libstdc++: Fix find_last_set(simd_mask) to ignore padding bits

With the change to the AVX512 find_last_set implementation, the change
to AVX512 operator!= is unnecessary. However, the latter was not
producing optimal code and unnecessarily set the padding bits. In
theory, the compiler could determine that with the new !=
implementation, the bit operation for clearing the padding bits is a
no-op and can be elided.

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

libstdc++-v3/ChangeLog:

	PR libstdc++/115454
	* include/experimental/bits/simd_x86.h (_S_not_equal_to): Use
	neq comparison instead of bitwise negation after eq.
	(_S_find_last_set): Clear unused high bits before computing
	bit_width.
	* testsuite/experimental/simd/pr115454_find_last_set.cc: New
	test.

(cherry picked from commit 1340ddea0158de3f49aeb75b4013e5fc313ff6f4)

1 files changed, 13 insertions, 13 deletions

diff --git a/libstdc++-v3/include/experimental/bits/simd_x86.h b/libstdc++-v3/include/experimental/bits/simd_x86.h
index 517c4b4..8a23aa2 100644
--- a/libstdc++-v3/include/experimental/bits/simd_x86.h
+++ b/libstdc++-v3/include/experimental/bits/simd_x86.h
@@ -2339,29 +2339,29 @@ template <typename _Abi, typename>
 		  __assert_unreachable<_Tp>();
 	      }
 	    else if constexpr (sizeof(__xi) == 64 && sizeof(_Tp) == 8)
-	      return ~_mm512_mask_cmpeq_epi64_mask(__k1, __xi, __yi);
+	      return _mm512_mask_cmpneq_epi64_mask(__k1, __xi, __yi);
 	    else if constexpr (sizeof(__xi) == 64 && sizeof(_Tp) == 4)
-	      return ~_mm512_mask_cmpeq_epi32_mask(__k1, __xi, __yi);
+	      return _mm512_mask_cmpneq_epi32_mask(__k1, __xi, __yi);
 	    else if constexpr (sizeof(__xi) == 64 && sizeof(_Tp) == 2)
-	      return ~_mm512_mask_cmpeq_epi16_mask(__k1, __xi, __yi);
+	      return _mm512_mask_cmpneq_epi16_mask(__k1, __xi, __yi);
 	    else if constexpr (sizeof(__xi) == 64 && sizeof(_Tp) == 1)
-	      return ~_mm512_mask_cmpeq_epi8_mask(__k1, __xi, __yi);
+	      return _mm512_mask_cmpneq_epi8_mask(__k1, __xi, __yi);
 	    else if constexpr (sizeof(__xi) == 32 && sizeof(_Tp) == 8)
-	      return ~_mm256_mask_cmpeq_epi64_mask(__k1, __xi, __yi);
+	      return _mm256_mask_cmpneq_epi64_mask(__k1, __xi, __yi);
 	    else if constexpr (sizeof(__xi) == 32 && sizeof(_Tp) == 4)
-	      return ~_mm256_mask_cmpeq_epi32_mask(__k1, __xi, __yi);
+	      return _mm256_mask_cmpneq_epi32_mask(__k1, __xi, __yi);
 	    else if constexpr (sizeof(__xi) == 32 && sizeof(_Tp) == 2)
-	      return ~_mm256_mask_cmpeq_epi16_mask(__k1, __xi, __yi);
+	      return _mm256_mask_cmpneq_epi16_mask(__k1, __xi, __yi);
 	    else if constexpr (sizeof(__xi) == 32 && sizeof(_Tp) == 1)
-	      return ~_mm256_mask_cmpeq_epi8_mask(__k1, __xi, __yi);
+	      return _mm256_mask_cmpneq_epi8_mask(__k1, __xi, __yi);
 	    else if constexpr (sizeof(__xi) == 16 && sizeof(_Tp) == 8)
-	      return ~_mm_mask_cmpeq_epi64_mask(__k1, __xi, __yi);
+	      return _mm_mask_cmpneq_epi64_mask(__k1, __xi, __yi);
 	    else if constexpr (sizeof(__xi) == 16 && sizeof(_Tp) == 4)
-	      return ~_mm_mask_cmpeq_epi32_mask(__k1, __xi, __yi);
+	      return _mm_mask_cmpneq_epi32_mask(__k1, __xi, __yi);
 	    else if constexpr (sizeof(__xi) == 16 && sizeof(_Tp) == 2)
-	      return ~_mm_mask_cmpeq_epi16_mask(__k1, __xi, __yi);
+	      return _mm_mask_cmpneq_epi16_mask(__k1, __xi, __yi);
 	    else if constexpr (sizeof(__xi) == 16 && sizeof(_Tp) == 1)
-	      return ~_mm_mask_cmpeq_epi8_mask(__k1, __xi, __yi);
+	      return _mm_mask_cmpneq_epi8_mask(__k1, __xi, __yi);
 	    else
 	      __assert_unreachable<_Tp>();
 	  }                                                   // }}}
@@ -5292,7 +5292,7 @@ template <typename _Abi, typename>
       _S_find_last_set(simd_mask<_Tp, _Abi> __k)
       {
 	if constexpr (__is_avx512_abi<_Abi>())
-	  return std::__bit_width(__k._M_data._M_data) - 1;
+	  return std::__bit_width(_Abi::_S_masked(__k._M_data)._M_data) - 1;
 	else
 	  return _Base::_S_find_last_set(__k);
       }