Lioncash
392c1335b7
Interpreter: Get rid of some aliasing casts
2015-12-09 19:14:53 -05:00
Lioncash
f7977fdee5
Jit: Fall back to interpreter when frsp's record bit is set
2015-12-09 14:11:45 -05:00
Lioncash
3acf165787
Interpreter: Update CR when FRSP's record bit is set
2015-12-09 12:51:53 -05:00
Lioncash
a98bddc352
Interpreter: Remove underscore from frsp's parameter
2015-12-09 12:50:50 -05:00
Pringo
aaa67ca57e
Update Issue Tracker Link in Comment
2015-12-02 09:01:28 -08:00
Lioncash
ef1cc2cec4
CPU: Convert CCPU into a namespace
...
There's not much point to a class with only static member functions.
2015-10-04 15:15:10 -04:00
shuffle2
2cb5c41fed
HostGetString: Actually fill a string with data
2015-09-28 05:40:52 +02:00
Lioncash
19ac565e0d
Common: Move asserts to their own header
2015-09-26 18:51:27 -04:00
Lioncash
bddcdd9d94
Jit_Util: Replace two MDisp usages with MatR
...
Same thing, less to read.
2015-09-21 08:20:35 -04:00
Lioncash
9f389fdccb
Gekko: Make sign-extension functions constexpr
2015-09-18 11:14:45 -04:00
Lioncash
00ffc47751
Jit_Util: Mark a class function as const
2015-09-17 00:21:50 -04:00
Lioncash
c6ea9eb7c3
JitCache: Remove unused define
2015-09-16 19:15:47 -04:00
flacs
29a0a2b626
Merge pull request #3043 from lioncash/jitalign
...
JitCache: Get rid of pointer casts
2015-09-16 21:22:01 +02:00
Lioncash
8aac59418b
JitCache: Get rid of pointer casts
...
Silences more ubsan runtime asserts
2015-09-16 06:25:48 -04:00
degasus
3ae466a33c
JitArm64: Fix lmw + stmw
2015-09-16 08:11:18 +02:00
Scott Mansell
c0a89c3bf4
Merge pull request #3009 from phire/depth_tested_pokes
...
Add some logging for depth tested efb color pokes.
2015-09-12 22:20:59 +12:00
Scott Mansell
44456bec0f
Add some logging for depth tested efb color pokes.
2015-09-12 22:19:59 +12:00
Lioncash
3f4852a03d
MathUtil: Convert IsPow2 into a constexpr function
2015-09-12 01:26:05 -04:00
Lioncash
b9e360df7b
MathUtil: Convert Clamp into a constexpr function
2015-09-12 01:18:28 -04:00
flacs
c5685ba53a
Merge pull request #2972 from lioncash/align
...
General: Replace GC_ALIGN macros with alignas
2015-09-11 17:00:13 +00:00
Lioncash
19459e827f
Partially revert "General: Toss out PRI macro usage"
2015-09-11 09:49:00 -04:00
flacs
48031eaff7
Merge pull request #2974 from Tilka/fprf
...
Jit64: fix errors in FPRF calculation
2015-09-08 18:59:22 +00:00
Ryan Houdek
5d7f834cde
Add run count to the JIT profile information
2015-09-08 11:09:52 -05:00
Ryan Houdek
a9a339a00c
Merge pull request #2962 from Sonicadvance1/aarch64_integer_gatherpipe
...
[AArch64] Implement integer gatherpipe writes.
2015-09-07 06:20:01 -05:00
Lioncash
8ce04f9a65
General: Replace GC_ALIGN macros with alignas
...
Standard supported alignment -> out with compiler-specific.
2015-09-06 12:53:51 -04:00
Scott Mansell
be4caa3dc0
Merge pull request #2961 from lioncash/printf
...
General: Toss out PRI macro usage
2015-09-06 21:02:22 +12:00
Lioncash
4fc71e9708
Common: Remove StdMakeUnique.h
2015-09-06 04:09:53 -04:00
comex
96e42dff52
Merge pull request #2977 from lioncash/unused
...
General: Remove unimplemented function prototypes
2015-09-05 22:20:47 -04:00
Lioncash
633be0387d
General: Remove unimplemented function prototypes
2015-09-05 22:01:07 -04:00
Lioncash
8fdb013d54
General: Toss out PRI macro usage
...
Now that VS supports more printf specifiers, these aren't necessary
2015-09-05 16:02:35 -04:00
Tillmann Karras
8f777cd839
Jit64: fix errors in FPRF calculation
2015-09-05 20:17:53 +02:00
Ryan Houdek
de80b9e988
Merge pull request #2971 from degasus/arm
...
JitArm64: fix smaller issues
2015-09-05 08:43:44 -05:00
degasus
24fec3ebca
JitArm64: Fix float load & store
2015-09-05 13:48:29 +02:00
degasus
36902c58eb
JitArm64: Fix lwbrx and lhbrx
2015-09-05 13:48:29 +02:00
degasus
696f95d5f9
JitArm64: Fix subfic
2015-09-05 13:48:29 +02:00
degasus
baa28e13f4
JitArm64: Remove FLUSH_INTERPRETER
...
It seems to be broken for some instructions, and there is no need for it any more.
2015-09-05 13:48:29 +02:00
Tillmann Karras
405554e327
Jit64: remove unnecessary indirection
2015-09-05 12:40:14 +02:00
Tillmann Karras
72eed1aa82
JitCache: drop unused method
2015-09-05 12:40:14 +02:00
Ryan Houdek
de051dac71
[AArch64] Implement integer gatherpipe writes.
2015-09-04 19:52:25 -05:00
Ryan Houdek
791c7d5a84
[AArch64] Clean up bogus vector FCVT{N,L} instruction usage.
...
Replace the instruction with the scalar variant FCVT instruction.
FCVT{N,L} 8 cycles latency on the Cortex A57
FCVT has five cycle latency and slightly higher throughput
On the A72 all three of these instructions will have three cycle latency,
While FCVT{N,L} will have half the throughput.
2015-09-04 19:41:54 -05:00
Ryan Houdek
2c68f6bfc5
[AArch64] Implement Fiora's preemptive paired loadstore optimization.
...
This provides a decent speed up in pretty much everything that touches pair loadstores because in most cases they are just regular non-quantizing
float loadstores that happen.
2015-09-04 19:20:33 -05:00
degasus
5797111ef0
JitArm64: Optimize fpr.R()
2015-09-02 22:46:14 +02:00
degasus
dfd44730c8
JitArm64: simplify fpr call
2015-09-02 22:46:14 +02:00
Ryan Houdek
ae0a06a018
[AArch64] Implement dcbz instruction
2015-08-31 15:39:47 -05:00
Ryan Houdek
0f54aa48b4
Merge pull request #2928 from Sonicadvance1/aarch64_improved_singles
...
[AArch64] Improve floating point single instructions.
2015-08-31 12:00:08 -05:00
Ryan Houdek
bcde1aa8ff
[AArch64] Improve floating point single instructions.
...
Instead of having an "INS" instruction after every single instruction to duplicate the bottom 64bits in to the top 64bits of the register,
create a new FPR register cache type to track when a register's lower 64bits is supposed to be duplicated in to the high 64bits.
Not necessarily actually having the lower bits duplicated in the host side register. This removes inefficient INS instructions from sequential single
float instructions.
In particular a very heavy single heavy block in Animal Crossing went from 712 instructions down to 520 instructions(~37% less instructions!)
2015-08-31 11:09:17 -05:00
Ryan Houdek
d003934b8a
Merge pull request #2929 from Sonicadvance1/aarch64_optimize_gpr_flush
...
Aarch64 optimize gpr flush
2015-08-31 10:55:45 -05:00
Ryan Houdek
8bf332cf08
[AArch64] Optimize GPR cache flushing.
...
If we are flushing multiple sequential guest GPRs then we can store two in a single STP instruction.
Ikaruga does this quite a bit in their blocks where they do an lmw at the very end and then we have to flush them all.
Typically cuts 16 STR instructions down to 8 STP instructions there.
2015-08-30 23:07:12 -05:00
Ryan Houdek
b907576510
[AArch64] Support profiling by cycle counters if they are available to EL0
2015-08-30 10:25:16 -05:00
Ryan Houdek
5110574c1f
Merge pull request #2921 from Sonicadvance1/aarch64_optimize_lmw
...
[AArch64] Optimize lmw.
2015-08-30 10:23:57 -05:00