[PATCH] D25165: [x86] allow 128/256-bit lowering for copysign vector intrinsics (PR30433)

Zvi Rackover via llvm-commits llvm-commits at lists.llvm.org
Sun Oct 2 15:35:36 PDT 2016

Previous message: [PATCH] D25165: [x86] allow 128/256-bit lowering for copysign vector intrinsics (PR30433)
Next message: [llvm] r283074 - Rangify for loops.
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

zvi added a comment.

LGTM.
Note that since sign-mask and mag-mask are complementary, we could avoid one constant-pool load with ANDNPS.


https://reviews.llvm.org/D25165

Previous message: [PATCH] D25165: [x86] allow 128/256-bit lowering for copysign vector intrinsics (PR30433)
Next message: [llvm] r283074 - Rangify for loops.
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

More information about the llvm-commits mailing list