[PATCH] libstdc++: Replace use of incorrect non-temporal store

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

[-- Attachment #1: Type: text/plain, Size: 1603 bytes --]

OK for master and backports?

Tested on x86_64-pc-linux-gnu

----- >8 -----

The call to the base implementation sometimes didn't find a matching
signature because the _Abi parameter of _SimdImpl* was "wrong" after
conversion. It has to call into <new ABI tag>::_SimdImpl instead of the
current ABI tag's _SimdImpl. This also reduces the number of possible
template instantiations.

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

libstdc++-v3/ChangeLog:

	PR libstdc++/110054
	* include/experimental/bits/simd_builtin.h (_S_masked_store):
	Call into deduced ABI's SimdImpl after conversion.
	* include/experimental/bits/simd_x86.h (_S_masked_store_nocvt):
	Don't use _mm_maskmoveu_si128. Use the generic fall-back
	implementation. Also fix masked stores without SSE2, which
	were not doing anything before.
---
 .../include/experimental/bits/simd_builtin.h  |  6 +--
 .../include/experimental/bits/simd_x86.h      | 38 ++-----------------
 2 files changed, 7 insertions(+), 37 deletions(-)


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

[-- Attachment #2: 0002-libstdc-Replace-use-of-incorrect-non-temporal-store.patch --]
[-- Type: text/x-patch, Size: 4388 bytes --]

diff --git a/libstdc++-v3/include/experimental/bits/simd_builtin.h b/libstdc++-v3/include/experimental/bits/simd_builtin.h
index 8337fa2d9a6..64ef6efaf8c 100644
--- a/libstdc++-v3/include/experimental/bits/simd_builtin.h
+++ b/libstdc++-v3/include/experimental/bits/simd_builtin.h
@@ -1628,7 +1628,7 @@ _S_masked_store_nocvt(_SimdWrapper<_Tp, _Np> __v, _Tp* __mem, _MaskMember<_Tp> _
 	    if constexpr (_UW_size == _TV_size) // one convert+store
 	      {
 		const _UW __converted = __convert<_UW>(__v);
-		_SuperImpl::_S_masked_store_nocvt(
+		_UAbi::_SimdImpl::_S_masked_store_nocvt(
 		  __converted, __mem,
 		  _UAbi::_MaskImpl::template _S_convert<
 		    __int_for_sizeof_t<_Up>>(__k));
@@ -1643,7 +1643,7 @@ _S_masked_store_nocvt(_SimdWrapper<_Tp, _Np> __v, _Tp* __mem, _MaskMember<_Tp> _
 		const array<_UV, _NAllStores> __converted
 		  = __convert_all<_UV, _NAllStores>(__v);
 		__execute_n_times<_NFullStores>([&](auto __i) _GLIBCXX_SIMD_ALWAYS_INLINE_LAMBDA {
-		  _SuperImpl::_S_masked_store_nocvt(
+		  _UAbi::_SimdImpl::_S_masked_store_nocvt(
 		    _UW(__converted[__i]), __mem + __i * _UW_size,
 		    _UAbi::_MaskImpl::template _S_convert<
 		      __int_for_sizeof_t<_Up>>(
@@ -1651,7 +1651,7 @@ _S_masked_store_nocvt(_SimdWrapper<_Tp, _Np> __v, _Tp* __mem, _MaskMember<_Tp> _
 		});
 		if constexpr (_NAllStores
 			      > _NFullStores) // one partial at the end
-		  _SuperImpl::_S_masked_store_nocvt(
+		  _UAbi::_SimdImpl::_S_masked_store_nocvt(
 		    _UW(__converted[_NFullStores]),
 		    __mem + _NFullStores * _UW_size,
 		    _UAbi::_MaskImpl::template _S_convert<
diff --git a/libstdc++-v3/include/experimental/bits/simd_x86.h b/libstdc++-v3/include/experimental/bits/simd_x86.h
index 77d2f84ab71..2e301e45677 100644
--- a/libstdc++-v3/include/experimental/bits/simd_x86.h
+++ b/libstdc++-v3/include/experimental/bits/simd_x86.h
@@ -1106,31 +1106,6 @@ _S_masked_store_nocvt(_SimdWrapper<_Tp, _Np> __v, _Tp* __mem, _SimdWrapper<bool,
 		else
 		  _mm512_mask_storeu_pd(__mem, __k, __vi);
 	      }
-#if 0 // with KNL either sizeof(_Tp) >= 4 or sizeof(_vi) <= 32
-      // with Skylake-AVX512, __have_avx512bw is true
-	  else if constexpr (__have_sse2)
-	    {
-	      using _M   = __vector_type_t<_Tp, _Np>;
-	      using _MVT = _VectorTraits<_M>;
-	      _mm_maskmoveu_si128(__auto_bitcast(__extract<0, 4>(__v._M_data)),
-				  __auto_bitcast(_MaskImpl::template _S_convert<_Tp, _Np>(__k._M_data)),
-				  reinterpret_cast<char*>(__mem));
-	      _mm_maskmoveu_si128(__auto_bitcast(__extract<1, 4>(__v._M_data)),
-				  __auto_bitcast(_MaskImpl::template _S_convert<_Tp, _Np>(
-				    __k._M_data >> 1 * _MVT::_S_full_size)),
-				  reinterpret_cast<char*>(__mem) + 1 * 16);
-	      _mm_maskmoveu_si128(__auto_bitcast(__extract<2, 4>(__v._M_data)),
-				  __auto_bitcast(_MaskImpl::template _S_convert<_Tp, _Np>(
-				    __k._M_data >> 2 * _MVT::_S_full_size)),
-				  reinterpret_cast<char*>(__mem) + 2 * 16);
-	      if constexpr (_Np > 48 / sizeof(_Tp))
-		_mm_maskmoveu_si128(
-		  __auto_bitcast(__extract<3, 4>(__v._M_data)),
-		  __auto_bitcast(_MaskImpl::template _S_convert<_Tp, _Np>(
-		    __k._M_data >> 3 * _MVT::_S_full_size)),
-		  reinterpret_cast<char*>(__mem) + 3 * 16);
-	    }
-#endif
 	    else
 	      __assert_unreachable<_Tp>();
 	  }
@@ -1233,8 +1208,8 @@ _S_masked_store_nocvt(_SimdWrapper<_Tp, _Np> __v, _Tp* __mem,
 	    else if constexpr (__have_avx && sizeof(_Tp) == 8)
 	      _mm_maskstore_pd(reinterpret_cast<double*>(__mem), __ki,
 			       __vector_bitcast<double>(__vi));
-	    else if constexpr (__have_sse2)
-	      _mm_maskmoveu_si128(__vi, __ki, reinterpret_cast<char*>(__mem));
+	    else
+	      _Base::_S_masked_store_nocvt(__v, __mem, __k);
 	  }
 	else if constexpr (sizeof(__v) == 32)
 	  {
@@ -1259,13 +1234,8 @@ _S_masked_store_nocvt(_SimdWrapper<_Tp, _Np> __v, _Tp* __mem,
 	    else if constexpr (__have_avx && sizeof(_Tp) == 8)
 	      _mm256_maskstore_pd(reinterpret_cast<double*>(__mem), __ki,
 				  __vector_bitcast<double>(__v));
-	    else if constexpr (__have_sse2)
-	      {
-		_mm_maskmoveu_si128(__lo128(__vi), __lo128(__ki),
-				    reinterpret_cast<char*>(__mem));
-		_mm_maskmoveu_si128(__hi128(__vi), __hi128(__ki),
-				    reinterpret_cast<char*>(__mem) + 16);
-	      }
+	    else
+	      _Base::_S_masked_store_nocvt(__v, __mem, __k);
 	  }
 	else
 	  __assert_unreachable<_Tp>();