preserve-emulation/ppsspp
1
0
Fork 0
mirror of https://github.com/hrydgard/ppsspp.git synced 2026-07-25 08:14:45 +02:00
Code Issues Packages Projects Releases Wiki Activity
45,601 Commits 76 Branches 131 Tags
https-linux-poc
Commit Graph
365 Commits
Author SHA1 Message Date
Unknown W. Brackets 757a1a414a arm64: Workaround an apparent gcc bug. 
Only seems to happen with unsigned.  This took a while to track down...
 2015-07-02 19:59:38 -07:00
Unknown W. Brackets e94fd3d4bd arm64: Fix div/divu remainders. 
Erp, I transposed the args when I pasted them.
 2015-06-28 16:52:49 -07:00
Unknown W. Brackets 81b923f1dc arm64: Correct movz/movn. Weren't right after all. 2015-06-28 16:49:28 -07:00
Unknown W. Brackets 4d7a948717 arm64: Fix a dump mistake with rounding modes. 2015-06-28 16:35:46 -07:00
Unknown W. Brackets b6612edf67 arm64: Use a cached rounding func for cvt.w.s. 
This is much faster for this particular instruction, although not all
games even use it.
 2015-06-28 12:40:29 -07:00
Unknown W. Brackets 1c163e4817 arm64: Avoid an ORR for c.ueq. 
This is about 15% faster for this single, uncommon instruction on A57.
 2015-06-28 10:52:17 -07:00
Unknown W. Brackets febe435946 arm64: Use FP load/stores for non-reg pointers. 2015-06-28 10:45:44 -07:00
Unknown W. Brackets 213ad4bcc9 arm64: Cleanup branch code a tiny bit. 
Want to make it clear that we can't kill W0 at this point (delay slots.)
 2015-06-28 09:28:54 -07:00
Unknown W. Brackets 0978aa4d5e arm64: Use msub for div/divu remainder. 
Not really much faster, but less instructions at least.
 2015-06-28 09:05:39 -07:00
Unknown W. Brackets 0a5b1c030b arm64: Implement ext and ins. 2015-06-28 08:45:17 -07:00
Unknown W. Brackets daddb73f22 arm64: Implement nor. 2015-06-28 00:41:04 -07:00
Unknown W. Brackets 11a851a139 arm64: Enable movz/movn. 2015-06-28 00:41:04 -07:00
Unknown W. Brackets 223e55a453 arm64: Undisable clz/clo, they work. 
Also, avoid a temp in clo.  It's the tiniest bit faster on A57, though
we'll see how it works out elsewhere.  A bit clearer without the temp
imho.
 2015-06-28 00:41:03 -07:00
Unknown W. Brackets 81bc8107cf arm64: Use UBFX, not LSR, for slti sign check. 
This is about 22% faster on the A57 (for just this one instruction, so not
a huge impact overall.)  Makes sense that it would be since not arith.
 2015-06-28 00:41:03 -07:00
Unknown W. Brackets fedbe645e0 arm64: Use all immediate compares in safemem. 
Ah, this is better.
 2015-06-27 00:22:09 -07:00
Unknown W. Brackets 3c29ec2051 arm64: Optimize codesize in safemem path a bit. 
Will only be used for scratchpad, I think.
 2015-06-27 00:22:04 -07:00
Unknown W. Brackets fbd4db0fc4 arm64: Add a safemem path. 
This is probably not optimal but at least it works.
 2015-06-27 00:22:04 -07:00
Unknown W. Brackets b3aa6d89e9 Fix UBFX encoding (thanks SonicAdvance1.) 2015-06-26 21:27:03 -07:00
Henrik Rydgard e848247f88 ARM64: Also save FP registers around the JIT dispatcher loop 2015-06-14 13:03:46 +02:00
Henrik Rydgard 2c05334d47 ARM64: Fix bug where we didn't save the FP registers correctly in the vertex decoder. 
Also port a few ops from dolphin's ARM64 emitter.
 2015-06-14 12:56:44 +02:00
Henrik RydgårdandUnknown W. Brackets 70fa830ba5 Split out the ReplaceJalTo test logic. 
This makes it so the IR, in the future, can work correctly for
replacements.
 2015-04-12 13:35:10 -07:00
Henrik RydgårdandUnknown W. Brackets d014d420db Unify JitOptions across the backends. 
This is required to make ExtractIR not a member of the various backends.
 2015-04-12 11:41:26 -07:00
Henrik RydgårdandUnknown W. Brackets 81dec36da8 Use an accessor to read the compilerPC. 
In the IR it will be read from the block.
 2015-04-11 01:14:37 -07:00
Henrik RydgårdandUnknown W. Brackets a897723e6a Separate out jit reading nearby instructions. 
This makes it easier to use an IR for these things, or remove them.
 2015-04-11 00:53:24 -07:00
Unknown W. Brackets b0d291032d armjit Avoid cfc1/mfc1 to $0. 2015-04-07 18:30:36 -07:00
Unknown W. Brackets 788b9d78f8 jit: Avoid a super unlikely write to zero. 2015-04-07 18:20:37 -07:00
Henrik Rydgård a8c2d0945a ARM64: lwl: Pass INVALID_REG to be sure SCRATCH1 doesn't get overwritten... 2015-04-06 18:13:41 +02:00
Henrik Rydgård 13c9390c53 ARM64: Emitter fix, disable swl/swr/lwl/lwr again fully 2015-04-06 18:13:38 +02:00
Henrik Rydgård fbaffdceab Remove some outdated comments, minor stuff 2015-04-06 18:13:36 +02:00
Henrik Rydgard 0a70618f87 ARM64: Accurate floating point rounding. For some reason, FTZ doesn't seem to work though. 2015-04-06 18:13:36 +02:00
Henrik Rydgard ad3d539451 ARM64: Attempt at lwl/lwr/swl/swr. The first two don't work 2015-04-06 18:13:35 +02:00
Henrik Rydgard 44286a2b37 ARM64: Accurate float->int conversion with rounding mode. 2015-04-06 18:13:34 +02:00
Henrik Rydgard acf08eefa8 ARM64: Fix FCVTL, use it in v2hf 2015-04-06 18:13:33 +02:00
Henrik Rydgard 8eedcc7fb0 ARM64: Speedup fpu/vfpu load/stores too using "pointerification". Actually noticeable gain. 2015-04-06 18:13:32 +02:00
Henrik Rydgard ad648baa9c ARM64 regcache: Add support to "pointerify" registers. Use in load/store to cut down instructions. 2015-04-06 18:13:32 +02:00
Henrik Rydgard 2780eef595 ARM64: Another couple of VFPU ops 2015-04-06 18:13:31 +02:00
Henrik Rydgard ca58f322e5 ARM64: Port over some missing VFPU instructions from ARM. Not much left now. 2015-04-06 18:13:30 +02:00
Henrik Rydgard f06e9a9d18 ARM64: Even more VFPU instructions 2015-04-06 18:13:30 +02:00
Henrik Rydgard 1b1ab73b0f ARM64: Enable some more VFPU instructions, some code cleanup 2015-04-06 18:13:29 +02:00
Henrik Rydgard 500ca94ab8 ARM64: Port over tons of VFPU code from ARM, leave most of it disabled. 2015-04-06 18:13:28 +02:00
Henrik Rydgard 8df8c210d1 ARM64: Start porting over VFPU stuff from ARM, fix regalloc bug 2015-04-06 18:13:28 +02:00
Henrik Rydgard 6cb107d6fc ARM64: Fix LDP disassembly 2015-04-06 18:13:25 +02:00
Henrik Rydgard 34e61ab875 ARM64: More FPU instructions (int<->float convert), minor stuff 2015-04-06 18:13:25 +02:00
Henrik Rydgard 25ec85551f ARM64: Implement FP compares, misc 2015-04-06 18:13:22 +02:00
Henrik Rydgard ceb9f66502 ARM64: Fix bug in mult 2015-04-06 18:13:21 +02:00
Henrik Rydgard 1a02e32ad1 ARM64: Implement the multiplication instructions 2015-04-06 18:13:20 +02:00
Henrik Rydgard a12e448fb4 ARM64: Stub vertex decoder jit, implementing just enough for the cube.elf cube. 2015-04-06 18:13:18 +02:00
Henrik Rydgard 57e759a605 ARM64: Fix and turn on basic block linking 2015-04-06 18:13:17 +02:00
Henrik Rydgard 5dff3f8c89 ARM64: Implement scalar FMOV. This makes the FPU2op ops work. 2015-04-06 18:13:16 +02:00
Henrik Rydgard 4233921ab7 ARM64: Some more instructions, func replacements 2015-04-06 18:13:16 +02:00