llvm dev - Nov 2010 - [LLVMdev] Static Profiling Algorithms in LLVM

Hi all,

Does LLVM infrastructure contain implementation of any static profiling
algorithm apart from "Spill-Weight" calculation present in Live
Intervals
class? The future work page does suggest implementation of some "static
profiling" algorithms to make an educated guesses about the relative
execution frequencies of various parts of the code.

Thanks

--Kapil
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.llvm.org/pipermail/llvm-dev/attachments/20101102/d10a2706/attachment.html>

On Tue, Nov 2, 2010 at 12:28 AM, kapil anand <kapilanand2 at gmail.com>
wrote:
> Hi all,
>
> Does LLVM infrastructure contain implementation of any static profiling
> algorithm apart from "Spill-Weight" calculation present in Live
Intervals
> class? The future work page does suggest implementation of some
"static
> profiling" algorithms to make an educated guesses about the relative
> execution frequencies of various parts of the code.
If you look at old releases, there was a profiling library and
transforms, including infrastructure to do any of the profiling with
random sampling.  Those were unmaintained and removed not that long
ago.  What you could profile was somewhat limited.

Andrew

> Thanks
>
> --Kapil
>
> _______________________________________________
> LLVM Developers mailing list
> LLVMdev at cs.uiuc.edu         http://llvm.cs.uiuc.edu
> http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev
>
>

Hello Kapil,

  I have implemented a static profiler for LLVM as a google summer of
code project in 2009. I wrote it for the 2.4 branch, but the
implementation never made into the tree. I have recently ported it to
LLVM 2.8, but I haven't tested it. You can take a look at the code
from: http://homepages.dcc.ufmg.br/~rimsa/tools/stprof-llvm.patch

  The implementation is based on Wu's [1994] paper and provides a
branch predictor that calculates probabilities. The implementation
also covers an intraprocedural and interprocedural frequency
calculator for edges and functions.

  Reference:
Youfeng Wu and James R. Larus. Static branch frequency and program
profile analysis. In MICRO 27: Proceedings of the 27th annual
international symposium on Microarchitecture. IEEE, 1994.

  Regards,
    Andrei

On Tue, Nov 2, 2010 at 10:46 AM, Andrew Lenharth <andrewl at lenharth.org>
wrote:
> On Tue, Nov 2, 2010 at 12:28 AM, kapil anand <kapilanand2 at
gmail.com> wrote:
>> Hi all,
>>
>> Does LLVM infrastructure contain implementation of any static profiling
>> algorithm apart from "Spill-Weight" calculation present in
Live Intervals
>> class? The future work page does suggest implementation of some
"static
>> profiling" algorithms to make an educated guesses about the
relative
>> execution frequencies of various parts of the code.
>
> If you look at old releases, there was a profiling library and
> transforms, including infrastructure to do any of the profiling with
> random sampling.  Those were unmaintained and removed not that long
> ago.  What you could profile was somewhat limited.
>
> Andrew
>
>
>> Thanks
>>
>> --Kapil
>>
>> _______________________________________________
>> LLVM Developers mailing list
>> LLVMdev at cs.uiuc.edu         http://llvm.cs.uiuc.edu
>> http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev
>>
>>
>
> _______________________________________________
> LLVM Developers mailing list
> LLVMdev at cs.uiuc.edu         http://llvm.cs.uiuc.edu
> http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev
>