their performance can be scaled up or down during the…
Read More
Huawei to open-source its UB-Mesh data center-scale interconnect soon, details technical aspects — one interconnect to rule them all is designed to replace everything from PCIe to TCP/IP
Huawei used its Hot Chips 2025 slot to introduce its UB-Mesh technology that is designed to unify all interconnections across…
Read More
Micron details new U.S. fab projects: HBM assembly comes to the U.S., Idaho Fab comes online in 2027, New York fabs later
Micron this month announced a renewed U.S. buildout strategy that expands investment plans to $150 million, plans to build an…
Read More
Tesla details how it finds punishing defective cores on its million-core Dojo supercomputers — a single error can ruin a weeks-long AI training run
Detecting malfunctioning cores and disabling them on a massive processor is challenging, but Tesla has developed its Stress tool, which…
Read More
