[committed] libstdc++: Fix simd compilation with Clang

[Matthias Kretz <m.kretz@gsi.de>]

[-- Attachment #1: Type: text/plain, Size: 1879 bytes --]

Slightly modified patch. I had to fix floating-point AVX512 blending on 
Clang by removing a cast. While at it I cleaned up the -Wundef noise.

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

Clang fails to compile some constant expressions involving simd.
Therefore, just disable this non-conforming extension for clang.

Fix AVX512 blend implementation for Clang. It was converting the bitmask
to bool before, which is obviously wrong. Instead use a Clang builtin to
convert the bitmask to vector-mask before using a vector blend ?:. A
similar change is required for the masked unary implementation, because
the GCC builtins do not exist on Clang.

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

libstdc++-v3/ChangeLog:

	* include/experimental/bits/simd_detail.h: Don't declare the
	simd API as constexpr with Clang.
	* include/experimental/bits/simd_x86.h (__movm): New.
	(_S_blend_avx512): Resolve FIXME. Implement blend using __movm
	and ?:.
	(_SimdImplX86::_S_masked_unary): Clang does not implement the
	same builtins. Implement the function using __movm, ?:, and -
	operators on vector_size types instead.
---
 .../include/experimental/bits/simd_detail.h   |  2 +-
 .../include/experimental/bits/simd_x86.h      | 58 +++++++++++++++++--
 2 files changed, 55 insertions(+), 5 deletions(-)


--
──────────────────────────────────────────────────────────────────────────
 Dr. Matthias Kretz                           https://mattkretz.github.io
 GSI Helmholtz Centre for Heavy Ion Research               https://gsi.de
 stdₓ::simd
──────────────────────────────────────────────────────────────────────────

[-- Attachment #2: 0001-libstdc-Fix-simd-compilation-with-Clang.patch --]
[-- Type: text/x-patch, Size: 4021 bytes --]

diff --git a/libstdc++-v3/include/experimental/bits/simd_detail.h b/libstdc++-v3/include/experimental/bits/simd_detail.h
index 30cc1ef0eef..49b94decf0a 100644
--- a/libstdc++-v3/include/experimental/bits/simd_detail.h
+++ b/libstdc++-v3/include/experimental/bits/simd_detail.h
@@ -267,7 +267,7 @@ namespace experimental
 #define _GLIBCXX_SIMD_IS_UNLIKELY(__x) __builtin_expect(__x, 0)
 #define _GLIBCXX_SIMD_IS_LIKELY(__x) __builtin_expect(__x, 1)
 
-#if defined __STRICT_ANSI__ && __STRICT_ANSI__
+#if __STRICT_ANSI__ || defined __clang__
 #define _GLIBCXX_SIMD_CONSTEXPR
 #define _GLIBCXX_SIMD_USE_CONSTEXPR_API const
 #else
diff --git a/libstdc++-v3/include/experimental/bits/simd_x86.h b/libstdc++-v3/include/experimental/bits/simd_x86.h
index 608918542c6..7b8f1c664b3 100644
--- a/libstdc++-v3/include/experimental/bits/simd_x86.h
+++ b/libstdc++-v3/include/experimental/bits/simd_x86.h
@@ -363,6 +363,53 @@ __maskload_pd(const double* __ptr, _Tp __k)
 
 // }}}
 
+#ifdef __clang__
+template <size_t _Np, typename _Tp, typename _Kp>
+  _GLIBCXX_SIMD_INTRINSIC constexpr auto
+  __movm(_Kp __k) noexcept
+  {
+    static_assert(is_unsigned_v<_Kp>);
+    if constexpr (sizeof(_Tp) == 1 && __have_avx512bw)
+      {
+	if constexpr (_Np <= 16 && __have_avx512vl)
+	  return __builtin_ia32_cvtmask2b128(__k);
+	else if constexpr (_Np <= 32 && __have_avx512vl)
+	  return __builtin_ia32_cvtmask2b256(__k);
+	else
+	  return __builtin_ia32_cvtmask2b512(__k);
+      }
+    else if constexpr (sizeof(_Tp) == 2 && __have_avx512bw)
+      {
+	if constexpr (_Np <= 8 && __have_avx512vl)
+	  return __builtin_ia32_cvtmask2w128(__k);
+	else if constexpr (_Np <= 16 && __have_avx512vl)
+	  return __builtin_ia32_cvtmask2w256(__k);
+	else
+	  return __builtin_ia32_cvtmask2w512(__k);
+      }
+    else if constexpr (sizeof(_Tp) == 4 && __have_avx512dq)
+      {
+	if constexpr (_Np <= 4 && __have_avx512vl)
+	  return __builtin_ia32_cvtmask2d128(__k);
+	else if constexpr (_Np <= 8 && __have_avx512vl)
+	  return __builtin_ia32_cvtmask2d256(__k);
+	else
+	  return __builtin_ia32_cvtmask2d512(__k);
+      }
+    else if constexpr (sizeof(_Tp) == 8 && __have_avx512dq)
+      {
+	if constexpr (_Np <= 2 && __have_avx512vl)
+	  return __builtin_ia32_cvtmask2q128(__k);
+	else if constexpr (_Np <= 4 && __have_avx512vl)
+	  return __builtin_ia32_cvtmask2q256(__k);
+	else
+	  return __builtin_ia32_cvtmask2q512(__k);
+      }
+    else
+      __assert_unreachable<_Tp>();
+  }
+#endif // __clang__
+
 #ifdef _GLIBCXX_SIMD_WORKAROUND_PR85048
 #include "simd_x86_conversions.h"
 #endif
@@ -619,14 +666,13 @@ _pdep_u32(
     _GLIBCXX_SIMD_INTRINSIC static _TV
     _S_blend_avx512(const _Kp __k, const _TV __a, const _TV __b) noexcept
     {
-#ifdef __clang__
-      // FIXME: this does a boolean choice, not a blend
-      return __k ? __a : __b;
-#else
       static_assert(__is_vector_type_v<_TV>);
       using _Tp = typename _VectorTraits<_TV>::value_type;
       static_assert(sizeof(_TV) >= 16);
       static_assert(sizeof(_Tp) <= 8);
+#ifdef __clang__
+      return __movm<_VectorTraits<_TV>::_S_full_size, _Tp>(__k) ? __b : __a;
+#else
       using _IntT
 	= conditional_t<(sizeof(_Tp) > 2),
 			conditional_t<sizeof(_Tp) == 4, int, long long>,
@@ -3483,6 +3529,9 @@ _S_masked_unary(const _SimdWrapper<_K, _Np> __k, const _SimdWrapper<_Tp, _Np> __
 	    // optimize masked unary increment and decrement as masked sub +/-1
 	    constexpr int __pm_one
 	      = is_same_v<_Op<void>, __increment<void>> ? -1 : 1;
+#ifdef __clang__
+	    return __movm<_Np, _Tp>(__k._M_data) ? __v._M_data - __pm_one : __v._M_data;
+#else // __clang__
 	    if constexpr (is_integral_v<_Tp>)
 	      {
 		constexpr bool __lp64 = sizeof(long) == sizeof(long long);
@@ -3526,6 +3575,7 @@ _S_masked_unary(const _SimdWrapper<_K, _Np> __k, const _SimdWrapper<_Tp, _Np> __
 		_GLIBCXX_SIMD_MASK_SUB(8, 16, subpd128);
 #undef _GLIBCXX_SIMD_MASK_SUB
 	      }
+#endif // __clang__
 	  }
 	else
 	  return _Base::template _S_masked_unary<_Op>(__k, __v);