07d0e60fe4
- Fork cudarc locally (vendor/cudarc): add CudaContext::load_cubin() that calls cuModuleLoadData directly — zero nvrtc dependency - Remove "nvrtc" feature from ml-core, ml-dqn, ml-ppo Cargo.toml - Replace all 89 Ptx::from_binary + load_module calls with load_cubin - ml-core cuda_autograd: wire 9 stub constructors to precompiled cubins (activation, elementwise, linear, loss, reduction, dropout, layer_norm, optimizer) - ml-core build.rs: compile 8 BF16-native CUDA kernels via nvcc - cubin_loader.rs: thin wrapper around CudaContext::load_cubin() - Fix size_of::<f32> in gpu_tensor.rs, stream_ops.rs, layer_norm.rs - Fix test data: Vec<f32> → Vec<half::bf16> for memcpy_htod - Stub ml-ppo/ml-dqn runtime compile_ptx calls (dead code) - backtest_metrics_kernel.cu: full native BF16 rewrite (no float) - backtest_env_kernel.cu: shared memory → __nv_bfloat16 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
20 lines
450 B
Rust
20 lines
450 B
Rust
use cudarc::driver::{CudaContext, CudaSlice, DriverError};
|
|
|
|
fn main() -> Result<(), DriverError> {
|
|
let size = 10;
|
|
|
|
let ctx1 = CudaContext::new(0)?;
|
|
let stream1 = ctx1.default_stream();
|
|
let a: CudaSlice<f64> = stream1.alloc_zeros::<f64>(size)?;
|
|
|
|
let ctx2 = CudaContext::new(1)?;
|
|
let stream2 = ctx2.default_stream();
|
|
|
|
let b = stream2.clone_dtod(&a)?;
|
|
|
|
stream2.clone_dtoh(&b)?;
|
|
stream1.clone_dtoh(&a)?;
|
|
|
|
Ok(())
|
|
}
|