Commit ba9967d6 authored by Andreas Marek's avatar Andreas Marek

Also put 256bit 4hv kernel in unfied file

parent 135e3732
......@@ -939,7 +939,6 @@ EXCLUDE = @top_srcdir@/src/GPU/check_for_gpu.F90 \
@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/complex_sse_2hv_double_precision.c \
@top_srcdir@/src/elpa2/kernels/real_avx-avx2_4hv_template.c \
@top_srcdir@/src/elpa2/kernels/real_bgp.f90 \
@top_srcdir@/src/elpa2/kernels/real_sse_4hv_double_precision.c \
@top_srcdir@/src/elpa2/kernels/real_avx512_6hv_double_precision.c \
......
......@@ -775,7 +775,6 @@ EXTRA_DIST = \
src/elpa2/kernels/complex_sse_1hv_template.c \
src/elpa2/kernels/complex_sse_2hv_template.c \
src/elpa2/kernels/complex_template.F90 \
src/elpa2/kernels/real_avx-avx2_4hv_template.c \
src/elpa2/kernels/real_avx-avx2_6hv_template.c \
src/elpa2/kernels/real_avx512_2hv_template.c \
src/elpa2/kernels/real_avx512_4hv_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 REALCASE 1
#define DOUBLE_PRECISION 1
#define BLOCK4 1
#define VEC_SET 256
#include "../../general/precision_macros.h"
#include "real_avx-avx2_4hv_template.c"
#include "real_128bit_BLOCK_template.c"
#undef BLOCK4
#undef VEC_SET
#undef REALCASE
#undef DOUBLE_PRECISION
......@@ -48,8 +48,12 @@
#define REALCASE 1
#define SINGLE_PRECISION 1
#define BLOCK4
#define VEC_SET 256
#include "../../general/precision_macros.h"
#include "real_avx-avx2_4hv_template.c"
#include "real_128bit_BLOCK_template.c"
#undef BLOCK4
#undef VEC_SET
#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