| #
930e68a5
|
| 12-Jan-2021 |
Mark Adams <524115-markadams4@users.noreply.gitlab.com> |
Adams/landau cleanup
Added mass matrix construction to GPU kernel to avoid problem with sparser mass matrix than Jacobian, messing up MatAXPY, rarely but unpredictably.
Added Kokkos solver st
Adams/landau cleanup
Added mass matrix construction to GPU kernel to avoid problem with sparser mass matrix than Jacobian, messing up MatAXPY, rarely but unpredictably.
Added Kokkos solver stubs to work with GPU offloaded matrices.
Fixed up ex2 for paper
Added runex2_[kokkos|cuda] targets to Landau makefile for paper
show more ...
|
| #
8ff777de
|
| 23-Dec-2020 |
Satish Balay <balay@mcs.anl.gov> |
Merge branch 'adams/landau-gpu-assembly' into 'master'
Adams/landau gpu assembly
See merge request petsc/petsc!3423
|
| #
a587d139
|
| 23-Dec-2020 |
Mark <cal2princeton@yahoo.com> |
Adding Cuda and Kokkos assembly. Added Device assembly to Landau operator. Added Kokkos test mat/ex5k.
|
| #
47f0c0cd
|
| 17-Nov-2020 |
Satish Balay <balay@mcs.anl.gov> |
Merge branch 'adams/landau-cuda-opt' into 'master'
Adams/landau cuda opt
See merge request petsc/petsc!3418
|
| #
52cdd6ea
|
| 17-Nov-2020 |
Mark <cal2princeton@yahoo.com> |
Nvidia optimizations
integrating new Cuda kernels
merged Peng's optimizations and cleanup (has debugging code)
wip, adding SOA
|
| #
bf5be063
|
| 26-Oct-2020 |
Satish Balay <balay@mcs.anl.gov> |
Merge remote-tracking branch 'origin/release' into master
|
| #
0bda62d2
|
| 25-Oct-2020 |
Satish Balay <balay@mcs.anl.gov> |
Merge branch 'adams/kokkos-64int-fix' into 'release'
fixed Kokkos bug with 64 int
See merge request petsc/petsc!3369
|
| #
37e8a436
|
| 23-Oct-2020 |
Mark Adams <ma2325@columbia.edu> |
fixed Kokkos bug with 64 int
|
| #
53d71bcd
|
| 26-Aug-2020 |
Satish Balay <balay@mcs.anl.gov> |
Merge branch 'adams/feature-dmplex-snes-landau-kokkos-barry-rebased' into 'master'
Adams/feature dmplex snes landau kokkos barry rebased
See merge request petsc/petsc!3050
|
| #
e0eea495
|
| 26-Aug-2020 |
Mark <cal2princeton@yahoo.com> |
Add a Landau collision operator, based on DMPlex and PetscFE, that uses p4est. It uses the new Kokkos interface and has a separate Cuda implementation. This could be deployed as 3rd party library, bu
Add a Landau collision operator, based on DMPlex and PetscFE, that uses p4est. It uses the new Kokkos interface and has a separate Cuda implementation. This could be deployed as 3rd party library, but this is easier to deploy to ECP, among other apps.
show more ...
|