Commit graph

28727 commits

Author SHA1 Message Date
lizzie
48e033396d update loicense 2026-05-16 01:51:42 +00:00
lizzie
bb7b879f11 restore stupid lock, make ps4sup library 2026-05-16 01:51:42 +00:00
lizzie
1db3fb0879 bs fix 2026-05-16 01:51:42 +00:00
lizzie
4d4131f83c fix eboot 2026-05-16 01:51:42 +00:00
lizzie
332e0386c6 temp fix for dpad 2026-05-16 01:51:42 +00:00
lizzie
76ef75afb6 add emutls.c 2026-05-16 01:51:41 +00:00
lizzie
c5e014abaa reduce arm codeisze, force 16x4 pages again 2026-05-16 01:51:41 +00:00
lizzie
d7aee42379 extra buffer precautions to not exhaust DMem, format better + perf history nerf 2026-05-16 01:51:41 +00:00
lizzie
707754cdef more inline pt2 2026-05-16 01:51:41 +00:00
lizzie
e74ca4381c fix atexit impl 2026-05-16 01:51:41 +00:00
lizzie
9f9d130fa0 fibers that don't immediately crash?!!?!?!!? 2026-05-16 01:51:41 +00:00
lizzie
1db720173d add fallback buffer back 2026-05-16 01:51:41 +00:00
lizzie
ed230bba32 force running services on host 2026-05-16 01:51:41 +00:00
lizzie
56d60ab236 fix alloc failures 2026-05-16 01:51:41 +00:00
lizzie
aede8db560 fix sdl2 2026-05-16 01:51:41 +00:00
lizzie
c86887d7ff fix for crashes on TLS due to openorbis being W E I R D 2026-05-16 01:51:41 +00:00
lizzie
a59aeea2e2 opengl bullshit 2026-05-16 01:51:41 +00:00
lizzie
51e4e1ca32 proper memswap mechanism 2026-05-16 01:51:41 +00:00
lizzie
9033c5fceb more stupid stuff 2026-05-16 01:51:41 +00:00
lizzie
488aaea1d6 fixes 4 stuff 2026-05-16 01:51:41 +00:00
lizzie
efc44db9df swap handling 2026-05-16 01:51:41 +00:00
lizzie
fc3c706fd5 license 2026-05-16 01:51:41 +00:00
lizzie
db9571cc9f add sce_module so it loads on real hw 2026-05-16 01:51:41 +00:00
lizzie
1ceffefad1 fixes for mbedtls 2026-05-16 01:51:41 +00:00
lizzie
0b9a0966f2 adapt to new master 2026-05-16 01:51:40 +00:00
lizzie
c73e17f4f1 evil haxx 2026-05-16 01:51:30 +00:00
lizzie
c7169dfbb1 extra ps4 defs 2026-05-16 01:51:30 +00:00
lizzie
27f0d1add1 make virtual buffer become an optional 2026-05-16 01:51:29 +00:00
lizzie
48c0912bdd force NO fastmem 2026-05-16 01:51:29 +00:00
lizzie
88ad8917dc more memory shit 2026-05-16 01:51:29 +00:00
lizzie
0b1d7d39bc MAP_SYSTEM 2026-05-16 01:51:29 +00:00
lizzie
14dccb898f (likely) fixes for virtual dmem? 2026-05-16 01:51:29 +00:00
lizzie
5be4ad6b65 disable fastmem 2026-05-16 01:51:29 +00:00
lizzie
bcb9e1514c try to fix the paths 2026-05-16 01:51:29 +00:00
lizzie
a7cb95d921 sysconf stub cuz crash(?) + some stderrp stuff 2026-05-16 01:51:29 +00:00
lizzie
4ad405e785 the orb 2026-05-16 01:51:29 +00:00
lizzie
1868834646 fself + pkg stuffs 2026-05-16 01:51:29 +00:00
lizzie
b20c03a7af make .pkg and .self 2026-05-16 01:51:29 +00:00
lizzie
66463d6947 exclude more stuff from vulkan 2026-05-16 01:51:29 +00:00
lizzie
a4f3edec96 exclude from vulkan surface selection 2026-05-16 01:51:29 +00:00
lizzie
fe8fbec2e8 buildable toolchain script + fixes for ffmpeg 2026-05-16 01:51:27 +00:00
lizzie
b95c0092e9 merge 2026-05-16 01:51:07 +00:00
lizzie
85b45d5472 merge 2026-05-16 01:50:50 +00:00
lizzie
ca8f2dd5c4 fix 2026-05-16 01:50:38 +00:00
lizzie
248b34ff4b toolchain-fix 2026-05-16 01:49:53 +00:00
lizzie
4d49341918
[vk, opengl] recognize and use ETC2 (if available) textures natively (#3237)
Some checks are pending
tx-src / sources (push) Waiting to run
Check Strings / check-strings (push) Waiting to run
this makes it so VK and OGL backends map the NVIDIA's ETC2 into VK_FORMAT_ETC-whatever and GL_ETC-whatever remaps, instead of using the default fallback for AR8G8B8. in short, just make the ETC2 textures be submitted as ETC2 instead of being submit as A8R8G8B8.

Signed-off-by: lizzie lizzie@eden-emu.dev

Reviewed-on: https://git.eden-emu.dev/eden-emu/eden/pulls/3237
Reviewed-by: Ghost <>
Reviewed-by: crueter <crueter@eden-emu.dev>
2026-05-15 22:08:09 +02:00
lizzie
2f0f8a979c
[dynarmic, macroHLE] Use faster ankerl for xbyak maps (#3716)
the nominal std::unordered_map<> isn't enough to warrant it's continued usage in xbyak internal structures, thus using ankerl should greatly remove a lot of indirection/stdc++ specific overhead from the usually poorly performant std::unordered_map

Both dynarmic and macroHLE should benefit greatly from a less-stupid unordered_dense

This should speedup both CPU and shader compilation latency (NOT BY A GREAT MARGIN) just enough to make loading zones in ToTK less horrific

Signed-off-by: lizzie <lizzie@eden-emu.dev>
Reviewed-on: https://git.eden-emu.dev/eden-emu/eden/pulls/3716
Reviewed-by: crueter <crueter@eden-emu.dev>
2026-05-15 22:07:45 +02:00
lizzie
413c7543ba
[hle] inline HLE cmif request to not allocate on heap stuff (#3605)
so basically each construction of HLEContext and whatever would result in a heap allocation (atleast 1)

so what if instead of that we did a memset() at ctor time and we avoided heap allocations altogether?

reminder that std::vector<> CAN do small object optimisation but it's not guaranteed

Signed-off-by: lizzie <lizzie@eden-emu.dev>

Reviewed-on: https://git.eden-emu.dev/eden-emu/eden/pulls/3605
Reviewed-by: crueter <crueter@eden-emu.dev>
2026-05-15 22:07:03 +02:00
lizzie
975aa4e2f2
[common] remove ptr indirection on WallClock (#3864)
also devirtualizes manually since compiler doesn't do it with LTO

Signed-off-by: lizzie <lizzie@eden-emu.dev>

Reviewed-on: https://git.eden-emu.dev/eden-emu/eden/pulls/3864
Reviewed-by: crueter <crueter@eden-emu.dev>
2026-05-15 22:06:38 +02:00
lizzie
a1f9e68f46
[hid_core] remove contentious mutex from EmulatedController and just rely on atomic semantics for fields (#3866)
inputs shouldnt be that critical to require a full mutex of them

this relies on CPU guaranteeing u32/u16/u8 atomic load/stores for EmulatedController fields, which works on x86_64 but may not have the same behaviour on other architectures - thats why i wrap them in `std::atomic<>`

Signed-off-by: lizzie <lizzie@eden-emu.dev>
Reviewed-on: https://git.eden-emu.dev/eden-emu/eden/pulls/3866
Reviewed-by: crueter <crueter@eden-emu.dev>
2026-05-15 22:06:23 +02:00