devtools/eigen
1
0
Fork 0
mirror of https://gitlab.com/libeigen/eigen.git synced 2026-04-10 11:34:33 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix cuda device warnings

Browse Source
This commit is contained in:
Antonio Sanchez
2025-02-28 15:21:23 -08:00
parent c53002f5fb
commit 23b1682723
53 changed files with 655 additions and 600 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
test/cuda_common.h
View File

@@ -37,26 +37,26 @@ void run_on_cuda(const Kernel& ker, int n, const Input& in, Output& out)
typename Output::Scalar* d_out;
std::ptrdiff_t in_bytes = in.size() * sizeof(typename Input::Scalar);
std::ptrdiff_t out_bytes = out.size() * sizeof(typename Output::Scalar);
cudaMalloc((void**)(&d_in), in_bytes);
cudaMalloc((void**)(&d_out), out_bytes);
cudaMemcpy(d_in, in.data(), in_bytes, cudaMemcpyHostToDevice);
cudaMemcpy(d_out, out.data(), out_bytes, cudaMemcpyHostToDevice);
// Simple and non-optimal 1D mapping assuming n is not too large
// That's only for unit testing!
dim3 Blocks(128);
dim3 Grids( (n+int(Blocks.x)-1)/int(Blocks.x) );
cudaThreadSynchronize();
cudaDeviceSynchronize();
run_on_cuda_meta_kernel<<<Grids,Blocks>>>(ker, n, d_in, d_out);
cudaThreadSynchronize();
cudaDeviceSynchronize();
// check inputs have not been modified
cudaMemcpy(const_cast<typename Input::Scalar*>(in.data()), d_in, in_bytes, cudaMemcpyDeviceToHost);
cudaMemcpy(out.data(), d_out, out_bytes, cudaMemcpyDeviceToHost);
cudaFree(d_in);
cudaFree(d_out);
}