119 lines
3.2 KiB
Plaintext
119 lines
3.2 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;
|
|
|
|
// Implementation of the GLSL findLSB() function
|
|
template<typename T>
|
|
<<<<<<< HEAD
|
|
inline T spvFindLSB(T x)
|
|
=======
|
|
static inline __attribute__((always_inline))
|
|
T findLSB(T x)
|
|
>>>>>>> 22755a0c... Update the Metal shaders to account for changes in the shader compilation.
|
|
{
|
|
return select(ctz(x), T(-1), x == T(0));
|
|
}
|
|
|
|
// Implementation of the signed GLSL findMSB() function
|
|
template<typename T>
|
|
<<<<<<< HEAD
|
|
inline T spvFindSMSB(T x)
|
|
=======
|
|
static inline __attribute__((always_inline))
|
|
T findSMSB(T x)
|
|
>>>>>>> 22755a0c... Update the Metal shaders to account for changes in the shader compilation.
|
|
{
|
|
T v = select(x, T(-1) - x, x < T(0));
|
|
return select(clz(T(0)) - (clz(v) + T(1)), T(-1), v == T(0));
|
|
}
|
|
|
|
// Implementation of the unsigned GLSL findMSB() function
|
|
template<typename T>
|
|
<<<<<<< HEAD
|
|
inline T spvFindUMSB(T x)
|
|
=======
|
|
static inline __attribute__((always_inline))
|
|
T findUMSB(T x)
|
|
>>>>>>> 22755a0c... Update the Metal shaders to account for changes in the shader compilation.
|
|
{
|
|
return select(clz(T(0)) - (clz(x) + T(1)), T(-1), x == T(0));
|
|
}
|
|
|
|
kernel void main0()
|
|
{
|
|
int signed_value = 0;
|
|
uint unsigned_value = 0u;
|
|
int s = extract_bits(signed_value, uint(5), uint(20));
|
|
uint u = extract_bits(unsigned_value, uint(6), uint(21));
|
|
s = insert_bits(s, 40, uint(5), uint(4));
|
|
u = insert_bits(u, 60u, uint(5), uint(4));
|
|
u = reverse_bits(u);
|
|
s = reverse_bits(s);
|
|
int v0 = int(popcount(u));
|
|
int v1 = popcount(s);
|
|
int v2 = int(spvFindUMSB(u));
|
|
int v3 = spvFindSMSB(s);
|
|
int v4 = int(spvFindLSB(u));
|
|
int v5 = spvFindLSB(s);
|
|
}
|
|
|