[LLVMdev] RFC: Integer saturation intrinsics

[Eli Friedman]

On Fri, Jun 17, 2011 at 4:50 PM, Eli Friedman <eli.friedman at gmail.com> wrote:
>>>> The plan is to form calls to these intrinsics in InstCombine. Legalizer can expand these intrinsics if they are not legal. The expansion should be fairly straight forward and produce code that is at least as good as what LLVM is currently generating for these code sequence.
>>>>
>>>> Comments?
>>>
>>> Is there some reason why pattern-matching this in an ARM-specific
>>> DAGCombine doesn't work?
>>
>> It's not possible to look beyond a single BB at isel time.
>
> Anything that we can match to ssat should be of the form max(min(x,
> SATMAX), SATMIN) (where max and min are icmp+select pairs).  If the
> min and max aren't in the same block, and we don't have an IR
> transformation to put them in the same block, we should fix that
> rather than introducing an instrinsic for this special case, I
> think...

Okay, thinking about it a bit more, I don't think this is practical.

I'm still skeptical that adding platform-independent intrinsics for
arbitrary ARM instructions is a good idea simply because we don't have
the infrastructure to handle them otherwise.  It wouldn't be
especially hard to allow target-specific transforms on IR...

-Eli