LLVM: lib/Target/AMDGPU/AMDGPUAtomicOptimizer.cpp File Reference (original) (raw)

This pass optimizes atomic operations by using a single lane of a wavefront to perform the atomic operation, thus reducing contention on that memory location. More...

This pass optimizes atomic operations by using a single lane of a wavefront to perform the atomic operation, thus reducing contention on that memory location.

Atomic optimizer uses following strategies to compute scan and reduced values

1. DPP - This is the most efficient implementation for scan. DPP uses Whole Wave Mode (WWM)
2. Iterative -

Definition in file AMDGPUAtomicOptimizer.cpp.