drashna/ryujinx
1
0
Fork 0
Code Activity Actions

Add a new JIT compiler for CPU code (#693)

Browse source 
* 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
This commit is contained in:
gdkchan 2019-08-08 15:56:22 -03:00 • committed by emmauss
parent 1ba58e9942
commit a731ab3a2a
310 changed files with 37389 additions and 2086 deletions
Download patch file Download diff file Expand all files Collapse all files

82
Ryujinx.Tests/Cpu/CpuTestSimdIns.cs
View file

@ -1,8 +1,8 @@
#define SimdIns
using NUnit.Framework;
using ARMeilleure.State;
using System.Runtime.Intrinsics;
using NUnit.Framework;
namespace Ryujinx.Tests.Cpu
{
@ -86,7 +86,7 @@ namespace Ryujinx.Tests.Cpu
uint w31 = TestContext.CurrentContext.Random.NextUInt();
ulong z = TestContext.CurrentContext.Random.NextULong();
Vector128<float> v0 = MakeVectorE0E1(z, z);
V128 v0 = MakeVectorE0E1(z, z);
SingleOpcode(opcode, x1: wn, x31: w31, v0: v0);
@ -103,7 +103,7 @@ namespace Ryujinx.Tests.Cpu
ulong x31 = TestContext.CurrentContext.Random.NextULong();
ulong z = TestContext.CurrentContext.Random.NextULong();
Vector128<float> v0 = MakeVectorE0E1(z, z);
V128 v0 = MakeVectorE0E1(z, z);
SingleOpcode(opcode, x1: xn, x31: x31, v0: v0);
@ -122,8 +122,8 @@ namespace Ryujinx.Tests.Cpu
opcode |= (imm5 << 16);
ulong z = TestContext.CurrentContext.Random.NextULong();
Vector128<float> v0 = MakeVectorE0E1(z, z);
Vector128<float> v1 = MakeVectorE0E1(a, a);
V128 v0 = MakeVectorE0E1(z, z);
V128 v1 = MakeVectorE0E1(a, a);
SingleOpcode(opcode, v0: v0, v1: v1);
@ -142,8 +142,8 @@ namespace Ryujinx.Tests.Cpu
opcode |= (imm5 << 16);
ulong z = TestContext.CurrentContext.Random.NextULong();
Vector128<float> v0 = MakeVectorE0E1(z, z);
Vector128<float> v1 = MakeVectorE0E1(a, a);
V128 v0 = MakeVectorE0E1(z, z);
V128 v1 = MakeVectorE0E1(a, a);
SingleOpcode(opcode, v0: v0, v1: v1);
@ -162,8 +162,8 @@ namespace Ryujinx.Tests.Cpu
opcode |= (imm5 << 16);
ulong z = TestContext.CurrentContext.Random.NextULong();
Vector128<float> v0 = MakeVectorE0E1(z, z);
Vector128<float> v1 = MakeVectorE0E1(a, a);
V128 v0 = MakeVectorE0E1(z, z);
V128 v1 = MakeVectorE0E1(a, a);
SingleOpcode(opcode, v0: v0, v1: v1);
@ -182,8 +182,8 @@ namespace Ryujinx.Tests.Cpu
opcode |= (imm5 << 16);
ulong z = TestContext.CurrentContext.Random.NextULong();
Vector128<float> v0 = MakeVectorE0E1(z, z);
Vector128<float> v1 = MakeVectorE0E1(a, a);
V128 v0 = MakeVectorE0E1(z, z);
V128 v1 = MakeVectorE0E1(a, a);
SingleOpcode(opcode, v0: v0, v1: v1);
@ -207,8 +207,8 @@ namespace Ryujinx.Tests.Cpu
opcode |= (imm5 << 16);
opcode |= ((q & 1) << 30);
Vector128<float> v0 = MakeVectorE0E1(z, z);
Vector128<float> v1 = MakeVectorE0E1(a, a);
V128 v0 = MakeVectorE0E1(z, z);
V128 v1 = MakeVectorE0E1(a, a);
SingleOpcode(opcode, v0: v0, v1: v1);
@ -232,8 +232,8 @@ namespace Ryujinx.Tests.Cpu
opcode |= (imm5 << 16);
opcode |= ((q & 1) << 30);
Vector128<float> v0 = MakeVectorE0E1(z, z);
Vector128<float> v1 = MakeVectorE0E1(a, a);
V128 v0 = MakeVectorE0E1(z, z);
V128 v1 = MakeVectorE0E1(a, a);
SingleOpcode(opcode, v0: v0, v1: v1);
@ -257,8 +257,8 @@ namespace Ryujinx.Tests.Cpu
opcode |= (imm5 << 16);
opcode |= ((q & 1) << 30);
Vector128<float> v0 = MakeVectorE0E1(z, z);
Vector128<float> v1 = MakeVectorE0E1(a, a);
V128 v0 = MakeVectorE0E1(z, z);
V128 v1 = MakeVectorE0E1(a, a);
SingleOpcode(opcode, v0: v0, v1: v1);
@ -282,8 +282,8 @@ namespace Ryujinx.Tests.Cpu
opcode |= (imm5 << 16);
opcode |= ((q & 1) << 30);
Vector128<float> v0 = MakeVectorE0E1(z, z);
Vector128<float> v1 = MakeVectorE0E1(a, a);
V128 v0 = MakeVectorE0E1(z, z);
V128 v1 = MakeVectorE0E1(a, a);
SingleOpcode(opcode, v0: v0, v1: v1);
@ -306,7 +306,7 @@ namespace Ryujinx.Tests.Cpu
opcode |= (imm5 << 16);
uint w31 = TestContext.CurrentContext.Random.NextUInt();
Vector128<float> v0 = MakeVectorE0E1(z, z);
V128 v0 = MakeVectorE0E1(z, z);
SingleOpcode(opcode, x1: wn, x31: w31, v0: v0);
@ -329,7 +329,7 @@ namespace Ryujinx.Tests.Cpu
opcode |= (imm5 << 16);
uint w31 = TestContext.CurrentContext.Random.NextUInt();
Vector128<float> v0 = MakeVectorE0E1(z, z);
V128 v0 = MakeVectorE0E1(z, z);
SingleOpcode(opcode, x1: wn, x31: w31, v0: v0);
@ -352,7 +352,7 @@ namespace Ryujinx.Tests.Cpu
opcode |= (imm5 << 16);
uint w31 = TestContext.CurrentContext.Random.NextUInt();
Vector128<float> v0 = MakeVectorE0E1(z, z);
V128 v0 = MakeVectorE0E1(z, z);
SingleOpcode(opcode, x1: wn, x31: w31, v0: v0);
@ -375,7 +375,7 @@ namespace Ryujinx.Tests.Cpu
opcode |= (imm5 << 16);
ulong x31 = TestContext.CurrentContext.Random.NextULong();
Vector128<float> v0 = MakeVectorE0E1(z, z);
V128 v0 = MakeVectorE0E1(z, z);
SingleOpcode(opcode, x1: xn, x31: x31, v0: v0);
@ -400,8 +400,8 @@ namespace Ryujinx.Tests.Cpu
opcode |= (imm5 << 16);
opcode |= (imm4 << 11);
Vector128<float> v0 = MakeVectorE0E1(z, z);
Vector128<float> v1 = MakeVectorE0E1(a, a);
V128 v0 = MakeVectorE0E1(z, z);
V128 v1 = MakeVectorE0E1(a, a);
SingleOpcode(opcode, v0: v0, v1: v1);
@ -426,8 +426,8 @@ namespace Ryujinx.Tests.Cpu
opcode |= (imm5 << 16);
opcode |= (imm4 << 11);
Vector128<float> v0 = MakeVectorE0E1(z, z);
Vector128<float> v1 = MakeVectorE0E1(a, a);
V128 v0 = MakeVectorE0E1(z, z);
V128 v1 = MakeVectorE0E1(a, a);
SingleOpcode(opcode, v0: v0, v1: v1);
@ -452,8 +452,8 @@ namespace Ryujinx.Tests.Cpu
opcode |= (imm5 << 16);
opcode |= (imm4 << 11);
Vector128<float> v0 = MakeVectorE0E1(z, z);
Vector128<float> v1 = MakeVectorE0E1(a, a);
V128 v0 = MakeVectorE0E1(z, z);
V128 v1 = MakeVectorE0E1(a, a);
SingleOpcode(opcode, v0: v0, v1: v1);
@ -478,8 +478,8 @@ namespace Ryujinx.Tests.Cpu
opcode |= (imm5 << 16);
opcode |= (imm4 << 11);
Vector128<float> v0 = MakeVectorE0E1(z, z);
Vector128<float> v1 = MakeVectorE0E1(a, a);
V128 v0 = MakeVectorE0E1(z, z);
V128 v1 = MakeVectorE0E1(a, a);
SingleOpcode(opcode, v0: v0, v1: v1);
@ -502,7 +502,7 @@ namespace Ryujinx.Tests.Cpu
ulong x0 = (ulong)TestContext.CurrentContext.Random.NextUInt() << 32;
uint w31 = TestContext.CurrentContext.Random.NextUInt();
Vector128<float> v1 = MakeVectorE0E1(a, a);
V128 v1 = MakeVectorE0E1(a, a);
SingleOpcode(opcode, x0: x0, x31: w31, v1: v1);
@ -525,7 +525,7 @@ namespace Ryujinx.Tests.Cpu
ulong x0 = (ulong)TestContext.CurrentContext.Random.NextUInt() << 32;
uint w31 = TestContext.CurrentContext.Random.NextUInt();
Vector128<float> v1 = MakeVectorE0E1(a, a);
V128 v1 = MakeVectorE0E1(a, a);
SingleOpcode(opcode, x0: x0, x31: w31, v1: v1);
@ -547,7 +547,7 @@ namespace Ryujinx.Tests.Cpu
opcode |= (imm5 << 16);
ulong x31 = TestContext.CurrentContext.Random.NextULong();
Vector128<float> v1 = MakeVectorE0E1(a, a);
V128 v1 = MakeVectorE0E1(a, a);
SingleOpcode(opcode, x31: x31, v1: v1);
@ -569,7 +569,7 @@ namespace Ryujinx.Tests.Cpu
opcode |= (imm5 << 16);
ulong x31 = TestContext.CurrentContext.Random.NextULong();
Vector128<float> v1 = MakeVectorE0E1(a, a);
V128 v1 = MakeVectorE0E1(a, a);
SingleOpcode(opcode, x31: x31, v1: v1);
@ -591,7 +591,7 @@ namespace Ryujinx.Tests.Cpu
opcode |= (imm5 << 16);
ulong x31 = TestContext.CurrentContext.Random.NextULong();
Vector128<float> v1 = MakeVectorE0E1(a, a);
V128 v1 = MakeVectorE0E1(a, a);
SingleOpcode(opcode, x31: x31, v1: v1);
@ -614,7 +614,7 @@ namespace Ryujinx.Tests.Cpu
ulong x0 = (ulong)TestContext.CurrentContext.Random.NextUInt() << 32;
uint w31 = TestContext.CurrentContext.Random.NextUInt();
Vector128<float> v1 = MakeVectorE0E1(a, a);
V128 v1 = MakeVectorE0E1(a, a);
SingleOpcode(opcode, x0: x0, x31: w31, v1: v1);
@ -637,7 +637,7 @@ namespace Ryujinx.Tests.Cpu
ulong x0 = (ulong)TestContext.CurrentContext.Random.NextUInt() << 32;
uint w31 = TestContext.CurrentContext.Random.NextUInt();
Vector128<float> v1 = MakeVectorE0E1(a, a);
V128 v1 = MakeVectorE0E1(a, a);
SingleOpcode(opcode, x0: x0, x31: w31, v1: v1);
@ -660,7 +660,7 @@ namespace Ryujinx.Tests.Cpu
ulong x0 = (ulong)TestContext.CurrentContext.Random.NextUInt() << 32;
uint w31 = TestContext.CurrentContext.Random.NextUInt();
Vector128<float> v1 = MakeVectorE0E1(a, a);
V128 v1 = MakeVectorE0E1(a, a);
SingleOpcode(opcode, x0: x0, x31: w31, v1: v1);
@ -682,7 +682,7 @@ namespace Ryujinx.Tests.Cpu
opcode |= (imm5 << 16);
ulong x31 = TestContext.CurrentContext.Random.NextULong();
Vector128<float> v1 = MakeVectorE0E1(a, a);
V128 v1 = MakeVectorE0E1(a, a);
SingleOpcode(opcode, x31: x31, v1: v1);