Benchmarks found: 51
bpfland-next-9141da8 vs main-fc0d1bd, with stress -c $((4 * $(nproc))) in the background - adjusted so MangoHud doesn't start while game is still loading
By erikas2bpfland-next-9141da8 vs main-fc0d1bd, with stress -c $((4 * $(nproc))) in the background
By erikas2bpfland-next-9141da8 vs main-fc0d1bd on idle system
By erikas2Tested bpfland from bpfland-next branch, commit ID c8d6efa, under stress -c $((3 * $(nproc)))
By erikas2Tested bpfland from bpfland-next branch, commit ID c8d6efa, under idle system
By erikas2Last daily commits of past several days, in bpfland-next branch. Under stress -c $((3 * $(nproc))) command.
By erikas2Last daily commits of past several days, in bpfland-next branch. Under idle system.
By erikas2I've noticed in https://flightlesssomething.duckdns.org/benchmark/22 that --nvcsw-max-thresh 60 gave much higher FPS than the rest, so decided to double check this...
By erikas2scx_bpfland bruteforce of each parameter (bpfland-next, f80123c)
By erikas2Windows 11 vs CachyOS w/ scx_rusty. Metrics are taken from Afterbuner/RivaTuner and modified by hand to match MangoHud format, so CSVs can be uploaded for comparison.
By erikas2