Gahow Wang
d77f921a12
- Naive GEMM kernel: one thread per output element (F32 + BF16) - Tiled GEMM kernel: 32x32 shared memory tiles (F32 + BF16) - cuBLAS wrapper: cublasGemmEx with row-major trick - GemmBackend enum for runtime backend selection - CublasContext RAII handle - Made error::check public for cross-crate use - 17 GEMM tests: small/medium/rect sizes, all backends, F32+BF16 - Cross-backend consistency verified (naive vs tiled vs cuBLAS) - All 44 tests pass across all crates Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
22 lines
649 B
Rust
22 lines
649 B
Rust
use std::env;
|
|
|
|
fn main() {
|
|
let cuda_path = env::var("CUDA_HOME")
|
|
.or_else(|_| env::var("CUDA_PATH"))
|
|
.unwrap_or_else(|_| "/usr/local/cuda".to_string());
|
|
|
|
println!("cargo:rustc-link-search=native={cuda_path}/lib64");
|
|
println!("cargo:rustc-link-lib=dylib=cudart");
|
|
println!("cargo:rustc-link-lib=dylib=cublas");
|
|
|
|
cc::Build::new()
|
|
.cuda(true)
|
|
.cudart("shared")
|
|
.flag("-gencode=arch=compute_120,code=sm_120")
|
|
.file("../../csrc/gemm/naive.cu")
|
|
.file("../../csrc/gemm/tiled.cu")
|
|
.compile("xserv_gemm_kernels");
|
|
|
|
println!("cargo:rerun-if-changed=../../csrc/gemm/");
|
|
}
|