Gahow Wang
08c88bf360
Hand-written tiled GEMM (csrc/ops/gemm.cu, TILE_SIZE=32, FP32 accumulate, boundary-masked) plus an out-of-place transpose kernel. Wire both through xtrain-cuda FFI (no_cuda-gated) and expose at the tensor level: Tensor::matmul, transpose_2d, and matmul_backward computing dA = dC·Bᵀ and dB = Aᵀ·dC by materializing transposes and reusing the forward. Also declare cuBLAS sgemm FFI + link cublas, used only as a correctness reference in tests. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
44 lines
1.5 KiB
Rust
44 lines
1.5 KiB
Rust
use std::env;
|
|
use std::path::Path;
|
|
use std::process::Command;
|
|
|
|
fn main() {
|
|
println!("cargo:rustc-check-cfg=cfg(no_cuda)");
|
|
println!("cargo:rerun-if-changed=../../csrc/");
|
|
|
|
let cuda_path = env::var("CUDA_HOME")
|
|
.or_else(|_| env::var("CUDA_PATH"))
|
|
.unwrap_or_else(|_| "/usr/local/cuda".to_string());
|
|
|
|
// Locally there is no nvcc / GPU. Detect that and skip the CUDA build so
|
|
// `cargo check`/`cargo build` of host-side Rust still works. The `no_cuda`
|
|
// cfg makes the FFI bindings + smoke test compile (but not run) without nvcc.
|
|
if !nvcc_available(&cuda_path) {
|
|
println!("cargo:warning=nvcc not found — skipping CUDA compilation (host-only build).");
|
|
println!("cargo:rustc-cfg=no_cuda");
|
|
return;
|
|
}
|
|
|
|
println!("cargo:rustc-link-search=native={cuda_path}/lib64");
|
|
println!("cargo:rustc-link-lib=dylib=cudart");
|
|
println!("cargo:rustc-link-lib=dylib=cuda");
|
|
// cuBLAS is used only as a correctness reference for the hand-written GEMM.
|
|
println!("cargo:rustc-link-lib=dylib=cublas");
|
|
|
|
cc::Build::new()
|
|
.cuda(true)
|
|
.cudart("shared")
|
|
.flag("-gencode=arch=compute_120,code=sm_120")
|
|
.file("../../csrc/test/vecadd.cu")
|
|
.file("../../csrc/ops/elementwise.cu")
|
|
.file("../../csrc/ops/gemm.cu")
|
|
.compile("xtrain_cuda_kernels");
|
|
}
|
|
|
|
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()
|
|
}
|