90 lines
2.3 KiB
Plaintext
90 lines
2.3 KiB
Plaintext
#pragma clang diagnostic ignored "-Wmissing-prototypes"
|
|
#pragma clang diagnostic ignored "-Wmissing-braces"
|
|
#pragma clang diagnostic ignored "-Wunused-variable"
|
|
|
|
#include <metal_stdlib>
|
|
#include <simd/simd.h>
|
|
|
|
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<uint,1> _data;
|
|
};
|
|
|
|
static inline __attribute__((always_inline))
|
|
void Load(thread const uint& size, const device ssbo& ssbo_1)
|
|
{
|
|
int byteAddrTemp = int(size >> uint(2));
|
|
uint4 data = uint4(ssbo_1._data[byteAddrTemp], ssbo_1._data[byteAddrTemp + 1], ssbo_1._data[byteAddrTemp + 2], ssbo_1._data[byteAddrTemp + 3]);
|
|
}
|
|
|
|
static inline __attribute__((always_inline))
|
|
void _main(thread const uint3& id, const device ssbo& ssbo_1)
|
|
{
|
|
uint param = 4u;
|
|
Load(param, ssbo_1);
|
|
}
|
|
|
|
kernel void main0(const device ssbo& ssbo_1 [[buffer(0)]], uint3 gl_GlobalInvocationID [[thread_position_in_grid]])
|
|
{
|
|
uint3 id = gl_GlobalInvocationID;
|
|
uint3 param = id;
|
|
_main(param, ssbo_1);
|
|
}
|
|
|