0PricingLogin
CUDA Academy · Lesson

SIMT: The Same Instruction, Many Threads

The execution model that makes GPUs fast.

How the GPU Stays Busy

Thousands of cores need a smart way to be told what to do. The GPU's answer is SIMT: Single Instruction, Multiple Threads. ⚡

One Instruction, Many Threads

In SIMT, one instruction is broadcast to a whole group of threads at once. Each thread runs that same step, but on its own piece of data.

All lessons in this course

  1. CPU vs GPU: Latency vs Throughput
  2. SIMT: The Same Instruction, Many Threads
  3. What CUDA Actually Is
  4. Problems That Love the GPU
← Back to CUDA Academy