91 lines
2.2 KiB
Plaintext
91 lines
2.2 KiB
Plaintext
#pragma clang diagnostic ignored "-Wmissing-braces"
|
|
#pragma clang diagnostic ignored "-Wunused-variable"
|
|
|
|
#include <metal_stdlib>
|
|
#include <simd/simd.h>
|
|
#include <metal_atomic>
|
|
|
|
template <typename T, size_t Num>
|
|
struct unsafe_array
|
|
{
|
|
T __Elements[Num ? Num : 1];
|
|
|
|
constexpr size_t size() const thread { return Num; }
|
|
constexpr size_t max_size() const thread { return Num; }
|
|
constexpr bool empty() const thread { return Num == 0; }
|
|
|
|
constexpr size_t size() const device { return Num; }
|
|
constexpr size_t max_size() const device { return Num; }
|
|
constexpr bool empty() const device { return Num == 0; }
|
|
|
|
constexpr size_t size() const constant { return Num; }
|
|
constexpr size_t max_size() const constant { return Num; }
|
|
constexpr bool empty() const constant { return Num == 0; }
|
|
|
|
constexpr size_t size() const threadgroup { return Num; }
|
|
constexpr size_t max_size() const threadgroup { return Num; }
|
|
constexpr bool empty() const threadgroup { return Num == 0; }
|
|
|
|
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];
|
|
}
|
|
};
|
|
|
|
using namespace metal;
|
|
|
|
struct SSBO
|
|
{
|
|
unsafe_array<float,1> in_data;
|
|
};
|
|
|
|
struct SSBO2
|
|
{
|
|
unsafe_array<float,1> out_data;
|
|
};
|
|
|
|
struct SSBO3
|
|
{
|
|
uint count;
|
|
};
|
|
|
|
constant uint3 gl_WorkGroupSize [[maybe_unused]] = uint3(4u, 1u, 1u);
|
|
|
|
kernel void main0(const device SSBO& _22 [[buffer(0)]], device SSBO2& _38 [[buffer(1)]], device SSBO3& _41 [[buffer(2)]], uint3 gl_GlobalInvocationID [[thread_position_in_grid]])
|
|
{
|
|
float _28 = _22.in_data[gl_GlobalInvocationID.x];
|
|
if (_28 > 12.0)
|
|
{
|
|
uint _45 = atomic_fetch_add_explicit((device atomic_uint*)&_41.count, 1u, memory_order_relaxed);
|
|
_38.out_data[_45] = _28;
|
|
}
|
|
}
|
|
|