Commit 4b618c06 authored by Andreas Marek's avatar Andreas Marek

Unify complex AVX block1 kernel

parent 53eb97d4
......@@ -893,8 +893,6 @@ EXCLUDE = @top_srcdir@/src/GPU/check_for_gpu.F90 \
@top_srcdir@/src/elpa2/elpa2_trans_ev_band_to_full_template.F90 \
@top_srcdir@/src/elpa2/elpa2_trans_ev_tridi_to_band_template.F90 \
@top_srcdir@/src/elpa2/kernels/simple_template.F90 \
@top_srcdir@/src/elpa2/kernels/complex_avx-avx2_1hv_template.c \
@top_srcdir@/src/elpa2/kernels/complex_avx-avx2_2hv_template.c \
@top_srcdir@/src/elpa2/kernels/real_template.F90 \
@top_srcdir@/src/elpa2/kernels/complex_sse_1hv_single_precision.c \
@top_srcdir@/src/elpa2/kernels/real_avx-avx2_6hv_single_precision.c \
......@@ -937,7 +935,6 @@ EXCLUDE = @top_srcdir@/src/GPU/check_for_gpu.F90 \
@top_srcdir@/src/elpa2/kernels/complex_avx512_2hv_template.c \
@top_srcdir@/src/elpa2/kernels/real_simple.F90 \
@top_srcdir@/src/elpa2/kernels/complex.F90 \
@top_srcdir@/src/elpa2/kernels/real_avx-avx2_2hv_template.c \
@top_srcdir@/src/elpa2/kernels/complex_avx512_1hv_template.c \
@top_srcdir@/src/elpa2/kernels/real_sse_2hv_double_precision.c \
@top_srcdir@/src/elpa2/kernels/real_sparc64_2hv_double_precision.c \
......
......@@ -791,8 +791,6 @@ EXTRA_DIST = \
src/elpa2/elpa2_trans_ev_band_to_full_template.F90 \
src/elpa2/elpa2_trans_ev_tridi_to_band_template.F90 \
src/elpa2/elpa2_tridiag_band_template.F90 \
src/elpa2/kernels/complex_avx-avx2_1hv_template.c \
src/elpa2/kernels/complex_avx-avx2_2hv_template.c \
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 \
......
This source diff could not be displayed because it is too large. You can view the blob instead.
......@@ -48,8 +48,12 @@
#define COMPLEXCASE 1
#define DOUBLE_PRECISION 1
#define BLOCK1 1
#define VEC_SET AVX_256
#include "../../general/precision_macros.h"
#include "complex_avx-avx2_1hv_template.c"
#include "complex_128bit_256bit_512bit_BLOCK_template.c"
#undef BLOCK1
#undef VEC_SET
#undef DOUBLE_PRECISION
#undef COMPLEXCASE
......@@ -48,8 +48,12 @@
#define COMPLEXCASE 1
#define SINGLE_PRECISION 1
#define BLOCK1 1
#define VEC_SET AVX_256
#include "../../general/precision_macros.h"
#include "complex_avx-avx2_1hv_template.c"
#include "complex_128bit_256bit_512bit_BLOCK_template.c"
#undef BLOCK1
#undef VEC_SET
#undef SINGLE_PRECISION
#undef COMPLEXCASE
This diff is collapsed.
......@@ -48,8 +48,12 @@
#define COMPLEXCASE 1
#define DOUBLE_PRECISION 1
#define VEC_SET AVX_256
#define BLOCK2 1
#include "../../general/precision_macros.h"
#include "complex_avx-avx2_2hv_template.c"
#include "complex_128bit_256bit_512bit_BLOCK_template.c"
#undef VEC_SET
#undef BLOCK2
#undef DOUBLE_PRECISION
#undef COMPLEXCASE
......@@ -48,8 +48,13 @@
#define COMPLEXCASE 1
#define SINGLE_PRECISION 1
#define VEC_SET AVX_256
#define BLOCK2 1
#include "../../general/precision_macros.h"
#include "complex_avx-avx2_2hv_template.c"
#include "complex_128bit_256bit_512bit_BLOCK_template.c"
#undef VEC_SET
#undef BLOCK2
#undef SINGLE_PRECISION
#undef COMPLEXCASE
This diff is collapsed.
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment