July 2012 - mpiwg-rma - mailman3.cels.anl.gov

Re: [Mpi3-rma] Disp_unit in allocate_shared should be returned by win_shared_query?
by Jim Dinan 18 Jul '12

18 Jul '12

It's not inherently damaging, but it requires us to maintain/provide access to another O(p) structure and suggests to users that another process' disp_unit is useful information, which is incorrect. IIRC, we did discuss this in the working group and intentionally omitted it. ~Jim. On 7/18/12 1:38 PM, Torsten Hoefler wrote: > On Wed, Jul 18, 2012 at 01:18:53PM -0500, James Dinan wrote: >> On 7/18/12 1:06 PM, Torsten Hoefler wrote: >>> On Wed, Jul 18, 2012 at 01:08:43PM -0500, Pavan Balaji wrote: >>>> >>>> On 07/18/2012 01:02 PM, Torsten Hoefler wrote: >>>>> Jim, >>>>>> Is one process' disp_unit meaningful at another process? I thought that >>>>>> this is not the case. MPI provides no other routines to query another >>>>>> process' disp_unit. >>>>> It is something that the user is passing in. I don't know of a >>>>> particular use-case but we can query all other arguments that each >>>>> process passed. One more integer seemed safe to me. >>>>> >>>>>> Also, what meaning does a disp_unit have in the context of load/store >>>>>> operations that will result from win_shared_query? >>>>> Nothing. >>>>> >>>>>> Maybe I'm missing something, but this doesn't seem necessary. >>>>> Well, it's better to have it than to introduce it with a different name >>>>> later. That was my main motivation. One could also use it in a library >>>>> context to query. But that's weak, I know. >>>> >>>> This doesn't seem critical, and can always be added in MPI-3.1 if we >>>> find it necessary. No reason to rush it. >>> >>> It cannot be added without a new function name. That was the concern >>> here. Adding it seems less risk than not adding it. In addition, it is >>> already added ;-). >> >> I am concerned that this is a harmful change. The disp_unit from one >> process has no meaningful use at another process. If the user wants to >> know it for some reason, they can use a separate communication operation. > I believe the potential damage is very limited. But we can have a vote. > > So far it's still yes: 5, no: 1 > > I'm just mediating, not making decisions. > > Torsten >

1 0

Re: [Mpi3-rma] Disp_unit in allocate_shared should be returned by win_shared_query?
by Torsten Hoefler 18 Jul '12

18 Jul '12

On Wed, Jul 18, 2012 at 01:18:53PM -0500, James Dinan wrote: > On 7/18/12 1:06 PM, Torsten Hoefler wrote: >> On Wed, Jul 18, 2012 at 01:08:43PM -0500, Pavan Balaji wrote: >>> >>> On 07/18/2012 01:02 PM, Torsten Hoefler wrote: >>>> Jim, >>>>> Is one process' disp_unit meaningful at another process? I thought that >>>>> this is not the case. MPI provides no other routines to query another >>>>> process' disp_unit. >>>> It is something that the user is passing in. I don't know of a >>>> particular use-case but we can query all other arguments that each >>>> process passed. One more integer seemed safe to me. >>>> >>>>> Also, what meaning does a disp_unit have in the context of load/store >>>>> operations that will result from win_shared_query? >>>> Nothing. >>>> >>>>> Maybe I'm missing something, but this doesn't seem necessary. >>>> Well, it's better to have it than to introduce it with a different name >>>> later. That was my main motivation. One could also use it in a library >>>> context to query. But that's weak, I know. >>> >>> This doesn't seem critical, and can always be added in MPI-3.1 if we >>> find it necessary. No reason to rush it. > > >> It cannot be added without a new function name. That was the concern >> here. Adding it seems less risk than not adding it. In addition, it is >> already added ;-). > > I am concerned that this is a harmful change. The disp_unit from one > process has no meaningful use at another process. If the user wants to > know it for some reason, they can use a separate communication operation. I believe the potential damage is very limited. But we can have a vote. So far it's still yes: 5, no: 1 I'm just mediating, not making decisions. Torsten -- ### qreharg rug ebs fv crryF ------------- http://www.unixer.de/ ----- Torsten Hoefler | Performance Modeling and Simulation Lead Blue Waters Directorate | University of Illinois (UIUC) 1205 W Clark Street | Urbana, IL, 61801 NCSA Building | +01 (217) 244-7736

1 0

Re: [Mpi3-rma] Disp_unit in allocate_shared should be returned by win_shared_query?
by Jim Dinan 18 Jul '12

18 Jul '12

On 7/18/12 1:06 PM, Torsten Hoefler wrote: > On Wed, Jul 18, 2012 at 01:08:43PM -0500, Pavan Balaji wrote: >> >> On 07/18/2012 01:02 PM, Torsten Hoefler wrote: >>> Jim, >>>> Is one process' disp_unit meaningful at another process? I thought that >>>> this is not the case. MPI provides no other routines to query another >>>> process' disp_unit. >>> It is something that the user is passing in. I don't know of a >>> particular use-case but we can query all other arguments that each >>> process passed. One more integer seemed safe to me. >>> >>>> Also, what meaning does a disp_unit have in the context of load/store >>>> operations that will result from win_shared_query? >>> Nothing. >>> >>>> Maybe I'm missing something, but this doesn't seem necessary. >>> Well, it's better to have it than to introduce it with a different name >>> later. That was my main motivation. One could also use it in a library >>> context to query. But that's weak, I know. >> >> This doesn't seem critical, and can always be added in MPI-3.1 if we >> find it necessary. No reason to rush it. > > It cannot be added without a new function name. That was the concern > here. Adding it seems less risk than not adding it. In addition, it is > already added ;-). I am concerned that this is a harmful change. The disp_unit from one process has no meaningful use at another process. If the user wants to know it for some reason, they can use a separate communication operation. ~Jim.

1 0

Re: [Mpi3-rma] Disp_unit in allocate_shared should be returned by win_shared_query?
by Pavan Balaji 18 Jul '12

18 Jul '12

On 07/18/2012 01:06 PM, Torsten Hoefler wrote: > It cannot be added without a new function name. That was the concern > here. Adding it seems less risk than not adding it. In addition, it is > already added ;-). Ah, I didn't realize you stuck it into the same function. Fine, then. -- Pavan Balaji http://www.mcs.anl.gov/~balaji

1 0

Re: [Mpi3-rma] Disp_unit in allocate_shared should be returned by win_shared_query?
by Pavan Balaji 18 Jul '12

18 Jul '12

On 07/18/2012 01:02 PM, Torsten Hoefler wrote: > Jim, >> Is one process' disp_unit meaningful at another process? I thought that >> this is not the case. MPI provides no other routines to query another >> process' disp_unit. > It is something that the user is passing in. I don't know of a > particular use-case but we can query all other arguments that each > process passed. One more integer seemed safe to me. > >> Also, what meaning does a disp_unit have in the context of load/store >> operations that will result from win_shared_query? > Nothing. > >> Maybe I'm missing something, but this doesn't seem necessary. > Well, it's better to have it than to introduce it with a different name > later. That was my main motivation. One could also use it in a library > context to query. But that's weak, I know. This doesn't seem critical, and can always be added in MPI-3.1 if we find it necessary. No reason to rush it. -- Pavan -- Pavan Balaji http://www.mcs.anl.gov/~balaji

1 0

Re: [Mpi3-rma] Disp_unit in allocate_shared should be returned by win_shared_query?
by Torsten Hoefler 18 Jul '12

18 Jul '12

On Wed, Jul 18, 2012 at 01:08:43PM -0500, Pavan Balaji wrote: > > On 07/18/2012 01:02 PM, Torsten Hoefler wrote: >> Jim, >>> Is one process' disp_unit meaningful at another process? I thought that >>> this is not the case. MPI provides no other routines to query another >>> process' disp_unit. >> It is something that the user is passing in. I don't know of a >> particular use-case but we can query all other arguments that each >> process passed. One more integer seemed safe to me. >> >>> Also, what meaning does a disp_unit have in the context of load/store >>> operations that will result from win_shared_query? >> Nothing. >> >>> Maybe I'm missing something, but this doesn't seem necessary. >> Well, it's better to have it than to introduce it with a different name >> later. That was my main motivation. One could also use it in a library >> context to query. But that's weak, I know. > > This doesn't seem critical, and can always be added in MPI-3.1 if we > find it necessary. No reason to rush it. It cannot be added without a new function name. That was the concern here. Adding it seems less risk than not adding it. In addition, it is already added ;-). Torsten -- ### qreharg rug ebs fv crryF ------------- http://www.unixer.de/ ----- Torsten Hoefler | Performance Modeling and Simulation Lead Blue Waters Directorate | University of Illinois (UIUC) 1205 W Clark Street | Urbana, IL, 61801 NCSA Building | +01 (217) 244-7736

1 0

Re: [Mpi3-rma] Disp_unit in allocate_shared should be returned by win_shared_query?
by Jim Dinan 18 Jul '12

18 Jul '12

Hi Torsten, Is one process' disp_unit meaningful at another process? I thought that this is not the case. MPI provides no other routines to query another process' disp_unit. Also, what meaning does a disp_unit have in the context of load/store operations that will result from win_shared_query? Maybe I'm missing something, but this doesn't seem necessary. ~Jim. On 7/18/12 9:54 AM, Torsten Hoefler wrote: > Hi group, > > Hubert just brought this up at the ticket. It's a valid point but may be > a bit late. Unfortunately, we're far away from a quorum at the Forum (we > have only Sreeram and me in the room). So I am broadcasting the question > to the mailinglist. > > Any opinions? I'd vote to add it also (as part of yesterday's change). > > Thanks, > Torsten >

1 0

Re: [Mpi3-rma] Disp_unit in allocate_shared should be returned by win_shared_query?
by Torsten Hoefler 18 Jul '12

18 Jul '12

Jim, > Is one process' disp_unit meaningful at another process? I thought that > this is not the case. MPI provides no other routines to query another > process' disp_unit. It is something that the user is passing in. I don't know of a particular use-case but we can query all other arguments that each process passed. One more integer seemed safe to me. > Also, what meaning does a disp_unit have in the context of load/store > operations that will result from win_shared_query? Nothing. > Maybe I'm missing something, but this doesn't seem necessary. Well, it's better to have it than to introduce it with a different name later. That was my main motivation. One could also use it in a library context to query. But that's weak, I know. We can back it out. We can also discuss it at a telecon. Torsten -- ### qreharg rug ebs fv crryF ------------- http://www.unixer.de/ ----- Torsten Hoefler | Performance Modeling and Simulation Lead Blue Waters Directorate | University of Illinois (UIUC) 1205 W Clark Street | Urbana, IL, 61801 NCSA Building | +01 (217) 244-7736

1 0

Re: [Mpi3-rma] Disp_unit in allocate_shared should be returned by win_shared_query?
by sreeram potluri 18 Jul '12

18 Jul '12

The implementation looks good to me otherwise. Sreeram Potluri On Wed, Jul 18, 2012 at 12:53 PM, sreeram potluri <potluri(a)cse.ohio-state.edu> wrote: > Torsten, > > A similar change might be required in the following sentence. Not > critical but to be more complete. > > If all processes in the group attached to the window speci ed size = > 0, then the call returns size = 0 and a baseptr as if MPI_ALLOC_MEM > was called with size = 0. > > to > > If all processes in the group attached to the window speci ed size = > 0, then the call returns size = 0, disp_unit = 0 and a baseptr as if > MPI_ALLOC_MEM was called with size = 0. > > Thanks > Seeram Potluri > > On Wed, Jul 18, 2012 at 12:00 PM, Torsten Hoefler <htor(a)illinois.edu> wrote: >> Ok, I implemented it in approved/one-sided. Please review new document >> on https://svn.mpi-forum.org/trac/mpi-forum-web/ticket/284 . >> >> Thanks, >> Torsten >> >> On Wed, Jul 18, 2012 at 10:54:36AM -0500, Jeff Hammond wrote: >>> makes sense. +1 from me. >>> >>> On Wed, Jul 18, 2012 at 10:53 AM, William Gropp <wgropp(a)illinois.edu> wrote: >>> > I agree - I vote for adding it. >>> > >>> > Bill >>> > >>> > William Gropp >>> > Director, Parallel Computing Institute >>> > Deputy Director for Research >>> > Institute for Advanced Computing Applications and Technologies >>> > Paul and Cynthia Saylor Professor of Computer Science >>> > University of Illinois Urbana-Champaign >>> > >>> > >>> > >>> > On Jul 18, 2012, at 10:22 AM, sreeram potluri wrote: >>> > >>> >> I'd also vote for adding it, to be consistent. >>> >> >>> >> Thanks, >>> >> Sreeram >>> >> >>> >> On Wed, Jul 18, 2012 at 9:54 AM, Torsten Hoefler <htor(a)illinois.edu> wrote: >>> >>> Hi group, >>> >>> >>> >>> Hubert just brought this up at the ticket. It's a valid point but may be >>> >>> a bit late. Unfortunately, we're far away from a quorum at the Forum (we >>> >>> have only Sreeram and me in the room). So I am broadcasting the question >>> >>> to the mailinglist. >>> >>> >>> >>> Any opinions? I'd vote to add it also (as part of yesterday's change). >>> >>> >>> >>> Thanks, >>> >>> Torsten >>> >>> >>> >>> -- >>> >>> ### qreharg rug ebs fv crryF ------------- http://www.unixer.de/ ----- >>> >>> Torsten Hoefler | Performance Modeling and Simulation Lead >>> >>> Blue Waters Directorate | University of Illinois (UIUC) >>> >>> 1205 W Clark Street | Urbana, IL, 61801 >>> >>> NCSA Building | +01 (217) 244-7736 >>> >>> _______________________________________________ >>> >>> mpi3-rma mailing list >>> >>> mpi3-rma(a)lists.mpi-forum.org >>> >>> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-rma >>> >> _______________________________________________ >>> >> mpi3-rma mailing list >>> >> mpi3-rma(a)lists.mpi-forum.org >>> >> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-rma >>> > >>> > _______________________________________________ >>> > mpi3-rma mailing list >>> > mpi3-rma(a)lists.mpi-forum.org >>> > http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-rma >>> >>> >>> >>> -- >>> Jeff Hammond >>> Argonne Leadership Computing Facility >>> University of Chicago Computation Institute >>> jhammond(a)alcf.anl.gov / (630) 252-5381 >>> http://www.linkedin.com/in/jeffhammond >>> https://wiki.alcf.anl.gov/parts/index.php/User:Jhammond >>> _______________________________________________ >>> mpi3-rma mailing list >>> mpi3-rma(a)lists.mpi-forum.org >>> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-rma >>> >> >> -- >> ### qreharg rug ebs fv crryF ------------- http://www.unixer.de/ ----- >> Torsten Hoefler | Performance Modeling and Simulation Lead >> Blue Waters Directorate | University of Illinois (UIUC) >> 1205 W Clark Street | Urbana, IL, 61801 >> NCSA Building | +01 (217) 244-7736 >> _______________________________________________ >> mpi3-rma mailing list >> mpi3-rma(a)lists.mpi-forum.org >> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-rma

1 0

Re: [Mpi3-rma] Disp_unit in allocate_shared should be returned by win_shared_query?
by sreeram potluri 18 Jul '12

18 Jul '12

Torsten, A similar change might be required in the following sentence. Not critical but to be more complete. If all processes in the group attached to the window specied size = 0, then the call returns size = 0 and a baseptr as if MPI_ALLOC_MEM was called with size = 0. to If all processes in the group attached to the window specied size = 0, then the call returns size = 0, disp_unit = 0 and a baseptr as if MPI_ALLOC_MEM was called with size = 0. Thanks Seeram Potluri On Wed, Jul 18, 2012 at 12:00 PM, Torsten Hoefler <htor(a)illinois.edu> wrote: > Ok, I implemented it in approved/one-sided. Please review new document > on https://svn.mpi-forum.org/trac/mpi-forum-web/ticket/284 . > > Thanks, > Torsten > > On Wed, Jul 18, 2012 at 10:54:36AM -0500, Jeff Hammond wrote: >> makes sense. +1 from me. >> >> On Wed, Jul 18, 2012 at 10:53 AM, William Gropp <wgropp(a)illinois.edu> wrote: >> > I agree - I vote for adding it. >> > >> > Bill >> > >> > William Gropp >> > Director, Parallel Computing Institute >> > Deputy Director for Research >> > Institute for Advanced Computing Applications and Technologies >> > Paul and Cynthia Saylor Professor of Computer Science >> > University of Illinois Urbana-Champaign >> > >> > >> > >> > On Jul 18, 2012, at 10:22 AM, sreeram potluri wrote: >> > >> >> I'd also vote for adding it, to be consistent. >> >> >> >> Thanks, >> >> Sreeram >> >> >> >> On Wed, Jul 18, 2012 at 9:54 AM, Torsten Hoefler <htor(a)illinois.edu> wrote: >> >>> Hi group, >> >>> >> >>> Hubert just brought this up at the ticket. It's a valid point but may be >> >>> a bit late. Unfortunately, we're far away from a quorum at the Forum (we >> >>> have only Sreeram and me in the room). So I am broadcasting the question >> >>> to the mailinglist. >> >>> >> >>> Any opinions? I'd vote to add it also (as part of yesterday's change). >> >>> >> >>> Thanks, >> >>> Torsten >> >>> >> >>> -- >> >>> ### qreharg rug ebs fv crryF ------------- http://www.unixer.de/ ----- >> >>> Torsten Hoefler | Performance Modeling and Simulation Lead >> >>> Blue Waters Directorate | University of Illinois (UIUC) >> >>> 1205 W Clark Street | Urbana, IL, 61801 >> >>> NCSA Building | +01 (217) 244-7736 >> >>> _______________________________________________ >> >>> mpi3-rma mailing list >> >>> mpi3-rma(a)lists.mpi-forum.org >> >>> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-rma >> >> _______________________________________________ >> >> mpi3-rma mailing list >> >> mpi3-rma(a)lists.mpi-forum.org >> >> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-rma >> > >> > _______________________________________________ >> > mpi3-rma mailing list >> > mpi3-rma(a)lists.mpi-forum.org >> > http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-rma >> >> >> >> -- >> Jeff Hammond >> Argonne Leadership Computing Facility >> University of Chicago Computation Institute >> jhammond(a)alcf.anl.gov / (630) 252-5381 >> http://www.linkedin.com/in/jeffhammond >> https://wiki.alcf.anl.gov/parts/index.php/User:Jhammond >> _______________________________________________ >> mpi3-rma mailing list >> mpi3-rma(a)lists.mpi-forum.org >> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-rma >> > > -- > ### qreharg rug ebs fv crryF ------------- http://www.unixer.de/ ----- > Torsten Hoefler | Performance Modeling and Simulation Lead > Blue Waters Directorate | University of Illinois (UIUC) > 1205 W Clark Street | Urbana, IL, 61801 > NCSA Building | +01 (217) 244-7736 > _______________________________________________ > mpi3-rma mailing list > mpi3-rma(a)lists.mpi-forum.org > http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-rma

1 0