[llvm] [AMDGPU] Skip the iterative atomic scan on native LDS atomics (PR #227222)

Carl Ritson via llvm-commits llvm-commits at lists.llvm.org
Tue Sep 29 19:20:02 PDT 2026

Previous message: [llvm] [AMDGPU] Skip the iterative atomic scan on native LDS atomics (PR #227222)
Next message: [llvm] [AMDGPU] Skip the iterative atomic scan on native LDS atomics (PR #227222)
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

perlfu wrote:

Doesn't this actually depend on number of active lanes?

https://github.com/llvm/llvm-project/pull/227222

Previous message: [llvm] [AMDGPU] Skip the iterative atomic scan on native LDS atomics (PR #227222)
Next message: [llvm] [AMDGPU] Skip the iterative atomic scan on native LDS atomics (PR #227222)
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

More information about the llvm-commits mailing list