Adds async_shader_compilation cvar (default true) that forces new
pipelines to be created async from the main thread, skips draws entirely
on D3D12 and on vulkan replaces pixel shader with placeholder until the
real one is ready. Causes some visual artifacts on first load but
greatly reduces load times and stutter.
Drivers and hardware may provide more optimal paths for untyped buffers
compared to typed.
Also, ByteAddressBuffer may be bound via a root descriptor in Direct3D 12,
greatly simplifying the binding logic.
ByteAddressBuffer also doesn't have the 128 * 2^20 element count limit that
typed and structured buffers have, and doesn't require the structure stride
to be specified at resource creation time in Direct3D 11.
With render target HLE, directly store linear values as R16G16B16A16_UNORM
without gamma conversion, as this format provides more than enough bits
(need at least 11 per component due to the maximum scale being 2^3 in the
piecewise linear gamma curve) to represent linear values without precision
loss.
This makes blending work correctly in linear space, improving quality of
transparency, lighting passes, and fixing issues such as transparent parts
of impact and footstep decals in 4D5307E6 being bright instead.
The new behavior is enabled by default, as it hugely improves the accuracy
of emulation of this format, that is pretty commonplace in Xbox 360 games,
with likely just a small GPU memory and bandwidth usage increase, compared
to the alternatives that were previously available on the HLE RB path.
It's currently implemented only on Direct3D 12, as most of the current GPU
emulation code is planned to be phased out and redone, and no methods other
than 8-bit with pre-conversion were implemented on Vulkan previously.
To implement on Vulkan later, same conversion as in the Direct3D 12
implementation will need to be done in ownership transfer and resolve
shaders. Currently it's somewhat inconvenient to decouple the conversion
functions in `SpirvShaderTranslator` from an instance of the translator due
to vector constant usage. Later, simpler SPIR-V generation functions may be
added (`spv::Builder` usage in general is overly verbose).
The previously default method (8-bit storage with pre-conversion in shaders
and incorrect blending) can be re-enabled by setting the
"gamma_render_target_as_unorm16" configuration option to `false`. This may
be useful if the game, for instance, switches between 8_8_8_8_GAMMA and
8_8_8_8 formats for the same data frequently, as switching will result in
EDRAM range ownership transfer data copying now. Also, the old path is
preserved for Vulkan devices not supporting R16G16B16A16_UNORM with
blending.
The other workaround that was available previously, replacing the PWL
encoding with host hardware sRGB with linear-space blending in render
target management and in texture fetching, was also inherently inaccurate
in many ways (especially when games have their own PWL encoding math, like
4541080F that displayed incorrect colors on the loading screen), and
required tracking of the encoding needed for ranges in the memory.
The sRGB workaround therefore was deleted in this commit, greatly
simplifying the code in the parts of render target, texture and memory
management and shader generation that were involved in it.
Replace the `SubmissionTracker`s with new `GPUCompletionTimeline`s with a
more unified interface (using a base class), and without the internal logic
for queue ownership transfers since that idea was scrapped during the
development of the `Presenter`.
Also use this fence management logic for GPU emulation, though without
architectural reworks for now, just on the bottom level.
Still very messy, but can be cleaned up in further GPU command processor
and presenter reworks.
Introduce "fast" readback resolve that reads from previous frame's
resolve buffers, quick swap between buffers each frame to avoid
copies so minimal performance impact and mostly correct bahavior.
Checks if previous frame had a buffer for the current resolve and
falls through to the slow path, which also allows to support
"screenshot" features in the games that do that without stalling
on normal resolve operations.
Re-enabled readback_memexport as separate feature, was previously
bundled with readback_resolve (probably not intentionally) and
ensures destination address is writeable to avoid memory access
related crashes and unnecessary work.
readback_resolve cvar changes from bool to string ternary with
"none", "fast" and "full" options, defaulting to the new "fast"
mode.
Enable portability subset physical device enumeration.
Don't use Vulkan 1.1+ logical devices on Vulkan 1.0 instances due to the
VkApplicationInfo::apiVersion specification.
Make sure all extension dependencies are enabled when creating a device.
Prefer exposing feature support over extension support via the device
interface to avoid causing confusion with regard to promoted extensions
(especially those that required some features as extensions, but had those
features made optional when they were promoted).
Allow creating presentation-only devices, not demanding any optional
features beyond the basic Vulkan 1.0, for use cases such as internal tools
or CPU rendering.
Require the independentBlend feature for GPU emulation as working around is
complicated, while support is almost ubiquitous.
Move the graphics system initialization fatal error message to xenia_main
after attempting to initialize all implementations, for automatic fallback
to other implementations in the future.
Log Vulkan driver info.
Improve Vulkan debug message logging, enabled by default.
Refactor code, with simplified logic for enabling extensions and layers.
VS/PS_NUM_REG is 6-bit on Adreno 200, and games aren't seen using the
bit 7 to indicate that no GPRs are used. It's not clear why Freedreno
configures it this way.
Some texture fetch fields were deprecated or moved during the development
of the Xenos, reflect that in the comments.
Add definitions of the registers configuring the conversion of vertex
positions to fixed-point. Although there isn't much that can be done with
it when emulating using PC GPU APIs, there are some places in Xenia that
wrongly (though sometimes deliberately, for results closer to the behavior
of the host GPU) assume that the conversion works like in Direct3D 10+,
however the Xenos supports only up to 4 subpixel bits rather than 8. The
effects of this difference are largely negligible, though.
Also add more detailed info about register references and differences from
other ATI/AMD GPUs for potential future contributors.
- Renamed CommonGPUSetting to GPUSetting
- Removed readback_resolve and memexport from d3d12 exclusive option. In the future it will be available for Vulkan too.
- Removed unused enum class: gpu_cvar
- Removed OS specific code from emulator_window
Hopefully prevents some potential #1971-like situations.
WAIT_REG_MEM's implementation also allowed the compiler to load the value
only once, which caused an infinite loop with the other changes in the
commit (even in debug builds), so it's now accessed as volatile. Possibly
it would be even better to replace it with some (acquire/release?) atomic
load/store some day at least for the registers actually seen as
participating in those waits.
Also fixes the endianness being handled only on the first wait iteration in
WAIT_REG_MEM.
There's no limit on the number of memory exports in a shader on the real
Xenos, and exports can be done anywhere, including in loops. Now, instead
of deferring the exports to the end of the shader, and assuming that export
allocs are executed only once, Xenia flushes exports when it reaches an
alloc (allocs terminate memory exports on Xenos, as well as individual ALU
instructions with `serialize`, but not handling this case for simplicity,
it's only truly mandatory to flush memory exports before starting a new
one), the end of the shader, or a pixel with outstanding exports is killed.
To know which eM# registers need to be flushed to the memory, traversing
the successors of each exec potentially writing any eM#, and specifying
that certain eM# registers might have potentially been written before each
reached control flow instruction, until a flush point or the end of the
shader is reached.
Also, some games export to sub-32bpp formats. These are now supported via
atomic AND clearing the bits of the dword to replace followed by an atomic
OR inserting the new byte/short.
The "close window" keyboard hotkey (Guide-B) now toggles between loglevel -1 and the loglevel set in your config.
Added LoggerBatch class, which accumulates strings into the threads scratch buffer. This is only intended to be used for very high frequency debug logging. if it exhausts the thread buffer, it just silently stops.
Cleaned nearly 8 years of dust off of the pm4 packet disassembler code, now supports all packets that the command processor supports.
Added extremely verbose logging for gpu register writes. This is not compiled in outside of debug builds, requires LogLevel::Debug and log_guest_driven_gpu_register_written_values = true.
Added full logging of all PM4 packets in the cp. This is not compiled in outside of debug builds, requires LogLevel::Debug and disassemble_pm4.
Piggybacked an implementation of guest callstack backtraces using the stackpoints from enable_host_guest_stack_synchronization. If enable_host_guest_stack_synchronization = false, no backtraces can be obtained.
Added log_ringbuffer_kickoff_initiator_bts. when a thread updates the cp's read pointer, it dumps the backtrace of that thread
Changed the names of the gpu registers CALLBACK_ADDRESS and CALLBACK_CONTEXT to the correct names.
Added a note about CP_PROG_COUNTER
Added CP_RB_WPTR to the gpu register table
Added notes about CP_RB_CNTL and CP_RB_RPTR_ADDR. Both aren't necessary for HLE
Changed name of UNKNOWN_0E00 gpu register to TC_CNTL_STATUS. Games only seem to write 1 to it (L2 invalidate)
Implemented Controller Hotkeys
Added controller hotkeys
Added guide button support for XInput and winkey
The hotkey configurations can be found in HID -> Display controller hotkeys
If the Xbox Gamebar overlay is enabled then use the Back button instead of the Guide button.
- Fixed hotkey thread destruction
- Fixed XINPUT_STATE by padding 4 bytes
- Added hotkey vibration for user feedback
- Replaced MessageBoxA with ImGuiDialog::ShowMessageBox
Co-authored-by: Margen67 <Margen67@users.noreply.github.com>
Reorganized SystemPageFlags for sharedmemory, each field now goes into its own array, the three arrays are page aligned in a single virtual allocation
Refactored sharedmemory a bit, use tzcnt if available when finding ranges (faster on pre-zen4 amd cpus)
Made commandprocessor GetcurrentRingReadcount inline, it was made noinline to match PGO decisions but i think PGO can make extra reg allocation decisions that make this inlining choice yield gains, whereas if we do it manually we lose a tiny bit of performance
Working on a more compact vectorized version of GetScissor to save icache on cmd processor thread
Add WriteRegisterForceinline, will probably end up amending to remove it
add ERMS path for vastcpy
Adding WriteRegistersFromMemCommonSense (name will be changed later), name is because i realized my approach with optimizing writeregisters has been backwards, instead of handling all checks more quickly within the loop that writes the registers, we need a different loop for each range with unique handling. we also manage to hoist a lot of the logic out of the loops
Use 100ns delay for MaybeYield, noticed we often return almost immediately from the syscall so we end up wasting some cpu, instead we give up the cpu for the min waitable time (on my system, this is 0.5 ms)
Added a note about affinity mask/dynamic process affinity updates to threading_win
Add TextureFetchConstantsWritten
Add constexpr getters to magicdiv class so it can be used from jitted x64/dxbc
Track the guest return address as well for guest/host sync, if multiple entries have the same guest stack find the first one with a matching guest retaddr. this fixes epic mickey 2 (which the previous guest-stack change had allowed to go ingame for a bit) and potentially also a crash in fable3.
Break if under debugger when stackpoints are overflowed
Add much more useful output for host exceptions, print out xenia_canary.exe relative offsets if exception is in module, formatmessage for ntstatus/win32err, strerror
Minor d3d12 microoptimization, instead of doing SetEventOnCompletion + WaitForSingleObject do SetEventOnCompletion w/ nullptr so that the wait happens in kernel mode, avoiding two extra context switches
add unimplemented kernel functions:
ExAllocatePoolWithTag
ObReferenceObject
ObDereferenceObject has no return value.
Log a message when ObDereferenceObject/Reference receive unregistered guest kernel objects
gave ObLookupThreadByThreadId its correct error status
hoist object_types initialization out of ObReferenceObjectByHandle
Fix out parameter values on error for a few kernel funcs
add note about msr to KeSetCurrentStackPointers
add X_STATUS_OBJECT_TYPE_MISMATCH check for xeNtSetEvent
add msr_mask field to X_KPCR
Remove dead #if 0'd code in math.h
On amd64, page_size == 4096 constant, on amd64 w/ win32, allocation_granularity == 65536. These values for x86 windows havent changed over the last 20 years so this is probably safe
and gives a modest code size reduction
Enable XE_USE_KUSER_SHARED. This sources host time from KUSER_SHARED instead of from QueryPerformanceCounter, which is far faster, but only has a granularity of 100 nanoseconds.
In some games seemingly random crashes were happening that were hard to trace because
the faulting thread was actually not the one that was misbehaving, another threads stack was underflowing into the faulting thread.
Added a bunch of code to synchronize the guest stack and host stack so that if a guest longjmps the host's stack will be adjusted.
Changes were also made to allow the guest to call into a piece of an existing x64 function.
This synchronization might have a slight performance impact on lower end cpus, to disable it set enable_host_guest_stack_synchronization to false.
It is possible it may have introduced regressions, but i dont know of any yet
So far, i know the synchronization change fixes the "hub crash" in super sonic and allows the game "london 2012" to go ingame.
Removed emit_useless_fpscr_updates, not emitting these updates breaks the raiden game
MapGuestAddressToMachineCode now returns nullptr if no address was found, instead of the start of the function
add Processor::LookupModule
Add Backend::DeinitializeBackendContext
Use WriteRegisterRangeFromRing_WithKnownBound<0, 0xFFFF> in WriteRegisterRangeFromRing for inlining (previously regressed on performance of ExecutePacketType0)
add notes about flags that trap in XamInputGetCapabilities
0 == 3 in XamInputGetCapabilities
Name arg 2 of XamInputSetState
PrefetchW in critical section kernel funcs if available & doing cmpxchg
Add terminated field to X_KTHREAD, set it on termination
Expanded the logic of NtResumeThread/NtSuspendThread to include checking the type of the handle (in release, LookupObject doesnt seem to do anything with the type)
and returning X_STATUS_OBJECT_TYPE_MISMATCH if invalid. Do termination check in NtSuspendThread.
Add basic host exception messagebox, need to flesh it out more (maybe use the new stack tracking stuff if on guest thrd?)
Add rdrand patching hack, mostly affects users with nvidia cards who have many threads on zen
Use page_size_shift in more places
Once again disable precompilation! Raiden is mostly weird ppc asm which probably breaks the precompilation. The code is still useful for running the compiler over the whole of an xex in debug to test for issues
"Fix" debug console, we were checking the cvar before any cvars were loaded, and the condition it checks in AttachConsole is somehow always false
Remove dead #if 0'd code in math.h
On amd64, page_size == 4096 constant, on amd64 w/ win32, allocation_granularity == 65536. These values for x86 windows havent changed over the last 20 years so this is probably safe
and gives a modest code size reduction
Enable XE_USE_KUSER_SHARED. This sources host time from KUSER_SHARED instead of from QueryPerformanceCounter, which is far faster, but only has a granularity of 100 nanoseconds.
In some games seemingly random crashes were happening that were hard to trace because
the faulting thread was actually not the one that was misbehaving, another threads stack was underflowing into the faulting thread.
Added a bunch of code to synchronize the guest stack and host stack so that if a guest longjmps the host's stack will be adjusted.
Changes were also made to allow the guest to call into a piece of an existing x64 function.
This synchronization might have a slight performance impact on lower end cpus, to disable it set enable_host_guest_stack_synchronization to false.
It is possible it may have introduced regressions, but i dont know of any yet
So far, i know the synchronization change fixes the "hub crash" in super sonic and allows the game "london 2012" to go ingame.
Removed emit_useless_fpscr_updates, not emitting these updates breaks the raiden game
MapGuestAddressToMachineCode now returns nullptr if no address was found, instead of the start of the function
add Processor::LookupModule
Add Backend::DeinitializeBackendContext
Use WriteRegisterRangeFromRing_WithKnownBound<0, 0xFFFF> in WriteRegisterRangeFromRing for inlining (previously regressed on performance of ExecutePacketType0)
add notes about flags that trap in XamInputGetCapabilities
0 == 3 in XamInputGetCapabilities
Name arg 2 of XamInputSetState
PrefetchW in critical section kernel funcs if available & doing cmpxchg
Add terminated field to X_KTHREAD, set it on termination
Expanded the logic of NtResumeThread/NtSuspendThread to include checking the type of the handle (in release, LookupObject doesnt seem to do anything with the type)
and returning X_STATUS_OBJECT_TYPE_MISMATCH if invalid. Do termination check in NtSuspendThread.
Add basic host exception messagebox, need to flesh it out more (maybe use the new stack tracking stuff if on guest thrd?)
Add rdrand patching hack, mostly affects users with nvidia cards who have many threads on zen
Use page_size_shift in more places
Once again disable precompilation! Raiden is mostly weird ppc asm which probably breaks the precompilation. The code is still useful for running the compiler over the whole of an xex in debug to test for issues
Fixes the PIX validation warning about missing resource states on every guest draw. Also potentially prevents drivers from making assumptions about the shared memory buffer based on the bindings, though no such cases are currently known.
Fix guest code profiler, it previously only worked with function precomp + all code you were about to execute already discovered
Allow AndNot if type is V128
Also fixes addressing of MSAA samples 2 and 3 for 64bpp color render targets in the ROV RB implementation on Direct3D 12.
Additionally, with FSI/ROV, alpha test and alpha to coverage are done only if the render target 0 was dynamically written to (according to the Direct3D 9 rules for writing to color render targets, though not sure if they actually apply to the alpha tests on Direct3D 9, but for safety).
There is also some code cleanup for things spotted during the development of the feature.
add xe::clear_lowest_bit, use it in place of shift-andnot in some bit iteration code
make is_allocated_ and is_enabled_ volatile in xma_context
preallocate avpacket buffer in XMAContext::Setup, the reallocations of the buffer in ffmpeg were showing up on profiles
check is_enabled and is_allocated BEFORE locking an xmacontext. XMA worker was spending most of its time locking and unlocking contexts
Removed XeDMAC, dma:: namespace. It was a bad idea and I couldn't make it work in the end. Kept vastcpy and moved it to the memory namespace instead
Made the rest of global_critical_region's members static. They never needed an instance.
Removed ifdef'ed out code from ring_buffer.h
Added EventInfo struct to threading, added Event::Query to aid with implementing NtQueryEvent.
Removed vector from WaitMultiple, instead use a fixed array of 64 handles that we populate. WaitForMultipleObjects cannot handle more than 64 objects.
Remove XE_MSVC_OPTIMIZE_SMALL() use in x64_sequences, x64 backend is now always size optimized because of premake
Make global_critical_region_ static constexpr in shared_memory.h to get rid of wasteage of 8 bytes (empty class=1byte, +alignment for next member=8)
Move trace-related data to the tail of SharedMemory to keep more important data together
In IssueDraw build an array of fetch constant addresses/sizes, then pre-lock the global lock before doing requestrange for each instead of individually locking within requestrange for each of them
Consistent access specifier protected for pm4_command_processor_declare
Devirtualize WriteOneRegisterFromRing.
Move ExecutePacket and ExecutePrimaryBuffer to pm4_command_buffer_x
Remove many redundant header inclusions access xenia-gpu
Minor microoptimization of ExecutePacketType0
Add TextureCache::RequestTextures for batch invocation of LoadTexturesData
Add TextureCache::LoadTexturesData for reducing the number of times we release and reacquire the global lock.
Ideally you should hold the global lock for as little time as possible, but if you are constantly acquiring and releasing it you are actually more likely to have contention
Add already_locked param to ObjectTable::LookupObject to help with reducing lock acquire/release pairs
Add missing checks to XAudioRegisterRenderDriverClient_entry. this is unlikely to fix anything, it was just an easy thing to do
Add NtQueryEvent system call implementation. I don't actually know of any games that need it.
Instead of using std::vector + push_back in KeWaitForMultipleObjects and xeNtWaitForMultipleObjectsEx use a fixed size array of 64 and track the count. More than 64 objects is not permitted by the kernel. The repeated reallocations from push_back were appearing unusually high on the profiler, but were masked until now by waitformultipleobjects natural overhead
Pre-lock the global lock before looking up each handle for xeNtWaitForMultipleObjectsEx and KeWaitForMultipleObjects.
Pre-lock before looking up the signal and waiter in NtSignalAndWaitForSingleObjectEx
add missing checks to NtWaitForMultipleObjectsEx
Support pre-locking in XObject::GetNativeObject
remove useless memorybarrier
remove double membarrier in wait pm4 cmd
add int64 cvar
use int64 cvar for x64 feature mask
Rework some functions that were frontend bound according to vtune placing some of their code in different noinline functions, profiling after indicating l1 cache misses decreased and perf of func increased
remove long vpinsrd dep chain code for conversion.h, instead do normal load+bswap or movbe if avail
Much faster entry table via split_map, code size could be improved though
GetResolveInfo was very large and had impact on icache, mark callees as noinline + msvc pragma optimize small
use log2 shifts instead of integer divides in memory
minor optimizations in PhysicalHeap::EnableAccessCallbacks, the majority of time in the function is spent looping, NOT calling Protect! Someone should optimize this function and rework the algo completely
remove wonky scheduling log message, it was spammy and unhelpful
lock count was unnecessary for criticalsection mutex, criticalsection is already a recursive mutex
brief notes i gotta run
PM4 buffer handling made a virtual member of commandprocessor, place the implementation/declaration into reusable macro files. this is probably the biggest boost here.
Optimized SET_CONSTANT/ LOAD_CONSTANT pm4 ops based on the register range they start writing at, this was also a nice boost
Expose X64 extension flags to code outside of x64 backend, so we can detect and use things like avx512, xop, avx2, etc in normal code
Add freelists for HIR structures to try to reduce the number of last level cache misses during optimization (currently disabled... fixme later)
Analyzed PGO feedback and reordered branches, uninlined functions, moved code out into different functions based on info from it in the PM4 functions, this gave like a 2% boost at best.
Added support for the db16cyc opcode, which is used often in xb360 spinlocks. before it was just being translated to nop, now on x64 we translate it to _mm_pause but may change that in the future to reduce cpu time wasted
texture util - all our divisors were powers of 2, instead we look up a shift. this made texture scaling slightly faster, more so on intel processors which seem to be worse at int divs. GetGuestTextureLayout is now a little faster, although it is still one of the heaviest functions in the emulator when scaling is on.
xe_unlikely_mutex was not a good choice for the guest clock lock, (running theory) on intel processors another thread may take a significant time to update the clock? maybe because of the uint64 division? really not sure, but switched it to xe_mutex. This fixed audio stutter that i had introduced to 1 or 2 games, fixed performance on that n64 rare game with the monkeys.
Took another crack at DMA implementation, another failure.
Instead of passing as a parameter, keep the ringbuffer reader as the first member of commandprocessor so it can be accessed through this
Added macro for noalias
Applied noalias to Memory::LookupHeap. This reduced the size of the executable by 7 kb.
Reworked kernel shim template, this shaved like 100kb off the exe and eliminated the indirect calls from the shim to the actual implementation. We still unconditionally generate string representations of kernel calls though :(, unless it is kHighFrequency
Add nvapi extensions support, currently unused. Will use CPUVISIBLE memory at some point
Inserted prefetches in a few places based on feedback from vtune.
Add native implementation of SHA int8 if all elements are the same
Vectorized comparisons for SetViewport, SetScissorRect
Vectorized ranged comparisons for WriteRegister
Add XE_MSVC_ASSUME
Move FormatInfo::name out of the structure, instead look up the name in a different table. Debug related data and critical runtime data are best kept apart
Templated UpdateSystemConstantValues based on ROV/RTV and primitive_polygonal
Add ArchFloatMask functions, these are for storing the results of floating point comparisons without doing costly float->int pipeline transfers (vucomiss/setb)
Use floatmasks in UpdateSystemConstantValues for checking if dirty, only transfer to int at end of function.
Instead of dirty |= (x == y) in UpdateSystemConstantValues, now we do dirty_u32 |= (x^y). if any of them are not equal, dirty_u32 will be nz, else if theyre all equal it will be zero. This is more friendly to register renaming and the lack of dependencies on EFLAGS lets the compiler reorder better
Add PrefetchSamplerParameters to D3D12TextureCache
use PrefetchSamplerParameters in UpdateBindings to eliminate cache misses that vtune detected
Add PrefetchTextureBinding to D3D12TextureCache
Prefetch texture bindings to get rid of more misses vtune detected (more accesses out of order with random strides)
Rewrote DMAC, still terrible though and have disabled it for now.
Replace tiny memcmp of 6 U64 in render_target_cache with inline loop, msvc fails to make it a loop and instead does a thunk to their memcmp function, which is optimized for larger sizes
PrefetchTextureBinding in AreActiveTextureSRVKeysUpToDate
Replace memcmp calls for pipelinedescription with handwritten cmp
Directly write some registers that dont have special handling in PM4 functions
Changed EstimateMaxY to try to eliminate mispredictions that vtune was reporting, msvc ended up turning the changed code into a series of blends
in ExecutePacketType3_EVENT_WRITE_EXT, instead of writing extents to an array on the stack and then doing xe_copy_and_swap_16 of the data to its dest, pre-swap each constant and then store those. msvc manages to unroll that into wider stores
stop logging XE_SWAP every time we receive XE_SWAP, stop logging the start and end of each viz query
Prefetch watch nodes in FireWatches based on feedback from vtune
Removed dead code from texture_info.cc
NOINLINE on GpuSwap, PGO builds did it so we should too.
Remove the logger_ != nullptr check from shouldlog, it will nearly always be true except on initialization and gets checked later anyway, this shrinks the size of the generated code for some
Select specialized vastcpy for current cpu, for now only have paths for MOVDIR64B and generic avx1
Add XE_UNLIKELY/LIKELY if, they map better to the c++ unlikely/likely attributes which we will need to use soon
Finished reimplementing STVL/STVR/LVL/LVR as their own opcodes. we now generate far less code for these instructions. this also means optimization passes can be written to simplify/remove/replace these instructions in some cases. Found that a good deal of the X86 we were emitting for these instructions was dead code or redundant.
the reduction in generated HIR/x86 should help a lot with compilation times and make function precompilation more feasible as a default
Don't static assert in default prefetch impl, in c++20 the assertion will be triggered even without an instantiation
Reorder some if/else to prod msvc into ordering the branches optimally. it somewhat worked...
Added some notes about which opcodes should be removed/refactored
Dispatch in WriteRegister via vector compares for the bounds. still not very optimal, we ought to be checking whether any register in a range may be special
A lot of work on trying to optimize writeregister, moved wraparound path into a noinline function based on profiling info
Hoist the IsUcodeAnalyzed check out of AnalyzeShader, instead check it before each call. Profiler recorded many hits in the stack frame setup of the function, but none in the actual body of it, so the check is often true but the stack frame setup is run unconditionally
Pre-check whether we're about to write a single register from a ring
Replace more jump tables from draw_util/texture_info with popcnt based sparse indexing/bit tables/shuffle lookups
Place the GPU register file on its own VAD/virtual allocation, it is no longer a member of graphics system
