39dce88d3b
This change introduces functions and in one case, a class, to support the `VK_KHR_sampler_ycbcr_conversion` extension. Except in the case of GBGR8 and BGRG8 formats, for which Metal natively supports implicit chroma reconstruction, we're on our own here. We have to do everything ourselves. Much of the complexity comes from the need to support multiple planes, which must now be passed to functions that use the corresponding combined image-samplers. The rest is from the actual Y'CbCr conversion itself, which requires additional post-processing of the sample retrieved from the image. Passing sampled images to a function was a particular problem. To support this, I've added a new class which is emitted to MSL shaders that pass sampled images with Y'CbCr conversions attached around. It can handle sampled images with or without Y'CbCr conversion. This is an awful abomination that should not exist, but I'm worried that there's some shader out there which does this. This support requires Metal 2.0 to work properly, because it uses default-constructed texture objects, which were only added in MSL 2. I'm not even going to get into arrays of combined image-samplers--that's a whole other can of worms. They are deliberately unsupported in this change. I've taken the liberty of refactoring the support for texture swizzling while I'm at it. It's now treated as a post-processing step similar to Y'CbCr conversion. I'd like to think this is cleaner than having everything in `to_function_name()`/`to_function_args()`. It still looks really hairy, though. I did, however, get rid of the explicit type arguments to `spvGatherSwizzle()`/`spvGatherCompareSwizzle()`. Update the C API. In addition to supporting this new functionality, add some compiler options that I added in previous changes, but for which I neglected to update the C API.
112 lines
3.7 KiB
GLSL
112 lines
3.7 KiB
GLSL
#pragma clang diagnostic ignored "-Wmissing-prototypes"
|
|
|
|
#include <metal_stdlib>
|
|
#include <simd/simd.h>
|
|
|
|
using namespace metal;
|
|
|
|
struct spvDescriptorSetBuffer0
|
|
{
|
|
array<texture2d<float>, 4> uSampler0 [[id(0)]];
|
|
array<sampler, 4> uSampler0Smplr [[id(4)]];
|
|
constant uint* spvSwizzleConstants [[id(8)]];
|
|
};
|
|
|
|
struct main0_out
|
|
{
|
|
float4 FragColor [[color(0)]];
|
|
};
|
|
|
|
struct main0_in
|
|
{
|
|
float2 vUV [[user(locn0)]];
|
|
};
|
|
|
|
template<typename T> struct spvRemoveReference { typedef T type; };
|
|
template<typename T> struct spvRemoveReference<thread T&> { typedef T type; };
|
|
template<typename T> struct spvRemoveReference<thread T&&> { typedef T type; };
|
|
template<typename T> inline constexpr thread T&& spvForward(thread typename spvRemoveReference<T>::type& x)
|
|
{
|
|
return static_cast<thread T&&>(x);
|
|
}
|
|
template<typename T> inline constexpr thread T&& spvForward(thread typename spvRemoveReference<T>::type&& x)
|
|
{
|
|
return static_cast<thread T&&>(x);
|
|
}
|
|
|
|
enum class spvSwizzle : uint
|
|
{
|
|
none = 0,
|
|
zero,
|
|
one,
|
|
red,
|
|
green,
|
|
blue,
|
|
alpha
|
|
};
|
|
|
|
template<typename T>
|
|
inline T spvGetSwizzle(vec<T, 4> x, T c, spvSwizzle s)
|
|
{
|
|
switch (s)
|
|
{
|
|
case spvSwizzle::none:
|
|
return c;
|
|
case spvSwizzle::zero:
|
|
return 0;
|
|
case spvSwizzle::one:
|
|
return 1;
|
|
case spvSwizzle::red:
|
|
return x.r;
|
|
case spvSwizzle::green:
|
|
return x.g;
|
|
case spvSwizzle::blue:
|
|
return x.b;
|
|
case spvSwizzle::alpha:
|
|
return x.a;
|
|
}
|
|
}
|
|
|
|
// Wrapper function that swizzles texture samples and fetches.
|
|
template<typename T>
|
|
inline vec<T, 4> spvTextureSwizzle(vec<T, 4> x, uint s)
|
|
{
|
|
if (!s)
|
|
return x;
|
|
return vec<T, 4>(spvGetSwizzle(x, x.r, spvSwizzle((s >> 0) & 0xFF)), spvGetSwizzle(x, x.g, spvSwizzle((s >> 8) & 0xFF)), spvGetSwizzle(x, x.b, spvSwizzle((s >> 16) & 0xFF)), spvGetSwizzle(x, x.a, spvSwizzle((s >> 24) & 0xFF)));
|
|
}
|
|
|
|
template<typename T>
|
|
inline T spvTextureSwizzle(T x, uint s)
|
|
{
|
|
return spvTextureSwizzle(vec<T, 4>(x, 0, 0, 1), s).x;
|
|
}
|
|
|
|
inline float4 sample_in_func_1(thread const array<texture2d<float>, 4> uSampler0, thread const array<sampler, 4> uSampler0Smplr, constant uint* uSampler0Swzl, thread float2& vUV)
|
|
{
|
|
return spvTextureSwizzle(uSampler0[2].sample(uSampler0Smplr[2], vUV), uSampler0Swzl[2]);
|
|
}
|
|
|
|
inline float4 sample_in_func_2(thread float2& vUV, thread texture2d<float> uSampler1, thread const sampler uSampler1Smplr, constant uint& uSampler1Swzl)
|
|
{
|
|
return spvTextureSwizzle(uSampler1.sample(uSampler1Smplr, vUV), uSampler1Swzl);
|
|
}
|
|
|
|
inline float4 sample_single_in_func(thread const texture2d<float> s, thread const sampler sSmplr, constant uint& sSwzl, thread float2& vUV)
|
|
{
|
|
return spvTextureSwizzle(s.sample(sSmplr, vUV), sSwzl);
|
|
}
|
|
|
|
fragment main0_out main0(main0_in in [[stage_in]], constant spvDescriptorSetBuffer0& spvDescriptorSet0 [[buffer(0)]], constant uint* spvSwizzleConstants [[buffer(30)]], texture2d<float> uSampler1 [[texture(0)]], sampler uSampler1Smplr [[sampler(0)]])
|
|
{
|
|
main0_out out = {};
|
|
constant uint* spvDescriptorSet0_uSampler0Swzl = &spvDescriptorSet0.spvSwizzleConstants[0];
|
|
constant uint& uSampler1Swzl = spvSwizzleConstants[0];
|
|
out.FragColor = sample_in_func_1(spvDescriptorSet0.uSampler0, spvDescriptorSet0.uSampler0Smplr, spvDescriptorSet0_uSampler0Swzl, in.vUV);
|
|
out.FragColor += sample_in_func_2(in.vUV, uSampler1, uSampler1Smplr, uSampler1Swzl);
|
|
out.FragColor += sample_single_in_func(spvDescriptorSet0.uSampler0[1], spvDescriptorSet0.uSampler0Smplr[1], spvDescriptorSet0_uSampler0Swzl[1], in.vUV);
|
|
out.FragColor += sample_single_in_func(uSampler1, uSampler1Smplr, uSampler1Swzl, in.vUV);
|
|
return out;
|
|
}
|
|
|