2019-08-14 15:09:39 +00:00
|
|
|
#pragma clang diagnostic ignored "-Wmissing-braces"
|
|
|
|
#pragma clang diagnostic ignored "-Wunused-variable"
|
|
|
|
|
2017-11-22 11:08:06 +00:00
|
|
|
#include <metal_stdlib>
|
|
|
|
#include <simd/simd.h>
|
2019-08-14 15:09:39 +00:00
|
|
|
|
|
|
|
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];
|
|
|
|
}
|
|
|
|
};
|
2017-11-22 11:08:06 +00:00
|
|
|
|
|
|
|
using namespace metal;
|
|
|
|
|
|
|
|
struct _6
|
|
|
|
{
|
|
|
|
int4 _m0;
|
|
|
|
uint4 _m1;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct _7
|
|
|
|
{
|
|
|
|
uint4 _m0;
|
|
|
|
int4 _m1;
|
|
|
|
};
|
|
|
|
|
MSL: Handle coherent, volatile, and restrict.
This maps them to their MSL equivalents. I've mapped `Coherent` to
`volatile` since MSL doesn't have anything weaker than `volatile` but
stronger than nothing.
As part of this, I had to remove the implicit `volatile` added for
atomic operation casts. If the buffer is already `coherent` or
`volatile`, then we would add a second `volatile`, which would be
redundant. I think this is OK even when the buffer *doesn't* have
`coherent`: `T *` is implicitly convertible to `volatile T *`, but not
vice-versa. It seems to compile OK at any rate. (Note that the
non-`volatile` overloads of the atomic functions documented in the spec
aren't present in the MSL 2.2 stdlib headers.)
`restrict` is tricky, because in MSL, as in C++, it needs to go *after*
the asterisk or ampersand for the pointer type it's modifying.
Another issue is that, in the `Simple`, `GLSL450`, and `Vulkan` memory
models, `Restrict` is the default (i.e. does not need to be specified);
but MSL likely follows the `OpenCL` model where `Aliased` is the
default. We probably need to implicitly set either `Restrict` or
`Aliased` depending on the module's declared memory model.
2019-07-10 16:17:40 +00:00
|
|
|
kernel void main0(device _6& restrict _8 [[buffer(0)]], device _7& restrict _9 [[buffer(1)]])
|
2017-11-22 11:08:06 +00:00
|
|
|
{
|
|
|
|
_9._m0 = _8._m1 + uint4(_8._m0);
|
|
|
|
_9._m0 = uint4(_8._m0) + _8._m1;
|
|
|
|
_9._m0 = _8._m1 + _8._m1;
|
|
|
|
_9._m0 = uint4(_8._m0 + _8._m0);
|
|
|
|
_9._m1 = int4(_8._m1 + _8._m1);
|
|
|
|
_9._m1 = _8._m0 + _8._m0;
|
|
|
|
_9._m1 = int4(_8._m1) + _8._m0;
|
|
|
|
_9._m1 = _8._m0 + int4(_8._m1);
|
|
|
|
}
|
|
|
|
|