5b952d2cbf
We were passing arrays by value which the compiler fails to optimize, causing abyssal performance. To fix this, we need to consider that descriptors can be in constant or const device address spaces. Also, lone descriptors are passed by value, so we explicitly remove address space qualifiers. One failure case is when shader passes a texture/sampler array as an argument. It's all UniformConstant in SPIR-V, but in MSL it might be thread, const device or constant, so that won't work ... Global variable use works fine though, and that should cover 99.9999999% of use cases.
41 lines
910 B
GLSL
41 lines
910 B
GLSL
#pragma clang diagnostic ignored "-Wmissing-prototypes"
|
|
|
|
#include <metal_stdlib>
|
|
#include <simd/simd.h>
|
|
|
|
using namespace metal;
|
|
|
|
struct main0_out
|
|
{
|
|
float4 FragColor [[color(0)]];
|
|
};
|
|
|
|
struct main0_in
|
|
{
|
|
float2 vUV [[user(locn0)]];
|
|
};
|
|
|
|
static inline __attribute__((always_inline))
|
|
float4 foo(thread bool& gl_HelperInvocation, texture2d<float> uSampler, sampler uSamplerSmplr, thread float2& vUV)
|
|
{
|
|
float4 color;
|
|
if (!gl_HelperInvocation)
|
|
{
|
|
color = uSampler.sample(uSamplerSmplr, vUV, level(0.0));
|
|
}
|
|
else
|
|
{
|
|
color = float4(1.0);
|
|
}
|
|
return color;
|
|
}
|
|
|
|
fragment main0_out main0(main0_in in [[stage_in]], texture2d<float> uSampler [[texture(0)]], sampler uSamplerSmplr [[sampler(0)]])
|
|
{
|
|
main0_out out = {};
|
|
bool gl_HelperInvocation = simd_is_helper_thread();
|
|
out.FragColor = foo(gl_HelperInvocation, uSampler, uSamplerSmplr, in.vUV);
|
|
return out;
|
|
}
|
|
|