rjx-mirror/Ryujinx.Tests/Cpu/CpuTestSimdRegElem.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

190 lines
7.7 KiB
C#

#define SimdRegElem
using ARMeilleure.State;
using NUnit.Framework;
namespace Ryujinx.Tests.Cpu
{
[Category("SimdRegElem")]
public sealed class CpuTestSimdRegElem : CpuTest
{
#if SimdRegElem
#region "ValueSource (Types)"
private static ulong[] _2S_()
{
return new ulong[] { 0x0000000000000000ul, 0x7FFFFFFF7FFFFFFFul,
0x8000000080000000ul, 0xFFFFFFFFFFFFFFFFul };
}
private static ulong[] _4H_()
{
return new ulong[] { 0x0000000000000000ul, 0x7FFF7FFF7FFF7FFFul,
0x8000800080008000ul, 0xFFFFFFFFFFFFFFFFul };
}
#endregion
#region "ValueSource (Opcodes)"
private static uint[] _Mla_Mls_Mul_Ve_4H_8H_()
{
return new uint[]
{
0x2F400000u, // MLA V0.4H, V0.4H, V0.H[0]
0x2F404000u, // MLS V0.4H, V0.4H, V0.H[0]
0x0F408000u // MUL V0.4H, V0.4H, V0.H[0]
};
}
private static uint[] _Mla_Mls_Mul_Ve_2S_4S_()
{
return new uint[]
{
0x2F800000u, // MLA V0.2S, V0.2S, V0.S[0]
0x2F804000u, // MLS V0.2S, V0.2S, V0.S[0]
0x0F808000u // MUL V0.2S, V0.2S, V0.S[0]
};
}
private static uint[] _SU_Mlal_Mlsl_Mull_Ve_4H4S_8H4S_()
{
return new uint[]
{
0x0F402000u, // SMLAL V0.4S, V0.4H, V0.H[0]
0x0F406000u, // SMLSL V0.4S, V0.4H, V0.H[0]
0x0F40A000u, // SMULL V0.4S, V0.4H, V0.H[0]
0x2F402000u, // UMLAL V0.4S, V0.4H, V0.H[0]
0x2F406000u, // UMLSL V0.4S, V0.4H, V0.H[0]
0x2F40A000u // UMULL V0.4S, V0.4H, V0.H[0]
};
}
private static uint[] _SU_Mlal_Mlsl_Mull_Ve_2S2D_4S2D_()
{
return new uint[]
{
0x0F802000u, // SMLAL V0.2D, V0.2S, V0.S[0]
0x0F806000u, // SMLSL V0.2D, V0.2S, V0.S[0]
0x0F80A000u, // SMULL V0.2D, V0.2S, V0.S[0]
0x2F802000u, // UMLAL V0.2D, V0.2S, V0.S[0]
0x2F806000u, // UMLSL V0.2D, V0.2S, V0.S[0]
0x2F80A000u // UMULL V0.2D, V0.2S, V0.S[0]
};
}
#endregion
private const int RndCnt = 2;
private const int RndCntIndex = 2;
[Test, Pairwise]
public void Mla_Mls_Mul_Ve_4H_8H([ValueSource("_Mla_Mls_Mul_Ve_4H_8H_")] uint opcodes,
[Values(0u)] uint rd,
[Values(1u, 0u)] uint rn,
[Values(2u, 0u)] uint rm,
[ValueSource("_4H_")] [Random(RndCnt)] ulong z,
[ValueSource("_4H_")] [Random(RndCnt)] ulong a,
[ValueSource("_4H_")] [Random(RndCnt)] ulong b,
[Values(0u, 7u)] [Random(1u, 6u, RndCntIndex)] uint index,
[Values(0b0u, 0b1u)] uint q) // <4H, 8H>
{
uint h = (index >> 2) & 1;
uint l = (index >> 1) & 1;
uint m = index & 1;
opcodes |= ((rm & 15) << 16) | ((rn & 31) << 5) | ((rd & 31) << 0);
opcodes |= (l << 21) | (m << 20) | (h << 11);
opcodes |= ((q & 1) << 30);
V128 v0 = MakeVectorE0E1(z, z);
V128 v1 = MakeVectorE0E1(a, a * q);
V128 v2 = MakeVectorE0E1(b, b * h);
SingleOpcode(opcodes, v0: v0, v1: v1, v2: v2);
CompareAgainstUnicorn();
}
[Test, Pairwise]
public void Mla_Mls_Mul_Ve_2S_4S([ValueSource("_Mla_Mls_Mul_Ve_2S_4S_")] uint opcodes,
[Values(0u)] uint rd,
[Values(1u, 0u)] uint rn,
[Values(2u, 0u)] uint rm,
[ValueSource("_2S_")] [Random(RndCnt)] ulong z,
[ValueSource("_2S_")] [Random(RndCnt)] ulong a,
[ValueSource("_2S_")] [Random(RndCnt)] ulong b,
[Values(0u, 1u, 2u, 3u)] uint index,
[Values(0b0u, 0b1u)] uint q) // <2S, 4S>
{
uint h = (index >> 1) & 1;
uint l = index & 1;
opcodes |= ((rm & 15) << 16) | ((rn & 31) << 5) | ((rd & 31) << 0);
opcodes |= (l << 21) | (h << 11);
opcodes |= ((q & 1) << 30);
V128 v0 = MakeVectorE0E1(z, z);
V128 v1 = MakeVectorE0E1(a, a * q);
V128 v2 = MakeVectorE0E1(b, b * h);
SingleOpcode(opcodes, v0: v0, v1: v1, v2: v2);
CompareAgainstUnicorn();
}
[Test, Pairwise]
public void SU_Mlal_Mlsl_Mull_Ve_4H4S_8H4S([ValueSource("_SU_Mlal_Mlsl_Mull_Ve_4H4S_8H4S_")] uint opcodes,
[Values(0u)] uint rd,
[Values(1u, 0u)] uint rn,
[Values(2u, 0u)] uint rm,
[ValueSource("_4H_")] [Random(RndCnt)] ulong z,
[ValueSource("_4H_")] [Random(RndCnt)] ulong a,
[ValueSource("_4H_")] [Random(RndCnt)] ulong b,
[Values(0u, 7u)] [Random(1u, 6u, RndCntIndex)] uint index,
[Values(0b0u, 0b1u)] uint q) // <4H4S, 8H4S>
{
uint h = (index >> 2) & 1;
uint l = (index >> 1) & 1;
uint m = index & 1;
opcodes |= ((rm & 15) << 16) | ((rn & 31) << 5) | ((rd & 31) << 0);
opcodes |= (l << 21) | (m << 20) | (h << 11);
opcodes |= ((q & 1) << 30);
V128 v0 = MakeVectorE0E1(z, z);
V128 v1 = MakeVectorE0E1(q == 0u ? a : 0ul, q == 1u ? a : 0ul);
V128 v2 = MakeVectorE0E1(b, b * h);
SingleOpcode(opcodes, v0: v0, v1: v1, v2: v2);
CompareAgainstUnicorn();
}
[Test, Pairwise]
public void SU_Mlal_Mlsl_Mull_Ve_2S2D_4S2D([ValueSource("_SU_Mlal_Mlsl_Mull_Ve_2S2D_4S2D_")] uint opcodes,
[Values(0u)] uint rd,
[Values(1u, 0u)] uint rn,
[Values(2u, 0u)] uint rm,
[ValueSource("_2S_")] [Random(RndCnt)] ulong z,
[ValueSource("_2S_")] [Random(RndCnt)] ulong a,
[ValueSource("_2S_")] [Random(RndCnt)] ulong b,
[Values(0u, 1u, 2u, 3u)] uint index,
[Values(0b0u, 0b1u)] uint q) // <2S2D, 4S2D>
{
uint h = (index >> 1) & 1;
uint l = index & 1;
opcodes |= ((rm & 15) << 16) | ((rn & 31) << 5) | ((rd & 31) << 0);
opcodes |= (l << 21) | (h << 11);
opcodes |= ((q & 1) << 30);
V128 v0 = MakeVectorE0E1(z, z);
V128 v1 = MakeVectorE0E1(q == 0u ? a : 0ul, q == 1u ? a : 0ul);
V128 v2 = MakeVectorE0E1(b, b * h);
SingleOpcode(opcodes, v0: v0, v1: v1, v2: v2);
CompareAgainstUnicorn();
}
#endif
}
}