GCN, nvptx libstdc++: Force use of '__atomic' builtins [PR119645]

For both GCN, nvptx, this gets rid of 'configure'-time:

    configure: WARNING: No native atomic operations are provided for this platform.
    configure: WARNING: They will be faked using a mutex.
    configure: WARNING: Performance of certain classes will degrade as a result.

..., and changes:

    -checking for lock policy for shared_ptr reference counts... mutex
    +checking for lock policy for shared_ptr reference counts... atomic

That means, '[...]/[target]/libstdc++-v3/', 'Makefile's change:

    -ATOMICITY_SRCDIR = config/cpu/generic/atomicity_mutex
    +ATOMICITY_SRCDIR = config/cpu/generic/atomicity_builtins

..., and '[...]/[target]/libstdc++-v3/config.h' changes:

    /* Defined if shared_ptr reference counting should use atomic operations. */
    -/* #undef HAVE_ATOMIC_LOCK_POLICY */
    +#define HAVE_ATOMIC_LOCK_POLICY 1

    /* Define if the compiler supports C++11 atomics. */
    -/* #undef _GLIBCXX_ATOMIC_BUILTINS */
    +#define _GLIBCXX_ATOMIC_BUILTINS 1

..., and '[...]/[target]/libstdc++-v3/include/[target]/bits/c++config.h'
changes:

    /* Defined if shared_ptr reference counting should use atomic operations. */
    -/* #undef _GLIBCXX_HAVE_ATOMIC_LOCK_POLICY */
    +#define _GLIBCXX_HAVE_ATOMIC_LOCK_POLICY 1

    /* Define if the compiler supports C++11 atomics. */
    -/* #undef _GLIBCXX_ATOMIC_BUILTINS */
    +#define _GLIBCXX_ATOMIC_BUILTINS 1

This means that '[...]/[target]/libstdc++-v3/libsupc++/atomicity.cc',
'[...]/[target]/libstdc++-v3/libsupc++/atomicity.o' then uses atomic
instructions for synchronization instead of C++ static local variables, which
in turn for their guard variables, via 'libstdc++-v3/libsupc++/guard.cc', used
'libgcc/gthr.h' recursive mutexes, which currently are unsupported for GCN.

For GCN, this turns ~500 libstdc++ execution test FAILs into PASSes, and also
progresses:

    PASS: g++.dg/tree-ssa/pr20458.C  -std=gnu++17 (test for excess errors)
    [-FAIL:-]{+PASS:+} g++.dg/tree-ssa/pr20458.C  -std=gnu++17 execution test
    PASS: g++.dg/tree-ssa/pr20458.C  -std=gnu++26 (test for excess errors)
    [-FAIL:-]{+PASS:+} g++.dg/tree-ssa/pr20458.C  -std=gnu++26 execution test
    UNSUPPORTED: g++.dg/tree-ssa/pr20458.C  -std=gnu++98: exception handling not supported

(For nvptx, there is no effective change, due to other misconfiguration.)

	PR target/119645
	libstdc++-v3/
	* acinclude.m4 (GLIBCXX_ENABLE_LOCK_POLICY) [GCN, nvptx]:
	Hard-code results.
	* configure: Regenerate.
	* configure.host [GCN, nvptx] (atomicity_dir): Set to
	'cpu/generic/atomicity_builtins'.

3 files changed, 21 insertions, 8 deletions

diff --git a/libstdc++-v3/acinclude.m4 b/libstdc++-v3/acinclude.m4
index 02fd349e..a0094c2 100644
--- a/libstdc++-v3/acinclude.m4
+++ b/libstdc++-v3/acinclude.m4
@@ -4023,10 +4023,11 @@ AC_DEFUN([GLIBCXX_ENABLE_LOCK_POLICY], [
     dnl Why don't we check 8-byte CAS for sparc64, where _Atomic_word is long?!
     dnl New targets should only check for CAS for the _Atomic_word type.
     AC_TRY_COMPILE([
-    #if defined __riscv
+    #if defined __AMDGCN__ || defined __nvptx__
+    /* Yes, please.  */
+    #elif defined __riscv
     # error "Defaulting to mutex-based locks for ABI compatibility"
-    #endif
-    #if ! defined __GCC_HAVE_SYNC_COMPARE_AND_SWAP_2
+    #elif ! defined __GCC_HAVE_SYNC_COMPARE_AND_SWAP_2
     # error "No 2-byte compare-and-swap"
     #elif ! defined __GCC_HAVE_SYNC_COMPARE_AND_SWAP_4
     # error "No 4-byte compare-and-swap"
diff --git a/libstdc++-v3/configure b/libstdc++-v3/configure
index 56d0bcb..819a1d82 100755
--- a/libstdc++-v3/configure
+++ b/libstdc++-v3/configure
@@ -16394,10 +16394,11 @@ ac_compiler_gnu=$ac_cv_cxx_compiler_gnu
                 cat confdefs.h - <<_ACEOF >conftest.$ac_ext
 /* end confdefs.h.  */
 
-    #if defined __riscv
+    #if defined __AMDGCN__ || defined __nvptx__
+    /* Yes, please.  */
+    #elif defined __riscv
     # error "Defaulting to mutex-based locks for ABI compatibility"
-    #endif
-    #if ! defined __GCC_HAVE_SYNC_COMPARE_AND_SWAP_2
+    #elif ! defined __GCC_HAVE_SYNC_COMPARE_AND_SWAP_2
     # error "No 2-byte compare-and-swap"
     #elif ! defined __GCC_HAVE_SYNC_COMPARE_AND_SWAP_4
     # error "No 4-byte compare-and-swap"
@@ -16444,7 +16445,7 @@ $as_echo "mutex" >&6; }
   # unnecessary for this test.
 
     cat > conftest.$ac_ext << EOF
-#line 16447 "configure"
+#line 16448 "configure"
 int main()
 {
   _Decimal32 d1;
@@ -16486,7 +16487,7 @@ ac_compiler_gnu=$ac_cv_cxx_compiler_gnu
   # unnecessary for this test.
 
   cat > conftest.$ac_ext << EOF
-#line 16489 "configure"
+#line 16490 "configure"
 template<typename T1, typename T2>
   struct same
   { typedef T2 type; };
diff --git a/libstdc++-v3/configure.host b/libstdc++-v3/configure.host
index 8375764..253e5a9 100644
--- a/libstdc++-v3/configure.host
+++ b/libstdc++-v3/configure.host
@@ -370,10 +370,21 @@ case "${host}" in
 	;;
     esac
     ;;
+  amdgcn-*-amdhsa)
+    # To avoid greater pain elsewhere, force use of '__atomic' builtins,
+    # regardless of the outcome of 'configure' checks; see PR119645
+    # "GCN, nvptx: libstdc++ 'checking for atomic builtins [...]... no'".
+    atomicity_dir=cpu/generic/atomicity_builtins
+    ;;
   arm*-*-freebsd*)
      port_specific_symbol_files="\$(srcdir)/../config/os/gnu-linux/arm-eabi-extra.ver"
      ;;
   nvptx-*-none)
+    # To avoid greater pain elsewhere, force use of '__atomic' builtins,
+    # regardless of the outcome of 'configure' checks; see PR119645
+    # "GCN, nvptx: libstdc++ 'checking for atomic builtins [...]... no'".
+    atomicity_dir=cpu/generic/atomicity_builtins
+
     # For 'make all-target-libstdc++-v3', re 'alloca'/VLA usage:
     EXTRA_CFLAGS="${EXTRA_CFLAGS} -mfake-ptx-alloca"
     OPTIMIZE_CXXFLAGS="${OPTIMIZE_CXXFLAGS} -mfake-ptx-alloca"