2018-09-10 19:47:35 +00:00
|
|
|
#pragma clang diagnostic ignored "-Wmissing-prototypes"
|
|
|
|
#pragma clang diagnostic ignored "-Wunused-variable"
|
|
|
|
|
|
|
|
#include <metal_stdlib>
|
|
|
|
#include <simd/simd.h>
|
|
|
|
#include <metal_atomic>
|
|
|
|
|
|
|
|
using namespace metal;
|
|
|
|
|
|
|
|
struct u0_counters
|
|
|
|
{
|
|
|
|
uint c;
|
|
|
|
};
|
|
|
|
|
|
|
|
// Returns 2D texture coords corresponding to 1D texel buffer coords
|
2019-09-17 19:11:19 +00:00
|
|
|
static inline __attribute__((always_inline))
|
|
|
|
uint2 spvTexelBufferCoord(uint tc)
|
2018-09-10 19:47:35 +00:00
|
|
|
{
|
|
|
|
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]])
|
|
|
|
{
|
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
|
|
|
uint _29 = atomic_fetch_sub_explicit((device atomic_uint*)&u0_counter.c, 1, memory_order_relaxed);
|
2018-09-27 09:10:22 +00:00
|
|
|
u0.write(uint4(uint(int(gl_GlobalInvocationID.x))), spvTexelBufferCoord(as_type<int>(as_type<float>(_29))));
|
2018-09-10 19:47:35 +00:00
|
|
|
}
|
|
|
|
|