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
40de4b47
Commit
40de4b47
authored
Feb 05, 2017
by
Andreas Marek
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
Keep tmat on device
parent
16300a2e
Changes
2
Pipelines
1
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
43 additions
and
43 deletions
+43
-43
src/elpa2_bandred_template.X90
src/elpa2_bandred_template.X90
+9
-9
src/elpa2_trans_ev_band_to_full_template.X90
src/elpa2_trans_ev_band_to_full_template.X90
+34
-34
No files found.
src/elpa2_bandred_template.X90
View file @
40de4b47
...
...
@@ -1973,15 +1973,15 @@
endif
!#ifdef WITH_MPI
! it should be possible to keep tmat dev on the device and not copy it arround
! this is not necessary tmat_dev is passed (unchanged) from one routine to the other
successCUDA = cuda_free(tmat_dev)
if (.not.(successCUDA)) then
print *,"bandred_&
&MATH_DATATYPE&
&: error in cudaFree"
stop
endif
!
!
it should be possible to keep tmat dev on the device and not copy it arround
!
!
this is not necessary tmat_dev is passed (unchanged) from one routine to the other
!
successCUDA = cuda_free(tmat_dev)
!
if (.not.(successCUDA)) then
!
print *,"bandred_&
!
&MATH_DATATYPE&
!
&: error in cudaFree"
!
stop
!
endif
!#endif
successCUDA = cuda_free(vav_dev)
...
...
src/elpa2_trans_ev_band_to_full_template.X90
View file @
40de4b47
...
...
@@ -281,22 +281,22 @@
endif
!#ifdef WITH_MPI
! it should be possible to keep tmat dev on the device and not copy it around
! already existent on GPU
successCUDA = cuda_malloc(tmat_dev, nbw*nbw* &
#if REALCASE == 1
size_of_PRECISION_real)
#endif
#if COMPLEXCASE == 1
size_of_PRECISION_complex)
#endif
if (.not.(successCUDA)) then
print *,"trans_ev_band_to_full_&
&MATH_DATATYPE&
&: error in cudaMalloc"
stop
endif
!
!
it should be possible to keep tmat dev on the device and not copy it around
!
!
already existent on GPU
!
successCUDA = cuda_malloc(tmat_dev, nbw*nbw* &
!
#if REALCASE == 1
!
size_of_PRECISION_real)
!
#endif
!
#if COMPLEXCASE == 1
!
size_of_PRECISION_complex)
!
#endif
!
!
if (.not.(successCUDA)) then
!
print *,"trans_ev_band_to_full_&
!
&MATH_DATATYPE&
!
&: error in cudaMalloc"
!
stop
!
endif
!#endif
#if REALCASE == 1
...
...
@@ -564,24 +564,24 @@
#endif /* WITH_MPI */
!#ifdef WITH_MPI
! it should be possible to keep tmat on the device and not copy it aroud
! ! copy to device, maybe this can be avoided tmat is input from bandred_real
successCUDA = cuda_memcpy(tmat_dev, loc(tmat(1,1,istep)), nbw*nbw* &
#if REALCASE == 1
size_of_PRECISION_real, &
#endif
#if COMPLEXCASE == 1
size_of_PRECISION_complex, &
#endif
cudaMemcpyHostToDevice)
if (.not.(successCUDA)) then
print *,"trans_ev_band_to_full_&
&MATH_DATATYPE&
&: error in cudaMemcpy"
stop
endif
!
!
it should be possible to keep tmat on the device and not copy it aroud
!
!
! copy to device, maybe this can be avoided tmat is input from bandred_real
!
!
successCUDA = cuda_memcpy(tmat_dev, loc(tmat(1,1,istep)), nbw*nbw* &
!
#if REALCASE == 1
!
size_of_PRECISION_real, &
!
#endif
!
#if COMPLEXCASE == 1
!
size_of_PRECISION_complex, &
!
#endif
!
cudaMemcpyHostToDevice)
!
!
if (.not.(successCUDA)) then
!
print *,"trans_ev_band_to_full_&
!
&MATH_DATATYPE&
!
&: error in cudaMemcpy"
!
stop
!
endif
!#endif /* WITH_MPI */
call timer%start("cublas")
...
...
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