Merge branch 'jczhang/feature-add-comments-matproduct' into 'main'

Mat/SF: add some comments to code

See merge request petsc/petsc!4231

MAT/SF: add some comments to code

Merge branch 'barry/2020-11-11/cleanup-matsetvaluesdevice' into 'main'

MatSetValuesDevice: Cleanup and simplify code, including example

See merge request petsc/petsc!3411

MatSetValuesDevice: Cleanup and simplify code, including example

User reported crash of example code. Kernel was passed an ierr that lived in CPU memory

MatSetValuesDevice: do not include private h

MatSetValuesDevice: Cleanup and simplify code, including example

User reported crash of example code. Kernel was passed an ierr that lived in CPU memory

MatSetValuesDevice: do not include private headers from public headers

Feature: MatSetValuesDevice determines automatically from the context (where it is included from) if it is being used from C, CUDA, or Kokkos, PETSC_DEVICE_FUNC_DEC no longer needs to be set before including petscaijdevice.h

Feature: MatSetValuesDevice() now ignores all values outside the global column range.

PetscSplitCSRDataStructure is now a pointer, not a struct, like most PETSc objects, please leave it that way.

Fix all uses of CTABLE that were related to the original MatSetValuesDevice()

Have atomicAdd use Kokkos atomic-add with CPU build when building with Kokkos.

Cuda should now work with --download-openmpi, this is done by updating updateCompilers() to rerun portions of packages/cuda.py after the compilers are reset to use MPI wrappers. This is needed because the resetting of the compilers removes all the compiler flags and packages/cuda.py sets certain values into these flags that was previously lost.

Add MPICXX_INCLUDES, MPICXX_LIBS to fix compile targets for Kokkos examples

'make check' now runs properly for Kokkos test of src/snes/ex3k, fixed bug in the makefile wrt MPI_IS_MPIUNI check

Testing makefile rules: add ex*cu binaries to clean rule

Reported-by: Sam Fagbemi <samkorede24@gmail.com>
Thanks-to: Stefano Zampini <stefano.zampini@gmail.com>
Thanks-to: Mark Adams <mfadams@lbl.gov>

/spend 16h

show more ...

Merge branch 'adams/landau-gpu-opt' into 'main'

Adams/landau gpu opt

See merge request petsc/petsc!3792

Add cuSparse Band LU factorization

Merge remote-tracking branch 'origin/release'

Merge branch 'barry/2021-04-05/fix-chkerrcusolver/release' into 'release'

Add proper error return codes for cuSolver error checker. CHKERRCUSOLVER()

See merge request petsc/petsc!3827

Add proper error return codes for cuSolver error checker. CHKERRCUSOLVER()

Don't check PetscCUDAInitialized in CHKERRCU* routines since it will not be set yet

/spend 2h

Merge branch 'adams/cusparse-lu-band' into 'main'

Add cuSparse Band LU factorization

See merge request petsc/petsc!3713

Add cuSparse Band LU factorization

Merge remote-tracking branch 'origin/jczhang/add-DMDAVecGetKokkosOffsetView'

Add DMDAVecGetKokkosOffsetView and friends

See merge request petsc/petsc!3383

Rename -mat_cusparse_transgen to -mat_form_explicit_transpose

Merge branch 'stefanozampini/fixes' into 'master'

Device fixes

See merge request petsc/petsc!3541

MATSEQAIJCUSPARSE: better handling of explicit transposition

keep track when the transposed matrix needs to be updated
call csr2csc only once, use thrust calls otherwise

Merge branch 'barry/2020-12-28/cusparse-not-initialized-indicates-out-of-resources' into 'master'

Sometimes cuSparse routines report they have not been initialized when we know they have been.

See

Merge branch 'barry/2020-12-28/cusparse-not-initialized-indicates-out-of-resources' into 'master'

Sometimes cuSparse routines report they have not been initialized when we know they have been.

See merge request petsc/petsc!3522

show more ...

Report resource errors from CUDA, cuBLAS, and cuSparse as PETSC_ERR_GPU_RESOURCE so test harness can retry them.

Convert the error code to a GPU resource error code so that the test harness will rer

Report resource errors from CUDA, cuBLAS, and cuSparse as PETSC_ERR_GPU_RESOURCE so test harness can retry them.

Convert the error code to a GPU resource error code so that the test harness will rerun the example multiple times.

This should decrease the number of false job failures for CUDA runs

/spend 1.5h

show more ...

Merge branch 'stefanozampini/gamg-gpu-setup' into 'master'

MatMat operations with CUSPARSE

See merge request petsc/petsc!3391

MatAXPY: add support for CUSPARSE

PetscStackCallThrust

MatSetValuesCOO: use cuda memory if possible

MatMPIAIJGetLocalMatMerge: support for merging two matrices

MatSetValuesCOO: perform addition of repeated entries when INSERT_VALUES is specified

use temporary data instead of persistent storage in cusparse implementation

MATSEQAIJCUSPARSE: add support for sparse MatMat operations

Merge branch 'adams/cusparse-host-buffer' into 'master'

Adams/cusparse host buffer

See merge request petsc/petsc!3502