Benchmarks found: 721
1440p highest. FPS capped to 500 with early to squash load screen spikes. Log hotkey set to R which also starts the benchmark.
By thisusernamechangethingisdumb1080p lowest. FPS capped to 500 with early to squash load screen spikes. Log hotkey set to R which also starts the benchmark.
By thisusernamechangethingisdumbRocket League | first minute of match replay | no additional workload | Ryzen 5700X | RTX 3060Ti | power profile balanced | kernel 6.15rc1
By yubysowhatRocket League | first minute of match replay | no additional workload | Ryzen 5700X | RTX 3060Ti | power profile balanced | kernel 6.15rc1
By yubysowhatRocket League | first minute of match replay | no additional workload | Ryzen 5700X | RTX 3060Ti | power profile balanced | kernel 6.15rc1
By yubysowhatMarvel Rivals Krakoa map replay used for consistency, CachyOS with sched-ext bpfland gaming profile and launch chain commands vs Windows 10 debloated and optimized for gaming using the new Marvel Rivals experimental switch shader compilation mode on or off. Windows 10 set up is using windows equivalent optimizations to launch chain like nvidia control panel competitive settings such as max frame queues.
By quackle_fpsWindows 10 Marvel Rivals Krakoa map, replay used for consistency, used experimental switch shader compilation on and off, focus on frametimes should be the main focus for competitive play. Marvel Rivals devs noted that experimental switch shader compilation on may cause game stuttering.
By quackle_fpsKrakoa map, replay used for consistency, BORE is with ananicy enabled and "out of the box" gaming experience like fresh CachyOS install for Linux noobs like me, while bpfland and lavd has ananicy disabled according to CachyOS wiki. Launch chain used for tests: env __GL_THREADED_OPTIMIZATIONS=1 __GL_YIELD="USLEEP" __GL_MaxFramesAllowed=1 DXVK_ASYNC=1 DXVK_FRAME_RATE=0 LD_PRELOAD="" mangohud game-performance %command%
By quackle_fps