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.
33 lines
1.1 KiB
Plaintext
33 lines
1.1 KiB
Plaintext
#pragma clang diagnostic ignored "-Wmissing-prototypes"
|
|
|
|
#include <metal_stdlib>
|
|
#include <simd/simd.h>
|
|
|
|
using namespace metal;
|
|
|
|
struct SSBO
|
|
{
|
|
float out_data[1];
|
|
};
|
|
|
|
constant uint3 gl_WorkGroupSize = uint3(4u, 4u, 1u);
|
|
|
|
void work(threadgroup float (&foo)[4][4], thread uint3& gl_LocalInvocationID, thread uint& gl_LocalInvocationIndex, device SSBO& v_67, thread uint3& gl_GlobalInvocationID)
|
|
{
|
|
foo[gl_LocalInvocationID.x][gl_LocalInvocationID.y] = float(gl_LocalInvocationIndex);
|
|
threadgroup_barrier(mem_flags::mem_threadgroup);
|
|
float x = 0.0;
|
|
x += foo[gl_LocalInvocationID.x][0];
|
|
x += foo[gl_LocalInvocationID.x][1];
|
|
x += foo[gl_LocalInvocationID.x][2];
|
|
x += foo[gl_LocalInvocationID.x][3];
|
|
v_67.out_data[gl_GlobalInvocationID.x] = x;
|
|
}
|
|
|
|
kernel void main0(device SSBO& v_67 [[buffer(0)]], uint3 gl_LocalInvocationID [[thread_position_in_threadgroup]], uint gl_LocalInvocationIndex [[thread_index_in_threadgroup]], uint3 gl_GlobalInvocationID [[thread_position_in_grid]])
|
|
{
|
|
threadgroup float foo[4][4];
|
|
work(foo, gl_LocalInvocationID, gl_LocalInvocationIndex, v_67, gl_GlobalInvocationID);
|
|
}
|
|
|