[PATCH] D130096: [Clang][AMDGPU] Emit AMDGPU library control constants in clang
Brian Sumner via Phabricator via cfe-commits
cfe-commits at lists.llvm.org
Tue Oct 11 13:33:45 PDT 2022
b-sumner added a comment.
In D130096#3850473 <https://reviews.llvm.org/D130096#3850473>, @arsenm wrote:
> In D130096#3850472 <https://reviews.llvm.org/D130096#3850472>, @jhuber6 wrote:
>
>> I don't like the fact that we need to have two different kinds of control constants, one per-TU and others per-link job. I'm wondering how difficult it would be to make the fast versions of the math calls use different entry points. That way we could handle this in the math header wrappers.
>
> That's really how the C linkage model wants you to handle this. I also would like to have FP value tracking optimizations take care of the special cases in the library code
There's the "small matter" of implementing the new device library functions. Why is all that more likeable than two kinds of control constants?
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D130096/new/
https://reviews.llvm.org/D130096
More information about the cfe-commits
mailing list