RPCSX/rpcsx
1
0
Fork 0
mirror of https://github.com/RPCSX/rpcsx.git synced 2026-01-01 06:10:00 +01:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity
9650 commits 5 branches 1 tag 150 MiB
Commit graph

341 commits

Author SHA1 Message Date
Nekotekina 71b71537a0 SPU TSX: implement Accurate PUTLLC option 
Allow spurious PUTLLC failure if disabled (default).
 2019-05-25 22:23:23 +03:00
Nekotekina b839cc9d5b SPU TSX: restore busy_wait in GETLLAR 2019-05-25 21:41:11 +03:00
Nekotekina 7de3c410cf SPU/PPU: update reservation logic on TSX path transactions 
Make use of lock bits in reservation counters.
On PPU, fallback to compare_and_swap instead of desperate retry.
On SPU, lighten write set on retry by 'locking' outside of the transaction.
 2019-05-20 14:32:50 +03:00
Nekotekina 9abb303569 vm: expand reservation lock bit area to 7 bit 
This is minor change.
 2019-05-19 17:46:55 +03:00
Nekotekina f33b81545e SPU: implement recompiler gateway function in assembly 
Use GHC calling convention directly for SPU object entry points.
This may address performance degradation after #5923.
 2019-05-14 22:15:04 +03:00
Nekotekina cc8c635855 SPU: PIC support preview 
SPU ASMJIT not supported yet.
Giga mode not supported properly.
 2019-05-14 22:15:04 +03:00
eladash 3a5f4ed757 Print SPU Group ID on the debugger 2019-04-20 20:43:58 +01:00
Nekotekina 9060177dbd SPU transactions: add SSE path if AVX is not available 
This handles hypothetical situation when AVX is disabled system-wise.
Also refactored register use, to match Windows path with Linux path.
This reduces read set a little at the cost of stack use.
 2019-04-16 23:49:18 +03:00
Nekotekina 3354f068fc PPU/SPU transactions: ease cache line interference (TSX path) 
Touch memory on the same memory page, but different cache lines.
 2019-04-10 13:58:12 +03:00
Nekotekina 71b88cdc82 New SPU interpreter (SPU fast) 
Use LLVM to build SPU interpreter.
Simplify interpreter loop.
 2019-03-27 20:33:44 +03:00
Nekotekina 4b381fbbb1 Implement spu_runtime::reset 
To handle JIT: Out Of Memory error.
 2019-03-23 02:43:41 +03:00
Nekotekina f143035af1 Fix sys_spu_thread_group_join wait condition 
After waiting, thread group cannot be safely accessed
Following #5643
 2019-03-01 00:08:19 +03:00
eladash 0861226271 Make more use of the new atomic_t<>::release 2019-02-10 00:16:57 +03:00
eladash e3ee481f01 Make sys_spu_thread_group_join return once per termination 2019-02-10 00:16:57 +03:00
Nekotekina 50922faac9 Remove SPUThread::jit_dispatcher 
Use global array - save memory
Move the array to JIT memory
 2019-01-29 03:32:16 +03:00
elad fc92ae4085 SPU/PPU atomics performance and LR event fixes (#5435) 
* Fix SPU LR event setting in atomic commands according to hw test
* MFC: increment timestamp for PUT cmd in non-tsx path
* MFC: fix reservation lost test on non-tsx path in regard to the lock bit
* Reservation notification moved out of writer_lock scope to reduce its lifetime
* Use passive_lock/unlock in ppu atomic inctrustions to reduce redundancy
* Lock only once for dma transfers (non-TSX)
* Don't use RDTSC in reservation update logic
* Remove MFC cmd args passing to process_mfc_cmd
* Reorder check_state cpu_flag::memory check for faster unlocking
* Specialization for 128-byte data copy in SPU dma transfers
* Implement memory range locks and isolate PPU and SPU passive lock logic
 2019-01-15 18:31:21 +03:00
eladash f19fd23227 spu: Fix support for multiple lists when one is stalled 2019-01-15 02:33:22 +03:00
Nekotekina cfdf50dcff SPU: ensure sys_spu_thread_group_join receives correct exit status 
Following #5334
 2019-01-13 14:45:36 +03:00
eladash 653a4ef0df Set group status INIT on last thread stopped 
this fixes the group status after sys_spu_thread_exit when not joining the spu group
 2018-12-25 19:59:41 +03:00
elad 90265edfcd SPU MFC: avoid copying of the lockline onto the stack in putllc/putlluc (#5392) 2018-12-04 21:09:55 +03:00
Nekotekina f442a8a84c SPU TG: add thread group stop counter 
Fix possible race condition introduced by waiting on `running` value
 2018-11-27 23:37:26 +03:00
Nekotekina febe4d4a10 Implement class cond_x16 
Use as reservation notifier
Limited to 16 threads but allows more precise control of contention
 2018-11-26 00:23:29 +03:00
Nekotekina 0044eb44e2 Cleanup after #5310 (SPU thread groups) 
Move lambda into a cpu_stop()
Use running thread counter to synchronize with sys_spu_thread_group_join()
Use SPU_STATUS_STOPPED_BY_STOP exclusively for sys_spu_thread_exit() as before
Remove unnecessary waiting in sys_spu_thread_group_exit()
Rollback some minor unnecessary changes
Use shared_mutex in SPU TG
 2018-11-14 12:50:24 +03:00
RipleyTom 0e0a82e536 Ensures threads are stopped in join 2018-11-13 10:19:28 +03:00
eladash 2e1aec4de8 Implement sys_spu_thread_tryreceive_event 2018-11-12 21:12:33 +03:00
Nekotekina 488928eca2 Fix SPU STOP instruction 
Check thread state after STOP instruction
 2018-11-05 14:35:50 +03:00
Nekotekina f06e6be2c1 Disable npc update for SPU thread groups 2018-11-05 13:14:11 +03:00
Nekotekina 1b37e775be Migration to named_thread<> 
Add atomic_t<>::try_dec instead of fetch_dec_sat
Add atomic_t<>::try_inc
GDBDebugServer is broken (needs rewrite)
Removed old_thread class (former named_thread)
Removed storing/rethrowing exceptions from thread
Emu.Stop doesn't inject an exception anymore
task_stack helper class removed
thread_base simplified (no shared_from_this)
thread_ctrl::spawn simplified (creates detached thread)
Implemented overrideable thread detaching logic
Disabled cellAdec, cellDmux, cellFsAio
SPUThread renamed to spu_thread
RawSPUThread removed, spu_thread used instead
Disabled deriving from ppu_thread
Partial support for thread renaming
lv2_timer... simplified, screw it
idm/fxm: butchered support for on_stop/on_init
vm: improved allocation structure (added size)
 2018-10-19 22:22:35 +03:00
Nekotekina a8a8cd88a0 Implement lf_queue<>, lf_value<> 
lf_queue<>: unbound FIFO queue with dynamic linked-list
lf_value<>: concurrently-assignable value readable without locking at the cost of memory (using dynamic linked list)

Add atomic_t<>::compare_exchange
 2018-09-27 12:16:43 +03:00
eladash 05cd3712a3 spu: Fix MMIO index checking 2018-09-17 17:24:54 +03:00
scribam d7bb59cd99 c++17: use std::size 2018-09-06 13:15:59 +03:00
Nekotekina ca5158a03e Cleanup semaphore<> (sema.h) and mutex.h (shared_mutex) 
Remove semaphore_lock and writer_lock classes, replace with std::lock_guard
Change semaphore<> interface to Lockable (+ exotic try_unlock method)
 2018-09-03 23:00:36 +03:00
Nekotekina 8abe6489ed Mega-cleanup for atomic_t<> and named bit-sets bs_t<> 
Remove "atomic operator" classes
Remove test, test_and_set, test_and_reset, test_and_complement global functions
Simplify atomic_t<> with constexpr if, remove some garbage
Redesign bs_t<> to use class, mark its methods constexpr
Implement atomic_bs_t<> for optimizations
Remove unused __bitwise_ops concept (should be in other header anyway)
Bitsets can now be tested via safe bool conversion
 2018-09-03 21:40:36 +03:00
eladash f349695a75 Rsx: rewrite address translation 2018-08-13 16:16:34 +03:00
eladash ac99fd764d mfc: clamp atomic cmd's addr 2018-07-14 01:40:40 +04:00
eladash a5d4e58ddd fix barrier type mfc transfers 2018-07-10 14:54:51 +04:00
Nekotekina 20900ebea2 SPU: rename block stats 
Use Block Weight and Retreats
 2018-07-06 00:33:52 +03:00
Nekotekina a0c0d8b993 SPU: simplify unimplemented event check 
Move checks closer to the actual use
 2018-07-06 00:33:52 +03:00
Nekotekina e4da284176 SPU: analyser v4 and fixes 
Build SPU cache after PPU, fix mixing progress
SPU ASMJIT: add support for Giga mode
SPU ASMJIT: use the same spu.log location as SPU LLVM
SPU: improve spu.log disasm
SPU: improve trampolines, unify with SPU ASMJIT
SPU: decode interrupt handler address from BR/BRA at 0x0
SPU LLVM: support Mega/Giga modes
SPU LLVM: implement function chunks
SPU LLVM: use PHI nodes, value visibility across basic blocks
SPU LLVM: implement function chunk table
New simple memory manager for LLVM (bugfix)
 2018-06-21 22:29:34 +03:00
eladash af62c92b7f mfc: clamp list transfer size 2018-06-17 23:20:00 +04:00
Nekotekina eb081bbcfa SPU: add 'Accurate PUTLLUC' option 
Effectively rollback previous PUTLLUC accuracy commit by default
Minor changes in GETLLAR/PUTLLUC transactions
 2018-06-12 02:09:22 +03:00
Nekotekina 12eee6a19e SPU ASMJIT: Implement Mega block mode (experimental) 
Disable extra modes for SPU LLVM for now.
In Mega mode, SPU Analyser tries to determine complete functions.
Recompiler tries to speed up returns via 'stack mirror'.
 2018-06-05 12:35:26 +03:00
Nekotekina ec6d1fb1ba SPU: optimize GETLLAR (TSX) 
Add an option "Accurate GETLLAR"
 2018-06-05 12:35:26 +03:00
Nekotekina a5f4e6ecef SPU: fix PUTLLUC accuracy 2018-06-04 16:01:17 +03:00
Nekotekina 759370ea1b SPU: rewrite FSM/FSMH/FSMB instructions 
Remove lookup tables
 2018-05-30 20:35:35 +03:00
Nekotekina 55e9d437a9 Fix warning (ignored attributes) 2018-05-30 20:35:35 +03:00
Nekotekina bdf6545571 SPU: rewrite spu_interpreter::SHUFB 
Use ASMJIT to generate SSSE3+ code at runtime
Remove static SSSE3 code from spu_interpreter
 2018-05-30 20:35:35 +03:00
kd-11 d48f391b41 lv2: Ease the pain of lower end CPUs 
- Avoid busy waiting in usleep code as much as possible, instead yield
- Also avoid busy_wait for SPU concurrency choker
 2018-05-29 13:54:30 +03:00
Nekotekina 3e580afe21 SPU: remove passive lock (fixup) 2018-05-23 15:36:29 +03:00
Nekotekina 72574b11ff SPU: use reservation spinlocks on writes (non-TSX) 
This should decrease contention by avoiding global lock
 2018-05-21 21:56:14 +03:00
Nekotekina 6fd402bcf8 Transactions: drop RDTSC usage 
Use simple increment (minor optimization)
 2018-05-21 00:18:37 +03:00
Nekotekina 7a6db3dd7e spu_getll_tx: diagnose loop count 2018-05-21 00:18:37 +03:00
Nekotekina 295f782b30 spu_putlluc_tx: diagnose loop count 2018-05-21 00:18:37 +03:00
Nekotekina a33f297315 Replace notifier::lock_shared() with try_lock_shared() 
Also add notify_one(), try_lock() and unlock()
Move some code in cond.cpp
 2018-05-21 00:18:37 +03:00
Nekotekina 8d5bbfb850 Update SPU dump: print current MFC cmd 2018-05-21 00:18:37 +03:00
Nekotekina 33a1c743a4 Transactions: move loops inside 
Rewrite loops in assembler (minor optimization)
 2018-05-21 00:18:37 +03:00
Nekotekina 67391322f4 Transactions: touch memory only after a failure 
Minor optimization
 2018-05-17 22:19:26 +03:00
Nekotekina 39088e5005 SPU: Allow waiting on LR+TM events (fixup) 2018-05-17 21:21:15 +03:00
Nekotekina 7afda26c69 spu_putllc_tx: preload a little more (WIN32) 2018-05-17 18:58:08 +03:00
Nekotekina 58e4d49bb5 Fixup (endless loop) 2018-05-17 18:33:44 +03:00
Nekotekina 367f039523 Build transactions at runtime 
Drop _xbegin family intrinsics due to bad codegen
Implemented `notifier` class, replacing vm::notify
Minor optimization: detach transactions from global mutex on TSX path
Minor optimization: don't acquire vm::passive_lock on PPU on TSX path
 2018-05-16 17:31:58 +03:00
Nekotekina 4c7afb6952 Opt-in set DAZ and FTZ 2018-05-13 00:03:08 +03:00
Nekotekina 737db90058 Set DAZ and FTZ 2018-05-09 23:38:26 +03:00
Nekotekina 8f91917e8c SPU ASMJIT: simplify patchpoints 
Remove SPU thread reference from spu_recompiler_base
Disable support for far jumps in pathpoints (they were rare and unsafe)
 2018-05-09 22:19:55 +03:00
Nekotekina 1ca51a023c SPU LLVM Recompiler (preview) 2018-05-09 22:19:55 +03:00
Nekotekina 767dfa271e SPU ASMJIT: internal jumptable 
Allow indirect calls within current function using a jumptable
This restores some functionality removed in SPU ASMJIT 2.0
Change SPUThread::get_ch_value prototype
 2018-05-08 13:05:29 +03:00
Nekotekina 4d60d85db5 SPU: fix MFC_PUTQLLUC_CMD fence trait 2018-05-08 13:05:29 +03:00
Nekotekina 9516250bec SPU: fix MFC_WrTagUpdate 2018-04-22 00:06:49 +03:00
Nekotekina 9ad5fc8a08 SPU: rewrite spu_channel_t 2018-04-22 00:06:49 +03:00
Nekotekina 8ca33bcb94 SPU ASMJIT v2.0 
Use X86Assembler and blocks
 2018-04-22 00:06:48 +03:00
Nekotekina ea82b732a3 SPU: fix non-TSX path 2018-04-08 23:30:50 +03:00
Nekotekina 0797164fac SPU: fix possible livelock 
The bug affects TSX path
 2018-04-07 20:51:21 +03:00
Nekotekina 3681507136 Rewrite vm::reservation 
Use flat virtual memory area
 2018-04-07 20:51:21 +03:00
Nekotekina 2b5cf2455f SPU: improve TSX usage 
Reduce transaction failure amount
Remove vm::try_to_lock
 2018-04-06 21:47:54 +03:00
Nekotekina d392379c7a Use vm::passive_lock for SPU threads 2018-04-06 15:47:00 +03:00
Nekotekina e88508b679 SPU: cache barrier/fence masks 2018-04-06 15:47:00 +03:00
Nekotekina 0e74f2e340 Fix MMIO on SPU 
Thanks Digitaldude555 for reporting the bug and @elad335 for pinging me
 2018-04-01 22:39:48 +03:00
Nekotekina d871675b3b Process RawSPU MMIO in do_dma_transfer 2018-04-01 22:39:48 +03:00
Nekotekina bb0cfe383d Fix MFC_SYNC_CMD 2018-04-01 20:52:54 +03:00
Nekotekina 898637f830 Remove mfc_thread 
Clear mfc_queue on reset
Improve MFC Proxy a bit
 2018-03-31 21:13:12 +03:00
eladash d27a375363 RawSPU/MFC: fix get start type proxy commands 2018-03-24 19:48:14 +04:00
eladash 3426531e38 qt/spu: remove max dma write size setting 
This wasn't really used for anything tbh
 2018-03-20 02:49:53 +04:00
Nekotekina 445b7c0758 Optimize SPU interpreter 
Made SPU decoder similar to PPU decoder
 2018-03-01 16:13:35 +03:00
elad b61a69c877 fix spu interpreter single stepping 2018-02-25 20:30:44 +04:00
Nekotekina cce0ad0c35 Clean vm::ps3 namespace use 2018-02-09 17:49:37 +03:00
elad 956ae17876 spu: add a missing STOP code 
should fix #2456
for whatever reason, this call accepts only an empty ouput mailbox, otherwise break
 2018-02-06 04:09:07 +04:00
kd-11 ab17b49e15 scheduler stuff 
- more threads for rsx
- better 1600
 2018-01-22 11:43:35 +03:00
kd-11 cbc8bf01a1 cell/scheduler: Manage thread placement depending on cpu hardware 2018-01-19 12:03:57 +03:00
elad 24e97b9e03 SPU: Allow writing to the WrSRR0 channel 2018-01-16 04:34:15 +04:00
elad 5848864f55 SPU: Allow reading of the RdSRR0 channel 
stupid bug
 2018-01-16 04:34:15 +04:00
Nekotekina 4aee4ed6d7 SPU: remove SSSE3 dependency 2017-12-20 00:04:08 +03:00
scribam 50f2be57f7 Spaces to tabs 2017-12-10 16:48:33 +04:00
Jake d17093e65b spu: Fix interrupt jump check - also change interrupt variable to atomic bool for ease of setting/checking 2017-12-01 20:29:59 +03:00
Jake 34e01ba3d8 mfc: Fix support for list transfer stall bit with partial support for out of order execution - Also give Sync commands a size so they are properly detected by queue checks 2017-12-01 20:29:59 +03:00
elad 91fd1465f2 SPU MFC: Clamp tag and size (#3803) 2017-11-29 16:28:41 +04:00
Jake 494cbac78b spu: save and restore mfc cmd after processing 2017-10-28 12:46:20 +03:00
Jake 0d46a8e786 spu: Implement readch(mfc_cmd) 2017-10-28 12:46:20 +03:00
Nekotekina 3a08dd7dde RawSPU: implement Prxy_TagStatus_offs 
Rollback to immediate MFC transfers
 2017-08-31 22:03:47 +03:00
kd-11 17c399d4e8 spu: acquire_pc rewritten to be more precise in timing 
- More accurate pauses may slightly reduce performance but makes it more viable
  to allow more threads to participate without stuttering
 2017-07-27 14:33:30 +03:00
Nekotekina b24eb621ae Use RTM instructions (skylake+) 2017-07-20 17:22:09 +03:00