[PATCH] D138507: HIP: Directly use sqrt builtins instead of calling ocml (f32 case)

Brian Sumner via Phabricator via cfe-commits cfe-commits at lists.llvm.org
Tue Nov 22 08:58:21 PST 2022

Previous message: [PATCH] D138507: HIP: Directly use sqrt builtins instead of calling ocml (f32 case)
Next message: [PATCH] D138507: HIP: Directly use sqrt builtins instead of calling ocml (f32 case)
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

b-sumner added a comment.

__builtin_sqrtf does not produce a correctly rounded result.  I don't recommend this change.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D138507/new/

https://reviews.llvm.org/D138507

Previous message: [PATCH] D138507: HIP: Directly use sqrt builtins instead of calling ocml (f32 case)
Next message: [PATCH] D138507: HIP: Directly use sqrt builtins instead of calling ocml (f32 case)
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

More information about the cfe-commits mailing list