Ryujinx-uplift/ARMeilleure/Instructions/InstEmitSimdMemory.cs
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

160 lines
4.5 KiB
C#

using ARMeilleure.Decoders;
using ARMeilleure.IntermediateRepresentation;
using ARMeilleure.State;
using ARMeilleure.Translation;
using System.Diagnostics;
using static ARMeilleure.Instructions.InstEmitHelper;
using static ARMeilleure.Instructions.InstEmitMemoryHelper;
using static ARMeilleure.IntermediateRepresentation.OperandHelper;
namespace ARMeilleure.Instructions
{
static partial class InstEmit
{
public static void Ld__Vms(ArmEmitterContext context)
{
EmitSimdMemMs(context, isLoad: true);
}
public static void Ld__Vss(ArmEmitterContext context)
{
EmitSimdMemSs(context, isLoad: true);
}
public static void St__Vms(ArmEmitterContext context)
{
EmitSimdMemMs(context, isLoad: false);
}
public static void St__Vss(ArmEmitterContext context)
{
EmitSimdMemSs(context, isLoad: false);
}
private static void EmitSimdMemMs(ArmEmitterContext context, bool isLoad)
{
OpCodeSimdMemMs op = (OpCodeSimdMemMs)context.CurrOp;
Operand n = GetIntOrSP(context, op.Rn);
long offset = 0;
for (int rep = 0; rep < op.Reps; rep++)
for (int elem = 0; elem < op.Elems; elem++)
for (int sElem = 0; sElem < op.SElems; sElem++)
{
int rtt = (op.Rt + rep + sElem) & 0x1f;
Operand tt = GetVec(rtt);
Operand address = context.Add(n, Const(offset));
if (isLoad)
{
EmitLoadSimd(context, address, tt, rtt, elem, op.Size);
if (op.RegisterSize == RegisterSize.Simd64 && elem == op.Elems - 1)
{
context.Copy(tt, context.VectorZeroUpper64(tt));
}
}
else
{
EmitStoreSimd(context, address, rtt, elem, op.Size);
}
offset += 1 << op.Size;
}
if (op.WBack)
{
EmitSimdMemWBack(context, offset);
}
}
private static void EmitSimdMemSs(ArmEmitterContext context, bool isLoad)
{
OpCodeSimdMemSs op = (OpCodeSimdMemSs)context.CurrOp;
Operand n = GetIntOrSP(context, op.Rn);
long offset = 0;
if (op.Replicate)
{
// Only loads uses the replicate mode.
Debug.Assert(isLoad, "Replicate mode is not valid for stores.");
int elems = op.GetBytesCount() >> op.Size;
for (int sElem = 0; sElem < op.SElems; sElem++)
{
int rt = (op.Rt + sElem) & 0x1f;
Operand t = GetVec(rt);
Operand address = context.Add(n, Const(offset));
for (int index = 0; index < elems; index++)
{
EmitLoadSimd(context, address, t, rt, index, op.Size);
}
if (op.RegisterSize == RegisterSize.Simd64)
{
context.Copy(t, context.VectorZeroUpper64(t));
}
offset += 1 << op.Size;
}
}
else
{
for (int sElem = 0; sElem < op.SElems; sElem++)
{
int rt = (op.Rt + sElem) & 0x1f;
Operand t = GetVec(rt);
Operand address = context.Add(n, Const(offset));
if (isLoad)
{
EmitLoadSimd(context, address, t, rt, op.Index, op.Size);
}
else
{
EmitStoreSimd(context, address, rt, op.Index, op.Size);
}
offset += 1 << op.Size;
}
}
if (op.WBack)
{
EmitSimdMemWBack(context, offset);
}
}
private static void EmitSimdMemWBack(ArmEmitterContext context, long offset)
{
OpCodeMemReg op = (OpCodeMemReg)context.CurrOp;
Operand n = GetIntOrSP(context, op.Rn);
Operand m;
if (op.Rm != RegisterAlias.Zr)
{
m = GetIntOrZR(context, op.Rm);
}
else
{
m = Const(offset);
}
context.Copy(n, context.Add(n, m));
}
}
}