@swiftbrowser/wasm-sdk 0.0.0-stage → 0.9.0

package/wasm32-unknown-wasip1/swift.xctoolchain/usr/lib/swift_static/clang/include/openmp_wrappers/math.h

@@ -0,0 +1,61 @@
+/*===---- openmp_wrapper/math.h -------- OpenMP math.h intercept ------ c++ -===
+ *
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ *
+ *===-----------------------------------------------------------------------===
+ */
+
+// If we are in C++ mode and include <math.h> (not <cmath>) first, we still need
+// to make sure <cmath> is read first. The problem otherwise is that we haven't
+// seen the declarations of the math.h functions when the system math.h includes
+// our cmath overlay. However, our cmath overlay, or better the underlying
+// overlay, e.g. CUDA, uses the math.h functions. Since we haven't declared them
+// yet we get errors. CUDA avoids this by eagerly declaring all math functions
+// (in the __device__ space) but we cannot do this. Instead we break the
+// dependence by forcing cmath to go first. While our cmath will in turn include
+// this file, the cmath guards will prevent recursion.
+#ifdef __cplusplus
+#include <cmath>
+#endif
+
+#ifndef __CLANG_OPENMP_MATH_H__
+#define __CLANG_OPENMP_MATH_H__
+
+#ifndef _OPENMP
+#error "This file is for OpenMP compilation only."
+#endif
+
+#include_next <math.h>
+
+// We need limits.h for __clang_cuda_math.h below and because it should not hurt
+// we include it eagerly here.
+#include <limits.h>
+
+// We need stdlib.h because (for now) __clang_cuda_math.h below declares `abs`
+// which should live in stdlib.h.
+#include <stdlib.h>
+
+#pragma omp begin declare variant match(                                       \
+    device = {arch(nvptx, nvptx64)}, implementation = {extension(match_any)})
+
+#define __CUDA__
+#define __OPENMP_NVPTX__
+#include <__clang_cuda_math.h>
+#undef __OPENMP_NVPTX__
+#undef __CUDA__
+
+#pragma omp end declare variant
+
+#ifdef __AMDGCN__
+#pragma omp begin declare variant match(device = {arch(amdgcn)})
+
+#define __OPENMP_AMDGCN__
+#include <__clang_hip_math.h>
+#undef __OPENMP_AMDGCN__
+
+#pragma omp end declare variant
+#endif
+
+#endif

package/wasm32-unknown-wasip1/swift.xctoolchain/usr/lib/swift_static/clang/include/orc/c_api.h

@@ -0,0 +1,202 @@
+/*===- c_api.h - C API for the ORC runtime ------------------------*- C -*-===*\
+|*                                                                            *|
+|* Part of the LLVM Project, under the Apache License v2.0 with LLVM          *|
+|* Exceptions.                                                                *|
+|* See https://llvm.org/LICENSE.txt for license information.                  *|
+|* SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception                    *|
+|*                                                                            *|
+|*===----------------------------------------------------------------------===*|
+|*                                                                            *|
+|* This file defines the C API for the ORC runtime                            *|
+|*                                                                            *|
+\*===----------------------------------------------------------------------===*/
+
+#ifndef ORC_RT_C_API_H
+#define ORC_RT_C_API_H
+
+#include <assert.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+/* Helper to suppress strict prototype warnings. */
+#ifdef __clang__
+#define ORC_RT_C_STRICT_PROTOTYPES_BEGIN                                       \
+  _Pragma("clang diagnostic push")                                             \
+      _Pragma("clang diagnostic error \"-Wstrict-prototypes\"")
+#define ORC_RT_C_STRICT_PROTOTYPES_END _Pragma("clang diagnostic pop")
+#else
+#define ORC_RT_C_STRICT_PROTOTYPES_BEGIN
+#define ORC_RT_C_STRICT_PROTOTYPES_END
+#endif
+
+/* Helper to wrap C code for C++ */
+#ifdef __cplusplus
+#define ORC_RT_C_EXTERN_C_BEGIN                                                \
+  extern "C" {                                                                 \
+  ORC_RT_C_STRICT_PROTOTYPES_BEGIN
+#define ORC_RT_C_EXTERN_C_END                                                  \
+  ORC_RT_C_STRICT_PROTOTYPES_END                                               \
+  }
+#else
+#define ORC_RT_C_EXTERN_C_BEGIN ORC_RT_C_STRICT_PROTOTYPES_BEGIN
+#define ORC_RT_C_EXTERN_C_END ORC_RT_C_STRICT_PROTOTYPES_END
+#endif
+
+ORC_RT_C_EXTERN_C_BEGIN
+
+typedef union {
+  char *ValuePtr;
+  char Value[sizeof(char *)];
+} orc_rt_WrapperFunctionResultDataUnion;
+
+/**
+ * orc_rt_WrapperFunctionResult is a kind of C-SmallVector with an
+ * out-of-band error state.
+ *
+ * If Size == 0 and Data.ValuePtr is non-zero then the value is in the
+ * 'out-of-band error' state, and Data.ValuePtr points at a malloc-allocated,
+ * null-terminated string error message.
+ *
+ * If Size <= sizeof(orc_rt_WrapperFunctionResultData) then the value is in
+ * the 'small' state and the content is held in the first Size bytes of
+ * Data.Value.
+ *
+ * If Size > sizeof(orc_rt_WrapperFunctionResultData) then the value is in the
+ * 'large' state and the content is held in the first Size bytes of the
+ * memory pointed to by Data.ValuePtr. This memory must have been allocated by
+ * malloc, and will be freed with free when this value is destroyed.
+ */
+typedef struct {
+  orc_rt_WrapperFunctionResultDataUnion Data;
+  size_t Size;
+} orc_rt_WrapperFunctionResult;
+
+/**
+ * Zero-initialize an orc_rt_WrapperFunctionResult.
+ */
+static inline void
+orc_rt_WrapperFunctionResultInit(orc_rt_WrapperFunctionResult *R) {
+  R->Size = 0;
+  R->Data.ValuePtr = 0;
+}
+
+/**
+ * Create an orc_rt_WrapperFunctionResult with an uninitialized buffer of
+ * size Size. The buffer is returned via the DataPtr argument.
+ */
+static inline orc_rt_WrapperFunctionResult
+orc_rt_WrapperFunctionResultAllocate(size_t Size) {
+  orc_rt_WrapperFunctionResult R;
+  R.Size = Size;
+  // If Size is 0 ValuePtr must be 0 or it is considered an out-of-band error.
+  R.Data.ValuePtr = 0;
+  if (Size > sizeof(R.Data.Value))
+    R.Data.ValuePtr = (char *)malloc(Size);
+  return R;
+}
+
+/**
+ * Create an orc_rt_WrapperFunctionResult from the given data range.
+ */
+static inline orc_rt_WrapperFunctionResult
+orc_rt_CreateWrapperFunctionResultFromRange(const char *Data, size_t Size) {
+  orc_rt_WrapperFunctionResult R;
+  R.Size = Size;
+  if (R.Size > sizeof(R.Data.Value)) {
+    char *Tmp = (char *)malloc(Size);
+    memcpy(Tmp, Data, Size);
+    R.Data.ValuePtr = Tmp;
+  } else
+    memcpy(R.Data.Value, Data, Size);
+  return R;
+}
+
+/**
+ * Create an orc_rt_WrapperFunctionResult by copying the given string,
+ * including the null-terminator.
+ *
+ * This function copies the input string. The client is responsible for freeing
+ * the ErrMsg arg.
+ */
+static inline orc_rt_WrapperFunctionResult
+orc_rt_CreateWrapperFunctionResultFromString(const char *Source) {
+  return orc_rt_CreateWrapperFunctionResultFromRange(Source,
+                                                     strlen(Source) + 1);
+}
+
+/**
+ * Create an orc_rt_WrapperFunctionResult representing an out-of-band
+ * error.
+ *
+ * This function copies the input string. The client is responsible for freeing
+ * the ErrMsg arg.
+ */
+static inline orc_rt_WrapperFunctionResult
+orc_rt_CreateWrapperFunctionResultFromOutOfBandError(const char *ErrMsg) {
+  orc_rt_WrapperFunctionResult R;
+  R.Size = 0;
+  char *Tmp = (char *)malloc(strlen(ErrMsg) + 1);
+  strcpy(Tmp, ErrMsg);
+  R.Data.ValuePtr = Tmp;
+  return R;
+}
+
+/**
+ * This should be called to destroy orc_rt_WrapperFunctionResult values
+ * regardless of their state.
+ */
+static inline void
+orc_rt_DisposeWrapperFunctionResult(orc_rt_WrapperFunctionResult *R) {
+  if (R->Size > sizeof(R->Data.Value) ||
+      (R->Size == 0 && R->Data.ValuePtr))
+    free(R->Data.ValuePtr);
+}
+
+/**
+ * Get a pointer to the data contained in the given
+ * orc_rt_WrapperFunctionResult.
+ */
+static inline char *
+orc_rt_WrapperFunctionResultData(orc_rt_WrapperFunctionResult *R) {
+  assert((R->Size != 0 || R->Data.ValuePtr == NULL) &&
+         "Cannot get data for out-of-band error value");
+  return R->Size > sizeof(R->Data.Value) ? R->Data.ValuePtr : R->Data.Value;
+}
+
+/**
+ * Safely get the size of the given orc_rt_WrapperFunctionResult.
+ *
+ * Asserts that we're not trying to access the size of an error value.
+ */
+static inline size_t
+orc_rt_WrapperFunctionResultSize(const orc_rt_WrapperFunctionResult *R) {
+  assert((R->Size != 0 || R->Data.ValuePtr == NULL) &&
+         "Cannot get size for out-of-band error value");
+  return R->Size;
+}
+
+/**
+ * Returns 1 if this value is equivalent to a value just initialized by
+ * orc_rt_WrapperFunctionResultInit, 0 otherwise.
+ */
+static inline size_t
+orc_rt_WrapperFunctionResultEmpty(const orc_rt_WrapperFunctionResult *R) {
+  return R->Size == 0 && R->Data.ValuePtr == 0;
+}
+
+/**
+ * Returns a pointer to the out-of-band error string for this
+ * orc_rt_WrapperFunctionResult, or null if there is no error.
+ *
+ * The orc_rt_WrapperFunctionResult retains ownership of the error
+ * string, so it should be copied if the caller wishes to preserve it.
+ */
+static inline const char *orc_rt_WrapperFunctionResultGetOutOfBandError(
+    const orc_rt_WrapperFunctionResult *R) {
+  return R->Size == 0 ? R->Data.ValuePtr : 0;
+}
+
+ORC_RT_C_EXTERN_C_END
+
+#endif /* ORC_RT_C_API_H */

package/wasm32-unknown-wasip1/swift.xctoolchain/usr/lib/swift_static/clang/include/pconfigintrin.h

@@ -0,0 +1,40 @@
+/*===---- pconfigintrin.h - X86 platform configuration ---------------------===
+ *
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ *
+ *===-----------------------------------------------------------------------===
+ */
+
+#if !defined __X86INTRIN_H && !defined __IMMINTRIN_H
+#error "Never use <pconfigintrin.h> directly; include <x86intrin.h> instead."
+#endif
+
+#ifndef __PCONFIGINTRIN_H
+#define __PCONFIGINTRIN_H
+
+#define __PCONFIG_KEY_PROGRAM 0x00000001
+
+#if __has_extension(gnu_asm)
+
+/* Define the default attributes for the functions in this file. */
+#define __DEFAULT_FN_ATTRS \
+  __attribute__((__always_inline__, __nodebug__,  __target__("pconfig")))
+
+static __inline unsigned int __DEFAULT_FN_ATTRS
+_pconfig_u32(unsigned int __leaf, __SIZE_TYPE__ __d[])
+{
+  unsigned int __result;
+  __asm__ ("pconfig"
+           : "=a" (__result), "=b" (__d[0]), "=c" (__d[1]), "=d" (__d[2])
+           : "a" (__leaf), "b" (__d[0]), "c" (__d[1]), "d" (__d[2])
+           : "cc");
+  return __result;
+}
+
+#undef __DEFAULT_FN_ATTRS
+
+#endif /* __has_extension(gnu_asm) */
+
+#endif

package/wasm32-unknown-wasip1/swift.xctoolchain/usr/lib/swift_static/clang/include/pkuintrin.h

@@ -0,0 +1,34 @@
+/*===---- pkuintrin.h - PKU intrinsics -------------------------------------===
+ *
+ *
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ *
+ *===-----------------------------------------------------------------------===
+ */
+#ifndef __IMMINTRIN_H
+#error "Never use <pkuintrin.h> directly; include <immintrin.h> instead."
+#endif
+
+#ifndef __PKUINTRIN_H
+#define __PKUINTRIN_H
+
+/* Define the default attributes for the functions in this file. */
+#define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__, __target__("pku")))
+
+static __inline__ unsigned int __DEFAULT_FN_ATTRS
+_rdpkru_u32(void)
+{
+  return __builtin_ia32_rdpkru();
+}
+
+static __inline__ void __DEFAULT_FN_ATTRS
+_wrpkru(unsigned int __val)
+{
+  __builtin_ia32_wrpkru(__val);
+}
+
+#undef __DEFAULT_FN_ATTRS
+
+#endif

package/wasm32-unknown-wasip1/swift.xctoolchain/usr/lib/swift_static/clang/include/pmmintrin.h

@@ -0,0 +1,314 @@
+/*===---- pmmintrin.h - SSE3 intrinsics ------------------------------------===
+ *
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ *
+ *===-----------------------------------------------------------------------===
+ */
+
+#ifndef __PMMINTRIN_H
+#define __PMMINTRIN_H
+
+#if !defined(__i386__) && !defined(__x86_64__)
+#error "This header is only meant to be used on x86 and x64 architecture"
+#endif
+
+#include <emmintrin.h>
+
+/* Define the default attributes for the functions in this file. */
+#if defined(__EVEX512__) && !defined(__AVX10_1_512__)
+#define __DEFAULT_FN_ATTRS                                                     \
+  __attribute__((__always_inline__, __nodebug__,                               \
+                 __target__("sse3,no-evex512"), __min_vector_width__(128)))
+#else
+#define __DEFAULT_FN_ATTRS                                                     \
+  __attribute__((__always_inline__, __nodebug__, __target__("sse3"),           \
+                 __min_vector_width__(128)))
+#endif
+
+#if defined(__cplusplus) && (__cplusplus >= 201103L)
+#define __DEFAULT_FN_ATTRS_CONSTEXPR __DEFAULT_FN_ATTRS constexpr
+#else
+#define __DEFAULT_FN_ATTRS_CONSTEXPR __DEFAULT_FN_ATTRS
+#endif
+
+/// Loads data from an unaligned memory location to elements in a 128-bit
+///    vector.
+///
+///    If the address of the data is not 16-byte aligned, the instruction may
+///    read two adjacent aligned blocks of memory to retrieve the requested
+///    data.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VLDDQU </c> instruction.
+///
+/// \param __p
+///    A pointer to a 128-bit integer vector containing integer values.
+/// \returns A 128-bit vector containing the moved values.
+static __inline__ __m128i __DEFAULT_FN_ATTRS
+_mm_lddqu_si128(__m128i_u const *__p)
+{
+  return (__m128i)__builtin_ia32_lddqu((char const *)__p);
+}
+
+/// Adds the even-indexed values and subtracts the odd-indexed values of
+///    two 128-bit vectors of [4 x float].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VADDSUBPS </c> instruction.
+///
+/// \param __a
+///    A 128-bit vector of [4 x float] containing the left source operand.
+/// \param __b
+///    A 128-bit vector of [4 x float] containing the right source operand.
+/// \returns A 128-bit vector of [4 x float] containing the alternating sums and
+///    differences of both operands.
+static __inline__ __m128 __DEFAULT_FN_ATTRS
+_mm_addsub_ps(__m128 __a, __m128 __b)
+{
+  return __builtin_ia32_addsubps((__v4sf)__a, (__v4sf)__b);
+}
+
+/// Horizontally adds the adjacent pairs of values contained in two
+///    128-bit vectors of [4 x float].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VHADDPS </c> instruction.
+///
+/// \param __a
+///    A 128-bit vector of [4 x float] containing one of the source operands.
+///    The horizontal sums of the values are stored in the lower bits of the
+///    destination.
+/// \param __b
+///    A 128-bit vector of [4 x float] containing one of the source operands.
+///    The horizontal sums of the values are stored in the upper bits of the
+///    destination.
+/// \returns A 128-bit vector of [4 x float] containing the horizontal sums of
+///    both operands.
+static __inline__ __m128 __DEFAULT_FN_ATTRS
+_mm_hadd_ps(__m128 __a, __m128 __b)
+{
+  return __builtin_ia32_haddps((__v4sf)__a, (__v4sf)__b);
+}
+
+/// Horizontally subtracts the adjacent pairs of values contained in two
+///    128-bit vectors of [4 x float].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VHSUBPS </c> instruction.
+///
+/// \param __a
+///    A 128-bit vector of [4 x float] containing one of the source operands.
+///    The horizontal differences between the values are stored in the lower
+///    bits of the destination.
+/// \param __b
+///    A 128-bit vector of [4 x float] containing one of the source operands.
+///    The horizontal differences between the values are stored in the upper
+///    bits of the destination.
+/// \returns A 128-bit vector of [4 x float] containing the horizontal
+///    differences of both operands.
+static __inline__ __m128 __DEFAULT_FN_ATTRS
+_mm_hsub_ps(__m128 __a, __m128 __b)
+{
+  return __builtin_ia32_hsubps((__v4sf)__a, (__v4sf)__b);
+}
+
+/// Moves and duplicates odd-indexed values from a 128-bit vector
+///    of [4 x float] to float values stored in a 128-bit vector of
+///    [4 x float].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VMOVSHDUP </c> instruction.
+///
+/// \param __a
+///    A 128-bit vector of [4 x float]. \n
+///    Bits [127:96] of the source are written to bits [127:96] and [95:64] of
+///    the destination. \n
+///    Bits [63:32] of the source are written to bits [63:32] and [31:0] of the
+///    destination.
+/// \returns A 128-bit vector of [4 x float] containing the moved and duplicated
+///    values.
+static __inline__ __m128 __DEFAULT_FN_ATTRS_CONSTEXPR
+_mm_movehdup_ps(__m128 __a)
+{
+  return __builtin_shufflevector((__v4sf)__a, (__v4sf)__a, 1, 1, 3, 3);
+}
+
+/// Duplicates even-indexed values from a 128-bit vector of
+///    [4 x float] to float values stored in a 128-bit vector of [4 x float].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VMOVSLDUP </c> instruction.
+///
+/// \param __a
+///    A 128-bit vector of [4 x float] \n
+///    Bits [95:64] of the source are written to bits [127:96] and [95:64] of
+///    the destination. \n
+///    Bits [31:0] of the source are written to bits [63:32] and [31:0] of the
+///    destination.
+/// \returns A 128-bit vector of [4 x float] containing the moved and duplicated
+///    values.
+static __inline__ __m128 __DEFAULT_FN_ATTRS_CONSTEXPR
+_mm_moveldup_ps(__m128 __a)
+{
+  return __builtin_shufflevector((__v4sf)__a, (__v4sf)__a, 0, 0, 2, 2);
+}
+
+/// Adds the even-indexed values and subtracts the odd-indexed values of
+///    two 128-bit vectors of [2 x double].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VADDSUBPD </c> instruction.
+///
+/// \param __a
+///    A 128-bit vector of [2 x double] containing the left source operand.
+/// \param __b
+///    A 128-bit vector of [2 x double] containing the right source operand.
+/// \returns A 128-bit vector of [2 x double] containing the alternating sums
+///    and differences of both operands.
+static __inline__ __m128d __DEFAULT_FN_ATTRS
+_mm_addsub_pd(__m128d __a, __m128d __b)
+{
+  return __builtin_ia32_addsubpd((__v2df)__a, (__v2df)__b);
+}
+
+/// Horizontally adds the pairs of values contained in two 128-bit
+///    vectors of [2 x double].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VHADDPD </c> instruction.
+///
+/// \param __a
+///    A 128-bit vector of [2 x double] containing one of the source operands.
+///    The horizontal sum of the values is stored in the lower bits of the
+///    destination.
+/// \param __b
+///    A 128-bit vector of [2 x double] containing one of the source operands.
+///    The horizontal sum of the values is stored in the upper bits of the
+///    destination.
+/// \returns A 128-bit vector of [2 x double] containing the horizontal sums of
+///    both operands.
+static __inline__ __m128d __DEFAULT_FN_ATTRS
+_mm_hadd_pd(__m128d __a, __m128d __b)
+{
+  return __builtin_ia32_haddpd((__v2df)__a, (__v2df)__b);
+}
+
+/// Horizontally subtracts the pairs of values contained in two 128-bit
+///    vectors of [2 x double].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VHSUBPD </c> instruction.
+///
+/// \param __a
+///    A 128-bit vector of [2 x double] containing one of the source operands.
+///    The horizontal difference of the values is stored in the lower bits of
+///    the destination.
+/// \param __b
+///    A 128-bit vector of [2 x double] containing one of the source operands.
+///    The horizontal difference of the values is stored in the upper bits of
+///    the destination.
+/// \returns A 128-bit vector of [2 x double] containing the horizontal
+///    differences of both operands.
+static __inline__ __m128d __DEFAULT_FN_ATTRS
+_mm_hsub_pd(__m128d __a, __m128d __b)
+{
+  return __builtin_ia32_hsubpd((__v2df)__a, (__v2df)__b);
+}
+
+/// Moves and duplicates one double-precision value to double-precision
+///    values stored in a 128-bit vector of [2 x double].
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// __m128d _mm_loaddup_pd(double const *dp);
+/// \endcode
+///
+/// This intrinsic corresponds to the <c> VMOVDDUP </c> instruction.
+///
+/// \param dp
+///    A pointer to a double-precision value to be moved and duplicated.
+/// \returns A 128-bit vector of [2 x double] containing the moved and
+///    duplicated values.
+#define        _mm_loaddup_pd(dp)        _mm_load1_pd(dp)
+
+/// Moves and duplicates the double-precision value in the lower bits of
+///    a 128-bit vector of [2 x double] to double-precision values stored in a
+///    128-bit vector of [2 x double].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VMOVDDUP </c> instruction.
+///
+/// \param __a
+///    A 128-bit vector of [2 x double]. Bits [63:0] are written to bits
+///    [127:64] and [63:0] of the destination.
+/// \returns A 128-bit vector of [2 x double] containing the moved and
+///    duplicated values.
+static __inline__ __m128d __DEFAULT_FN_ATTRS_CONSTEXPR
+_mm_movedup_pd(__m128d __a)
+{
+  return __builtin_shufflevector((__v2df)__a, (__v2df)__a, 0, 0);
+}
+
+/// Establishes a linear address memory range to be monitored and puts
+///    the processor in the monitor event pending state. Data stored in the
+///    monitored address range causes the processor to exit the pending state.
+///
+/// The \c MONITOR instruction can be used in kernel mode, and in other modes
+/// if MSR <c> C001_0015h[MonMwaitUserEn] </c> is set.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c MONITOR instruction.
+///
+/// \param __p
+///    The memory range to be monitored. The size of the range is determined by
+///    CPUID function 0000_0005h.
+/// \param __extensions
+///    Optional extensions for the monitoring state.
+/// \param __hints
+///    Optional hints for the monitoring state.
+static __inline__ void __DEFAULT_FN_ATTRS
+_mm_monitor(void const *__p, unsigned __extensions, unsigned __hints)
+{
+  __builtin_ia32_monitor(__p, __extensions, __hints);
+}
+
+/// Used with the \c MONITOR instruction to wait while the processor is in
+///    the monitor event pending state. Data stored in the monitored address
+///    range, or an interrupt, causes the processor to exit the pending state.
+///
+/// The \c MWAIT instruction can be used in kernel mode, and in other modes if
+/// MSR <c> C001_0015h[MonMwaitUserEn] </c> is set.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c MWAIT instruction.
+///
+/// \param __extensions
+///    Optional extensions for the monitoring state, which can vary by
+///    processor.
+/// \param __hints
+///    Optional hints for the monitoring state, which can vary by processor.
+static __inline__ void __DEFAULT_FN_ATTRS
+_mm_mwait(unsigned __extensions, unsigned __hints)
+{
+  __builtin_ia32_mwait(__extensions, __hints);
+}
+
+#undef __DEFAULT_FN_ATTRS
+#undef __DEFAULT_FN_ATTRS_CONSTEXPR
+
+#endif /* __PMMINTRIN_H */