688c5fcbda
This should hopefully reduce underutilization of the GPU, especially on GPUs where the thread execution width is greater than the number of control points. This also simplifies initialization by reading the buffer directly instead of using Metal's vertex-attribute-in-compute support. It turns out the only way in which shader stages are allowed to differ in their interfaces is in the number of components per vector; the base type must be the same. Since we are using the raw buffer instead of attributes, we can now also emit arrays and matrices directly into the buffer, instead of flattening them and then unpacking them. Structs are still flattened, however; this is due to the need to handle vectors with fewer components than were output, and I think handling this while also directly emitting structs could get ugly. Another advantage of this scheme is that the extra invocations needed to read the attributes when there were more input than output points are now no more. The number of threads per workgroup is now lcm(SIMD-size, output control points). This should ensure we always process a whole number of patches per workgroup. To avoid complexity handling indices in the tessellation control shader, I've also changed the way vertex shaders for tessellation are handled. They are now compute kernels using Metal's support for vertex-style stage input. This lets us always emit vertices into the buffer in order of vertex shader execution. Now we no longer have to deal with indexing in the tessellation control shader. This also fixes a long-standing issue where if an index were greater than the number of vertices to draw, the vertex shader would wind up writing outside the buffer, and the vertex would be lost. This is a breaking change, and I know SPIRV-Cross has other clients, so I've hidden this behind an option for now. In the future, I want to remove this option and make it the default.
69 lines
2.5 KiB
GLSL
69 lines
2.5 KiB
GLSL
#pragma clang diagnostic ignored "-Wmissing-prototypes"
|
|
#pragma clang diagnostic ignored "-Wmissing-braces"
|
|
|
|
#include <metal_stdlib>
|
|
#include <simd/simd.h>
|
|
|
|
using namespace metal;
|
|
|
|
template<typename T, size_t Num>
|
|
struct spvUnsafeArray
|
|
{
|
|
T elements[Num ? Num : 1];
|
|
|
|
thread T& operator [] (size_t pos) thread
|
|
{
|
|
return elements[pos];
|
|
}
|
|
constexpr const thread T& operator [] (size_t pos) const thread
|
|
{
|
|
return elements[pos];
|
|
}
|
|
|
|
device T& operator [] (size_t pos) device
|
|
{
|
|
return elements[pos];
|
|
}
|
|
constexpr const device T& operator [] (size_t pos) const device
|
|
{
|
|
return elements[pos];
|
|
}
|
|
|
|
constexpr const constant T& operator [] (size_t pos) const constant
|
|
{
|
|
return elements[pos];
|
|
}
|
|
|
|
threadgroup T& operator [] (size_t pos) threadgroup
|
|
{
|
|
return elements[pos];
|
|
}
|
|
constexpr const threadgroup T& operator [] (size_t pos) const threadgroup
|
|
{
|
|
return elements[pos];
|
|
}
|
|
};
|
|
|
|
struct main0_out
|
|
{
|
|
float4x4 vOutputs;
|
|
};
|
|
|
|
struct main0_in
|
|
{
|
|
float4x4 vInputs;
|
|
};
|
|
|
|
kernel void main0(uint3 gl_GlobalInvocationID [[thread_position_in_grid]], device main0_out* spvOut [[buffer(28)]], constant uint* spvIndirectParams [[buffer(29)]], device MTLQuadTessellationFactorsHalf* spvTessLevel [[buffer(26)]], device main0_in* spvIn [[buffer(22)]])
|
|
{
|
|
device main0_out* gl_out = &spvOut[gl_GlobalInvocationID.x - gl_GlobalInvocationID.x % 4];
|
|
device main0_in* gl_in = &spvIn[min(gl_GlobalInvocationID.x / 4, spvIndirectParams[1] - 1) * spvIndirectParams[0]];
|
|
uint gl_InvocationID = gl_GlobalInvocationID.x % 4;
|
|
uint gl_PrimitiveID = min(gl_GlobalInvocationID.x / 4, spvIndirectParams[1]);
|
|
spvUnsafeArray<float4x4, 32> _16 = spvUnsafeArray<float4x4, 32>({ gl_in[0].vInputs, gl_in[1].vInputs, gl_in[2].vInputs, gl_in[3].vInputs, gl_in[4].vInputs, gl_in[5].vInputs, gl_in[6].vInputs, gl_in[7].vInputs, gl_in[8].vInputs, gl_in[9].vInputs, gl_in[10].vInputs, gl_in[11].vInputs, gl_in[12].vInputs, gl_in[13].vInputs, gl_in[14].vInputs, gl_in[15].vInputs, gl_in[16].vInputs, gl_in[17].vInputs, gl_in[18].vInputs, gl_in[19].vInputs, gl_in[20].vInputs, gl_in[21].vInputs, gl_in[22].vInputs, gl_in[23].vInputs, gl_in[24].vInputs, gl_in[25].vInputs, gl_in[26].vInputs, gl_in[27].vInputs, gl_in[28].vInputs, gl_in[29].vInputs, gl_in[30].vInputs, gl_in[31].vInputs });
|
|
spvUnsafeArray<float4x4, 32> tmp;
|
|
tmp = _16;
|
|
gl_out[gl_InvocationID].vOutputs = tmp[gl_InvocationID];
|
|
}
|
|
|