@cpp-linter/clang-tidy-darwin-arm64 20.1.8 → 21.1.8

package/lib/clang/{20/include/hlsl/hlsl_intrinsics.h → 21/include/hlsl/hlsl_alias_intrinsics.h}

@@ -1,4 +1,4 @@
-//===----- hlsl_intrinsics.h - HLSL definitions for intrinsics ----------===//
+//===--- hlsl_alias_intrinsics.h - HLSL alias definitions for intrinsics --===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
@@ -6,10 +6,8 @@
 //
 //===----------------------------------------------------------------------===//
 
-#ifndef _HLSL_HLSL_INTRINSICS_H_
-#define _HLSL_HLSL_INTRINSICS_H_
-
-#include "hlsl_detail.h"
+#ifndef _HLSL_HLSL_ALIAS_INTRINSICS_H_
+#define _HLSL_HLSL_ALIAS_INTRINSICS_H_
 
 namespace hlsl {
 
@@ -58,6 +56,15 @@ int16_t3 abs(int16_t3);
 _HLSL_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_abs)
 int16_t4 abs(int16_t4);
+
+_HLSL_AVAILABILITY(shadermodel, 6.2)
+constexpr uint16_t abs(uint16_t V) { return V; }
+_HLSL_AVAILABILITY(shadermodel, 6.2)
+constexpr uint16_t2 abs(uint16_t2 V) { return V; }
+_HLSL_AVAILABILITY(shadermodel, 6.2)
+constexpr uint16_t3 abs(uint16_t3 V) { return V; }
+_HLSL_AVAILABILITY(shadermodel, 6.2)
+constexpr uint16_t4 abs(uint16_t4 V) { return V; }
 #endif
 
 _HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
@@ -82,6 +89,11 @@ int3 abs(int3);
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_abs)
 int4 abs(int4);
 
+constexpr uint abs(uint V) { return V; }
+constexpr uint2 abs(uint2 V) { return V; }
+constexpr uint3 abs(uint3 V) { return V; }
+constexpr uint4 abs(uint4 V) { return V; }
+
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_abs)
 float abs(float);
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_abs)
@@ -100,6 +112,11 @@ int64_t3 abs(int64_t3);
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_abs)
 int64_t4 abs(int64_t4);
 
+constexpr uint64_t abs(uint64_t V) { return V; }
+constexpr uint64_t2 abs(uint64_t2 V) { return V; }
+constexpr uint64_t3 abs(uint64_t3 V) { return V; }
+constexpr uint64_t4 abs(uint64_t4 V) { return V; }
+
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_abs)
 double abs(double);
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_abs)
@@ -117,16 +134,18 @@ double4 abs(double4);
 /// \brief Returns the arccosine of the input value, \a Val.
 /// \param Val The input value.
 
-#ifdef __HLSL_ENABLE_16_BIT
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_acos)
 half acos(half);
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_acos)
 half2 acos(half2);
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_acos)
 half3 acos(half3);
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_acos)
 half4 acos(half4);
-#endif
 
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_acos)
 float acos(float);
@@ -137,6 +156,27 @@ float3 acos(float3);
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_acos)
 float4 acos(float4);
 
+//===----------------------------------------------------------------------===//
+// AddUint64 builtins
+//===----------------------------------------------------------------------===//
+
+/// \fn T AddUint64(T a, T b)
+/// \brief Implements unsigned 64-bit integer addition using pairs of unsigned
+/// 32-bit integers.
+/// \param x [in] The first unsigned 32-bit integer pair(s)
+/// \param y [in] The second unsigned 32-bit integer pair(s)
+///
+/// This function takes one or two pairs (low, high) of unsigned 32-bit integer
+/// values and returns pairs (low, high) of unsigned 32-bit integer
+/// values representing the result of unsigned 64-bit integer addition.
+
+_HLSL_AVAILABILITY(shadermodel, 6.0)
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_adduint64)
+uint32_t2 AddUint64(uint32_t2, uint32_t2);
+_HLSL_AVAILABILITY(shadermodel, 6.0)
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_adduint64)
+uint32_t4 AddUint64(uint32_t4, uint32_t4);
+
 //===----------------------------------------------------------------------===//
 // all builtins
 //===----------------------------------------------------------------------===//
@@ -249,6 +289,28 @@ bool all(double3);
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_all)
 bool all(double4);
 
+//===----------------------------------------------------------------------===//
+// and builtins
+//===----------------------------------------------------------------------===//
+
+/// \fn bool and(bool x, bool y)
+/// \brief Logically ands two boolean vectors elementwise and produces a bool
+/// vector output.
+
+// TODO: Clean up clang-format marker once we've resolved
+//       https://github.com/llvm/llvm-project/issues/127851
+//
+// clang-format off
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_and)
+bool and(bool x, bool y);
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_and)
+bool2 and(bool2 x, bool2 y);
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_and)
+bool3 and(bool3 x, bool3 y);
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_and)
+bool4 and(bool4 x, bool4 y);
+// clang-format on
+
 //===----------------------------------------------------------------------===//
 // any builtins
 //===----------------------------------------------------------------------===//
@@ -379,39 +441,6 @@ double3 asdouble(uint3, uint3);
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_asdouble)
 double4 asdouble(uint4, uint4);
 
-//===----------------------------------------------------------------------===//
-// asfloat builtins
-//===----------------------------------------------------------------------===//
-
-/// \fn float asfloat(T Val)
-/// \brief Interprets the bit pattern of x as float point number.
-/// \param Val The input value.
-
-template <typename T, int N>
-constexpr vector<float, N> asfloat(vector<T, N> V) {
-  return __detail::bit_cast<float, T, N>(V);
-}
-
-template <typename T> constexpr float asfloat(T F) {
-  return __detail::bit_cast<float, T>(F);
-}
-
-//===----------------------------------------------------------------------===//
-// asint builtins
-//===----------------------------------------------------------------------===//
-
-/// \fn int asint(T Val)
-/// \brief Interprets the bit pattern of x as an integer.
-/// \param Val The input value.
-
-template <typename T, int N> constexpr vector<int, N> asint(vector<T, N> V) {
-  return __detail::bit_cast<int, T, N>(V);
-}
-
-template <typename T> constexpr int asint(T F) {
-  return __detail::bit_cast<int, T>(F);
-}
-
 //===----------------------------------------------------------------------===//
 // asin builtins
 //===----------------------------------------------------------------------===//
@@ -420,16 +449,18 @@ template <typename T> constexpr int asint(T F) {
 /// \brief Returns the arcsine of the input value, \a Val.
 /// \param Val The input value.
 
-#ifdef __HLSL_ENABLE_16_BIT
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_asin)
 half asin(half);
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_asin)
 half2 asin(half2);
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_asin)
 half3 asin(half3);
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_asin)
 half4 asin(half4);
-#endif
 
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_asin)
 float asin(float);
@@ -440,40 +471,6 @@ float3 asin(float3);
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_asin)
 float4 asin(float4);
 
-//===----------------------------------------------------------------------===//
-// asuint builtins
-//===----------------------------------------------------------------------===//
-
-/// \fn uint asuint(T Val)
-/// \brief Interprets the bit pattern of x as an unsigned integer.
-/// \param Val The input value.
-
-template <typename T, int N> constexpr vector<uint, N> asuint(vector<T, N> V) {
-  return __detail::bit_cast<uint, T, N>(V);
-}
-
-template <typename T> constexpr uint asuint(T F) {
-  return __detail::bit_cast<uint, T>(F);
-}
-
-//===----------------------------------------------------------------------===//
-// asuint splitdouble builtins
-//===----------------------------------------------------------------------===//
-
-/// \fn void asuint(double D, out uint lowbits, out int highbits)
-/// \brief Split and interprets the lowbits and highbits of double D into uints.
-/// \param D The input double.
-/// \param lowbits The output lowbits of D.
-/// \param highbits The output highbits of D.
-_HLSL_BUILTIN_ALIAS(__builtin_hlsl_elementwise_splitdouble)
-void asuint(double, out uint, out uint);
-_HLSL_BUILTIN_ALIAS(__builtin_hlsl_elementwise_splitdouble)
-void asuint(double2, out uint2, out uint2);
-_HLSL_BUILTIN_ALIAS(__builtin_hlsl_elementwise_splitdouble)
-void asuint(double3, out uint3, out uint3);
-_HLSL_BUILTIN_ALIAS(__builtin_hlsl_elementwise_splitdouble)
-void asuint(double4, out uint4, out uint4);
-
 //===----------------------------------------------------------------------===//
 // atan builtins
 //===----------------------------------------------------------------------===//
@@ -482,16 +479,18 @@ void asuint(double4, out uint4, out uint4);
 /// \brief Returns the arctangent of the input value, \a Val.
 /// \param Val The input value.
 
-#ifdef __HLSL_ENABLE_16_BIT
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_atan)
 half atan(half);
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_atan)
 half2 atan(half2);
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_atan)
 half3 atan(half3);
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_atan)
 half4 atan(half4);
-#endif
 
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_atan)
 float atan(float);
@@ -512,16 +511,18 @@ float4 atan(float4);
 /// \param y The y-coordinate.
 /// \param x The x-coordinate.
 
-#ifdef __HLSL_ENABLE_16_BIT
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_atan2)
 half atan2(half y, half x);
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_atan2)
 half2 atan2(half2 y, half2 x);
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_atan2)
 half3 atan2(half3 y, half3 x);
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_atan2)
 half4 atan2(half4 y, half4 x);
-#endif
 
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_atan2)
 float atan2(float y, float x);
@@ -728,16 +729,18 @@ float4 cos(float4);
 /// \brief Returns the hyperbolic cosine of the input value, \a Val.
 /// \param Val The input value.
 
-#ifdef __HLSL_ENABLE_16_BIT
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_cosh)
 half cosh(half);
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_cosh)
 half2 cosh(half2);
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_cosh)
 half3 cosh(half3);
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_cosh)
 half4 cosh(half4);
-#endif
 
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_cosh)
 float cosh(float);
@@ -871,35 +874,6 @@ float3 degrees(float3);
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_elementwise_degrees)
 float4 degrees(float4);
 
-//===----------------------------------------------------------------------===//
-// distance builtins
-//===----------------------------------------------------------------------===//
-
-/// \fn K distance(T X, T Y)
-/// \brief Returns a distance scalar between \a X and \a Y.
-/// \param X The X input value.
-/// \param Y The Y input value.
-
-_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
-const inline half distance(half X, half Y) {
-  return __detail::distance_impl(X, Y);
-}
-
-const inline float distance(float X, float Y) {
-  return __detail::distance_impl(X, Y);
-}
-
-template <int N>
-_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
-const inline half distance(vector<half, N> X, vector<half, N> Y) {
-  return __detail::distance_vec_impl(X, Y);
-}
-
-template <int N>
-const inline float distance(vector<float, N> X, vector<float, N> Y) {
-  return __detail::distance_vec_impl(X, Y);
-}
-
 //===----------------------------------------------------------------------===//
 // dot product builtins
 //===----------------------------------------------------------------------===//
@@ -1253,40 +1227,6 @@ float3 floor(float3);
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_floor)
 float4 floor(float4);
 
-//===----------------------------------------------------------------------===//
-// fmod builtins
-//===----------------------------------------------------------------------===//
-
-/// \fn T fmod(T x, T y)
-/// \brief Returns the linear interpolation of x to y.
-/// \param x [in] The dividend.
-/// \param y [in] The divisor.
-///
-/// Return the floating-point remainder of the x parameter divided by the y
-/// parameter.
-
-_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
-_HLSL_BUILTIN_ALIAS(__builtin_elementwise_fmod)
-half fmod(half, half);
-_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
-_HLSL_BUILTIN_ALIAS(__builtin_elementwise_fmod)
-half2 fmod(half2, half2);
-_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
-_HLSL_BUILTIN_ALIAS(__builtin_elementwise_fmod)
-half3 fmod(half3, half3);
-_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
-_HLSL_BUILTIN_ALIAS(__builtin_elementwise_fmod)
-half4 fmod(half4, half4);
-
-_HLSL_BUILTIN_ALIAS(__builtin_elementwise_fmod)
-float fmod(float, float);
-_HLSL_BUILTIN_ALIAS(__builtin_elementwise_fmod)
-float2 fmod(float2, float2);
-_HLSL_BUILTIN_ALIAS(__builtin_elementwise_fmod)
-float3 fmod(float3, float3);
-_HLSL_BUILTIN_ALIAS(__builtin_elementwise_fmod)
-float4 fmod(float4, float4);
-
 //===----------------------------------------------------------------------===//
 // frac builtins
 //===----------------------------------------------------------------------===//
@@ -1388,30 +1328,6 @@ float3 lerp(float3, float3, float3);
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_lerp)
 float4 lerp(float4, float4, float4);
 
-//===----------------------------------------------------------------------===//
-// length builtins
-//===----------------------------------------------------------------------===//
-
-/// \fn T length(T x)
-/// \brief Returns the length of the specified floating-point vector.
-/// \param x [in] The vector of floats, or a scalar float.
-///
-/// Length is based on the following formula: sqrt(x[0]^2 + x[1]^2 + ...).
-
-_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
-const inline half length(half X) { return __detail::length_impl(X); }
-const inline float length(float X) { return __detail::length_impl(X); }
-
-template <int N>
-_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
-const inline half length(vector<half, N> X) {
-  return __detail::length_vec_impl(X);
-}
-
-template <int N> const inline float length(vector<float, N> X) {
-  return __detail::length_vec_impl(X);
-}
-
 //===----------------------------------------------------------------------===//
 // log builtins
 //===----------------------------------------------------------------------===//
@@ -1856,6 +1772,28 @@ float3 normalize(float3);
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_normalize)
 float4 normalize(float4);
 
+//===----------------------------------------------------------------------===//
+// or builtins
+//===----------------------------------------------------------------------===//
+
+/// \fn bool or(bool x, bool y)
+/// \brief Logically ors two boolean vectors elementwise and produces a bool
+/// vector output.
+
+// TODO: Clean up clang-format marker once we've resolved
+//       https://github.com/llvm/llvm-project/issues/127851
+//
+// clang-format off
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_or)
+bool or(bool, bool);
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_or)
+bool2 or(bool2, bool2);
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_or)
+bool3 or(bool3, bool3);
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_or)
+bool4 or(bool4, bool4);
+// clang-format on
+
 //===----------------------------------------------------------------------===//
 // pow builtins
 //===----------------------------------------------------------------------===//
@@ -1944,29 +1882,12 @@ uint64_t4 reversebits(uint64_t4);
 /// x[0] * y[1] - y[0] * x[1]
 
 _HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
-_HLSL_BUILTIN_ALIAS(__builtin_hlsl_cross)
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_crossf16)
 half3 cross(half3, half3);
 
-_HLSL_BUILTIN_ALIAS(__builtin_hlsl_cross)
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_crossf32)
 float3 cross(float3, float3);
 
-//===----------------------------------------------------------------------===//
-// D3DCOLORtoUBYTE4 builtin
-//===----------------------------------------------------------------------===//
-
-/// \fn T D3DCOLORtoUBYTE4(T x)
-/// \brief Converts a floating-point, 4D vector set by a D3DCOLOR to a UBYTE4.
-/// \param x [in] The floating-point vector4 to convert.
-///
-/// The return value is the UBYTE4 representation of the \a x parameter.
-///
-/// This function swizzles and scales components of the \a x parameter. Use this
-/// function to compensate for the lack of UBYTE4 support in some hardware.
-
-constexpr vector<uint, 4> D3DCOLORtoUBYTE4(vector<float, 4> V) {
-  return __detail::d3d_color_to_ubyte4_impl(V);
-}
-
 //===----------------------------------------------------------------------===//
 // rcp builtins
 //===----------------------------------------------------------------------===//
@@ -2140,6 +2061,41 @@ template <typename T, int Sz>
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_select)
 vector<T, Sz> select(vector<bool, Sz>, vector<T, Sz>, vector<T, Sz>);
 
+/// \fn vector<T,Sz> select(vector<bool,Sz> Conds, T TrueVal,
+///                         vector<T,Sz> FalseVals)
+/// \brief ternary operator for vectors. All vectors must be the same size.
+/// \param Conds The Condition input values.
+/// \param TrueVal The scalar value to splat from when conditions are true.
+/// \param FalseVals The vector values are chosen from when conditions are
+/// false.
+
+template <typename T, int Sz>
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_select)
+vector<T, Sz> select(vector<bool, Sz>, T, vector<T, Sz>);
+
+/// \fn vector<T,Sz> select(vector<bool,Sz> Conds, vector<T,Sz> TrueVals,
+///                         T FalseVal)
+/// \brief ternary operator for vectors. All vectors must be the same size.
+/// \param Conds The Condition input values.
+/// \param TrueVals The vector values are chosen from when conditions are true.
+/// \param FalseVal The scalar value to splat from when conditions are false.
+
+template <typename T, int Sz>
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_select)
+vector<T, Sz> select(vector<bool, Sz>, vector<T, Sz>, T);
+
+/// \fn vector<T,Sz> select(vector<bool,Sz> Conds, vector<T,Sz> TrueVals,
+///                         T FalseVal)
+/// \brief ternary operator for vectors. All vectors must be the same size.
+/// \param Conds The Condition input values.
+/// \param TrueVal The scalar value to splat from when conditions are true.
+/// \param FalseVal The scalar value to splat from when conditions are false.
+
+template <typename T, int Sz>
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_select)
+__detail::enable_if_t<__detail::is_arithmetic<T>::Value, vector<T, Sz>> select(
+    vector<bool, Sz>, T, T);
+
 //===----------------------------------------------------------------------===//
 // sin builtins
 //===----------------------------------------------------------------------===//
@@ -2178,16 +2134,18 @@ float4 sin(float4);
 /// \brief Returns the hyperbolic sine of the input value, \a Val.
 /// \param Val The input value.
 
-#ifdef __HLSL_ENABLE_16_BIT
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_sinh)
 half sinh(half);
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_sinh)
 half2 sinh(half2);
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_sinh)
 half3 sinh(half3);
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_sinh)
 half4 sinh(half4);
-#endif
 
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_sinh)
 float sinh(float);
@@ -2269,16 +2227,18 @@ float4 step(float4, float4);
 /// \brief Returns the tangent of the input value, \a Val.
 /// \param Val The input value.
 
-#ifdef __HLSL_ENABLE_16_BIT
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_tan)
 half tan(half);
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_tan)
 half2 tan(half2);
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_tan)
 half3 tan(half3);
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_tan)
 half4 tan(half4);
-#endif
 
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_tan)
 float tan(float);
@@ -2297,16 +2257,18 @@ float4 tan(float4);
 /// \brief Returns the hyperbolic tangent of the input value, \a Val.
 /// \param Val The input value.
 
-#ifdef __HLSL_ENABLE_16_BIT
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_tanh)
 half tanh(half);
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_tanh)
 half2 tanh(half2);
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_tanh)
 half3 tanh(half3);
+_HLSL_16BIT_AVAILABILITY(shadermodel, 6.2)
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_tanh)
 half4 tanh(half4);
-#endif
 
 _HLSL_BUILTIN_ALIAS(__builtin_elementwise_tanh)
 float tanh(float);
@@ -2388,6 +2350,10 @@ _HLSL_AVAILABILITY(shadermodel, 6.0)
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_is_first_lane)
 __attribute__((convergent)) bool WaveIsFirstLane();
 
+_HLSL_AVAILABILITY(shadermodel, 6.0)
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_get_lane_count)
+__attribute__((convergent)) uint WaveGetLaneCount();
+
 //===----------------------------------------------------------------------===//
 // WaveReadLaneAt builtins
 //===----------------------------------------------------------------------===//
@@ -2396,77 +2362,108 @@ __attribute__((convergent)) bool WaveIsFirstLane();
 // the specified wave.
 
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
-__attribute__((convergent)) bool WaveReadLaneAt(bool, int32_t);
+__attribute__((convergent)) bool WaveReadLaneAt(bool, uint32_t);
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
-__attribute__((convergent)) bool2 WaveReadLaneAt(bool2, int32_t);
+__attribute__((convergent)) bool2 WaveReadLaneAt(bool2, uint32_t);
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
-__attribute__((convergent)) bool3 WaveReadLaneAt(bool3, int32_t);
+__attribute__((convergent)) bool3 WaveReadLaneAt(bool3, uint32_t);
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
-__attribute__((convergent)) bool4 WaveReadLaneAt(bool4, int32_t);
+__attribute__((convergent)) bool4 WaveReadLaneAt(bool4, uint32_t);
 
 #ifdef __HLSL_ENABLE_16_BIT
 _HLSL_AVAILABILITY(shadermodel, 6.0)
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
-__attribute__((convergent)) int16_t WaveReadLaneAt(int16_t, int32_t);
+__attribute__((convergent)) int16_t WaveReadLaneAt(int16_t, uint32_t);
+_HLSL_AVAILABILITY(shadermodel, 6.0)
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
+__attribute__((convergent)) int16_t2 WaveReadLaneAt(int16_t2, uint32_t);
+_HLSL_AVAILABILITY(shadermodel, 6.0)
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
+__attribute__((convergent)) int16_t3 WaveReadLaneAt(int16_t3, uint32_t);
+_HLSL_AVAILABILITY(shadermodel, 6.0)
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
+__attribute__((convergent)) int16_t4 WaveReadLaneAt(int16_t4, uint32_t);
+
+_HLSL_AVAILABILITY(shadermodel, 6.0)
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
+__attribute__((convergent)) uint16_t WaveReadLaneAt(uint16_t, uint32_t);
 _HLSL_AVAILABILITY(shadermodel, 6.0)
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
-__attribute__((convergent)) int16_t2 WaveReadLaneAt(int16_t2, int32_t);
+__attribute__((convergent)) uint16_t2 WaveReadLaneAt(uint16_t2, uint32_t);
 _HLSL_AVAILABILITY(shadermodel, 6.0)
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
-__attribute__((convergent)) int16_t3 WaveReadLaneAt(int16_t3, int32_t);
+__attribute__((convergent)) uint16_t3 WaveReadLaneAt(uint16_t3, uint32_t);
 _HLSL_AVAILABILITY(shadermodel, 6.0)
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
-__attribute__((convergent)) int16_t4 WaveReadLaneAt(int16_t4, int32_t);
+__attribute__((convergent)) uint16_t4 WaveReadLaneAt(uint16_t4, uint32_t);
 #endif
 
 _HLSL_16BIT_AVAILABILITY(shadermodel, 6.0)
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
-__attribute__((convergent)) half WaveReadLaneAt(half, int32_t);
+__attribute__((convergent)) half WaveReadLaneAt(half, uint32_t);
 _HLSL_16BIT_AVAILABILITY(shadermodel, 6.0)
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
-__attribute__((convergent)) half2 WaveReadLaneAt(half2, int32_t);
+__attribute__((convergent)) half2 WaveReadLaneAt(half2, uint32_t);
 _HLSL_16BIT_AVAILABILITY(shadermodel, 6.0)
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
-__attribute__((convergent)) half3 WaveReadLaneAt(half3, int32_t);
+__attribute__((convergent)) half3 WaveReadLaneAt(half3, uint32_t);
 _HLSL_16BIT_AVAILABILITY(shadermodel, 6.0)
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
-__attribute__((convergent)) half4 WaveReadLaneAt(half4, int32_t);
+__attribute__((convergent)) half4 WaveReadLaneAt(half4, uint32_t);
+
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
+__attribute__((convergent)) int WaveReadLaneAt(int, uint32_t);
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
+__attribute__((convergent)) int2 WaveReadLaneAt(int2, uint32_t);
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
+__attribute__((convergent)) int3 WaveReadLaneAt(int3, uint32_t);
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
+__attribute__((convergent)) int4 WaveReadLaneAt(int4, uint32_t);
+
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
+__attribute__((convergent)) uint WaveReadLaneAt(uint, uint32_t);
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
+__attribute__((convergent)) uint2 WaveReadLaneAt(uint2, uint32_t);
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
+__attribute__((convergent)) uint3 WaveReadLaneAt(uint3, uint32_t);
+_HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
+__attribute__((convergent)) uint4 WaveReadLaneAt(uint4, uint32_t);
 
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
-__attribute__((convergent)) int WaveReadLaneAt(int, int32_t);
+__attribute__((convergent)) float WaveReadLaneAt(float, uint32_t);
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
-__attribute__((convergent)) int2 WaveReadLaneAt(int2, int32_t);
+__attribute__((convergent)) float2 WaveReadLaneAt(float2, uint32_t);
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
-__attribute__((convergent)) int3 WaveReadLaneAt(int3, int32_t);
+__attribute__((convergent)) float3 WaveReadLaneAt(float3, uint32_t);
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
-__attribute__((convergent)) int4 WaveReadLaneAt(int4, int32_t);
+__attribute__((convergent)) float4 WaveReadLaneAt(float4, uint32_t);
 
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
-__attribute__((convergent)) float WaveReadLaneAt(float, int32_t);
+__attribute__((convergent)) int64_t WaveReadLaneAt(int64_t, uint32_t);
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
-__attribute__((convergent)) float2 WaveReadLaneAt(float2, int32_t);
+__attribute__((convergent)) int64_t2 WaveReadLaneAt(int64_t2, uint32_t);
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
-__attribute__((convergent)) float3 WaveReadLaneAt(float3, int32_t);
+__attribute__((convergent)) int64_t3 WaveReadLaneAt(int64_t3, uint32_t);
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
-__attribute__((convergent)) float4 WaveReadLaneAt(float4, int32_t);
+__attribute__((convergent)) int64_t4 WaveReadLaneAt(int64_t4, uint32_t);
 
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
-__attribute__((convergent)) int64_t WaveReadLaneAt(int64_t, int32_t);
+__attribute__((convergent)) uint64_t WaveReadLaneAt(uint64_t, uint32_t);
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
-__attribute__((convergent)) int64_t2 WaveReadLaneAt(int64_t2, int32_t);
+__attribute__((convergent)) uint64_t2 WaveReadLaneAt(uint64_t2, uint32_t);
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
-__attribute__((convergent)) int64_t3 WaveReadLaneAt(int64_t3, int32_t);
+__attribute__((convergent)) uint64_t3 WaveReadLaneAt(uint64_t3, uint32_t);
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
-__attribute__((convergent)) int64_t4 WaveReadLaneAt(int64_t4, int32_t);
+__attribute__((convergent)) uint64_t4 WaveReadLaneAt(uint64_t4, uint32_t);
 
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
-__attribute__((convergent)) double WaveReadLaneAt(double, int32_t);
+__attribute__((convergent)) double WaveReadLaneAt(double, uint32_t);
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
-__attribute__((convergent)) double2 WaveReadLaneAt(double2, int32_t);
+__attribute__((convergent)) double2 WaveReadLaneAt(double2, uint32_t);
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
-__attribute__((convergent)) double3 WaveReadLaneAt(double3, int32_t);
+__attribute__((convergent)) double3 WaveReadLaneAt(double3, uint32_t);
 _HLSL_BUILTIN_ALIAS(__builtin_hlsl_wave_read_lane_at)
-__attribute__((convergent)) double4 WaveReadLaneAt(double4, int32_t);
+__attribute__((convergent)) double4 WaveReadLaneAt(double4, uint32_t);
 
 //===----------------------------------------------------------------------===//
 // WaveActiveMax builtins
@@ -2811,4 +2808,4 @@ _HLSL_BUILTIN_ALIAS(__builtin_hlsl_group_memory_barrier_with_group_sync)
 void GroupMemoryBarrierWithGroupSync(void);
 
 } // namespace hlsl
-#endif //_HLSL_HLSL_INTRINSICS_H_
+#endif //_HLSL_HLSL_ALIAS_INTRINSICS_H_