Skip to content
GitLab
Projects
Groups
Snippets
/
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
Menu
Open sidebar
elpa
elpa
Commits
2ca871e3
Commit
2ca871e3
authored
Feb 10, 2021
by
Andreas Marek
Browse files
Use default(none) in elpa1_tridiag
parent
a0d5d730
Changes
1
Pipelines
1
Hide whitespace changes
Inline
Side-by-side
src/elpa1/elpa1_tridiag_template.F90
View file @
2ca871e3
...
...
@@ -581,8 +581,17 @@ subroutine tridiag_&
#ifdef WITH_OPENMP_TRADITIONAL
call
obj
%
timer
%
start
(
"OpenMP parallel"
)
!$OMP PARALLEL PRIVATE(my_thread,n_threads,n_iter,i,l_col_beg,l_col_end,j,l_row_beg,l_row_end)
!todo : check whether GPU implementation with large matrix multiply is beneficial
! for a larger number of threads; could be addressed with autotuning if this
! is the case
!$omp parallel &
!$omp num_threads(max_threads) &
!$omp default(none) &
!$omp private(my_thread,n_threads,n_iter,i,l_col_beg,l_col_end,j,l_row_beg,l_row_end) &
!$omp shared(useGPU, isSkewsymmetric, cudaMemcpyDeviceToHost, successCuda, u_row, u_row_dev, &
!$omp & v_row, v_row_dev, v_col, v_col_dev, u_col, u_col_dev, a_dev, a_offset, &
!$omp& max_local_cols, max_local_rows, obj, wantDebug, l_rows_per_tile, l_cols_per_tile, &
!$omp& matrixRows, istep, tile_size, l_rows, l_cols, ur_p, uc_p, a_mat)
my_thread
=
omp_get_thread_num
()
n_threads
=
omp_get_num_threads
()
...
...
Write
Preview
Supports
Markdown
0%
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment