d92de00cc1
This is a fairly fundamental change on how IDs are handled.
It serves many purposes:
- Improve performance. We only need to iterate over IDs which are
relevant at any one time.
- Makes sure we iterate through IDs in SPIR-V module declaration order
rather than ID space. IDs don't have to be monotonically increasing,
which was an assumption SPIRV-Cross used to have. It has apparently
never been a problem until now.
- Support LUTs of structs. We do this by interleaving declaration of
constants and struct types in SPIR-V module order.
To support this, the ParsedIR interface needed to change slightly.
Before setting any ID with variant_set<T> we let ParsedIR know
that an ID with a specific type has been added. The surface for change
should be minimal.
ParsedIR will maintain a per-type list of IDs which the cross-compiler
will need to consider for later.
Instead of looping over ir.ids[] (which can be extremely large), we loop
over types now, using:
ir.for_each_typed_id<SPIRVariable>([&](uint32_t id, SPIRVariable &var) {
handle_variable(var);
});
Now we make sure that we're never looking at irrelevant types.
54 lines
1.4 KiB
Plaintext
54 lines
1.4 KiB
Plaintext
#pragma clang diagnostic ignored "-Wmissing-prototypes"
|
|
|
|
#include <metal_stdlib>
|
|
#include <simd/simd.h>
|
|
|
|
using namespace metal;
|
|
|
|
struct Data
|
|
{
|
|
float a;
|
|
float b;
|
|
};
|
|
|
|
struct Data_1
|
|
{
|
|
float a;
|
|
float b;
|
|
};
|
|
|
|
constant float X_tmp [[function_constant(0)]];
|
|
constant float X = is_function_constant_defined(X_tmp) ? X_tmp : 4.0;
|
|
|
|
struct SSBO
|
|
{
|
|
Data outdata[1];
|
|
};
|
|
|
|
constant uint3 gl_WorkGroupSize = uint3(2u, 1u, 1u);
|
|
|
|
constant Data_1 _25[2] = { Data_1{ 1.0, 2.0 }, Data_1{ 3.0, 4.0 } };
|
|
|
|
// Implementation of an array copy function to cover GLSL's ability to copy an array via assignment.
|
|
template<typename T, uint N>
|
|
void spvArrayCopyFromStack1(thread T (&dst)[N], thread const T (&src)[N])
|
|
{
|
|
for (uint i = 0; i < N; dst[i] = src[i], i++);
|
|
}
|
|
|
|
template<typename T, uint N>
|
|
void spvArrayCopyFromConstant1(thread T (&dst)[N], constant T (&src)[N])
|
|
{
|
|
for (uint i = 0; i < N; dst[i] = src[i], i++);
|
|
}
|
|
|
|
kernel void main0(device SSBO& _53 [[buffer(0)]], uint3 gl_WorkGroupID [[threadgroup_position_in_grid]], uint3 gl_LocalInvocationID [[thread_position_in_threadgroup]])
|
|
{
|
|
Data_1 _31[2] = { Data_1{ X, 2.0 }, Data_1{ 3.0, 5.0 } };
|
|
Data_1 data2[2];
|
|
spvArrayCopyFromStack1(data2, _31);
|
|
_53.outdata[gl_WorkGroupID.x].a = _25[gl_LocalInvocationID.x].a + data2[gl_LocalInvocationID.x].a;
|
|
_53.outdata[gl_WorkGroupID.x].b = _25[gl_LocalInvocationID.x].b + data2[gl_LocalInvocationID.x].b;
|
|
}
|
|
|