Intel and AMD's new ACE CPU extensions bring an efficient AI-oriented instruction set to x86, a new design makes matrix multiplication more power- and density-efficient

Intel and AMD released the full specification for ACE CPU extensions that boost matrix multiplication performance on x86 processors. The extensions use AVX10 registers and add dedicated silicon to enable 16x more operations per input vector than AVX10 for AI workloads. This improves power efficiency and simplifies development for CPU-based AI tasks without GPU dependency.