gcc/0020-simdmath-Enable-simdmath-on-kunpeng.patch

From 49ad10199dbdda2c36850a2617f5c985977939c5 Mon Sep 17 00:00:00 2001
From: bule <bule1@huawei.com>
Date: Sun, 27 Aug 2023 16:49:42 +0800
Subject: [PATCH 20/22] [simdmath] Enable simdmath on kunpeng

This enable simd math function supported by libmathlib on fortran/c/c++.
Use -fsimdmath to turn on the generation of simdmath function. The
supported functions can be found in simdmath.h. Add more simd declaration
if you need more kinds of math functions. -msimdmath-64 is used to turn
on 64-bit simd math functions which is not supported by libmathlib.
Therefore, this option is default to off.
---
 gcc/c-family/c-opts.cc                        |  4 ++
 gcc/common.opt                                |  4 ++
 gcc/config/aarch64/aarch64.cc                 |  9 ++++-
 gcc/config/aarch64/aarch64.opt                |  6 +++
 gcc/fortran/scanner.cc                        |  3 ++
 gcc/opts.cc                                   | 17 ++++++++
 .../gcc.target/aarch64/simd_pcs_attribute-3.c |  2 +-
 libgomp/Makefile.am                           |  4 +-
 libgomp/Makefile.in                           | 10 +++--
 libgomp/configure                             |  4 +-
 libgomp/configure.ac                          |  2 +-
 libgomp/simdmath.h.in                         | 40 +++++++++++++++++++
 libgomp/simdmath_f.h.in                       | 11 +++++
 13 files changed, 106 insertions(+), 10 deletions(-)
 create mode 100644 libgomp/simdmath.h.in
 create mode 100644 libgomp/simdmath_f.h.in

diff --git a/gcc/c-family/c-opts.cc b/gcc/c-family/c-opts.cc
index a341a0617..5134f6128 100644
--- a/gcc/c-family/c-opts.cc
+++ b/gcc/c-family/c-opts.cc
@@ -801,6 +801,10 @@ c_common_post_options (const char **pfilename)
   if (cpp_opts->deps.style == DEPS_NONE)
     check_deps_environment_vars ();
 
+  if (flag_simdmath)
+    {
+      defer_opt (OPT_include, "simdmath.h");
+    }
   handle_deferred_opts ();
 
   sanitize_cpp_opts ();
diff --git a/gcc/common.opt b/gcc/common.opt
index f5eef8a45..e9d580957 100644
--- a/gcc/common.opt
+++ b/gcc/common.opt
@@ -2125,6 +2125,10 @@ fmath-errno
 Common Var(flag_errno_math) Init(1) Optimization SetByCombined
 Set errno after built-in math functions.
 
+fsimdmath
+Common Var(flag_simdmath) Init(0) Optimization
+Enable auto-vectorize math functions for mathlib.  This option will turn on -fno-math-errno and -fopenmp-simd.
+
 fmax-errors=
 Common Joined RejectNegative UInteger Var(flag_max_errors)
 -fmax-errors=<number>	Maximum number of errors to report.
diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
index 226dc9dff..a3da4ca30 100644
--- a/gcc/config/aarch64/aarch64.cc
+++ b/gcc/config/aarch64/aarch64.cc
@@ -26904,8 +26904,13 @@ aarch64_simd_clone_compute_vecsize_and_simdlen (struct cgraph_node *node,
   elt_bits = GET_MODE_BITSIZE (SCALAR_TYPE_MODE (base_type));
   if (known_eq (clonei->simdlen, 0U))
     {
-      count = 2;
-      vec_bits = (num == 0 ? 64 : 128);
+      /* Currently mathlib or sleef hasn't provide function for V2SF mode
+      simdclone of single precision functions. (e.g._ZCVnN2v_expf)
+      Therefore this mode is disabled by default to avoid link error.
+      Use -msimdmath-64 option to enable this mode.  */
+      count = flag_simdmath_64 ? 2 : 1;
+      vec_bits = ((num == 0 && flag_simdmath_64) ? 64 : 128);
+
       clonei->simdlen = exact_div (vec_bits, elt_bits);
     }
   else
diff --git a/gcc/config/aarch64/aarch64.opt b/gcc/config/aarch64/aarch64.opt
index 92220b26e..a64b927e9 100644
--- a/gcc/config/aarch64/aarch64.opt
+++ b/gcc/config/aarch64/aarch64.opt
@@ -190,6 +190,12 @@ precision of square root results to about 16 bits for
 single precision and to 32 bits for double precision.
 If enabled, it implies -mlow-precision-recip-sqrt.
 
+msimdmath-64
+Target Var(flag_simdmath_64) Optimization
+Allow compiler to generate V2SF 64 bits simdclone of math functions,
+which is not currently supported in mathlib or sleef.
+Therefore this option is disabled by default.
+
 mlow-precision-div
 Target Var(flag_mlow_precision_div) Optimization
 Enable the division approximation.  Enabling this reduces
diff --git a/gcc/fortran/scanner.cc b/gcc/fortran/scanner.cc
index 2dff25147..63e262f51 100644
--- a/gcc/fortran/scanner.cc
+++ b/gcc/fortran/scanner.cc
@@ -2769,6 +2769,9 @@ gfc_new_file (void)
   if (flag_pre_include != NULL)
     load_file (flag_pre_include, NULL, false);
 
+  if (flag_simdmath)
+    load_file ("simdmath_f.h", NULL, false);
+
   if (gfc_cpp_enabled ())
     {
       gfc_cpp_preprocess (gfc_source_file);
diff --git a/gcc/opts.cc b/gcc/opts.cc
index b522ed7e2..c3cc2c169 100644
--- a/gcc/opts.cc
+++ b/gcc/opts.cc
@@ -322,6 +322,7 @@ static const char undocumented_msg[] = N_("This option lacks documentation.");
 static const char use_diagnosed_msg[] = N_("Uses of this option are diagnosed.");
 
 typedef char *char_p; /* For DEF_VEC_P.  */
+static void set_simdmath_flags (struct gcc_options *opts, int set);
 
 static void set_debug_level (uint32_t dinfo, int extended,
 			     const char *arg, struct gcc_options *opts,
@@ -2850,6 +2851,10 @@ common_handle_option (struct gcc_options *opts,
       dc->min_margin_width = value;
       break;
 
+    case OPT_fsimdmath:
+      set_simdmath_flags (opts, value);
+      break;
+
     case OPT_fdump_:
       /* Deferred.  */
       break;
@@ -3227,6 +3232,18 @@ common_handle_option (struct gcc_options *opts,
   return true;
 }
 
+/* The following routines are used to set -fno-math-errno and -fopenmp-simd
+   to enable vector mathlib.  */
+static void
+set_simdmath_flags (struct gcc_options *opts, int set)
+{
+  if (set)
+    {
+      opts->x_flag_errno_math = 0;
+      opts->x_flag_openmp_simd = 1;
+    }
+}
+
 /* Used to set the level of strict aliasing warnings in OPTS,
    when no level is specified (i.e., when -Wstrict-aliasing, and not
    -Wstrict-aliasing=level was given).
diff --git a/gcc/testsuite/gcc.target/aarch64/simd_pcs_attribute-3.c b/gcc/testsuite/gcc.target/aarch64/simd_pcs_attribute-3.c
index 95f6a6803..e0e0efa9d 100644
--- a/gcc/testsuite/gcc.target/aarch64/simd_pcs_attribute-3.c
+++ b/gcc/testsuite/gcc.target/aarch64/simd_pcs_attribute-3.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-Ofast" } */
+/* { dg-options "-Ofast -msimdmath-64" } */
 
 __attribute__ ((__simd__))
 __attribute__ ((__nothrow__ , __leaf__ , __const__))
diff --git a/libgomp/Makefile.am b/libgomp/Makefile.am
index f8b2a06d6..8dfa160d6 100644
--- a/libgomp/Makefile.am
+++ b/libgomp/Makefile.am
@@ -75,10 +75,10 @@ libgomp_la_SOURCES += openacc.f90
 endif
 
 nodist_noinst_HEADERS = libgomp_f.h
-nodist_libsubinclude_HEADERS = omp.h openacc.h acc_prof.h
+nodist_libsubinclude_HEADERS = omp.h openacc.h acc_prof.h simdmath.h
 if USE_FORTRAN
 nodist_finclude_HEADERS = omp_lib.h omp_lib.f90 omp_lib.mod omp_lib_kinds.mod \
-	openacc_lib.h openacc.f90 openacc.mod openacc_kinds.mod
+	openacc_lib.h openacc.f90 openacc.mod openacc_kinds.mod simdmath_f.h
 endif
 
 LTLDFLAGS = $(shell $(SHELL) $(top_srcdir)/../libtool-ldflags $(LDFLAGS))
diff --git a/libgomp/Makefile.in b/libgomp/Makefile.in
index 6f0cb7161..90fc326f0 100644
--- a/libgomp/Makefile.in
+++ b/libgomp/Makefile.in
@@ -147,7 +147,7 @@ am__CONFIG_DISTCLEAN_FILES = config.status config.cache config.log \
  configure.lineno config.status.lineno
 mkinstalldirs = $(SHELL) $(top_srcdir)/../mkinstalldirs
 CONFIG_HEADER = config.h
-CONFIG_CLEAN_FILES = omp.h omp_lib.h omp_lib.f90 libgomp_f.h \
+CONFIG_CLEAN_FILES = omp.h omp_lib.h simdmath.h simdmath_f.h omp_lib.f90 libgomp_f.h \
 	libgomp.spec
 CONFIG_CLEAN_VPATH_FILES =
 am__vpath_adj_setup = srcdirstrip=`echo "$(srcdir)" | sed 's|.|.|g'`;
@@ -583,9 +583,9 @@ libgomp_la_SOURCES = alloc.c atomic.c barrier.c critical.c env.c \
 @PLUGIN_GCN_TRUE@libgomp_plugin_gcn_la_LIBADD = libgomp.la $(PLUGIN_GCN_LIBS)
 @PLUGIN_GCN_TRUE@libgomp_plugin_gcn_la_LIBTOOLFLAGS = --tag=disable-static
 nodist_noinst_HEADERS = libgomp_f.h
-nodist_libsubinclude_HEADERS = omp.h openacc.h acc_prof.h
+nodist_libsubinclude_HEADERS = omp.h openacc.h acc_prof.h simdmath.h
 @USE_FORTRAN_TRUE@nodist_finclude_HEADERS = omp_lib.h omp_lib.f90 omp_lib.mod omp_lib_kinds.mod \
-@USE_FORTRAN_TRUE@	openacc_lib.h openacc.f90 openacc.mod openacc_kinds.mod
+@USE_FORTRAN_TRUE@	openacc_lib.h openacc.f90 openacc.mod openacc_kinds.mod simdmath_f.h
 
 LTLDFLAGS = $(shell $(SHELL) $(top_srcdir)/../libtool-ldflags $(LDFLAGS))
 LINK = $(LIBTOOL) --tag CC $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) --mode=link \
@@ -676,6 +676,10 @@ omp.h: $(top_builddir)/config.status $(srcdir)/omp.h.in
 	cd $(top_builddir) && $(SHELL) ./config.status $@
 omp_lib.h: $(top_builddir)/config.status $(srcdir)/omp_lib.h.in
 	cd $(top_builddir) && $(SHELL) ./config.status $@
+simdmath_f.h: $(top_builddir)/config.status $(srcdir)/simdmath_f.h.in
+	cd $(top_builddir) && $(SHELL) ./config.status $@
+simdmath.h: $(top_builddir)/config.status $(srcdir)/simdmath.h.in
+	cd $(top_builddir) && $(SHELL) ./config.status $@
 omp_lib.f90: $(top_builddir)/config.status $(srcdir)/omp_lib.f90.in
 	cd $(top_builddir) && $(SHELL) ./config.status $@
 libgomp_f.h: $(top_builddir)/config.status $(srcdir)/libgomp_f.h.in
diff --git a/libgomp/configure b/libgomp/configure
index 85fdb4d3f..471c957b7 100755
--- a/libgomp/configure
+++ b/libgomp/configure
@@ -17064,7 +17064,7 @@ fi
 
 
 
-ac_config_files="$ac_config_files omp.h omp_lib.h omp_lib.f90 libgomp_f.h"
+ac_config_files="$ac_config_files omp.h omp_lib.h simdmath.h simdmath_f.h omp_lib.f90 libgomp_f.h"
 
 ac_config_files="$ac_config_files Makefile testsuite/Makefile libgomp.spec"
 
@@ -18215,6 +18215,8 @@ do
     "libtool") CONFIG_COMMANDS="$CONFIG_COMMANDS libtool" ;;
     "omp.h") CONFIG_FILES="$CONFIG_FILES omp.h" ;;
     "omp_lib.h") CONFIG_FILES="$CONFIG_FILES omp_lib.h" ;;
+    "simdmath.h") CONFIG_FILES="$CONFIG_FILES simdmath.h" ;;
+    "simdmath_f.h") CONFIG_FILES="$CONFIG_FILES simdmath_f.h" ;;
     "omp_lib.f90") CONFIG_FILES="$CONFIG_FILES omp_lib.f90" ;;
     "libgomp_f.h") CONFIG_FILES="$CONFIG_FILES libgomp_f.h" ;;
     "Makefile") CONFIG_FILES="$CONFIG_FILES Makefile" ;;
diff --git a/libgomp/configure.ac b/libgomp/configure.ac
index a9b1f3973..1f81a0d30 100644
--- a/libgomp/configure.ac
+++ b/libgomp/configure.ac
@@ -472,7 +472,7 @@ CFLAGS="$save_CFLAGS"
 # Determine what GCC version number to use in filesystem paths.
 GCC_BASE_VER
 
-AC_CONFIG_FILES(omp.h omp_lib.h omp_lib.f90 libgomp_f.h)
+AC_CONFIG_FILES(omp.h omp_lib.h simdmath.h simdmath_f.h omp_lib.f90 libgomp_f.h)
 AC_CONFIG_FILES(Makefile testsuite/Makefile libgomp.spec)
 AC_CONFIG_FILES([testsuite/libgomp-test-support.pt.exp:testsuite/libgomp-test-support.exp.in])
 AC_CONFIG_FILES([testsuite/libgomp-site-extra.exp])
diff --git a/libgomp/simdmath.h.in b/libgomp/simdmath.h.in
new file mode 100644
index 000000000..ab91a4ec3
--- /dev/null
+++ b/libgomp/simdmath.h.in
@@ -0,0 +1,40 @@
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#pragma omp declare simd simdlen(2) notinbranch
+double cos (double x);
+
+#pragma omp declare simd simdlen(4) notinbranch
+float cosf (float x);
+
+#pragma omp declare simd simdlen(2) notinbranch
+double sin (double x);
+
+#pragma omp declare simd simdlen(4) notinbranch
+float sinf (float x);
+
+#pragma omp declare simd simdlen(2) notinbranch
+double exp (double x);
+
+#pragma omp declare simd simdlen(4) notinbranch
+float expf (float x);
+
+#pragma omp declare simd simdlen(2) notinbranch
+double log (double x);
+
+#pragma omp declare simd simdlen(4) notinbranch
+float logf (float x);
+
+#pragma omp declare simd simdlen(2) notinbranch
+double pow (double x, double y);
+
+#pragma omp declare simd simdlen(4) notinbranch
+float powf (float x, float y);
+
+#pragma omp declare simd simdlen(4) notinbranch
+float exp2f (float x);
+
+#ifdef __cplusplus
+} // extern "C"
+#endif
diff --git a/libgomp/simdmath_f.h.in b/libgomp/simdmath_f.h.in
new file mode 100644
index 000000000..550595015
--- /dev/null
+++ b/libgomp/simdmath_f.h.in
@@ -0,0 +1,11 @@
+!GCC$ builtin (cos) attributes simd (notinbranch)
+!GCC$ builtin (cosf) attributes simd (notinbranch)
+!GCC$ builtin (sin) attributes simd (notinbranch)
+!GCC$ builtin (sinf) attributes simd (notinbranch)
+!GCC$ builtin (exp) attributes simd (notinbranch)
+!GCC$ builtin (expf) attributes simd (notinbranch)
+!GCC$ builtin (exp2f) attributes simd (notinbranch)
+!GCC$ builtin (log) attributes simd (notinbranch)
+!GCC$ builtin (logf) attributes simd (notinbranch)
+!GCC$ builtin (pow) attributes simd (notinbranch)
+!GCC$ builtin (powf) attributes simd (notinbranch)
-- 
2.33.0