Admit PA_SC_AA_CONFIG bit29 only without active perspective or linear centroid inputs, or with a skipped pixel program. Active/unspecified centroid inputs and unrelated AA fields remain refused. Source: pinned PS5_Mesa 0b2d6d1a GFX10.3 schema/RADV producer; existing ENA/ADDR intersection. Console covered-centroid interpolation remains unmeasured.
Full build/all 124 runtime libraries, conventions and registration pass. Final Windows suite: 965 pass, zero fail, seven skips of 972. Isolated state test passes 20 repeats and fails 5/5 with main State.cpp; four guard mutants fail 5/5 each. Original two title register captures reproduce the main refusal and pass this check with candidate, five times each. NVIDIA relevant groups pass; AMD draw-cache failure also occurs on unchanged main and is reported in issue4435.
AI-assisted: Codex.
TessellationLowering refused every domain-program read of the off-chip
ring outside its patch's control points, so domain programs that read
the hull's patch constants, like the quad terrain domain in Ghost of
Yotei at 0x8000 - 208 * (rel + 1), aborted.
Such reads now lower to a new PatchInput kind and become Patch inputs.
Hull outputs and domain inputs place a constant by its off-chip address
modulo the record stride, in a record-sized array at location
ceil(hsStride / 16); each program derives both on its own, so the two
interfaces match although they compile separately. Domain reads at an
address that does not move with the relative patch, across more than
one record or inside the control-point region still throw, as does a
domain program that reads patch constants but no control point. Hull
patch-constant writes now take the same bound: above the control points
of all NUM_PATCHES patches, not just one patch's.
TessellationLowering proved ring and LDS addresses affine over a
relative patch index of up to 256. A hull that lays its patch-constant
records out downwards, at 0x8000 - 208 * (rel + 1) like the quad
particle hull in Ghost of Yotei, then reached a negative address for
the last slot and aborted as "not affine". The relative patch index of
hull and domain programs stays below VGT_LS_HS_CONFIG.NUM_PATCHES
(bits 7:0, patches per threadgroup), which is 63 for that draw.
DecodeShaderStages now carries NUM_PATCHES as patchesPerGroup in the
tessellation configuration (draw keys, hull and domain cache keys,
recompile request version 22) and refuses zero, and the lowering bounds
the relative patch index by it. Configurations without it keep 256.
8 MiB window, so a range larger than the window is always imported alone. A
buffer bound across two such ranges then has no import and is copied whole on
every use: PPSA25344 binds a 368 MiB buffer across a 320.75 MiB and a 47.3 MiB
range and copies it on almost every frame.
When UploadFinish meets such a region, it imports the run of the ranges the
region crosses, provided every one of them is larger than the window, and
retires their own imports. It does this before any region of the build
confirms an import, so the retire moves the epoch ahead of every pointer the
build would use. A range that large is registered whole, not grown in 64 KiB
pieces like a heap, so the joined import is not re-imported as a heap grows; it
stands in refreshImports while exactly its ranges stand. A later join that
reaches a joined import takes it in, so two joins that share a range never
retire each other in turn.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
WindowsMappings::Collect handed GetWriteWatch the whole remaining output
capacity for every private region it walked. The call's cost follows that
capacity, not the size of the range: on Windows 11 (26200) a query of one
16 KiB region took 0.35 us with room for 4 entries and 6.5 us with room
for the 65536 the write tracker passes. Flexible memory is committed in
16 KiB allocations, one region each, so a resetting walk over 33 MiB of it
took 14.7 ms, 5.8 times a memcmp of the same bytes.
Each query now gets room for the pages its region spans, which is the most
it can report, so every walk returns the same pages; the 33 MiB walk takes
1.23 ms. guest_memory checks that a walk over eight 16 KiB allocations
reports every stored page once, in order, with room for 32, 5 and 1 pages.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
The [present] line divided the GPU busy and idle time of a window by the
presentations that got a swapchain image. That time covers the GPU work
of every frame, so with frames dropped for want of an image it read
several times too high (278.9 ms instead of about 52 ms on a hidden
window, reported on #4684). Those two figures are now divided by the
presented and dropped frames; the per-present blit figures are unchanged.
