RPCSX/rpcsx
1
0
Fork 0
mirror of https://github.com/RPCSX/rpcsx.git synced 2025-12-06 07:12:14 +01:00
Code Issues Actions Packages Projects Releases Wiki Activity
11245 commits 5 branches 1 tag 150 MiB
Commit graph

64 commits

Author SHA1 Message Date
Nekotekina 3ac819ee70 atomic.cpp: fix waiting on multiple variables 
Silly bugs are so silly...
 2020-11-14 17:25:02 +03:00
Nekotekina 00f877e812 atomic.cpp: fix rare overload scenario 
If slot allocation fails, increase reference counter in every slot.
This prevents search routine from "losing" some slots.
 2020-11-14 13:56:23 +03:00
Nekotekina e48f160a29 atomic.cpp: continuation of fixing all-ones masks 
Also added missing const noexcept.
 2020-11-13 12:40:02 +03:00
Nekotekina cfda4d0ade atomic.cpp: optimize raw_notify() for unspecified pointer mode 
Remove unnecessary optimization from cond_alloc().
Optimistic case was absolutely dominating anyway.
Although the whole function is a dirty hack.
Now scanning through all threads is faster.
 2020-11-13 07:05:33 +03:00
Nekotekina 3888b0429c atomic.cpp: print some stats on stop 2020-11-12 05:52:22 +03:00
Nekotekina 70761a4ef0 atomic.cpp: fix notification bug from few commits before 
Make sure forced notification ignores mask comparison.
Also fix masks provided by smaller types to correct ones.
 2020-11-12 05:01:44 +03:00
Nekotekina e37df998e9 atomic.cpp: minor optimization 
Silly MSVC emits unnecessary initialize-on-first-use code guards.
Didn't check other compiler. But workaround just works anyway.
 2020-11-12 03:41:19 +03:00
Nekotekina c30cdfb3a7 atomic.cpp: merge more atomic variables for simplicity 
Compress 16-bit ref counter and two 48+64 bit slot allocators.
This allowed to remove some weird unnecessary logic paths.
Adjust hashtable size to keep it the same.
 2020-11-12 03:39:05 +03:00
Nekotekina 350b704cd7 atomic.cpp: combine two atomics (ref ctr and wait ptr) 
Should fit into cache line perfectly.
Also makes ptr check more robust.
 2020-11-12 01:06:12 +03:00
Nekotekina ad013d59f4 atomic.cpp: don't load actual memory on empty mask 
It's not an optimization. It just allows some tricks safely.
 2020-11-11 23:59:09 +03:00
Nekotekina d391133524 atomic.cpp: minor notification improvement 
Check mask before locking the reference.
Can help to not bother non-eligible waiters.
 2020-11-11 23:51:41 +03:00
Nekotekina 4b823469f7 atomic.cpp: restore notify_all() behaviour 
Restore batch notification with non-blocking attempts.
 2020-11-11 22:43:13 +03:00
Nekotekina 7cd1e767be atomic.cpp: implement some atomic wait operations. 
Instead of plain waiting while equal to some value,
it can be something like less, or greater, or even bitcount.
But it's a draft and untested. Hopefully doesn't break anything.
 2020-11-11 20:46:37 +03:00
Nekotekina c047ab6147 atomic.cpp: waitable atomics got brutally rewritten 
Hashtable increased and flatten, tree-alike extensions removed.
Some things simplified, so it can actually decrease perf a bit.
But most platforms shouldn't be affected.
Removed limit of 56 waiters per pointer.
Real limit now is about 65535.
 2020-11-11 05:35:27 +03:00
Nekotekina fd7ea82965 atomic.cpp: fix 3-arg notify functions 
Third arg forces comparison with itself, and possibly forced wakeup.
 2020-11-07 19:18:14 +03:00
Nekotekina 0bd989b118 atomic.cpp: allow waiting on multiple variables simultaneously 
Arbitrary maximum set to 8, but really we need 2, maybe 3.
Added atomic_wait::list object for multi-waiting.
Added atomic_wait::get_unique_tsc just in case.
 2020-11-07 18:18:02 +03:00
Nekotekina bd0b292b39 atomic.cpp: adjust assumed pointer mask 
Increase waiter mask (allow 65535 waiters).
Assume 47-bit pointers instead of 48-bit.
 2020-11-07 15:08:46 +03:00
Nekotekina 31f0a0c064 atomic.cpp: add minor safety check 2020-11-07 15:08:46 +03:00
Nekotekina 3e445eff8e atomic.cpp: maintenance of wait() function 
Move hashtable allocation into another function.
 2020-11-07 15:08:46 +03:00
Nekotekina 0a5742587a atomic.cpp: upgrade raw_notify() 
Now it searches all semaphores if data arg is nullptr.
Also it tries to wake up all threads if thread_id is 0.
 2020-11-06 17:15:40 +03:00
Nekotekina ad4df2d946 atomic.cpp: refactor native signaling functions 
Add native_alert() and try_native_alert()
 2020-11-06 17:15:40 +03:00
Nekotekina bfe9580551 atomic.cpp: fix cond_handle data structures 
Fix a critical bug with possible id out of range.
 2020-11-06 16:56:59 +03:00
Nekotekina 557f0c5a8a atomic.cpp: remove load() from notify functions 
Only compare masks for overlap for second overload (with mask provided).
Explicit "new value" can be provided in new 3-arg overloads.
Also rename atomic_storage_futex -> atomic_wait_engine.
 2020-11-06 04:44:31 +03:00
Nekotekina 9fb8d449fe atomic.cpp: more improvements 
Add ref counters for internal semaphores for concurrent notifying.
Lack of them could result in loss of notification.
 2020-11-06 00:14:53 +03:00
Nekotekina 1bb7c74c93 atomic.cpp: various cleanups and fixes 
Add pointer comparison to notifiers (to prevent spurious wakeups).
Fix a bug with a possible double notification in raw_notify().
Fix a bug with incorrect allocatin bit slots for cond_handle.
Add a semaphore counter to track max allowed number of threads.
Use #define for some constants to STRINGIZE them in errors.
Add some error messages when certain limits are reached.
Fix a bug with a wrong check simply throwing std::abort.
Use "special" notify_all patch with batch processing for every arch.
Fix Win7 bug who no one probably noticed.
 2020-11-06 00:10:16 +03:00
Nekotekina 5248240e10 atomic.cpp: improvements. 
Reduced static memory amount for waitable atomics.
Allow notifier to skip notifications if wait/notify masks don't overlap.
Improve raw_notify to wake up the thread by its id, add thread_id arg.
Add optional mask argument to notify_one() and notify_all().
 2020-11-05 05:51:43 +03:00
Nekotekina c50233cc92 atomics.cpp: add support for waiting on 128-bit atomics 
Complementarily.
Also refactored to make waiting mask non-template arg.
 2020-10-28 03:47:41 +03:00
Nekotekina 6806e3d5c7 atomic.cpp: implement notify callback 
Notification can be very heavy, especially if we need to wake many threads.
Callback is set for cpu_thread in order to set wait flag accordingly.
 2020-10-27 17:56:19 +03:00
Nekotekina d344701fd5 atomic.cpp: add sparse atomics 
Set alignment as second template argument (typically cache line).
 2020-10-26 01:15:31 +03:00
Nekotekina af6fcb19a8 atomic.cpp: add std primitive fallback for other platforms 
Other platforms = not Windows or Linux.
 2020-10-25 16:45:22 +03:00
Nekotekina 7db77a5580 atomic.cpp: use new thread alerting API (Win8+) 
Win7 will remain using old API (keyed events).
 2020-10-24 19:06:02 +03:00
Nekotekina c479d431a4 atomic.cpp: experimental optimization (Win7+) 
Try non-blocking wake up function first.
 2020-10-24 14:16:32 +03:00
Nekotekina 8628fc441d atomic.cpp: rewrite internals (again) 
Use individual semaphore for each thread.
Unfortunately, limit max thread waiting for single address (60).
If limit is reached, use busy waiting.
 2020-10-24 14:16:32 +03:00
Nekotekina d48d67767a atomic.cpp: integrate callback check in ptr_cmp function 2020-10-24 14:16:32 +03:00
Nekotekina 59d9e7ce98 Revert "Atomics: use WaitOnAddress if available (Win8+)" 
This reverts commit f0fd7e2e19.
 2020-10-21 09:59:08 +03:00
Nekotekina 306593a0c5 Revert "atomic.cpp: fixup for WaitOnAddress path" 
This reverts commit 3b8bce1bed.
 2020-10-21 09:54:22 +03:00
Nekotekina 3b8bce1bed atomic.cpp: fixup for WaitOnAddress path 
Also fix wait quantum.
 2020-10-21 08:18:27 +03:00
Nekotekina f0fd7e2e19 Atomics: use WaitOnAddress if available (Win8+) 2020-10-21 00:22:08 +03:00
Eladash 17c8b34088
atomic.cpp: Optimize sema_get to not always use atomic instruction (#8907) 2020-09-16 22:15:14 +03:00
Eladash fe9c61fe73 atomic.hpp: Fix atomic_storage_futex::raw_notify 2020-09-12 22:11:40 +03:00
Nekotekina 032e7c0491 Replace utils::cntlz{32,64} with std::countl_zero 2020-04-14 16:05:58 +03:00
Nekotekina d0c199d455 Replace utils::cnttz{32,64} with std::countr_{zero,one} 
Make #include <bit> mandatory.
 2020-04-14 16:05:58 +03:00
Nekotekina Aux1 250736ece5 Fix warnings in emucore 2020-03-04 21:23:34 +03:00
Nekotekina ec1ea466fd atomic.hpp: fix typo 2019-10-23 16:01:14 +03:00
Nekotekina b844cd81e8 atomic.hpp: remove <string> dependency 2019-10-20 23:06:17 +03:00
Nekotekina 2dde133e1f atomic.hpp: fix internal resource deallocation 
Also remove debug printf.
 2019-10-20 23:06:17 +03:00
Nekotekina 4d46e66833 atomic.hpp: improve internal data layout 
Put semaphore control variable together in hashtable.
Avoid unnecessary allocation of extents.
 2019-10-20 20:08:09 +03:00
Nekotekina 56b310ebac atomic.hpp: reimplement USE_FUTEX path for Linux 2019-10-20 20:05:36 +03:00
Nekotekina e0f60c5dce atomic.hpp: rewrite collision handling 
Remove "fallback" code path.
Remove USE_FUTEX code path temporarily.
 2019-10-20 18:29:20 +03:00
Nekotekina db7042b986 Restore using keyed events in waitable atomics on Windows 2019-10-18 23:08:00 +03:00