Mojo module
globals
This module provides GPU-specific global constants and configuration values.
The module defines hardware-specific constants like warp size and thread block limits that are used throughout the GPU programming interface. It handles both NVIDIA and AMD GPU architectures, automatically detecting and configuring the appropriate values based on the available hardware.
The constants are resolved at compile time based on the target GPU architecture and are used to optimize code generation and ensure hardware compatibility.
Aliases
-
MAX_THREADS_PER_BLOCK_METADATA = _resolve_max_threads_per_block_metadata().value: This is metadata tag that is used in conjunction with __llvm_metadata to give a hint to the compiler about the max threads per block that's used. -
WARP_SIZE = _resolve_warp_size(): The number of threads that execute in lockstep within a warp on the GPU. This constant represents the hardware warp size, which is the number of threads that execute instructions synchronously as a unit. The value is architecture-dependent:- 32 threads per warp on NVIDIA GPUs
- 64 threads per warp on AMD GPUs
- 0 if no GPU is detected
The warp size is a fundamental parameter that affects:
- Thread scheduling and execution
- Memory access coalescing
- Synchronization primitives
- Overall performance optimization
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!