R/Ryujinx.Graphics.Vulkan/Shaders/ColorCopyBetweenMsNonMs.comp
gdkchan f82309fa2d
Vulkan: Implement multisample <-> non-multisample copies and depth-stencil resolve (#3723)
* Vulkan: Implement multisample <-> non-multisample copies and depth-stencil resolve

* FramebufferParams is no longer required there

* Implement Specialization Constants and merge CopyMS Shaders (#15)

* Vulkan: Initial Specialization Constants

* Replace with specialized helper shader

* Reimplement everything

Fix nonexistant interaction with Ryu pipeline caching
Decouple specialization info from data and relocate them
Generalize mapping and add type enum to better match spv types
Use local fixed scopes instead of global unmanaged allocs

* Fix misses in initial implementation

Use correct info variable in Create2DLayerView
Add ShaderStorageImageMultisample to required feature set

* Use texture for source image

* No point in using ReadOnlyMemory

* Apply formatting feedback

Co-authored-by: gdkchan <gab.dark.100@gmail.com>

* Apply formatting suggestions on shader source

Co-authored-by: gdkchan <gab.dark.100@gmail.com>

Co-authored-by: gdkchan <gab.dark.100@gmail.com>

* Support conversion with samples count that does not match the requested count, other minor changes

Co-authored-by: mageven <62494521+mageven@users.noreply.github.com>
2022-11-02 18:17:19 -03:00

89 lines
No EOL
2.5 KiB
Text

#version 450 core
// +ve for MsToNonMs, -ve for reverse
layout (constant_id = 0) const int convType = 0;
layout (std140, binding = 0) uniform sample_counts_log2_in
{
ivec4 sample_counts_log2;
};
#define R8_ID 1
#define R16_ID 2
#define R32_ID 4
#define RG32_ID 8
#define RGBA32_ID 16
#define R8_TYPE r8ui
#define R16_TYPE r16ui
#define R32_TYPE r32ui
#define RG32_TYPE rg32ui
#define RGBA32_TYPE rgba32ui
#define DECLARE_BINDINGS(type) layout (set = 3, binding = 0, type##_TYPE) uniform uimage2DMS dstMS ## type; \
layout (set = 3, binding = 0, type##_TYPE) uniform uimage2D dst ## type;
#define CASE_SIZE(type) case type##_ID: imageSz = imageSize(dst ## type); break;
#define CASE_CONVERT(type) case type##_ID: imageStore(dst ## type, ivec2(coords), texelFetch(srcMS, shiftedCoords, sampleIdx)); break; \
case -type##_ID: imageStore(dstMS ## type, shiftedCoords, sampleIdx, texelFetch(src, ivec2(coords), 0)); break;
// src tex
layout (set = 2, binding = 0) uniform usampler2DMS srcMS;
layout (set = 2, binding = 0) uniform usampler2D src;
// dst img
DECLARE_BINDINGS(R8)
DECLARE_BINDINGS(R16)
DECLARE_BINDINGS(R32)
DECLARE_BINDINGS(RG32)
DECLARE_BINDINGS(RGBA32)
layout (local_size_x = 32, local_size_y = 32, local_size_z = 1) in;
void main()
{
uvec2 coords = gl_GlobalInvocationID.xy;
ivec2 imageSz = ivec2(0, 0);
switch (convType)
{
case 0: break;
CASE_SIZE(R8 )
CASE_SIZE(R16 )
CASE_SIZE(R32 )
CASE_SIZE(RG32 )
CASE_SIZE(RGBA32)
default:
imageSz = textureSize(src, 0);
break;
}
if (int(coords.x) >= imageSz.x || int(coords.y) >= imageSz.y)
{
return;
}
int deltaX = sample_counts_log2.x - sample_counts_log2.z;
int deltaY = sample_counts_log2.y - sample_counts_log2.w;
int samplesInXLog2 = sample_counts_log2.z;
int samplesInYLog2 = sample_counts_log2.w;
int samplesInX = 1 << samplesInXLog2;
int samplesInY = 1 << samplesInYLog2;
int sampleIdx = ((int(coords.x) >> deltaX) & (samplesInX - 1)) | (((int(coords.y) >> deltaY) & (samplesInY - 1)) << samplesInXLog2);
samplesInXLog2 = sample_counts_log2.x;
samplesInYLog2 = sample_counts_log2.y;
ivec2 shiftedCoords = ivec2(int(coords.x) >> samplesInXLog2, int(coords.y) >> samplesInYLog2);
switch (convType)
{
CASE_CONVERT(R8 )
CASE_CONVERT(R16 )
CASE_CONVERT(R32 )
CASE_CONVERT(RG32 )
CASE_CONVERT(RGBA32)
}
}