Repacked copies and depth stencil copies allocated device-local memory
directly and stopped the title on a refusal; they now take the same
allocation path as the other images. Device buffers choose their host
fallback type the same way, the host placement line carries the cumulative
MiB, and the debt file records that a placed image stays in host memory
for its lifetime.
A queue that delivered an end-of-pipe interrupt from its own release stopped
delivering the flip's event for the rest of the run, so a title that raises a
release interrupt once and then waits on the flip event never saw it again.
Count the flips a queue has taken since its last delivered release interrupt:
four consecutive flips keep the latch, a fifth clears it and raises the event,
so the queue recovers within five flips. Gran Turismo 7 (PPSA01317) pairs two
flips with one release interrupt per frame, which stays under the limit, and a
title that flips without further release interrupts recovers.
Extend agc_driver_eop_interrupts: a latched queue still delivers its own
releases, flips keep reaching the video output while their event is suppressed,
an event returns once the latch clears, and a release followed by two flips
raises none.
ARCHITECTURE.md and the libSceAgcDriver debt entry now say that a
settled Windows import under 1 MiB returns to the write watch only when
no storage image overlaps it, and why.
Compute LDS beyond the device's shared-memory limit lives in a storage
buffer, and its 64-bit atomics took a lock in that buffer. AMD's Windows
driver compiles the lock's acquire and release to s_barrier, which inside
the divergent lock loop pairs with the program's own barriers, so the
device-memory case of agc_driver_lds_lock_budget read half its sum.
With shaderBufferInt64Atomics the device-memory LDS now uses a 64-bit view
of the buffer instead: 64-bit atomics are compare-exchange loops on it and
32-bit atomics stay native, so no lock is taken. Without the feature the
lock is kept. The per-workgroup slice is rounded up to an even dword count
so that the 64-bit view stays aligned.
A sampled 32_UINT or 32_SINT T# with a depth swizzle that no live depth
surface matches threw, while the 16-bit case already falls back to guest
memory through an R16_UNORM view. The 32-bit case now reads the guest
bytes through an R32_SFLOAT view, which the shader casts back to the
stored dword.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
Main's #7325 adds verifyChainedTableOffset to the image table tests
where this branch adds its selected-record tests. Keep both, with
main's call after this branch's.
Main's #7269 keeps the synchronous settle's buffer, memory and fence
per device in ImportSettle, so clearing one device's imports releases
only that device's objects. This branch's settle batches move there
too: each device's ImportSettle holds its batch target, memory and
batches with their fences, so switching devices no longer drops a
device's batch handles, and clearing a device waits for and destroys
only its own batches. The per-import settle state is renamed
pendingSettles to stay clear of main's per-device map, and a submitted
settle records the device whose batch it is in.
Main's #7101 reads a key buffer's words in one call where this branch
names the reason a narrowing is skipped. Keep main's bulk read and
count both of its unmapped-page skips as unmapped.
Color format 7 (COLOR_11_11_10, float) keeps its 10-bit component in the
low bits; with the reversed component order (COMP_SWAP 2) that is blue,
with red in the high 11 bits. Vulkan has no such layout, so the target was
refused at decode.
Render it the way 10_11_11 unorm targets are rendered: an R32_UINT
attachment, the reversed export mapping 0xc6, and a new
ColorExportPacking::Float11_11_10 that makes the pixel shader pack each
export with the format-43 image store conversion (toward zero, overflow to
the largest finite value, negatives to zero, NaN kept). Blending, partial
writes, 16-bit integer exports, DCC and the other component orders throw.
AI-assisted: yes
Dean