Hi,
I have tried to implement gotvm as a GPU-accelerating deep learning runtime system on my edge computing architecture.
When I make gotvm without cuda, there is no error.
However, when I uncomment the cuda-related lines in tvm_runtime_pack.cc, the following errors are occurred.
$ make
# gotvm
/tmp/go-build192519998/b001/_x013.o: In function `tvm::runtime::CUDADeviceAPI::SetDevice(DLContext)':
tvm_runtime_pack.cc:(.text._ZN3tvm7runtime13CUDADeviceAPI9SetDeviceE9DLContext[_ZN3tvm7runtime13CUDADeviceAPI9SetDeviceE9DLContext]+0x2c): undefined reference to `cudaSetDevice'
tvm_runtime_pack.cc:(.text._ZN3tvm7runtime13CUDADeviceAPI9SetDeviceE9DLContext[_ZN3tvm7runtime13CUDADeviceAPI9SetDeviceE9DLContext]+0xb8): undefined reference to `cudaGetErrorString'
/tmp/go-build192519998/b001/_x013.o: In function `tvm::runtime::CUDADeviceAPI::GetAttr(DLContext, tvm::runtime::DeviceAttrKind, tvm::runtime::TVMRetValue*)':
....
tvm_runtime_pack.cc:(.text._ZNK3tvm7runtime21CUDAPrepGlobalBarrierclERKNS0_7TVMArgsEPNS0_11TVMRetValueE[_ZNK3tvm7runtime21CUDAPrepGlobalBarrierclERKNS0_7TVMArgsEPNS0_11TVMRetValueE]+0x1c0): undefined reference to `cuGetErrorName'
collect2: error: ld returned 1 exit status
Makefile:34: recipe for target 'all' failed
make: *** [all] Error 2
Is there anyone who succeeds to make gotvm when the cuda is enabled?
R. Kim