Var = Rc<RefCell<VarNode>> on a define-by-run tape: value + optional grad + parents + backward closure. backward() seeds a scalar loss, walks reverse topo order, and pushes grads to parents. push_grad always SUMs into the grad slot — the fan-out accumulation path T3 lacked. Per-crate build.rs emits the no_cuda cfg (does not propagate); engine gated, grad_check stays host-only. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
28 lines
930 B
Rust
28 lines
930 B
Rust
use std::env;
|
|
use std::path::Path;
|
|
use std::process::Command;
|
|
|
|
// xtrain-autodiff's `Var` tape calls GPU ops (via xtrain-tensor), so it gates
|
|
// those call sites behind `not(no_cuda)` — the same per-crate convention as
|
|
// xtrain-cuda / xtrain-tensor (cfg does not propagate across crates). The
|
|
// grad_check harness itself is host-only and always compiles. This script only
|
|
// detects nvcc and emits the cfg; it compiles no CUDA.
|
|
fn main() {
|
|
println!("cargo:rustc-check-cfg=cfg(no_cuda)");
|
|
|
|
let cuda_path = env::var("CUDA_HOME")
|
|
.or_else(|_| env::var("CUDA_PATH"))
|
|
.unwrap_or_else(|_| "/usr/local/cuda".to_string());
|
|
|
|
if !nvcc_available(&cuda_path) {
|
|
println!("cargo:rustc-cfg=no_cuda");
|
|
}
|
|
}
|
|
|
|
fn nvcc_available(cuda_path: &str) -> bool {
|
|
if Command::new("nvcc").arg("--version").output().is_ok() {
|
|
return true;
|
|
}
|
|
Path::new(&format!("{cuda_path}/bin/nvcc")).exists()
|
|
}
|