[Openmp-commits] TLS for POWER

[Samuel F Antao]

The clang implementation of threadprivate using TLS has been committed. It
happens that the initial approach was changed so that  it leverages the
clang's implementation of TLS_dynamic, so it does not require any help from
the runtime to accomplish privatization, hence no need for this patch
anymore. The use of TLS for thread private is turned on by default for PPC
and activated with -fopenmp-use-tls for the other targets.

Let me know if there are any questions about this.

Thanks!
Samuel

2015-06-25 19:56 GMT-04:00 Samuel F Antao <sfantao at us.ibm.com>:

> The corresponding clang patch has been posted for review in
> http://reviews.llvm.org/D10753.
>
> Thanks!
> Samuel
>
> 2015-06-22 21:40 GMT-04:00 Hal Finkel <hfinkel at anl.gov>:
>
>> [+Johnny, Andrey]
>>
>> Any objections to this direction?
>>
>>  -Hal
>>
>> ----- Original Message -----
>> > From: "Hal Finkel" <hfinkel at anl.gov>
>> > To: "Alexandre Eichenberger" <alexe at us.ibm.com>
>> > Cc: openmp-commits at dcs-maillist2.engr.illinois.edu
>> > Sent: Monday, June 22, 2015 8:38:28 PM
>> > Subject: Re: [Openmp-commits] TLS for POWER
>> >
>> > Hi Alexandre,
>> >
>> > Thanks!
>> >
>> > Please also post the Clang patch for review on the cfe list.
>> >
>> >  -Hal
>> >
>> > ----- Original Message -----
>> > > From: "Alexandre Eichenberger" <alexe at us.ibm.com>
>> > > To: "Hal Finkel" <hfinkel at anl.gov>
>> > > Cc: openmp-commits at dcs-maillist2.engr.illinois.edu
>> > > Sent: Monday, June 22, 2015 4:17:22 PM
>> > > Subject: Re: [Openmp-commits] TLS for POWER
>> > >
>> > > Hal, Brian
>> > >
>> > > below is the revised patch.  I defined a new macro
>> > > KMP_THREADPRIVATE_TLS
>> > > that is currently set only for PPC64, and other architectures/OS
>> > > can
>> > > be
>> > > added in that macro definition.
>> > >
>> > > I added comments when defining functions, as requested.
>> > >
>> > > I could not add "static" for the kmp_threadprivate.c function as it
>> > > is
>> > > defined there, but used in kmp_runtime.c
>> > >
>> > > Let me know of any additional suggestion you or fellow reviewers
>> > > may
>> > > have
>> > >
>> > > Alexandre
>> > >
>> > > (See attached file: threadprivate-patch2)
>> > >
>> > >
>> > >
>> > > From:       Hal Finkel <hfinkel at anl.gov>
>> > > To: Alexandre Eichenberger/Watson/IBM at IBMUS
>> > > Cc: <openmp-commits at dcs-maillist2.engr.illinois.edu>
>> > > Date:       06/18/2015 12:50 PM
>> > > Subject:    Re: [Openmp-commits] TLS for POWER
>> > >
>> > >
>> > >
>> > > Hi Alexandre,
>> > >
>> > > First, thanks for working on this! I think that we should
>> > > definitely
>> > > enable
>> > > this mode of supporting thread locals if possible.
>> > >
>> > > As an organizational note, I think it would be better to add a new
>> > > feature
>> > > macro for using TLS in this way (currently enabled only for PPC64).
>> > > As you
>> > > point out, other architectures will likely also want to do this,
>> > > and
>> > > we
>> > > should make this straightforward.
>> > >
>> > > +#if KMP_ARCH_PPC64
>> > > +void kmpc_threadprivate_call_unprocessed_constructors();
>> > > +#endif
>> > >
>> > > This function could be static, right?
>> > >
>> > > +       list. This is because each thread maintain a private
>> > > variable
>> > >
>> > > maintain -> maintains
>> > >
>> > > +void
>> > > +kmpc_threadprivate_call_unprocessed_constructors()
>> > >
>> > > I don't like that the comment explaining what this does is embedded
>> > > in some
>> > > other function (above). Please at least comment on where the
>> > > comment
>> > > is
>> > > explaining what this does.
>> > >
>> > > +        // one or more register occured since the last parallel
>> > > loop
>> > >
>> > > register -> registrations
>> > >
>> > >  -Hal
>> > >
>> > > ----- Original Message -----
>> > > > From: "Alexandre Eichenberger" <alexe at us.ibm.com>
>> > > > To: openmp-commits at dcs-maillist2.engr.illinois.edu
>> > > > Sent: Friday, June 12, 2015 5:51:27 PM
>> > > > Subject: [Openmp-commits] TLS for POWER
>> > > >
>> > > >
>> > > > I would like to request switching the threadprivate scheme to TLS
>> > > > (Thread
>> > > > Level Storage) for POWER before we get legacy code out there.
>> > > > Individual
>> > > > measurements has shown TLS to have about 10x lower overhead
>> > > > (number
>> > > > may
>> > > > change depending to the TLS scheme). TLS is also used by other
>> > > > compilers
>> > > > (e.g. XL) and thus provide better interoperability.
>> > > >
>> > > > Approach is relatively simple: compiler still generate a call to
>> > > > register
>> > > > the constructors and the destructors, but the functions calling
>> > > > the
>> > > > constructor/destructors have been changed a bit so that the
>> > > > compiler
>> > > > call
>> > > > the constructor on the TLS version of the object (not the global
>> > > > one,
>> > > > as it
>> > > > currently is in KMP). Then, prior to starting a parallel
>> > > > function,
>> > > > the
>> > > > workers check if there are no new constructors/destructors that
>> > > > have
>> > > > been
>> > > > registered; if there are, they will call the constructors prior
>> > > > to
>> > > > starting
>> > > > the parallel region. Destructors are called when killing a worker
>> > > > thread.
>> > > >
>> > > > KMP code change have been done (exclusively under #def for power
>> > > > architecture), LLVM changes have been done, code has been tested.
>> > > > Commit
>> > > > will need to be coordinated with the LLVM changes, which must go
>> > > > at
>> > > > the
>> > > > same time.
>> > > >
>> > > > If there is interest, and no code legacy issue, this patch could
>> > > > also
>> > > > be
>> > > > applied for other architectures that have TLS support.
>> > > >
>> > > > Alexandre
>> > > >
>> > > >
>> > > > (See attached file: tls_patch)
>> > > > _______________________________________________
>> > > > Openmp-commits mailing list
>> > > > Openmp-commits at dcs-maillist2.engr.illinois.edu
>> > > > http://lists.cs.uiuc.edu/mailman/listinfo/openmp-commits
>> > > >
>> > >
>> > > --
>> > > Hal Finkel
>> > > Assistant Computational Scientist
>> > > Leadership Computing Facility
>> > > Argonne National Laboratory
>> > >
>> > >
>> > >
>> >
>> > --
>> > Hal Finkel
>> > Assistant Computational Scientist
>> > Leadership Computing Facility
>> > Argonne National Laboratory
>> > _______________________________________________
>> > Openmp-commits mailing list
>> > Openmp-commits at dcs-maillist2.engr.illinois.edu
>> > http://lists.cs.uiuc.edu/mailman/listinfo/openmp-commits
>> >
>>
>> --
>> Hal Finkel
>> Assistant Computational Scientist
>> Leadership Computing Facility
>> Argonne National Laboratory
>> _______________________________________________
>> Openmp-commits mailing list
>> Openmp-commits at dcs-maillist2.engr.illinois.edu
>> http://lists.cs.uiuc.edu/mailman/listinfo/openmp-commits
>>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/openmp-commits/attachments/20150713/7dd510dc/attachment.html>