Glossary
Matrix Math Acceleration (MMA)
An on-chip acceleration feature in IBM Power10 and Power11 processors that speeds up the matrix math operations used in AI inferencing, without requiring a separate GPU.
Matrix Math Acceleration is built into every core of IBM's Power10 and Power11 processors, giving Power-based IBM i, AIX, and Linux systems built-in AI inferencing capability. Because it lives on the processor rather than requiring a dedicated GPU or accelerator card, it lets an IBM i shop run AI inferencing workloads on the same physical server already running production partitions, per IBM's published Power11 AI Redbook guidance.