[llvm] AMDGPU/GlobalISel: Handle G_BITCAST for 16 bit extendedLLTs (PR #208750)

Petar Avramovic via llvm-commits llvm-commits at lists.llvm.org
Tue Jul 14 07:15:11 PDT 2026


petar-avramovic wrote:

rewrite using widen scalar (knows how to delete same type bitcast), legalize action is a bit awkward, need to make sure to not widen for vector to scalar bitcast (this is lower action)

https://github.com/llvm/llvm-project/pull/208750


More information about the llvm-commits mailing list