bsyu/caffe repository overview

root@minsky:/data/mydocker# vi dockerfile.caffe FROM bsyu/p2p:ppc64le-xenial

⁠RUN executes a shell command

⁠You can chain multiple commands together with &&

⁠A \ is used to split long lines to help with readability

⁠This particular instruction installs the source files

⁠for deviceQuery by installing the CUDA samples via apt

RUN apt-get update && apt-get install -y cuda

RUN mkdir /tmp/temp COPY libcudnn5* /tmp/temp/ COPY cuda-repo-* /tmp/temp/ COPY mldl-repo-local_1-3ibm5_ppc64el.deb /tmp/temp/

RUN dpkg -i /tmp/temp/cuda-repo-ubuntu1604-8-0-local_8.0.44-1_ppc64el.deb &&
dpkg -i /tmp/temp/libcudnn5_5.1.5-1+cuda8.0_ppc64el.deb &&
dpkg -i /tmp/temp/libcudnn5-dev_5.1.5-1+cuda8.0_ppc64el.deb &&
dpkg -i /tmp/temp/mldl-repo-local_1-3ibm5_ppc64el.deb &&
rm -rf /tmp/temp &&
apt-get update && apt-get install -y caffe-nv libnccl1 &&
rm -rf /var/lib/apt/lists/*

⁠set the working directory

WORKDIR /opt/DL/caffe-nv/bin ENV LD_LIBRARY_PATH="/opt/DL/nccl/lib:/opt/DL/openblas/lib:/opt/DL/nccl/lib:/usr/local/cuda-8.0/lib6:/usr/lib:/usr/local/lib"

⁠CMD defines the default command to be run in the container

⁠CMD is overridden by supplying a command + arguments to

⁠docker run, e.g. nvcc --version or bash

CMD ./caffe

root@minsky:/data/mydocker# docker build -t bsyu/caffe:ppc64le-xenial -f dockerfile.caffe .

root@minsky:/data/mydocker# nvidia-docker run --rm -v /nvme:/nvme bsyu/caffe:ppc64le-xenial ./caffe train -gpu 0,1,2,3 --solver=/nvme/solver.prototxt I0202 02:27:22.200032 1 caffe.cpp:197] Using GPUs 0, 1, 2, 3 I0202 02:27:22.201119 1 caffe.cpp:202] GPU 0: Tesla P100-SXM2-16GB I0202 02:27:22.201659 1 caffe.cpp:202] GPU 1: Tesla P100-SXM2-16GB I0202 02:27:22.202191 1 caffe.cpp:202] GPU 2: Tesla P100-SXM2-16GB I0202 02:27:22.202721 1 caffe.cpp:202] GPU 3: Tesla P100-SXM2-16GB I0202 02:27:23.986641 1 solver.cpp:48] Initializing solver from parameters: ... I0202 02:27:28.246285 1 parallel.cpp:334] Starting Optimization I0202 02:27:28.246449 1 solver.cpp:304] Solving AlexNet I0202 02:27:28.246492 1 solver.cpp:305] Learning Rate Policy: step I0202 02:27:28.303807 1 solver.cpp:362] Iteration 0, Testing net (#0) I0202 02:27:44.866096 1 solver.cpp:429] Test net output #0: accuracy = 0.000890625 I0202 02:27:44.866148 1 solver.cpp:429] Test net output #1: loss = 6.91031 (* 1 = 6.91031 loss) I0202 02:27:45.356459 1 solver.cpp:242] Iteration 0 (0 iter/s, 17.1098s/200 iter), loss = 6.91465 I0202 02:27:45.356503 1 solver.cpp:261] Train net output #0: loss = 6.91465 (* 1 = 6.91465 loss) I0202 02:27:45.356540 1 sgd_solver.cpp:106] Iteration 0, lr = 0.01 ...