33636d250b
build.rs compiles every .cu under crates/ml-backtesting/cuda/ to \$OUT_DIR/<name>.cubin via nvcc (no nvrtc per feedback_no_nvrtc.md); pairs every env::var with rerun-if-env-changed per pearl_build_rs_rerun_if_env_changed.md. Default arch sm_86 (RTX 3050 local); production sets FOXHUNT_CUDA_ARCH=sm_89 (L40S) or sm_90 (H100). First kernel: book_update_apply_snapshot — block-per-backtest replace of the 10-level book from a broadcast MBP-10 snapshot. Single-writer per level (thread tid = level idx), no atomics per feedback_no_atomicadd.md. lob_state.cuh defines the canonical per-block shared-mem layout that all subsequent kernels share (Book struct in this commit; Orders, Pos, IsvKellyState[5] added in C5-C7). LobSimCuda host struct (in src/sim.rs) constructed from an &MlDevice; owns per-backtest device book state + mapped-pinned input snapshots. apply_snapshot launches the kernel and synchronises; read_books drains device state for tests. Three Ring 1 fixture tests (book_update_replace, _two_step, _n_backtests=4) — N≤4 bit-exact GPU oracle assertions loaded from JSON. All three pass on RTX 3050 locally. Verifies the build-script → cubin → cudarc.load_cubin → kernel launch → DtoH read pipeline end-to-end. cudarc added as direct path dep (../../vendor/cudarc) since it's not in [workspace.dependencies] — same vendored fork ml-alpha uses. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
34 lines
961 B
TOML
34 lines
961 B
TOML
[package]
|
|
name = "ml-backtesting"
|
|
version.workspace = true
|
|
edition.workspace = true
|
|
rust-version.workspace = true
|
|
authors.workspace = true
|
|
license.workspace = true
|
|
repository.workspace = true
|
|
homepage.workspace = true
|
|
documentation.workspace = true
|
|
publish.workspace = true
|
|
keywords.workspace = true
|
|
categories.workspace = true
|
|
description = "ML backtesting framework + LOB simulator + per-horizon execution policy"
|
|
|
|
[dependencies]
|
|
ml-core.workspace = true
|
|
ml-alpha = { path = "../ml-alpha" } # loader + trunk reuse — see real-LOB spec §1
|
|
cudarc = { path = "../../vendor/cudarc" } # CUDA bindings — same vendored fork as ml-alpha
|
|
serde = { workspace = true, features = ["derive"] }
|
|
serde_json.workspace = true
|
|
chrono.workspace = true
|
|
anyhow.workspace = true
|
|
csv.workspace = true
|
|
bytemuck = { workspace = true, features = ["derive"] }
|
|
tracing.workspace = true
|
|
thiserror.workspace = true
|
|
|
|
[dev-dependencies]
|
|
tempfile = "3.12"
|
|
|
|
[lints]
|
|
workspace = true
|