* BufferUtils: use naive function pointer on Apple arm64
Use naive function pointer on Apple arm64 because ASLR breaks asmjit.
See BufferUtils.cpp comment for explanation on why this happens and how
to fix if you want to use asmjit.
* build-macos: fix source maps for Mac
Tell Qt not to strip debug symbols when we're in debug or relwithdebinfo
modes.
* LLVM PPU: fix aarch64 on macOS
Force MachO on macOS to fix LLVM being unable to patch relocations
during codegen. Adds Aarch64 NEON intrinsics for x86 intrinsics used by
PPUTranslator/Recompiler.
* virtual memory: use 16k pages on aarch64 macOS
Temporary hack to get things working by using 16k pages instead of 4k
pages in VM emulation.
* PPU/SPU: fix NEON intrinsics and compilation for arm64 macOS
Fixes some intrinsics usage and patches usages of asmjit to properly
emit absolute jmps so ASLR doesn't cause out of bounds rel jumps. Also
patches the SPU recompiler to properly work on arm64 by telling LLVM to
target arm64.
* virtual memory: fix W^X toggles on macOS aarch64
Fixes W^X on macOS aarch64 by setting all JIT mmap'd regions to default
to RW mode. For both SPU and PPU execution threads, when initialization
finishes we toggle to RX mode. This exploits Apple's per-thread setting
for RW/RX to let us be technically compliant with the OS's W^X
enforcement while not needing to actually separate the memory
allocated for code/data.
* PPU: implement aarch64 specific functions
Implements ppu_gateway for arm64 and patches LLVM initialization to use
the correct triple. Adds some fixes for macOS W^X JIT restrictions when
entering/exiting JITed code.
* PPU: Mark rpcs3 calls as non-tail
Strictly speaking, rpcs3 JIT -> C++ calls are not tail calls. If you
call a function inside e.g. an L2 syscall, it will clobber LR on arm64
and subtly break returns in emulated code. Only JIT -> JIT "calls"
should be tail.
* macOS/arm64: compatibility fixes
* vm: patch virtual memory for arm64 macOS
Tag mmap calls with MAP_JIT to allow W^X on macOS. Fix mmap calls to
existing mmap'd addresses that were tagged with MAP_JIT on macOS. Fix
memory unmapping on 16K page machines with a hack to mark "unmapped"
pages as RW.
* PPU: remove wrong comment
* PPU: fix a merge regression
* vm: remove 16k page hacks
* PPU: formatting fixes
* PPU: fix arm64 null function assembly
* ppu: clean up arch-specific instructions
- Adds AVX512 path for upload_untouched u16 with primitive restart, and
AVX2 and AVX512 paths for upload_untouched without restart
- The AVX512 paths handle the remainder in simd code with masking, which
provided a large speedup
- On my i5-1135G7 in demons souls benchmarking a scene in boletaria with
a lot of geometry on screen via perf:
SSE4_1 0.64%
AVX2 0.59%
AVX512 0.56%
AVX512 w/ remainder masking 0.51%
- For some reason this has a massive impact on performance above some arbitrary threshold of calls
Shows up under surface_cache::get_merged_memory_region when doing gathers.
- Creating new images is expensive.
- We can keep around a set of images that have been recently discarded and use them instead of creating new ones from scratch each time.
* Update asmjit dependency (aarch64 branch)
* Disable USE_DISCORD_RPC by default
* Dump some JIT objects in rpcs3 cache dir
* Add SIGILL handler for all platforms
* Fix resetting zeroing denormals in thread pool
* Refactor most v128:: utils into global gv_** functions
* Refactor PPU interpreter (incomplete), remove "precise"
* - Instruction specializations with multiple accuracy flags
* - Adjust calling convention for speed
* - Removed precise/fast setting, replaced with static
* - Started refactoring interpreters for building at runtime JIT
* (I got tired of poor compiler optimizations)
* - Expose some accuracy settings (SAT, NJ, VNAN, FPCC)
* - Add exec_bytes PPU thread variable (akin to cycle count)
* PPU LLVM: fix VCTUXS+VCTSXS instruction NaN results
* SPU interpreter: remove "precise" for now (extremely non-portable)
* - As with PPU, settings changed to static/dynamic for interpreters.
* - Precise options will be implemented later
* Fix termination after fatal error dialog
Drop AVX2 path for now, since it usually operates on small data.
Rely on automatic SSE vectorization on recent compilers.
Side refactoring on JIT.h to workaround weird conflict issue.
Optimize CPU capability tests for arch-tuned builds.
Separate streaming and non-streaming utilities.
Rewritten copy_data_swap_u32(_cmp) with AVX2 path.
- Just use RGB565 for all blit targets. Avoids really dumb transforms done by GPU hw.
- When X16 is used, all the channels get written to R channel alone. CmdBlit does perform format conversion!
- gl: Force image copy when blit is requested with compatible targets. Avoids format conversion issues.
- Avoids a situation where blit-dst and blit-src have overlapping ranges. Uploading blit-dst destroys blit-src and vice-versa.
This is not the end of the world, but blit-src should be kept around until the operation is completed to avoid stale references!
- Explicitly declare one version for CB flush and the other for Async flush
- Always flush descriptors on CB flush in case of page fault handling.
Other threads other than offloader can also enter the method and require normal flow.
- Fix overlapping interrupt IDs.
- Minor formatting fixes
