[libcxx] implement <experimental/simd> declarations based on P0214R7.

[timshen]

Summary

The patch includes all declarations, and also implements the following features:

• ABI.
• narrowing-conversion related SFIANE, including simd<> ctors and (static_)simd_cast.

[lichray]

I beg you to resubmit this patch relative to "libcxx"; I had to arc export this patch and patch -p1 < your.diff manually rather than just arc patch D41148.

libcxx/include/experimental/simd

1069 ↗

(On Diff #126662)

Does it causes a problem if the logic of is_convertible is folded into __is_non_narrowing_convertible?

1088 ↗

(On Diff #126662)

Really? decltype(simd(...), 0) = 0 seems passing your tests.

libcxx/test/std/experimental/simd/simd_cast.pass.cpp

87 ↗

(On Diff #126662)

No more return 0; in main; no other files do so.

libcxx/test/std/experimental/simd/traits.pass.cpp

37 ↗

(On Diff #126662)

> > is not a fashion...

[timshen]

Address comments:

• Generator ctor is implementable
• Format issues of tests
• SFINAE on __is_non_narrowing_convertible for arithmetics only.

[timshen]

libcxx/include/experimental/simd

1069 ↗

(On Diff #126662)

Avoided to answer this question by sfinae on is_arithmetic.

[EricWF]

libcxx/include/experimental/simd

1 ↗

(On Diff #126813)

Please add the license header similar to experimental/filesystem.

581 ↗

(On Diff #126813)

The first include should be <experimental/__config>

590 ↗

(On Diff #126813)

(1) _LIBCPP_STD_VER is never less than 11. It's an odd libc++ quirk.
(2) We don't normally generate explicit errors when headers are used incorrectly.

594 ↗

(On Diff #126813)

I would just remove this. The experimental part of the name should say enough.

Also we normally wait until an implementation is mostly complete before landing it.

596 ↗

(On Diff #126813)

Please define macros to open and close the namespace similar to _LIBCPP_BEGIN_NAMESPACE_EXPERIMENTAL_FILESYSTEM in <experimental/__config>

libcxx/test/std/experimental/simd/traits.pass.cpp

15 ↗

(On Diff #126813)

Please create a directory called simd/traits/ and then put each trait in a separate test file under that directory.
The foo_v tests should be in the same file as the foo tests.

[timshen]

Address second round of comments.

[timshen]

libcxx/include/experimental/simd

594 ↗

(On Diff #126813)

Also we normally wait until an implementation is mostly complete before landing it.

What's the definition of "landing"? I prefer to implement this library in multiple patches, does that mean I keep working on the next ones and finally commit all of them all at once? If that's the case, SGTM.

libcxx/test/std/experimental/simd/traits.pass.cpp

15 ↗

(On Diff #126813)

Thanks! Done for all tests. Used directory names like "simd.cons", "simd.traits", "simd.casts".

[timshen]

Formatted the files.

[timshen]

include "test_macros.h" in the tests

[timshen]

Rebase.

[timshen]

Rebased.

[timshen]

Rebase.

[mclow.lists]

I'm going to stop here, because all the things I've noted are ticky-tack; formatting and minor changes.
More substantial comments coming soon.

libcxx/include/experimental/simd

40 ↗

(On Diff #139036)

A blank line between the separate groups (as in the paper) will make this much easier to read

67 ↗

(On Diff #139036)

And here you have an extra line - go figure.

113 ↗

(On Diff #139036)

blank line, extra space (see below ) should be (see below)

144 ↗

(On Diff #139036)

This is better formatting than in the paper :-)

316 ↗

(On Diff #139036)

These would be much easier to read lined up, and with blank lines.

template <class Abi> floatv<Abi>   acos(floatv<Abi>   x);
template <class Abi> doublev<Abi>  acos(doublev<Abi>  x);
template <class Abi> ldoublev<Abi> acos(ldoublev<Abi> x);

template <class Abi> floatv<Abi>   asin(floatv<Abi>   x);
template <class Abi> doublev<Abi>  asin(doublev<Abi>  x);
template <class Abi> ldoublev<Abi> asin(ldoublev<Abi> x);

626 ↗

(On Diff #139036)

Do you need the trailing return type here? instead of something like decltype(_to{declval<_From>()})

Then you don't need to name a, and can get rid of the (gcc-specific) attribute.

653 ↗

(On Diff #139036)

This won't work if _Tp has an explicit default ctor (which is probably not true for anything in SIMD). Do you lose anything by writing return _Tp{} ?

669 ↗

(On Diff #139036)

Isn't the parallelism TS based on C++17?

[timshen]

Address comments.

[timshen]

libcxx/include/experimental/simd

669 ↗

(On Diff #139036)

I intended to have a C++11 (and C++14) compatible implementation.

[mclow.lists]

When you add a new header file to libc++, you have to update two additional files:

• include/module.modulemap
• test/libcxx/double_include.sh.cpp

See http://llvm.org/viewvc/llvm-project?view=revision&revision=329144 for an example of how to do this.

libcxx/test/std/experimental/simd/simd.cons/geneartor.pass.cpp

3 ↗

(On Diff #139393)

Surely you didn't really mean to name this file "geneartor.pass.cpp"

[mclow.lists]

libcxx/test/std/experimental/simd/simd.traits/is_abi_tag.pass.cpp

44 ↗

(On Diff #139393)

Needs negative tests.

libcxx/test/std/experimental/simd/simd.traits/is_simd.pass.cpp

68 ↗

(On Diff #139393)

Negative tests, too, please.

libcxx/test/std/experimental/simd/simd.traits/is_simd_flag_type.pass.cpp

27 ↗

(On Diff #139393)

It's good that you check that all the things do pass, but you should have some failing tests, too:

static_assert(!is_simd_flag_type<void>::value, "");
static_assert(!is_simd_flag_type<int>::value, "");
static_assert(!is_simd_flag_type<float>::value, "");
static_assert(!is_simd_flag_type<std::string>::value, "");
static_assert(!is_simd_flag_type<fixed_size_simd<int8_t>>::value, "");
static_assert(!is_simd_flag_type<native_simd_mask<int8_t>>::value, "");

libcxx/test/std/experimental/simd/simd.traits/is_simd_mask.pass.cpp

68 ↗

(On Diff #139393)

How about a couple more negative tests here?
You've got int, how about float, and std::string and a few of the simd types?

[timshen]

Addressed comments.

[timshen]

libcxx/test/std/experimental/simd/simd.traits/is_simd_mask.pass.cpp

68 ↗

(On Diff #139393)

I used "UserType" instead of std::string, as I don't want to pull in the whole <string> header. I figured that UserType should serve the same purpose.

[timshen]

Update file comments copy-paste error.

[mclow.lists]

This looks ready to land to me.

libcxx/test/std/experimental/simd/simd.traits/is_simd_mask.pass.cpp

122 ↗

(On Diff #141436)

Minor formatting nit. When I have stacks of tests like this, I usually leave a space after the '(', so that positive and negative tests line up, and so I can see at a glance which are which.

Example:

static_assert( is_simd_mask_v<fixed_size_simd_mask<double, 32>>, "");
static_assert(!is_simd_mask_v<void>, "");

[timshen]

Update formatting on static_asserts.

libcxx/trunk/include/experimental/__config

 
 #define _LIBCPP_END_NAMESPACE_EXPERIMENTAL_COROUTINES \
   } _LIBCPP_END_NAMESPACE_EXPERIMENTAL
 
 #define _VSTD_CORO _VSTD_EXPERIMENTAL::coroutines_v1
 
 #define _VSTD_FS ::std::experimental::filesystem::v1
 
+#define _LIBCPP_BEGIN_NAMESPACE_EXPERIMENTAL_SIMD \
+    _LIBCPP_BEGIN_NAMESPACE_EXPERIMENTAL inline namespace parallelism_v2 {
+
+#define _LIBCPP_END_NAMESPACE_EXPERIMENTAL_SIMD \
+    } _LIBCPP_END_NAMESPACE_EXPERIMENTAL
+
+#define _LIBCPP_BEGIN_NAMESPACE_EXPERIMENTAL_SIMD_ABI \
+    _LIBCPP_BEGIN_NAMESPACE_EXPERIMENTAL_SIMD namespace simd_abi {
+
+#define _LIBCPP_END_NAMESPACE_EXPERIMENTAL_SIMD_ABI \
+    } _LIBCPP_END_NAMESPACE_EXPERIMENTAL_SIMD
+
 #endif

libcxx/trunk/include/experimental/simd

+// -*- C++ -*-
+//===------------------------------- simd ---------------------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is dual licensed under the MIT and the University of Illinois Open
+// Source Licenses. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+#ifndef _LIBCPP_EXPERIMENTAL_SIMD
+#define _LIBCPP_EXPERIMENTAL_SIMD
+
+/*
+    experimental/simd synopsis
+
+namespace std::experimental {
+
+inline namespace parallelism_v2 {
+
+namespace simd_abi {
+
+struct scalar {};
+template <int N> struct fixed_size {};
+template <typename T> inline constexpr int max_fixed_size = implementation-defined;
+template <typename T> using compatible = implementation-defined;
+template <typename T> using native = implementation-defined;
+
+} // simd_abi
+
+struct element_aligned_tag {};
+struct vector_aligned_tag {};
+template <size_t> struct overaligned_tag {};
+inline constexpr element_aligned_tag element_aligned{};
+inline constexpr vector_aligned_tag vector_aligned{};
+template <size_t N> inline constexpr overaligned_tag<N> overaligned{};
+
+// traits [simd.traits]
+template <class T> struct is_abi_tag;
+template <class T> inline constexpr bool is_abi_tag_v = is_abi_tag<T>::value;
+
+template <class T> struct is_simd;
+template <class T> inline constexpr bool is_simd_v = is_simd<T>::value;
+
+template <class T> struct is_simd_mask;
+template <class T> inline constexpr bool is_simd_mask_v = is_simd_mask<T>::value;
+
+template <class T> struct is_simd_flag_type;
+template <class T> inline constexpr bool is_simd_flag_type_v = is_simd_flag_type<T>::value;
+
+template <class T, size_t N> struct abi_for_size { using type = see below; };
+template <class T, size_t N> using abi_for_size_t = typename abi_for_size<T, N>::type;
+
+template <class T, class Abi = simd_abi::compatible<T>> struct simd_size;
+template <class T, class Abi = simd_abi::compatible<T>>
+inline constexpr size_t simd_size_v = simd_size<T, Abi>::value;
+
+template <class T, class U = typename T::value_type> struct memory_alignment;
+template <class T, class U = typename T::value_type>
+inline constexpr size_t memory_alignment_v = memory_alignment<T, U>::value;
+
+// class template simd [simd.class]
+template <class T, class Abi = simd_abi::compatible<T>> class simd;
+template <class T> using native_simd = simd<T, simd_abi::native<T>>;
+template <class T, int N> using fixed_size_simd = simd<T, simd_abi::fixed_size<N>>;
+
+// class template simd_mask [simd.mask.class]
+template <class T, class Abi = simd_abi::compatible<T>> class simd_mask;
+template <class T> using native_simd_mask = simd_mask<T, simd_abi::native<T>>;
+template <class T, int N> using fixed_size_simd_mask = simd_mask<T, simd_abi::fixed_size<N>>;
+
+// casts [simd.casts]
+template <class T, class U, class Abi> see below simd_cast(const simd<U, Abi>&);
+template <class T, class U, class Abi> see below static_simd_cast(const simd<U, Abi>&);
+
+template <class T, class Abi>
+fixed_size_simd<T, simd_size_v<T, Abi>> to_fixed_size(const simd<T, Abi>&) noexcept;
+template <class T, class Abi>
+fixed_size_simd_mask<T, simd_size_v<T, Abi>> to_fixed_size(const simd_mask<T, Abi>&) noexcept;
+template <class T, size_t N> native_simd<T> to_native(const fixed_size_simd<T, N>&) noexcept;
+template <class T, size_t N>
+native_simd_mask<T> to_native(const fixed_size_simd_mask<T, N>> &) noexcept;
+template <class T, size_t N> simd<T> to_compatible(const fixed_size_simd<T, N>&) noexcept;
+template <class T, size_t N> simd_mask<T> to_compatible(const fixed_size_simd_mask<T, N>&) noexcept;
+
+template <size_t... Sizes, class T, class Abi>
+tuple<simd<T, abi_for_size_t<Sizes>>...> split(const simd<T, Abi>&);
+template <size_t... Sizes, class T, class Abi>
+tuple<simd_mask<T, abi_for_size_t<Sizes>>...> split(const simd_mask<T, Abi>&);
+template <class V, class Abi>
+array<V, simd_size_v<typename V::value_type, Abi> / V::size()> split(
+const simd<typename V::value_type, Abi>&);
+template <class V, class Abi>
+array<V, simd_size_v<typename V::value_type, Abi> / V::size()> split(
+const simd_mask<typename V::value_type, Abi>&);
+
+template <class T, class... Abis>
+simd<T, abi_for_size_t<T, (simd_size_v<T, Abis> + ...)>> concat(const simd<T, Abis>&...);
+template <class T, class... Abis>
+simd_mask<T, abi_for_size_t<T, (simd_size_v<T, Abis> + ...)>> concat(const simd_mask<T, Abis>&...);
+
+// reductions [simd.mask.reductions]
+template <class T, class Abi> bool all_of(const simd_mask<T, Abi>&) noexcept;
+template <class T, class Abi> bool any_of(const simd_mask<T, Abi>&) noexcept;
+template <class T, class Abi> bool none_of(const simd_mask<T, Abi>&) noexcept;
+template <class T, class Abi> bool some_of(const simd_mask<T, Abi>&) noexcept;
+template <class T, class Abi> int popcount(const simd_mask<T, Abi>&) noexcept;
+template <class T, class Abi> int find_first_set(const simd_mask<T, Abi>&);
+template <class T, class Abi> int find_last_set(const simd_mask<T, Abi>&);
+
+bool all_of(see below) noexcept;
+bool any_of(see below) noexcept;
+bool none_of(see below) noexcept;
+bool some_of(see below) noexcept;
+int popcount(see below) noexcept;
+int find_first_set(see below) noexcept;
+int find_last_set(see below) noexcept;
+
+// masked assignment [simd.whereexpr]
+template <class M, class T> class const_where_expression;
+template <class M, class T> class where_expression;
+
+// masked assignment [simd.mask.where]
+template <class T> struct nodeduce { using type = T; }; // exposition only
+
+template <class T> using nodeduce_t = typename nodeduce<T>::type; // exposition only
+
+template <class T, class Abi>
+where_expression<simd_mask<T, Abi>, simd<T, Abi>>
+where(const typename simd<T, Abi>::mask_type&, simd<T, Abi>&) noexcept;
+
+template <class T, class Abi>
+const_where_expression<simd_mask<T, Abi>, const simd<T, Abi>>
+where(const typename simd<T, Abi>::mask_type&, const simd<T, Abi>&) noexcept;
+
+template <class T, class Abi>
+where_expression<simd_mask<T, Abi>, simd_mask<T, Abi>>
+where(const nodeduce_t<simd_mask<T, Abi>>&, simd_mask<T, Abi>&) noexcept;
+
+template <class T, class Abi>
+const_where_expression<simd_mask<T, Abi>, const simd_mask<T, Abi>>
+where(const nodeduce_t<simd_mask<T, Abi>>&, const simd_mask<T, Abi>&) noexcept;
+
+template <class T> where_expression<bool, T> where(see below k, T& d) noexcept;
+
+template <class T>
+const_where_expression<bool, const T> where(see below k, const T& d) noexcept;
+
+// reductions [simd.reductions]
+template <class T, class Abi, class BinaryOperation = std::plus<>>
+T reduce(const simd<T, Abi>&, BinaryOperation = BinaryOperation());
+
+template <class M, class V, class BinaryOperation>
+typename V::value_type reduce(const const_where_expression<M, V>& x,
+typename V::value_type neutral_element, BinaryOperation binary_op);
+
+template <class M, class V>
+typename V::value_type reduce(const const_where_expression<M, V>& x, plus<> binary_op = plus<>());
+
+template <class M, class V>
+typename V::value_type reduce(const const_where_expression<M, V>& x, multiplies<> binary_op);
+
+template <class M, class V>
+typename V::value_type reduce(const const_where_expression<M, V>& x, bit_and<> binary_op);
+
+template <class M, class V>
+typename V::value_type reduce(const const_where_expression<M, V>& x, bit_or<> binary_op);
+
+template <class M, class V>
+typename V::value_type reduce(const const_where_expression<M, V>& x, bit_xor<> binary_op);
+
+template <class T, class Abi> T hmin(const simd<T, Abi>&);
+template <class M, class V> T hmin(const const_where_expression<M, V>&);
+template <class T, class Abi> T hmax(const simd<T, Abi>&);
+template <class M, class V> T hmax(const const_where_expression<M, V>&);
+
+// algorithms [simd.alg]
+template <class T, class Abi> simd<T, Abi> min(const simd<T, Abi>&, const simd<T, Abi>&) noexcept;
+
+template <class T, class Abi> simd<T, Abi> max(const simd<T, Abi>&, const simd<T, Abi>&) noexcept;
+
+template <class T, class Abi>
+std::pair<simd<T, Abi>, simd<T, Abi>> minmax(const simd<T, Abi>&, const simd<T, Abi>&) noexcept;
+
+template <class T, class Abi>
+simd<T, Abi> clamp(const simd<T, Abi>& v, const simd<T, Abi>& lo, const simd<T, Abi>& hi);
+
+// [simd.whereexpr]
+template <class M, class T>
+class const_where_expression {
+  const M& mask; // exposition only
+  T& data; // exposition only
+public:
+  const_where_expression(const const_where_expression&) = delete;
+  const_where_expression& operator=(const const_where_expression&) = delete;
+  remove_const_t<T> operator-() const &&;
+  template <class U, class Flags> void copy_to(U* mem, Flags f) const &&;
+};
+
+template <class M, class T>
+class where_expression : public const_where_expression<M, T> {
+public:
+  where_expression(const where_expression&) = delete;
+  where_expression& operator=(const where_expression&) = delete;
+  template <class U> void operator=(U&& x);
+  template <class U> void operator+=(U&& x);
+  template <class U> void operator-=(U&& x);
+  template <class U> void operator*=(U&& x);
+  template <class U> void operator/=(U&& x);
+  template <class U> void operator%=(U&& x);
+  template <class U> void operator&=(U&& x);
+  template <class U> void operator|=(U&& x);
+  template <class U> void operator^=(U&& x);
+  template <class U> void operator<<=(U&& x);
+  template <class U> void operator>>=(U&& x);
+  void operator++();
+  void operator++(int);
+  void operator--();
+  void operator--(int);
+  template <class U, class Flags> void copy_from(const U* mem, Flags);
+};
+
+// [simd.class]
+template <class T, class Abi> class simd {
+public:
+  using value_type = T;
+  using reference = see below;
+  using mask_type = simd_mask<T, Abi>;
+
+  using abi_type = Abi;
+  static constexpr size_t size() noexcept;
+  simd() = default;
+
+  // implicit type conversion constructor
+  template <class U> simd(const simd<U, simd_abi::fixed_size<size()>>&);
+
+  // implicit broadcast constructor (see below for constraints)
+  template <class U> simd(U&& value);
+
+  // generator constructor (see below for constraints)
+  template <class G> explicit simd(G&& gen);
+
+  // load constructor
+  template <class U, class Flags> simd(const U* mem, Flags f);
+
+  // loads [simd.load]
+  template <class U, class Flags> void copy_from(const U* mem, Flags f);
+
+  // stores [simd.store]
+  template <class U, class Flags> void copy_to(U* mem, Flags f) const;
+
+  // scalar access [simd.subscr]
+  reference operator[](size_t);
+  value_type operator[](size_t) const;
+
+  // unary operators [simd.unary]
+  simd& operator++();
+  simd operator++(int);
+  simd& operator--();
+  simd operator--(int);
+  mask_type operator!() const;
+  simd operator~() const; // see below
+  simd operator+() const;
+  simd operator-() const;
+
+  // binary operators [simd.binary]
+  friend simd operator+ (const simd&, const simd&);
+  friend simd operator- (const simd&, const simd&);
+  friend simd operator* (const simd&, const simd&);
+  friend simd operator/ (const simd&, const simd&);
+  friend simd operator% (const simd&, const simd&);
+  friend simd operator& (const simd&, const simd&);
+  friend simd operator| (const simd&, const simd&);
+  friend simd operator^ (const simd&, const simd&);
+  friend simd operator<<(const simd&, const simd&);
+  friend simd operator>>(const simd&, const simd&);
+  friend simd operator<<(const simd&, int);
+  friend simd operator>>(const simd&, int);
+
+  // compound assignment [simd.cassign]
+  friend simd& operator+= (simd&, const simd&);
+  friend simd& operator-= (simd&, const simd&);
+  friend simd& operator*= (simd&, const simd&);
+  friend simd& operator/= (simd&, const simd&);
+  friend simd& operator%= (simd&, const simd&);
+
+  friend simd& operator&= (simd&, const simd&);
+  friend simd& operator|= (simd&, const simd&);
+  friend simd& operator^= (simd&, const simd&);
+  friend simd& operator<<=(simd&, const simd&);
+  friend simd& operator>>=(simd&, const simd&);
+  friend simd& operator<<=(simd&, int);
+  friend simd& operator>>=(simd&, int);
+
+  // compares [simd.comparison]
+  friend mask_type operator==(const simd&, const simd&);
+  friend mask_type operator!=(const simd&, const simd&);
+  friend mask_type operator>=(const simd&, const simd&);
+  friend mask_type operator<=(const simd&, const simd&);
+  friend mask_type operator> (const simd&, const simd&);
+  friend mask_type operator< (const simd&, const simd&);
+};
+
+// [simd.math]
+template <class Abi> using scharv = simd<signed char, Abi>; // exposition only
+template <class Abi> using shortv = simd<short, Abi>; // exposition only
+template <class Abi> using intv = simd<int, Abi>; // exposition only
+template <class Abi> using longv = simd<long int, Abi>; // exposition only
+template <class Abi> using llongv = simd<long long int, Abi>; // exposition only
+template <class Abi> using floatv = simd<float, Abi>; // exposition only
+template <class Abi> using doublev = simd<double, Abi>; // exposition only
+template <class Abi> using ldoublev = simd<long double, Abi>; // exposition only
+template <class T, class V> using samesize = fixed_size_simd<T, V::size()>; // exposition only
+
+template <class Abi> floatv<Abi> acos(floatv<Abi> x);
+template <class Abi> doublev<Abi> acos(doublev<Abi> x);
+template <class Abi> ldoublev<Abi> acos(ldoublev<Abi> x);
+
+template <class Abi> floatv<Abi> asin(floatv<Abi> x);
+template <class Abi> doublev<Abi> asin(doublev<Abi> x);
+template <class Abi> ldoublev<Abi> asin(ldoublev<Abi> x);
+
+template <class Abi> floatv<Abi> atan(floatv<Abi> x);
+template <class Abi> doublev<Abi> atan(doublev<Abi> x);
+template <class Abi> ldoublev<Abi> atan(ldoublev<Abi> x);
+
+template <class Abi> floatv<Abi> atan2(floatv<Abi> y, floatv<Abi> x);
+template <class Abi> doublev<Abi> atan2(doublev<Abi> y, doublev<Abi> x);
+template <class Abi> ldoublev<Abi> atan2(ldoublev<Abi> y, ldoublev<Abi> x);
+
+template <class Abi> floatv<Abi> cos(floatv<Abi> x);
+template <class Abi> doublev<Abi> cos(doublev<Abi> x);
+template <class Abi> ldoublev<Abi> cos(ldoublev<Abi> x);
+
+template <class Abi> floatv<Abi> sin(floatv<Abi> x);
+template <class Abi> doublev<Abi> sin(doublev<Abi> x);
+template <class Abi> ldoublev<Abi> sin(ldoublev<Abi> x);
+
+template <class Abi> floatv<Abi> tan(floatv<Abi> x);
+template <class Abi> doublev<Abi> tan(doublev<Abi> x);
+template <class Abi> ldoublev<Abi> tan(ldoublev<Abi> x);
+
+template <class Abi> floatv<Abi> acosh(floatv<Abi> x);
+template <class Abi> doublev<Abi> acosh(doublev<Abi> x);
+template <class Abi> ldoublev<Abi> acosh(ldoublev<Abi> x);
+
+template <class Abi> floatv<Abi> asinh(floatv<Abi> x);
+template <class Abi> doublev<Abi> asinh(doublev<Abi> x);
+template <class Abi> ldoublev<Abi> asinh(ldoublev<Abi> x);
+
+template <class Abi> floatv<Abi> atanh(floatv<Abi> x);
+template <class Abi> doublev<Abi> atanh(doublev<Abi> x);
+template <class Abi> ldoublev<Abi> atanh(ldoublev<Abi> x);
+
+template <class Abi> floatv<Abi> cosh(floatv<Abi> x);
+template <class Abi> doublev<Abi> cosh(doublev<Abi> x);
+template <class Abi> ldoublev<Abi> cosh(ldoublev<Abi> x);
+
+template <class Abi> floatv<Abi> sinh(floatv<Abi> x);
+template <class Abi> doublev<Abi> sinh(doublev<Abi> x);
+template <class Abi> ldoublev<Abi> sinh(ldoublev<Abi> x);
+
+template <class Abi> floatv<Abi> tanh(floatv<Abi> x);
+template <class Abi> doublev<Abi> tanh(doublev<Abi> x);
+template <class Abi> ldoublev<Abi> tanh(ldoublev<Abi> x);
+
+template <class Abi> floatv<Abi> exp(floatv<Abi> x);
+template <class Abi> doublev<Abi> exp(doublev<Abi> x);
+template <class Abi> ldoublev<Abi> exp(ldoublev<Abi> x);
+
+template <class Abi> floatv<Abi> exp2(floatv<Abi> x);
+template <class Abi> doublev<Abi> exp2(doublev<Abi> x);
+template <class Abi> ldoublev<Abi> exp2(ldoublev<Abi> x);
+
+template <class Abi> floatv<Abi> expm1(floatv<Abi> x);
+template <class Abi> doublev<Abi> expm1(doublev<Abi> x);
+template <class Abi> ldoublev<Abi> expm1(ldoublev<Abi> x);
+
+template <class Abi> floatv<Abi> frexp(floatv<Abi> value, samesize<int, floatv<Abi>>* exp);
+template <class Abi> doublev<Abi> frexp(doublev<Abi> value, samesize<int, doublev<Abi>>* exp);
+template <class Abi> ldoublev<Abi> frexp(ldoublev<Abi> value, samesize<int, ldoublev<Abi>>* exp);
+
+template <class Abi> samesize<int, floatv<Abi>> ilogb(floatv<Abi> x);
+template <class Abi> samesize<int, doublev<Abi>> ilogb(doublev<Abi> x);
+template <class Abi> samesize<int, ldoublev<Abi>> ilogb(ldoublev<Abi> x);
+
+template <class Abi> floatv<Abi> ldexp(floatv<Abi> x, samesize<int, floatv<Abi>> exp);
+template <class Abi> doublev<Abi> ldexp(doublev<Abi> x, samesize<int, doublev<Abi>> exp);
+template <class Abi> ldoublev<Abi> ldexp(ldoublev<Abi> x, samesize<int, ldoublev<Abi>> exp);
+
+template <class Abi> floatv<Abi> log(floatv<Abi> x);
+template <class Abi> doublev<Abi> log(doublev<Abi> x);
+template <class Abi> ldoublev<Abi> log(ldoublev<Abi> x);
+
+template <class Abi> floatv<Abi> log10(floatv<Abi> x);
+template <class Abi> doublev<Abi> log10(doublev<Abi> x);
+template <class Abi> ldoublev<Abi> log10(ldoublev<Abi> x);
+
+template <class Abi> floatv<Abi> log1p(floatv<Abi> x);
+template <class Abi> doublev<Abi> log1p(doublev<Abi> x);
+template <class Abi> ldoublev<Abi> log1p(ldoublev<Abi> x);
+
+template <class Abi> floatv<Abi> log2(floatv<Abi> x);
+template <class Abi> doublev<Abi> log2(doublev<Abi> x);
+template <class Abi> ldoublev<Abi> log2(ldoublev<Abi> x);
+
+template <class Abi> floatv<Abi> logb(floatv<Abi> x);
+template <class Abi> doublev<Abi> logb(doublev<Abi> x);
+template <class Abi> ldoublev<Abi> logb(ldoublev<Abi> x);
+
+template <class Abi> floatv<Abi> modf(floatv<Abi> value, floatv<Abi>* iptr);
+template <class Abi> doublev<Abi> modf(doublev<Abi> value, doublev<Abi>* iptr);
+template <class Abi> ldoublev<Abi> modf(ldoublev<Abi> value, ldoublev<Abi>* iptr);
+
+template <class Abi> floatv<Abi> scalbn(floatv<Abi> x, samesize<int, floatv<Abi>> n);
+template <class Abi> doublev<Abi> scalbn(doublev<Abi> x, samesize<int, doublev<Abi>> n);
+template <class Abi> ldoublev<Abi> scalbn(ldoublev<Abi> x, samesize<int, ldoublev<Abi>> n);
+template <class Abi> floatv<Abi> scalbln(floatv<Abi> x, samesize<long int, floatv<Abi>> n);
+template <class Abi> doublev<Abi> scalbln(doublev<Abi> x, samesize<long int, doublev<Abi>> n);
+template <class Abi> ldoublev<Abi> scalbln(ldoublev<Abi> x, samesize<long int, ldoublev<Abi>> n);
+
+template <class Abi> floatv<Abi> cbrt(floatv<Abi> x);
+template <class Abi> doublev<Abi> cbrt(doublev<Abi> x);
+template <class Abi> ldoublev<Abi> cbrt(ldoublev<Abi> x);
+
+template <class Abi> scharv<Abi> abs(scharv<Abi> j);
+template <class Abi> shortv<Abi> abs(shortv<Abi> j);
+template <class Abi> intv<Abi> abs(intv<Abi> j);
+template <class Abi> longv<Abi> abs(longv<Abi> j);
+template <class Abi> llongv<Abi> abs(llongv<Abi> j);
+template <class Abi> floatv<Abi> abs(floatv<Abi> j);
+template <class Abi> doublev<Abi> abs(doublev<Abi> j);
+template <class Abi> ldoublev<Abi> abs(ldoublev<Abi> j);
+
+template <class Abi> floatv<Abi> hypot(floatv<Abi> x, floatv<Abi> y);
+template <class Abi> doublev<Abi> hypot(doublev<Abi> x, doublev<Abi> y);
+template <class Abi> ldoublev<Abi> hypot(doublev<Abi> x, doublev<Abi> y);
+template <class Abi> floatv<Abi> hypot(floatv<Abi> x, floatv<Abi> y, floatv<Abi> z);
+template <class Abi> doublev<Abi> hypot(doublev<Abi> x, doublev<Abi> y, doublev<Abi> z);
+template <class Abi> ldoublev<Abi> hypot(ldoublev<Abi> x, ldoublev<Abi> y, ldoublev<Abi> z);
+
+template <class Abi> floatv<Abi> pow(floatv<Abi> x, floatv<Abi> y);
+template <class Abi> doublev<Abi> pow(doublev<Abi> x, doublev<Abi> y);
+template <class Abi> ldoublev<Abi> pow(ldoublev<Abi> x, ldoublev<Abi> y);
+
+template <class Abi> floatv<Abi> sqrt(floatv<Abi> x);
+template <class Abi> doublev<Abi> sqrt(doublev<Abi> x);
+template <class Abi> ldoublev<Abi> sqrt(ldoublev<Abi> x);
+
+template <class Abi> floatv<Abi> erf(floatv<Abi> x);
+template <class Abi> doublev<Abi> erf(doublev<Abi> x);
+template <class Abi> ldoublev<Abi> erf(ldoublev<Abi> x);
+template <class Abi> floatv<Abi> erfc(floatv<Abi> x);
+template <class Abi> doublev<Abi> erfc(doublev<Abi> x);
+template <class Abi> ldoublev<Abi> erfc(ldoublev<Abi> x);
+
+template <class Abi> floatv<Abi> lgamma(floatv<Abi> x);
+template <class Abi> doublev<Abi> lgamma(doublev<Abi> x);
+template <class Abi> ldoublev<Abi> lgamma(ldoublev<Abi> x);
+
+template <class Abi> floatv<Abi> tgamma(floatv<Abi> x);
+template <class Abi> doublev<Abi> tgamma(doublev<Abi> x);
+template <class Abi> ldoublev<Abi> tgamma(ldoublev<Abi> x);
+
+template <class Abi> floatv<Abi> ceil(floatv<Abi> x);
+template <class Abi> doublev<Abi> ceil(doublev<Abi> x);
+template <class Abi> ldoublev<Abi> ceil(ldoublev<Abi> x);
+
+template <class Abi> floatv<Abi> floor(floatv<Abi> x);
+template <class Abi> doublev<Abi> floor(doublev<Abi> x);
+template <class Abi> ldoublev<Abi> floor(ldoublev<Abi> x);
+
+template <class Abi> floatv<Abi> nearbyint(floatv<Abi> x);
+template <class Abi> doublev<Abi> nearbyint(doublev<Abi> x);
+template <class Abi> ldoublev<Abi> nearbyint(ldoublev<Abi> x);
+
+template <class Abi> floatv<Abi> rint(floatv<Abi> x);
+template <class Abi> doublev<Abi> rint(doublev<Abi> x);
+template <class Abi> ldoublev<Abi> rint(ldoublev<Abi> x);
+
+template <class Abi> samesize<long int, floatv<Abi>> lrint(floatv<Abi> x);
+template <class Abi> samesize<long int, doublev<Abi>> lrint(doublev<Abi> x);
+template <class Abi> samesize<long int, ldoublev<Abi>> lrint(ldoublev<Abi> x);
+template <class Abi> samesize<long long int, floatv<Abi>> llrint(floatv<Abi> x);
+template <class Abi> samesize<long long int, doublev<Abi>> llrint(doublev<Abi> x);
+template <class Abi> samesize<long long int, ldoublev<Abi>> llrint(ldoublev<Abi> x);
+
+template <class Abi> floatv<Abi> round(floatv<Abi> x);
+template <class Abi> doublev<Abi> round(doublev<Abi> x);
+template <class Abi> ldoublev<Abi> round(ldoublev<Abi> x);
+template <class Abi> samesize<long int, floatv<Abi>> lround(floatv<Abi> x);
+template <class Abi> samesize<long int, doublev<Abi>> lround(doublev<Abi> x);
+template <class Abi> samesize<long int, ldoublev<Abi>> lround(ldoublev<Abi> x);
+template <class Abi> samesize<long long int, floatv<Abi>> llround(floatv<Abi> x);
+template <class Abi> samesize<long long int, doublev<Abi>> llround(doublev<Abi> x);
+template <class Abi> samesize<long long int, ldoublev<Abi>> llround(ldoublev<Abi> x);
+
+template <class Abi> floatv<Abi> trunc(floatv<Abi> x);
+template <class Abi> doublev<Abi> trunc(doublev<Abi> x);
+template <class Abi> ldoublev<Abi> trunc(ldoublev<Abi> x);
+
+template <class Abi> floatv<Abi> fmod(floatv<Abi> x, floatv<Abi> y);
+template <class Abi> doublev<Abi> fmod(doublev<Abi> x, doublev<Abi> y);
+template <class Abi> ldoublev<Abi> fmod(ldoublev<Abi> x, ldoublev<Abi> y);
+
+template <class Abi> floatv<Abi> remainder(floatv<Abi> x, floatv<Abi> y);
+template <class Abi> doublev<Abi> remainder(doublev<Abi> x, doublev<Abi> y);
+template <class Abi> ldoublev<Abi> remainder(ldoublev<Abi> x, ldoublev<Abi> y);
+
+template <class Abi> floatv<Abi> remquo(floatv<Abi> x, floatv<Abi> y, samesize<int, floatv<Abi>>* quo);
+template <class Abi> doublev<Abi> remquo(doublev<Abi> x, doublev<Abi> y, samesize<int, doublev<Abi>>* quo);
+template <class Abi> ldoublev<Abi> remquo(ldoublev<Abi> x, ldoublev<Abi> y, samesize<int, ldoublev<Abi>>* quo);
+
+template <class Abi> floatv<Abi> copysign(floatv<Abi> x, floatv<Abi> y);
+template <class Abi> doublev<Abi> copysign(doublev<Abi> x, doublev<Abi> y);
+template <class Abi> ldoublev<Abi> copysign(ldoublev<Abi> x, ldoublev<Abi> y);
+
+template <class Abi> doublev<Abi> nan(const char* tagp);
+template <class Abi> floatv<Abi> nanf(const char* tagp);
+template <class Abi> ldoublev<Abi> nanl(const char* tagp);
+
+template <class Abi> floatv<Abi> nextafter(floatv<Abi> x, floatv<Abi> y);
+template <class Abi> doublev<Abi> nextafter(doublev<Abi> x, doublev<Abi> y);
+template <class Abi> ldoublev<Abi> nextafter(ldoublev<Abi> x, ldoublev<Abi> y);
+
+template <class Abi> floatv<Abi> nexttoward(floatv<Abi> x, ldoublev<Abi> y);
+template <class Abi> doublev<Abi> nexttoward(doublev<Abi> x, ldoublev<Abi> y);
+template <class Abi> ldoublev<Abi> nexttoward(ldoublev<Abi> x, ldoublev<Abi> y);
+
+template <class Abi> floatv<Abi> fdim(floatv<Abi> x, floatv<Abi> y);
+template <class Abi> doublev<Abi> fdim(doublev<Abi> x, doublev<Abi> y);
+template <class Abi> ldoublev<Abi> fdim(ldoublev<Abi> x, ldoublev<Abi> y);
+
+template <class Abi> floatv<Abi> fmax(floatv<Abi> x, floatv<Abi> y);
+template <class Abi> doublev<Abi> fmax(doublev<Abi> x, doublev<Abi> y);
+template <class Abi> ldoublev<Abi> fmax(ldoublev<Abi> x, ldoublev<Abi> y);
+
+template <class Abi> floatv<Abi> fmin(floatv<Abi> x, floatv<Abi> y);
+template <class Abi> doublev<Abi> fmin(doublev<Abi> x, doublev<Abi> y);
+template <class Abi> ldoublev<Abi> fmin(ldoublev<Abi> x, ldoublev<Abi> y);
+
+template <class Abi> floatv<Abi> fma(floatv<Abi> x, floatv<Abi> y, floatv<Abi> z);
+template <class Abi> doublev<Abi> fma(doublev<Abi> x, doublev<Abi> y, doublev<Abi> z);
+template <class Abi> ldoublev<Abi> fma(ldoublev<Abi> x, ldoublev<Abi> y, ldoublev<Abi> z);
+
+template <class Abi> samesize<int, floatv<Abi>> fpclassify(floatv<Abi> x);
+template <class Abi> samesize<int, doublev<Abi>> fpclassify(doublev<Abi> x);
+template <class Abi> samesize<int, ldoublev<Abi>> fpclassify(ldoublev<Abi> x);
+
+template <class Abi> simd_mask<float, Abi> isfinite(floatv<Abi> x);
+template <class Abi> simd_mask<double, Abi> isfinite(doublev<Abi> x);
+template <class Abi> simd_mask<long double, Abi> isfinite(ldoublev<Abi> x);
+
+template <class Abi> simd_mask<float, Abi> isinf(floatv<Abi> x);
+template <class Abi> simd_mask<double, Abi> isinf(doublev<Abi> x);
+template <class Abi> simd_mask<long double, Abi> isinf(ldoublev<Abi> x);
+
+template <class Abi> simd_mask<float, Abi> isnan(floatv<Abi> x);
+template <class Abi> simd_mask<double, Abi> isnan(doublev<Abi> x);
+template <class Abi> simd_mask<long double, Abi> isnan(ldoublev<Abi> x);
+
+template <class Abi> simd_mask<float, Abi> isnormal(floatv<Abi> x);
+template <class Abi> simd_mask<double, Abi> isnormal(doublev<Abi> x);
+template <class Abi> simd_mask<long double, Abi> isnormal(ldoublev<Abi> x);
+
+template <class Abi> simd_mask<float, Abi> signbit(floatv<Abi> x);
+template <class Abi> simd_mask<double, Abi> signbit(doublev<Abi> x);
+template <class Abi> simd_mask<long double, Abi> signbit(ldoublev<Abi> x);
+
+template <class Abi> simd_mask<float, Abi> isgreater(floatv<Abi> x, floatv<Abi> y);
+template <class Abi> simd_mask<double, Abi> isgreater(doublev<Abi> x, doublev<Abi> y);
+template <class Abi> simd_mask<long double, Abi> isgreater(ldoublev<Abi> x, ldoublev<Abi> y);
+
+template <class Abi> simd_mask<float, Abi> isgreaterequal(floatv<Abi> x, floatv<Abi> y);
+template <class Abi> simd_mask<double, Abi> isgreaterequal(doublev<Abi> x, doublev<Abi> y);
+template <class Abi> simd_mask<long double, Abi> isgreaterequal(ldoublev<Abi> x, ldoublev<Abi> y);
+
+template <class Abi> simd_mask<float, Abi> isless(floatv<Abi> x, floatv<Abi> y);
+template <class Abi> simd_mask<double, Abi> isless(doublev<Abi> x, doublev<Abi> y);
+template <class Abi> simd_mask<long double, Abi> isless(ldoublev<Abi> x, ldoublev<Abi> y);
+
+template <class Abi> simd_mask<float, Abi> islessequal(floatv<Abi> x, floatv<Abi> y);
+template <class Abi> simd_mask<double, Abi> islessequal(doublev<Abi> x, doublev<Abi> y);
+template <class Abi> simd_mask<long double, Abi> islessequal(ldoublev<Abi> x, ldoublev<Abi> y);
+
+template <class Abi> simd_mask<float, Abi> islessgreater(floatv<Abi> x, floatv<Abi> y);
+template <class Abi> simd_mask<double, Abi> islessgreater(doublev<Abi> x, doublev<Abi> y);
+template <class Abi> simd_mask<long double, Abi> islessgreater(ldoublev<Abi> x, ldoublev<Abi> y);
+
+template <class Abi> simd_mask<float, Abi> isunordered(floatv<Abi> x, floatv<Abi> y);
+template <class Abi> simd_mask<double, Abi> isunordered(doublev<Abi> x, doublev<Abi> y);
+template <class Abi> simd_mask<long double, Abi> isunordered(ldoublev<Abi> x, ldoublev<Abi> y);
+
+template <class V> struct simd_div_t { V quot, rem; };
+template <class Abi> simd_div_t<scharv<Abi>> div(scharv<Abi> numer, scharv<Abi> denom);
+template <class Abi> simd_div_t<shortv<Abi>> div(shortv<Abi> numer, shortv<Abi> denom);
+template <class Abi> simd_div_t<intv<Abi>> div(intv<Abi> numer, intv<Abi> denom);
+template <class Abi> simd_div_t<longv<Abi>> div(longv<Abi> numer, longv<Abi> denom);
+template <class Abi> simd_div_t<llongv<Abi>> div(llongv<Abi> numer, llongv<Abi> denom);
+
+// [simd.mask.class]
+template <class T, class Abi>
+class simd_mask {
+public:
+  using value_type = bool;
+  using reference = see below;
+  using simd_type = simd<T, Abi>;
+  using abi_type = Abi;
+  static constexpr size_t size() noexcept;
+  simd_mask() = default;
+
+  // broadcast constructor
+  explicit simd_mask(value_type) noexcept;
+
+  // implicit type conversion constructor
+  template <class U> simd_mask(const simd_mask<U, simd_abi::fixed_size<size()>>&) noexcept;
+
+  // load constructor
+  template <class Flags> simd_mask(const value_type* mem, Flags);
+
+  // loads [simd.mask.copy]
+  template <class Flags> void copy_from(const value_type* mem, Flags);
+  template <class Flags> void copy_to(value_type* mem, Flags) const;
+
+  // scalar access [simd.mask.subscr]
+  reference operator[](size_t);
+  value_type operator[](size_t) const;
+
+  // unary operators [simd.mask.unary]
+  simd_mask operator!() const noexcept;
+
+  // simd_mask binary operators [simd.mask.binary]
+  friend simd_mask operator&&(const simd_mask&, const simd_mask&) noexcept;
+  friend simd_mask operator||(const simd_mask&, const simd_mask&) noexcept;
+  friend simd_mask operator& (const simd_mask&, const simd_mask&) noexcept;
+  friend simd_mask operator| (const simd_mask&, const simd_mask&) noexcept;
+  friend simd_mask operator^ (const simd_mask&, const simd_mask&) noexcept;
+
+  // simd_mask compound assignment [simd.mask.cassign]
+  friend simd_mask& operator&=(simd_mask&, const simd_mask&) noexcept;
+  friend simd_mask& operator|=(simd_mask&, const simd_mask&) noexcept;
+  friend simd_mask& operator^=(simd_mask&, const simd_mask&) noexcept;
+
+  // simd_mask compares [simd.mask.comparison]
+  friend simd_mask operator==(const simd_mask&, const simd_mask&) noexcept;
+  friend simd_mask operator!=(const simd_mask&, const simd_mask&) noexcept;
+};
+
+} // parallelism_v2
+} // std::experimental
+
+*/
+
+#include <experimental/__config>
+#include <array>
+#include <cstddef>
+#include <functional>
+
+#if !defined(_LIBCPP_HAS_NO_PRAGMA_SYSTEM_HEADER)
+#pragma GCC system_header
+#endif
+
+_LIBCPP_BEGIN_NAMESPACE_EXPERIMENTAL_SIMD
+
+enum class _StorageKind {
+  _Scalar,
+  _Array,
+};
+
+template <_StorageKind __kind, int _Np>
+struct __simd_abi {};
+
+template <class _Tp, class _Abi>
+struct __simd_storage_traits {};
+
+template <class _Tp, int __num_element>
+struct __simd_storage_traits<_Tp,
+                             __simd_abi<_StorageKind::_Array, __num_element>> {
+  using type = std::array<_Tp, __num_element>;
+};
+
+template <class _Tp>
+struct __simd_storage_traits<_Tp, __simd_abi<_StorageKind::_Scalar, 1>> {
+  using type = _Tp;
+};
+
+template <class _To, class _From>
+constexpr decltype(_To{std::declval<_From>()}, true)
+__is_non_narrowing_convertible_impl(_From) {
+  return true;
+}
+
+template <class _To>
+constexpr bool __is_non_narrowing_convertible_impl(...) {
+  return false;
+}
+
+template <class _From, class _To>
+constexpr typename std::enable_if<std::is_arithmetic<_To>::value &&
+                                      std::is_arithmetic<_From>::value,
+                                  bool>::type
+__is_non_narrowing_arithmetic_convertible() {
+  return __is_non_narrowing_convertible_impl<_To>(_From{});
+}
+
+template <class _From, class _To>
+constexpr typename std::enable_if<!(std::is_arithmetic<_To>::value &&
+                                    std::is_arithmetic<_From>::value),
+                                  bool>::type
+__is_non_narrowing_arithmetic_convertible() {
+  return false;
+}
+
+template <class _Tp>
+constexpr _Tp __variadic_sum() {
+  return _Tp{};
+}
+
+template <class _Tp, class _Up, class... _Args>
+constexpr _Tp __variadic_sum(_Up __first, _Args... __rest) {
+  return static_cast<_Tp>(__first) + __variadic_sum<_Tp>(__rest...);
+}
+
+_LIBCPP_END_NAMESPACE_EXPERIMENTAL_SIMD
+_LIBCPP_BEGIN_NAMESPACE_EXPERIMENTAL_SIMD_ABI
+
+using scalar = __simd_abi<_StorageKind::_Scalar, 1>;
+
+template <int _Np>
+using fixed_size = __simd_abi<_StorageKind::_Array, _Np>;
+
+#if _LIBCPP_STD_VER > 14 && !defined(_LIBCPP_HAS_NO_VARIABLE_TEMPLATES)
+template <class _Tp>
+_LIBCPP_INLINE_VAR constexpr int max_fixed_size = 32;
+#endif
+template <class _Tp>
+using compatible = fixed_size<16 / sizeof(_Tp)>;
+template <class _Tp>
+using native = compatible<_Tp>;
+
+_LIBCPP_END_NAMESPACE_EXPERIMENTAL_SIMD_ABI
+_LIBCPP_BEGIN_NAMESPACE_EXPERIMENTAL_SIMD
+
+template <class _Tp, class _Abi = simd_abi::compatible<_Tp>>
+class simd;
+template <class _Tp, class _Abi = simd_abi::compatible<_Tp>>
+class simd_mask;
+
+struct element_aligned_tag {};
+struct vector_aligned_tag {};
+template <size_t>
+struct overaligned_tag {};
+#if _LIBCPP_STD_VER > 14
+_LIBCPP_INLINE_VAR constexpr element_aligned_tag element_aligned{};
+_LIBCPP_INLINE_VAR constexpr vector_aligned_tag vector_aligned{};
+#if !defined(_LIBCPP_HAS_NO_VARIABLE_TEMPLATES)
+template <size_t _Np>
+_LIBCPP_INLINE_VAR constexpr overaligned_tag<_Np> overaligned{};
+#endif
+#endif
+
+// traits [simd.traits]
+template <class _Tp>
+struct is_abi_tag : std::integral_constant<bool, false> {};
+
+template <_StorageKind __kind, int _Np>
+struct is_abi_tag<__simd_abi<__kind, _Np>>
+    : std::integral_constant<bool, true> {};
+
+template <class _Tp>
+struct is_simd : std::integral_constant<bool, false> {};
+
+template <class _Tp, class _Abi>
+struct is_simd<simd<_Tp, _Abi>> : std::integral_constant<bool, true> {};
+
+template <class _Tp>
+struct is_simd_mask : std::integral_constant<bool, false> {};
+
+template <class _Tp, class _Abi>
+struct is_simd_mask<simd_mask<_Tp, _Abi>> : std::integral_constant<bool, true> {
+};
+
+template <class _Tp>
+struct is_simd_flag_type : std::integral_constant<bool, false> {};
+
+template <>
+struct is_simd_flag_type<element_aligned_tag>
+    : std::integral_constant<bool, true> {};
+
+template <>
+struct is_simd_flag_type<vector_aligned_tag>
+    : std::integral_constant<bool, true> {};
+
+template <size_t _Align>
+struct is_simd_flag_type<overaligned_tag<_Align>>
+    : std::integral_constant<bool, true> {};
+
+#if _LIBCPP_STD_VER > 14 && !defined(_LIBCPP_HAS_NO_VARIABLE_TEMPLATES)
+template <class _Tp>
+_LIBCPP_INLINE_VAR constexpr bool is_abi_tag_v = is_abi_tag<_Tp>::value;
+template <class _Tp>
+_LIBCPP_INLINE_VAR constexpr bool is_simd_v = is_simd<_Tp>::value;
+template <class _Tp>
+_LIBCPP_INLINE_VAR constexpr bool is_simd_mask_v = is_simd_mask<_Tp>::value;
+template <class _Tp>
+_LIBCPP_INLINE_VAR constexpr bool is_simd_flag_type_v =
+    is_simd_flag_type<_Tp>::value;
+#endif
+template <class _Tp, size_t _Np>
+struct abi_for_size {
+  using type = simd_abi::fixed_size<_Np>;
+};
+template <class _Tp, size_t _Np>
+using abi_for_size_t = typename abi_for_size<_Tp, _Np>::type;
+
+template <class _Tp, class _Abi = simd_abi::compatible<_Tp>>
+struct simd_size;
+
+template <class _Tp, _StorageKind __kind, int _Np>
+struct simd_size<_Tp, __simd_abi<__kind, _Np>>
+    : std::integral_constant<size_t, _Np> {
+  static_assert(
+      std::is_arithmetic<_Tp>::value &&
+          !std::is_same<typename std::remove_const<_Tp>::type, bool>::value,
+      "Element type should be vectorizable");
+};
+
+template <class _Tp, class _Up = typename _Tp::value_type>
+struct memory_alignment;
+
+#if _LIBCPP_STD_VER > 14 && !defined(_LIBCPP_HAS_NO_VARIABLE_TEMPLATES)
+template <class _Tp, class _Abi = simd_abi::compatible<_Tp>>
+_LIBCPP_INLINE_VAR constexpr size_t simd_size_v = simd_size<_Tp, _Abi>::value;
+
+template <class _Tp, class _Up = typename _Tp::value_type>
+_LIBCPP_INLINE_VAR constexpr size_t memory_alignment_v =
+    memory_alignment<_Tp, _Up>::value;
+#endif
+
+// class template simd [simd.class]
+template <class _Tp>
+using native_simd = simd<_Tp, simd_abi::native<_Tp>>;
+template <class _Tp, int _Np>
+using fixed_size_simd = simd<_Tp, simd_abi::fixed_size<_Np>>;
+
+// class template simd_mask [simd.mask.class]
+template <class _Tp>
+using native_simd_mask = simd_mask<_Tp, simd_abi::native<_Tp>>;
+
+template <class _Tp, int _Np>
+using fixed_size_simd_mask = simd_mask<_Tp, simd_abi::fixed_size<_Np>>;
+
+// casts [simd.casts]
+template <class _Tp>
+struct __static_simd_cast_traits {
+  template <class _Up, class _Abi>
+  static simd<_Tp, _Abi> __apply(const simd<_Up, _Abi>& __v);
+};
+
+template <class _Tp, class _NewAbi>
+struct __static_simd_cast_traits<simd<_Tp, _NewAbi>> {
+  template <class _Up, class _Abi>
+  static typename std::enable_if<simd<_Up, _Abi>::size() ==
+                                     simd<_Tp, _NewAbi>::size(),
+                                 simd<_Tp, _NewAbi>>::type
+  __apply(const simd<_Up, _Abi>& __v);
+};
+
+template <class _Tp>
+struct __simd_cast_traits {
+  template <class _Up, class _Abi>
+  static typename std::enable_if<
+      __is_non_narrowing_arithmetic_convertible<_Up, _Tp>(),
+      simd<_Tp, _Abi>>::type
+  __apply(const simd<_Up, _Abi>& __v);
+};
+
+template <class _Tp, class _NewAbi>
+struct __simd_cast_traits<simd<_Tp, _NewAbi>> {
+  template <class _Up, class _Abi>
+  static typename std::enable_if<
+      __is_non_narrowing_arithmetic_convertible<_Up, _Tp>() &&
+          simd<_Up, _Abi>::size() == simd<_Tp, _NewAbi>::size(),
+      simd<_Tp, _NewAbi>>::type
+  __apply(const simd<_Up, _Abi>& __v);
+};
+
+template <class _Tp, class _Up, class _Abi>
+auto simd_cast(const simd<_Up, _Abi>& __v)
+    -> decltype(__simd_cast_traits<_Tp>::__apply(__v)) {
+  return __simd_cast_traits<_Tp>::__apply(__v);
+}
+
+template <class _Tp, class _Up, class _Abi>
+auto static_simd_cast(const simd<_Up, _Abi>& __v)
+    -> decltype(__static_simd_cast_traits<_Tp>::__apply(__v)) {
+  return __static_simd_cast_traits<_Tp>::__apply(__v);
+}
+
+template <class _Tp, class _Abi>
+fixed_size_simd<_Tp, simd_size<_Tp, _Abi>::value>
+to_fixed_size(const simd<_Tp, _Abi>&) noexcept;
+
+template <class _Tp, class _Abi>
+fixed_size_simd_mask<_Tp, simd_size<_Tp, _Abi>::value>
+to_fixed_size(const simd_mask<_Tp, _Abi>&) noexcept;
+
+template <class _Tp, size_t _Np>
+native_simd<_Tp> to_native(const fixed_size_simd<_Tp, _Np>&) noexcept;
+
+template <class _Tp, size_t _Np>
+native_simd_mask<_Tp> to_native(const fixed_size_simd_mask<_Tp, _Np>&) noexcept;
+
+template <class _Tp, size_t _Np>
+simd<_Tp> to_compatible(const fixed_size_simd<_Tp, _Np>&) noexcept;
+
+template <class _Tp, size_t _Np>
+simd_mask<_Tp> to_compatible(const fixed_size_simd_mask<_Tp, _Np>&) noexcept;
+
+template <size_t... __sizes, class _Tp, class _Abi>
+tuple<simd<_Tp, abi_for_size_t<_Tp, __sizes>>...> split(const simd<_Tp, _Abi>&);
+
+template <size_t... __sizes, class _Tp, class _Abi>
+tuple<simd_mask<_Tp, abi_for_size_t<_Tp, __sizes>>...>
+split(const simd_mask<_Tp, _Abi>&);
+
+template <class _SimdType, class _Abi>
+array<_SimdType, simd_size<typename _SimdType::value_type, _Abi>::value /
+                     _SimdType::size()>
+split(const simd<typename _SimdType::value_type, _Abi>&);
+
+template <class _SimdType, class _Abi>
+array<_SimdType, simd_size<typename _SimdType::value_type, _Abi>::value /
+                     _SimdType::size()>
+split(const simd_mask<typename _SimdType::value_type, _Abi>&);
+
+template <class _Tp, class... _Abis>
+simd<_Tp, abi_for_size_t<_Tp, __variadic_sum(simd_size<_Tp, _Abis>::value...)>>
+concat(const simd<_Tp, _Abis>&...);
+
+template <class _Tp, class... _Abis>
+simd_mask<_Tp,
+          abi_for_size_t<_Tp, __variadic_sum(simd_size<_Tp, _Abis>::value...)>>
+concat(const simd_mask<_Tp, _Abis>&...);
+
+// reductions [simd.mask.reductions]
+template <class _Tp, class _Abi>
+bool all_of(const simd_mask<_Tp, _Abi>&) noexcept;
+template <class _Tp, class _Abi>
+bool any_of(const simd_mask<_Tp, _Abi>&) noexcept;
+template <class _Tp, class _Abi>
+bool none_of(const simd_mask<_Tp, _Abi>&) noexcept;
+template <class _Tp, class _Abi>
+bool some_of(const simd_mask<_Tp, _Abi>&) noexcept;
+template <class _Tp, class _Abi>
+int popcount(const simd_mask<_Tp, _Abi>&) noexcept;
+template <class _Tp, class _Abi>
+int find_first_set(const simd_mask<_Tp, _Abi>&);
+template <class _Tp, class _Abi>
+int find_last_set(const simd_mask<_Tp, _Abi>&);
+bool all_of(bool) noexcept;
+bool any_of(bool) noexcept;
+bool none_of(bool) noexcept;
+bool some_of(bool) noexcept;
+int popcount(bool) noexcept;
+int find_first_set(bool) noexcept;
+int find_last_set(bool) noexcept;
+
+// masked assignment [simd.whereexpr]
+template <class _MaskType, class _Tp>
+class const_where_expression;
+template <class _MaskType, class _Tp>
+class where_expression;
+
+// masked assignment [simd.mask.where]
+template <class _Tp>
+struct __nodeduce {
+  using type = _Tp;
+};
+
+template <class _Tp, class _Abi>
+where_expression<simd_mask<_Tp, _Abi>, simd<_Tp, _Abi>>
+where(const typename simd<_Tp, _Abi>::mask_type&, simd<_Tp, _Abi>&) noexcept;
+
+template <class _Tp, class _Abi>
+const_where_expression<simd_mask<_Tp, _Abi>, const simd<_Tp, _Abi>>
+where(const typename simd<_Tp, _Abi>::mask_type&,
+      const simd<_Tp, _Abi>&) noexcept;
+
+template <class _Tp, class _Abi>
+where_expression<simd_mask<_Tp, _Abi>, simd_mask<_Tp, _Abi>>
+where(const typename __nodeduce<simd_mask<_Tp, _Abi>>::type&,
+      simd_mask<_Tp, _Abi>&) noexcept;
+
+template <class _Tp, class _Abi>
+const_where_expression<simd_mask<_Tp, _Abi>, const simd_mask<_Tp, _Abi>>
+where(const typename __nodeduce<simd_mask<_Tp, _Abi>>::type&,
+      const simd_mask<_Tp, _Abi>&) noexcept;
+
+template <class _Tp>
+where_expression<bool, _Tp> where(bool, _Tp&) noexcept;
+
+template <class _Tp>
+const_where_expression<bool, const _Tp> where(bool, const _Tp&) noexcept;
+
+// reductions [simd.reductions]
+template <class _Tp, class _Abi, class _BinaryOp = std::plus<_Tp>>
+_Tp reduce(const simd<_Tp, _Abi>&, _BinaryOp = _BinaryOp());
+
+template <class _MaskType, class _SimdType, class _BinaryOp>
+typename _SimdType::value_type
+reduce(const const_where_expression<_MaskType, _SimdType>&,
+       typename _SimdType::value_type neutral_element, _BinaryOp binary_op);
+
+template <class _MaskType, class _SimdType>
+typename _SimdType::value_type
+reduce(const const_where_expression<_MaskType, _SimdType>&,
+       plus<typename _SimdType::value_type> binary_op = {});
+
+template <class _MaskType, class _SimdType>
+typename _SimdType::value_type
+reduce(const const_where_expression<_MaskType, _SimdType>&,
+       multiplies<typename _SimdType::value_type> binary_op);
+
+template <class _MaskType, class _SimdType>
+typename _SimdType::value_type
+reduce(const const_where_expression<_MaskType, _SimdType>&,
+       bit_and<typename _SimdType::value_type> binary_op);
+
+template <class _MaskType, class _SimdType>
+typename _SimdType::value_type
+reduce(const const_where_expression<_MaskType, _SimdType>&,
+       bit_or<typename _SimdType::value_type> binary_op);
+
+template <class _MaskType, class _SimdType>
+typename _SimdType::value_type
+reduce(const const_where_expression<_MaskType, _SimdType>&,
+       bit_xor<typename _SimdType::value_type> binary_op);
+
+template <class _Tp, class _Abi>
+_Tp hmin(const simd<_Tp, _Abi>&);
+template <class _MaskType, class _SimdType>
+typename _SimdType::value_type
+hmin(const const_where_expression<_MaskType, _SimdType>&);
+template <class _Tp, class _Abi>
+_Tp hmax(const simd<_Tp, _Abi>&);
+template <class _MaskType, class _SimdType>
+typename _SimdType::value_type
+hmax(const const_where_expression<_MaskType, _SimdType>&);
+
+// algorithms [simd.alg]
+template <class _Tp, class _Abi>
+simd<_Tp, _Abi> min(const simd<_Tp, _Abi>&, const simd<_Tp, _Abi>&) noexcept;
+
+template <class _Tp, class _Abi>
+simd<_Tp, _Abi> max(const simd<_Tp, _Abi>&, const simd<_Tp, _Abi>&) noexcept;
+
+template <class _Tp, class _Abi>
+std::pair<simd<_Tp, _Abi>, simd<_Tp, _Abi>>
+minmax(const simd<_Tp, _Abi>&, const simd<_Tp, _Abi>&) noexcept;
+
+template <class _Tp, class _Abi>
+simd<_Tp, _Abi> clamp(const simd<_Tp, _Abi>&, const simd<_Tp, _Abi>&,
+                      const simd<_Tp, _Abi>&);
+
+// [simd.whereexpr]
+// TODO implement where expressions.
+template <class _MaskType, class _Tp>
+class const_where_expression {
+public:
+  const_where_expression(const const_where_expression&) = delete;
+  const_where_expression& operator=(const const_where_expression&) = delete;
+  typename remove_const<_Tp>::type operator-() const&&;
+  template <class _Up, class _Flags>
+  void copy_to(_Up*, _Flags) const&&;
+};
+
+template <class _MaskType, class _Tp>
+class where_expression : public const_where_expression<_MaskType, _Tp> {
+public:
+  where_expression(const where_expression&) = delete;
+  where_expression& operator=(const where_expression&) = delete;
+  template <class _Up>
+  void operator=(_Up&&);
+  template <class _Up>
+  void operator+=(_Up&&);
+  template <class _Up>
+  void operator-=(_Up&&);
+  template <class _Up>
+  void operator*=(_Up&&);
+  template <class _Up>
+  void operator/=(_Up&&);
+  template <class _Up>
+  void operator%=(_Up&&);
+  template <class _Up>
+  void operator&=(_Up&&);
+  template <class _Up>
+  void operator|=(_Up&&);
+  template <class _Up>
+  void operator^=(_Up&&);
+  template <class _Up>
+  void operator<<=(_Up&&);
+  template <class _Up>
+  void operator>>=(_Up&&);
+  void operator++();
+  void operator++(int);
+  void operator--();
+  void operator--(int);
+  template <class _Up, class _Flags>
+  void copy_from(const _Up*, _Flags);
+};
+
+// [simd.class]
+// TODO: implement simd
+template <class _Tp, class _Abi>
+class simd {
+private:
+  template <class _Up>
+  static constexpr bool __can_broadcast() {
+    return (std::is_arithmetic<_Up>::value &&
+            __is_non_narrowing_arithmetic_convertible<_Up, _Tp>()) ||
+           (!std::is_arithmetic<_Up>::value &&
+            std::is_convertible<_Up, _Tp>::value) ||
+           std::is_same<typename std::remove_const<_Up>::type, int>::value ||
+           (std::is_same<typename std::remove_const<_Up>::type,
+                         unsigned int>::value &&
+            std::is_unsigned<_Tp>::value);
+  }
+
+public:
+  using value_type = _Tp;
+  // TODO: this is strawman implementation. Turn it into a proxy type.
+  using reference = _Tp&;
+  using mask_type = simd_mask<_Tp, _Abi>;
+
+  using abi_type = _Abi;
+
+  static constexpr size_t size() noexcept {
+    return simd_size<_Tp, _Abi>::value;
+  }
+
+  simd() = default;
+
+  // implicit type conversion constructor
+  template <class _Up,
+            class = typename std::enable_if<
+                std::is_same<_Abi, simd_abi::fixed_size<size()>>::value &&
+                __is_non_narrowing_arithmetic_convertible<_Up, _Tp>()>::type>
+  simd(const simd<_Up, simd_abi::fixed_size<size()>>&) {}
+
+  // implicit broadcast constructor
+  template <class _Up,
+            class = typename std::enable_if<__can_broadcast<_Up>()>::type>
+  simd(_Up&&);
+
+  // generator constructor
+  // TODO: for now only check for the index 0. This is because C++11 doesn't
+  // have index_sequence, and it's hard to check for all indicies without using
+  // index_sequence.
+  template <class _Generator,
+            int = decltype(simd(std::declval<_Generator>()(
+                               std::integral_constant<size_t, 0>())),
+                           int())()>
+  explicit simd(_Generator&&);
+
+  // load constructor
+  template <class _Up, class _Flags>
+  simd(const _Up*, _Flags);
+
+  // loads [simd.load]
+  template <class _Up, class _Flags>
+  void copy_from(const _Up*, _Flags);
+
+  // stores [simd.store]
+  template <class _Up, class _Flags>
+  void copy_to(_Up*, _Flags) const;
+
+  // scalar access [simd.subscr]
+  reference operator[](size_t);
+  value_type operator[](size_t) const;
+
+  // unary operators [simd.unary]
+  simd& operator++();
+  simd operator++(int);
+  simd& operator--();
+  simd operator--(int);
+  mask_type operator!() const;
+  simd operator~() const;
+  simd operator+() const;
+  simd operator-() const;
+
+  // binary operators [simd.binary]
+  friend simd operator+(const simd&, const simd&);
+  friend simd operator-(const simd&, const simd&);
+  friend simd operator*(const simd&, const simd&);
+  friend simd operator/(const simd&, const simd&);
+  friend simd operator%(const simd&, const simd&);
+  friend simd operator&(const simd&, const simd&);
+  friend simd operator|(const simd&, const simd&);
+  friend simd operator^(const simd&, const simd&);
+  friend simd operator<<(const simd&, const simd&);
+  friend simd operator>>(const simd&, const simd&);
+  friend simd operator<<(const simd&, int);
+  friend simd operator>>(const simd&, int);
+
+  // compound assignment [simd.cassign]
+  friend simd& operator+=(simd&, const simd&);
+  friend simd& operator-=(simd&, const simd&);
+  friend simd& operator*=(simd&, const simd&);
+  friend simd& operator/=(simd&, const simd&);
+  friend simd& operator%=(simd&, const simd&);
+
+  friend simd& operator&=(simd&, const simd&);
+  friend simd& operator|=(simd&, const simd&);
+  friend simd& operator^=(simd&, const simd&);
+  friend simd& operator<<=(simd&, const simd&);
+  friend simd& operator>>=(simd&, const simd&);
+  friend simd& operator<<=(simd&, int);
+  friend simd& operator>>=(simd&, int);
+
+  // compares [simd.comparison]
+  friend mask_type operator==(const simd&, const simd&);
+  friend mask_type operator!=(const simd&, const simd&);
+  friend mask_type operator>=(const simd&, const simd&);
+  friend mask_type operator<=(const simd&, const simd&);
+  friend mask_type operator>(const simd&, const simd&);
+  friend mask_type operator<(const simd&, const simd&);
+};
+
+// [simd.mask.class]
+template <class _Tp, class _Abi>
+// TODO: implement simd_mask
+class simd_mask {
+public:
+  using value_type = bool;
+  // TODO: this is strawman implementation. Turn it into a proxy type.
+  using reference = bool&;
+  using simd_type = simd<_Tp, _Abi>;
+  using abi_type = _Abi;
+  static constexpr size_t size() noexcept;
+  simd_mask() = default;
+
+  // broadcast constructor
+  explicit simd_mask(value_type) noexcept;
+
+  // implicit type conversion constructor
+  template <class _Up>
+  simd_mask(const simd_mask<_Up, simd_abi::fixed_size<size()>>&) noexcept;
+
+  // load constructor
+  template <class _Flags>
+  simd_mask(const value_type*, _Flags);
+
+  // loads [simd.mask.copy]
+  template <class _Flags>
+  void copy_from(const value_type*, _Flags);
+  template <class _Flags>
+  void copy_to(value_type*, _Flags) const;
+
+  // scalar access [simd.mask.subscr]
+  reference operator[](size_t);
+  value_type operator[](size_t) const;
+
+  // unary operators [simd.mask.unary]
+  simd_mask operator!() const noexcept;
+
+  // simd_mask binary operators [simd.mask.binary]
+  friend simd_mask operator&&(const simd_mask&, const simd_mask&) noexcept;
+  friend simd_mask operator||(const simd_mask&, const simd_mask&) noexcept;
+  friend simd_mask operator&(const simd_mask&, const simd_mask&)noexcept;
+  friend simd_mask operator|(const simd_mask&, const simd_mask&) noexcept;
+  friend simd_mask operator^(const simd_mask&, const simd_mask&) noexcept;
+
+  // simd_mask compound assignment [simd.mask.cassign]
+  friend simd_mask& operator&=(simd_mask&, const simd_mask&) noexcept;
+  friend simd_mask& operator|=(simd_mask&, const simd_mask&) noexcept;
+  friend simd_mask& operator^=(simd_mask&, const simd_mask&) noexcept;
+
+  // simd_mask compares [simd.mask.comparison]
+  friend simd_mask operator==(const simd_mask&, const simd_mask&) noexcept;
+  friend simd_mask operator!=(const simd_mask&, const simd_mask&) noexcept;
+};
+
+_LIBCPP_END_NAMESPACE_EXPERIMENTAL_SIMD
+
+#endif /* _LIBCPP_EXPERIMENTAL_SIMD */

libcxx/trunk/include/module.modulemap

module experimental {
     module propagate_const {
       header "experimental/propagate_const"
       export *
     }
     module regex {
       header "experimental/regex"
       export *
     }
+    module simd {
+      header "experimental/simd"
+      export *
+    }
     module set {
       header "experimental/set"
       export *
     }
     module string {
       header "experimental/string"
       export *
     }

libcxx/trunk/test/libcxx/double_include.sh.cpp

 #include <experimental/forward_list>
 #include <experimental/functional>
 #include <experimental/iterator>
 #include <experimental/list>
 #include <experimental/map>
 #include <experimental/memory_resource>
 #include <experimental/propagate_const>
 #include <experimental/regex>
+#include <experimental/simd>
 #include <experimental/set>
 #include <experimental/string>
 #include <experimental/type_traits>
 #include <experimental/unordered_map>
 #include <experimental/unordered_set>
 #include <experimental/utility>
 #include <experimental/vector>
 #endif // __cplusplus >= 201103L
 
 // extended headers
 #include <ext/hash_map>
 #include <ext/hash_set>
 
 #if defined(WITH_MAIN)
 int main() {}
 #endif

libcxx/trunk/test/std/experimental/simd/nothing_to_do.pass.cpp

+//===----------------------------------------------------------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is dual licensed under the MIT and the University of Illinois Open
+// Source Licenses. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include <experimental/simd>
+
+int main() {}

libcxx/trunk/test/std/experimental/simd/simd.casts/simd_cast.pass.cpp

+//===----------------------------------------------------------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is dual licensed under the MIT and the University of Illinois Open
+// Source Licenses. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+// UNSUPPORTED: c++98, c++03
+
+// <experimental/simd>
+//
+// [simd.casts]
+// template <class T, class U, class Abi> see below simd_cast(const simd<U, Abi>&);
+#include <experimental/simd>
+#include <cstdint>
+
+using namespace std::experimental::parallelism_v2;
+
+static_assert(std::is_same<decltype(simd_cast<int32_t>(native_simd<int32_t>())),
+                           native_simd<int32_t>>::value,
+              "");
+
+static_assert(
+    std::is_same<decltype(simd_cast<int64_t>(fixed_size_simd<int32_t, 4>())),
+                 fixed_size_simd<int64_t, 4>>::value,
+    "");
+
+static_assert(std::is_same<decltype(simd_cast<fixed_size_simd<int64_t, 1>>(
+                               simd<int32_t, simd_abi::scalar>())),
+                           fixed_size_simd<int64_t, 1>>::value,
+              "");
+
+static_assert(std::is_same<decltype(simd_cast<simd<int64_t, simd_abi::scalar>>(
+                               fixed_size_simd<int32_t, 1>())),
+                           simd<int64_t, simd_abi::scalar>>::value,
+              "");
+
+int main() {}

libcxx/trunk/test/std/experimental/simd/simd.casts/static_simd_cast.pass.cpp

+//===----------------------------------------------------------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is dual licensed under the MIT and the University of Illinois Open
+// Source Licenses. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+// UNSUPPORTED: c++98, c++03
+
+// <experimental/simd>
+//
+// [simd.casts]
+// template <class T, class U, class Abi> see below static_simd_cast(const simd<U, Abi>&);
+
+#include <experimental/simd>
+#include <cstdint>
+
+using namespace std::experimental::parallelism_v2;
+
+static_assert(
+    std::is_same<decltype(static_simd_cast<float>(native_simd<int>())),
+                 native_simd<float>>::value,
+    "");
+
+static_assert(std::is_same<decltype(static_simd_cast<fixed_size_simd<float, 1>>(
+                               simd<int, simd_abi::scalar>())),
+                           fixed_size_simd<float, 1>>::value,
+              "");
+
+static_assert(
+    std::is_same<decltype(static_simd_cast<simd<float, simd_abi::scalar>>(
+                     fixed_size_simd<int, 1>())),
+                 simd<float, simd_abi::scalar>>::value,
+    "");
+
+int main() {}

libcxx/trunk/test/std/experimental/simd/simd.cons/broadcast.pass.cpp

+//===----------------------------------------------------------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is dual licensed under the MIT and the University of Illinois Open
+// Source Licenses. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+// UNSUPPORTED: c++98, c++03
+
+// <experimental/simd>
+//
+// [simd.class]
+// template <class U> simd(U&& value);
+
+#include <cstdint>
+#include <experimental/simd>
+
+using namespace std::experimental::parallelism_v2;
+
+template <class T, class... Args>
+auto not_supported_native_simd_ctor(Args&&... args)
+    -> decltype(native_simd<T>(std::forward<Args>(args)...), void()) = delete;
+
+template <class T>
+void not_supported_native_simd_ctor(...) {}
+
+template <class T, class... Args>
+auto supported_native_simd_ctor(Args&&... args)
+    -> decltype(native_simd<T>(std::forward<Args>(args)...), void()) {}
+
+template <class T>
+void supported_native_simd_ctor(...) = delete;
+
+void compile_narrowing_conversion() {
+  supported_native_simd_ctor<int8_t>(3);
+  supported_native_simd_ctor<int16_t>(3);
+  supported_native_simd_ctor<int32_t>(3);
+  supported_native_simd_ctor<int64_t>(3);
+  supported_native_simd_ctor<uint8_t>(3);
+  supported_native_simd_ctor<uint16_t>(3);
+  supported_native_simd_ctor<uint32_t>(3);
+  supported_native_simd_ctor<uint64_t>(3);
+  supported_native_simd_ctor<float>(3.f);
+  supported_native_simd_ctor<double>(3.);
+  supported_native_simd_ctor<long double>(3.);
+
+  not_supported_native_simd_ctor<float>(3.);
+  not_supported_native_simd_ctor<int8_t>(long(3));
+  not_supported_native_simd_ctor<float>(long(3));
+  not_supported_native_simd_ctor<int>(3.);
+}
+
+int main() {}

libcxx/trunk/test/std/experimental/simd/simd.cons/genertor.pass.cpp

+//===----------------------------------------------------------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is dual licensed under the MIT and the University of Illinois Open
+// Source Licenses. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+// UNSUPPORTED: c++98, c++03
+
+// <experimental/simd>
+//
+// [simd.class]
+// template <class G> explicit simd(G&& gen);
+
+#include <cstdint>
+#include <experimental/simd>
+
+using namespace std::experimental::parallelism_v2;
+
+template <class T, class... Args>
+auto not_supported_native_simd_ctor(Args&&... args)
+    -> decltype(native_simd<T>(std::forward<Args>(args)...), void()) = delete;
+
+template <class T>
+void not_supported_native_simd_ctor(...) {}
+
+template <class T, class... Args>
+auto supported_native_simd_ctor(Args&&... args)
+    -> decltype(native_simd<T>(std::forward<Args>(args)...), void()) {}
+
+template <class T>
+void supported_native_simd_ctor(...) = delete;
+
+void compile_generator() {
+  supported_native_simd_ctor<int>([](int i) { return i; });
+  not_supported_native_simd_ctor<int>([](int i) { return float(i); });
+  not_supported_native_simd_ctor<int>([](intptr_t i) { return (int*)(i); });
+  not_supported_native_simd_ctor<int>([](int* i) { return i; });
+}
+
+int main() {}

libcxx/trunk/test/std/experimental/simd/simd.traits/abi_for_size.pass.cpp

+//===----------------------------------------------------------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is dual licensed under the MIT and the University of Illinois Open
+// Source Licenses. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+// UNSUPPORTED: c++98, c++03
+
+// <experimental/simd>
+//
+// [simd.traits]
+// template <class T, size_t N> struct abi_for_size { using type = see below ; };
+// template <class T, size_t N> using abi_for_size_t = typename abi_for_size<T, N>::type;
+
+#include <cstdint>
+#include <experimental/simd>
+
+using namespace std::experimental::parallelism_v2;
+
+static_assert(std::is_same<typename abi_for_size<int, 4>::type,
+                           simd_abi::fixed_size<4>>::value,
+              "");
+
+static_assert(
+    std::is_same<abi_for_size_t<int, 4>, simd_abi::fixed_size<4>>::value, "");
+
+int main() {}

libcxx/trunk/test/std/experimental/simd/simd.traits/is_abi_tag.pass.cpp

+//===----------------------------------------------------------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is dual licensed under the MIT and the University of Illinois Open
+// Source Licenses. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+// UNSUPPORTED: c++98, c++03
+
+// <experimental/simd>
+//
+// [simd.traits]
+// template <class T> struct is_abi_tag;
+// template <class T> inline constexpr bool is_abi_tag_v = is_abi_tag<T>::value;
+
+#include <cstdint>
+#include <experimental/simd>
+#include "test_macros.h"
+
+using namespace std::experimental::parallelism_v2;
+
+struct UserType {};
+
+static_assert( is_abi_tag<simd_abi::native<int8_t>>::value, "");
+static_assert( is_abi_tag<simd_abi::native<int16_t>>::value, "");
+static_assert( is_abi_tag<simd_abi::native<int32_t>>::value, "");
+static_assert( is_abi_tag<simd_abi::native<int64_t>>::value, "");
+static_assert( is_abi_tag<simd_abi::native<uint8_t>>::value, "");
+static_assert( is_abi_tag<simd_abi::native<uint16_t>>::value, "");
+static_assert( is_abi_tag<simd_abi::native<uint32_t>>::value, "");
+static_assert( is_abi_tag<simd_abi::native<uint64_t>>::value, "");
+static_assert( is_abi_tag<simd_abi::native<float>>::value, "");
+static_assert( is_abi_tag<simd_abi::native<double>>::value, "");
+
+static_assert( is_abi_tag<simd_abi::compatible<int8_t>>::value, "");
+static_assert( is_abi_tag<simd_abi::compatible<int16_t>>::value, "");
+static_assert( is_abi_tag<simd_abi::compatible<int32_t>>::value, "");
+static_assert( is_abi_tag<simd_abi::compatible<int64_t>>::value, "");
+static_assert( is_abi_tag<simd_abi::compatible<uint8_t>>::value, "");
+static_assert( is_abi_tag<simd_abi::compatible<uint16_t>>::value, "");
+static_assert( is_abi_tag<simd_abi::compatible<uint32_t>>::value, "");
+static_assert( is_abi_tag<simd_abi::compatible<uint64_t>>::value, "");
+static_assert( is_abi_tag<simd_abi::compatible<float>>::value, "");
+static_assert( is_abi_tag<simd_abi::compatible<double>>::value, "");
+
+static_assert( is_abi_tag<simd_abi::scalar>::value, "");
+static_assert(!std::is_same<simd_abi::scalar, simd_abi::fixed_size<1>>::value,
+              "");
+
+static_assert( is_abi_tag<simd_abi::fixed_size<1>>::value, "");
+static_assert( is_abi_tag<simd_abi::fixed_size<2>>::value, "");
+static_assert( is_abi_tag<simd_abi::fixed_size<3>>::value, "");
+static_assert( is_abi_tag<simd_abi::fixed_size<4>>::value, "");
+static_assert( is_abi_tag<simd_abi::fixed_size<5>>::value, "");
+static_assert( is_abi_tag<simd_abi::fixed_size<32>>::value, "");
+
+static_assert(!is_abi_tag<void>::value, "");
+static_assert(!is_abi_tag<int>::value, "");
+static_assert(!is_abi_tag<float>::value, "");
+static_assert(!is_abi_tag<UserType>::value, "");
+static_assert(!is_abi_tag<simd<int>>::value, "");
+static_assert(!is_abi_tag<simd<float>>::value, "");
+static_assert(!is_abi_tag<simd_mask<int>>::value, "");
+static_assert(!is_abi_tag<simd_mask<float>>::value, "");
+
+#if TEST_STD_VER > 14 && !defined(_LIBCPP_HAS_NO_VARIABLE_TEMPLATES) &&        \
+    !defined(_LIBCPP_HAS_NO_INLINE_VARIABLES)
+
+static_assert( is_abi_tag_v<simd_abi::native<int8_t>>, "");
+static_assert( is_abi_tag_v<simd_abi::native<int16_t>>, "");
+static_assert( is_abi_tag_v<simd_abi::native<int32_t>>, "");
+static_assert( is_abi_tag_v<simd_abi::native<int64_t>>, "");
+static_assert( is_abi_tag_v<simd_abi::native<uint8_t>>, "");
+static_assert( is_abi_tag_v<simd_abi::native<uint16_t>>, "");
+static_assert( is_abi_tag_v<simd_abi::native<uint32_t>>, "");
+static_assert( is_abi_tag_v<simd_abi::native<uint64_t>>, "");
+static_assert( is_abi_tag_v<simd_abi::native<float>>, "");
+static_assert( is_abi_tag_v<simd_abi::native<double>>, "");
+
+static_assert( is_abi_tag_v<simd_abi::compatible<int8_t>>, "");
+static_assert( is_abi_tag_v<simd_abi::compatible<int16_t>>, "");
+static_assert( is_abi_tag_v<simd_abi::compatible<int32_t>>, "");
+static_assert( is_abi_tag_v<simd_abi::compatible<int64_t>>, "");
+static_assert( is_abi_tag_v<simd_abi::compatible<uint8_t>>, "");
+static_assert( is_abi_tag_v<simd_abi::compatible<uint16_t>>, "");
+static_assert( is_abi_tag_v<simd_abi::compatible<uint32_t>>, "");
+static_assert( is_abi_tag_v<simd_abi::compatible<uint64_t>>, "");
+static_assert( is_abi_tag_v<simd_abi::compatible<float>>, "");
+static_assert( is_abi_tag_v<simd_abi::compatible<double>>, "");
+
+static_assert( is_abi_tag_v<simd_abi::scalar>, "");
+static_assert(!std::is_same<simd_abi::scalar, simd_abi::fixed_size<1>>::value,
+              "");
+
+static_assert( is_abi_tag_v<simd_abi::fixed_size<1>>, "");
+static_assert( is_abi_tag_v<simd_abi::fixed_size<2>>, "");
+static_assert( is_abi_tag_v<simd_abi::fixed_size<3>>, "");
+static_assert( is_abi_tag_v<simd_abi::fixed_size<4>>, "");
+static_assert( is_abi_tag_v<simd_abi::fixed_size<5>>, "");
+static_assert( is_abi_tag_v<simd_abi::fixed_size<32>>, "");
+
+static_assert(!is_abi_tag_v<void>, "");
+static_assert(!is_abi_tag_v<int>, "");
+static_assert(!is_abi_tag_v<float>, "");
+static_assert(!is_abi_tag_v<UserType>, "");
+static_assert(!is_abi_tag_v<simd<int>>, "");
+static_assert(!is_abi_tag_v<simd<float>>, "");
+static_assert(!is_abi_tag_v<simd_mask<int>>, "");
+static_assert(!is_abi_tag_v<simd_mask<float>>, "");
+
+#endif
+
+int main() {}

libcxx/trunk/test/std/experimental/simd/simd.traits/is_simd.pass.cpp

+//===----------------------------------------------------------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is dual licensed under the MIT and the University of Illinois Open
+// Source Licenses. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+// UNSUPPORTED: c++98, c++03
+
+// <experimental/simd>
+//
+// [simd.traits]
+// template <class T> struct is_simd;
+// template <class T> inline constexpr bool is_simd_v = is_simd<T>::value;
+
+#include <cstdint>
+#include <experimental/simd>
+#include "test_macros.h"
+
+using namespace std::experimental::parallelism_v2;
+
+struct UserType {};
+
+static_assert( is_simd<native_simd<int8_t>>::value, "");
+static_assert( is_simd<native_simd<int16_t>>::value, "");
+static_assert( is_simd<native_simd<int32_t>>::value, "");
+static_assert( is_simd<native_simd<int64_t>>::value, "");
+static_assert( is_simd<native_simd<uint8_t>>::value, "");
+static_assert( is_simd<native_simd<uint16_t>>::value, "");
+static_assert( is_simd<native_simd<uint32_t>>::value, "");
+static_assert( is_simd<native_simd<uint64_t>>::value, "");
+static_assert( is_simd<native_simd<float>>::value, "");
+static_assert( is_simd<native_simd<double>>::value, "");
+
+static_assert( is_simd<fixed_size_simd<int8_t, 1>>::value, "");
+static_assert( is_simd<fixed_size_simd<int16_t, 1>>::value, "");
+static_assert( is_simd<fixed_size_simd<int32_t, 1>>::value, "");
+static_assert( is_simd<fixed_size_simd<int64_t, 1>>::value, "");
+static_assert( is_simd<fixed_size_simd<uint8_t, 1>>::value, "");
+static_assert( is_simd<fixed_size_simd<uint16_t, 1>>::value, "");
+static_assert( is_simd<fixed_size_simd<uint32_t, 1>>::value, "");
+static_assert( is_simd<fixed_size_simd<uint64_t, 1>>::value, "");
+static_assert( is_simd<fixed_size_simd<float, 1>>::value, "");
+static_assert( is_simd<fixed_size_simd<double, 1>>::value, "");
+
+static_assert( is_simd<fixed_size_simd<int8_t, 3>>::value, "");
+static_assert( is_simd<fixed_size_simd<int16_t, 3>>::value, "");
+static_assert( is_simd<fixed_size_simd<int32_t, 3>>::value, "");
+static_assert( is_simd<fixed_size_simd<int64_t, 3>>::value, "");
+static_assert( is_simd<fixed_size_simd<uint8_t, 3>>::value, "");
+static_assert( is_simd<fixed_size_simd<uint16_t, 3>>::value, "");
+static_assert( is_simd<fixed_size_simd<uint32_t, 3>>::value, "");
+static_assert( is_simd<fixed_size_simd<uint64_t, 3>>::value, "");
+static_assert( is_simd<fixed_size_simd<float, 3>>::value, "");
+static_assert( is_simd<fixed_size_simd<double, 3>>::value, "");
+
+static_assert( is_simd<fixed_size_simd<int8_t, 32>>::value, "");
+static_assert( is_simd<fixed_size_simd<int16_t, 32>>::value, "");
+static_assert( is_simd<fixed_size_simd<int32_t, 32>>::value, "");
+static_assert( is_simd<fixed_size_simd<int64_t, 32>>::value, "");
+static_assert( is_simd<fixed_size_simd<uint8_t, 32>>::value, "");
+static_assert( is_simd<fixed_size_simd<uint16_t, 32>>::value, "");
+static_assert( is_simd<fixed_size_simd<uint32_t, 32>>::value, "");
+static_assert( is_simd<fixed_size_simd<uint64_t, 32>>::value, "");
+static_assert( is_simd<fixed_size_simd<float, 32>>::value, "");
+static_assert( is_simd<fixed_size_simd<double, 32>>::value, "");
+
+static_assert(!is_simd<void>::value, "");
+static_assert(!is_simd<int>::value, "");
+static_assert(!is_simd<float>::value, "");
+static_assert(!is_simd<simd_mask<int>>::value, "");
+static_assert(!is_simd<simd_mask<float>>::value, "");
+static_assert(!is_simd<UserType>::value, "");
+
+#if TEST_STD_VER > 14 && !defined(_LIBCPP_HAS_NO_VARIABLE_TEMPLATES) &&        \
+    !defined(_LIBCPP_HAS_NO_INLINE_VARIABLES)
+
+static_assert( is_simd_v<native_simd<int8_t>>, "");
+static_assert( is_simd_v<native_simd<int16_t>>, "");
+static_assert( is_simd_v<native_simd<int32_t>>, "");
+static_assert( is_simd_v<native_simd<int64_t>>, "");
+static_assert( is_simd_v<native_simd<uint8_t>>, "");
+static_assert( is_simd_v<native_simd<uint16_t>>, "");
+static_assert( is_simd_v<native_simd<uint32_t>>, "");
+static_assert( is_simd_v<native_simd<uint64_t>>, "");
+static_assert( is_simd_v<native_simd<float>>, "");
+static_assert( is_simd_v<native_simd<double>>, "");
+
+static_assert( is_simd_v<fixed_size_simd<int8_t, 1>>, "");
+static_assert( is_simd_v<fixed_size_simd<int16_t, 1>>, "");
+static_assert( is_simd_v<fixed_size_simd<int32_t, 1>>, "");
+static_assert( is_simd_v<fixed_size_simd<int64_t, 1>>, "");
+static_assert( is_simd_v<fixed_size_simd<uint8_t, 1>>, "");
+static_assert( is_simd_v<fixed_size_simd<uint16_t, 1>>, "");
+static_assert( is_simd_v<fixed_size_simd<uint32_t, 1>>, "");
+static_assert( is_simd_v<fixed_size_simd<uint64_t, 1>>, "");
+static_assert( is_simd_v<fixed_size_simd<float, 1>>, "");
+static_assert( is_simd_v<fixed_size_simd<double, 1>>, "");
+
+static_assert( is_simd_v<fixed_size_simd<int8_t, 3>>, "");
+static_assert( is_simd_v<fixed_size_simd<int16_t, 3>>, "");
+static_assert( is_simd_v<fixed_size_simd<int32_t, 3>>, "");
+static_assert( is_simd_v<fixed_size_simd<int64_t, 3>>, "");
+static_assert( is_simd_v<fixed_size_simd<uint8_t, 3>>, "");
+static_assert( is_simd_v<fixed_size_simd<uint16_t, 3>>, "");
+static_assert( is_simd_v<fixed_size_simd<uint32_t, 3>>, "");
+static_assert( is_simd_v<fixed_size_simd<uint64_t, 3>>, "");
+static_assert( is_simd_v<fixed_size_simd<float, 3>>, "");
+static_assert( is_simd_v<fixed_size_simd<double, 3>>, "");
+
+static_assert( is_simd_v<fixed_size_simd<int8_t, 32>>, "");
+static_assert( is_simd_v<fixed_size_simd<int16_t, 32>>, "");
+static_assert( is_simd_v<fixed_size_simd<int32_t, 32>>, "");
+static_assert( is_simd_v<fixed_size_simd<int64_t, 32>>, "");
+static_assert( is_simd_v<fixed_size_simd<uint8_t, 32>>, "");
+static_assert( is_simd_v<fixed_size_simd<uint16_t, 32>>, "");
+static_assert( is_simd_v<fixed_size_simd<uint32_t, 32>>, "");
+static_assert( is_simd_v<fixed_size_simd<uint64_t, 32>>, "");
+static_assert( is_simd_v<fixed_size_simd<float, 32>>, "");
+static_assert( is_simd_v<fixed_size_simd<double, 32>>, "");
+
+static_assert(!is_simd_v<void>, "");
+static_assert(!is_simd_v<int>, "");
+static_assert(!is_simd_v<float>, "");
+static_assert(!is_simd_v<simd_mask<int>>, "");
+static_assert(!is_simd_v<simd_mask<float>>, "");
+static_assert(!is_simd_v<UserType>, "");
+
+#endif
+
+int main() {}

libcxx/trunk/test/std/experimental/simd/simd.traits/is_simd_flag_type.pass.cpp

+//===----------------------------------------------------------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is dual licensed under the MIT and the University of Illinois Open
+// Source Licenses. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+// UNSUPPORTED: c++98, c++03
+
+// <experimental/simd>
+//
+// [simd.traits]
+// template <class T> struct is_simd_flag_type;
+// template <class T> inline constexpr bool is_simd_flag_type_v = is_simd_flag_type<T>::value;
+
+#include <cstdint>
+#include <experimental/simd>
+#include "test_macros.h"
+
+using namespace std::experimental::parallelism_v2;
+
+struct UserType {};
+
+static_assert( is_simd_flag_type<element_aligned_tag>::value, "");
+static_assert( is_simd_flag_type<vector_aligned_tag>::value, "");
+static_assert( is_simd_flag_type<overaligned_tag<16>>::value, "");
+static_assert( is_simd_flag_type<overaligned_tag<32>>::value, "");
+
+static_assert(!is_simd_flag_type<void>::value, "");
+static_assert(!is_simd_flag_type<int>::value, "");
+static_assert(!is_simd_flag_type<float>::value, "");
+static_assert(!is_simd_flag_type<UserType>::value, "");
+static_assert(!is_simd_flag_type<simd<int8_t>>::value, "");
+static_assert(!is_simd_flag_type<simd_mask<int8_t>>::value, "");
+
+#if TEST_STD_VER > 14 && !defined(_LIBCPP_HAS_NO_VARIABLE_TEMPLATES) &&        \
+    !defined(_LIBCPP_HAS_NO_INLINE_VARIABLES)
+
+static_assert( is_simd_flag_type_v<element_aligned_tag>, "");
+static_assert( is_simd_flag_type_v<vector_aligned_tag>, "");
+static_assert( is_simd_flag_type_v<overaligned_tag<16>>, "");
+static_assert( is_simd_flag_type_v<overaligned_tag<32>>, "");
+
+static_assert(!is_simd_flag_type_v<void>, "");
+static_assert(!is_simd_flag_type_v<int>, "");
+static_assert(!is_simd_flag_type_v<float>, "");
+static_assert(!is_simd_flag_type_v<UserType>, "");
+static_assert(!is_simd_flag_type_v<simd<int8_t>>, "");
+static_assert(!is_simd_flag_type_v<simd_mask<int8_t>>, "");
+
+#endif
+
+int main() {}

libcxx/trunk/test/std/experimental/simd/simd.traits/is_simd_mask.pass.cpp

+//===----------------------------------------------------------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is dual licensed under the MIT and the University of Illinois Open
+// Source Licenses. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+// UNSUPPORTED: c++98, c++03
+
+// <experimental/simd>
+//
+// [simd.traits]
+// template <class T> struct is_simd_mask;
+// template <class T> inline constexpr bool is_simd_mask_v = is_simd_mask<T>::value;
+
+#include <cstdint>
+#include <experimental/simd>
+#include "test_macros.h"
+
+using namespace std::experimental::parallelism_v2;
+
+struct UserType {};
+
+static_assert( is_simd_mask<native_simd_mask<int8_t>>::value, "");
+static_assert( is_simd_mask<native_simd_mask<int16_t>>::value, "");
+static_assert( is_simd_mask<native_simd_mask<int32_t>>::value, "");
+static_assert( is_simd_mask<native_simd_mask<int64_t>>::value, "");
+static_assert( is_simd_mask<native_simd_mask<uint8_t>>::value, "");
+static_assert( is_simd_mask<native_simd_mask<uint16_t>>::value, "");
+static_assert( is_simd_mask<native_simd_mask<uint32_t>>::value, "");
+static_assert( is_simd_mask<native_simd_mask<uint64_t>>::value, "");
+static_assert( is_simd_mask<native_simd_mask<float>>::value, "");
+static_assert( is_simd_mask<native_simd_mask<double>>::value, "");
+
+static_assert( is_simd_mask<fixed_size_simd_mask<int8_t, 1>>::value, "");
+static_assert( is_simd_mask<fixed_size_simd_mask<int16_t, 1>>::value, "");
+static_assert( is_simd_mask<fixed_size_simd_mask<int32_t, 1>>::value, "");
+static_assert( is_simd_mask<fixed_size_simd_mask<int64_t, 1>>::value, "");
+static_assert( is_simd_mask<fixed_size_simd_mask<uint8_t, 1>>::value, "");
+static_assert( is_simd_mask<fixed_size_simd_mask<uint16_t, 1>>::value, "");
+static_assert( is_simd_mask<fixed_size_simd_mask<uint32_t, 1>>::value, "");
+static_assert( is_simd_mask<fixed_size_simd_mask<uint64_t, 1>>::value, "");
+static_assert( is_simd_mask<fixed_size_simd_mask<float, 1>>::value, "");
+static_assert( is_simd_mask<fixed_size_simd_mask<double, 1>>::value, "");
+
+static_assert( is_simd_mask<fixed_size_simd_mask<int8_t, 3>>::value, "");
+static_assert( is_simd_mask<fixed_size_simd_mask<int16_t, 3>>::value, "");
+static_assert( is_simd_mask<fixed_size_simd_mask<int32_t, 3>>::value, "");
+static_assert( is_simd_mask<fixed_size_simd_mask<int64_t, 3>>::value, "");
+static_assert( is_simd_mask<fixed_size_simd_mask<uint8_t, 3>>::value, "");
+static_assert( is_simd_mask<fixed_size_simd_mask<uint16_t, 3>>::value, "");
+static_assert( is_simd_mask<fixed_size_simd_mask<uint32_t, 3>>::value, "");
+static_assert( is_simd_mask<fixed_size_simd_mask<uint64_t, 3>>::value, "");
+static_assert( is_simd_mask<fixed_size_simd_mask<float, 3>>::value, "");
+static_assert( is_simd_mask<fixed_size_simd_mask<double, 3>>::value, "");
+
+static_assert( is_simd_mask<fixed_size_simd_mask<int8_t, 32>>::value, "");
+static_assert( is_simd_mask<fixed_size_simd_mask<int16_t, 32>>::value, "");
+static_assert( is_simd_mask<fixed_size_simd_mask<int32_t, 32>>::value, "");
+static_assert( is_simd_mask<fixed_size_simd_mask<int64_t, 32>>::value, "");
+static_assert( is_simd_mask<fixed_size_simd_mask<uint8_t, 32>>::value, "");
+static_assert( is_simd_mask<fixed_size_simd_mask<uint16_t, 32>>::value, "");
+static_assert( is_simd_mask<fixed_size_simd_mask<uint32_t, 32>>::value, "");
+static_assert( is_simd_mask<fixed_size_simd_mask<uint64_t, 32>>::value, "");
+static_assert( is_simd_mask<fixed_size_simd_mask<float, 32>>::value, "");
+static_assert( is_simd_mask<fixed_size_simd_mask<double, 32>>::value, "");
+
+static_assert(!is_simd_mask<void>::value, "");
+static_assert(!is_simd_mask<int>::value, "");
+static_assert(!is_simd_mask<float>::value, "");
+static_assert(!is_simd_mask<simd<int>>::value, "");
+static_assert(!is_simd_mask<simd<float>>::value, "");
+static_assert(!is_simd_mask<UserType>::value, "");
+
+#if TEST_STD_VER > 14 && !defined(_LIBCPP_HAS_NO_VARIABLE_TEMPLATES) &&        \
+    !defined(_LIBCPP_HAS_NO_INLINE_VARIABLES)
+
+static_assert( is_simd_mask_v<native_simd_mask<int8_t>>, "");
+static_assert( is_simd_mask_v<native_simd_mask<int16_t>>, "");
+static_assert( is_simd_mask_v<native_simd_mask<int32_t>>, "");
+static_assert( is_simd_mask_v<native_simd_mask<int64_t>>, "");
+static_assert( is_simd_mask_v<native_simd_mask<uint8_t>>, "");
+static_assert( is_simd_mask_v<native_simd_mask<uint16_t>>, "");
+static_assert( is_simd_mask_v<native_simd_mask<uint32_t>>, "");
+static_assert( is_simd_mask_v<native_simd_mask<uint64_t>>, "");
+static_assert( is_simd_mask_v<native_simd_mask<float>>, "");
+static_assert( is_simd_mask_v<native_simd_mask<double>>, "");
+
+static_assert( is_simd_mask_v<fixed_size_simd_mask<int8_t, 1>>, "");
+static_assert( is_simd_mask_v<fixed_size_simd_mask<int16_t, 1>>, "");
+static_assert( is_simd_mask_v<fixed_size_simd_mask<int32_t, 1>>, "");
+static_assert( is_simd_mask_v<fixed_size_simd_mask<int64_t, 1>>, "");
+static_assert( is_simd_mask_v<fixed_size_simd_mask<uint8_t, 1>>, "");
+static_assert( is_simd_mask_v<fixed_size_simd_mask<uint16_t, 1>>, "");
+static_assert( is_simd_mask_v<fixed_size_simd_mask<uint32_t, 1>>, "");
+static_assert( is_simd_mask_v<fixed_size_simd_mask<uint64_t, 1>>, "");
+static_assert( is_simd_mask_v<fixed_size_simd_mask<float, 1>>, "");
+static_assert( is_simd_mask_v<fixed_size_simd_mask<double, 1>>, "");
+
+static_assert( is_simd_mask_v<fixed_size_simd_mask<int8_t, 3>>, "");
+static_assert( is_simd_mask_v<fixed_size_simd_mask<int16_t, 3>>, "");
+static_assert( is_simd_mask_v<fixed_size_simd_mask<int32_t, 3>>, "");
+static_assert( is_simd_mask_v<fixed_size_simd_mask<int64_t, 3>>, "");
+static_assert( is_simd_mask_v<fixed_size_simd_mask<uint8_t, 3>>, "");
+static_assert( is_simd_mask_v<fixed_size_simd_mask<uint16_t, 3>>, "");
+static_assert( is_simd_mask_v<fixed_size_simd_mask<uint32_t, 3>>, "");
+static_assert( is_simd_mask_v<fixed_size_simd_mask<uint64_t, 3>>, "");
+static_assert( is_simd_mask_v<fixed_size_simd_mask<float, 3>>, "");
+static_assert( is_simd_mask_v<fixed_size_simd_mask<double, 3>>, "");
+
+static_assert( is_simd_mask_v<fixed_size_simd_mask<int8_t, 32>>, "");
+static_assert( is_simd_mask_v<fixed_size_simd_mask<int16_t, 32>>, "");
+static_assert( is_simd_mask_v<fixed_size_simd_mask<int32_t, 32>>, "");
+static_assert( is_simd_mask_v<fixed_size_simd_mask<int64_t, 32>>, "");
+static_assert( is_simd_mask_v<fixed_size_simd_mask<uint8_t, 32>>, "");
+static_assert( is_simd_mask_v<fixed_size_simd_mask<uint16_t, 32>>, "");
+static_assert( is_simd_mask_v<fixed_size_simd_mask<uint32_t, 32>>, "");
+static_assert( is_simd_mask_v<fixed_size_simd_mask<uint64_t, 32>>, "");
+static_assert( is_simd_mask_v<fixed_size_simd_mask<float, 32>>, "");
+static_assert( is_simd_mask_v<fixed_size_simd_mask<double, 32>>, "");
+
+static_assert(!is_simd_mask_v<void>, "");
+static_assert(!is_simd_mask_v<int>, "");
+static_assert(!is_simd_mask_v<float>, "");
+static_assert(!is_simd_mask_v<simd<int>>, "");
+static_assert(!is_simd_mask_v<simd<float>>, "");
+static_assert(!is_simd_mask_v<UserType>, "");
+
+#endif
+
+int main() {}