[singa] branch dev updated: multi process for mnist dataset

[zh...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

zhaojing pushed a commit to branch dev
in repository https://gitbox.apache.org/repos/asf/singa.git


The following commit(s) were added to refs/heads/dev by this push:
     new 208209a1 multi process for mnist dataset
     new aedc52ed Merge pull request #1033 from NLGithubWP/mulit_process
208209a1 is described below

commit 208209a1b72d1b8cb3b359d65293bfd2ebcb669c
Author: NLGithubWP <xi...@gmail.com>
AuthorDate: Fri Feb 17 11:01:16 2023 +0800

    multi process for mnist dataset
---
 .../autograd/mnist_multiprocess.py                 | 39 ++++++++++++++++++++++
 1 file changed, 39 insertions(+)

diff --git a/examples/largedataset_cnn/autograd/mnist_multiprocess.py b/examples/largedataset_cnn/autograd/mnist_multiprocess.py
new file mode 100644
index 00000000..f51344ff
--- /dev/null
+++ b/examples/largedataset_cnn/autograd/mnist_multiprocess.py
@@ -0,0 +1,39 @@
+#
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+#
+
+from mnist_cnn import *
+import multiprocessing
+import sys
+
+if __name__ == '__main__':
+
+    # Generate a NCCL ID to be used for collective communication
+    nccl_id = singa.NcclIdHolder()
+
+    # Number of GPUs to be used
+    world_size = int(sys.argv[1])
+
+    process = []
+    for local_rank in range(0, world_size):
+        process.append(
+            multiprocessing.Process(target=train_mnist_cnn,
+                                    args=(True, local_rank, world_size, nccl_id)))
+
+    for p in process:
+        p.start()