mirror of
https://github.com/italicsjenga/vello.git
synced 2024-10-18 07:21:30 +11:00
acb3933d94
This patch switches to a variable size encoding of draw objects. In addition to the CPU-side scene encoding, it changes the representation of intermediate per draw object state from the `Annotated` struct to a variable "info" encoding. In addition, the bounding boxes are moved to a separate array (for a more "structure of "arrays" approach). Data that's unchanged from the scene encoding is not copied. Rather, downstream stages can access the data from the scene buffer (reducing allocation and copying). Prefix sums, computed in `DrawMonoid` track the offset of both scene and intermediate data. The tags for the CPU-side encoding have been split into their own stream (again a change from AoS to SoA style). This is not necessarily the final form. There's some stuff (including at least one piet-gpu-derive type) that can be deleted. In addition, the linewidth field should probably move from the info to path-specific. Also, the 1:1 correspondence between draw object and path has not yet been broken. Closes #152
67 lines
1.4 KiB
HLSL
Generated
67 lines
1.4 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 path_bbox_alloc;
|
|
Alloc drawmonoid_alloc;
|
|
Alloc clip_alloc;
|
|
Alloc clip_bic_alloc;
|
|
Alloc clip_stack_alloc;
|
|
Alloc clip_bbox_alloc;
|
|
Alloc draw_bbox_alloc;
|
|
Alloc drawinfo_alloc;
|
|
uint n_trans;
|
|
uint n_path;
|
|
uint n_clip;
|
|
uint trans_offset;
|
|
uint linewidth_offset;
|
|
uint pathtag_offset;
|
|
uint pathseg_offset;
|
|
uint drawtag_offset;
|
|
uint drawdata_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(76))
|
|
{
|
|
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();
|
|
}
|