Commit graph

1184 commits

Author SHA1 Message Date
Unknown W. Brackets
a89d61463e Make the VFPU jit use far jumps for memory access. 2013-01-26 23:08:19 -08:00
Henrik Rydgard
1ed9a6ba56 Small fixes. v0.6. 2013-01-26 21:39:35 +01:00
Unknown W. Brackets
7ba8d1efe9 Android buildfix. 2013-01-26 12:01:23 -08:00
Unknown W. Brackets
7f4e322266 Cut thread switching time down.
Based on profiling release Windows.

Took these funcs from taking 1.6% to 0.5% time.
2013-01-26 11:29:20 -08:00
Unknown W. Brackets
a6094e25ff Get rid of waitTypeStrings and resched reason copy. 2013-01-26 11:29:20 -08:00
Unknown W. Brackets
1cb7a88137 Don't use a dynamic string for wait debugging.
Happens in release, and shows up on the profiler.
Not huge, but should save ~0.5% of cpu time.
2013-01-26 11:29:19 -08:00
Henrik Rydgård
88d484f028 Merge pull request #506 from unknownbrackets/jit-minor
Jit memory access cleanup + VFPU
2013-01-26 10:51:33 -08:00
Unknown W. Brackets
0e8e9697c5 Add lv.q/sv.q support to the x86 jit. 2013-01-26 10:09:18 -08:00
Unknown W. Brackets
b77ce99d01 Oops, no slow read for immediates usually. 2013-01-26 09:27:52 -08:00
Unknown W. Brackets
9cd5836b85 Rename WriteFinish() to Finish() is safe mem.
It's nothing to do with writing.
2013-01-26 09:09:47 -08:00
Unknown W. Brackets
3e419f513a Refactor jit safe memory reads without dup code.
But, maybe too automagical...
2013-01-26 08:42:34 -08:00
Henrik Rydgard
3126d17624 Change logging for PCM audio to INFO, as mentioned in Issue #505 2013-01-26 14:30:06 +01:00
Unknown W. Brackets
b7ef3e7bef Make sure to log / check bad immediate mem access.
Although, theoretically, this should never happen.
Also, definitely time to refactor.
2013-01-25 23:06:43 -08:00
Unknown W. Brackets
3418383917 Immediately break on bad mem access in jit slowmem. 2013-01-25 22:52:51 -08:00
Unknown W. Brackets
4bb515cab0 Don't log an incorrect pc for bad jit mem access. 2013-01-25 22:52:42 -08:00
Unknown W. Brackets
db5fa233a8 Make sure we don't mark a reg dirty on noop. 2013-01-25 22:34:01 -08:00
Henrik Rydgard
2738417040 VFPU JIT: start setting up infrastructure. very incomplete. vdot works if undisabled, but isn't complete. 2013-01-26 01:34:19 +01:00
Henrik Rydgard
68991511ee Split out the FPU reg cache into its own file too. 2013-01-26 01:34:19 +01:00
Henrik Rydgard
ad5e2b58c6 Separate the two regcaches before doing major surgery to FPURegCache. 2013-01-26 01:34:18 +01:00
Henrik Rydgård
be12d2efe3 Merge pull request #498 from lioncash/master
Fix a duplicate branch in Loaders.cpp
2013-01-25 16:07:51 -08:00
Lioncash
eb84b00a3d Fix a duplicate branch in MIPS/MIPSDis.cpp
Copypaste error for beql.

Thanks go out to [Unknown] for specifying the correct value of o.
2013-01-25 17:57:12 -05:00
Lioncash
e1aff1fd91 Fix duplicate branches.
I think this should be UNKNOWN_ELF.
2013-01-25 17:05:09 -05:00
Henrik Rydgård
67f849a442 Merge pull request #496 from lioncash/master
Memory leak cleanup. Fixing some small things that were fixed in the Dolphin source, but didn't make it over here.
2013-01-25 11:17:21 -08:00
Henrik Rydgard
dd149a50a3 Must flush FPR regcache before thrashing the fp regs 2013-01-25 19:55:30 +01:00
Henrik Rydgard
aabc0aa9ef Quick implementation of LV.Q and SV.Q in x86/x64 JIT 2013-01-25 19:50:30 +01:00
Lioncash
1cc74aa6c0 Get rid of unused iterators. 2013-01-25 13:11:06 -05:00
Henrik Rydgard
0930b5b587 Typo + warning fix 2013-01-25 19:08:28 +01:00
Henrik Rydgard
4deaec8924 Make ADPCM audio a little less crackly in a hacky way.. 2013-01-25 18:36:05 +01:00
Henrik Rydgard
31b73a0b99 No need for double precision in ADPCM decoder 2013-01-25 18:29:15 +01:00
Henrik Rydgard
8a32779150 Misc GPU stats etc changes 2013-01-25 18:29:14 +01:00
Unknown W. Brackets
6e6e71d116 Quick fix rtc crash, probably gives wrong results. 2013-01-25 08:34:04 -08:00
Unknown W. Brackets
1cd5421bdc Buildfix for missing functions on Android/win32. 2013-01-25 08:32:30 -08:00
Unknown W. Brackets
f102908f5d Fix crashes when localtime() can't handle the date. 2013-01-25 08:31:50 -08:00
Claus Østergaard
aa5996d028 File seek beyond file size should not fail
This caused Ridge Racer 2 to freeze after a few seconds
2013-01-25 13:13:32 +01:00
Henrik Rydgård
0c4b7905ac Merge pull request #488 from Xele02/sceRtc
Make sceRTC pass the tests.
2013-01-25 01:16:30 -08:00
Henrik Rydgård
0f080aeaaa Merge pull request #492 from unknownbrackets/jit-minor
ALU jit optimizations
2013-01-25 01:01:34 -08:00
Henrik Rydgård
d062e3cc83 Merge pull request #490 from unknownbrackets/jit-nice-delays
Nice delay slots, ahoy
2013-01-25 00:57:13 -08:00
Unknown W. Brackets
a7c6f46829 Optimize and/or 0 to just a mov in x86 jit. 2013-01-25 00:25:40 -08:00
Unknown W. Brackets
ab9bea068c Jit reg+reg compile time, and avoid flushing EDX. 2013-01-25 00:16:55 -08:00
Unknown W. Brackets
ce5f393fb8 Hit immediates in the ALU better and more simply. 2013-01-25 00:16:55 -08:00
Unknown W. Brackets
2748437032 Add support for FPU and VFPU for nice delay slots. 2013-01-24 20:18:18 -08:00
Unknown W. Brackets
f7ebddc4a3 Whitelist common delay slot ops with outreg info. 2013-01-24 19:59:33 -08:00
Unknown W. Brackets
d1909a1581 Add a quick disable define for nice delay slots. 2013-01-24 19:11:03 -08:00
raven02
7ccb87d11e Fix sound too fast issue 2013-01-25 08:48:28 +08:00
Xele02
0e69cd92c7 Make sceRTC pass the tests. 2013-01-25 01:40:38 +01:00
Unknown W. Brackets
75cbe18afc Simplify nice delay slot detect, and yes for noop.
NOOP seems very common so this should already benefit speed a bit.
2013-01-24 08:29:32 -08:00
raven02
3672214811 Comment int src 2013-01-24 23:43:26 +08:00
Unknown W. Brackets
2eba209f64 Move around the jit nice delay slot logic.
Nice delay slots don't not save flags, they run before the CMP.
2013-01-24 07:31:51 -08:00
raven02
faaa837ca2 Use u32 for leftVolume/rightVolume/format 2013-01-24 23:31:30 +08:00
raven02
2a1e366d33 Implement sceAudioSRCChReserve/Release/OutputBlocking 2013-01-24 23:29:49 +08:00