gdkchan
|
a1a589d31e
|
Update the Ryujinx project to use ARMeilleure
|
2019-08-01 20:55:03 -03:00 |
|
gdkchan
|
6c54009f23
|
Change win10-x64 to win-x64 on projects
|
2019-08-01 18:45:04 -03:00 |
|
gdkchan
|
8c14041c34
|
Allow switching between CPUs through a config entry (pt. 2)
|
2019-08-01 18:23:56 -03:00 |
|
gdkchan
|
8d7adc7be7
|
Add runtime identifiers on the ARMeilleure project
|
2019-08-01 18:19:58 -03:00 |
|
gdkchan
|
15dc188dc4
|
Allow changing CPU emulators with a config entry
|
2019-08-01 17:55:27 -03:00 |
|
gdkchan
|
5708164352
|
CpuThreadState is gone
|
2019-08-01 14:38:49 -03:00 |
|
gdkchan
|
3edfb06099
|
Some nits, small improvements on the pre allocator
|
2019-08-01 14:34:57 -03:00 |
|
gdkchan
|
ac5f4894ac
|
Add a new register allocator, higher quality code for hot code (tier up), and other tweaks
|
2019-08-01 14:34:57 -03:00 |
|
gdkchan
|
9f4e6815c7
|
Float operands don't need to use the same register when VEX is supported
|
2019-08-01 14:34:56 -03:00 |
|
gdkchan
|
c7e78bcb45
|
Another fix on VectorInsert FP32 (thanks to LDj3SNuD
|
2019-08-01 14:34:56 -03:00 |
|
gdkchan
|
6b42189d05
|
Avoid memory protection races on JIT Cache
|
2019-08-01 14:34:56 -03:00 |
|
gdkchan
|
eaa734b8e6
|
Port over the ARM32 instructions
|
2019-08-01 14:34:56 -03:00 |
|
gdkchan
|
8938e9f2e0
|
Fix vector insert FP32 SSE2 path
|
2019-08-01 14:34:56 -03:00 |
|
gdkchan
|
1c18425884
|
Some refactoring
|
2019-08-01 14:34:56 -03:00 |
|
gdkchan
|
4d4ccd6c52
|
Add an extra space on comments to match code style
|
2019-08-01 14:34:56 -03:00 |
|
gdkchan
|
bbad6280b1
|
Fix a regression related to calls and the V128 type
|
2019-08-01 14:34:56 -03:00 |
|
gdkchan
|
846ebe9a9c
|
Rename Dest to Destination and Inst to Instruction
|
2019-08-01 14:34:56 -03:00 |
|
gdkchan
|
db5e612914
|
Change placement of XMM callee save and restore code to match other compilers
|
2019-08-01 14:34:56 -03:00 |
|
gdkchan
|
a3ea200444
|
Fix SSE2 VectorInsert8 path, and other fixes
|
2019-08-01 14:34:56 -03:00 |
|
gdkchan
|
36be15fe6c
|
Support multiple destination operands
|
2019-08-01 14:34:56 -03:00 |
|
gdk
|
ceb5c055a0
|
Initial support for the System-V ABI
|
2019-08-01 14:34:56 -03:00 |
|
gdkchan
|
40b8a2a750
|
Generate inline stack probes when the stack allocation is too large
|
2019-08-01 14:34:56 -03:00 |
|
gdkchan
|
15f73fa36d
|
Fix silly mistake introduced on last commit on CpuId
|
2019-08-01 14:34:56 -03:00 |
|
gdkchan
|
581b7c8bbf
|
Add SSE2-only paths on vector extract and insert, some refactoring on the pre-allocator
|
2019-08-01 14:34:56 -03:00 |
|
gdkchan
|
3a0676c596
|
Fix regression on Sha1h and revert Fcm** changes
|
2019-08-01 14:34:55 -03:00 |
|
gdkchan
|
93963c97d2
|
Add hardware capability detection
|
2019-08-01 14:34:55 -03:00 |
|
gdkchan
|
679ff7271d
|
Fix REX.W prefix regression on float conversion instructions, add some sort of profiler
|
2019-08-01 14:34:55 -03:00 |
|
gdkchan
|
c114de7ff4
|
Remove some unused code on the assembler
|
2019-08-01 14:34:55 -03:00 |
|
gdkchan
|
e091b06cf9
|
Some refactoring on the code generator, assert on invalid operations and use a separate enum for intrinsics
|
2019-08-01 14:34:55 -03:00 |
|
gdkchan
|
beda03f8c8
|
Use generic GetFunctionPointerForDelegate method and other tweaks
|
2019-08-01 14:34:55 -03:00 |
|
gdkchan
|
686f7f4ff2
|
Stop using GetFunctionPointer as that can't be called from native code, misc. fixes and tweaks
|
2019-08-01 14:34:55 -03:00 |
|
gdkchan
|
70970b4c22
|
Update ITimeZoneService
|
2019-08-01 14:34:55 -03:00 |
|
gdkchan
|
fbf7f83677
|
Update Ryujinx.Tests
|
2019-08-01 14:33:04 -03:00 |
|
gdkchan
|
2910e1e670
|
Fix V128 return pointer passing, RCX is clobbered
|
2019-08-01 14:33:04 -03:00 |
|
gdkchan
|
bae5a93e3a
|
Update Ryujinx.Graphics
|
2019-08-01 14:33:04 -03:00 |
|
gdkchan
|
c533716e5d
|
Update Ryujinx.HLE
|
2019-08-01 14:33:04 -03:00 |
|
gdkchan
|
4069fa8e33
|
Add a faster linear scan allocator, unwinding support on windows, and other changes
|
2019-08-01 14:30:25 -03:00 |
|
gdkchan
|
4f38a65509
|
Update tests
|
2019-08-01 14:30:24 -03:00 |
|
gdkchan
|
ba9ff58d94
|
Misc. fixes and integrate LDj3SNuD fixes
|
2019-08-01 14:30:24 -03:00 |
|
gdkchan
|
c306809b0b
|
More instructions
|
2019-08-01 14:30:24 -03:00 |
|
gdkchan
|
9f8fbc1d8a
|
Fix arguments count with struct return values, other fixes
|
2019-08-01 14:30:23 -03:00 |
|
gdkchan
|
0bacc3fd63
|
Fix float constant passed to functions, save and restore non-volatile XMM registers, other fixes
|
2019-08-01 14:30:23 -03:00 |
|
gdkchan
|
87238b509c
|
Use old memory access methods, made a start on SIMD memory insts support, some fixes
|
2019-08-01 14:30:23 -03:00 |
|
gdkchan
|
6f654c681e
|
Support passing V128 structs, some cleanup on the register allocator, merge LDj3SNuD fixes
|
2019-08-01 14:30:23 -03:00 |
|
gdkchan
|
05498c36a8
|
Update FCVT (Scalar) encoding on the table to support the Half-float variants
|
2019-08-01 14:30:22 -03:00 |
|
gdkchan
|
ca3a73dd4e
|
Implement FP & SIMD comparison instructions, and some fixes
|
2019-08-01 14:30:22 -03:00 |
|
gdkchan
|
bb3ccccd3c
|
Fix check with tolerance on tester
|
2019-08-01 14:30:22 -03:00 |
|
gdkchan
|
0d553aff83
|
Add SCVTF and UCVTF (vector, fixed-point) variants to the opcode table
|
2019-08-01 14:30:22 -03:00 |
|
gdkchan
|
3c09d49067
|
Implement SIMD shift instruction and fix Dup_V
|
2019-08-01 14:30:22 -03:00 |
|
gdkchan
|
5d7aadd57c
|
Implement float conversion instruction, merge in LDj3SNuD fixes, and some other misc. fixes
|
2019-08-01 14:30:22 -03:00 |
|