#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
{
    float4 values[1];
};

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

static inline __attribute__((always_inline))
void in_function(threadgroup spvUnsafeArray<short4, 4>& foo, thread uint& gl_LocalInvocationIndex, device SSBO& _23, thread uint3& gl_GlobalInvocationID)
{
    foo[gl_LocalInvocationIndex] = short4(_23.values[gl_GlobalInvocationID.x] != float4(10.0));
    threadgroup_barrier(mem_flags::mem_threadgroup);
    _23.values[gl_GlobalInvocationID.x] = select(float4(40.0), float4(30.0), bool4(foo[gl_LocalInvocationIndex ^ 3u]));
}

kernel void main0(device SSBO& _23 [[buffer(0)]], uint gl_LocalInvocationIndex [[thread_index_in_threadgroup]], uint3 gl_GlobalInvocationID [[thread_position_in_grid]])
{
    threadgroup spvUnsafeArray<short4, 4> foo;
    in_function(foo, gl_LocalInvocationIndex, _23, gl_GlobalInvocationID);
}