[LLVMdev] RE : Question about LLVM NEON intrinsics
rengolin at systemcall.org
Fri Sep 21 03:50:23 PDT 2012
On 21 September 2012 11:19, Sebastien DELDON-GNB
<sebastien.deldon at st.com> wrote:
> Hi Renato,
> I guess one solution could be to define LLVM max intrinsic and have LLVM backends generating the appropriate instructions (using SSE inst for x86, NEON for ARM etc.).
That's a grey area... As Eli said, different back-ends have different
semantics, so trying to add generic intrinsics that will be converted
to target-specific intrinsics is bound to create semantic problems
when generating IR, or worse, silently producing bad code in the end.
Besides, if we're going to transform one intrinsic into another, it's
better to leave the current IR syntax as is (vector operations) and
transform that into target-specific intrinsics directly, or bail. IR
operations' semantics are better defined than intrinsics', so you
leave less room for silent codegen faults.
More information about the llvm-dev