DeepBench

DeepBench copied to clipboard

run_mkl_igemm_ia.sh : numa error: node argument 1 is out of range

2

On ubuntu 16.04, when running ~/repos/DeepBench/code/intel/gemm/run_mkl_igemm_ia.sh on a single cpu machine (Intel(R) Core(TM) i7-6700HQ CPU @ 2.60GHz) : IGEMM benchmark GEMM_S8U8S32 - libnuma: node argument 1 is out of range...

WilliamTambellini

No BackwardWeights in RNNs

2

What is the reason for not incorporating/benchmarking `BackwardWeights` at least for NVIDIA? There is no use of `cudnnRNNBackwardWeights`.

dagamayank

Fail to compile on Ubuntu 16.4

1

os: ubuntu 16.4 GPU: Tesla V100-SXM2 *4 ,one node cuda:9.1 nccl: 2.1.15 cudnn:7.0 cmd: make CUDA_PATH=/usr/local/cuda CUDNN_PATH=/usr/lib/x86_64-linux-gnu MPI_PATH=/usr/local/openmpi-1.10.2_cuda9.1 NCCL_PATH=/usr/lib/x86_64-linux-gnu USE_TENSOR_CORES=1 ARCH=sm_70 while compile the benchmark, it met the error, just...

inspurasc

why mkl has much slower for backward than forward?

3

according to benchmark result, mkl's deep learning with convolution (not gemm) has a much slower backward speed than the forward pass. for example , for W=341, H=79,C=32,N=4, K=32, R=5, S=10,...

frankmanbb