vello/piet-gpu/shader/gen/bbox_clear.hlsl
Raph Levien 3b67a4e7c1 New clip implementation
This PR reworks the clip implementation. The highlight is that clip bounding box accounting is now done on GPU rather than CPU. The clip mask is also rasterized on EndClip rather than BeginClip, which decreases memory traffic needed for the clip stack.

This is a pretty good working state, but not all cleanup has been applied. An important next step is to remove the CPU clip accounting (it is computed and encoded, but that result is not used). Another step is to remove the Annotated structure entirely.

Fixes #88. Also relevant to #119
2022-02-17 17:13:28 -08:00

63 lines
1.3 KiB
HLSL
Generated

struct Alloc
{
uint offset;
};
struct Config
{
uint n_elements;
uint n_pathseg;
uint width_in_tiles;
uint height_in_tiles;
Alloc tile_alloc;
Alloc bin_alloc;
Alloc ptcl_alloc;
Alloc pathseg_alloc;
Alloc anno_alloc;
Alloc trans_alloc;
Alloc bbox_alloc;
Alloc drawmonoid_alloc;
Alloc clip_alloc;
Alloc clip_bic_alloc;
Alloc clip_stack_alloc;
Alloc clip_bbox_alloc;
uint n_trans;
uint n_path;
uint n_clip;
uint trans_offset;
uint linewidth_offset;
uint pathtag_offset;
uint pathseg_offset;
};
static const uint3 gl_WorkGroupSize = uint3(512u, 1u, 1u);
ByteAddressBuffer _21 : register(t1, space0);
RWByteAddressBuffer _45 : register(u0, space0);
static uint3 gl_GlobalInvocationID;
struct SPIRV_Cross_Input
{
uint3 gl_GlobalInvocationID : SV_DispatchThreadID;
};
void comp_main()
{
uint ix = gl_GlobalInvocationID.x;
if (ix < _21.Load(68))
{
uint out_ix = (_21.Load(40) >> uint(2)) + (6u * ix);
_45.Store(out_ix * 4 + 8, 65535u);
_45.Store((out_ix + 1u) * 4 + 8, 65535u);
_45.Store((out_ix + 2u) * 4 + 8, 0u);
_45.Store((out_ix + 3u) * 4 + 8, 0u);
}
}
[numthreads(512, 1, 1)]
void main(SPIRV_Cross_Input stage_input)
{
gl_GlobalInvocationID = stage_input.gl_GlobalInvocationID;
comp_main();
}