BZLZHH 7db5b35a3e [Perf] (MG_State): remember every dirty rect, not just their union ...

A Minecraft frame updates ~95 scattered 16x16 sprites in a 1024x512
atlas; MipmapStorage's single union dirty box turned ~95KB of changed
texels into a ~2MB upload on every backend. The storage now keeps a
bounded (96-slot) list of pairwise-disjoint dirty rects BEHIND the
untouched union box: rects cascade-merge on touch or overlap, overflow
folds the pair with minimum enlargement and re-cascades, whole-level
dirties and respecifies just clear the list (empty list = "union box
tells all"). GetDirtyRects hands the list out only when it has 2+
rects, fits the caller's capacity, and its summed area is under 75% of
the union box - fewer driver calls beat equal bytes - so consumers can
never stage more than the union box did.

The list is maintained inside the same four mutation funnels every
texel writer already goes through (MarkDirty, MarkDirtyRegion,
AllocateLevel, TruncateToLevelCount - callers enumerated at the
declaration), so list and union box cannot disagree. Backends OPT IN:
the union-box API and its update order are byte-identical, and an
unmodified backend keeps rendering exactly as before.

96 slots is measured, not guessed: on the bench's 95-sprite lattice a
16-slot list collapses to >93% of the union box, 96 slots reach 4.8%
(~2MB -> ~95KB staged per frame). Verified by a 2859-check fuzz run
against a reference dirty bitmap (union exactness, full coverage,
disjointness, bounds, profitability). Unit tests 421/421.

2026-08-06 20:17:19 -04:00

..

EGLState

[Refactor] (Lifecycle): own MobileGL's lifecycle from the EGL layer instead of ELF static ctor/dtor - the first EGL/WGL entry point lazily initializes via a thread-safe, re-init-capable EnsureInitialized (AutoInit is gone), the last eglTerminate with no initialized display and nothing current tears the whole library down deterministically inside the EGL lifecycle, and the global singletons move to leak-at-exit heap storage so process exit runs no backend destructors at all (AutoDestroy and the Windows DllMain abandon hook are gone); fixes the exit-time SIGABRT from undefined static-destruction order - the DirectGLES buffer-pool mutex abort on Android clean exits, and the pre-existing macOS QueryTest/ProgramTest 'Subprocess aborted' gtest failures now pass (ctest 411/411)

2026-07-26 10:59:14 -04:00

GLState

[Perf] (MG_State): remember every dirty rect, not just their union

2026-08-06 20:17:19 -04:00