Open jglaser opened 4 years ago
To start with, a lot of work on LLVM whose IR cannot currently describe non-default-rounded operations. Then additional work on the AMDGPU target to support the updated IR.
We could enable some now, but unfortunately not all. Which ones are the most important?
I noticed that
__fsub_add_ru
and friends are not supported in HIP, because they were disabled in the device-lib a while ago. What would it take to re-enable IEEE 754 rounding modes (up/down) for single precision floats again?