0PricingLogin
CUDA Academy · Lesson

Registers and Shared Memory Limits

How resources cap resident blocks.

The Resource Budget

Each SM owns a fixed pool of registers and shared memory. Every resident block must carve its share from these pools.

Registers Per Thread

Your kernel uses some number of registers per thread. Multiply by threads per block and you see one blocks register cost.

All lessons in this course

  1. What Occupancy Really Means
  2. Registers and Shared Memory Limits
  3. The Occupancy Calculator API
  4. Occupancy Is Not the Whole Story
← Back to CUDA Academy