[PATCH] D15091: AMDGPU: Use generic bitreverse intrinsic

Matt Arsenault via llvm-commits llvm-commits at lists.llvm.org
Tue Dec 1 15:13:01 PST 2015

Previous message: [PATCH] D15091: AMDGPU: Use generic bitreverse intrinsic
Next message: [llvm] r254335 - Have 'optnone' respect the -fast-isel=false option.
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

arsenm added a comment.

Actually the AArch64 bitreverse test is broken from the legalization fix. It looks like it now gets scalarized  and then fully expanded instead of the expansion with vector ops.


http://reviews.llvm.org/D15091

Previous message: [PATCH] D15091: AMDGPU: Use generic bitreverse intrinsic
Next message: [llvm] r254335 - Have 'optnone' respect the -fast-isel=false option.
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

More information about the llvm-commits mailing list