From 596ee153016a39fad2a1cb187b584e7263eb4e8e Mon Sep 17 00:00:00 2001
From: "github-actions[bot]"
 <41898282+github-actions[bot]@users.noreply.github.com>
Date: Mon, 16 Sep 2024 15:26:57 +0200
Subject: [PATCH] Create rule S6983 (#3973)

* Create rule S6983

* Address review comments

* Review comments 2

* Add tags

---------

Co-authored-by: ghislainpiot <ghislainpiot@users.noreply.github.com>
Co-authored-by: Ghislain Piot <ghislain.piot@sonarsource.com>
---
 rules/S6983/metadata.json        |  2 +
 rules/S6983/python/metadata.json | 25 ++++++++++++
 rules/S6983/python/rule.adoc     | 70 ++++++++++++++++++++++++++++++++
 3 files changed, 97 insertions(+)
 create mode 100644 rules/S6983/metadata.json
 create mode 100644 rules/S6983/python/metadata.json
 create mode 100644 rules/S6983/python/rule.adoc

diff --git a/rules/S6983/metadata.json b/rules/S6983/metadata.json
new file mode 100644
index 00000000000..2c63c085104
--- /dev/null
+++ b/rules/S6983/metadata.json
@@ -0,0 +1,2 @@
+{
+}
diff --git a/rules/S6983/python/metadata.json b/rules/S6983/python/metadata.json
new file mode 100644
index 00000000000..10e9be93bd2
--- /dev/null
+++ b/rules/S6983/python/metadata.json
@@ -0,0 +1,25 @@
+{
+  "title": "The \"num_workers\" parameter should be specified for \"torch.utils.data.DataLoader\"",
+  "type": "CODE_SMELL",
+  "status": "ready",
+  "remediation": {
+    "func": "Constant\/Issue",
+    "constantCost": "2min"
+  },
+  "tags": [
+    "pytorch",
+    "machine-learning"
+  ],
+  "defaultSeverity": "Minor",
+  "ruleSpecification": "RSPEC-6983",
+  "sqKey": "S6983",
+  "scope": "All",
+  "defaultQualityProfiles": ["Sonar way"],
+  "quickfix": "targeted",
+  "code": {
+    "impacts": {
+      "RELIABILITY": "LOW"
+    },
+    "attribute": "COMPLETE"
+  }
+}
diff --git a/rules/S6983/python/rule.adoc b/rules/S6983/python/rule.adoc
new file mode 100644
index 00000000000..83c001778d5
--- /dev/null
+++ b/rules/S6983/python/rule.adoc
@@ -0,0 +1,70 @@
+This rule raises an issue when a `torch.utils.data.Dataloader` is instantiated without specifying the `num_workers` parameter.
+
+== Why is this an issue?
+
+In the PyTorch library, the data loaders are used to provide an interface where common operations such as batching can be implemented.
+It is also possible to parallelize the data loading process by using multiple worker processes.
+This can improve performance by increasing the number of batches being fetched in parallel, at the cost of higher memory usage.
+This performance increase can also be attributed to avoiding the Global Interpreter Lock (GIL) in the Python interpreter.
+
+
+== How to fix it
+Specify the `num_workers` parameter when instantiating the `torch.utils.data.Dataloader` object.
+
+The default value of `0` will use the main process to load the data, and might be faster for small datasets that can fit completely in memory.
+
+For larger datasets, it is recommended to use a value of `1` or higher to parallelize the data loading process.
+
+=== Code examples
+
+==== Noncompliant code example
+
+[source,python,diff-id=1,diff-type=noncompliant]
+----
+from torch.utils.data import DataLoader
+from torchvision import datasets
+from torchvision.transforms import ToTensor
+
+train_dataset = datasets.MNIST(root='data', train=True, transform=ToTensor())
+train_data_loader = DataLoader(train_dataset, batch_size=32)# Noncompliant: the num_workers parameter is not specified
+----
+
+==== Compliant solution
+
+[source,python,diff-id=1,diff-type=compliant]
+----
+from torch.utils.data import DataLoader
+from torchvision import datasets
+from torchvision.transforms import ToTensor
+
+train_dataset = datasets.MNIST(root='data', train=True, transform=ToTensor())
+train_data_loader = DataLoader(train_dataset, batch_size=32, num_workers=4)
+----
+
+== Resources
+=== Documentation
+
+* PyTorch documentation - https://pytorch.org/docs/stable/data.html#single-and-multi-process-data-loading[Single- and Multi-process Data Loading]
+
+* PyTorch documentation - https://pytorch.org/tutorials/beginner/basics/data_tutorial.html[Datasets and DataLoaders]
+
+ifdef::env-github,rspecator-view[]
+
+(visible only on this page)
+
+== Implementation specification 
+
+
+=== Message 
+
+Primary : Specify the `num_workers` parameter. 
+
+=== Issue location
+
+Primary : Name of the instantiation
+
+=== Quickfix
+
+Fill in with the default parameter
+
+endif::env-github,rspecator-view[]
\ No newline at end of file