Skip to content
GitLab
Projects
Groups
Snippets
Help
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
elpa
Project overview
Project overview
Details
Activity
Releases
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Issues
11
Issues
11
List
Boards
Labels
Service Desk
Milestones
Merge Requests
0
Merge Requests
0
Operations
Operations
Incidents
Environments
Analytics
Analytics
Repository
Value Stream
Wiki
Wiki
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Create a new issue
Commits
Issue Boards
Open sidebar
elpa
elpa
Commits
3bb78876
Commit
3bb78876
authored
Nov 20, 2017
by
Andreas Marek
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
Fix error in compute_hh_trafo
parent
a4fc25e4
Changes
3
Pipelines
1
Expand all
Hide whitespace changes
Inline
Side-by-side
Showing
3 changed files
with
3726 additions
and
3377 deletions
+3726
-3377
.gitlab-ci.yml
.gitlab-ci.yml
+3687
-3375
generate_gitlab_ci_tests.py
generate_gitlab_ci_tests.py
+1
-1
src/elpa2/compute_hh_trafo.F90
src/elpa2/compute_hh_trafo.F90
+38
-1
No files found.
.gitlab-ci.yml
View file @
3bb78876
This diff is collapsed.
Click to expand it.
generate_gitlab_ci_tests.py
View file @
3bb78876
...
...
@@ -373,7 +373,7 @@ instruction_set = {
"sse"
:
" --enable-sse --enable-sse-assembly"
,
"avx"
:
" --enable-avx"
,
"avx2"
:
" --enable-avx2"
,
"power8"
:
" --disable-sse --disable-sse-assembly --disable-avx --disable-avx2 --disable-mpi-module --with-GPU-compute-capability=sm_60 "
,
"power8"
:
" --
enable-vsx --
disable-sse --disable-sse-assembly --disable-avx --disable-avx2 --disable-mpi-module --with-GPU-compute-capability=sm_60 "
,
}
...
...
src/elpa2/compute_hh_trafo.F90
View file @
3bb78876
...
...
@@ -544,7 +544,7 @@
&
_
generic_simple_
&
&
PRECISION
&
&
(
a
(
1
:
stripe_width
,
j
+
off
+
a_off
:
j
+
off
+
a_off
+
nbw
-1
,
istripe
),
bcast_buffer
(
1
:
nbw
,
j
+
off
),
&
nbw
,
nl
,
stripe_width
)
nbw
,
nl
,
stripe_width
)
#endif
#endif /* WITH_OPENMP */
...
...
@@ -877,6 +877,43 @@
#endif /* REALCASE == 1 */
#if REALCASE == 1
! implementation of sse block 2 real case
#if defined(WITH_REAL_SSE_BLOCK2_KERNEL)
#ifndef WITH_FIXED_REAL_KERNEL
if
(
kernel
.eq.
ELPA_2STAGE_REAL_SSE_BLOCK2
)
then
#endif /* not WITH_FIXED_REAL_KERNEL */
#if (!defined(WITH_FIXED_REAL_KERNEL)) || (defined(WITH_FIXED_REAL_KERNEL) && !defined(WITH_REAL_SSE_BLOCK6_KERNEL) && !defined(WITH_REAL_SSE_BLOCK4_KERNEL))
do
j
=
ncols
,
2
,
-2
w
(:,
1
)
=
bcast_buffer
(
1
:
nbw
,
j
+
off
)
w
(:,
2
)
=
bcast_buffer
(
1
:
nbw
,
j
+
off
-1
)
#ifdef WITH_OPENMP
call
double_hh_trafo_
&
&
MATH_DATATYPE
&
&
_
sse_2hv_
&
&
PRECISION
&
&
(
c_loc
(
a
(
1
,
j
+
off
+
a_off
-1
,
istripe
,
my_thread
)),
w
,
nbw
,
nl
,
stripe_width
,
nbw
)
#else
call
double_hh_trafo_
&
&
MATH_DATATYPE
&
&
_
sse_2hv_
&
&
PRECISION
&
&
(
c_loc
(
a
(
1
,
j
+
off
+
a_off
-1
,
istripe
)),
w
,
nbw
,
nl
,
stripe_width
,
nbw
)
#endif
enddo
#endif /* (!defined(WITH_FIXED_REAL_KERNEL)) || (defined(WITH_FIXED_REAL_KERNEL) && !defined(WITH_REAL_SSE_BLOCK6_KERNEL) && !defined(WITH_REAL_SSE_BLOCK4_KERNEL)) */
#ifndef WITH_FIXED_REAL_KERNEL
endif
#endif /* not WITH_FIXED_REAL_KERNEL */
#endif /* WITH_REAL_SSE_BLOCK2_KERNEL */
#endif /* REALCASE == 1 */
#if COMPLEXCASE == 1
! implementation of sparc64 block 2 complex case
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a 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