[llvm] [LLVM][PhaseOrdering] Run CSE after InstCombine has cleaned the result of vectorisation. (PR #120443)

Paul Walker via llvm-commits llvm-commits at lists.llvm.org
Thu Mar 13 08:04:50 PDT 2025

Previous message: [libc] [llvm] [libc][math][c23] Add fsqrtf16 C23 math functions. (PR #131153)
Next message: [llvm] [VPlan] Fix crash with inloop fmuladd reductions with blend (PR #131154)
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

paulwalker-arm wrote:

I see the results have improved as Florian predicted.  Are the new results acceptable? or do I need to search for an alternate solutions?

https://github.com/llvm/llvm-project/pull/120443

Previous message: [libc] [llvm] [libc][math][c23] Add fsqrtf16 C23 math functions. (PR #131153)
Next message: [llvm] [VPlan] Fix crash with inloop fmuladd reductions with blend (PR #131154)
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

More information about the llvm-commits mailing list