[LLVMdev] Parallel Loop Metadata

[Tobias Grosser]

On 02/08/2013 07:02 PM, Sebastian Pop wrote:
> Nadav Rotem wrote:
>>
>> On Feb 7, 2013, at 10:55 AM, Pekka Jääskeläinen <pekka.jaaskelainen at tut.fi> wrote:
>>
>>> Hi Nadav,
>>>
>>> On 02/07/2013 07:46 PM, Nadav Rotem wrote:
>>>> Pekka suggested that we add two kind of metadata: llvm.loop.parallel
>>>> (attached to each loop latch) and llvm.mem.parallel (attached to each memory
>>>> instruction!).  I think that the motivation for the first metadata is clear -
>>>> it says that the loop is data-parallel. I can also see us adding additional
>>>> metadata such as llvm.loop.unrollcnt to allow the users to control the unroll
>>>> count of loops using pragmas. That's fine. Pekka, can you think of
>>>> transformations that may need invalidate or take this metadata into
>>>> consideration ?
>>>
>>> Any pass that introduces new non-parallel memory instructions to the loop,
>>> because they think the loop is sequential and it's ok to do so. I do not know
>>> any other such pass than the one pointed out earlier, reg2mem (if the
>>> variables inside the loop body reuse stack slots). E.g., inlining
>>> should be safe. So should be unrolling an inner loop inside a parallel loop.
>>>
>>
>> I suggest that we only add the 'llvm.loop.parallel' metadata and not llvm.mem.parallem.
>
>
> Ok.  A solution similar to Pekka's, using fewer annotations as you suggested, is
> to reference in 'llvm.loop.parallel' all the datarefs to which the parallel
> access semantics applies.  When the list of datarefs in 'llvm.loop.parallel'
> differs from the datarefs in the loop, the annotation is deemed invalid.

That sounds elegant and seems to solve the correctness problems.

Cheers,
Tobias