llvm dev - Oct 2014 - [LLVMdev] [cfe-dev][Openmp-dev] Provide LLVM IR and OpenMP LLVM IR as input in a Pass

----- Original Message -----
> From: "Simone Atzeni" <simone.at at gmail.com>
> To: "Hal Finkel" <hfinkel at anl.gov>
> Cc: llvmdev at cs.uiuc.edu, cfe-dev at cs.uiuc.edu, openmp-dev at
dcs-maillist2.engr.illinois.edu
> Sent: Tuesday, October 21, 2014 3:42:03 PM
> Subject: Re: [LLVMdev] [cfe-dev][Openmp-dev] Provide LLVM IR and OpenMP
LLVM IR as input in a Pass
> 
> 
> Hi Hal,
> 
> 
> thanks for your answer.
> 
> 
> 
> 
> I think it would be better if you gave us some idea of what you're
> trying to do. clang's OpenMP implementation turns the OpenMP pragmas
> into function calls to the runtime library. You can run passes on
> this IR as you would any other IR. When you say, "Do some operation
> on it and get results" do you mean generating code, linking and
> executing that code?
> 
> -Hal
> 
> 
> 
> I want to use the pass Polly to find any data dependence in the code.
> Since it does not work on OpenMP,
Why not? The loops in the outlined OpenMP regions are just regular loops (with
runtime bounds). Can polly not handle them?
> I was thinking to apply it on the
> not-OpenMP IR, then I need the results of Polly to apply other
> passes to the OpenMP IR.
I don't think this will work for the OpenMP'd loops. The IR will look
completely different, be in different functions, etc.

 -Hal
> 
> 
> That is why I need both.
> 
> 
> Best,
> Simone
> 
> 
> 
> 
> 
> 
> 
> 
> 
> 
> I hope this is clear and you can give me some suggestion.
> 
> 
> 
> 
> 
> Thanks.
> 
> 
> Best Regards,
> Simone
> 
> _______________________________________________
> LLVM Developers mailing list
> LLVMdev at cs.uiuc.edu http://llvm.cs.uiuc.edu
> http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev
> 
> 
> --
> Hal Finkel
> Assistant Computational Scientist
> Leadership Computing Facility
> Argonne National Laboratory
> 
-- 
Hal Finkel
Assistant Computational Scientist
Leadership Computing Facility
Argonne National Laboratory

>> I want to use the pass Polly to find any data dependence in the code.
>> Since it does not work on OpenMP,
> 
> Why not? The loops in the outlined OpenMP regions are just regular loops
(with runtime bounds). Can polly not handle them?
I tried it, it does not work and I also talked already with the Polly
developers. They are slightly different, for example when the pragmas are
translated actually the compiler introduces new functions and Polly get
confused.
> 
>> I was thinking to apply it on the
>> not-OpenMP IR, then I need the results of Polly to apply other
>> passes to the OpenMP IR.
> 
> I don't think this will work for the OpenMP'd loops. The IR will
look completely different, be in different functions, etc.
What I did, and it works, is to build a script that call clang with Polly the
first time and write the results in a file, then call Clang again with OpenMP
and at the point I can apply other passes on the OpenMP IR reading the Polly
results from that file.
But it’s kind of a “dirty" solution, I was wondering if I can, in some way,
introduce my own option "-myoption” that compile the code in both ways and
make it available to the passes I want to call.

Simone

----- Original Message -----
> From: "Simone Atzeni" <simone.at at gmail.com>
> To: "Hal Finkel" <hfinkel at anl.gov>
> Cc: llvmdev at cs.uiuc.edu, cfe-dev at cs.uiuc.edu, openmp-dev at
dcs-maillist2.engr.illinois.edu
> Sent: Tuesday, October 21, 2014 3:52:38 PM
> Subject: Re: [LLVMdev] [cfe-dev][Openmp-dev] Provide LLVM IR and OpenMP
LLVM IR as input in a Pass
> 
> 
> >> I want to use the pass Polly to find any data dependence in the
> >> code.
> >> Since it does not work on OpenMP,
> > 
> > Why not? The loops in the outlined OpenMP regions are just regular
> > loops (with runtime bounds). Can polly not handle them?
> 
> I tried it, it does not work and I also talked already with the Polly
> developers. They are slightly different, for example when the
> pragmas are translated actually the compiler introduces new
> functions and Polly get confused.
Right. So the long-term solution here is to figure out what enhancements are
necessary to the various components to make this work.
> 
> > 
> >> I was thinking to apply it on the
> >> not-OpenMP IR, then I need the results of Polly to apply other
> >> passes to the OpenMP IR.
> > 
> > I don't think this will work for the OpenMP'd loops. The IR
will
> > look completely different, be in different functions, etc.
> 
> What I did, and it works, is to build a script that call clang with
> Polly the first time and write the results in a file, then call
> Clang again with OpenMP and at the point I can apply other passes on
> the OpenMP IR reading the Polly results from that file.
> But it’s kind of a “dirty" solution, I was wondering if I can, in
> some way, introduce my own option "-myoption” that compile the code
> in both ways and make it available to the passes I want to call.
Not currently.

 -Hal
> 
> Simone
-- 
Hal Finkel
Assistant Computational Scientist
Leadership Computing Facility
Argonne National Laboratory