2019-08-14 15:09:39 +00:00
|
|
|
#pragma clang diagnostic ignored "-Wmissing-braces"
|
|
|
|
#pragma clang diagnostic ignored "-Wunused-variable"
|
|
|
|
|
MSL: Add support for subgroup operations.
Some support for subgroups is present starting in Metal 2.0 on both iOS
and macOS. macOS gains more complete support in 10.14 (Metal 2.1).
Some restrictions are present. On iOS and on macOS 10.13, the
implementation of `OpGroupNonUniformElect` is incorrect: if thread 0 has
already terminated or is not executing a conditional branch, the first
thread that *is* will falsely believe itself not to be. Unfortunately,
this operation is part of the "basic" feature set; without it, subgroups
cannot be supported at all.
The `SubgroupSize` and `SubgroupLocalInvocationId` builtins are only
available in compute shaders (and, by extension, tessellation control
shaders), despite SPIR-V making them available in all stages. This
limits the usefulness of some of the subgroup operations in fragment
shaders.
Although Metal on macOS supports some clustered, inclusive, and
exclusive operations, it does not support them all. In particular,
inclusive and exclusive min, max, and, or, and xor; as well as cluster
sizes other than 4 are not supported. If this becomes a problem, they
could be emulated, but at a significant performance cost due to the need
for non-uniform operations.
2019-05-15 21:03:30 +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];
|
|
|
|
}
|
|
|
|
};
|
MSL: Add support for subgroup operations.
Some support for subgroups is present starting in Metal 2.0 on both iOS
and macOS. macOS gains more complete support in 10.14 (Metal 2.1).
Some restrictions are present. On iOS and on macOS 10.13, the
implementation of `OpGroupNonUniformElect` is incorrect: if thread 0 has
already terminated or is not executing a conditional branch, the first
thread that *is* will falsely believe itself not to be. Unfortunately,
this operation is part of the "basic" feature set; without it, subgroups
cannot be supported at all.
The `SubgroupSize` and `SubgroupLocalInvocationId` builtins are only
available in compute shaders (and, by extension, tessellation control
shaders), despite SPIR-V making them available in all stages. This
limits the usefulness of some of the subgroup operations in fragment
shaders.
Although Metal on macOS supports some clustered, inclusive, and
exclusive operations, it does not support them all. In particular,
inclusive and exclusive min, max, and, or, and xor; as well as cluster
sizes other than 4 are not supported. If this becomes a problem, they
could be emulated, but at a significant performance cost due to the need
for non-uniform operations.
2019-05-15 21:03:30 +00:00
|
|
|
|
|
|
|
using namespace metal;
|
|
|
|
|
|
|
|
struct SSBO
|
|
|
|
{
|
|
|
|
float FragColor;
|
|
|
|
};
|
|
|
|
|
|
|
|
kernel void main0(device SSBO& _9 [[buffer(0)]], uint gl_NumSubgroups [[quadgroups_per_threadgroup]], uint gl_SubgroupID [[quadgroup_index_in_threadgroup]], uint gl_SubgroupSize [[thread_execution_width]], uint gl_SubgroupInvocationID [[thread_index_in_quadgroup]])
|
|
|
|
{
|
|
|
|
_9.FragColor = float(gl_NumSubgroups);
|
|
|
|
_9.FragColor = float(gl_SubgroupID);
|
|
|
|
_9.FragColor = float(gl_SubgroupSize);
|
|
|
|
_9.FragColor = float(gl_SubgroupInvocationID);
|
|
|
|
simdgroup_barrier(mem_flags::mem_device | mem_flags::mem_threadgroup | mem_flags::mem_texture);
|
|
|
|
simdgroup_barrier(mem_flags::mem_device | mem_flags::mem_threadgroup | mem_flags::mem_texture);
|
|
|
|
simdgroup_barrier(mem_flags::mem_device);
|
|
|
|
simdgroup_barrier(mem_flags::mem_threadgroup);
|
|
|
|
simdgroup_barrier(mem_flags::mem_texture);
|
|
|
|
}
|
|
|
|
|