c++ - caffe cudnn version 4 & 5 -


i use cudnn acceleration in caffe program. use cudnn 4 @ begin , it's working fine when updated cudnn version 5.0, pow function doesn't work. calling function in batch_norm layer

caffe_gpu_powx(variance_.count(), variance_.gpu_data(), dtype(0.5), variance_.mutable_gpu_data()); 

and data after calling doesn't change. pow function defined below, same in caffe github banch

template <typename dtype> \__global__ void powx_kernel(const int n, const dtype* a,     const dtype alpha, dtype* y)  {      cuda_kernel_loop(index, n)      {                     y[index] = pow(a[index], alpha);        }   }  template <> void caffe_gpu_powx<float>(const int n, const float* a,     const float alpha, float* y) {     // nolint_next_line(whitespace/operators)     powx_kernel<float><<<caffe_get_blocks(n), caffe_cuda_num_threads>>>(       n, a, alpha, y); } 

i made mistake have set code generation "compute_52,sm_52" @ begin titan x, lower gpu should set "compute_20,sm_20". , it's working fine now.


Comments

Popular posts from this blog

asynchronous - C# WinSCP .NET assembly: How to upload multiple files asynchronously -

aws api gateway - SerializationException in posting new Records via Dynamodb Proxy Service in API -

asp.net - Problems sending emails from forum -