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
b57f0f88
Commit
b57f0f88
authored
Jun 09, 2019
by
Andreas Marek
Browse files
Only AVX block1 kernel
parent
28a03265
Changes
5
Pipelines
1
Expand all
Hide whitespace changes
Inline
Side-by-side
Makefile.am
View file @
b57f0f88
...
...
@@ -794,6 +794,7 @@ EXTRA_DIST = \
src/elpa2/kernels/complex_avx512_1hv_template.c
\
src/elpa2/kernels/complex_avx512_2hv_template.c
\
src/elpa2/kernels/complex_128bit_256bit_512bit_BLOCK_template.c
\
src/elpa2/kernels/complex_avx-avx2_2hv_template.c
\
src/elpa2/kernels/complex_template.F90
\
src/elpa2/kernels/real_vsx_4hv_template.c
\
src/elpa2/kernels/real_vsx_6hv_template.c
\
...
...
src/elpa2/kernels/complex_128bit_256bit_512bit_BLOCK_template.c
View file @
b57f0f88
...
...
@@ -178,10 +178,9 @@
#define _mm256_FMSUBADD_pd(a,b,c) _mm256_fmsubadd_pd(a,b,c)
#endif
#endif
/* HAVE_AVX2 */
#define _SIMD_FMADDSUB _mm256_FMADDSUB_pd
#define _SIMD_FMSUBADD _mm256_FMSUBADD_pd
#endif
/* HAVE_AVX2 */
#endif
/* DOUBLE_PRECISION_COMPLEX */
...
...
@@ -215,10 +214,9 @@
#define _mm256_FMSUBADD_ps(a,b,c) _mm256_fmsubadd_ps(a,b,c)
#endif
#endif
/* HAVE_AVX2 */
#define _SIMD_FMADDSUB _mm256_FMADDSUB_ps
#define _SIMD_FMSUBADD _mm256_FMSUBADD_ps
#endif
/* HAVE_AVX2 */
#endif
/* SINGLE_PRECISION_COMPLEX */
...
...
@@ -530,36 +528,6 @@ static __forceinline void CONCAT_8ARGS(hh_trafo_complex_kernel_,ROW_LENGTH,_,SIM
!f>#endif
*/
/*
!f>#if defined(HAVE_AVX) || defined(HAVE_AVX2)
!f> interface
!f> subroutine double_hh_trafo_complex_AVX_AVX2_2hv_double(q, hh, pnb, pnq, pldq, pldh) &
!f> bind(C, name="double_hh_trafo_complex_AVX_AVX2_2hv_double")
!f> use, intrinsic :: iso_c_binding
!f> integer(kind=c_int) :: pnb, pnq, pldq, pldh
!f> ! complex(kind=c_double_complex) :: q(*)
!f> type(c_ptr), value :: q
!f> complex(kind=c_double_complex) :: hh(pnb,2)
!f> end subroutine
!f> end interface
!f>#endif
*/
/*
!f>#if defined(HAVE_AVX) || defined(HAVE_AVX2)
!f> interface
!f> subroutine double_hh_trafo_complex_AVX_AVX2_2hv_single(q, hh, pnb, pnq, pldq, pldh) &
!f> bind(C, name="double_hh_trafo_complex_AVX_AVX2_2hv_single")
!f> use, intrinsic :: iso_c_binding
!f> integer(kind=c_int) :: pnb, pnq, pldq, pldh
!f> ! complex(kind=c_float_complex) :: q(*)
!f> type(c_ptr), value :: q
!f> complex(kind=c_float_complex) :: hh(pnb,2)
!f> end subroutine
!f> end interface
!f>#endif
*/
void
CONCAT_7ARGS
(
PREFIX
,
_hh_trafo_complex_
,
SIMD_SET
,
_
,
BLOCK
,
hv_
,
WORD_LENGTH
)
(
DATA_TYPE_PTR
q
,
DATA_TYPE_PTR
hh
,
int
*
pnb
,
int
*
pnq
,
int
*
pldq
#ifdef BLOCK1
)
...
...
src/elpa2/kernels/complex_avx-avx2_2hv_double_precision.c
View file @
b57f0f88
...
...
@@ -51,7 +51,7 @@
#define VEC_SET AVX_256
#define BLOCK2 1
#include
"../../general/precision_macros.h"
#include
"complex_
128bit_256bit_512bit_BLOCK
_template.c"
#include
"complex_
avx-avx2_2hv
_template.c"
#undef VEC_SET
#undef BLOCK2
#undef DOUBLE_PRECISION
...
...
src/elpa2/kernels/complex_avx-avx2_2hv_single_precision.c
View file @
b57f0f88
...
...
@@ -51,7 +51,7 @@
#define VEC_SET AVX_256
#define BLOCK2 1
#include
"../../general/precision_macros.h"
#include
"complex_
128bit_256bit_512bit_BLOCK
_template.c"
#include
"complex_
avx-avx2_2hv
_template.c"
#undef VEC_SET
#undef BLOCK2
#undef SINGLE_PRECISION
...
...
src/elpa2/kernels/complex_avx-avx2_2hv_template.c
0 → 100644
View file @
b57f0f88
This diff is collapsed.
Click to expand it.
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