steam-frame/FEX-Emu--FEX
1
0 Fork 0
mirror of https://github.com/FEX-Emu/FEX.git synced 2026-10-11 09:00:21 +02:00
Code Issues Packages Projects Releases 67 Wiki Activity
15,031 Commits 11 Branches 71 Tags
e4e45bcc59cd2e629dd3eca1d39263b3385a4ee6
Commit Graph
121 Commits
Author SHA1 Message Date
Ryan Houdek 4048faa54b FEXCore/Frontend: Ensure instruction sizes account for sha256 in thunk op 
Fixes the hashing mechanism from DiskCache.cpp, allowing it to properly
handle thunk relocations.

Fixes #5896
 2026-09-02 14:32:08 -07:00
Justin Becker 34a87cc94c Decoder: fix illegal LEA encoding 2026-07-27 15:48:35 -07:00
LC ab4fb7b3ad [SVE256] Ensure insertion behavior for AES operations on SSE 
These slipped through, so now we can add tests for them to prevent that
from happening again.
 2026-07-03 19:35:31 -04:00
LC df41b85827 OpcodeDispatcher: Merge VPINSRB/VPINSRW handling 
We can just pass the size through Bind instead of having two functions
that effectively do the same thing, only differing on element size.
 2026-06-21 15:33:37 -04:00
LC 8989ce1766 [SVE256] Handle SSE insertions for PCMPESTRM/PCMPISTRM ops 
See #3799
 2026-06-19 18:53:50 -04:00
LC f64d4c571b [SVE256] Handle SSE insertions for MOVSHDUP/MOVSLDUP 
See #3799
 2026-06-17 20:38:58 -04:00
LC daaa6ec129 [SVE256] Handle SSE insertions for aligned and unaligned moves 
See #3799
 2026-06-17 19:39:06 -04:00
LC 88afc22d5b [SVE256] Handle SSE insertions for MOVNTDQA 
See #3799
 2026-06-17 19:38:57 -04:00
LC 634fbb5a73 [SVE256] Handle SSE insertions for Float->Int/Int->Float conversions 
See #3799
 2026-06-17 04:44:39 -04:00
LC a0e8f1097f [SVE256] Handle SSE insertions for PHMINPOSUW 
See #3799
 2026-06-17 01:21:19 -04:00
LC 32b11603d8 [SVE256] Handle SSE insertions for PMOVSX/PMOVZX ops 2026-06-17 00:04:03 -04:00
LC c62805e86d OpcodeDispatcher: Make use of Bind consistently 
We had a few places that were using Bind, and a few other places
that were using specializations as a means to composing the instruction
tables. Instead, we can just use Bind consistently, which lets us tidy
up a bunch of the implementations (and gets rid of some unnecessary
codegen).
 2026-06-16 15:07:59 -04:00
Ryan Houdek 1b58664541 X86Tables: Describe instructions that support LOCK prefix 2026-06-02 19:41:02 -07:00
Daniel Lu 5cce65cdfa OpcodeDispatcher: Decode INVD and WBINVD through privileged op handling 2026-05-22 15:25:22 -07:00
Simon Scherer ab14882761 FEXCore: Fix 2byte stack access for 0x66 PUSH/POP FS/GS 2026-04-27 15:21:11 -07:00
Ryan Houdek 2e6a7f869c OpcodeDispatcher: Fixes nop encoded prefetch instruction 
We had a bug where nop encoded prefetch instructions were getting
flagged as illegal instructions erroneously. Fix that and add a unittest
for ensuring execution.

Fixes `Devil May Cry 4`
 2026-04-06 11:04:46 -07:00
Tony Wasserka 22faa58e0b X86Tables: Use explicit type for SecondInstGroupOps definition 
GCC considers it a "conflicting declaration" to use auto for a variable that
was already declared before.
 2026-03-16 19:15:05 +01:00
Lioncache c8f3772753 X87Tables: Handle aliases for FSTP 2026-02-26 19:08:48 -05:00
Lioncache b046942a28 X87Tables: Handle aliases for FXCH 2026-02-26 17:44:12 -05:00
Lioncache 6909d49683 X87Tables: Add handling for FCOMP DE D0 aliases 
Handles the single remaining alias for FCOMP.
 2026-02-26 16:14:55 -05:00
Ryan Houdek cf3c41acc7 FEXCore: Fixup ARPL implementation 
Some subtle details were wrong in the implementation, and some minor
changes to be more optimal.
 2026-02-10 14:29:32 -08:00
FrontMage 9bf9c00474 x86: implement ARPL (0x63) in 32-bit mode 2026-02-10 14:12:52 -08:00
FrontMage 51afcc5ca8 x87: fix dispatch table sizes after adding FCOM/FCOMP 2026-02-10 18:08:41 +08:00
FrontMage 7a0ed4c462 x87: support 0xDC D0/D8 FCOM/FCOMP st(i) 2026-02-10 18:08:41 +08:00
Tony Wasserka ba2b0ef809 Enable automatic code formatting for X86Tables.h 2026-01-23 15:39:54 +01:00
Ryan Houdek 0b92d431f5 Frontend: Only decode REX if it is at the correct location 
Otherwise it is a nop
 2025-12-29 17:57:12 -08:00
Ryan Houdek 3025a10808 FEXCore: Revert literal optimization from #4884 
This no longer does anything due to #5123
 2025-12-22 10:00:55 -08:00
Billy Laws 2878583627 OpcodeDispatcher: Support relocated operand type variants 
In order to support code caching of 32-bit libraries, any library-base
relative relocations on the guest must be transformed into FEX
relocations so e.g. absolute jumps or loads refer to the correct
location when the library is loaded at a different base address.
 2025-12-22 16:19:02 +00:00
Ryan Houdek d654f55c3c OpcodeDispatcher: Move FEX reserved instruction 
This now conflicts with an SMX instruction, so move it over to another
bytecode that is unlikely to be used.
 2025-10-16 11:20:58 -07:00
Lioncache 7aa5bc0503 EnumUtils: Further simplify enum passthrough formatting 
Turns out a simpler way was added to the docs at some point and I never
noticed.

Before:
   text     data      bss      dec      hex  filename
4159895  1471360  4336824  9968079   9819cf  Bin/FEX

After:
   text     data      bss      dec      hex  filename
4157159  1471360  4336824  9965343   980f1f  Bin/FEX
 2025-10-07 01:52:05 -04:00
Lioncache b7117b86ea X86Tables: Remove unused LateInitCopyTable() 2025-10-06 15:04:36 -04:00
Ryan Houdek b5d93bc4a0 Merge pull request #4928 from lioncash/passthru 
EnumUtils: Add define for default passthrough formatting
 2025-10-03 19:45:41 -07:00
Ryan Houdek f45be1f59e OpcodeDispatcher: Implement support for imm extrq/insertq 
Fairly straightforward to implement, but not exciting in their
performance.
 2025-10-03 13:05:43 -07:00
Lioncache a0c2ce0068 EnumUtils: Add define for default passthrough formatting 
Handles a normal case where printing an enum type as an integral value
is still desirable.

Mainly just a way to reduce boilerplate.
 2025-10-03 14:21:19 -04:00
Ryan Houdek 3fa400bc55 Frontend: Improve DecodeInst size from 128 bytes to 80 
We were paying a large cost per Literal type that we can special case
for the two class of instructions that use a 64-bit literal.

If we packed this would get to a further 62 bytes but probably not worth
it.
 2025-09-12 16:07:01 -07:00
Ryan Houdek 90ea16325a Frontend: Move a couple of members from DecodeInst 
LastEscapePrefix doesn't need to be in DecodeInst, and we can have a
couple of flags for ForceTSO/DecodedSIB/DecodedModRM.
 2025-09-12 15:37:18 -07:00
Lioncache f9c15fa0a5 Frontend/OpcodeDispatcher: Remove unused headers 
Removes assorted unused headers and forward declarations.
 2025-09-09 00:28:05 -04:00
Ryan Houdek bd0cae9298 Merge pull request #4825 from bylaws/unityomg 
Frontend: Force acq/rel semantics for known Unity ringbuffer offsets
 2025-09-06 17:09:13 -07:00
Ryan Houdek 6ae94581bb Merge pull request #4821 from bylaws/monof 
Frontend: Fix tailcall handling when mono hacks are enabled
 2025-09-06 16:51:08 -07:00
Billy Laws 28a1c28cb4 Frontend: Track the raw opcode and use for mono tailcall detection 
This path was nonfunctional prior to this, as the jump is a group-opcode
which wouldn't be picked up (as Op is rewritten in NormalOp).
 2025-09-02 22:42:02 +01:00
Billy Laws fcba49768c Frontend: Force acq/rel semantics for known Unity ringbuffer offsets 
Unity games crash with TSO disabled due to the SPSC GfxDevice
ThreadedStreamBuffer read/write pointer updates missing acq/rel
semantics. Rather than attempting to use heuristics to match cases like
this, which could be overzealous and hit more accesses than necessary, just
target the problem directly as this is consist across 32/64 bit Unity versions
for at least the past 10 years. Gate this behind the existing Unity mono
hacks to avoid false-positives in non-Unity games.
 2025-09-02 22:05:22 +01:00
Lioncache 1f756fb386 General: Replace usages of .at(0) with .data() where applicable 
This is generally more straightforward in cases where bounds checking isn't necessary.
 2025-09-02 13:03:37 -04:00
Ryan Houdek add54b8089 X86Tables: Convert AVX tables to constexpr 
One set of tables for 128-bit and one set of tables for 256-bit.
This one took a bit longer since I needed to convert a few handlers over
to `Bind`. With this all of our x86 tables are costexpr so they end up
in RO mapped memory which is great.
 2025-08-27 14:55:10 -07:00
Ryan Houdek 80cacc462e X86Tables: Move x87 tables to be constexpr 2025-08-27 12:24:25 -07:00
Ryan Houdek 1a2b2f8870 X86Tables: Move Second ModRM table to be constexpr 2025-08-27 12:24:25 -07:00
Ryan Houdek e8c576047f X86Tables: Moves Base ops to be constexpr 2025-08-27 12:24:25 -07:00
Ryan Houdek 995d3152eb X86Tables: Convert Secondary tables to constexpr 2025-08-27 12:24:25 -07:00
Ryan Houdek ddc40cc273 X86Tables: Converts PrimaryGroup table to constexpr 2025-08-27 12:24:25 -07:00
Ryan Houdek 5ee311b831 X86Tables: Converts H0F3A table to constexpr 2025-08-27 12:24:24 -07:00
Ryan Houdek ea90296e22 X86Tables: Converts H0F38 table to constexpr 2025-08-27 12:24:24 -07:00