From: Matthias Kretz <m.kretz@gsi.de>
Date: Fri, 2 Jun 2023 19:33:04 +0000 (+0200)
Subject: libstdc++: Avoid vector casts while still avoiding PR90424
X-Git-Tag: releases/gcc-11.5.0~156
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=4190a95cb837c5d221d9c5677f49f3c7d4d5576f;p=thirdparty%2Fgcc.git

libstdc++: Avoid vector casts while still avoiding PR90424

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

libstdc++-v3/ChangeLog:

	PR libstdc++/109822
	* include/experimental/bits/simd_builtin.h (_S_store): Rewrite
	to avoid casts to other vector types. Implement store as
	succession of power-of-2 sized memcpy to avoid PR90424.

(cherry picked from commit 9165ede56ababd6471e7a2ce4eab30f3d5129e14)
---

diff --git a/libstdc++-v3/include/experimental/bits/simd_builtin.h b/libstdc++-v3/include/experimental/bits/simd_builtin.h
index 9cdef60b85b2..9c8094d70167 100644
--- a/libstdc++-v3/include/experimental/bits/simd_builtin.h
+++ b/libstdc++-v3/include/experimental/bits/simd_builtin.h
@@ -1291,6 +1291,18 @@ struct _CommonImplBuiltin
 
   // }}}
   // _S_store {{{
+  template <size_t _Bytes>
+    _GLIBCXX_SIMD_INTRINSIC static void
+    _S_memcpy(char* __dst, const char* __src)
+    {
+      if constexpr (_Bytes > 0)
+	{
+	  constexpr size_t _Ns = std::__bit_floor(_Bytes);
+	  __builtin_memcpy(__dst, __src, _Ns);
+	  _S_memcpy<_Bytes - _Ns>(__dst + _Ns, __src + _Ns);
+	}
+    }
+
   template <size_t _ReqBytes = 0, typename _TV>
     _GLIBCXX_SIMD_INTRINSIC static void
     _S_store(_TV __x, void* __addr)
@@ -1298,33 +1310,11 @@ struct _CommonImplBuiltin
       constexpr size_t _Bytes = _ReqBytes == 0 ? sizeof(__x) : _ReqBytes;
       static_assert(sizeof(__x) >= _Bytes);
 
+#if !defined __clang__ && _GLIBCXX_SIMD_WORKAROUND_PR90424
       if constexpr (__is_vector_type_v<_TV>)
-	{
-	  using _Tp = typename _VectorTraits<_TV>::value_type;
-	  constexpr size_t _Np = _Bytes / sizeof(_Tp);
-	  static_assert(_Np * sizeof(_Tp) == _Bytes);
-
-#ifdef _GLIBCXX_SIMD_WORKAROUND_PR90424
-	  using _Up = conditional_t<
-	    (is_integral_v<_Tp> || _Bytes < 4),
-	    conditional_t<(sizeof(__x) > sizeof(long long)), long long, _Tp>,
-	    float>;
-	  const auto __v = __vector_bitcast<_Up>(__x);
-#else // _GLIBCXX_SIMD_WORKAROUND_PR90424
-	  const __vector_type_t<_Tp, _Np> __v = __x;
-#endif // _GLIBCXX_SIMD_WORKAROUND_PR90424
-
-	  if constexpr ((_Bytes & (_Bytes - 1)) != 0)
-	    {
-	      constexpr size_t _MoreBytes = std::__bit_ceil(_Bytes);
-	      alignas(decltype(__v)) char __tmp[_MoreBytes];
-	      __builtin_memcpy(__tmp, &__v, _MoreBytes);
-	      __builtin_memcpy(__addr, __tmp, _Bytes);
-	    }
-	  else
-	    __builtin_memcpy(__addr, &__v, _Bytes);
-	}
+	_S_memcpy<_Bytes>(reinterpret_cast<char*>(__addr), reinterpret_cast<const char*>(&__x));
       else
+#endif // _GLIBCXX_SIMD_WORKAROUND_PR90424
 	__builtin_memcpy(__addr, &__x, _Bytes);
     }