0
0
Fork 0
This repository has been archived on 2024-10-12. You can view files and clone it, but cannot push or open issues or pull requests.
ryujinx-final/ARMeilleure/Instructions/InstEmitMul.cs

100 lines
3.1 KiB
C#
Raw Normal View History

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 18:56:22 +00:00
using ARMeilleure.Decoders;
using ARMeilleure.IntermediateRepresentation;
using ARMeilleure.Translation;
using System;
using static ARMeilleure.Instructions.InstEmitHelper;
namespace ARMeilleure.Instructions
{
static partial class InstEmit
{
public static void Madd(ArmEmitterContext context) => EmitMul(context, isAdd: true);
public static void Msub(ArmEmitterContext context) => EmitMul(context, isAdd: false);
private static void EmitMul(ArmEmitterContext context, bool isAdd)
{
OpCodeMul op = (OpCodeMul)context.CurrOp;
Operand a = GetIntOrZR(context, op.Ra);
Operand n = GetIntOrZR(context, op.Rn);
Operand m = GetIntOrZR(context, op.Rm);
Operand res = context.Multiply(n, m);
res = isAdd ? context.Add(a, res) : context.Subtract(a, res);
SetIntOrZR(context, op.Rd, res);
}
public static void Smaddl(ArmEmitterContext context) => EmitMull(context, MullFlags.SignedAdd);
public static void Smsubl(ArmEmitterContext context) => EmitMull(context, MullFlags.SignedSubtract);
public static void Umaddl(ArmEmitterContext context) => EmitMull(context, MullFlags.Add);
public static void Umsubl(ArmEmitterContext context) => EmitMull(context, MullFlags.Subtract);
[Flags]
private enum MullFlags
{
Subtract = 0,
Add = 1 << 0,
Signed = 1 << 1,
SignedAdd = Signed | Add,
SignedSubtract = Signed | Subtract
}
private static void EmitMull(ArmEmitterContext context, MullFlags flags)
{
OpCodeMul op = (OpCodeMul)context.CurrOp;
Operand GetExtendedRegister32(int index)
{
Operand value = GetIntOrZR(context, index);
if ((flags & MullFlags.Signed) != 0)
{
return context.SignExtend32(value.Type, value);
}
else
{
return context.ZeroExtend32(value.Type, value);
}
}
Operand a = GetIntOrZR(context, op.Ra);
Operand n = GetExtendedRegister32(op.Rn);
Operand m = GetExtendedRegister32(op.Rm);
Operand res = context.Multiply(n, m);
res = (flags & MullFlags.Add) != 0 ? context.Add(a, res) : context.Subtract(a, res);
SetIntOrZR(context, op.Rd, res);
}
public static void Smulh(ArmEmitterContext context)
{
OpCodeMul op = (OpCodeMul)context.CurrOp;
Operand n = GetIntOrZR(context, op.Rn);
Operand m = GetIntOrZR(context, op.Rm);
Operand d = context.Multiply64HighSI(n, m);
SetIntOrZR(context, op.Rd, d);
}
public static void Umulh(ArmEmitterContext context)
{
OpCodeMul op = (OpCodeMul)context.CurrOp;
Operand n = GetIntOrZR(context, op.Rn);
Operand m = GetIntOrZR(context, op.Rm);
Operand d = context.Multiply64HighUI(n, m);
SetIntOrZR(context, op.Rd, d);
}
}
}