APS5_FRAME_CAPTURE=<dir> makes the AGC driver record a few frames of a
title: the shader registrations and ABI resolutions, video output and
EOP flip reservations it made since it started, a snapshot of every
readable guest allocation (the title image included) taken at a frame
boundary once the driver is idle, and for the next frames each
submission, flip and suspend point with the thread that made it, its
serial progress and the guest pages the write tracker saw the CPU write
before it. At the end it stores the presented display buffers as
reference images. APS5_FRAME_CAPTURE_AT_FLIP, _TRIGGER and _FRAMES pick
the frames.
agc_frame_replay maps the captured memory at its addresses and replays
the calls of each captured thread on a thread of its own, in captured
order, through the current build of the driver with no title running.
It paces GPU work to the in-flight depth the title had, releases GPU
waits that the title's CPU threads released without calling the driver
(AgcDriverAwaitedWaits), and reports frame times, released waits and
how closely the replayed display buffers match the references.
Tests: agc_frame_capture (file format) and agc_driver_frame_replay
(two captured frames of CPU writes and DMA copies replayed and
compared). Docs: BUILD.md, ENVIRONMENT.md and the libSceAgcDriver debt
file.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
Implement sceCesUcsProfileInitGb18030_2000 and sceCesUcsProfileInitGb18030_2005.
Two-byte cells are the CP936 table plus the cells that differ, and four-byte
sequences are runs over the BMP and the supplementary planes, generated from
ICU's gb-18030-2000.ucm (before ICU-8427) and gb-18030-2005.ucm with ICU's
GB 18030 ranges. The GB, MBC and MBCS string conversions accept both profiles
and produce four-byte UTF-8 and surrogate pairs for supplementary characters.
Since #6291 a pixel shader's EXEC copy is read as the saved word ANDed
with WQM(Ballot(true)). MaskReplaySafety only accepts a whole-quad
expansion of a ballot it can show excludes helper lanes, and a ballot
of true includes them, so a stencil-exporting shader whose own-lane
masks come from an EXEC copy was refused (own-lane mask not stable).
Every lane of a quad is active (real or helper), so a ballot of true
holds the same quad bits as the all-ones mask the proof already treats
as quad-stable; it is now classified the same way. Helper-dependent
ballots stay uncertain.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
The merge resolution had dropped its storage image sentences, which main keeps and this branch does not change.
Co-Authored-By: Claude Sonnet 5.5 <[email protected]>
Table T#s keyed at runtime no longer fault on image_atomic_*32: the
table operation stays supported, elements carry the atomic flag through
dedup into the descriptor binding, and the table path binds AtomicView
like the direct path. 64-bit atomics stay unsupported, packed and BY
formats stay unsupported, and the debt entry records the relaxed
Device-scoped emission and the remaining gaps.
Copy the source array into this and return this, as the console does
(measured on a PS4 Pro, firmware 10.71). Knowledge is Power: Decades
imports it; the inventory stub threw NotImplemented.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
The recompiler orders an LDS atomic, and the compare-exchange loop that
writes a byte or a halfword of LDS (ds_write_b8/b16), with a
workgroup-scope OpMemoryBarrier after the update. AMD's proprietary
Windows driver 32.0.21042.62 (Radeon 0x13c0, RDNA 2) compiles that
memory barrier to s_barrier, as the code objects in its pipeline cache
show. Such updates usually sit in branches that only some waves of a
workgroup take, so those waves execute extra s_barriers, which pair
with the other waves' barriers, and the other waves read LDS before it
is written. An OpMemoryBarrier is not an execution barrier and SPIR-V
allows it in non-uniform control flow, so the SPIR-V is valid; a
device-scope OpMemoryBarrier compiles to GL0 and GL1 cache
invalidations without s_barrier there.
PS5LM Plus (PPSA99581, llama.cpp's Vulkan backend) drifted into
garbage on that driver with flash attention on. Its flash-attention
shader stores two halfwords to LDS in a branch that two of its four
waves take, inside the KV loop. The driver's code had 23 s_barrier for
the guest's 21; a replay of the dispatch differed from NVIDIA in 159
words, up to 1.7e38, and now has 21 and differs only in the last bit
of 9 words.
On that driver the fence is now device scope, which orders everything
the workgroup-scope fence did. Other drivers keep the workgroup scope.
The flag is part of the shader cache key, and agc_shader_replay takes
--device-scope-lds-memory-barriers to replay a request the way that
driver compiles it. The LDS update helper already fences, so the
second, identical fence after it in ds_min/max_f32 and the other
read-modify-write LDS operations is dropped.
agc_driver_lds_subword_store_branch stores a halfword to LDS in a
branch that waves 0-1 of four take, delays those waves and then
exchanges LDS slots across one s_barrier. Before, thread 64 read a
stale slot on the AMD driver; it passes on AMD and NVIDIA now.
agc_subgroup_barrier checks the driver quirk and that ds_write_b16,
ds_add_u32 and ds_max_f32 each emit one fence of the expected scope.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01BM2kfDbr6MydxsfTckZJDR
Implement sceCesUcsProfileInitEucJpX0208, sceCesUcsProfileInitEucJpX0208Ss2,
sceCesUcsProfileInitEucJpX0208Ss2Ss3 and sceCesUcsProfileInitSJis1997X0208.
The JIS X 0208 table is JIS0208.TXT, derived from the CP932 table without
rows 13 and 89-92 and with six cells changed. The EUC-JP variants add SS2
half-width katakana and SS3 JIS X 0212 as their names say. Cell 0x2140 and
the Shift-JIS single bytes 0x5C and 0x7E, where the sources disagree, throw.
