85 lines
2.3 KiB
Plaintext
85 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>
|
|
#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 u0_counters
|
|
{
|
|
uint c;
|
|
};
|
|
|
|
// Returns 2D texture coords corresponding to 1D texel buffer coords
|
|
static inline __attribute__((always_inline))
|
|
uint2 spvTexelBufferCoord(uint tc)
|
|
{
|
|
return uint2(tc % 4096, tc / 4096);
|
|
}
|
|
|
|
kernel void main0(device u0_counters& u0_counter [[buffer(0)]], texture2d<uint, access::write> u0 [[texture(0)]], uint3 gl_GlobalInvocationID [[thread_position_in_grid]])
|
|
{
|
|
uint _29 = atomic_fetch_add_explicit((device atomic_uint*)&u0_counter.c, 1, memory_order_relaxed);
|
|
float4 r0;
|
|
r0.x = as_type<float>(_29);
|
|
u0.write(uint4(uint(int(gl_GlobalInvocationID.x))), spvTexelBufferCoord(((uint(as_type<int>(r0.x)) * 1u) + (uint(0) >> 2u))));
|
|
}
|
|
|