Each 8×8-tile workgroup previously had all 64 threads walk the entire item list, re-reading every item from the SSBO 64× and running the per-pixel reject for items that never touch the tile — O(tiles × N) item loads dominated by SSBO traffic. The workgroup now streams the item list in chunks of 64: each thread loads one item, tests its AABB against the whole tile, and the survivors are compacted — in original buffer order — into shared memory. Every thread then runs the unchanged per-pixel accumulate over only those survivors. This drops SSBO traffic ~64× (each item read once per workgroup instead of once per pixel) and shrinks the inner loop to the items that actually overlap the tile. Draw order is preserved exactly: chunks run in array order and the in-chunk compaction is a stable in-order scan, so later items still overdraw earlier ones (no atomic-append nondeterminism). The inner loop body is byte-for-byte the original per-pixel logic, so output is pixel-identical — the cull only decides which items reach it. Threads no longer early-return so every thread reaches the workgroup barriers. Applied to ui-quads, ui-circles, ui-images and ui-text; shared helpers (uiTileBounds / uiAabbOverlapsTile) live in ui-shared.glsl. Resolves #46 Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
109 lines
3.8 KiB
GLSL
109 lines
3.8 KiB
GLSL
#version 460
|
||
#extension GL_GOOGLE_include_directive : enable
|
||
#include "ui-shared.glsl"
|
||
|
||
// One workgroup per 8×8 screen tile. The workgroup cooperatively streams the
|
||
// GlyphItem list in chunks of 64 (see ui-shared.glsl), culling each chunk
|
||
// against the tile and compacting survivors — in buffer order — into shared
|
||
// memory; every thread then accumulates over only those survivors.
|
||
layout(push_constant) uniform PC {
|
||
UIDispatchHeader hdr;
|
||
uint fontTextureSlot;
|
||
uint fontSamplerSlot;
|
||
uint _p0;
|
||
uint _p1;
|
||
} pc;
|
||
|
||
layout(local_size_x = 8, local_size_y = 8, local_size_z = 1) in;
|
||
|
||
// SDF tuning — must match Crafter::FontAtlas::kOnEdgeValue / kPixelDistScale.
|
||
const float ON_EDGE = 128.0 / 255.0;
|
||
const float DIST_SCALE = 32.0;
|
||
|
||
shared vec4 s_rect[UI_CHUNK];
|
||
shared vec4 s_uv[UI_CHUNK];
|
||
shared vec4 s_color[UI_CHUNK];
|
||
shared uint s_keep[UI_CHUNK];
|
||
shared uint s_order[UI_CHUNK];
|
||
shared uint s_count;
|
||
|
||
void main() {
|
||
ivec2 screenPx;
|
||
bool valid = uiResolveScreenPixel(pc.hdr, screenPx);
|
||
|
||
vec4 dst = vec4(0.0);
|
||
vec2 sp = vec2(0.0);
|
||
if (valid) {
|
||
dst = imageLoad(uiImages[pc.hdr.outImage], screenPx);
|
||
sp = vec2(screenPx) + 0.5;
|
||
}
|
||
|
||
vec2 tileMin, tileMax;
|
||
uiTileBounds(tileMin, tileMax);
|
||
|
||
uint lid = gl_LocalInvocationIndex;
|
||
for (uint base = 0u; base < pc.hdr.itemCount; base += UI_CHUNK) {
|
||
uint idx = base + lid;
|
||
bool keep = false;
|
||
if (idx < pc.hdr.itemCount) {
|
||
s_rect[lid] = uiGlyphHeap[pc.hdr.itemBuffer].items[idx].rect;
|
||
s_uv[lid] = uiGlyphHeap[pc.hdr.itemBuffer].items[idx].uv;
|
||
s_color[lid] = uiGlyphHeap[pc.hdr.itemBuffer].items[idx].color;
|
||
keep = uiAabbOverlapsTile(s_rect[lid].xy, s_rect[lid].xy + s_rect[lid].zw,
|
||
tileMin, tileMax);
|
||
}
|
||
s_keep[lid] = keep ? 1u : 0u;
|
||
barrier();
|
||
|
||
if (lid == 0u) {
|
||
uint n = 0u;
|
||
uint lim = min(UI_CHUNK, pc.hdr.itemCount - base);
|
||
for (uint k = 0u; k < lim; ++k)
|
||
if (s_keep[k] != 0u) s_order[n++] = k;
|
||
s_count = n;
|
||
}
|
||
barrier();
|
||
|
||
if (valid) {
|
||
for (uint j = 0u; j < s_count; ++j) {
|
||
uint c = s_order[j];
|
||
|
||
vec2 lo = s_rect[c].xy;
|
||
vec2 hi = s_rect[c].xy + s_rect[c].zw;
|
||
if (sp.x < lo.x || sp.y < lo.y) continue;
|
||
if (sp.x >= hi.x || sp.y >= hi.y) continue;
|
||
|
||
vec2 t = (sp - s_rect[c].xy) / s_rect[c].zw;
|
||
vec2 uv = mix(s_uv[c].xy, s_uv[c].zw, t);
|
||
|
||
float sdf = texture(
|
||
sampler2D(uiTextures[nonuniformEXT(pc.fontTextureSlot)],
|
||
uiSamplers[nonuniformEXT(pc.fontSamplerSlot)]),
|
||
uv
|
||
).r;
|
||
|
||
// Distance in atlas-pixels (negative inside the glyph).
|
||
float dAtlas = (ON_EDGE - sdf) * DIST_SCALE;
|
||
|
||
// Atlas-px per screen-px along this glyph's transform — keeps AA crisp
|
||
// at any rendering size. uvSpan * atlasSize / screenSpan.
|
||
vec2 uvSpan = s_uv[c].zw - s_uv[c].xy;
|
||
// FontAtlas::kAtlasSize = 1024.
|
||
vec2 atlasPerScreen = (uvSpan * 1024.0) / s_rect[c].zw;
|
||
float scalePx = max(atlasPerScreen.x, atlasPerScreen.y);
|
||
// 1-screen-px AA band, expressed in atlas-pixel units of dAtlas.
|
||
float band = max(scalePx, 0.0001);
|
||
|
||
float a = clamp(0.5 - dAtlas / band, 0.0, 1.0);
|
||
if (a <= 0.0) continue;
|
||
|
||
vec4 col = s_color[c];
|
||
vec4 src = vec4(col.rgb, col.a * a);
|
||
dst = uiBlendOver(dst, src);
|
||
}
|
||
}
|
||
barrier();
|
||
}
|
||
|
||
if (valid) imageStore(uiImages[pc.hdr.outImage], screenPx, dst);
|
||
}
|