Commit c7118e58 authored by xiabo's avatar xiabo
Browse files

Adapt to rocm

parent 95d5f333
...@@ -1675,7 +1675,8 @@ std::tuple<torch::Tensor, torch::Tensor, int> filtered_lrelu_op( ...@@ -1675,7 +1675,8 @@ std::tuple<torch::Tensor, torch::Tensor, int> filtered_lrelu_op(
int maxSharedBytes = 0; int maxSharedBytes = 0;
int result=cudaDeviceGetAttribute(&maxSharedBytes, int result=cudaDeviceGetAttribute(&maxSharedBytes,
// cudaDevAttrMaxSharedMemoryPerBlockOptin, // cudaDevAttrMaxSharedMemoryPerBlockOptin,
hipDeviceAttributeSharedMemPerBlockOptin, // hipDeviceAttributeSharedMemPerBlockOptin,
hipDeviceAttributeMaxSharedMemoryPerBlock,
x.device().index()); x.device().index());
int sharedKB = maxSharedBytes >> 10; int sharedKB = maxSharedBytes >> 10;
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment