ConceptAI & ML
Tensor cores
A hardware unit and instruction in Volta GPUs that performs 4x4x4 mixed-precision matrix multiply and accumulate operations in a single clock cycle.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
GPU architecture2Matrix multiplication2Floating-point operations1Mixed precision training1SIMD execution1
Opens up
Concepts that name this one as a prerequisite.
Lecturers
3Each in their own terms, from the easiest level.
Onur Mutlu
Specialized floating-point multiply and accumulate units in modern GPUs designed to accelerate machine learning workloads.Andrej Karpathy
Specialized hardware instructions in the A100 architecture that perform 4x4 matrix multiplications efficiently.
Connections
7The lectures that define it or assume it, and the concepts next to it.