RecordedFillClearsWithoutWait now also runs with a D32_SFLOAT_S8_UINT target: a
recorded SMem 0 fill (0xf0) over the HTILE clears depth and stencil at the bind
without a GPU wait, and is stored back as expanded (0xfffff3ff). The stencil case
alone fails with APS5_NO_PENDING_HTILE_FILLS=1.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A depth target's bind (storeBackClearedHtile) reads its HTILE words to find a fast clear and
stores them back expanded. When a recorded fill over the HTILE was still pending, that read
made the flush hook submit the open batch and wait for the GPU, under the GPU mutex. A title
that clears its depth targets with buffer fill kernels pays that wait at every clear.
Uniform fills now note their 32-bit word with the pending write (NotePendingWordFill; the byte
value the DCC key paths use is unchanged). When every pending write over the HTILE is such a
fill and the rest of the range already holds the same word, the bind takes the landed word
from the notes, and stores the expanded words as a GPU fill recorded behind the pending ones.
Any other pending write keeps the read. APS5_NO_PENDING_HTILE_FILLS=1 always reads.
PPSA12544 on a Radeon 780M (Windows): 1271 pending-write syncs per 10 s waited 5.5 s at the
bind, about 4.3 ms each; with this change there are none, and the scene runs at 60-61 fps
instead of 44-46.
Since #6346 a CPU write elsewhere in an image table's 64 KiB block no
longer fails the table's unchanged proof on Windows, because the proof
is answered per page there too. The Windows-only expectation of a second
resolution is stale and agc_driver_image_table_reuse fails on Windows.
Expect the Linux count on every host.
Imports, type-3 mirrors and the buffers and textures placed in host memory share the driver's system memory heap. On Windows that heap is half the physical memory, so on a 16 GiB machine the old budget (the heap less 2 GiB) let imports hold about 6 of its 8 GiB, and host buffer allocations then overflowed into the 256 MiB device-local host-visible heap and failed. The budget now reserves the larger of 2 GiB and half the largest host heap.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Since 2688b7646 a read and written V# element is staged in device memory
up to 16 MiB when the direct dispatch's threads times the V# stride cover
at least half of it. A raw buffer has stride 0, so it never passed and
kept the 2 MiB written window: GL storage buffers compiled by Mesa stay
bound in place in the host import however hard a dispatch sweeps them.
The PS5 OpenGL Showcase's particle update (262,144 threads, each loading
and storing its own 32-byte record of an 8 MiB SSBO) took about 53 ms of
GPU per frame on an RTX 4060 bound in place; staged it takes about 0.1 ms
plus 2.2 ms of bulk copies.
The recompiler already records the furthest byte each buffer resource's
accesses reach past their base (maxByteExtent). The binding plan now
carries it per guest buffer element (DescriptorBinding::bufferExtent,
shader disk cache format 37), and a raw element uses it as its record
size in the sweep test. Strided elements are unchanged.
guest_dynamic_loader and guest_dynamic_loader_fixed_base run the same
GuestDynamicLoader.cpp in the same working directory, and both copy the
module fixture to anyps5-relinked-module-for-test.prx.guest.prx and
anyps5-host-loaded-module-for-test.prx before loading it. Under ctest
--parallel one test rewrote or removed a file the other had mapped:
Bus error, or failed at GuestDynamicLoader.cpp:92. Give both one
RESOURCE_LOCK.
Adrià