Benchmark #1585

Download
BORE vs SCX schedulers in Rocket League

First minute of match replay | No additional workload

Submitted 2 weeks ago by yubysowhat

Specifications
Label OS GPU CPU RAM OS specific
BORE Steam Runtime 3 (sniper) NVIDIA GeForce RTX 3060 Ti AMD Ryzen 7 5700X 8-Core Processor 34 GB 6.16.0-rc5-1-cachyos-rc-lto performance
Bpfland Steam Runtime 3 (sniper) NVIDIA GeForce RTX 3060 Ti AMD Ryzen 7 5700X 8-Core Processor 34 GB 6.16.0-rc5-1-cachyos-rc-lto performance
Chaos Steam Runtime 3 (sniper) NVIDIA GeForce RTX 3060 Ti AMD Ryzen 7 5700X 8-Core Processor 34 GB 6.16.0-rc5-1-cachyos-rc-lto performance
Flash Steam Runtime 3 (sniper) NVIDIA GeForce RTX 3060 Ti AMD Ryzen 7 5700X 8-Core Processor 34 GB 6.16.0-rc5-1-cachyos-rc-lto performance
LAVD Steam Runtime 3 (sniper) NVIDIA GeForce RTX 3060 Ti AMD Ryzen 7 5700X 8-Core Processor 34 GB 6.16.0-rc5-1-cachyos-rc-lto performance
p2dq Steam Runtime 3 (sniper) NVIDIA GeForce RTX 3060 Ti AMD Ryzen 7 5700X 8-Core Processor 34 GB 6.16.0-rc5-1-cachyos-rc-lto performance
# Top runs: * **Highest FPS**: `BORE` with a mean FPS marginally higher than the rest, showing its superior performance. * **Smoothest FPS**: `LAVD` demonstrated the lowest standard deviation and variance in FPS, indicating the most stable and consistent performance. * **Best overall**: `BORE` as it not only achieves the highest FPS but also maintains an acceptable level of stability among the runs. # Summary The benchmark comparison between the standard `bore` and various `sched_ext` implementations in Rocket League shows distinct differences in both frame rate performance and stability. `bore` stands out with the highest average FPS among all, suggesting it is highly optimized for this setup. However, when it comes to frame stability, the `scx_lavd` variant excels, showing the least variation in frame times and thus providing a smoother gameplay experience. This highlights how different scheduling strategies can significantly affect gaming performance, with `scx` schedulers offering different trade-offs between raw performance and stability.