Re: [petsc-dev] MatMatMult

2017-06-06 Thread Pierre Jolivet
> On 6 Jun 2017, at 11:21 PM, Barry Smith wrote: > >> >> On Jun 6, 2017, at 1:52 PM, Pierre Jolivet >> wrote: >> >> On Tue, 6 Jun 2017 13:44:06 -0500, Hong wrote: >>> Pierre : >>> Yes, of course I defined (*C)->ops->matmultnumeric = MatMatMultNumeric_MPIBAIJ_MPIDense in MatMa

Re: [petsc-dev] PETSc statistics

2017-06-06 Thread Jeff Hammond
On Tue, Jun 6, 2017 at 2:23 PM Barry Smith wrote: > > > On Jun 6, 2017, at 12:47 PM, Jed Brown wrote: > > > > Matthew Knepley writes: > > > >> On Tue, Jun 6, 2017 at 2:15 AM, Dave May > wrote: > >> > >>> Hello, > >>> > >>> Is there a place where I can find up-to-date statistics about the PETSc

Re: [petsc-dev] PETSc statistics

2017-06-06 Thread Barry Smith
> On Jun 6, 2017, at 12:47 PM, Jed Brown wrote: > > Matthew Knepley writes: > >> On Tue, Jun 6, 2017 at 2:15 AM, Dave May wrote: >> >>> Hello, >>> >>> Is there a place where I can find up-to-date statistics about the PETSc >>> user base? >>> >>> I was thinking about these metrics: >>> * av

Re: [petsc-dev] MatMatMult

2017-06-06 Thread Barry Smith
> On Jun 6, 2017, at 1:52 PM, Pierre Jolivet wrote: > > On Tue, 6 Jun 2017 13:44:06 -0500, Hong wrote: >> Pierre : >> >>> Yes, of course I defined (*C)->ops->matmultnumeric = >>> MatMatMultNumeric_MPIBAIJ_MPIDense in >>> MatMatMultSymbolic_MPIBAIJ_MPIDense. >>> However, the routine MatMatMultSy

Re: [petsc-dev] MatMatMult

2017-06-06 Thread Hong
What is your calling procedure for using MatMatMultNumeric_MPIBAIJ_MPIDense? Hong On Tue, Jun 6, 2017 at 1:52 PM, Pierre Jolivet wrote: > On Tue, 6 Jun 2017 13:44:06 -0500, Hong wrote: > >> Pierre : >> >> Yes, of course I defined (*C)->ops->matmultnumeric = >>> MatMatMultNumeric_MPIBAIJ_MPIDense

Re: [petsc-dev] MatMatMult

2017-06-06 Thread Pierre Jolivet
On Tue, 6 Jun 2017 13:44:06 -0500, Hong wrote: Pierre : Yes, of course I defined (*C)->ops->matmultnumeric = MatMatMultNumeric_MPIBAIJ_MPIDense in MatMatMultSymbolic_MPIBAIJ_MPIDense. However, the routine MatMatMultSymbolic_MPIBAIJ_MPIDense is never reached when calling MatMatMult with scall ==

Re: [petsc-dev] MatMatMult

2017-06-06 Thread Hong
Pierre : > > > Yes, of course I defined (*C)->ops->matmultnumeric = > MatMatMultNumeric_MPIBAIJ_MPIDense in MatMatMultSymbolic_MPIBAIJ_MPIDense. > However, the routine MatMatMultSymbolic_MPIBAIJ_MPIDense is never reached > when calling MatMatMult with scall == MAT_REUSE_MATRIX ( > http://www.mcs.an

Re: [petsc-dev] PETSc statistics

2017-06-06 Thread Matthew Knepley
On Tue, Jun 6, 2017 at 12:47 PM, Jed Brown wrote: > Matthew Knepley writes: > > > On Tue, Jun 6, 2017 at 2:15 AM, Dave May > wrote: > > > >> Hello, > >> > >> Is there a place where I can find up-to-date statistics about the PETSc > >> user base? > >> > >> I was thinking about these metrics: > >

Re: [petsc-dev] PETSc statistics

2017-06-06 Thread Jed Brown
Matthew Knepley writes: > On Tue, Jun 6, 2017 at 2:15 AM, Dave May wrote: > >> Hello, >> >> Is there a place where I can find up-to-date statistics about the PETSc >> user base? >> >> I was thinking about these metrics: >> * average monthly downloads >> > > This has email statistics: https://arx

Re: [petsc-dev] MatMatMult

2017-06-06 Thread Pierre Jolivet
On Tue, 6 Jun 2017 10:57:10 -0500, Hong wrote: Pierre: Hello, I'm implementing MatMatMult for A of type MPIBAIJ, B and C of type MPIDENSE. 1) I copied around some code for the case where A is of type MPIAIJ. Any reason why communications and computations are not overlapped in the MatMatMult imp

Re: [petsc-dev] PETSc statistics

2017-06-06 Thread Matthew Knepley
On Tue, Jun 6, 2017 at 2:15 AM, Dave May wrote: > Hello, > > Is there a place where I can find up-to-date statistics about the PETSc > user base? > > I was thinking about these metrics: > * average monthly downloads > This has email statistics: https://arxiv.org/abs/1510.01122 Its very hard to g

Re: [petsc-dev] MatMatMult

2017-06-06 Thread Hong
Pierre: > Hello, > I'm implementing MatMatMult for A of type MPIBAIJ, B and C of type > MPIDENSE. > 1) I copied around some code for the case where A is of type MPIAIJ. Any > reason why communications and computations are not overlapped in the > MatMatMult implementation? http://www.mcs.anl.gov/pe

[petsc-dev] MatMatMult

2017-06-06 Thread Pierre Jolivet
Hello, I'm implementing MatMatMult for A of type MPIBAIJ, B and C of type MPIDENSE. 1) I copied around some code for the case where A is of type MPIAIJ. Any reason why communications and computations are not overlapped in the MatMatMult implementation? http://www.mcs.anl.gov/petsc/petsc-curren

[petsc-dev] PETSc statistics

2017-06-06 Thread Dave May
Hello, Is there a place where I can find up-to-date statistics about the PETSc user base? I was thinking about these metrics: * average monthly downloads * total citations (looks like 1518 from google scholar) * any estimates of the number of actual users Any other metrics would be welcome as we