Commit b6369e22 authored by Andreas Marek's avatar Andreas Marek

Unify 128bit kernels real block2 and block4

parent 9233720a
......@@ -905,7 +905,6 @@ EXCLUDE = @top_srcdir@/src/GPU/check_for_gpu.F90 \
@top_srcdir@/src/elpa2/kernels/complex_avx-avx2_2hv_double_precision.c \
@top_srcdir@/src/elpa2/kernels/real_avx512_2hv_double_precision.c \
@top_srcdir@/src/elpa2/kernels/real_avx512_2hv_single_precision.c \
@top_srcdir@/src/elpa2/kernels/real_sse_4hv_template.c \
@top_srcdir@/src/elpa2/kernels/complex_avx-avx2_2hv_single_precision.c \
@top_srcdir@/src/elpa2/kernels/complex_avx512_1hv_double_precision.c \
@top_srcdir@/src/elpa2/kernels/real_sse_6hv_single_precision.c \
......@@ -913,7 +912,6 @@ EXCLUDE = @top_srcdir@/src/GPU/check_for_gpu.F90 \
@top_srcdir@/src/elpa2/kernels/asm_x86_64_double_precision.s \
@top_srcdir@/src/elpa2/kernels/real_avx512_4hv_double_precision.c \
@top_srcdir@/src/elpa2/kernels/real_sse_6hv_double_precision.c \
@top_srcdir@/src/elpa2/kernels/real_sse_2hv_template.c \
@top_srcdir@/src/elpa2/kernels/complex_avx512_1hv_single_precision.c \
@top_srcdir@/src/elpa2/kernels/asm_x86_64_single_precision.s \
@top_srcdir@/src/elpa2/kernels/real_avx512_6hv_template.c \
......
......@@ -784,8 +784,7 @@ EXTRA_DIST = \
src/elpa2/kernels/real_vsx_2hv_template.c \
src/elpa2/kernels/real_vsx_4hv_template.c \
src/elpa2/kernels/real_vsx_6hv_template.c \
src/elpa2/kernels/real_sse_2hv_template.c \
src/elpa2/kernels/real_sse_4hv_template.c \
src/elpa2/kernels/real_128bit_BLOCK_template.c \
src/elpa2/kernels/real_sse_6hv_template.c \
src/elpa2/kernels/real_template.F90 \
src/elpa2/kernels/simple_template.F90 \
......
This diff is collapsed.
......@@ -48,8 +48,10 @@
#define REALCASE 1
#define DOUBLE_PRECISION 1
#define BLOCK2
#include "../../general/precision_macros.h"
#include "real_sse_2hv_template.c"
#include "real_128bit_BLOCK_template.c"
#undef REALCASE
#undef BLOCK2
#undef DOUBLE_PRECISION
......@@ -48,8 +48,10 @@
#define REALCASE 1
#define SINGLE_PRECISION 1
#define BLOCK2
#include "../../general/precision_macros.h"
#include "real_sse_2hv_template.c"
#include "real_128bit_BLOCK_template.c"
#undef BLOCK2
#undef REALCASE
#undef SINGLE_PRECISION
......@@ -48,8 +48,10 @@
#define REALCASE 1
#define DOUBLE_PRECISION 1
#define BLOCK4 1
#include "../../general/precision_macros.h"
#include "real_sse_4hv_template.c"
#include "real_128bit_BLOCK_template.c"
#undef BLOCK4
#undef REALCASE
#undef DOUBLE_PRECISION
......@@ -48,8 +48,10 @@
#define REALCASE 1
#define SINGLE_PRECISION 1
#define BLOCK4
#include "../../general/precision_macros.h"
#include "real_sse_4hv_template.c"
#include "real_128bit_BLOCK_template.c"
#undef BLOCK4
#undef REALCASE
#undef SINGLE_PRECISION
......@@ -48,8 +48,10 @@
#define REALCASE 1
#define DOUBLE_PRECISION 1
#define BLOCK2 1
#include "../../general/precision_macros.h"
#include "real_sse_2hv_template.c"
#include "real_128bit_BLOCK_template.c"
#undef BLOCK2
#undef REALCASE
#undef DOUBLE_PRECISION
......@@ -48,8 +48,10 @@
#define REALCASE 1
#define SINGLE_PRECISION 1
#define BLOCK2 1
#include "../../general/precision_macros.h"
#include "real_sse_2hv_template.c"
#include "real_128bit_BLOCK_template.c"
#undef BLOCK2
#undef REALCASE
#undef SINGLE_PRECISION
This diff is collapsed.
......@@ -48,8 +48,10 @@
#define REALCASE 1
#define DOUBLE_PRECISION 1
#define BLOCK4 1
#include "../../general/precision_macros.h"
#include "real_sse_4hv_template.c"
#include "real_128bit_BLOCK_template.c"
#undef BLOCK4
#undef REALCASE
#undef DOUBLE_PRECISION
......@@ -48,8 +48,10 @@
#define REALCASE 1
#define SINGLE_PRECISION 1
#define BLOCK4 1
#include "../../general/precision_macros.h"
#include "real_sse_4hv_template.c"
#include "real_128bit_BLOCK_template.c"
#undef BLOCK4
#undef REALCASE
#undef SINGLE_PRECISION
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