0PricingLogin
CUDA Academy · Lesson

On-Demand Page Migration

Faults move data where it is used.

Where Does the Data Live?

With managed memory the data has no fixed home. It quietly moves between CPU and GPU through on-demand page migration, following wherever you use it.

Memory Comes in Pages

The system tracks memory in fixed chunks called pages, often 4 KB or 64 KB. Migration happens one page at a time, not byte by byte.

All lessons in this course

  1. One Pointer, Both Sides
  2. On-Demand Page Migration
  3. Prefetching with cudaMemPrefetchAsync
  4. Hints via cudaMemAdvise
← Back to CUDA Academy