| Commit message (Collapse) | Author | Age | Files | Lines |
|---|
| |\
| |
| | |
MKW performance improvements
|
| | |
| |
| |
| |
| |
| |
| |
| | |
Keep error reporting and debug-build history. EDEN_NX2_3D_HISTORY enables the full ring in release builds without recording every method during normal play.
Assisted by Codex.
(cherry picked from commit cac6081916e8e5461e2754308cd8986deaec774b)
|
| | |
| |
| |
| |
| |
| |
| |
| | |
Use the owned parameter vector for DMA FIFO appends. Add a native JIT regression covering reallocation and repeated invocations against the copied-input path.
Assisted by Codex.
(cherry picked from commit 5b6803aaab18e332493903ee49cab026c041d5dc)
|
| |/
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Writing any register outside the instance loop's own methods now draws the
waiting instances first, so the batch sees the base instance it was begun
with. When a title writes another register in the middle of a loop, such
as a per-instance constant buffer, the loop is drawn in several batches,
and each later batch started again at global_base_instance_index with one
extra instance, so it used the instance IDs of the first records.
Count the instances already drawn for the current loop and start the next
batch after them, without the extra first-instance draw. A loop that is
not split is drawn exactly as before.
Follow-up to 2ad0830d2f and eb99da6072.
Assisted-by: Claude Sonnet 5.5 (implementation and commit message)
|
| |\
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| | |
Resolved by area:
- audio feature_support.h: nx2's native revision handling.
- fiber.cpp: ours, which also drops the unused rewind stack.
- host_memory.cpp: ours granule bitmap and HintCold, plus nx2's
fallocate hole punching per whole dirty granule on Linux.
- texture_cache.h: nx2's old-age eviction pass, then our Collect().
- kepler_compute.cpp: shared upscale slots, then Fortune's Weave's,
then the Kirby Air Riders scan.
- nx2_gsv.h: ours, plus nx2's GetBufferMaxResolution and graphics
device ids (1-based).
- nvhost_ctrl_gpu.cpp: engine support flag bits 40-44.
- lower_to_maxwell.h: ours as the base, with nx2's seven lowering
commits applied one at a time. Second texture descriptor buffers
are read bindless in TEX, TLD.SCR (level zero) and SUST; FSEL
keeps its operand modifiers; TXD takes any channel mask.
lower_to_maxwell.h lowers 837 Fortune's Weave and 1183 Mario Kart
World shader dumps with the same rejects as nx2 and ours (12 and 0).
Assisted-by: Claude Sonnet 5.5 (conflict analysis and drafting)
|
| | |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| | |
The 3D methods 0x504/0x508 write eight 256-byte root tables, which
shaders read as constant banks 24-31; NVN2 keeps push constants in table
0 (bank 17 after the Ampere lowering). Fire Emblem: Fortune's Weave
keeps its material constants there and never binds bank 17, and the
blit constants pass replaced those reads with render-target sizes,
flooding its 3D scenes red.
Maxwell3D now keeps the tables, the buffer cache streams table 0 as bank
17 when the game has not bound one, and the blit constants pass leaves
shaders that read bank 17 outside its parameter block alone.
Assisted-by: Claude Opus 5.5 (debugging, implementation and drafting)
Signed-off-by: Duck912 <350528965+Duck912@users.noreply.github.com>
|
| |/
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
A draw of N instances arrives as Begin(First)/End and N-1 Begin(Subsequent)/
End pairs. The draw manager draws the first at once and the rest together at
DrawDeferred, which ran at the next Begin(First) or when the macro returned.
NVN's draw macros reset the base instance register and its copy in
c[0][0x644] right after the loop, before returning, so the deferred instances
were drawn with base instance 0 and read the first records of the instance
buffer instead of their own.
In Mario Kart World every tree mesh is drawn this way, from one shared
instance buffer: each mesh got other meshes' transforms, which showed as
low-detail, inflated or scattered trees.
Any write other than the loop's own methods (draw begin/end, vertex and
index counts, inline indices) now draws the waiting instances first.
|
| |
|
|
|
|
|
|
|
| |
- (std::min)/(std::max) where windows.h's macros are visible
- LAMBDA_FORCEINLINE: always_inline under clang (clang-cl defines
_MSC_VER but rejects [[msvc::forceinline]] on lambdas)
- ImageBase::FindView: find_if, as MSVC's STL takes its vectorized find
for ImageViewInfo under clang-cl and fails a size assertion
- parentheses for -Wlogical-op-parentheses in the Ampere lowering
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
front paths
Clean A/B in title 1 (3 rounds each): 1.46x the draws a second of one
thread, frames 17% shorter, no crashes, front register copies equal to
the back's in 57,089 checks. EDEN_NX2_SPLIT=0 runs everything on one
thread, =1 keeps macros on the back.
The front's per-write paths no longer check guarded statics
(GpuSplit::Get, Nx2Profile::Enabled, the skip-same switches) and the
ring's method writes are inline. Notes row 145.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The GPU thread (front) takes the CPU's commands, parses command lists
and runs the puller; engine method calls and everything behind them
(registers, draws, dispatches, the rasterizer and its caches) run in
order on a second thread (back), fed through a single-producer
single-consumer ring (gpu_split.h). Work the front did on back-owned
state (end of command list flushes, channel binds, semaphore releases,
syncpoint increments, flush/invalidate requests, presentation) is
deferred into the same ring; the front waits for the back only where it
needs a result from that state: semaphore acquires and MME DMA reads.
EDEN_NX2_SPLIT=1 runs macros on the back. EDEN_NX2_SPLIT=2 runs the 3D
and compute macros on the front against copies of the registers they
read (Maxwell3D/KeplerCompute Front*), drops state writes that keep a
register's value there, and sends the rest. EDEN_NX2_SPLIT_VERIFY=1
compares the copies with the back's registers every 4096 macro calls
(0 differences in 40,193 checks in title 1); EDEN_NX2_SPLIT_CHECK=1
logs the stack of any other thread using the Vulkan scheduler while the
back runs. Switch 2 titles, Vulkan, non-accurate GPU only.
Title 1, 3D attract loop: ~44,000 draws a second on one thread, ~47,400
with EDEN_NX2_SPLIT=1, 50,000-66,500 with EDEN_NX2_SPLIT=2.
|
| |
|
|
|
|
|
|
| |
ProcessMethodCall and the draw manager behind it act only on executable methods, so
CallMethod stops at the dirty flags for the rest (macro replays write ~2.4 million of
those a second). No change beyond run-to-run noise in two profiled runs; it only removes
work. Notes: row 133 corrected (those courses are bound by the GPU thread, not the host
GPU: 20-40% busy), rows 135-137 (same-value writes, native compute registers, 2D blits).
|
| |
|
|
|
|
|
|
|
|
|
| |
Title 1 makes ~6 million 3D register writes a second and ~60% of them write the value
the register already holds (counted with EDEN_NX2_GPU_PROFILE), most from macro memo
replays. For registers without side effects (not in execution_mask: draws, clears,
constant buffer data and binds, semaphores, ...) such a write changes nothing, but it
set dirty flags that made the next draw re-check that state. CallMethod and the sunk
writes now skip them after shadow RAM processing. Two profiled runs each: macro calls
169 ns instead of 185, draw setup 5.80 us instead of 5.95. EDEN_NX2_SKIP_SAME=0 turns it
off.
|
| |
|
|
|
|
|
|
|
| |
Nearly every macro call arrives whole in one method run (~1,000,000 a second in title
1); its parameters were appended to a std::vector first (~2% of the GPU thread). They
are now copied to a stack array. Still a copy: the command list is often guest memory
read in place, which the guest may reuse while the macro runs, and the macro memo
stores the parameters after the call. Accurate GPU mode keeps the vector (it rewrites
parameters in place). EDEN_NX2_MACRO_COPY=1 always uses the vector.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
off the hot path
- AMD CPUs have no CPUID leaf 0x15, so the TSC frequency stayed 0 and
every guest CNTPCT read went through QueryPerformanceCounter (~10% of
the game's main core in title 1). Measure it like Intel CPUs without
a crystal frequency.
- A rejected native shader was rethrown (two C++ throws) every time it
was bound; return false instead (~1-2% of the GPU thread).
- The semaphore watch, pushbuffer entry hashing, first-write trace and
per-macro debug logs ran on every command word or macro call; they
now cost a flag check unless their environment variable is set
(~4% of the GPU thread). Also starts the macro engine's profile zone.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
Title 4 calls a 3D macro with a 6-word IncreaseOnce header, ends the main
GPFIFO entry after the first word and supplies the other five in a 5-word
subroutine entry. The split-method parking (an entry elsewhere was treated
as a call with a clean method state) fed those parameters to the parser as
headers: the macro ran with garbage, later draws read megabytes of unmapped
memory and the host driver timed out at the loading screen after the dock
scene. As on the hardware, the method state now simply continues; the old
guess stays behind EDEN_NX2_PARK_SPLIT_METHODS.
Debug aids: splits are logged at debug level with the words around them,
and a 3D write that interrupts a macro's parameters dumps the last 48 writes.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
- Native QMD: a launch whose shader Eden can't translate still completes and
fires its releases (the console never fails a launch; queues wait on them).
- QMD releases with flag bit 19 are max releases: NVN2 tracks QMD completion
in a word other releases also advance, so a plain write moved it backwards.
- Ampere lowering: LDSM.16.M88.{1,2,4} (SHFL + LDS), IMAD with a negated
uniform addend, strong LDG (bit 77), 2D TLD4 gather, RED MIN/MAX/..., AST of
RZ. 210 of the 214 shaders title 4 uses after its menu now lower.
- Maxwell3D: ignore constant buffer binds to slots >= 18 instead of writing
past the state array.
- Debug: EDEN_NX2_SEM_WATCH covers QMD and compute-macro releases and logs
address spaces; EDEN_NX2_3D_METHODS logs the first write to each 3D method;
constant buffer binds are logged once per stage/slot.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
From changes.patch: the TU104/GA10x MME interpreter (shared macro context for
the process's channels, also on the compute class), native compute with QMD
3.0 dependency scheduling, the Ampere-to-Maxwell shader lowering, native
vertex stream sizes, and the console's GOB swizzle for textures, DMA copies
and the host unswizzle shaders. Switch 2 channels turn all of it on at init.
The lowering is widened for title 4 (all 32 of its programs lower): general
TEX (any dimension/LOD/mask, operand split 1+1/2+1/2+2/4+n, any but consistent
descriptor buffer), cube/array, SULD channel masks, 128-bit STG, indexed IPA,
VOTE, SHFL with any immediate or predicate output, R2P/P2R byte select,
uniform ULOP3/ULEA/UBREV/UFLO.SH/UISETP signed/UMOV URZ, IMNMX cbuf, IADD3
and FFMA uniform operands, FMUL /4 /8 x8, and BSSY/BSYNC/BREAK/WARPSYNC as
no-ops. The capture stops at unmapped memory. EDEN_NX2_SHADER_DUMP dumps every
native program; tools in C:\dev\nx2work test the lowering offline.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
fences
- gsv 204: real syncpoint shared page (values mirrored from host1x, armed waits
acknowledged by a 500us poller); first handle is the writable request event.
- syncpt 22/201/202: per-slot events signalled through host1x guest actions.
- nx2:gpu sub 101 memory is identity-mapped (GPU VA == CPU VA) into every
nvhost-as-gpu GMMU via Nx2GpuMemoryRegistry; SMMU physical range widened to
34 bits for the 10/12 GiB layouts.
- Puller runs Ampere 3D/compute/copy classes on the Maxwell engines; class 0 unbinds.
- Turing+ macros are skipped (Eden only has the Fermi macro ISA).
- Submits with increment_value get Eden-side syncpoint increments, since NVN2
signals completion with semaphore releases only.
|
| |
|
|
|
|
|
|
|
| |
Inline index draws arrive as a batch but were processed one word at a time, so each index ran through the full per-method path and got appended a byte at a time.
Handle the whole batch in one pass instead, updating state once and appending all the indices together. Replay shadow control still goes word by word since it has to reload each one.
Reviewed-on: https://git.eden-emu.dev/eden-emu/eden/pulls/4083
Reviewed-by: Lizzie <lizzie@eden-emu.dev>
Reviewed-by: MaranBr <maranbr@eden-emu.dev>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
GetMacroAddress only reads a couple of indices per macro, but ProcessMacro was
then building a full std::vector GPUVAddr> with one push_back per parameter word
every submission. macro_segments already holds base, count per chunk, so
GetMacroAddress can just walk it instead, drops the per-word loop, a
.clear(), and a vector member.
Also makes it so it returns on the first match in the macro dispatch instead of running every
std::get_if check.
Reviewed-on: https://git.eden-emu.dev/eden-emu/eden/pulls/4067
Reviewed-by: Lizzie <lizzie@eden-emu.dev>
Reviewed-by: CamilleLaVey <camillelavey99@gmail.com>
|
| |
|
|
|
|
|
|
|
|
| |
reworked a bit to remove references of parent objects and instead pass as arguments to methods to prevent useless reloads
Signed-off-by: lizzie <lizzie@eden-emu.dev>
Co-authored-by: maufeat <sahyno1996@gmail.com>
Reviewed-on: https://git.eden-emu.dev/eden-emu/eden/pulls/3908
Reviewed-by: Maufeat <sahyno1996@gmail.com>
Reviewed-by: crueter <crueter@eden-emu.dev>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
format estimate (#4006)
u8 may have been 0xff, (aka. 255), but bitset was only 255 elements, so doing bitset[255] is technically OOB
additionally the max size estimate for index formats was not correct, there can be up to 256 elements with a u8 format index, not just 255
Signed-off-by: lizzie <lizzie@eden-emu.dev>
Reviewed-on: https://git.eden-emu.dev/eden-emu/eden/pulls/4006
Reviewed-by: crueter <crueter@eden-emu.dev>
Reviewed-by: MaranBr <maranbr@eden-emu.dev>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
on hot paths (#3758)
usual indirection removal
helps very slightly to codegen
the idea is basically to reduce the amount of pointer deference overall in the code, and use idiomatic std::variant<>-isms to not rely on vtables/unique_ptr overhead
this should allow the compiler to emit better code
of course it's a tiny optimisation and only CPU side, but allows us to reduce indirection which is almost always a good thing
"but youre passing more parameters to the function!!!" its literally memoized into a register my friend
Signed-off-by: lizzie <lizzie@eden-emu.dev>
Reviewed-on: https://git.eden-emu.dev/eden-emu/eden/pulls/3758
Reviewed-by: crueter <crueter@eden-emu.dev>
Reviewed-by: MaranBr <maranbr@eden-emu.dev>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
(#3712)
Removed the early return in ProcessDirtyRegisters to ensure all dependent dirty flags are set even if the register value hasn't changed.
This fixes flickering and vertex explosions on the Hero's Path in The Legend of Zelda: Breath of the Wild, fixes the teleport bug in The Legend of Zelda: Tears of the Kingdom, fixes the grey Luigi in Luigi's Mansion 3, and may also improve rendering in other games that rely on redundant register writes.
Reviewed-on: https://git.eden-emu.dev/eden-emu/eden/pulls/3712
Reviewed-by: Lizzie <lizzie@eden-emu.dev>
Reviewed-by: CamilleLaVey <camillelavey99@gmail.com>
Co-authored-by: MaranBr <maranbr@outlook.com>
Co-committed-by: MaranBr <maranbr@outlook.com>
|
| |
|
|
|
|
|
|
|
|
| |
Should slightly boost perf on android, Desktop is mainly unaffected (for now)
Reviewed-on: https://git.eden-emu.dev/eden-emu/eden/pulls/3653
Reviewed-by: CamilleLaVey <camillelavey99@gmail.com>
Reviewed-by: DraVee <chimera@dravee.dev>
Co-authored-by: lizzie <lizzie@eden-emu.dev>
Co-committed-by: lizzie <lizzie@eden-emu.dev>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
pipeline through multiple targeted optimizations (#3296)
- Scheduler: Reduced lock scope to allow parallel command preparation across channels
- DmaPusher: Added command prefetching (16-command lookahead) to improve cache hit rate
- Maxwell3D: Pre-allocated macro parameter vectors to eliminate dynamic allocations and unrolls dirty register tracking loop for better cache locality
- MacroEngine: Added last-executed macro cache to skip hash table lookups on hot path
Co-authored-by: lizzie <lizzie@eden-emu.dev>
Reviewed-on: https://git.eden-emu.dev/eden-emu/eden/pulls/3296
Reviewed-by: Maufeat <sahyno1996@gmail.com>
Reviewed-by: DraVee <dravee@eden-emu.dev>
Co-authored-by: CamilleLaVey <camillelavey99@gmail.com>
Co-committed-by: CamilleLaVey <camillelavey99@gmail.com>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
for core stuff:
just remove unique ptrs that dont need any pointer stability at all (afterall its an allocation within an allocation so yeah)
for fibers:
Main reasoning behind this is because virtualBuffer<> is stupidly fucking expensive and it also clutters my fstat view
ALSO mmap is a syscall, syscalls are bad for performance or whatever
ALSO std::vector<> is better suited for handling this kind of "fixed size thing where its like big but not THAT big" (512 KiB isn't going to kill your memory usage for each fiber...)
for core.cpp stuff
- inlines stuff into std::optional<> as opposed to std::unique_ptr<> (because yknow, we are making the Impl from an unique_ptr, allocating within an allocation is unnecessary)
- reorganizes the structures a bit so padding doesnt screw us up (it's not perfect but eh saves a measly 44 bytes)
- removes unused/dead code
- uses std::vector<> instead of std::deque<>
no perf impact expected, maybe some initialisation boost but very minimal impact nonethless
lto gets rid of most calls anyways - the heavy issue is with shared_ptr and the cache coherency from the atomics... but i clumped them together because well, they kinda do not suffer from cache coherency - hopefully not a mistake
this balloons the size of Impl to about 1.67 MB - which is fine because we throw it in the stack anyways
REST OF INTERFACES: most of them ballooned in size as well, but overhead is ok since its an allocation within an alloc, no stack is used (when it comes to storing these i mean)
Signed-off-by: lizzie lizzie@eden-emu.dev
Reviewed-on: https://git.eden-emu.dev/eden-emu/eden/pulls/3306
Reviewed-by: CamilleLaVey <camillelavey99@gmail.com>
Reviewed-by: MaranBr <maranbr@eden-emu.dev>
Co-authored-by: lizzie <lizzie@eden-emu.dev>
Co-committed-by: lizzie <lizzie@eden-emu.dev>
|
| |
|
|
|
|
|
| |
Reviewed-on: https://git.eden-emu.dev/eden-emu/eden/pulls/2547
Reviewed-by: MaranBr <maranbr@eden-emu.dev>
Co-authored-by: lizzie <lizzie@eden-emu.dev>
Co-committed-by: lizzie <lizzie@eden-emu.dev>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
Compilation and CMake fixes for both Windows on ARM and clang-cl, meaning Windows can now be built on both MSVC and clang on both amd64 and aarch64.
Compiling on clang is *dramatically* faster so this should be useful for CI.
Co-authored-by: crueter <crueter@eden-emu.dev>
Co-authored-by: crueter <crueter@crueter.xyz>
Reviewed-on: https://git.eden-emu.dev/eden-emu/eden/pulls/348
Reviewed-by: CamilleLaVey <camillelavey99@gmail.com>
Reviewed-by: crueter <crueter@eden-emu.dev>
Co-authored-by: lizzie <lizzie@eden-emu.dev>
Co-committed-by: lizzie <lizzie@eden-emu.dev>
|
| |
|
|
|
| |
Allows the use of the macro in constexpr-contexts.
Also avoids some potential problems when nesting braces inside it.
|
| | |
|
| |
|
|
| |
GL_TRANSFORM_FEEDBACK_PRIMITIVES_WRITTEN queries
|
| | |
|
| | |
|
| | |
|
| | |
|
| | |
|
| | |
|
| | |
|
| | |
|
| | |
|
| |\
| |
| | |
Re-add the invalidate_texture_data_cache register
|
| | | |
|
| | |
| |
| |
| |
| |
| | |
constexpr static to static constexpr for consistency
Signed-off-by: arades79 <scravers@protonmail.com>
|
| |/
|
|
|
|
| |
where possible
Signed-off-by: arades79 <scravers@protonmail.com>
|
| |\
| |
| | |
video_core: Implement maxwell3d draw texture method
|
| | | |
|
| | | |
|
| |/ |
|
| | |
|
