2019-03-23 11:50:19 -07:00
|
|
|
#define SimdTbl
|
|
|
|
|
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 11:56:22 -07:00
|
|
|
using ARMeilleure.State;
|
|
|
|
|
2019-03-23 11:50:19 -07:00
|
|
|
using NUnit.Framework;
|
|
|
|
|
|
|
|
using System.Collections.Generic;
|
|
|
|
|
|
|
|
namespace Ryujinx.Tests.Cpu
|
|
|
|
{
|
|
|
|
[Category("SimdTbl")]
|
|
|
|
public sealed class CpuTestSimdTbl : CpuTest
|
|
|
|
{
|
|
|
|
#if SimdTbl
|
|
|
|
|
|
|
|
#region "Helper methods"
|
|
|
|
private static ulong GenIdxsForTbls(int regs)
|
|
|
|
{
|
|
|
|
const byte idxInRngMin = (byte)0;
|
|
|
|
byte idxInRngMax = (byte)((16 * regs) - 1);
|
|
|
|
byte idxOutRngMin = (byte) (16 * regs);
|
|
|
|
const byte idxOutRngMax = (byte)255;
|
|
|
|
|
|
|
|
ulong idxs = 0ul;
|
|
|
|
|
|
|
|
for (int cnt = 1; cnt <= 8; cnt++)
|
|
|
|
{
|
|
|
|
ulong idxInRng = (ulong)TestContext.CurrentContext.Random.NextByte(idxInRngMin, idxInRngMax);
|
|
|
|
ulong idxOutRng = (ulong)TestContext.CurrentContext.Random.NextByte(idxOutRngMin, idxOutRngMax);
|
|
|
|
|
|
|
|
ulong idx = TestContext.CurrentContext.Random.NextBool() ? idxInRng : idxOutRng;
|
|
|
|
|
|
|
|
idxs = (idxs << 8) | idx;
|
|
|
|
}
|
|
|
|
|
|
|
|
return idxs;
|
|
|
|
}
|
|
|
|
#endregion
|
|
|
|
|
|
|
|
#region "ValueSource (Types)"
|
|
|
|
private static ulong[] _8B_()
|
|
|
|
{
|
|
|
|
return new ulong[] { 0x0000000000000000ul, 0x7F7F7F7F7F7F7F7Ful,
|
|
|
|
0x8080808080808080ul, 0xFFFFFFFFFFFFFFFFul };
|
|
|
|
}
|
|
|
|
|
|
|
|
private static IEnumerable<ulong> _GenIdxsForTbl1_()
|
|
|
|
{
|
|
|
|
yield return 0x0000000000000000ul;
|
|
|
|
yield return 0x7F7F7F7F7F7F7F7Ful;
|
|
|
|
yield return 0x8080808080808080ul;
|
|
|
|
yield return 0xFFFFFFFFFFFFFFFFul;
|
|
|
|
|
|
|
|
for (int cnt = 1; cnt <= RndCntIdxs; cnt++)
|
|
|
|
{
|
|
|
|
yield return GenIdxsForTbls(regs: 1);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
private static IEnumerable<ulong> _GenIdxsForTbl2_()
|
|
|
|
{
|
|
|
|
yield return 0x0000000000000000ul;
|
|
|
|
yield return 0x7F7F7F7F7F7F7F7Ful;
|
|
|
|
yield return 0x8080808080808080ul;
|
|
|
|
yield return 0xFFFFFFFFFFFFFFFFul;
|
|
|
|
|
|
|
|
for (int cnt = 1; cnt <= RndCntIdxs; cnt++)
|
|
|
|
{
|
|
|
|
yield return GenIdxsForTbls(regs: 2);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
private static IEnumerable<ulong> _GenIdxsForTbl3_()
|
|
|
|
{
|
|
|
|
yield return 0x0000000000000000ul;
|
|
|
|
yield return 0x7F7F7F7F7F7F7F7Ful;
|
|
|
|
yield return 0x8080808080808080ul;
|
|
|
|
yield return 0xFFFFFFFFFFFFFFFFul;
|
|
|
|
|
|
|
|
for (int cnt = 1; cnt <= RndCntIdxs; cnt++)
|
|
|
|
{
|
|
|
|
yield return GenIdxsForTbls(regs: 3);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
private static IEnumerable<ulong> _GenIdxsForTbl4_()
|
|
|
|
{
|
|
|
|
yield return 0x0000000000000000ul;
|
|
|
|
yield return 0x7F7F7F7F7F7F7F7Ful;
|
|
|
|
yield return 0x8080808080808080ul;
|
|
|
|
yield return 0xFFFFFFFFFFFFFFFFul;
|
|
|
|
|
|
|
|
for (int cnt = 1; cnt <= RndCntIdxs; cnt++)
|
|
|
|
{
|
|
|
|
yield return GenIdxsForTbls(regs: 4);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
#endregion
|
|
|
|
|
|
|
|
#region "ValueSource (Opcodes)"
|
2019-10-04 07:43:20 -07:00
|
|
|
private static uint[] _SingleRegisterTable_V_8B_16B_()
|
2019-03-23 11:50:19 -07:00
|
|
|
{
|
|
|
|
return new uint[]
|
|
|
|
{
|
|
|
|
0x0E000000u, // TBL V0.8B, { V0.16B }, V0.8B
|
2019-10-04 07:43:20 -07:00
|
|
|
0x0E001000u // TBX V0.8B, { V0.16B }, V0.8B
|
2019-03-23 11:50:19 -07:00
|
|
|
};
|
|
|
|
}
|
|
|
|
|
2019-10-04 07:43:20 -07:00
|
|
|
private static uint[] _TwoRegisterTable_V_8B_16B_()
|
2019-03-23 11:50:19 -07:00
|
|
|
{
|
|
|
|
return new uint[]
|
|
|
|
{
|
|
|
|
0x0E002000u, // TBL V0.8B, { V0.16B, V1.16B }, V0.8B
|
2019-10-04 07:43:20 -07:00
|
|
|
0x0E003000u // TBX V0.8B, { V0.16B, V1.16B }, V0.8B
|
2019-03-23 11:50:19 -07:00
|
|
|
};
|
|
|
|
}
|
|
|
|
|
2019-10-04 07:43:20 -07:00
|
|
|
private static uint[] _ThreeRegisterTable_V_8B_16B_()
|
2019-03-23 11:50:19 -07:00
|
|
|
{
|
|
|
|
return new uint[]
|
|
|
|
{
|
|
|
|
0x0E004000u, // TBL V0.8B, { V0.16B, V1.16B, V2.16B }, V0.8B
|
2019-10-04 07:43:20 -07:00
|
|
|
0x0E005000u // TBX V0.8B, { V0.16B, V1.16B, V2.16B }, V0.8B
|
2019-03-23 11:50:19 -07:00
|
|
|
};
|
|
|
|
}
|
|
|
|
|
2019-10-04 07:43:20 -07:00
|
|
|
private static uint[] _FourRegisterTable_V_8B_16B_()
|
2019-03-23 11:50:19 -07:00
|
|
|
{
|
|
|
|
return new uint[]
|
|
|
|
{
|
|
|
|
0x0E006000u, // TBL V0.8B, { V0.16B, V1.16B, V2.16B, V3.16B }, V0.8B
|
2019-10-04 07:43:20 -07:00
|
|
|
0x0E006000u // TBX V0.8B, { V0.16B, V1.16B, V2.16B, V3.16B }, V0.8B
|
2019-03-23 11:50:19 -07:00
|
|
|
};
|
|
|
|
}
|
|
|
|
#endregion
|
|
|
|
|
2019-10-04 07:43:20 -07:00
|
|
|
private const int RndCntDest = 2;
|
2019-03-23 11:50:19 -07:00
|
|
|
private const int RndCntTbls = 2;
|
|
|
|
private const int RndCntIdxs = 2;
|
|
|
|
|
2019-10-04 07:43:20 -07:00
|
|
|
[Test, Pairwise]
|
|
|
|
public void SingleRegisterTable_V_8B_16B([ValueSource("_SingleRegisterTable_V_8B_16B_")] uint opcodes,
|
|
|
|
[Values(0u)] uint rd,
|
|
|
|
[Values(1u)] uint rn,
|
|
|
|
[Values(2u)] uint rm,
|
|
|
|
[ValueSource("_8B_")] [Random(RndCntDest)] ulong z,
|
|
|
|
[ValueSource("_8B_")] [Random(RndCntTbls)] ulong table0,
|
|
|
|
[ValueSource("_GenIdxsForTbl1_")] ulong indexes,
|
|
|
|
[Values(0b0u, 0b1u)] uint q) // <8B, 16B>
|
2019-03-23 11:50:19 -07:00
|
|
|
{
|
|
|
|
opcodes |= ((rm & 31) << 16) | ((rn & 31) << 5) | ((rd & 31) << 0);
|
|
|
|
opcodes |= ((q & 1) << 30);
|
|
|
|
|
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 11:56:22 -07:00
|
|
|
V128 v0 = MakeVectorE0E1(z, z);
|
|
|
|
V128 v1 = MakeVectorE0E1(table0, table0);
|
|
|
|
V128 v2 = MakeVectorE0E1(indexes, q == 1u ? indexes : 0ul);
|
2019-03-23 11:50:19 -07:00
|
|
|
|
|
|
|
SingleOpcode(opcodes, v0: v0, v1: v1, v2: v2);
|
|
|
|
|
|
|
|
CompareAgainstUnicorn();
|
|
|
|
}
|
|
|
|
|
2019-10-04 07:43:20 -07:00
|
|
|
[Test, Pairwise]
|
|
|
|
public void TwoRegisterTable_V_8B_16B([ValueSource("_TwoRegisterTable_V_8B_16B_")] uint opcodes,
|
|
|
|
[Values(0u)] uint rd,
|
|
|
|
[Values(1u)] uint rn,
|
|
|
|
[Values(3u)] uint rm,
|
|
|
|
[ValueSource("_8B_")] [Random(RndCntDest)] ulong z,
|
|
|
|
[ValueSource("_8B_")] [Random(RndCntTbls)] ulong table0,
|
|
|
|
[ValueSource("_8B_")] [Random(RndCntTbls)] ulong table1,
|
|
|
|
[ValueSource("_GenIdxsForTbl2_")] ulong indexes,
|
|
|
|
[Values(0b0u, 0b1u)] uint q) // <8B, 16B>
|
2019-03-23 11:50:19 -07:00
|
|
|
{
|
|
|
|
opcodes |= ((rm & 31) << 16) | ((rn & 31) << 5) | ((rd & 31) << 0);
|
|
|
|
opcodes |= ((q & 1) << 30);
|
|
|
|
|
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 11:56:22 -07:00
|
|
|
V128 v0 = MakeVectorE0E1(z, z);
|
|
|
|
V128 v1 = MakeVectorE0E1(table0, table0);
|
|
|
|
V128 v2 = MakeVectorE0E1(table1, table1);
|
|
|
|
V128 v3 = MakeVectorE0E1(indexes, q == 1u ? indexes : 0ul);
|
2019-03-23 11:50:19 -07:00
|
|
|
|
|
|
|
SingleOpcode(opcodes, v0: v0, v1: v1, v2: v2, v3: v3);
|
|
|
|
|
|
|
|
CompareAgainstUnicorn();
|
|
|
|
}
|
|
|
|
|
2019-10-04 07:43:20 -07:00
|
|
|
[Test, Pairwise]
|
|
|
|
public void Mod_TwoRegisterTable_V_8B_16B([ValueSource("_TwoRegisterTable_V_8B_16B_")] uint opcodes,
|
|
|
|
[Values(30u, 1u)] uint rd,
|
|
|
|
[Values(31u)] uint rn,
|
|
|
|
[Values(1u, 30u)] uint rm,
|
|
|
|
[ValueSource("_8B_")] [Random(RndCntDest)] ulong z,
|
|
|
|
[ValueSource("_8B_")] [Random(RndCntTbls)] ulong table0,
|
|
|
|
[ValueSource("_8B_")] [Random(RndCntTbls)] ulong table1,
|
|
|
|
[ValueSource("_GenIdxsForTbl2_")] ulong indexes,
|
|
|
|
[Values(0b0u, 0b1u)] uint q) // <8B, 16B>
|
2019-03-23 11:50:19 -07:00
|
|
|
{
|
|
|
|
opcodes |= ((rm & 31) << 16) | ((rn & 31) << 5) | ((rd & 31) << 0);
|
|
|
|
opcodes |= ((q & 1) << 30);
|
|
|
|
|
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 11:56:22 -07:00
|
|
|
V128 v30 = MakeVectorE0E1(z, z);
|
|
|
|
V128 v31 = MakeVectorE0E1(table0, table0);
|
|
|
|
V128 v0 = MakeVectorE0E1(table1, table1);
|
|
|
|
V128 v1 = MakeVectorE0E1(indexes, indexes);
|
2019-03-23 11:50:19 -07:00
|
|
|
|
|
|
|
SingleOpcode(opcodes, v0: v0, v1: v1, v30: v30, v31: v31);
|
|
|
|
|
|
|
|
CompareAgainstUnicorn();
|
|
|
|
}
|
|
|
|
|
2019-10-04 07:43:20 -07:00
|
|
|
[Test, Pairwise]
|
|
|
|
public void ThreeRegisterTable_V_8B_16B([ValueSource("_ThreeRegisterTable_V_8B_16B_")] uint opcodes,
|
|
|
|
[Values(0u)] uint rd,
|
|
|
|
[Values(1u)] uint rn,
|
|
|
|
[Values(4u)] uint rm,
|
|
|
|
[ValueSource("_8B_")] [Random(RndCntDest)] ulong z,
|
|
|
|
[ValueSource("_8B_")] [Random(RndCntTbls)] ulong table0,
|
|
|
|
[ValueSource("_8B_")] [Random(RndCntTbls)] ulong table1,
|
|
|
|
[ValueSource("_8B_")] [Random(RndCntTbls)] ulong table2,
|
|
|
|
[ValueSource("_GenIdxsForTbl3_")] ulong indexes,
|
|
|
|
[Values(0b0u, 0b1u)] uint q) // <8B, 16B>
|
2019-03-23 11:50:19 -07:00
|
|
|
{
|
|
|
|
opcodes |= ((rm & 31) << 16) | ((rn & 31) << 5) | ((rd & 31) << 0);
|
|
|
|
opcodes |= ((q & 1) << 30);
|
|
|
|
|
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 11:56:22 -07:00
|
|
|
V128 v0 = MakeVectorE0E1(z, z);
|
|
|
|
V128 v1 = MakeVectorE0E1(table0, table0);
|
|
|
|
V128 v2 = MakeVectorE0E1(table1, table1);
|
|
|
|
V128 v3 = MakeVectorE0E1(table2, table2);
|
|
|
|
V128 v4 = MakeVectorE0E1(indexes, q == 1u ? indexes : 0ul);
|
2019-03-23 11:50:19 -07:00
|
|
|
|
|
|
|
SingleOpcode(opcodes, v0: v0, v1: v1, v2: v2, v3: v3, v4: v4);
|
|
|
|
|
|
|
|
CompareAgainstUnicorn();
|
|
|
|
}
|
|
|
|
|
2019-10-04 07:43:20 -07:00
|
|
|
[Test, Pairwise]
|
|
|
|
public void Mod_ThreeRegisterTable_V_8B_16B([ValueSource("_ThreeRegisterTable_V_8B_16B_")] uint opcodes,
|
|
|
|
[Values(30u, 2u)] uint rd,
|
|
|
|
[Values(31u)] uint rn,
|
|
|
|
[Values(2u, 30u)] uint rm,
|
|
|
|
[ValueSource("_8B_")] [Random(RndCntDest)] ulong z,
|
|
|
|
[ValueSource("_8B_")] [Random(RndCntTbls)] ulong table0,
|
|
|
|
[ValueSource("_8B_")] [Random(RndCntTbls)] ulong table1,
|
|
|
|
[ValueSource("_8B_")] [Random(RndCntTbls)] ulong table2,
|
|
|
|
[ValueSource("_GenIdxsForTbl3_")] ulong indexes,
|
|
|
|
[Values(0b0u, 0b1u)] uint q) // <8B, 16B>
|
2019-03-23 11:50:19 -07:00
|
|
|
{
|
|
|
|
opcodes |= ((rm & 31) << 16) | ((rn & 31) << 5) | ((rd & 31) << 0);
|
|
|
|
opcodes |= ((q & 1) << 30);
|
|
|
|
|
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 11:56:22 -07:00
|
|
|
V128 v30 = MakeVectorE0E1(z, z);
|
|
|
|
V128 v31 = MakeVectorE0E1(table0, table0);
|
|
|
|
V128 v0 = MakeVectorE0E1(table1, table1);
|
|
|
|
V128 v1 = MakeVectorE0E1(table2, table2);
|
|
|
|
V128 v2 = MakeVectorE0E1(indexes, indexes);
|
2019-03-23 11:50:19 -07:00
|
|
|
|
|
|
|
SingleOpcode(opcodes, v0: v0, v1: v1, v2: v2, v30: v30, v31: v31);
|
|
|
|
|
|
|
|
CompareAgainstUnicorn();
|
|
|
|
}
|
|
|
|
|
2019-10-04 07:43:20 -07:00
|
|
|
[Test, Pairwise]
|
|
|
|
public void FourRegisterTable_V_8B_16B([ValueSource("_FourRegisterTable_V_8B_16B_")] uint opcodes,
|
|
|
|
[Values(0u)] uint rd,
|
|
|
|
[Values(1u)] uint rn,
|
|
|
|
[Values(5u)] uint rm,
|
|
|
|
[ValueSource("_8B_")] [Random(RndCntDest)] ulong z,
|
|
|
|
[ValueSource("_8B_")] [Random(RndCntTbls)] ulong table0,
|
|
|
|
[ValueSource("_8B_")] [Random(RndCntTbls)] ulong table1,
|
|
|
|
[ValueSource("_8B_")] [Random(RndCntTbls)] ulong table2,
|
|
|
|
[ValueSource("_8B_")] [Random(RndCntTbls)] ulong table3,
|
|
|
|
[ValueSource("_GenIdxsForTbl4_")] ulong indexes,
|
|
|
|
[Values(0b0u, 0b1u)] uint q) // <8B, 16B>
|
2019-03-23 11:50:19 -07:00
|
|
|
{
|
|
|
|
opcodes |= ((rm & 31) << 16) | ((rn & 31) << 5) | ((rd & 31) << 0);
|
|
|
|
opcodes |= ((q & 1) << 30);
|
|
|
|
|
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 11:56:22 -07:00
|
|
|
V128 v0 = MakeVectorE0E1(z, z);
|
|
|
|
V128 v1 = MakeVectorE0E1(table0, table0);
|
|
|
|
V128 v2 = MakeVectorE0E1(table1, table1);
|
|
|
|
V128 v3 = MakeVectorE0E1(table2, table2);
|
|
|
|
V128 v4 = MakeVectorE0E1(table3, table3);
|
|
|
|
V128 v5 = MakeVectorE0E1(indexes, q == 1u ? indexes : 0ul);
|
2019-03-23 11:50:19 -07:00
|
|
|
|
|
|
|
SingleOpcode(opcodes, v0: v0, v1: v1, v2: v2, v3: v3, v4: v4, v5: v5);
|
|
|
|
|
|
|
|
CompareAgainstUnicorn();
|
|
|
|
}
|
|
|
|
|
2019-10-04 07:43:20 -07:00
|
|
|
[Test, Pairwise]
|
|
|
|
public void Mod_FourRegisterTable_V_8B_16B([ValueSource("_FourRegisterTable_V_8B_16B_")] uint opcodes,
|
|
|
|
[Values(30u, 3u)] uint rd,
|
|
|
|
[Values(31u)] uint rn,
|
|
|
|
[Values(3u, 30u)] uint rm,
|
|
|
|
[ValueSource("_8B_")] [Random(RndCntDest)] ulong z,
|
|
|
|
[ValueSource("_8B_")] [Random(RndCntTbls)] ulong table0,
|
|
|
|
[ValueSource("_8B_")] [Random(RndCntTbls)] ulong table1,
|
|
|
|
[ValueSource("_8B_")] [Random(RndCntTbls)] ulong table2,
|
|
|
|
[ValueSource("_8B_")] [Random(RndCntTbls)] ulong table3,
|
|
|
|
[ValueSource("_GenIdxsForTbl4_")] ulong indexes,
|
|
|
|
[Values(0b0u, 0b1u)] uint q) // <8B, 16B>
|
2019-03-23 11:50:19 -07:00
|
|
|
{
|
|
|
|
opcodes |= ((rm & 31) << 16) | ((rn & 31) << 5) | ((rd & 31) << 0);
|
|
|
|
opcodes |= ((q & 1) << 30);
|
|
|
|
|
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 11:56:22 -07:00
|
|
|
V128 v30 = MakeVectorE0E1(z, z);
|
|
|
|
V128 v31 = MakeVectorE0E1(table0, table0);
|
|
|
|
V128 v0 = MakeVectorE0E1(table1, table1);
|
|
|
|
V128 v1 = MakeVectorE0E1(table2, table2);
|
|
|
|
V128 v2 = MakeVectorE0E1(table3, table3);
|
|
|
|
V128 v3 = MakeVectorE0E1(indexes, indexes);
|
2019-03-23 11:50:19 -07:00
|
|
|
|
|
|
|
SingleOpcode(opcodes, v0: v0, v1: v1, v2: v2, v3: v3, v30: v30, v31: v31);
|
|
|
|
|
|
|
|
CompareAgainstUnicorn();
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
}
|
|
|
|
}
|