fb5ee4cb5c
This command allows the caller to set the base value of `BuiltInWorkgroupId`, and thus of `BuiltInGlobalInvocationId`. Metal provides no direct support for this... but it does provide a builtin, `[[grid_origin]]`, normally used to pass the base values for the stage input region, which we will now abuse to pass the dispatch base and avoid burning a buffer binding. `[[grid_origin]]`, as part of Metal's support for compute stage input, requires MSL 1.2. For 1.0 and 1.1, we're forced to provide a buffer. (Curiously, this builtin was undocumented until the MSL 2.2 release. Go figure.)
42 lines
1.2 KiB
Plaintext
42 lines
1.2 KiB
Plaintext
#pragma clang diagnostic ignored "-Wunused-variable"
|
|
|
|
#include <metal_stdlib>
|
|
#include <simd/simd.h>
|
|
#include <metal_atomic>
|
|
|
|
using namespace metal;
|
|
|
|
struct SSBO
|
|
{
|
|
float4 in_data[1];
|
|
};
|
|
|
|
struct SSBO2
|
|
{
|
|
float4 out_data[1];
|
|
};
|
|
|
|
struct SSBO3
|
|
{
|
|
uint counter;
|
|
};
|
|
|
|
constant uint _59_tmp [[function_constant(10)]];
|
|
constant uint _59 = is_function_constant_defined(_59_tmp) ? _59_tmp : 1u;
|
|
constant uint3 gl_WorkGroupSize [[maybe_unused]] = uint3(_59, 1u, 1u);
|
|
|
|
kernel void main0(const device SSBO& _27 [[buffer(0)]], device SSBO2& _49 [[buffer(1)]], device SSBO3& _52 [[buffer(2)]], uint3 gl_GlobalInvocationID [[thread_position_in_grid]], uint3 gl_WorkGroupID [[threadgroup_position_in_grid]], uint3 spvDispatchBase [[grid_origin]])
|
|
{
|
|
gl_GlobalInvocationID += spvDispatchBase * gl_WorkGroupSize;
|
|
gl_WorkGroupID += spvDispatchBase;
|
|
uint ident = gl_GlobalInvocationID.x;
|
|
uint workgroup = gl_WorkGroupID.x;
|
|
float4 idata = _27.in_data[ident];
|
|
if (dot(idata, float4(1.0, 5.0, 6.0, 2.0)) > 8.19999980926513671875)
|
|
{
|
|
uint _56 = atomic_fetch_add_explicit((device atomic_uint*)&_52.counter, 1u, memory_order_relaxed);
|
|
_49.out_data[_56] = idata;
|
|
}
|
|
}
|
|
|