Commit graph

60 commits

Author SHA1 Message Date
Unknown W. Brackets
8daff0a25e armjit: Fix some downcount issues with rounding.
When setting the rounding mode we need to be super careful about not
destroying flags or R0 if they are needed.
2014-08-30 16:43:13 -07:00
Unknown W. Brackets
e9b5e6f277 armjit: Maintain rounding mode throughout jit. 2014-08-22 19:57:50 -07:00
Unknown W. Brackets
1fcbb7bbd4 armjit: Respect the rounding mode for mul/etc. 2014-08-22 00:32:01 -07:00
Unknown W. Brackets
0078faef8b Fix some log semicolons that might affect logic.
But, these should all be right.
2014-06-29 19:09:38 -07:00
Unknown W. Brackets
5a89c17cf0 armjit: Allow R1 in regalloc, use LR as temp.
LR should be safe, although it may make stack traces not work within jit,
they don't really tend to work anyway.
2014-03-28 18:38:38 -07:00
Unknown W. Brackets
05ab192c9c Reduce includes in Core/HLE/.
Especially templates.
2014-03-15 11:22:19 -07:00
Henrik Rydgard
1cb7965cb1 Jit feature preparation: Introduce "proxy blocks".
When these are invalidated, the block they point to gets invalidated too.

Will be useful to implement various types of block merging and function inlining
without affecting correctness of cache clears etc.

Also, with this commit we can now fully inline replaced functions. fabsf() boils
down to 1-2 instructions and the block continues, for example.
2013-12-19 00:39:49 +01:00
Unknown W. Brackets
763eff181d Fix handling of jalr when delay slot changes rd. 2013-11-14 23:39:13 -08:00
Henrik Rydgård
ef8631c57f Cache VFPU_CTRL_CC in a register 2013-11-12 17:58:29 +01:00
Henrik Rydgård
17074f5a7f Cache fpcond in a register to avoid store/load between compare and branch 2013-11-12 10:33:38 +01:00
Unknown W. Brackets
bb960480c8 x86/armjit: Stop compiling on a jump to invalid. 2013-11-10 21:59:50 -08:00
Unknown W. Brackets
359110f010 x86/armjit: Add jump following (off by default.)
Inlines function calls up to a certain extent.  Allows us to get
immediates all the way to a syscall, for example, usually.

Not sure if faster.
2013-11-10 21:59:49 -08:00
Unknown W. Brackets
aacb31bc18 armjit: Copy over (disabled) immbranch optim.
This does a little loop unrolling.  Costs a bit more cache space, but
avoids flushing regs for longer.

Not enabled.
2013-11-10 21:59:48 -08:00
Unknown W. Brackets
7e46ee0b0f armjit: Replace MOVI2R with using the regcache.
So that it can optimize the value with existing imms.

Not actually optimizing yet.
2013-11-10 15:50:45 -08:00
Unknown W. Brackets
1cc68f50ca armjit: Small optimization to syscall instr. 2013-11-10 14:38:10 -08:00
Unknown W. Brackets
b30928036e armjit: Avoid flushing an imm in beq/bne/etc.
We might be able to STMIA it instead.
2013-11-10 14:38:10 -08:00
Henrik Rydgard
5a95e267fb Add an optimization to discard registers at the end of functions when possible.
Works in some games but crashes many so hiding it for now. Do not add UI.
2013-11-08 12:43:48 +01:00
Henrik Rydgard
91393093bc Re-enable the "nice delay slot" optimization on ARM 2013-11-07 15:29:12 +01:00
Henrik Rydgård
1e158fa652 ARM vtx dec: Preserving our FP scratch register appears to improve
stability.

Also added some logging.
2013-11-06 11:47:26 +01:00
Henrik Rydgard
6483c0c2cd Two minor armjit optimizations 2013-11-05 16:25:01 +01:00
Unknown W. Brackets
732ae13ebb Fast path CallSyscall where possible.
It seems we're spending a decent amount of time there, which isn't
entirely unexpected.  We can eliminate some things easily.
2013-11-04 07:59:37 -08:00
Unknown W. Brackets
9a707f6c00 Fix typo, ARM build. 2013-10-17 15:28:50 -07:00
Unknown W. Brackets
2e8ef3027f Write the retaddr to rd, not always ra, in jalr.
Thanks go entirely to @Kingcom for pointing this out.

Don't know of any games not using RA as the rd.
2013-10-17 07:39:33 -07:00
Unknown W. Brackets
3a1b6fb269 Fix some sign comparison warnings. 2013-10-05 11:13:41 -07:00
Unknown W. Brackets
97aa1a631e Improve typesafety in the x86 regalloc. 2013-08-24 19:41:10 -07:00
Unknown W. Brackets
109ad17ac6 Use a typesafe struct for opcodes.
Also, correctly read delayslots using Read_Instruction on ARM.
2013-08-24 15:36:24 -07:00
Unknown W. Brackets
8327cd0f8e Clean up some inconsistency in jit branches on arm. 2013-08-16 02:02:56 -07:00
Unknown W. Brackets
2758634a0f Avoid overhead calling __KernelIdle().
~1.8% improvement in Zettai Hero Project.
2013-08-15 01:35:17 -07:00
Unknown W. Brackets
5387e5c717 Oops, typo. 2013-08-15 00:38:53 -07:00
Unknown W. Brackets
df50e03146 Add a safety log for cases we don't handle right. 2013-08-14 23:14:25 -07:00
Unknown W. Brackets
e639f8d15f Handle branches in VFPU delay slots better.
Based on tests on a PSP, all branches are attempted.  The behavior is
technically undefined.

It seems to take the delay slot's target if they differ and both pass.
This is the behavior the interpreter has, but it's more work in jit.

Since only a couple games seem to do this, and clearly expect this
behavior, this fixes all known cases of #1926.
2013-08-14 22:56:02 -07:00
Henrik Rydgard
76a937f489 ARMJIT Experiment: Keep downcount in a register. Needs benchmarking. 2013-07-27 17:27:26 +02:00
Unknown W. Brackets
c9c3bc83e4 Log more info about branches in delay slots. 2013-06-30 13:19:27 -07:00
Unknown W. Brackets
a640ac4001 Bail out on a delay slot in VFPU on arm also.
Otherwise we loop infinitely.

Workaround for #1926.  Should fix #1679.
2013-06-03 00:06:24 -07:00
Unknown W. Brackets
5595146f56 Add reporting for jumps in delay slots. 2013-05-26 20:30:14 -07:00
Henrik Rydgard
9eace8a80e Combine the two JitCache implementations (x86, ARM) into one. 2013-04-27 01:32:03 +02:00
Unknown W. Brackets
ed76563973 Don't bother checking nice, just do it after. 2013-03-11 02:18:27 -07:00
Unknown W. Brackets
b5fe67eb3d If the out is RA, delay slot isn't nice for jal.
Fixes Phantasy Star Portable 2 in jit.
2013-03-11 02:14:38 -07:00
Unknown W. Brackets
d525abbcad Cleanup some indentation, more compares to 0. 2013-03-07 02:08:45 -08:00
Unknown W. Brackets
028e85dc92 Cleanup some differences between the two jits. 2013-03-07 02:08:44 -08:00
Sacha
268d16bd24 Use correct args for STR(..) throughout armjit. 2013-03-07 00:59:07 +10:00
Henrik Rydgard
81589b67e5 Save one instruction on jal, shorten block exits by one instruction (moved to dispatcher). 2013-02-15 23:37:59 +01:00
Henrik Rydgard
048cf35922 More ARMJit FPU work - some instructions and optimizations. 2013-02-14 00:02:09 +01:00
Unknown W. Brackets
44b5adeaac Properly jit the break instruction.
Otherwise, it just keeps on going past it.
We never want to hit this anyway, but it's good to know if we do.
2013-02-01 00:49:14 -08:00
Henrik Rydgard
d8f4e27926 Rename ARMABI_MOVI2R to MOVI2R 2013-01-31 23:41:05 +01:00
Henrik Rydgard
c97f63a9d9 Minor armjit opt 2013-01-30 20:01:42 +01:00
Henrik Rydgard
739b76a55a Armjit: branch code cleanup #1 2013-01-30 01:05:36 +01:00
Unknown W. Brackets
dbe597ce64 Buildfix Android, darn. 2013-01-22 08:23:27 -08:00
Unknown W. Brackets
c324983340 Make the jit support bltzal and friends.
Fixes problems with jit in games.  Android changes completely untested.
2013-01-22 08:04:01 -08:00
Henrik Rydgard
bc9c3db303 Armjit: Add option for fastmem. Small optimization. 2013-01-11 17:25:54 +01:00