Jimmy7892 0f42ba865e bench: a 150,000-combination sweep on 200,000 bars, on the CPU and on a GPU ...

Both sweep benchmarks gain the point a GPU sweep is for. The CPU job runs
it on manifoldbt alone: vectorbt is out of scope as on the other large
points, and raptorbt is declared out of scope too, its loop measured at
14.8 ms a backtest, so about 37 minutes a call. The sweeps job gets 60
minutes instead of 45 for the ten or so this point adds. The reason
printed for raptorbt now names raptorbt: the sentence for an engine with
no grid API was written for NautilusTrader and would have said so.

The CPU job now asks for the CPU path by name. With the engine's default
device ("auto"), a workstation with a GPU and a licence that covers it
ran this job's sweeps on the card: 2.0 s for this point where the CPU
takes tens of seconds. The GitHub runner has no GPU, so no published
number was affected.

Measured: 2.79 s on a Modal L4 and 1.75 s on an RTX 3090, against 42 s on
four CPU threads of the same workstation, every cell bit-identical. The
Modal run grows from about 30 s to about 2.5 minutes, most of it the
untimed CPU parity run of this point.

Correction to 923559d: the local run whose data digests did not match the
CPU job's differed by platform, not by numpy version. Windows produces
other digests than Linux with the same numpy 2.4.3; the report keeps
refusing to pair them.

2026-10-25 12:08:01 +01:00

..

gpu

bench: a 150,000-combination sweep on 200,000 bars, on the CPU and on a GPU

2026-10-25 12:08:01 +01:00

vs_hft

bench: publish hft results from run 40024529245 [skip ci]

2026-10-23 21:35:28 +00:00

vs_vectorbt

bench: a 150,000-combination sweep on 200,000 bars, on the CPU and on a GPU

2026-10-25 12:08:01 +01:00

bench_backtrader_only.py

Initial commit: manifoldbt public repo

2026-03-17 16:15:40 +01:00

bench_vs_competitors.py

fix: benchmark timestamp ns, vectorbt trade count x2, remove fake perf numbers from README

2026-03-17 16:23:22 +01:00