// Slang HLSL compatibility library

typedef uint UINT;

__generic<T> __magic_type(HLSLAppendStructuredBufferType) struct AppendStructuredBuffer
{
    __intrinsic_op void Append(T value);

    __intrinsic_op void GetDimensions(
        out uint numStructs,
        out uint stride);
};

__magic_type(HLSLByteAddressBufferType) struct ByteAddressBuffer
{
    __intrinsic_op void GetDimensions(
        out uint dim);

    __intrinsic_op uint Load(int location);
    __intrinsic_op uint Load(int location, out uint status);

    __intrinsic_op uint2 Load2(int location);
    __intrinsic_op uint2 Load2(int location, out uint status);

    __intrinsic_op uint3 Load3(int location);
    __intrinsic_op uint3 Load3(int location, out uint status);

    __intrinsic_op uint4 Load4(int location);
    __intrinsic_op uint4 Load4(int location, out uint status);
};

__generic<T>
__magic_type(HLSLStructuredBufferType)
__intrinsic_type(${{
	// TODO: we really need a simple way to write an "expression splice"
	sb << kIROp_structuredBufferType;
}})
struct StructuredBuffer
{
    __intrinsic_op void GetDimensions(
        out uint numStructs,
        out uint stride);

    __intrinsic_op T Load(int location);
    __intrinsic_op T Load(int location, out uint status);

    __intrinsic_op(bufferLoad)
    __subscript(uint index) -> T;
};

__generic<T> __magic_type(HLSLConsumeStructuredBufferType) struct ConsumeStructuredBuffer
{
    __intrinsic_op T Consume();

    __intrinsic_op void GetDimensions(
        out uint numStructs,
        out uint stride);
};

__generic<T, let N : int> __magic_type(HLSLInputPatchType) struct InputPatch
{
    __intrinsic_op __subscript(uint index) -> T;
};

__generic<T, let N : int> __magic_type(HLSLOutputPatchType) struct OutputPatch
{
    __intrinsic_op __subscript(uint index) -> T { set; }
};

__magic_type(HLSLRWByteAddressBufferType) struct RWByteAddressBuffer
{
    // Note(tfoley): supports alll operations from `ByteAddressBuffer`
    // TODO(tfoley): can this be made a sub-type?

    __intrinsic_op void GetDimensions(
        out uint dim);

    __intrinsic_op uint Load(int location);
    __intrinsic_op uint Load(int location, out uint status);

    __intrinsic_op uint2 Load2(int location);
    __intrinsic_op uint2 Load2(int location, out uint status);

    __intrinsic_op uint3 Load3(int location);
    __intrinsic_op uint3 Load3(int location, out uint status);

    __intrinsic_op uint4 Load4(int location);
    __intrinsic_op uint4 Load4(int location, out uint status);

    // Added operations:

    __intrinsic_op void InterlockedAdd(
        UINT dest,
        UINT value,
        out UINT original_value);
    __intrinsic_op void InterlockedAdd(
        UINT dest,
        UINT value);

    __intrinsic_op void InterlockedAnd(
        UINT dest,
        UINT value,
        out UINT original_value);
    __intrinsic_op void InterlockedAnd(
        UINT dest,
        UINT value);

    __intrinsic_op void InterlockedCompareExchange(
        UINT dest,
        UINT compare_value,
        UINT value,
        out UINT original_value);
    __intrinsic_op void InterlockedCompareExchange(
        UINT dest,
        UINT compare_value,
        UINT value);

    __intrinsic_op void InterlockedCompareStore(
        UINT dest,
        UINT compare_value,
        UINT value);
    __intrinsic_op void InterlockedCompareStore(
        UINT dest,
        UINT compare_value);

    __intrinsic_op void InterlockedExchange(
        UINT dest,
        UINT value,
        out UINT original_value);
    __intrinsic_op void InterlockedExchange(
        UINT dest,
        UINT value);

    __intrinsic_op void InterlockedMax(
        UINT dest,
        UINT value,
        out UINT original_value);
    __intrinsic_op void InterlockedMax(
        UINT dest,
        UINT value);

    __intrinsic_op void InterlockedMin(
        UINT dest,
        UINT value,
        out UINT original_value);
    __intrinsic_op void InterlockedMin(
        UINT dest,
        UINT value);

    __intrinsic_op void InterlockedOr(
        UINT dest,
        UINT value,
        out UINT original_value);
    __intrinsic_op void InterlockedOr(
        UINT dest,
        UINT value);

    __intrinsic_op void InterlockedXor(
        UINT dest,
        UINT value,
        out UINT original_value);
    __intrinsic_op void InterlockedXor(
        UINT dest,
        UINT value);

    __intrinsic_op void Store(
        uint address,
        uint value);

    __intrinsic_op void Store2(
        uint address,
        uint2 value);

    __intrinsic_op void Store3(
        uint address,
        uint3 value);

    __intrinsic_op void Store4(
        uint address,
        uint4 value);
};

__generic<T>
__magic_type(HLSLRWStructuredBufferType)
__intrinsic_type(${{
	// TODO: we really need a simple way to write an "expression splice"
	sb << kIROp_readWriteStructuredBufferType;
}})
struct RWStructuredBuffer
{
    __intrinsic_op uint DecrementCounter();

    __intrinsic_op void GetDimensions(
        out uint numStructs,
        out uint stride);

    __intrinsic_op uint IncrementCounter();

    __intrinsic_op T Load(int location);
    __intrinsic_op T Load(int location, out uint status);

	__intrinsic_op
	__subscript(uint index) -> T
	{
		__intrinsic_op(bufferLoad)
		get;

		__intrinsic_op(bufferStore)
		set;
	}
};

__generic<T> __magic_type(HLSLPointStreamType) struct PointStream
{
    void Append(T value);
    void RestartStrip();
};

__generic<T> __magic_type(HLSLLineStreamType) struct LineStream
{
    void Append(T value);
    void RestartStrip();
};

__generic<T> __magic_type(HLSLTriangleStreamType) struct TriangleStream
{
    void Append(T value);
    void RestartStrip();
};

// Note(tfoley): Trying to systematically add all the HLSL builtins

// Try to terminate the current draw or dispatch call (HLSL SM 4.0)
__intrinsic_op void abort();

// Absolute value (HLSL SM 1.0)
__generic<T : __BuiltinSignedArithmeticType> __intrinsic_op T abs(T x);
__generic<T : __BuiltinSignedArithmeticType, let N : int> __intrinsic_op vector<T,N> abs(vector<T,N> x);
__generic<T : __BuiltinSignedArithmeticType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> abs(matrix<T,N,M> x);

// Inverse cosine (HLSL SM 1.0)
__generic<T : __BuiltinFloatingPointType> __intrinsic_op T acos(T x);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<T,N> acos(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> acos(matrix<T,N,M> x);

// Test if all components are non-zero (HLSL SM 1.0)
__generic<T : __BuiltinType> __intrinsic_op T all(T x);
__generic<T : __BuiltinType, let N : int> __intrinsic_op vector<T,N> all(vector<T,N> x);
__generic<T : __BuiltinType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> all(matrix<T,N,M> x);

// Barrier for writes to all memory spaces (HLSL SM 5.0)
__intrinsic_op void AllMemoryBarrier();

// Thread-group sync and barrier for writes to all memory spaces (HLSL SM 5.0)
__intrinsic_op void AllMemoryBarrierWithGroupSync();

// Test if any components is non-zero (HLSL SM 1.0)
__generic<T : __BuiltinType> __intrinsic_op T any(T x);
__generic<T : __BuiltinType, let N : int> __intrinsic_op vector<T,N> any(vector<T,N> x);
__generic<T : __BuiltinType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> any(matrix<T,N,M> x);


// Reinterpret bits as a double (HLSL SM 5.0)
__intrinsic_op double asdouble(uint lowbits, uint highbits);

// Reinterpret bits as a float (HLSL SM 4.0)
__intrinsic_op float asfloat( int x);
__intrinsic_op float asfloat(uint x);
__generic<let N : int> __intrinsic_op vector<float,N> asfloat(vector< int,N> x);
__generic<let N : int> __intrinsic_op vector<float,N> asfloat(vector<uint,N> x);
__generic<let N : int, let M : int> __intrinsic_op matrix<float,N,M> asfloat(matrix< int,N,M> x);
__generic<let N : int, let M : int> __intrinsic_op matrix<float,N,M> asfloat(matrix<uint,N,M> x);


// Inverse sine (HLSL SM 1.0)
__generic<T : __BuiltinFloatingPointType> __intrinsic_op T asin(T x);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<T,N> asin(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> asin(matrix<T,N,M> x);

// Reinterpret bits as an int (HLSL SM 4.0)
__intrinsic_op int asint(float x);
__intrinsic_op int asint(uint x);
__generic<let N : int> __intrinsic_op vector<int,N> asint(vector<float,N> x);
__generic<let N : int> __intrinsic_op vector<int,N> asint(vector<uint,N> x);
__generic<let N : int, let M : int> __intrinsic_op matrix<int,N,M> asint(matrix<float,N,M> x);
__generic<let N : int, let M : int> __intrinsic_op matrix<int,N,M> asint(matrix<uint,N,M> x);

// Reinterpret bits of double as a uint (HLSL SM 5.0)
__intrinsic_op void asuint(double value, out uint lowbits, out uint highbits);

// Reinterpret bits as a uint (HLSL SM 4.0)
__intrinsic_op uint asuint(float x);
__intrinsic_op uint asuint(int x);
__generic<let N : int> __intrinsic_op vector<uint,N> asuint(vector<float,N> x);
__generic<let N : int> __intrinsic_op vector<uint,N> asuint(vector<int,N> x);
__generic<let N : int, let M : int> __intrinsic_op matrix<uint,N,M> asuint(matrix<float,N,M> x);
__generic<let N : int, let M : int> __intrinsic_op matrix<uint,N,M> asuint(matrix<int,N,M> x);

// Inverse tangent (HLSL SM 1.0)
__generic<T : __BuiltinFloatingPointType> __intrinsic_op T atan(T x);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<T,N> atan(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> atan(matrix<T,N,M> x);

__generic<T : __BuiltinFloatingPointType>
__target_intrinsic(glsl,"atan($0,$1)")
__intrinsic_op
T atan2(T y, T x);

__generic<T : __BuiltinFloatingPointType, let N : int>
__target_intrinsic(glsl,"atan($0,$1)")
__intrinsic_op
vector<T,N> atan2(vector<T,N> y, vector<T,N> x);

__generic<T : __BuiltinFloatingPointType, let N : int, let M : int>
__target_intrinsic(glsl,"atan($0,$1)")
__intrinsic_op
matrix<T,N,M> atan2(matrix<T,N,M> y, matrix<T,N,M> x);

// Ceiling (HLSL SM 1.0)
__generic<T : __BuiltinFloatingPointType> __intrinsic_op T ceil(T x);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<T,N> ceil(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> ceil(matrix<T,N,M> x);


// Check access status to tiled resource
__intrinsic_op bool CheckAccessFullyMapped(uint status);

// Clamp (HLSL SM 1.0)
__generic<T : __BuiltinArithmeticType> T clamp(T x, T min, T max);
__generic<T : __BuiltinArithmeticType, let N : int> vector<T,N> clamp(vector<T,N> x, vector<T,N> min, vector<T,N> max);
__generic<T : __BuiltinArithmeticType, let N : int, let M : int> matrix<T,N,M> clamp(matrix<T,N,M> x, matrix<T,N,M> min, matrix<T,N,M> max);

// Clip (discard) fragment conditionally
__generic<T : __BuiltinFloatingPointType> __intrinsic_op void clip(T x);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op void clip(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op void clip(matrix<T,N,M> x);

// Cosine
__generic<T : __BuiltinFloatingPointType> T cos(T x);
__generic<T : __BuiltinFloatingPointType, let N : int> vector<T,N> cos(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> matrix<T,N,M> cos(matrix<T,N,M> x);

// Hyperbolic cosine
__generic<T : __BuiltinFloatingPointType> __intrinsic_op T cosh(T x);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<T,N> cosh(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> cosh(matrix<T,N,M> x);

// Population count
__intrinsic_op uint countbits(uint value);

// Cross product
__generic<T : __BuiltinArithmeticType> __intrinsic_op vector<T,3> cross(vector<T,3> x, vector<T,3> y);

// Convert encoded color
__intrinsic_op int4 D3DCOLORtoUBYTE4(float4 x);

// Partial-difference derivatives
__generic<T : __BuiltinFloatingPointType>
__target_intrinsic(glsl, dFdx)
__intrinsic_op
T ddx(T x);
__generic<T : __BuiltinFloatingPointType, let N : int>
__target_intrinsic(glsl, dFdx)
__intrinsic_op
vector<T,N> ddx(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int>
__target_intrinsic(glsl, dFdx)
__intrinsic_op
matrix<T,N,M> ddx(matrix<T,N,M> x);

__generic<T : __BuiltinFloatingPointType>
__glsl_extension(GL_ARB_derivative_control)
__target_intrinsic(glsl, dFdxCoarse)
__intrinsic_op
T ddx_coarse(T x);
__generic<T : __BuiltinFloatingPointType, let N : int>
__glsl_extension(GL_ARB_derivative_control)
__target_intrinsic(glsl, dFdxCoarse)
__intrinsic_op
vector<T,N> ddx_coarse(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int>
__glsl_extension(GL_ARB_derivative_control)
__target_intrinsic(glsl, dFdxCoarse)
__intrinsic_op
matrix<T,N,M> ddx_coarse(matrix<T,N,M> x);

__generic<T : __BuiltinFloatingPointType>
__glsl_extension(GL_ARB_derivative_control)
__target_intrinsic(glsl, dFdxFine)
__intrinsic_op
T ddx_fine(T x);
__generic<T : __BuiltinFloatingPointType, let N : int>
__glsl_extension(GL_ARB_derivative_control)
__target_intrinsic(glsl, dFdxFine)
__intrinsic_op
vector<T,N> ddx_fine(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int>
__glsl_extension(GL_ARB_derivative_control)
__target_intrinsic(glsl, dFdxFine)
__intrinsic_op
matrix<T,N,M> ddx_fine(matrix<T,N,M> x);

__generic<T : __BuiltinFloatingPointType>
__target_intrinsic(glsl, dFdy)
__intrinsic_op
T ddy(T x);
__generic<T : __BuiltinFloatingPointType, let N : int>
__target_intrinsic(glsl, dFdy)
__intrinsic_op
vector<T,N> ddy(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int>
__target_intrinsic(glsl, dFdy)
__intrinsic_op
 matrix<T,N,M> ddy(matrix<T,N,M> x);

__generic<T : __BuiltinFloatingPointType>
__glsl_extension(GL_ARB_derivative_control)
__target_intrinsic(glsl, dFdyCoarse)
__intrinsic_op
T ddy_coarse(T x);
__generic<T : __BuiltinFloatingPointType, let N : int>
__glsl_extension(GL_ARB_derivative_control)
__target_intrinsic(glsl, dFdyCoarse)
__intrinsic_op
vector<T,N> ddy_coarse(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int>
__glsl_extension(GL_ARB_derivative_control)
__target_intrinsic(glsl, dFdyCoarse)
__intrinsic_op
matrix<T,N,M> ddy_coarse(matrix<T,N,M> x);

__generic<T : __BuiltinFloatingPointType>
__glsl_extension(GL_ARB_derivative_control)
__target_intrinsic(glsl, dFdyFine)
__intrinsic_op
T ddy_fine(T x);
__generic<T : __BuiltinFloatingPointType, let N : int>
__glsl_extension(GL_ARB_derivative_control)
__target_intrinsic(glsl, dFdyFine)
__intrinsic_op
vector<T,N> ddy_fine(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int>
__glsl_extension(GL_ARB_derivative_control)
__target_intrinsic(glsl, dFdyFine)
__intrinsic_op
matrix<T,N,M> ddy_fine(matrix<T,N,M> x);


// Radians to degrees
__generic<T : __BuiltinFloatingPointType> __intrinsic_op T degrees(T x);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<T,N> degrees(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> degrees(matrix<T,N,M> x);

// Matrix determinant

__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op T determinant(matrix<T,N,N> m);

// Barrier for device memory
__intrinsic_op void DeviceMemoryBarrier();
__intrinsic_op void DeviceMemoryBarrierWithGroupSync();

// Vector distance

__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op T distance(vector<T,N> x, vector<T,N> y);

// Vector dot product

__generic<T : __BuiltinArithmeticType, let N : int> __intrinsic_op T dot(vector<T,N> x, vector<T,N> y);

// Helper for computing distance terms for lighting (obsolete)

__generic<T : __BuiltinFloatingPointType> __intrinsic_op vector<T,4> dst(vector<T,4> x, vector<T,4> y);

// Error message

// __intrinsic_op void errorf( string format, ... );

// Attribute evaluation

__generic<T : __BuiltinArithmeticType> __intrinsic_op T EvaluateAttributeAtCentroid(T x);
__generic<T : __BuiltinArithmeticType, let N : int> __intrinsic_op vector<T,N> EvaluateAttributeAtCentroid(vector<T,N> x);
__generic<T : __BuiltinArithmeticType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> EvaluateAttributeAtCentroid(matrix<T,N,M> x);

__generic<T : __BuiltinArithmeticType> __intrinsic_op T EvaluateAttributeAtSample(T x, uint sampleindex);
__generic<T : __BuiltinArithmeticType, let N : int> __intrinsic_op vector<T,N> EvaluateAttributeAtSample(vector<T,N> x, uint sampleindex);
__generic<T : __BuiltinArithmeticType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> EvaluateAttributeAtSample(matrix<T,N,M> x, uint sampleindex);

__generic<T : __BuiltinArithmeticType> __intrinsic_op T EvaluateAttributeSnapped(T x, int2 offset);
__generic<T : __BuiltinArithmeticType, let N : int> __intrinsic_op vector<T,N> EvaluateAttributeSnapped(vector<T,N> x, int2 offset);
__generic<T : __BuiltinArithmeticType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> EvaluateAttributeSnapped(matrix<T,N,M> x, int2 offset);

// Base-e exponent
__generic<T : __BuiltinFloatingPointType> __intrinsic_op T exp(T x);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<T,N> exp(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> exp(matrix<T,N,M> x);

// Base-2 exponent
__generic<T : __BuiltinFloatingPointType> __intrinsic_op T exp2(T x);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<T,N> exp2(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> exp2(matrix<T,N,M> x);

// Convert 16-bit float stored in low bits of integer
__intrinsic_op float f16tof32(uint value);
__generic<let N : int> __intrinsic_op vector<float,N> f16tof32(vector<uint,N> value);

// Convert to 16-bit float stored in low bits of integer
__intrinsic_op uint f32tof16(float value);
__generic<let N : int> __intrinsic_op vector<uint,N> f32tof16(vector<float,N> value);

// Flip surface normal to face forward, if needed
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<T,N> faceforward(vector<T,N> n, vector<T,N> i, vector<T,N> ng);

// Find first set bit starting at high bit and working down
__intrinsic_op int firstbithigh(int value);
__generic<let N : int> __intrinsic_op vector<int,N> firstbithigh(vector<int,N> value);

__intrinsic_op uint firstbithigh(uint value);
__generic<let N : int> __intrinsic_op vector<uint,N> firstbithigh(vector<uint,N> value);

// Find first set bit starting at low bit and working up
__intrinsic_op int firstbitlow(int value);
__generic<let N : int> __intrinsic_op vector<int,N> firstbitlow(vector<int,N> value);

__intrinsic_op uint firstbitlow(uint value);
__generic<let N : int> __intrinsic_op vector<uint,N> firstbitlow(vector<uint,N> value);

// Floor (HLSL SM 1.0)
__generic<T : __BuiltinFloatingPointType> __intrinsic_op T floor(T x);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<T,N> floor(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> floor(matrix<T,N,M> x);

// Fused multiply-add for doubles
__intrinsic_op double fma(double a, double b, double c);
__generic<let N : int> __intrinsic_op vector<double, N> fma(vector<double, N> a, vector<double, N> b, vector<double, N> c);
__generic<let N : int, let M : int> __intrinsic_op matrix<double,N,M> fma(matrix<double,N,M> a, matrix<double,N,M> b, matrix<double,N,M> c);

// Floating point remainder of x/y
__generic<T : __BuiltinFloatingPointType> __intrinsic_op T fmod(T x, T y);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<T,N> fmod(vector<T,N> x, vector<T,N> y);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> fmod(matrix<T,N,M> x, matrix<T,N,M> y);

// Fractional part
__generic<T : __BuiltinFloatingPointType>
__target_intrinsic(glsl, fract)
__intrinsic_op
T frac(T x);

__generic<T : __BuiltinFloatingPointType, let N : int>
__target_intrinsic(glsl, fract)
__intrinsic_op
vector<T,N> frac(vector<T,N> x);

__generic<T : __BuiltinFloatingPointType, let N : int, let M : int>
__target_intrinsic(glsl, fract)
__intrinsic_op
matrix<T,N,M> frac(matrix<T,N,M> x);

// Split float into mantissa and exponent
__generic<T : __BuiltinFloatingPointType> __intrinsic_op T frexp(T x, out T exp);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<T,N> frexp(vector<T,N> x, out vector<T,N> exp);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> frexp(matrix<T,N,M> x, out matrix<T,N,M> exp);

// Texture filter width
__generic<T : __BuiltinFloatingPointType> __intrinsic_op T fwidth(T x);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<T,N> fwidth(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> fwidth(matrix<T,N,M> x);

// Get number of samples in render target
__intrinsic_op uint GetRenderTargetSampleCount();

// Get position of given sample
__intrinsic_op float2 GetRenderTargetSamplePosition(int Index);

// Group memory barrier
__intrinsic_op void GroupMemoryBarrier();
__intrinsic_op void GroupMemoryBarrierWithGroupSync();

// Atomics
__intrinsic_op void InterlockedAdd(in out  int dest,  int value, out  int original_value);
__intrinsic_op void InterlockedAdd(in out uint dest, uint value, out uint original_value);

__intrinsic_op void InterlockedAnd(in out  int dest,  int value, out  int original_value);
__intrinsic_op void InterlockedAnd(in out uint dest, uint value, out uint original_value);

__intrinsic_op void InterlockedCompareExchange(in out  int dest,  int compare_value,  int value, out  int original_value);
__intrinsic_op void InterlockedCompareExchange(in out uint dest, uint compare_value, uint value, out uint original_value);

__intrinsic_op void InterlockedCompareStore(in out  int dest,  int compare_value,  int value);
__intrinsic_op void InterlockedCompareStore(in out uint dest, uint compare_value, uint value);

__intrinsic_op void InterlockedExchange(in out  int dest,  int value, out  int original_value);
__intrinsic_op void InterlockedExchange(in out uint dest, uint value, out uint original_value);

__intrinsic_op void InterlockedMax(in out  int dest,  int value, out  int original_value);
__intrinsic_op void InterlockedMax(in out uint dest, uint value, out uint original_value);

__intrinsic_op void InterlockedMin(in out  int dest,  int value, out  int original_value);
__intrinsic_op void InterlockedMin(in out uint dest, uint value, out uint original_value);

__intrinsic_op void InterlockedOr(in out  int dest,  int value, out  int original_value);
__intrinsic_op void InterlockedOr(in out uint dest, uint value, out uint original_value);

__intrinsic_op void InterlockedXor(in out  int dest,  int value, out  int original_value);
__intrinsic_op void InterlockedXor(in out uint dest, uint value, out uint original_value);

// Is floating-point value finite?
__generic<T : __BuiltinFloatingPointType> __intrinsic_op bool isfinite(T x);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<bool,N> isfinite(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op matrix<bool,N,M> isfinite(matrix<T,N,M> x);

// Is floating-point value infinite?
__generic<T : __BuiltinFloatingPointType> __intrinsic_op bool isinf(T x);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<bool,N> isinf(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op matrix<bool,N,M> isinf(matrix<T,N,M> x);

// Is floating-point value not-a-number?
__generic<T : __BuiltinFloatingPointType> __intrinsic_op bool isnan(T x);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<bool,N> isnan(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op matrix<bool,N,M> isnan(matrix<T,N,M> x);

// Construct float from mantissa and exponent
__generic<T : __BuiltinFloatingPointType> __intrinsic_op T ldexp(T x, T exp);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<T,N> ldexp(vector<T,N> x, vector<T,N> exp);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> ldexp(matrix<T,N,M> x, matrix<T,N,M> exp);

// Vector length
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op T length(vector<T,N> x);

// Linear interpolation
__generic<T : __BuiltinFloatingPointType>
__target_intrinsic(glsl, mix)
__intrinsic_op
T lerp(T x, T y, T s);

__generic<T : __BuiltinFloatingPointType, let N : int>
__target_intrinsic(glsl, mix)
__intrinsic_op
vector<T,N> lerp(vector<T,N> x, vector<T,N> y, vector<T,N> s);

__generic<T : __BuiltinFloatingPointType, let N : int, let M : int>
__target_intrinsic(glsl, mix)
__intrinsic_op
matrix<T,N,M> lerp(matrix<T,N,M> x, matrix<T,N,M> y, matrix<T,N,M> s);

// Legacy lighting function (obsolete)
__intrinsic_op float4 lit(float n_dot_l, float n_dot_h, float m);

// Base-e logarithm
__generic<T : __BuiltinFloatingPointType> __intrinsic_op T log(T x);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<T,N> log(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> log(matrix<T,N,M> x);

// Base-10 logarithm
__generic<T : __BuiltinFloatingPointType> __intrinsic_op T log10(T x);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<T,N> log10(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> log10(matrix<T,N,M> x);

// Base-2 logarithm
__generic<T : __BuiltinFloatingPointType> __intrinsic_op T log2(T x);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<T,N> log2(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> log2(matrix<T,N,M> x);

// multiply-add
__generic<T : __BuiltinArithmeticType> __intrinsic_op T mad(T mvalue, T avalue, T bvalue);
__generic<T : __BuiltinArithmeticType, let N : int> __intrinsic_op vector<T,N> mad(vector<T,N> mvalue, vector<T,N> avalue, vector<T,N> bvalue);
__generic<T : __BuiltinArithmeticType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> mad(matrix<T,N,M> mvalue, matrix<T,N,M> avalue, matrix<T,N,M> bvalue);

// maximum
__generic<T : __BuiltinArithmeticType> __intrinsic_op T max(T x, T y);
__generic<T : __BuiltinArithmeticType, let N : int> __intrinsic_op vector<T,N> max(vector<T,N> x, vector<T,N> y);
__generic<T : __BuiltinArithmeticType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> max(matrix<T,N,M> x, matrix<T,N,M> y);

// minimum
__generic<T : __BuiltinArithmeticType> __intrinsic_op T min(T x, T y);
__generic<T : __BuiltinArithmeticType, let N : int> __intrinsic_op vector<T,N> min(vector<T,N> x, vector<T,N> y);
__generic<T : __BuiltinArithmeticType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> min(matrix<T,N,M> x, matrix<T,N,M> y);

// split into integer and fractional parts (both with same sign)
__generic<T : __BuiltinFloatingPointType> __intrinsic_op T modf(T x, out T ip);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<T,N> modf(vector<T,N> x, out vector<T,N> ip);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> modf(matrix<T,N,M> x, out matrix<T,N,M> ip);

// msad4 (whatever that is)
__intrinsic_op uint4 msad4(uint reference, uint2 source, uint4 accum);

// General inner products

// scalar-scalar
__generic<T : __BuiltinArithmeticType> __intrinsic_op T mul(T x, T y);

// scalar-vector and vector-scalar
__generic<T : __BuiltinArithmeticType, let N : int> __intrinsic_op vector<T,N> mul(vector<T,N> x, T y);
__generic<T : __BuiltinArithmeticType, let N : int> __intrinsic_op vector<T,N> mul(T x, vector<T,N> y);

// scalar-matrix and matrix-scalar
__generic<T : __BuiltinArithmeticType, let N : int, let M :int> __intrinsic_op matrix<T,N,M> mul(matrix<T,N,M> x, T y);
__generic<T : __BuiltinArithmeticType, let N : int, let M :int> __intrinsic_op matrix<T,N,M> mul(T x, matrix<T,N,M> y);

// vector-vector (dot product)
__generic<T : __BuiltinArithmeticType, let N : int> __intrinsic_op(dot) T mul(vector<T,N> x, vector<T,N> y);

// vector-matrix
__generic<T : __BuiltinArithmeticType, let N : int, let M : int> __intrinsic_op(mulVectorMatrix) vector<T,M> mul(vector<T,N> x, matrix<T,N,M> y);

// matrix-vector
__generic<T : __BuiltinArithmeticType, let N : int, let M : int> __intrinsic_op(mulMatrixVector) vector<T,N> mul(matrix<T,N,M> x, vector<T,M> y);

// matrix-matrix
__generic<T : __BuiltinArithmeticType, let R : int, let N : int, let C : int> __intrinsic_op(mulMatrixMatrix) matrix<T,R,C> mul(matrix<T,R,N> x, matrix<T,N,C> y);

// noise (deprecated)
__intrinsic_op float noise(float x);
__generic<let N : int> __intrinsic_op float noise(vector<float, N> x);

// Normalize a vector
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<T,N> normalize(vector<T,N> x);

// Raise to a power
__generic<T : __BuiltinFloatingPointType> __intrinsic_op T pow(T x, T y);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<T,N> pow(vector<T,N> x, vector<T,N> y);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> pow(matrix<T,N,M> x, matrix<T,N,M> y);

// Output message

// __intrinsic_op void printf( string format, ... );

// Tessellation factor fixup routines

__intrinsic_op void Process2DQuadTessFactorsAvg(
    in  float4 RawEdgeFactors,
    in  float2 InsideScale,
    out float4 RoundedEdgeTessFactors,
    out float2 RoundedInsideTessFactors,
    out float2 UnroundedInsideTessFactors);

__intrinsic_op void Process2DQuadTessFactorsMax(
    in  float4 RawEdgeFactors,
    in  float2 InsideScale,
    out float4 RoundedEdgeTessFactors,
    out float2 RoundedInsideTessFactors,
    out float2 UnroundedInsideTessFactors);

__intrinsic_op void Process2DQuadTessFactorsMin(
    in  float4 RawEdgeFactors,
    in  float2 InsideScale,
    out float4 RoundedEdgeTessFactors,
    out float2 RoundedInsideTessFactors,
    out float2 UnroundedInsideTessFactors);

__intrinsic_op void ProcessIsolineTessFactors(
    in  float RawDetailFactor,
    in  float RawDensityFactor,
    out float RoundedDetailFactor,
    out float RoundedDensityFactor);

__intrinsic_op void ProcessQuadTessFactorsAvg(
    in  float4 RawEdgeFactors,
    in  float InsideScale,
    out float4 RoundedEdgeTessFactors,
    out float2 RoundedInsideTessFactors,
    out float2 UnroundedInsideTessFactors);

__intrinsic_op void ProcessQuadTessFactorsMax(
    in  float4 RawEdgeFactors,
    in  float InsideScale,
    out float4 RoundedEdgeTessFactors,
    out float2 RoundedInsideTessFactors,
    out float2 UnroundedInsideTessFactors);

__intrinsic_op void ProcessQuadTessFactorsMin(
    in  float4 RawEdgeFactors,
    in  float InsideScale,
    out float4 RoundedEdgeTessFactors,
    out float2 RoundedInsideTessFactors,
    out float2 UnroundedInsideTessFactors);

__intrinsic_op void ProcessTriTessFactorsAvg(
    in  float3 RawEdgeFactors,
    in  float InsideScale,
    out float3 RoundedEdgeTessFactors,
    out float RoundedInsideTessFactor,
    out float UnroundedInsideTessFactor);

__intrinsic_op void ProcessTriTessFactorsMax(
    in  float3 RawEdgeFactors,
    in  float InsideScale,
    out float3 RoundedEdgeTessFactors,
    out float RoundedInsideTessFactor,
    out float UnroundedInsideTessFactor);

__intrinsic_op void ProcessTriTessFactorsMin(
    in  float3 RawEdgeFactors,
    in  float InsideScale,
    out float3 RoundedEdgeTessFactors,
    out float RoundedInsideTessFactors,
    out float UnroundedInsideTessFactors);

// Degrees to radians
__generic<T : __BuiltinFloatingPointType> __intrinsic_op T radians(T x);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<T,N> radians(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> radians(matrix<T,N,M> x);

// Approximate reciprocal
__generic<T : __BuiltinFloatingPointType> __intrinsic_op T rcp(T x);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<T,N> rcp(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> rcp(matrix<T,N,M> x);

// Reflect incident vector across plane with given normal
__generic<T : __BuiltinFloatingPointType, let N : int>
__intrinsic_op
vector<T,N> reflect(vector<T,N> i, vector<T,N> n);

// Refract incident vector given surface normal and index of refraction
__generic<T : __BuiltinFloatingPointType, let N : int>
__intrinsic_op
vector<T,N> refract(vector<T,N> i, vector<T,N> n, float eta);

// Reverse order of bits
__intrinsic_op uint reversebits(uint value);
__generic<let N : int> vector<uint,N> reversebits(vector<uint,N> value);

// Round-to-nearest
__generic<T : __BuiltinFloatingPointType> __intrinsic_op T round(T x);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<T,N> round(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> round(matrix<T,N,M> x);

// Reciprocal of square root
__generic<T : __BuiltinFloatingPointType> __intrinsic_op T rsqrt(T x);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<T,N> rsqrt(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> rsqrt(matrix<T,N,M> x);

// Clamp value to [0,1] range
__generic<T : __BuiltinFloatingPointType>
__target_intrinsic(glsl, "clamp($0, 0, 1)")
T saturate(T x);

__generic<T : __BuiltinFloatingPointType, let N : int>
__target_intrinsic(glsl, "clamp($0, 0, 1)")
vector<T,N> saturate(vector<T,N> x);

__generic<T : __BuiltinFloatingPointType, let N : int, let M : int>
__target_intrinsic(glsl, "clamp($0, 0, 1)")
matrix<T,N,M> saturate(matrix<T,N,M> x);

__generic<T : __BuiltinFloatingPointType>
__specialized_for_target(glsl)
T saturate(T x)
{
    return clamp(x, T(0), T(1));
}

__generic<T : __BuiltinFloatingPointType, let N : int>
__specialized_for_target(glsl)
vector<T,N> saturate(vector<T,N> x)
{
    return clamp(x,
        vector<T,N>(T(0)),
        vector<T,N>(T(1)));
}

// HACK: need a helper to turn a scalar into a matrix,
// because GLSL and HLSL disagree on the semantics of
// constructing a matrix from a single scalar.
__generic<T, let N : int, let M : int>
matrix<T,N,M> __scalarToMatrix(T value);

__generic<T : __BuiltinFloatingPointType, let N : int, let M : int>
__specialized_for_target(glsl)
matrix<T,N,M> saturate(matrix<T,N,M> x)
{
    return clamp(x,
        __scalarToMatrix<T,N,M>(T(0)),
        __scalarToMatrix<T,N,M>(T(1)));
}


// Extract sign of value
__generic<T : __BuiltinSignedArithmeticType> __intrinsic_op int sign(T x);
__generic<T : __BuiltinSignedArithmeticType, let N : int> __intrinsic_op vector<int,N> sign(vector<T,N> x);
__generic<T : __BuiltinSignedArithmeticType, let N : int, let M : int> __intrinsic_op matrix<int,N,M> sign(matrix<T,N,M> x);


// Sine
__generic<T : __BuiltinFloatingPointType> T sin(T x);
__generic<T : __BuiltinFloatingPointType, let N : int> vector<T,N> sin(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> matrix<T,N,M> sin(matrix<T,N,M> x);

// Sine and cosine
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op void sincos(T x, out T s, out T c);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op void sincos(vector<T,N> x, out vector<T,N> s, out vector<T,N> c);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op void sincos(matrix<T,N,M> x, out matrix<T,N,M> s, out matrix<T,N,M> c);

// Hyperbolic Sine
__generic<T : __BuiltinFloatingPointType> __intrinsic_op T sinh(T x);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<T,N> sinh(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> sinh(matrix<T,N,M> x);

// Smooth step (Hermite interpolation)
__generic<T : __BuiltinFloatingPointType> __intrinsic_op T smoothstep(T min, T max, T x);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<T,N> smoothstep(vector<T,N> min, vector<T,N> max, vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> smoothstep(matrix<T,N,M> min, matrix<T,N,M> max, matrix<T,N,M> x);

// Square root
__generic<T : __BuiltinFloatingPointType> __intrinsic_op T sqrt(T x);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<T,N> sqrt(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> sqrt(matrix<T,N,M> x);

// Step function
__generic<T : __BuiltinFloatingPointType> __intrinsic_op T step(T y, T x);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<T,N> step(vector<T,N> y, vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> step(matrix<T,N,M> y, matrix<T,N,M> x);

// Tangent
__generic<T : __BuiltinFloatingPointType> __intrinsic_op T tan(T x);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<T,N> tan(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> tan(matrix<T,N,M> x);

// Hyperbolic tangent
__generic<T : __BuiltinFloatingPointType> __intrinsic_op T tanh(T x);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<T,N> tanh(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> tanh(matrix<T,N,M> x);

// Legacy texture-fetch operations

/*
__intrinsic_op float4 tex1D(sampler1D s, float t);
__intrinsic_op float4 tex1D(sampler1D s, float t, float ddx, float ddy);
__intrinsic_op float4 tex1Dbias(sampler1D s, float4 t);
__intrinsic_op float4 tex1Dgrad(sampler1D s, float t, float ddx, float ddy);
__intrinsic_op float4 tex1Dlod(sampler1D s, float4 t);
__intrinsic_op float4 tex1Dproj(sampler1D s, float4 t);

__intrinsic_op float4 tex2D(sampler2D s, float2 t);
__intrinsic_op float4 tex2D(sampler2D s, float2 t, float2 ddx, float2 ddy);
__intrinsic_op float4 tex2Dbias(sampler2D s, float4 t);
__intrinsic_op float4 tex2Dgrad(sampler2D s, float2 t, float2 ddx, float2 ddy);
__intrinsic_op float4 tex2Dlod(sampler2D s, float4 t);
__intrinsic_op float4 tex2Dproj(sampler2D s, float4 t);

__intrinsic_op float4 tex3D(sampler3D s, float3 t);
__intrinsic_op float4 tex3D(sampler3D s, float3 t, float3 ddx, float3 ddy);
__intrinsic_op float4 tex3Dbias(sampler3D s, float4 t);
__intrinsic_op float4 tex3Dgrad(sampler3D s, float3 t, float3 ddx, float3 ddy);
__intrinsic_op float4 tex3Dlod(sampler3D s, float4 t);
__intrinsic_op float4 tex3Dproj(sampler3D s, float4 t);

__intrinsic_op float4 texCUBE(samplerCUBE s, float3 t);
__intrinsic_op float4 texCUBE(samplerCUBE s, float3 t, float3 ddx, float3 ddy);
__intrinsic_op float4 texCUBEbias(samplerCUBE s, float4 t);
__intrinsic_op float4 texCUBEgrad(samplerCUBE s, float3 t, float3 ddx, float3 ddy);
__intrinsic_op float4 texCUBElod(samplerCUBE s, float4 t);
__intrinsic_op float4 texCUBEproj(samplerCUBE s, float4 t);
*/

// Matrix transpose
__generic<T : __BuiltinType, let N : int, let M : int> __intrinsic_op matrix<T,M,N> transpose(matrix<T,N,M> x);

// Truncate to integer
__generic<T : __BuiltinFloatingPointType> __intrinsic_op T trunc(T x);
__generic<T : __BuiltinFloatingPointType, let N : int> __intrinsic_op vector<T,N> trunc(vector<T,N> x);
__generic<T : __BuiltinFloatingPointType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> trunc(matrix<T,N,M> x);

// Shader model 6.0 stuff

__intrinsic_op uint GlobalOrderedCountIncrement(uint countToAppendForThisLane);

__generic<T : __BuiltinType> __intrinsic_op T QuadReadLaneAt(T sourceValue, int quadLaneID);
__generic<T : __BuiltinType, let N : int> __intrinsic_op vector<T,N> QuadReadLaneAt(vector<T,N> sourceValue, int quadLaneID);
__generic<T : __BuiltinType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> QuadReadLaneAt(matrix<T,N,M> sourceValue, int quadLaneID);

__generic<T : __BuiltinType> __intrinsic_op T QuadSwapX(T localValue);
__generic<T : __BuiltinType, let N : int> __intrinsic_op vector<T,N> QuadSwapX(vector<T,N> localValue);
__generic<T : __BuiltinType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> QuadSwapX(matrix<T,N,M> localValue);

__generic<T : __BuiltinType> __intrinsic_op T QuadSwapY(T localValue);
__generic<T : __BuiltinType, let N : int> __intrinsic_op vector<T,N> QuadSwapY(vector<T,N> localValue);
__generic<T : __BuiltinType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> QuadSwapY(matrix<T,N,M> localValue);

__generic<T : __BuiltinIntegerType> __intrinsic_op T WaveAllBitAnd(T expr);
__generic<T : __BuiltinIntegerType, let N : int> __intrinsic_op vector<T,N> WaveAllBitAnd(vector<T,N> expr);
__generic<T : __BuiltinIntegerType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> WaveAllBitAnd(matrix<T,N,M> expr);

__generic<T : __BuiltinIntegerType> __intrinsic_op T WaveAllBitOr(T expr);
__generic<T : __BuiltinIntegerType, let N : int> __intrinsic_op vector<T,N> WaveAllBitOr(vector<T,N> expr);
__generic<T : __BuiltinIntegerType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> WaveAllBitOr(matrix<T,N,M> expr);

__generic<T : __BuiltinIntegerType> __intrinsic_op T WaveAllBitXor(T expr);
__generic<T : __BuiltinIntegerType, let N : int> __intrinsic_op vector<T,N> WaveAllBitXor(vector<T,N> expr);
__generic<T : __BuiltinIntegerType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> WaveAllBitXor(matrix<T,N,M> expr);

__generic<T : __BuiltinArithmeticType> __intrinsic_op T WaveAllMax(T expr);
__generic<T : __BuiltinArithmeticType, let N : int> __intrinsic_op vector<T,N> WaveAllMax(vector<T,N> expr);
__generic<T : __BuiltinArithmeticType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> WaveAllMax(matrix<T,N,M> expr);

__generic<T : __BuiltinArithmeticType> __intrinsic_op T WaveAllMin(T expr);
__generic<T : __BuiltinArithmeticType, let N : int> __intrinsic_op vector<T,N> WaveAllMin(vector<T,N> expr);
__generic<T : __BuiltinArithmeticType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> WaveAllMin(matrix<T,N,M> expr);

__generic<T : __BuiltinArithmeticType> __intrinsic_op T WaveAllProduct(T expr);
__generic<T : __BuiltinArithmeticType, let N : int> __intrinsic_op vector<T,N> WaveAllProduct(vector<T,N> expr);
__generic<T : __BuiltinArithmeticType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> WaveAllProduct(matrix<T,N,M> expr);

__generic<T : __BuiltinArithmeticType> __intrinsic_op T WaveAllSum(T expr);
__generic<T : __BuiltinArithmeticType, let N : int> __intrinsic_op vector<T,N> WaveAllSum(vector<T,N> expr);
__generic<T : __BuiltinArithmeticType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> WaveAllSum(matrix<T,N,M> expr);

__intrinsic_op bool WaveAllEqual(bool expr);
__intrinsic_op bool WaveAllTrue(bool expr);
__intrinsic_op bool WaveAnyTrue(bool expr);

uint64_t WaveBallot(bool expr);

uint WaveGetLaneCount();
uint WaveGetLaneIndex();
uint WaveGetOrderedIndex();

bool WaveIsHelperLane();

bool WaveOnce();

__generic<T : __BuiltinArithmeticType> __intrinsic_op T WavePrefixProduct(T expr);
__generic<T : __BuiltinArithmeticType, let N : int> __intrinsic_op vector<T,N> WavePrefixProduct(vector<T,N> expr);
__generic<T : __BuiltinArithmeticType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> WavePrefixProduct(matrix<T,N,M> expr);

__generic<T : __BuiltinArithmeticType> __intrinsic_op T WavePrefixSum(T expr);
__generic<T : __BuiltinArithmeticType, let N : int> __intrinsic_op vector<T,N> WavePrefixSum(vector<T,N> expr);
__generic<T : __BuiltinArithmeticType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> WavePrefixSum(matrix<T,N,M> expr);

__generic<T : __BuiltinType> __intrinsic_op T WaveReadFirstLane(T expr);
__generic<T : __BuiltinType, let N : int> __intrinsic_op vector<T,N> WaveReadFirstLane(vector<T,N> expr);
__generic<T : __BuiltinType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> WaveReadFirstLane(matrix<T,N,M> expr);

__generic<T : __BuiltinType> __intrinsic_op T WaveReadLaneAt(T expr, int laneIndex);
__generic<T : __BuiltinType, let N : int> __intrinsic_op vector<T,N> WaveReadLaneAt(vector<T,N> expr, int laneIndex);
__generic<T : __BuiltinType, let N : int, let M : int> __intrinsic_op matrix<T,N,M> WaveReadLaneAt(matrix<T,N,M> expr, int laneIndex);

// `typedef`s to help with the fact that HLSL has been sorta-kinda case insensitive at various points
typedef Texture2D texture2D;

${{{{

// Component-wise multiplication ops
for(auto op : binaryOps)
{
    switch (op.opCode)
    {
    default:
        continue;

    case kIROp_Mul:
    case kIRPseudoOp_MulAssign:
        break;
    }

    for (auto type : kBaseTypes)
    {
        if ((type.flags & op.flags) == 0)
            continue;

        char const* leftType = type.name;
        char const* rightType = leftType;
        char const* resultType = leftType;

        char const* leftQual = "";
        if(op.flags & ASSIGNMENT) leftQual = "in out ";

        sb << "__generic<let N : int, let M : int> ";
        sb << "__intrinsic_op(" << int(op.opCode) << ") matrix<" << resultType << ",N,M> operator" << op.opName << "(" << leftQual << "matrix<" << leftType << ",N,M> left, matrix<" << rightType << ",N,M> right);\n";
    }
}

//

// Buffer types

static const struct {
    char const*         name;
    SlangResourceAccess access;
} kBaseBufferAccessLevels[] = {
    { "",                   SLANG_RESOURCE_ACCESS_READ },
    { "RW",                 SLANG_RESOURCE_ACCESS_READ_WRITE },
    { "RasterizerOrdered",  SLANG_RESOURCE_ACCESS_RASTER_ORDERED },
};
static const int kBaseBufferAccessLevelCount = sizeof(kBaseBufferAccessLevels) / sizeof(kBaseBufferAccessLevels[0]);

for (int aa = 0; aa < kBaseBufferAccessLevelCount; ++aa)
{

    sb << "__generic<T> __magic_type(Texture, ";
    sb << ResourceType::makeFlavor(ResourceType::Shape::ShapeBuffer, kBaseBufferAccessLevels[aa].access);
    sb << ") struct ";
    sb << kBaseBufferAccessLevels[aa].name;
    sb << "Buffer {\n";

    sb << "__intrinsic_op void GetDimensions(out uint dim);\n";

    sb << "__target_intrinsic(glsl, \"texelFetch($$P, $0)$$z\")\n";
    sb << "__intrinsic_op T Load(int location);\n";

    sb << "__intrinsic_op T Load(int location, out uint status);\n";

    sb << "__target_intrinsic(glsl, \"texelFetch($$P, int($0))$$z\")\n";
    sb << "__intrinsic_op __subscript(uint index) -> T";

    if (kBaseBufferAccessLevels[aa].access != SLANG_RESOURCE_ACCESS_READ)
    {
        sb << " { get; set; }\n";
    }
    else
    {
        sb << ";\n";
    }

    sb << "};\n";
}

}}}}