foxhunt/crates/ml-alpha/build.rs

//! Pre-compile all ml-alpha CUDA kernels into arch-specific cubins.
//!
//! Per `feedback_no_nvrtc.md`: no runtime kernel compilation.
//! Per `pearl_build_rs_rerun_if_env_changed.md`: every `std::env::var`
//! is paired with `cargo:rerun-if-env-changed`.

use std::path::{Path, PathBuf};
use std::process::Command;

const KERNELS: &[&str] = &[
    "mamba2_alpha_kernel",          // Mamba2 SSM scan kernel (used by PerceptionTrainer's encoder prefix)
    "snap_feature_assemble",
    "cfc_step",
    "multi_horizon_heads",
    "projection",
    "bce_loss_multi_horizon",        // Kendall σ-weighted multi-horizon BCE (axis A)
    "adamw_step",
    "grad_norm",
    "horizon_lambda",                // ISV-driven per-horizon gradient scaler (EMA + lambda)
    "layer_norm",                    // Phase 1: trunk pre-CfC normalisation
    "variable_selection",            // Phase 2D: TFT-style per-feature gating
    "attention_pool",                // Phase 3: single-Q learned content summary at CfC k=0
    "reduce_axis0",                  // Phase B: cross-batch param-grad reducer
    "output_smoothness",             // CRT.train: per-horizon adjacent-position prob-jitter penalty
    "smoothness_lambda_controller",  // CRT.train: ISV-driven λ controller anchored on h30 jitter
    "gpu_log_ring",                  // GPU diagnostic log ring — tick kernel + log_record helper
    "bucket_transition_kernels",     // Per-horizon CfC Phase 1→2 transition: tau_sort, bucket_assign, bucket_iqr, channels_in_bucket, heads_compact, zero_off_bucket (ALPHA fix 2026-05-21)
    "cfc_step_per_branch",           // Per-horizon CfC Phase 2: fused per-(batch, branch) fwd + bwd over [25,25,25,25,28] buckets
    "heads_block_diagonal_fwd",      // Per-horizon CfC Phase 2: heads w_skip projection with compact ragged storage (640→128 floats)
    "aux_trunk",                     // SDD-3 Layer B3: smaller single-bucket CfC trunk (AUX_HIDDEN=64) for outcome-supervision (D-labels)
    "aux_heads",                     // SDD-3 Layer B4: per-direction linear regression heads on AuxTrunk output (long + short, N_AUX_HORIZONS each)
    "aux_loss",                      // SDD-3 Layer B4: Huber loss + grad for aux trade-outcome regression targets (NaN-masked)
    "aux_vec_add",                   // SDD-3 Layer B5: element-wise dst += src for aux→encoder gradient accumulation (lifted stop-grad)
    "dqn_distributional_q",          // RL Phase C: C51 distributional Q-head fwd + Bellman TD bwd for integrated RL trainer
    "rl_gamma_controller",           // RL Phase C: ISV controller emitting γ to ISV[RL_GAMMA_INDEX=400]
    "rl_target_tau_controller",      // RL Phase C: ISV controller emitting τ to ISV[RL_TARGET_TAU_INDEX=401]
];

// Cache bust v20 (2026-05-22): RL Phase C — dqn_distributional_q.cu (C51 fwd + categorical-CE bwd over 9 actions × 21 atoms), rl_gamma_controller.cu (γ→ISV[400], anchored on mean trade duration), rl_target_tau_controller.cu (τ→ISV[401], anchored on Q-divergence). Per pearl_controller_anchors_isv_driven, γ + τ are not constants — Wiener-α adaptive with first-observation bootstrap.

fn main() {
    println!("cargo:rerun-if-changed=build.rs");
    // Track shared headers so .cuh / .h edits trigger rebuilds of every
    // .cu that #includes them. Without these, an edit to a helper header
    // leaves a stale cubin.
    println!("cargo:rerun-if-changed=cuda/gpu_log_ids.h");
    println!("cargo:rerun-if-changed=cuda/gpu_log_helpers.cuh");

    println!("cargo:rerun-if-env-changed=CARGO_FEATURE_CUDA");
    if std::env::var("CARGO_FEATURE_CUDA").is_err() {
        eprintln!("  ml-alpha: cuda feature disabled, skipping kernel build");
        return;
    }

    println!("cargo:rerun-if-env-changed=CUDA_COMPUTE_CAP");
    println!("cargo:rerun-if-env-changed=CUDA_HOME");
    let cap = std::env::var("CUDA_COMPUTE_CAP").unwrap_or_else(|_| "80".to_string());
    let arch = format!("sm_{cap}");

    let nvcc = match find_nvcc() {
        Some(p) => p,
        None => {
            eprintln!("  ml-alpha: nvcc not found, skipping kernel build (set CUDA_HOME or install CUDA toolkit)");
            return;
        }
    };

    let out = PathBuf::from(std::env::var("OUT_DIR").expect("OUT_DIR not set by cargo"));

    for k in KERNELS {
        let src = PathBuf::from(format!("cuda/{k}.cu"));
        if !src.exists() {
            eprintln!("  ml-alpha: skipping {k} — source not yet present");
            continue;
        }
        println!("cargo:rerun-if-changed={}", src.display());
        let cubin = out.join(format!("{k}.cubin"));
        compile(&nvcc, &src, &cubin, &arch);
    }
}

fn compile(nvcc: &Path, src: &Path, cubin: &Path, arch: &str) {
    let status = Command::new(nvcc)
        .args([
            "-cubin",
            &format!("-arch={arch}"),
            "-O3",
            "--use_fast_math",
            "--ftz=true",
            "--fmad=true",
            "-o",
            cubin.to_str().unwrap(),
            src.to_str().unwrap(),
        ])
        .status()
        .unwrap_or_else(|e| panic!("nvcc spawn failed for {}: {e}", src.display()));
    if !status.success() {
        panic!(
            "nvcc failed for {} (exit {})",
            src.display(),
            status.code().unwrap_or(-1)
        );
    }
    eprintln!(
        "  ml-alpha: compiled {} -> {} ({arch})",
        src.display(),
        cubin.display()
    );
}

fn find_nvcc() -> Option<PathBuf> {
    if let Ok(home) = std::env::var("CUDA_HOME") {
        let p = PathBuf::from(home).join("bin/nvcc");
        if p.exists() {
            return Some(p);
        }
    }
    for cand in ["/usr/local/cuda/bin/nvcc", "/usr/bin/nvcc"] {
        let p = PathBuf::from(cand);
        if p.exists() {
            return Some(p);
        }
    }
    Command::new("nvcc")
        .arg("--version")
        .output()
        .ok()
        .filter(|o| o.status.success())
        .map(|_| PathBuf::from("nvcc"))
}