[LLVMdev] LLVM Loop Vectorizer puzzle

[Redmond, Paul]

On 2013-05-23, at 10:37 AM, Arnold Schwaighofer wrote:

> 
> On May 23, 2013, at 9:15 AM, Renato Golin <renato.golin at linaro.org> wrote:
> 
>> On 23 May 2013 14:52, Arnold Schwaighofer <aschwaighofer at apple.com> wrote:
>> I would like us to grow a few annotations, among others, one to force vectorization irrespective whether the loop vectorizer thinks it is beneficial or not - however, this is future music.
>> 
>> Isn't that part of the ivdep implementation? I thought there was support for that already...
> 
> No, llvm.loop.parallel only communicates information about memory dependencies (or there absence of) and the loop vectorizer only uses it for this. I don’t think we should give it additional semantics of forcing vectorization.
> 
> Of course, you could locally patch llvm to abuse it for other purposes...
> 

I was recently thinking about how to extend the parallel loop metadata to support other hints. Does it make sense to use a single loop id metadata and attach hints to it?

For example, here is a simple loop with llvm.loop.parallel and llvm.mem.parallel_loop_access metadata:

loop.body:                                        ; preds = %loop.body, %loop.body.lr.ph
  %indvars.iv = phi i64 [ %4, %loop.body.lr.ph ], [ %indvars.iv.next, %loop.body ]
  %__index.addr.07 = phi i32 [ %__low, %loop.body.lr.ph ], [ %7, %loop.body ]
  %ref1 = load i32*** %3, align 8, !llvm.mem.parallel_loop_access !0
  %5 = load i32** %ref1, align 8, !llvm.mem.parallel_loop_access !0
  %arrayidx = getelementptr inbounds i32* %5, i64 %indvars.iv
  %6 = trunc i64 %indvars.iv to i32
  store i32 %6, i32* %arrayidx, align 4, !llvm.mem.parallel_loop_access !0
  %indvars.iv.next = add i64 %indvars.iv, 1
  %7 = add i32 %__index.addr.07, 1
  %exitcond = icmp eq i32 %7, %__high
  br i1 %exitcond, label %loop.end, label %loop.body, !llvm.loop.parallel !0

If I want to add metadata for the vector length how should it look? One thing that would be nice is not having to check branches for different types of loop metadata. How about changing llvm.loop.parallel to llvm.loop and making the hints child nodes?

e.g.,

 br i1 %exitcond, label %loop.end, label %loop.body, !llvm.loop !0

...

!0 = metadata !{ metadata !1, metadata !2 }
!1 = metadata !{ metadata !"llvm.loop.parallel" }
!2 = metadata !{ metadata !"llvm.vectorization.vector_width", i32 8 }

I'm not even sure you would need the llvm.loop.parallel anymore since the vectorizer could just look to see if the loop id on a parallel_loop_access matches the loop id of the loop being vectorized. 

Does this make any sense?

> 
> If we decide, that
> 
> #pragma ivdep
> 
> should imply forced vectorization (which I am not sure it should), the front-end can than in addition to the llvm.loop.parallel metadata, emit meta data to force vectorization. But, I don’t think we should overload the semantics of llvm.loop.parallel.

ivdep doesn't force vectorization. It just says if you can't prove there is or isn't a dependency the assume there isn't.

paul