[PATCH] D40514: AMDGPU: Restrict ieee_mode to HSA.

Tue Nov 28 19:05:02 PST 2017

jvesely added a comment.

In https://reviews.llvm.org/D40514#938223, @b-sumner wrote:

> In https://reviews.llvm.org/D40514#938106, @jvesely wrote:
>
> > The current behavior is broken for OpenCL so no one should depend on it.
>
>
> What is broken about the current behavior?

"fmin and fmax behave as defined by C99 and may not match the IEEE 754-2008 definition for minNum and
maxNum with regard to signaling NaNs. Specifically, signaling NaNs may behave as quiet NaNs."

the CL CTS checks this behaviour, so we either need to flush SNaNs before calling v_min/v_max or disable the ieee_mode for CL. this patch does the latter.
as for GL compute I'd expect the behaviour to follow that of graphics GLSL, which is currently not the case

Repository:
  rL LLVM

https://reviews.llvm.org/D40514