#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 SSBO
{
    spvUnsafeArray<float, 1> in_data;
};

struct SSBO2
{
    spvUnsafeArray<float, 1> out_data;
};

constant uint3 gl_WorkGroupSize [[maybe_unused]] = uint3(4u, 1u, 1u);

kernel void main0(const device SSBO& _22 [[buffer(0)]], device SSBO2& _44 [[buffer(1)]], uint3 gl_GlobalInvocationID [[thread_position_in_grid]], uint gl_LocalInvocationIndex [[thread_index_in_threadgroup]])
{
    threadgroup float sShared[4];
    uint ident = gl_GlobalInvocationID.x;
    float idata = _22.in_data[ident];
    sShared[gl_LocalInvocationIndex] = idata;
    threadgroup_barrier(mem_flags::mem_threadgroup);
    _44.out_data[ident] = sShared[(4u - gl_LocalInvocationIndex) - 1u];
}