119 lines
2.9 KiB
Plaintext
119 lines
2.9 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 foo
|
|
{
|
|
unsafe_array<int,128> a;
|
|
uint b;
|
|
float2 c;
|
|
};
|
|
|
|
struct bar
|
|
{
|
|
int d;
|
|
};
|
|
|
|
static inline __attribute__((always_inline))
|
|
device foo* select_buffer(device foo& a, constant bar& cb)
|
|
{
|
|
return (cb.d != 0) ? &a : nullptr;
|
|
}
|
|
|
|
static inline __attribute__((always_inline))
|
|
thread uint3* select_input(thread uint3& gl_GlobalInvocationID, thread uint3& gl_LocalInvocationID, constant bar& cb)
|
|
{
|
|
return (cb.d != 0) ? &gl_GlobalInvocationID : &gl_LocalInvocationID;
|
|
}
|
|
|
|
kernel void main0(device foo& buf [[buffer(0)]], constant bar& cb [[buffer(1)]], uint3 gl_GlobalInvocationID [[thread_position_in_grid]], uint3 gl_LocalInvocationID [[thread_position_in_threadgroup]])
|
|
{
|
|
device foo* _46 = select_buffer(buf, cb);
|
|
device foo* _45 = _46;
|
|
device foo* _48 = _45;
|
|
device int* _52;
|
|
device int* _55;
|
|
_52 = &_48->a[0u];
|
|
_55 = &buf.a[0u];
|
|
int _57;
|
|
int _58;
|
|
for (;;)
|
|
{
|
|
_57 = *_52;
|
|
_58 = *_55;
|
|
if (_57 != _58)
|
|
{
|
|
int _66 = (_57 + _58) + int((*select_input(gl_GlobalInvocationID, gl_LocalInvocationID, cb)).x);
|
|
*_52 = _66;
|
|
*_55 = _66;
|
|
_52 = &_52[1u];
|
|
_55 = &_55[1u];
|
|
continue;
|
|
}
|
|
else
|
|
{
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
|