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
3b218e91
Commit
3b218e91
authored
Sep 06, 2016
by
Andreas Marek
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
SIngle precision complex block1 AVX-512 kernel
parent
50d4667f
Changes
3
Pipelines
1
Expand all
Hide whitespace changes
Inline
Side-by-side
Showing
3 changed files
with
327 additions
and
440 deletions
+327
-440
Makefile.am
Makefile.am
+3
-3
src/elpa2_kernels/elpa2_kernels_complex_avx512_1hv_single_precision.c
...rnels/elpa2_kernels_complex_avx512_1hv_single_precision.c
+303
-416
src/mod_compute_hh_trafo_complex.F90
src/mod_compute_hh_trafo_complex.F90
+21
-21
No files found.
Makefile.am
View file @
3b218e91
...
@@ -237,9 +237,9 @@ endif
...
@@ -237,9 +237,9 @@ endif
if
WITH_COMPLEX_AVX512_BLOCK1_KERNEL
if
WITH_COMPLEX_AVX512_BLOCK1_KERNEL
libelpa@SUFFIX@
_private_la_SOURCES
+=
src/elpa2_kernels/elpa2_kernels_complex_avx512_1hv_double_precision.c
libelpa@SUFFIX@
_private_la_SOURCES
+=
src/elpa2_kernels/elpa2_kernels_complex_avx512_1hv_double_precision.c
#
if WANT_SINGLE_PRECISION_COMPLEX
if
WANT_SINGLE_PRECISION_COMPLEX
#
libelpa@SUFFIX@_private_la_SOURCES += src/elpa2_kernels/elpa2_kernels_complex_avx512_1hv_single_precision.c
libelpa@SUFFIX@
_private_la_SOURCES
+=
src/elpa2_kernels/elpa2_kernels_complex_avx512_1hv_single_precision.c
#
endif
endif
endif
endif
if
WITH_COMPLEX_SSE_BLOCK2_KERNEL
if
WITH_COMPLEX_SSE_BLOCK2_KERNEL
...
...
src/elpa2_kernels/elpa2_kernels_complex_avx512_1hv_single_precision.c
View file @
3b218e91
This diff is collapsed.
Click to expand it.
src/mod_compute_hh_trafo_complex.F90
View file @
3b218e91
...
@@ -739,27 +739,27 @@ module compute_hh_trafo_complex
...
@@ -739,27 +739,27 @@ module compute_hh_trafo_complex
#endif /* WITH_NO_SPECIFIC_COMPLEX_KERNEL */
#endif /* WITH_NO_SPECIFIC_COMPLEX_KERNEL */
#endif /* WITH_COMPLEX_AVX_BLOCK1_KERNEL || WITH_COMPLEX_AVX_BLOCK1_KERNEL */
#endif /* WITH_COMPLEX_AVX_BLOCK1_KERNEL || WITH_COMPLEX_AVX_BLOCK1_KERNEL */
!
#if defined(WITH_COMPLEX_AVX512_BLOCK1_KERNEL)
#if defined(WITH_COMPLEX_AVX512_BLOCK1_KERNEL)
!
#if defined(WITH_NO_SPECIFIC_COMPLEX_KERNEL)
#if defined(WITH_NO_SPECIFIC_COMPLEX_KERNEL)
!
if ( (THIS_COMPLEX_ELPA_KERNEL .eq. COMPLEX_ELPA_KERNEL_AVX512_BLOCK1)) then
if
(
(
THIS_COMPLEX_ELPA_KERNEL
.eq.
COMPLEX_ELPA_KERNEL_AVX512_BLOCK1
))
then
!
#endif /* WITH_NO_SPECIFIC_COMPLEX_KERNEL */
#endif /* WITH_NO_SPECIFIC_COMPLEX_KERNEL */
!
ttt = mpi_wtime()
ttt
=
mpi_wtime
()
!
#if defined(WITH_NO_SPECIFIC_COMPLEX_KERNEL) || (defined(WITH_ONE_SPECIFIC_COMPLEX_KERNEL) && !defined(WITH_COMPLEX_AVX512_BLOCK2_KERNEL) )
#if defined(WITH_NO_SPECIFIC_COMPLEX_KERNEL) || (defined(WITH_ONE_SPECIFIC_COMPLEX_KERNEL) && !defined(WITH_COMPLEX_AVX512_BLOCK2_KERNEL) )
!
do j = ncols, 1, -1
do
j
=
ncols
,
1
,
-1
!
#ifdef WITH_OPENMP
#ifdef WITH_OPENMP
!
call single_hh_trafo_complex_avx512_1hv_single(a(1,j+off+a_off,istripe,my_thread), &
call
single_hh_trafo_complex_avx512_1hv_single
(
a
(
1
,
j
+
off
+
a_off
,
istripe
,
my_thread
),
&
!
bcast_buffer(1,j+off),nbw,nl,stripe_width)
bcast_buffer
(
1
,
j
+
off
),
nbw
,
nl
,
stripe_width
)
!
#else
#else
!
call single_hh_trafo_complex_avx512_1hv_single(a(1,j+off+a_off,istripe), &
call
single_hh_trafo_complex_avx512_1hv_single
(
a
(
1
,
j
+
off
+
a_off
,
istripe
),
&
!
bcast_buffer(1,j+off),nbw,nl,stripe_width)
bcast_buffer
(
1
,
j
+
off
),
nbw
,
nl
,
stripe_width
)
!
#endif
#endif
!
enddo
enddo
!
#endif /* defined(WITH_NO_SPECIFIC_COMPLEX_KERNEL) || (defined(WITH_ONE_SPECIFIC_COMPLEX_KERNEL) && !defined(WITH_COMPLEX_AVX512_BLOCK2_KERNEL) ) */
#endif /* defined(WITH_NO_SPECIFIC_COMPLEX_KERNEL) || (defined(WITH_ONE_SPECIFIC_COMPLEX_KERNEL) && !defined(WITH_COMPLEX_AVX512_BLOCK2_KERNEL) ) */
!
!
#if defined(WITH_NO_SPECIFIC_COMPLEX_KERNEL)
#if defined(WITH_NO_SPECIFIC_COMPLEX_KERNEL)
!
endif ! ( (THIS_COMPLEX_ELPA_KERNEL .eq. COMPLEX_ELPA_KERNEL_AVX512_BLOCK1))
endif
! ( (THIS_COMPLEX_ELPA_KERNEL .eq. COMPLEX_ELPA_KERNEL_AVX512_BLOCK1))
!
#endif /* WITH_NO_SPECIFIC_COMPLEX_KERNEL */
#endif /* WITH_NO_SPECIFIC_COMPLEX_KERNEL */
!
#endif /* WITH_COMPLEX_AVX512_BLOCK1_KERNEL */
#endif /* WITH_COMPLEX_AVX512_BLOCK1_KERNEL */
#ifdef WITH_OPENMP
#ifdef WITH_OPENMP
if
(
my_thread
==
1
)
then
if
(
my_thread
==
1
)
then
...
...
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