Re: [petsc-users] [Ext] Re: matcreate and assembly issue

Karl, Are you taking into account that every "integer" index might be 64 bits instead of 32 bits, depending on the PETSc configuration / compilation choices for PetscInt? Ernesto. From: petsc-users [mailto:petsc-users-boun...@mcs.anl.gov] On Behalf Of Junchao Zhang Sent: Thursday, July 2,

Re: [petsc-users] matcreate and assembly issue

Is it because indices for the nonzeros also need memory? --Junchao Zhang On Thu, Jul 2, 2020 at 10:04 PM Karl Lin wrote: > Hi, Matthew > > Thanks for the reply. However, I don't really get why additional malloc > would double the memory footprint. If I know there is only 1GB matrix being >

Re: [petsc-users] matcreate and assembly issue

Hi, Matthew Thanks for the reply. However, I don't really get why additional malloc would double the memory footprint. If I know there is only 1GB matrix being loaded, there shouldn't be 2GB memory occupied even if Petsc needs to allocate more space. regards, Karl On Thu, Jul 2, 2020 at 8:10

Re: [petsc-users] matcreate and assembly issue

https://www.mcs.anl.gov/petsc/documentation/faq.html#efficient-assembly Perhaps we should provide more information at this FAQ to help track down such issues. > On Jul 2, 2020, at 8:10 PM, Matthew Knepley wrote:

Re: [petsc-users] matcreate and assembly issue

On Thu, Jul 2, 2020 at 7:30 PM Karl Lin wrote: > Hi, Matt > > Thanks for the tip last time. We just encountered another issue with large > data sets. This time the behavior is the opposite from last time. The data > is 13.5TB, the total number of matrix columns is 2.4 billion. Our program >

Re: [petsc-users] matcreate and assembly issue

Hi, Matt Thanks for the tip last time. We just encountered another issue with large data sets. This time the behavior is the opposite from last time. The data is 13.5TB, the total number of matrix columns is 2.4 billion. Our program crashed during matrix loading due to memory overflow in one

Re: [petsc-users] DIVERGED_NANORINF when using HYPRE/BoomerAMG

> On Jul 2, 2020, at 7:48 AM, Andrea Iob wrote: > > I did some tests: depending on the smoother (set with the option > "-pc_hypre_boomeramg_smooth_type"), the arithmetic exception is throw by > different functions. Backtraces are at the bottom. Sorry for > the lack of line numbers, but, at

Re: [petsc-users] DIVERGED_NANORINF when using HYPRE/BoomerAMG

I did some tests: depending on the smoother (set with the option "-pc_hypre_boomeramg_smooth_type"), the arithmetic exception is throw by different functions. Backtraces are at the bottom. Sorry for the lack of line numbers, but, at the moment, I don't have a version of the PETSc library

Re: [petsc-users] MatGetRow for global rows of a parallel matrix

Thank you so much! Eda Zhang, Hong , 2 Tem 2020 Per, 07:29 tarihinde şunu yazdı: > > Dense matrix is stored in column-major order, so you might want to use > MatGetColumnVector() to access columns of the matrix instead of the rows. For > instance, you can get the n-th column out of the matrix