[cfe-dev] _Float16 support (Kaylor, Andrew via cfe-dev)
Jon Chesterfield via cfe-dev
cfe-dev at lists.llvm.org
Wed Jan 23 02:00:48 PST 2019
> I haven't looked at what happens with clang when compiling for other
> targets that don't have native support for half-precision arithmetic, but I
> would imagine that similar problems exist.
As a comparison point, our out of tree target uses __fp16 (and will move to
_Float16 once I find time to work out what semantic changes that causes)
but doesn't have native support for it.
In order to avoid spuriously converting to/from f32 across function calls
it's special cased in the calling convention. Essentially pass in the low
half of a f32 register without changing the bit pattern. This has no
drawbacks known to me.
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the cfe-dev