1
0
Fork 0
mirror of https://github.com/Ryujinx/Ryujinx.git synced 2024-11-30 20:02:02 +00:00
Ryujinx/ARMeilleure/Instructions/InstEmitMemoryEx32.cs

241 lines
8.7 KiB
C#
Raw Normal View History

Add most of the A32 instruction set to ARMeilleure (#897) * Implement TEQ and MOV (Imm16) * Initial work on A32 instructions + SVC. No tests yet, hangs in rtld. * Implement CLZ, fix BFI and BFC Now stops on SIMD initialization. * Exclusive access instructions, fix to mul, system instructions. Now gets to a break after SignalProcessWideKey64. * Better impl of UBFX, add UDIV and SDIV Now boots way further - now stuck on VMOV instruction. * Many more instructions, start on SIMD and testing framework. * Fix build issues * svc: Rework 32 bit codepath Fixing once and for all argument ordering issues. * Fix 32 bits stacktrace * hle debug: Add 32 bits dynamic section parsing * Fix highCq mode, add many tests, fix some instruction bugs Still suffers from critical malloc failure :weary: * Fix incorrect opcode decoders and a few more instructions. * Add a few instructions and fix others. re-disable highCq for now. Disabled the svc memory clear since i'm not sure about it. * Fix build * Fix typo in ordered/exclusive stores. * Implement some more instructions, fix others. Uxtab16/Sxtab16 are untested. * Begin impl of pairwise, some other instructions. * Add a few more instructions, a quick hack to fix svcs for now. * Add tests and fix issues with VTRN, VZIP, VUZP * Add a few more instructions, fix Vmul_1 encoding. * Fix way too many instruction bugs, add tests for some of the more important ones. * Fix HighCq, enable FastFP paths for some floating point instructions (not entirely sure why these were disabled, so important to note this commit exists) Branching has been removed in A32 shifts until I figure out if it's worth it * Cleanup Part 1 There should be no functional change between these next few commits. Should is the key word. (except for removing break handler) * Implement 32 bits syscalls Co-authored-by: riperiperi <rhy3756547@hotmail.com> Implement all 32 bits counterparts of the 64 bits syscalls we currently have. * Refactor part 2: Move index/subindex logic to Operand May have inadvertently fixed one (1) bug * Add FlushProcessDataCache32 * Address jd's comments * Remove 16 bit encodings from OpCodeTable Still need to catch some edge cases (operands that use the "F" flag) and make Q encodings with non-even indexes undefined. * Correct Fpscr handling for FP vector slow paths WIP * Add StandardFPSCRValue behaviour for all Arithmetic instructions * Add StandardFPSCRValue behaviour to compare instructions. * Force passing of fpcr to FPProcessException and FPUnpack. Reduces potential for code error significantly * OpCode cleanup * Remove urgency from DMB comment in MRRC DMB is currently a no-op via the instruction, so it should likely still be a no-op here. * Test Cleanup * Fix FPDefaultNaN on Ryzen CPUs * Improve some tests, fix some shift instructions, add slow path for Vadd * Fix Typo * More test cleanup * Flip order of Fx and index, to indicate that the operand's is the "base" * Remove Simd32 register type, use Int32 and Int64 for scalars like A64 does. * Reintroduce alignment to DecoderHelper (removed by accident) * One more realign as reading diffs is hard * Use I32 registers in A32 (part 2) Swap default integer register type based on current execution mode. * FPSCR flags as Registers (part 1) Still need to change NativeContext and ExecutionContext to allow getting/setting with the flag values. * Use I32 registers in A32 (part 1) * FPSCR flags as registers (part 2) Only CMP flags are on the registers right now. It could be useful to use more of the space in non-fast-float when implementing A32 flags accurately in the fast path. * Address Feedback * Correct FP->Int behaviour (should saturate) * Make branches made by writing to PC eligible for Rejit Greatly improves performance in most games. * Remove unused branching for Vtbl * RejitRequest as a class rather than a tuple Makes a lot more sense than storing tuples on a dictionary. * Add VMOVN, VSHR (imm), VSHRN (imm) and related tests * Re-order InstEmitSystem32 Alphabetical sorting. * Address Feedback Feedback from Ac_K, remove and sort usings. * Address Feedback 2 * Address Feedback from LDj3SNuD Opcode table reordered to have alphabetical sorting within groups, Vmaxnm and Vminnm have split names to be less ambiguous, SoftFloat nits, Test nits and Test simplification with ValueSource. * Add Debug Asserts to A32 helpers Mainly to prevent the shift ones from being used on I64 operands, as they expect I32 input for most operations (eg. carry flag setting), and expect I32 input for shift and boolean amounts. Most other helper functions don't take Operands, throw on out of range values, and take specific types of OpCode, so didn't need any asserts. * Use ConstF rather than creating an operand. (useful for pooling in future) * Move exclusive load to helper, reference call flag rather than literal 1. * Address LDj feedback (minus table flatten) one final look before it's all gone. the world is so beautiful. * Flatten OpCodeTable oh no * Address more table ordering * Call Flag as int on A32 Co-authored-by: Natalie C. <cyuubiapps@gmail.com> Co-authored-by: Thog <thog@protonmail.com>
2020-02-23 21:20:40 +00:00
using ARMeilleure.Decoders;
using ARMeilleure.IntermediateRepresentation;
using ARMeilleure.State;
using ARMeilleure.Translation;
using static ARMeilleure.Instructions.InstEmitHelper;
using static ARMeilleure.Instructions.InstEmitMemoryExHelper;
using static ARMeilleure.IntermediateRepresentation.OperandHelper;
namespace ARMeilleure.Instructions
{
static partial class InstEmit32
{
public static void Clrex(ArmEmitterContext context)
{
Add Profiled Persistent Translation Cache. (#769) * Delete DelegateTypes.cs * Delete DelegateCache.cs * Add files via upload * Update Horizon.cs * Update Program.cs * Update MainWindow.cs * Update Aot.cs * Update RelocEntry.cs * Update Translator.cs * Update MemoryManager.cs * Update InstEmitMemoryHelper.cs * Update Delegates.cs * Nit. * Nit. * Nit. * 10 fewer MSIL bytes for us * Add comment. Nits. * Update Translator.cs * Update Aot.cs * Nits. * Opt.. * Opt.. * Opt.. * Opt.. * Allow to change compression level. * Update MemoryManager.cs * Update Translator.cs * Manage corner cases during the save phase. Nits. * Update Aot.cs * Translator response tweak for Aot disabled. Nit. * Nit. * Nits. * Create DelegateHelpers.cs * Update Delegates.cs * Nit. * Nit. * Nits. * Fix due to #784. * Fixes due to #757 & #841. * Fix due to #846. * Fix due to #847. * Use MethodInfo for managed method calls. Use IR methods instead of managed methods about Max/Min (S/U). Follow-ups & Nits. * Add missing exception messages. Reintroduce slow path for Fmov_Vi. Implement slow path for Fmov_Si. * Switch to the new folder structure. Nits. * Impl. index-based relocation information. Impl. cache file version field. * Nit. * Address gdkchan comments. Mainly: - fixed cache file corruption issue on exit; - exposed a way to disable AOT on the GUI. * Address AcK77 comment. * Address Thealexbarney, jduncanator & emmauss comments. Header magic, CpuId (FI) & Aot -> Ptc. * Adaptation to the new application reloading system. Improvements to the call system of managed methods. Follow-ups. Nits. * Get the same boot times as on master when PTC is disabled. * Profiled Aot. * A32 support (#897). * #975 support (1 of 2). * #975 support (2 of 2). * Rebase fix & nits. * Some fixes and nits (still one bug left). * One fix & nits. * Tests fix (by gdk) & nits. * Support translations not only in high quality and rejit. Nits. * Added possibility to skip translations and continue execution, using `ESC` key. * Update SettingsWindow.cs * Update GLRenderer.cs * Update Ptc.cs * Disabled Profiled PTC by default as requested in the past by gdk. * Fix rejit bug. Increased number of parallel translations. Add stack unwinding stuffs support (1 of 2). Nits. * Add stack unwinding stuffs support (2 of 2). Tuned number of parallel translations. * Restored the ability to assemble jumps with 8-bit offset when Profiled PTC is disabled or during profiling. Modifications due to rebase. Nits. * Limited profiling of the functions to be translated to the addresses belonging to the range of static objects only. * Nits. * Nits. * Update Delegates.cs * Nit. * Update InstEmitSimdArithmetic.cs * Address riperiperi comments. * Fixed the issue of unjustifiably longer boot times at the second boot than at the first boot, measured at the same time or reference point and with the same number of translated functions. * Implemented a simple redundant load/save mechanism. Halved the value of Decoder.MaxInstsPerFunction more appropriate for the current performance of the Translator. Replaced by Logger.PrintError to Logger.PrintDebug in TexturePool.cs about the supposed invalid texture format to avoid the spawn of the log. Nits. * Nit. Improved Logger.PrintError in TexturePool.cs to avoid log spawn. Added missing code for FZ handling (in output) for fp max/min instructions (slow paths). * Add configuration migration for PTC Co-authored-by: Thog <me@thog.eu>
2020-06-16 19:28:02 +01:00
context.Call(typeof(NativeInterface).GetMethod(nameof(NativeInterface.ClearExclusive)));
Add most of the A32 instruction set to ARMeilleure (#897) * Implement TEQ and MOV (Imm16) * Initial work on A32 instructions + SVC. No tests yet, hangs in rtld. * Implement CLZ, fix BFI and BFC Now stops on SIMD initialization. * Exclusive access instructions, fix to mul, system instructions. Now gets to a break after SignalProcessWideKey64. * Better impl of UBFX, add UDIV and SDIV Now boots way further - now stuck on VMOV instruction. * Many more instructions, start on SIMD and testing framework. * Fix build issues * svc: Rework 32 bit codepath Fixing once and for all argument ordering issues. * Fix 32 bits stacktrace * hle debug: Add 32 bits dynamic section parsing * Fix highCq mode, add many tests, fix some instruction bugs Still suffers from critical malloc failure :weary: * Fix incorrect opcode decoders and a few more instructions. * Add a few instructions and fix others. re-disable highCq for now. Disabled the svc memory clear since i'm not sure about it. * Fix build * Fix typo in ordered/exclusive stores. * Implement some more instructions, fix others. Uxtab16/Sxtab16 are untested. * Begin impl of pairwise, some other instructions. * Add a few more instructions, a quick hack to fix svcs for now. * Add tests and fix issues with VTRN, VZIP, VUZP * Add a few more instructions, fix Vmul_1 encoding. * Fix way too many instruction bugs, add tests for some of the more important ones. * Fix HighCq, enable FastFP paths for some floating point instructions (not entirely sure why these were disabled, so important to note this commit exists) Branching has been removed in A32 shifts until I figure out if it's worth it * Cleanup Part 1 There should be no functional change between these next few commits. Should is the key word. (except for removing break handler) * Implement 32 bits syscalls Co-authored-by: riperiperi <rhy3756547@hotmail.com> Implement all 32 bits counterparts of the 64 bits syscalls we currently have. * Refactor part 2: Move index/subindex logic to Operand May have inadvertently fixed one (1) bug * Add FlushProcessDataCache32 * Address jd's comments * Remove 16 bit encodings from OpCodeTable Still need to catch some edge cases (operands that use the "F" flag) and make Q encodings with non-even indexes undefined. * Correct Fpscr handling for FP vector slow paths WIP * Add StandardFPSCRValue behaviour for all Arithmetic instructions * Add StandardFPSCRValue behaviour to compare instructions. * Force passing of fpcr to FPProcessException and FPUnpack. Reduces potential for code error significantly * OpCode cleanup * Remove urgency from DMB comment in MRRC DMB is currently a no-op via the instruction, so it should likely still be a no-op here. * Test Cleanup * Fix FPDefaultNaN on Ryzen CPUs * Improve some tests, fix some shift instructions, add slow path for Vadd * Fix Typo * More test cleanup * Flip order of Fx and index, to indicate that the operand's is the "base" * Remove Simd32 register type, use Int32 and Int64 for scalars like A64 does. * Reintroduce alignment to DecoderHelper (removed by accident) * One more realign as reading diffs is hard * Use I32 registers in A32 (part 2) Swap default integer register type based on current execution mode. * FPSCR flags as Registers (part 1) Still need to change NativeContext and ExecutionContext to allow getting/setting with the flag values. * Use I32 registers in A32 (part 1) * FPSCR flags as registers (part 2) Only CMP flags are on the registers right now. It could be useful to use more of the space in non-fast-float when implementing A32 flags accurately in the fast path. * Address Feedback * Correct FP->Int behaviour (should saturate) * Make branches made by writing to PC eligible for Rejit Greatly improves performance in most games. * Remove unused branching for Vtbl * RejitRequest as a class rather than a tuple Makes a lot more sense than storing tuples on a dictionary. * Add VMOVN, VSHR (imm), VSHRN (imm) and related tests * Re-order InstEmitSystem32 Alphabetical sorting. * Address Feedback Feedback from Ac_K, remove and sort usings. * Address Feedback 2 * Address Feedback from LDj3SNuD Opcode table reordered to have alphabetical sorting within groups, Vmaxnm and Vminnm have split names to be less ambiguous, SoftFloat nits, Test nits and Test simplification with ValueSource. * Add Debug Asserts to A32 helpers Mainly to prevent the shift ones from being used on I64 operands, as they expect I32 input for most operations (eg. carry flag setting), and expect I32 input for shift and boolean amounts. Most other helper functions don't take Operands, throw on out of range values, and take specific types of OpCode, so didn't need any asserts. * Use ConstF rather than creating an operand. (useful for pooling in future) * Move exclusive load to helper, reference call flag rather than literal 1. * Address LDj feedback (minus table flatten) one final look before it's all gone. the world is so beautiful. * Flatten OpCodeTable oh no * Address more table ordering * Call Flag as int on A32 Co-authored-by: Natalie C. <cyuubiapps@gmail.com> Co-authored-by: Thog <thog@protonmail.com>
2020-02-23 21:20:40 +00:00
}
public static void Dmb(ArmEmitterContext context) => EmitBarrier(context);
public static void Dsb(ArmEmitterContext context) => EmitBarrier(context);
public static void Ldrex(ArmEmitterContext context)
{
EmitExLoadOrStore(context, WordSizeLog2, AccessType.LoadZx | AccessType.Exclusive);
}
public static void Ldrexb(ArmEmitterContext context)
{
EmitExLoadOrStore(context, ByteSizeLog2, AccessType.LoadZx | AccessType.Exclusive);
}
public static void Ldrexd(ArmEmitterContext context)
{
EmitExLoadOrStore(context, DWordSizeLog2, AccessType.LoadZx | AccessType.Exclusive);
}
public static void Ldrexh(ArmEmitterContext context)
{
EmitExLoadOrStore(context, HWordSizeLog2, AccessType.LoadZx | AccessType.Exclusive);
}
public static void Lda(ArmEmitterContext context)
{
EmitExLoadOrStore(context, WordSizeLog2, AccessType.LoadZx | AccessType.Ordered);
}
public static void Ldab(ArmEmitterContext context)
{
EmitExLoadOrStore(context, ByteSizeLog2, AccessType.LoadZx | AccessType.Ordered);
}
public static void Ldaex(ArmEmitterContext context)
{
EmitExLoadOrStore(context, WordSizeLog2, AccessType.LoadZx | AccessType.Exclusive | AccessType.Ordered);
}
public static void Ldaexb(ArmEmitterContext context)
{
EmitExLoadOrStore(context, ByteSizeLog2, AccessType.LoadZx | AccessType.Exclusive | AccessType.Ordered);
}
public static void Ldaexd(ArmEmitterContext context)
{
EmitExLoadOrStore(context, DWordSizeLog2, AccessType.LoadZx | AccessType.Exclusive | AccessType.Ordered);
}
public static void Ldaexh(ArmEmitterContext context)
{
EmitExLoadOrStore(context, HWordSizeLog2, AccessType.LoadZx | AccessType.Exclusive | AccessType.Ordered);
}
public static void Ldah(ArmEmitterContext context)
{
EmitExLoadOrStore(context, HWordSizeLog2, AccessType.LoadZx | AccessType.Ordered);
}
// Stores.
public static void Strex(ArmEmitterContext context)
{
EmitExLoadOrStore(context, WordSizeLog2, AccessType.Store | AccessType.Exclusive);
}
public static void Strexb(ArmEmitterContext context)
{
EmitExLoadOrStore(context, ByteSizeLog2, AccessType.Store | AccessType.Exclusive);
}
public static void Strexd(ArmEmitterContext context)
{
EmitExLoadOrStore(context, DWordSizeLog2, AccessType.Store | AccessType.Exclusive);
}
public static void Strexh(ArmEmitterContext context)
{
EmitExLoadOrStore(context, HWordSizeLog2, AccessType.Store | AccessType.Exclusive);
}
public static void Stl(ArmEmitterContext context)
{
EmitExLoadOrStore(context, WordSizeLog2, AccessType.Store | AccessType.Ordered);
}
public static void Stlb(ArmEmitterContext context)
{
EmitExLoadOrStore(context, ByteSizeLog2, AccessType.Store | AccessType.Ordered);
}
public static void Stlex(ArmEmitterContext context)
{
EmitExLoadOrStore(context, WordSizeLog2, AccessType.Store | AccessType.Exclusive | AccessType.Ordered);
}
public static void Stlexb(ArmEmitterContext context)
{
EmitExLoadOrStore(context, ByteSizeLog2, AccessType.Store | AccessType.Exclusive | AccessType.Ordered);
}
public static void Stlexd(ArmEmitterContext context)
{
EmitExLoadOrStore(context, DWordSizeLog2, AccessType.Store | AccessType.Exclusive | AccessType.Ordered);
}
public static void Stlexh(ArmEmitterContext context)
{
EmitExLoadOrStore(context, HWordSizeLog2, AccessType.Store | AccessType.Exclusive | AccessType.Ordered);
}
public static void Stlh(ArmEmitterContext context)
{
EmitExLoadOrStore(context, HWordSizeLog2, AccessType.Store | AccessType.Ordered);
}
private static void EmitExLoadOrStore(ArmEmitterContext context, int size, AccessType accType)
{
IOpCode32MemEx op = (IOpCode32MemEx)context.CurrOp;
Operand address = context.Copy(GetIntA32(context, op.Rn));
var exclusive = (accType & AccessType.Exclusive) != 0;
var ordered = (accType & AccessType.Ordered) != 0;
if (ordered)
{
EmitBarrier(context);
}
if ((accType & AccessType.Load) != 0)
{
if (size == DWordSizeLog2)
{
// Keep loads atomic - make the call to get the whole region and then decompose it into parts
// for the registers.
Operand value = EmitLoadExclusive(context, address, exclusive, size);
Operand valueLow = context.ConvertI64ToI32(value);
valueLow = context.ZeroExtend32(OperandType.I64, valueLow);
Operand valueHigh = context.ShiftRightUI(value, Const(32));
Operand lblBigEndian = Label();
Operand lblEnd = Label();
context.BranchIfTrue(lblBigEndian, GetFlag(PState.EFlag));
SetIntA32(context, op.Rt, valueLow);
SetIntA32(context, op.Rt | 1, valueHigh);
context.Branch(lblEnd);
context.MarkLabel(lblBigEndian);
SetIntA32(context, op.Rt | 1, valueLow);
SetIntA32(context, op.Rt, valueHigh);
context.MarkLabel(lblEnd);
}
else
{
SetIntA32(context, op.Rt, EmitLoadExclusive(context, address, exclusive, size));
}
}
else
{
if (size == DWordSizeLog2)
{
// Split the result into 2 words (based on endianness)
Operand lo = context.ZeroExtend32(OperandType.I64, GetIntA32(context, op.Rt));
Operand hi = context.ZeroExtend32(OperandType.I64, GetIntA32(context, op.Rt | 1));
Operand lblBigEndian = Label();
Operand lblEnd = Label();
context.BranchIfTrue(lblBigEndian, GetFlag(PState.EFlag));
Operand leResult = context.BitwiseOr(lo, context.ShiftLeft(hi, Const(32)));
Operand leS = EmitStoreExclusive(context, address, leResult, exclusive, size);
if (exclusive)
{
SetIntA32(context, op.Rd, leS);
}
context.Branch(lblEnd);
context.MarkLabel(lblBigEndian);
Operand beResult = context.BitwiseOr(hi, context.ShiftLeft(lo, Const(32)));
Operand beS = EmitStoreExclusive(context, address, beResult, exclusive, size);
if (exclusive)
{
SetIntA32(context, op.Rd, beS);
}
context.MarkLabel(lblEnd);
}
else
{
Operand s = EmitStoreExclusive(context, address, context.ZeroExtend32(OperandType.I64, GetIntA32(context, op.Rt)), exclusive, size);
// This is only needed for exclusive stores. The function returns 0
// when the store is successful, and 1 otherwise.
if (exclusive)
{
SetIntA32(context, op.Rd, s);
}
}
}
}
private static void EmitBarrier(ArmEmitterContext context)
{
// Note: This barrier is most likely not necessary, and probably
// doesn't make any difference since we need to do a ton of stuff
// (software MMU emulation) to read or write anything anyway.
}
}
}