Commit graph

11 commits

Author SHA1 Message Date
Nekotekina
12c83b340d Remove built_function
With today's branch prediction techniques, it's hardly useful.
2022-01-24 22:21:41 +03:00
Nekotekina
a4d94a83b9 PPU/simd.hpp: minor changes in DP instructions 2022-01-21 13:57:46 +03:00
Nekotekina
628354ba92 Use global variable in gv_zeroupper 2022-01-20 21:16:00 +03:00
Nekotekina
8c3fb3998c PPU: fix crash on SSE41 CPU in internal builder 2022-01-20 14:42:58 +03:00
Nekotekina
d572d90bb7 PPU: fixup for old CPU
Abort building interpreter function when out of registers.
2022-01-20 08:31:08 +03:00
Nekotekina
b42fae0989 PPU: refactor shift and splat instructions
Fix utils::rol32/64 functions.
Fix immediate clamping in splat instructions.
Other fixes.
2022-01-19 23:01:31 +03:00
Nekotekina
4728478247 PPU: improve interpreter codegen
Implement more sensible check for EVEX prefix and SSE
2022-01-18 04:20:06 +03:00
Nekotekina
14cca55b50 PPU: refactor vector rounding instructions
Fix: nearbyint -> roundeven
2022-01-18 00:10:32 +03:00
Nekotekina
248f9424ac PPU: refactor VPack instructions 2022-01-18 00:10:19 +03:00
Nekotekina
b404d37eb0 PPU: more interpreter refactoring (VPERM)
Notably, runtime-built SSSE3 version of VPERM.
Some other instructions are refactored and vectorized.
Aarch64 impl of multiple instructions including VPERM.
2022-01-18 00:10:19 +03:00
Nekotekina
580bd2b25e Initial Linux Aarch64 support
* 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
2022-01-15 06:48:04 +03:00