[Libclc-dev] [PATCH 1/2] amdgcn/fmin: Explicitly check for NaNs
Matt Arsenault via Libclc-dev
libclc-dev at lists.llvm.org
Wed Nov 15 11:43:47 PST 2017
On 11/15/2017 09:21 AM, Jan Vesely via Libclc-dev wrote:
> v_min instruction fails to handle certain NaNs correctly.
> Signed-off-by: Jan Vesely <jan.vesely at rutgers.edu>
> Fixes most of fmin CTS on carrizo. It still fails on denormals, but IMO
> that's CTS bug.
> EG/NI does not seem to suffer the same problem.
What exact problem are you trying to solve? Do you have an example? NaNs
should work correctly. We do have some issues with denorm flushing
behavior changing on gfx9.
More information about the Libclc-dev