Options:
  Input size: N = 32, C = 64, H = 256, W = 256
  Output size: N = 32, K = 64, OH = 241, OW = 241
  Filter size: K = 64, C = 64, R = 16, S = 16
  Number of iterations: 1
  Validation: off

Initializing... done!
Initializing Convolution...
Calculating...(iter=0) 40.041388 sec
Avg. throughput: 97.343027 GFLOPS