Home
last modified time | relevance | path

Searched hist:"5 e71baeff2f3138f93cd4f5927dfd596eb8325cc" (Results 1 – 7 of 7) sorted by relevance

/petsc/src/benchmarks/streams/
H A Dprocess.pydiff 5e71baeff2f3138f93cd4f5927dfd596eb8325cc Fri Nov 06 21:32:36 UTC 2015 Barry Smith <bsmith@mcs.anl.gov> Add PetscProccessManagementView() and -process_view to use hwloc to display location of PETSc MPI processes on cores
This is to allow users and developers to know if the correct binding and mapping of processes to cores
on multicore systems is done as expected. Without this benchmarking to develop optimized code is not possible

Allow -process_view to be used with streams, determined optimal binding for streams on Intel 4 numa thing system

Funded-by: P-ECP
Time: 4
H A DMPIVersion.cdiff 5e71baeff2f3138f93cd4f5927dfd596eb8325cc Fri Nov 06 21:32:36 UTC 2015 Barry Smith <bsmith@mcs.anl.gov> Add PetscProccessManagementView() and -process_view to use hwloc to display location of PETSc MPI processes on cores
This is to allow users and developers to know if the correct binding and mapping of processes to cores
on multicore systems is done as expected. Without this benchmarking to develop optimized code is not possible

Allow -process_view to be used with streams, determined optimal binding for streams on Intel 4 numa thing system

Funded-by: P-ECP
Time: 4
H A Dmakefilediff 5e71baeff2f3138f93cd4f5927dfd596eb8325cc Fri Nov 06 21:32:36 UTC 2015 Barry Smith <bsmith@mcs.anl.gov> Add PetscProccessManagementView() and -process_view to use hwloc to display location of PETSc MPI processes on cores
This is to allow users and developers to know if the correct binding and mapping of processes to cores
on multicore systems is done as expected. Without this benchmarking to develop optimized code is not possible

Allow -process_view to be used with streams, determined optimal binding for streams on Intel 4 numa thing system

Funded-by: P-ECP
Time: 4
/petsc/src/sys/utils/
H A Dmemc.cdiff 5e71baeff2f3138f93cd4f5927dfd596eb8325cc Fri Nov 06 21:32:36 UTC 2015 Barry Smith <bsmith@mcs.anl.gov> Add PetscProccessManagementView() and -process_view to use hwloc to display location of PETSc MPI processes on cores
This is to allow users and developers to know if the correct binding and mapping of processes to cores
on multicore systems is done as expected. Without this benchmarking to develop optimized code is not possible

Allow -process_view to be used with streams, determined optimal binding for streams on Intel 4 numa thing system

Funded-by: P-ECP
Time: 4
/petsc/src/sys/objects/
H A Dinit.cdiff 5e71baeff2f3138f93cd4f5927dfd596eb8325cc Fri Nov 06 21:32:36 UTC 2015 Barry Smith <bsmith@mcs.anl.gov> Add PetscProccessManagementView() and -process_view to use hwloc to display location of PETSc MPI processes on cores
This is to allow users and developers to know if the correct binding and mapping of processes to cores
on multicore systems is done as expected. Without this benchmarking to develop optimized code is not possible

Allow -process_view to be used with streams, determined optimal binding for streams on Intel 4 numa thing system

Funded-by: P-ECP
Time: 4
H A Dpinit.cdiff 5e71baeff2f3138f93cd4f5927dfd596eb8325cc Fri Nov 06 21:32:36 UTC 2015 Barry Smith <bsmith@mcs.anl.gov> Add PetscProccessManagementView() and -process_view to use hwloc to display location of PETSc MPI processes on cores
This is to allow users and developers to know if the correct binding and mapping of processes to cores
on multicore systems is done as expected. Without this benchmarking to develop optimized code is not possible

Allow -process_view to be used with streams, determined optimal binding for streams on Intel 4 numa thing system

Funded-by: P-ECP
Time: 4
/petsc/include/
H A Dpetscsys.hdiff 5e71baeff2f3138f93cd4f5927dfd596eb8325cc Fri Nov 06 21:32:36 UTC 2015 Barry Smith <bsmith@mcs.anl.gov> Add PetscProccessManagementView() and -process_view to use hwloc to display location of PETSc MPI processes on cores
This is to allow users and developers to know if the correct binding and mapping of processes to cores
on multicore systems is done as expected. Without this benchmarking to develop optimized code is not possible

Allow -process_view to be used with streams, determined optimal binding for streams on Intel 4 numa thing system

Funded-by: P-ECP
Time: 4