[LLVMdev] LLVM Loop Vectorizer puzzle

[Pekka Jääskeläinen]

On 05/23/2013 09:37 PM, Redmond, Paul wrote:
> So it should look like:
>
> !0 = metadata !{ metadata !0, metadata !1, metadata !2 }
> !1 = metadata !{ metadata !"llvm.loop.parallel" }
> !2 = metadata !{ metadata !"llvm.vectorization.vector_width", i32 8 }
>
> Correct?

Yep. And yes, I think one can just add the parallel_loop_access MD
also to volatile inline asm calls and other instructions which might
prevent parallelization. At least I do not quickly see a case that could
break.

-- 
--Pekka