[llvm] [X86] Fix VECREDUCE_XOR to PARITY lowering for 16-bit elements (PR #219216)

Simon Pilgrim via llvm-commits llvm-commits at lists.llvm.org
Thu Aug 27 11:56:52 PDT 2026

Previous message: [llvm] [X86] Fix VECREDUCE_XOR to PARITY lowering for 16-bit elements (PR #219216)
Next message: [llvm] [AArch64] Widen v3i8/v4i8 VECTOR_MATCH needles (PR #218972)
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

RKSimon wrote:

Either masking the movmsk result or a PACKSSWB of the source with zero

https://github.com/llvm/llvm-project/pull/219216

Previous message: [llvm] [X86] Fix VECREDUCE_XOR to PARITY lowering for 16-bit elements (PR #219216)
Next message: [llvm] [AArch64] Widen v3i8/v4i8 VECTOR_MATCH needles (PR #218972)
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

More information about the llvm-commits mailing list