Open
Description
I have a question about the runtime support that allows for the migration of the following cuda codes. Thanks.
auto pipe = cuda::make_pipeline();
// pipeline load W/X and compute WX;
pipe.producer_acquire();
cuda::memcpy_async(W_shared + (threadIdx.y * tx + threadIdx.x) * vec_size,
W + (idx * feat_out + j) * feat_in +
(threadIdx.y * tx + threadIdx.x) * vec_size,
cuda::aligned_size_t<W_copy_size>(W_copy_size), pipe);
cuda::memcpy_async(X_shared + (threadIdx.y * tx + threadIdx.x) * vec_size,
X + (batch_idx * feat_in) +
(threadIdx.y * tx + threadIdx.x) * vec_size,
cuda::aligned_size_t<X_copy_size>(X_copy_size), pipe);
pipe.producer_commit();