[PATCH] libstdc++: Correct NTTP and simd_mask ctor call

[Matthias Kretz via Gcc-patches]

OK for master and all backports (after 11.4 is done)?

tested on powerpc64le-linux-gnu and x86_64-pc-linux-gnu

----------- 8< ------------

Signed-off-by: Matthias Kretz <m.kr...@gsi.de>

libstdc++-v3/ChangeLog:

        PR libstdc++/109822
        * include/experimental/bits/simd.h (to_native): Use int NTTP
        as specified in PTS2.
        (to_compatible): Likewise. Add missing tag to call mask
        generator ctor.
        * testsuite/experimental/simd/pr109822_cast_functions.cc: New
        test.
---
 libstdc++-v3/include/experimental/bits/simd.h |  7 ++-
 .../simd/pr109822_cast_functions.cc           | 63 +++++++++++++++++++
 2 files changed, 67 insertions(+), 3 deletions(-)
 create mode 100644 libstdc++-v3/testsuite/experimental/simd/
pr109822_cast_functions.cc


--
──────────────────────────────────────────────────────────────────────────
 Dr. Matthias Kretz                           https://mattkretz.github.io
 GSI Helmholtz Centre for Heavy Ion Research               https://gsi.de
 stdₓ::simd
──────────────────────────────────────────────────────────────────────────
diff --git a/libstdc++-v3/include/experimental/bits/simd.h b/libstdc++-v3/include/experimental/bits/simd.h
index 26f08f83ab0..f94b8361ab0 100644
--- a/libstdc++-v3/include/experimental/bits/simd.h
+++ b/libstdc++-v3/include/experimental/bits/simd.h
@@ -3304,7 +3304,7 @@ to_native(const fixed_size_simd<_Tp, _Np>& __x)
     return {__mem, vector_aligned};
   }
 
-template <typename _Tp, size_t _Np>
+template <typename _Tp, int _Np>
   _GLIBCXX_SIMD_INTRINSIC
   enable_if_t<(_Np == native_simd_mask<_Tp>::size()), native_simd_mask<_Tp>>
   to_native(const fixed_size_simd_mask<_Tp, _Np>& __x)
@@ -3315,7 +3315,7 @@ to_native(const fixed_size_simd_mask<_Tp, _Np>& __x)
   }
 
 // to_compatible {{{2
-template <typename _Tp, size_t _Np>
+template <typename _Tp, int _Np>
   _GLIBCXX_SIMD_INTRINSIC enable_if_t<(_Np == simd<_Tp>::size()), simd<_Tp>>
   to_compatible(const simd<_Tp, simd_abi::fixed_size<_Np>>& __x)
   {
@@ -3324,12 +3324,13 @@ to_compatible(const simd<_Tp, simd_abi::fixed_size<_Np>>& __x)
     return {__mem, vector_aligned};
   }
 
-template <typename _Tp, size_t _Np>
+template <typename _Tp, int _Np>
   _GLIBCXX_SIMD_INTRINSIC
   enable_if_t<(_Np == simd_mask<_Tp>::size()), simd_mask<_Tp>>
   to_compatible(const simd_mask<_Tp, simd_abi::fixed_size<_Np>>& __x)
   {
     return simd_mask<_Tp>(
+	     __private_init,
 	     [&](auto __i) constexpr _GLIBCXX_SIMD_ALWAYS_INLINE_LAMBDA { return __x[__i]; });
   }
 
diff --git a/libstdc++-v3/testsuite/experimental/simd/pr109822_cast_functions.cc b/libstdc++-v3/testsuite/experimental/simd/pr109822_cast_functions.cc
new file mode 100644
index 00000000000..3deafbf7a1f
--- /dev/null
+++ b/libstdc++-v3/testsuite/experimental/simd/pr109822_cast_functions.cc
@@ -0,0 +1,63 @@
+// { dg-options "-std=gnu++17" }
+// { dg-do compile { target c++17 } }
+
+#include <experimental/simd>
+
+namespace stdx = std::experimental;
+
+template <typename T, typename V>
+  void
+  test01()
+  {
+    using M = typename V::mask_type;
+    [[maybe_unused]] auto x = to_fixed_size(V());
+    [[maybe_unused]] auto k = to_fixed_size(M());
+    if constexpr (stdx::simd<T>::size() == V::size())
+      {
+	[[maybe_unused]] auto xx = to_compatible(x);
+	[[maybe_unused]] auto kk = to_compatible(k);
+	x = to_fixed_size(xx);
+	k = to_fixed_size(kk);
+      }
+    if constexpr (stdx::native_simd<T>::size() == V::size())
+      {
+	[[maybe_unused]] auto xx = to_native(x);
+	[[maybe_unused]] auto kk = to_native(k);
+	x = to_fixed_size(xx);
+	k = to_fixed_size(kk);
+      }
+  }
+
+template <typename T>
+  void
+  iterate_abis()
+  {
+    test01<T, stdx::simd<T, stdx::simd_abi::scalar>>();
+    test01<T, stdx::simd<T>>();
+    test01<T, stdx::native_simd<T>>();
+    test01<T, stdx::fixed_size_simd<T, 3>>();
+    test01<T, stdx::fixed_size_simd<T, stdx::simd_abi::max_fixed_size<T> - 4>>();
+  }
+
+int
+main()
+{
+  iterate_abis<char>();
+  iterate_abis<wchar_t>();
+  iterate_abis<char16_t>();
+  iterate_abis<char32_t>();
+
+  iterate_abis<signed char>();
+  iterate_abis<unsigned char>();
+  iterate_abis<short>();
+  iterate_abis<unsigned short>();
+  iterate_abis<int>();
+  iterate_abis<unsigned int>();
+  iterate_abis<long>();
+  iterate_abis<unsigned long>();
+  iterate_abis<long long>();
+  iterate_abis<unsigned long long>();
+  iterate_abis<float>();
+  iterate_abis<double>();
+  iterate_abis<long double>();
+}