Commit graph

34 commits

Author SHA1 Message Date
gdkchan
a731ab3a2a Add a new JIT compiler for CPU code (#693)
* Start of the ARMeilleure project

* Refactoring around the old IRAdapter, now renamed to PreAllocator

* Optimize the LowestBitSet method

* Add CLZ support and fix CLS implementation

* Add missing Equals and GetHashCode overrides on some structs, misc small tweaks

* Implement the ByteSwap IR instruction, and some refactoring on the assembler

* Implement the DivideUI IR instruction and fix 64-bits IDIV

* Correct constant operand type on CSINC

* Move division instructions implementation to InstEmitDiv

* Fix destination type for the ConditionalSelect IR instruction

* Implement UMULH and SMULH, with new IR instructions

* Fix some issues with shift instructions

* Fix constant types for BFM instructions

* Fix up new tests using the new V128 struct

* Update tests

* Move DIV tests to a separate file

* Add support for calls, and some instructions that depends on them

* Start adding support for SIMD & FP types, along with some of the related ARM instructions

* Fix some typos and the divide instruction with FP operands

* Fix wrong method call on Clz_V

* Implement ARM FP & SIMD move instructions, Saddlv_V, and misc. fixes

* Implement SIMD logical instructions and more misc. fixes

* Fix PSRAD x86 instruction encoding, TRN, UABD and UABDL implementations

* Implement float conversion instruction, merge in LDj3SNuD fixes, and some other misc. fixes

* Implement SIMD shift instruction and fix Dup_V

* Add SCVTF and UCVTF (vector, fixed-point) variants to the opcode table

* Fix check with tolerance on tester

* Implement FP & SIMD comparison instructions, and some fixes

* Update FCVT (Scalar) encoding on the table to support the Half-float variants

* Support passing V128 structs, some cleanup on the register allocator, merge LDj3SNuD fixes

* Use old memory access methods, made a start on SIMD memory insts support, some fixes

* Fix float constant passed to functions, save and restore non-volatile XMM registers, other fixes

* Fix arguments count with struct return values, other fixes

* More instructions

* Misc. fixes and integrate LDj3SNuD fixes

* Update tests

* Add a faster linear scan allocator, unwinding support on windows, and other changes

* Update Ryujinx.HLE

* Update Ryujinx.Graphics

* Fix V128 return pointer passing, RCX is clobbered

* Update Ryujinx.Tests

* Update ITimeZoneService

* Stop using GetFunctionPointer as that can't be called from native code, misc. fixes and tweaks

* Use generic GetFunctionPointerForDelegate method and other tweaks

* Some refactoring on the code generator, assert on invalid operations and use a separate enum for intrinsics

* Remove some unused code on the assembler

* Fix REX.W prefix regression on float conversion instructions, add some sort of profiler

* Add hardware capability detection

* Fix regression on Sha1h and revert Fcm** changes

* Add SSE2-only paths on vector extract and insert, some refactoring on the pre-allocator

* Fix silly mistake introduced on last commit on CpuId

* Generate inline stack probes when the stack allocation is too large

* Initial support for the System-V ABI

* Support multiple destination operands

* Fix SSE2 VectorInsert8 path, and other fixes

* Change placement of XMM callee save and restore code to match other compilers

* Rename Dest to Destination and Inst to Instruction

* Fix a regression related to calls and the V128 type

* Add an extra space on comments to match code style

* Some refactoring

* Fix vector insert FP32 SSE2 path

* Port over the ARM32 instructions

* Avoid memory protection races on JIT Cache

* Another fix on VectorInsert FP32 (thanks to LDj3SNuD

* Float operands don't need to use the same register when VEX is supported

* Add a new register allocator, higher quality code for hot code (tier up), and other tweaks

* Some nits, small improvements on the pre allocator

* CpuThreadState is gone

* Allow changing CPU emulators with a config entry

* Add runtime identifiers on the ARMeilleure project

* Allow switching between CPUs through a config entry (pt. 2)

* Change win10-x64 to win-x64 on projects

* Update the Ryujinx project to use ARMeilleure

* Ensure that the selected register is valid on the hybrid allocator

* Allow exiting on returns to 0 (should fix test regression)

* Remove register assignments for most used variables on the hybrid allocator

* Do not use fixed registers as spill temp

* Add missing namespace and remove unneeded using

* Address PR feedback

* Fix types, etc

* Enable AssumeStrictAbiCompliance by default

* Ensure that Spill and Fill don't load or store any more than necessary
2019-08-08 21:56:22 +03:00
LDj3SNuD
e5b88de22a Add Saddlv_V Inst. Improve Cnt_V, Dup_Gp & Ins_Gp Tests. Tuneup Cls_V & Clz_V Tests. (#720)
* Update PackageReferences.

* Improve Cnt_V Test. Tuneup Cls_V & Clz_V Tests.

Nit.

* Nit.

* Improve Dup_Gp & Ins_Gp Tests.

* Update for Saddlv_V Inst.

* Update for Saddlv_V Inst.

* Update for Saddlv_V Inst.
2019-07-08 11:55:37 -03:00
Alex Barney
b2b736abc2 Misc cleanup (#708)
* Fix typos

* Remove unneeded using statements

* Enforce var style more

* Remove redundant qualifiers

* Fix some indentation

* Disable naming warnings on files with external enum names

* Fix build

* Mass find & replace for comments with no spacing

* Standardize todo capitalization and for/if spacing
2019-07-02 04:39:22 +02:00
LDj3SNuD
10c74182ba Implement the remaining tests for Simd and Fp instructions of data processing type. Small opts. for Fmov_Ftoi/1 & Fmov_Itof/1 Insts. (#709)
* Update CpuTestSimdShImm.cs

* Update OpCodeTable.cs

* Update CpuTestSimdReg.cs

* Add Ins_Gp & Ins_V Tests.

Improve Smov_S & Umov_S Tests.

* Add Bic_Vi & Orr_Vi Tests.

* OpTable Fixes for Bic_Vi & Orr_Vi Insts.

* Add Saddlv_V & Uaddlv_V Tests.

* Nit.

* Add Smull_V & Umull_V Tests.

Improve Simd Permute Tests.

* Nit.

* Add Fcsel_S Test.

* Add Fnmadd_S, Fnmsub_S & Fnmul_S Tests.

* Fmov_V -> Fmov_Vi

* OpTable Fixes for Fmov_Si & Fmov_Vi Insts.

* Add Fmov_Vi Test.

* Add Fmov_S Test.

* Add Fmov_Si Test.

Add new test category SimdFmov.

* Nit.

* OpTable Fixes for Fmov_Ftoi/1 & Fmov_Itof/1 Insts.

* Small opts. for Fmov_Ftoi/1 & Fmov_Itof/1 Insts.

Small simpl. for Smov_S Inst.
Remove unnecessary method EmitIntZeroUpperIfNeeded.

* Add Fmov_Ftoi/1 & Fmov_Itof/1 Tests.
2019-06-29 20:02:48 -03:00
LDj3SNuD
ffbfbb5549 Add FCVT <Hd>, <Sn> and FCVT <Sd>, <Hn> Inst.; add Tests. (#692)
* Update OpCodeTable.cs

* Update InstEmitSimdCvt.cs

* Update CpuTestSimd.cs

* Address PR feedback.
2019-05-30 19:51:39 -03:00
LDj3SNuD
51ea6fa583 Add Smaxv_V, Sminv_V, Umaxv_V, Uminv_V Inst.; add Tests. (#691)
* Update InstEmitSimdHelper.cs

* Update InstEmitSimdArithmetic.cs

* Update OpCodeTable.cs

* Update CpuTestSimd.cs
2019-05-29 21:29:24 -03:00
gdkchan
8a7d99cdea Refactoring and optimization on CPU translation (#661)
* Refactoring and optimization on CPU translation

* Remove now unused property

* Rename ilBlock -> block (local)

* Change equality comparison on RegisterMask for consistency

Co-Authored-By: gdkchan <gab.dark.100@gmail.com>

* Add back the aggressive inlining attribute to the Synchronize method

* Implement IEquatable on the Register struct

* Fix identation
2019-04-26 14:55:12 +10:00
LDj3SNuD
16de171c44 Sse optimized the Scalar & Vector fp-to-fp conversion instructions (MNPZ & IX); added the related Tests (AMNPZ & IX). Small refactoring of existing instructions. (#676)
* Nit.

* Update InstEmitSimdCvt.cs

* Update VectorHelper.cs

* Update InstEmitSimdArithmetic.cs

* Update CpuTestSimd.cs

* Superseded.
2019-04-26 08:58:29 +10:00
LDj3SNuD
74da8785a5 Sse optimized the 32-bit Vector & Scalar integer-to-fp conversion instructions (signed & unsigned); added the related Gp & V_Fixed Tests (signed & unsigned). (#662)
* Update CpuTestSimdCvt.cs

* Update CpuTestSimd.cs

* Update CpuTestSimdShImm.cs

* Update InstEmitSimdCvt.cs

* Update OpCodeTable.cs

* Update InstEmitSimdCvt.cs
2019-04-20 23:07:35 -03:00
LDj3SNuD
233fc95e1e Sse optimized the Vector & Scalar fp-to-integer conversion instructions (unsigned); improved the related Tests. (#656)
* Update InstEmitSimdCvt.cs

* Update CpuTestSimdCvt.cs

* Update CpuTestSimd.cs

* Update CpuTestSimdShImm.cs

* Update InstEmitSimdCvt.cs
2019-04-12 13:14:16 -03:00
LDj3SNuD
febc2ad6f4 Sse optimized all the fp to integer conversion instructions (signed) with Tests (signed & unsigned). (#655)
* Update CpuTestSimdCvt.cs

* Update CpuTestSimd.cs

* Update CpuTestSimdShImm.cs

* Update InstEmitSimdCvt.cs

* Update InstEmitSimdMove.cs

* Update InstEmitSimdCmp.cs

* Update VectorHelper.cs

* Update InstEmitSimdHelper.cs

* Update OpCodeTable.cs

* Update InstEmitSimdCvt.cs

* Update InstEmitSimdHelper.cs

* Update InstEmitSimdMove.cs
2019-04-03 09:21:22 -03:00
LDj3SNuD
464ec7ced8 Add Cmeq_V, Cmge_V, Cmgt_V, Cmle_V & Cmlt_V (Z & ~Z) Sse opt.. (#646)
* Follow-up (Neg_V).

* Follow-up (Not_V & Orn_V).

* Add Cmeq/ge/gt/le/lt_V (Z & ~Z) Sse opt..

* Add EmitLd/Stvectmp2/3.

* Remove Dup (EmitVectorPairwiseSseOrSse2OpF).

* Remove Dup (EmitFcmpOrFcmpe).

* Add S/Uabd/l_V Sse opt.. Remove Dup (Srhadd_V).

* Nit.
2019-03-25 10:23:27 +11:00
LDj3SNuD
c106ae9944 Add Tbl_V Sse opt. with Tests. (#651)
* Add v4, v5, v30, v31 required for Tbl_V Tests.

* Add Tests for Tbl_V.

* Add Tbl_V Sse opt..

* Nit.

* Small opt. on comparison constant vector.

* Nit.

* Add EmitLd/Stvectmp2/3.

* Nit.
2019-03-23 15:50:19 -03:00
LDj3SNuD
1bef70c068 Add Rshrn_V & Shrn_V Sse opt.. Add Mla_V, Mls_V & Mul_V Sse opt.; add Tests. (#614)
* Update CountLeadingZeros().

* Remove obsolete Tests.

* Follow-up.

* Follow-up.

* Follow-up.

* Add Mla_V, Mls_V & Mul_V Tests.

* Update PackageReferences.

* Remove EmitLd/Stvectmp2().

* Remove Dup. Nits.

* Remove EmitLd/Stvectmp2() & Dup; nits.

* Remove Tmp stuff & Dup; rework Fcvtz() as Fcvtn().

* Remove Tmp stuff, EmitLd/Stvectmp2() & Dup. Nits.

* Add (R)shrn_V Sse opt.; add "Part" & "Shift" opt..

Remove Tmp stuff; remove Dup.
Nits.

* Add Mla/Mls/Mul_V Sse opt.. Add "Part" opt..

Remove EmitLd/Stvectmp2(), remove Dup.
Nits.

* Nits.

* Nits.

* Nit.

* Add "Part" opt.. Nit.

* Nit.

* Nit.

* Add Cmhi_V & Cmhs_V Sse opt..
2019-03-13 19:23:52 +11:00
gdkchan
e21ebbf666 Misc. CPU optimizations (#575)
* Add optimizations related to caller/callee saved registers, thread synchronization and disable tier 0

* Refactoring

* Add a config entry to enable or disable the reg load/store opt.

* Remove unnecessary register state stores for calls when the callee is know

* Rename IoType to VarType

* Enable tier 0 while fixing some perf issues related to tier 0

* Small tweak -- Compile before adding to the cache, to avoid lags

* Add required config entry
2019-02-28 13:03:31 +11:00
gdkchan
81aa50feb0 Optimize MOVI/MVNI instructions using intrinsics (#606) 2019-02-26 23:50:36 +11:00
gdkchan
ef3f9a2abe Optmize BFM instruction (#607) 2019-02-26 20:16:50 +11:00
gdkchan
504f4f4abf Remove all the calls to StaticCast methods (#605) 2019-02-26 10:46:34 +11:00
gdkchan
5001f78b1d Optimize address translation and write tracking on the MMU (#571)
* Implement faster address translation and write tracking on the MMU

* Rename MemoryAlloc to MemoryManagement, and other nits

* Support multi-level page tables

* Fix typo

* Reword comment a bit

* Support scalar vector loads/stores on the memory fast path, and minor fixes

* Add missing cast

* Alignment

* Fix VirtualFree function signature

* Change MemoryProtection enum to uint aswell for consistency
2019-02-24 18:24:35 +11:00
gdkchan
9679896b94
Implement fixed-point variant of the UCVTF and SCVTF instructions (#578)
* Add fixed-point variant of the UCVTF instruction

* Change encoding of some fixed-point instructions to not allow invalid encodings

* Fix Fcvtzu_Gp_Fixed encoding

* Add SCVTF (fixed-point GP to Scalar) instruction

* Simplify *Fixed encodings
2019-02-23 20:52:48 -03:00
gdkchan
932224f051 ARM exclusive monitor and multicore fixes (#589)
* Implement ARM exclusive load/store with compare exchange insts, and enable multicore by default

* Fix comment typo

* Support Linux and OSX on MemoryAlloc and CompareExchange128, some cleanup

* Use intel syntax on assembly code

* Adjust identation

* Add CPUID check and fix exclusive reservation granule size

* Update schema multicore scheduling default value

* Make the cpu id check code lower case aswell
2019-02-19 10:52:06 +11:00
gdkchan
948a758270 Optimize CMN/ADDS to do a single comparision like CMP/SUBS (#576) 2019-02-18 15:17:34 +11:00
gdkchan
a694420d11
Implement speculative translation on the CPU (#515)
* Implement speculative translation on the cpu, and change the way how branches to unknown or untranslated addresses works

* Port t0opt changes and other cleanups

* Change namespace from translation related classes to ChocolArm64.Translation, other minor tweaks

* Fix typo

* Translate higher quality code for indirect jumps aswell, and on some cases that were missed when lower quality (tier 0) code was available

* Remove debug print

* Remove direct argument passing optimization, and enable tail calls for BR instructions

* Call delegates directly with Callvirt rather than calling Execute, do not emit calls for tier 0 code

* Remove unused property

* Rename argument on ArmSubroutine delegate
2019-02-04 18:26:05 -03:00
gdkchan
c1bdf19061
Implement some ARM32 memory instructions and CMP (#565)
* Implement ARM32 memory instructions: LDM, LDR, LDRB, LDRD, LDRH, LDRSB, LDRSH, STM, STR, STRB, STRD, STRH (immediate and register + immediate variants), implement CMP (immediate and register shifted by immediate variants)

* Rename some opcode classes and flag masks for consistency

* Fix a few suboptimal ARM32 codegen issues, only loads should be considered on decoder when checking if Rt == PC, and only NZCV flags should be considered for comparison optimizations

* Take into account Rt2 for LDRD instructions aswell when checking if the instruction changes PC

* Re-align arm32 instructions on the opcode table
2019-01-29 13:06:11 -03:00
LDj3SNuD
8f7fcede7f Add Smlal_Ve, Smlsl_Ve, Smull_Ve, Umlal_Ve, Umlsl_Ve, Umull_Ve Inst.; add Tests. Add Sse Opt. for Trn1/2_V and Uzp1/2_V Inst. Nits. (#566)
* Update OpCodeTable.cs

* Update InstEmitSimdArithmetic.cs

* Update InstEmitSimdHelper.cs

* Update CpuTestSimdRegElem.cs

* Update InstEmitSimdMove.cs

* Update InstEmitSimdCvt.cs

* Update SoftFallback.cs

* Update InstEmitSimdHelper.cs

* Update SoftFloat.cs

* Update CryptoHelper.cs

* Update InstEmitSimdArithmetic.cs

* Update InstEmitSimdCmp.cs

* Address PR feedback.

* Address PR feedback.
2019-01-29 10:54:39 -03:00
gdkchan
36b9ab0e48
Add ARM32 support on the translator (#561)
* Remove ARM32 interpreter and add ARM32 support on the translator

* Nits.

* Rename Cond -> Condition

* Align code again

* Rename Data to Alu

* Enable ARM32 support and handle undefined instructions

* Use the IsThumb method to check if its a thumb opcode

* Remove another 32-bits check
2019-01-24 23:59:53 -02:00
LDj3SNuD
0f5b6dfbe8 Fix Frecpe_S/V and Frsqrte_S/V (full FP emu.). Add Sse Opt. & SoftFloat Impl. for Fcmeq/ge/gt/le/lt_S/V (Reg & Zero), Faddp_S/V, Fmaxp_V, Fminp_V Inst.; add Sse Opt. for Shll_V, S/Ushll_V Inst.; improve Sse Opt. for Xtn_V Inst.. Add Tests. (#543)
* Update Optimizations.cs

* Update InstEmitSimdShift.cs

* Update InstEmitSimdHelper.cs

* Update InstEmitSimdArithmetic.cs

* Update InstEmitSimdMove.cs

* Update SoftFloat.cs

* Update InstEmitSimdCmp.cs

* Update CpuTestSimdShImm.cs

* Update CpuTestSimd.cs

* Update CpuTestSimdReg.cs

* Nit.

* Update SoftFloat.cs

* Update InstEmitSimdArithmetic.cs

* Update InstEmitSimdHelper.cs

* Update CpuTestSimd.cs

* Explicit some implicit casts.

* Simplify some powers; nits.

* Update OpCodeTable.cs

* Update InstEmitSimdArithmetic.cs

* Update CpuTestSimdReg.cs

* Update InstEmitSimdArithmetic.cs
2018-12-26 15:11:36 -02:00
MS-DOS1999
6aaf9ccb53 Add Frintz_S/V opcode and unit test, correction of some unit tests (#523)
* Add Frintz_S/V opcode and unit test, correction of some unit tests

* --test

* fix code style issue

* delete tab
2018-12-17 22:29:47 -02:00
gdkchan
36e8e074c9
Misc. CPU improvements (#519)
* Fix and simplify TranslatorCache

* Fix some assignment alignments, remove some unused usings

* Changes to ILEmitter, separate it from ILEmitterCtx

* Rename ILEmitter to ILMethodBuilder

* Rename LdrLit and *_Fix opcodes

* Revert TranslatorCache impl to the more performant one, fix a few issues with it

* Allow EmitOpCode to be called even after everything has been emitted

* Make Emit and AdvanceOpCode private, simplify it a bit now that it starts emiting from the entry point

* Remove unneeded temp use

* Add missing exit call on TestExclusive

* Use better hash

* Implement the == and != operators
2018-12-10 22:58:52 -02:00
LDj3SNuD
ad00fd0244 Fix Sshl_V; Add S/Uqrshl_V, S/Uqshl_V, S/Urshl_V; Add Tests. (#516)
* Update OpCodeTable.cs

* Update InstEmitSimdShift.cs

* Update SoftFallback.cs

* Update CpuTestSimdReg.cs

* Nit.

* Update SoftFallback.cs

* Update Optimizations.cs

* Update InstEmitSimdLogical.cs

* Update InstEmitSimdArithmetic.cs
2018-12-01 22:34:43 -02:00
LDj3SNuD
e603b7afbc Add Sse Opt. for S/Umax_V, S/Umin_V, S/Uaddw_V, S/Usubw_V, Fabs_S/V, Fneg_S/V Inst.; for Fcvtl_V, Fcvtn_V Inst.; and for Fcmp_S Inst.. Add/Improve other Sse Opt.. Add Tests. (#496)
* Update CpuTest.cs

* Update CpuTestSimd.cs

* Update CpuTestSimdReg.cs

* Update InstEmitSimdCmp.cs

* Update SoftFloat.cs

* Update InstEmitAluHelper.cs

* Update InstEmitSimdArithmetic.cs

* Update InstEmitSimdHelper.cs

* Update VectorHelper.cs

* Update InstEmitSimdCvt.cs

* Update InstEmitSimdArithmetic.cs

* Update CpuTestSimd.cs

* Update InstEmitSimdArithmetic.cs

* Update OpCodeTable.cs

* Update InstEmitSimdArithmetic.cs

* Update InstEmitSimdCmp.cs

* Update InstEmitSimdCvt.cs

* Update CpuTestSimd.cs

* Update CpuTestSimdReg.cs

* Create CpuTestSimdFcond.cs

* Update OpCodeTable.cs

* Update InstEmitSimdMove.cs

* Update CpuTestSimdIns.cs

* Create CpuTestSimdExt.cs

* Nit.

* Update PackageReference.
2018-11-18 00:41:16 -02:00
gdkchan
a4822b7946
Fix BLR when the source reg is X30 (#493) 2018-11-09 16:41:20 -02:00
LDj3SNuD
1e7ea76f14 Add Flush-to-zero mode (input, output) to FP instructions (slow paths); update FP Tests. Update Naming Conventions for Tests project. (#489)
* Update SoftFloat.cs

* Update SoftFallback.cs

* Update InstEmitSimdShift.cs

* Update InstEmitSimdCvt.cs

* Update InstEmitSimdArithmetic.cs

* Update CryptoHelper.cs

* Update CpuTestSimd.cs

* Update CpuTestSimdReg.cs

* Update CpuThreadState.cs

* Update OpCodeTable.cs

* Add files via upload

* Nit.

* Remove unused using. Nit.

* Remove unused using. FZ update.

* Nit.

* Remove unused using.
2018-11-01 01:22:09 -03:00
Alex Barney
9cb57fb4bb Adjust naming conventions for Ryujinx and ChocolArm64 projects (#484)
* Change naming convention for Ryujinx project

* Change naming convention for ChocolArm64 project

* Fix NaN

* Remove unneeded this. from Ryujinx project

* Adjust naming from new PRs

* Name changes based on feedback

* How did this get removed?

* Rebasing fix

* Change FP enum case

* Remove prefix from ChocolArm64 classes - Part 1

* Remove prefix from ChocolArm64 classes - Part 2

* Fix alignment from last commit's renaming

* Rename namespaces

* Rename stragglers

* Fix alignment

* Rename OpCode class

* Missed a few

* Adjust alignment
2018-10-30 22:43:02 -03:00