333 lines
15 KiB
C++
333 lines
15 KiB
C++
|
// This file is part of the FidelityFX SDK.
|
||
|
|
//
|
||
|
|
// Copyright (c) 2022-2023 Advanced Micro Devices, Inc. All rights reserved.
|
||
|
|
//
|
||
|
|
// Permission is hereby granted, free of charge, to any person obtaining a copy
|
||
|
|
// of this software and associated documentation files (the "Software"), to deal
|
||
|
|
// in the Software without restriction, including without limitation the rights
|
||
|
|
// to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||
|
|
// copies of the Software, and to permit persons to whom the Software is
|
||
|
|
// furnished to do so, subject to the following conditions:
|
||
|
|
// The above copyright notice and this permission notice shall be included in
|
||
|
|
// all copies or substantial portions of the Software.
|
||
|
|
//
|
||
|
|
// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||
|
|
// IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||
|
|
// FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||
|
|
// AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||
|
|
// LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||
|
|
// OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
||
|
|
// THE SOFTWARE.
|
||
|
|
|
||
|
|
/// A define for a true value in a boolean expression.
|
||
|
|
///
|
||
|
|
/// @ingroup CPU
|
||
|
|
#define FFX_TRUE (1)
|
||
|
|
|
||
|
|
/// A define for a false value in a boolean expression.
|
||
|
|
///
|
||
|
|
/// @ingroup CPU
|
||
|
|
#define FFX_FALSE (0)
|
||
|
|
|
||
|
|
#if !defined(FFX_STATIC)
|
||
|
|
/// A define to abstract declaration of static variables and functions.
|
||
|
|
///
|
||
|
|
/// @ingroup CPU
|
||
|
|
#define FFX_STATIC static
|
||
|
|
#endif // #if !defined(FFX_STATIC)
|
||
|
|
|
||
|
|
#ifdef __clang__
|
||
|
|
#pragma clang diagnostic ignored "-Wunused-variable"
|
||
|
|
#endif
|
||
|
|
|
||
|
|
/// Interpret the bit layout of an IEEE-754 floating point value as an unsigned integer.
|
||
|
|
///
|
||
|
|
/// @param [in] x A 32bit floating value.
|
||
|
|
///
|
||
|
|
/// @returns
|
||
|
|
/// An unsigned 32bit integer value containing the bit pattern of <c><i>x</i></c>.
|
||
|
|
///
|
||
|
|
/// @ingroup CPU
|
||
|
|
FFX_STATIC FfxUInt32 ffxAsUInt32(FfxFloat32 x)
|
||
|
|
{
|
||
|
|
union
|
||
|
|
{
|
||
|
|
FfxFloat32 f;
|
||
|
|
FfxUInt32 u;
|
||
|
|
} bits;
|
||
|
|
|
||
|
|
bits.f = x;
|
||
|
|
return bits.u;
|
||
|
|
}
|
||
|
|
|
||
|
|
FFX_STATIC FfxFloat32 ffxDot2(FfxFloat32x2 a, FfxFloat32x2 b)
|
||
|
|
{
|
||
|
|
return a[0] * b[0] + a[1] * b[1];
|
||
|
|
}
|
||
|
|
|
||
|
|
FFX_STATIC FfxFloat32 ffxDot3(FfxFloat32x3 a, FfxFloat32x3 b)
|
||
|
|
{
|
||
|
|
return a[0] * b[0] + a[1] * b[1] + a[2] * b[2];
|
||
|
|
}
|
||
|
|
|
||
|
|
FFX_STATIC FfxFloat32 ffxDot4(FfxFloat32x4 a, FfxFloat32x4 b)
|
||
|
|
{
|
||
|
|
return a[0] * b[0] + a[1] * b[1] + a[2] * b[2] + a[3] * b[3];
|
||
|
|
}
|
||
|
|
|
||
|
|
/// Compute the linear interopation between two values.
|
||
|
|
///
|
||
|
|
/// Implemented by calling the GLSL <c><i>mix</i></c> instrinsic function. Implements the
|
||
|
|
/// following math:
|
||
|
|
///
|
||
|
|
/// (1 - t) * x + t * y
|
||
|
|
///
|
||
|
|
/// @param [in] x The first value to lerp between.
|
||
|
|
/// @param [in] y The second value to lerp between.
|
||
|
|
/// @param [in] t The value to determine how much of <c><i>x</i></c> and how much of <c><i>y</i></c>.
|
||
|
|
///
|
||
|
|
/// @returns
|
||
|
|
/// A linearly interpolated value between <c><i>x</i></c> and <c><i>y</i></c> according to <c><i>t</i></c>.
|
||
|
|
///
|
||
|
|
/// @ingroup CPU
|
||
|
|
FFX_STATIC FfxFloat32 ffxLerp(FfxFloat32 x, FfxFloat32 y, FfxFloat32 t)
|
||
|
|
{
|
||
|
|
return y * t + (-x * t + x);
|
||
|
|
}
|
||
|
|
|
||
|
|
/// Compute the reciprocal of a value.
|
||
|
|
///
|
||
|
|
/// @param [in] x The value to compute the reciprocal for.
|
||
|
|
///
|
||
|
|
/// @returns
|
||
|
|
/// The reciprocal value of <c><i>x</i></c>.
|
||
|
|
///
|
||
|
|
/// @ingroup CPU
|
||
|
|
FFX_STATIC FfxFloat32 ffxReciprocal(FfxFloat32 a)
|
||
|
|
{
|
||
|
|
return 1.0f / a;
|
||
|
|
}
|
||
|
|
|
||
|
|
/// Compute the square root of a value.
|
||
|
|
///
|
||
|
|
/// @param [in] x The first value to compute the min of.
|
||
|
|
///
|
||
|
|
/// @returns
|
||
|
|
/// The the square root of <c><i>x</i></c>.
|
||
|
|
///
|
||
|
|
/// @ingroup CPU
|
||
|
|
FFX_STATIC FfxFloat32 ffxSqrt(FfxFloat32 x)
|
||
|
|
{
|
||
|
|
return sqrt(x);
|
||
|
|
}
|
||
|
|
|
||
|
|
FFX_STATIC FfxUInt32 AShrSU1(FfxUInt32 a, FfxUInt32 b)
|
||
|
|
{
|
||
|
|
return FfxUInt32(FfxInt32(a) >> FfxInt32(b));
|
||
|
|
}
|
||
|
|
|
||
|
|
/// Compute the factional part of a decimal value.
|
||
|
|
///
|
||
|
|
/// This function calculates <c><i>x - floor(x)</i></c>.
|
||
|
|
///
|
||
|
|
/// @param [in] x The value to compute the fractional part from.
|
||
|
|
///
|
||
|
|
/// @returns
|
||
|
|
/// The fractional part of <c><i>x</i></c>.
|
||
|
|
///
|
||
|
|
/// @ingroup CPU
|
||
|
|
FFX_STATIC FfxFloat32 ffxFract(FfxFloat32 a)
|
||
|
|
{
|
||
|
|
return a - floor(a);
|
||
|
|
}
|
||
|
|
|
||
|
|
/// Compute the reciprocal square root of a value.
|
||
|
|
///
|
||
|
|
/// @param [in] x The value to compute the reciprocal for.
|
||
|
|
///
|
||
|
|
/// @returns
|
||
|
|
/// The reciprocal square root value of <c><i>x</i></c>.
|
||
|
|
///
|
||
|
|
/// @ingroup CPU
|
||
|
|
FFX_STATIC FfxFloat32 rsqrt(FfxFloat32 a)
|
||
|
|
{
|
||
|
|
return ffxReciprocal(ffxSqrt(a));
|
||
|
|
}
|
||
|
|
|
||
|
|
FFX_STATIC FfxFloat32 ffxMin(FfxFloat32 x, FfxFloat32 y)
|
||
|
|
{
|
||
|
|
return x < y ? x : y;
|
||
|
|
}
|
||
|
|
|
||
|
|
FFX_STATIC FfxUInt32 ffxMin(FfxUInt32 x, FfxUInt32 y)
|
||
|
|
{
|
||
|
|
return x < y ? x : y;
|
||
|
|
}
|
||
|
|
|
||
|
|
FFX_STATIC FfxFloat32 ffxMax(FfxFloat32 x, FfxFloat32 y)
|
||
|
|
{
|
||
|
|
return x > y ? x : y;
|
||
|
|
}
|
||
|
|
|
||
|
|
FFX_STATIC FfxUInt32 ffxMax(FfxUInt32 x, FfxUInt32 y)
|
||
|
|
{
|
||
|
|
return x > y ? x : y;
|
||
|
|
}
|
||
|
|
|
||
|
|
/// Clamp a value to a [0..1] range.
|
||
|
|
///
|
||
|
|
/// @param [in] x The value to clamp to [0..1] range.
|
||
|
|
///
|
||
|
|
/// @returns
|
||
|
|
/// The clamped version of <c><i>x</i></c>.
|
||
|
|
///
|
||
|
|
/// @ingroup CPU
|
||
|
|
FFX_STATIC FfxFloat32 ffxSaturate(FfxFloat32 a)
|
||
|
|
{
|
||
|
|
return ffxMin(1.0f, ffxMax(0.0f, a));
|
||
|
|
}
|
||
|
|
|
||
|
|
////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
|
||
|
|
////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
|
||
|
|
|
||
|
|
FFX_STATIC void opAAddOneF3(FfxFloat32x3 d, FfxFloat32x3 a, FfxFloat32 b)
|
||
|
|
{
|
||
|
|
d[0] = a[0] + b;
|
||
|
|
d[1] = a[1] + b;
|
||
|
|
d[2] = a[2] + b;
|
||
|
|
return;
|
||
|
|
}
|
||
|
|
|
||
|
|
FFX_STATIC void opACpyF3(FfxFloat32x3 d, FfxFloat32x3 a)
|
||
|
|
{
|
||
|
|
d[0] = a[0];
|
||
|
|
d[1] = a[1];
|
||
|
|
d[2] = a[2];
|
||
|
|
return;
|
||
|
|
}
|
||
|
|
|
||
|
|
FFX_STATIC void opAMulF3(FfxFloat32x3 d, FfxFloat32x3 a, FfxFloat32x3 b)
|
||
|
|
{
|
||
|
|
d[0] = a[0] * b[0];
|
||
|
|
d[1] = a[1] * b[1];
|
||
|
|
d[2] = a[2] * b[2];
|
||
|
|
return;
|
||
|
|
}
|
||
|
|
|
||
|
|
FFX_STATIC void opAMulOneF3(FfxFloat32x3 d, FfxFloat32x3 a, FfxFloat32 b)
|
||
|
|
{
|
||
|
|
d[0] = a[0] * b;
|
||
|
|
d[1] = a[1] * b;
|
||
|
|
d[2] = a[2] * b;
|
||
|
|
return;
|
||
|
|
}
|
||
|
|
|
||
|
|
FFX_STATIC void opARcpF3(FfxFloat32x3 d, FfxFloat32x3 a)
|
||
|
|
{
|
||
|
|
d[0] = ffxReciprocal(a[0]);
|
||
|
|
d[1] = ffxReciprocal(a[1]);
|
||
|
|
d[2] = ffxReciprocal(a[2]);
|
||
|
|
return;
|
||
|
|
}
|
||
|
|
|
||
|
|
/// Convert FfxFloat32 to half (in lower 16-bits of output).
|
||
|
|
///
|
||
|
|
/// This function implements the same fast technique that is documented here: ftp://ftp.fox-toolkit.org/pub/fasthalffloatconversion.pdf
|
||
|
|
///
|
||
|
|
/// The function supports denormals.
|
||
|
|
///
|
||
|
|
/// Some conversion rules are to make computations possibly "safer" on the GPU,
|
||
|
|
/// -INF & -NaN -> -65504
|
||
|
|
/// +INF & +NaN -> +65504
|
||
|
|
///
|
||
|
|
/// @param [in] f The 32bit floating point value to convert.
|
||
|
|
///
|
||
|
|
/// @returns
|
||
|
|
/// The closest 16bit floating point value to <c><i>f</i></c>.
|
||
|
|
///
|
||
|
|
/// @ingroup CPU
|
||
|
|
FFX_STATIC FfxUInt32 f32tof16(FfxFloat32 f)
|
||
|
|
{
|
||
|
|
static FfxUInt16 base[512] = {
|
||
|
|
0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
|
||
|
|
0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
|
||
|
|
0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
|
||
|
|
0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
|
||
|
|
0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
|
||
|
|
0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0001, 0x0002, 0x0004, 0x0008, 0x0010, 0x0020, 0x0040, 0x0080, 0x0100, 0x0200, 0x0400,
|
||
|
|
0x0800, 0x0c00, 0x1000, 0x1400, 0x1800, 0x1c00, 0x2000, 0x2400, 0x2800, 0x2c00, 0x3000, 0x3400, 0x3800, 0x3c00, 0x4000, 0x4400, 0x4800, 0x4c00, 0x5000,
|
||
|
|
0x5400, 0x5800, 0x5c00, 0x6000, 0x6400, 0x6800, 0x6c00, 0x7000, 0x7400, 0x7800, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff,
|
||
|
|
0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff,
|
||
|
|
0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff,
|
||
|
|
0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff,
|
||
|
|
0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff,
|
||
|
|
0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff,
|
||
|
|
0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x7bff, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000,
|
||
|
|
0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000,
|
||
|
|
0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000,
|
||
|
|
0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000,
|
||
|
|
0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000,
|
||
|
|
0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8001, 0x8002,
|
||
|
|
0x8004, 0x8008, 0x8010, 0x8020, 0x8040, 0x8080, 0x8100, 0x8200, 0x8400, 0x8800, 0x8c00, 0x9000, 0x9400, 0x9800, 0x9c00, 0xa000, 0xa400, 0xa800, 0xac00,
|
||
|
|
0xb000, 0xb400, 0xb800, 0xbc00, 0xc000, 0xc400, 0xc800, 0xcc00, 0xd000, 0xd400, 0xd800, 0xdc00, 0xe000, 0xe400, 0xe800, 0xec00, 0xf000, 0xf400, 0xf800,
|
||
|
|
0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff,
|
||
|
|
0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff,
|
||
|
|
0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff,
|
||
|
|
0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff,
|
||
|
|
0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff,
|
||
|
|
0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff, 0xfbff
|
||
|
|
};
|
||
|
|
|
||
|
|
static FfxUInt8 shift[512] = {
|
||
|
|
0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
|
||
|
|
0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
|
||
|
|
0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
|
||
|
|
0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
|
||
|
|
0x18, 0x18, 0x18, 0x17, 0x16, 0x15, 0x14, 0x13, 0x12, 0x11, 0x10, 0x0f, 0x0e, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d,
|
||
|
|
0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
|
||
|
|
0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
|
||
|
|
0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
|
||
|
|
0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
|
||
|
|
0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
|
||
|
|
0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
|
||
|
|
0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
|
||
|
|
0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
|
||
|
|
0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
|
||
|
|
0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x17, 0x16, 0x15, 0x14, 0x13, 0x12, 0x11, 0x10, 0x0f, 0x0e, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d,
|
||
|
|
0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x18,
|
||
|
|
0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
|
||
|
|
0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
|
||
|
|
0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
|
||
|
|
0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
|
||
|
|
0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18
|
||
|
|
};
|
||
|
|
|
||
|
|
union
|
||
|
|
{
|
||
|
|
FfxFloat32 f;
|
||
|
|
FfxUInt32 u;
|
||
|
|
} bits;
|
||
|
|
|
||
|
|
bits.f = f;
|
||
|
|
FfxUInt32 u = bits.u;
|
||
|
|
FfxUInt32 i = u >> 23;
|
||
|
|
return (FfxUInt32)(base[i]) + ((u & 0x7fffff) >> shift[i]);
|
||
|
|
}
|
||
|
|
|
||
|
|
/// Pack 2x32-bit floating point values in a single 32bit value.
|
||
|
|
///
|
||
|
|
/// This function first converts each component of <c><i>value</i></c> into their nearest 16-bit floating
|
||
|
|
/// point representation, and then stores the X and Y components in the lower and upper 16 bits of the
|
||
|
|
/// 32bit unsigned integer respectively.
|
||
|
|
///
|
||
|
|
/// @param [in] value A 2-dimensional floating point value to convert and pack.
|
||
|
|
///
|
||
|
|
/// @returns
|
||
|
|
/// A packed 32bit value containing 2 16bit floating point values.
|
||
|
|
///
|
||
|
|
/// @ingroup CPU
|
||
|
|
FFX_STATIC FfxUInt32 packHalf2x16(FfxFloat32x2 a)
|
||
|
|
{
|
||
|
|
return f32tof16(a[0]) + (f32tof16(a[1]) << 16);
|
||
|
|
}
|