by Wayne Joubert on (#6ZM4G)
Explosive datacenter demand has caused developers to leave no stone unturned in search of higher efficiencies. The DeepSeek team, not satisfied with Nvidia's CUDA libraries, used a virtualized form of assembly language (PTX) to write kernel codes to accelerate their AI computations. Others have attempted to generate optimized kernels using AI, though some results have [...]The post Why are CUDA kernels hard to optimize? first appeared on John D. Cook.