Data parallelism vs model parallelism in MLOps - Interactive Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to split data across multiple devices for parallel processing.

MLOps

distributed_data = dataset.[1](num_devices)

Drag options to blanks, or click blank then click option'

Abatch

Bsplit

Cshuffle

Drepeat

Attempts:

3 left

💡 Hint

Common Mistakes

Using batch instead of split causes incorrect data division.

The split method divides the dataset into parts for each device, enabling data parallelism.

2fill in blank

medium

Complete the code to assign different parts of the model to different devices.

MLOps

model = Model().to_device([1])

Drag options to blanks, or click blank then click option'

Acpu

Ball

Cgpu1

Dgpu0

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'all' tries to put the whole model everywhere, which is incorrect.

Assigning the model part to gpu0 places it on the first GPU, which is common in model parallelism.

3fill in blank

hard

Fix the error in the code to correctly synchronize gradients across devices in data parallelism.

MLOps

optimizer.zero_grad()
loss.backward()
[1].all_reduce(gradients)

Drag options to blanks, or click blank then click option'

Atorch.distributed

Boptimizer

Cmodel

Ddevice

Attempts:

3 left

💡 Hint

Common Mistakes

Using model or optimizer instead of the distributed module causes runtime errors.

torch.distributed.all_reduce is used to synchronize gradients across devices in data parallelism.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps device names to model parts for model parallelism.

MLOps

model_parts = {device: model.[1](device) for device in [2]

Drag options to blanks, or click blank then click option'

Ato_device

Bdevices

Cdevice_list

Dcpu

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'cpu' instead of a list causes errors.

The method to_device moves model parts to devices listed in device_list, enabling model parallelism.

5fill in blank

hard

Fill all three blanks to create a dictionary comprehension that maps device names to batch sizes for data parallelism.

MLOps

batch_sizes = {device: total_batch_size [1] len([2]) for device in [3]

Drag options to blanks, or click blank then click option'

A//

Bdevices

Cdevice_list

Dbatch_sizes

Attempts:

3 left

💡 Hint

Common Mistakes

Using '/' causes float division, which is not suitable for batch sizes.

Using integer division // divides the total batch size by the number of devices in device_list for data parallelism.

Practice

1. What is the main difference between data parallelism and model parallelism in machine learning training?

easy

A. Data parallelism splits the data across workers, while model parallelism splits the model across workers.

B. Data parallelism splits the model across workers, while model parallelism splits the data across workers.

C. Data parallelism uses only one worker, model parallelism uses multiple workers.

D. Data parallelism trains different models, model parallelism trains the same model multiple times.

Solution

1. Step 1: Understand data parallelism

   Data parallelism means dividing the input data into parts and sending each part to a different worker. Each worker runs the full model on its data part.

2. Step 2: Understand model parallelism

   Model parallelism means splitting the model itself into parts and assigning each part to a different worker. The data flows through these parts sequentially.

3. Final Answer:

   Data parallelism splits the data across workers, while model parallelism splits the model across workers. -> Option A

4. Quick Check:

   Data vs Model split [OK]

Hint: Data parallelism splits data; model parallelism splits model [OK]

Common Mistakes:

• Confusing which is split: data or model
• Thinking both split data only
• Assuming model parallelism uses one worker

2. Which of the following is the correct way to describe data parallelism in a distributed training setup?

easy

A. The data is duplicated on one worker and processed sequentially.

B. Each worker trains a different part of the model on the full dataset.

C. The model is split into layers, each trained by a different worker on the full data.

D. Each worker trains the full model on a subset of the data.

Solution

1. Step 1: Analyze data parallelism setup

   In data parallelism, the full model is copied to each worker. Each worker trains on a different subset of the data.

2. Step 2: Evaluate options

   Each worker trains the full model on a subset of the data. correctly states that each worker trains the full model on a subset of data. Other options describe model splitting or incorrect data handling.

3. Final Answer:

   Each worker trains the full model on a subset of the data. -> Option D

4. Quick Check:

   Full model + data subset [OK]

Hint: Data parallelism = full model per worker, split data [OK]

Common Mistakes:

• Thinking model is split in data parallelism
• Assuming data is duplicated on one worker
• Confusing model layers with data chunks

3. Consider a model split into 3 parts for model parallelism across 3 workers. If input data batch size is 90, how is the data processed?

medium

A. Each worker processes 30 data samples independently on the full model.

B. All 90 samples flow sequentially through the 3 model parts on different workers.

C. Each worker processes all 90 samples on its model part independently.

D. The data is split into 3 parts, each processed by a different worker on the full model.

Solution

1. Step 1: Understand model parallelism data flow

   In model parallelism, the model is split into parts on different workers. The full data batch flows through these parts sequentially.

2. Step 2: Analyze data processing

   All 90 samples pass through the first model part on worker 1, then output flows to worker 2's model part, and so on.

3. Final Answer:

   All 90 samples flow sequentially through the 3 model parts on different workers. -> Option B

4. Quick Check:

   Model split, data flows through [OK]

Hint: Model parallelism splits model; data flows through all parts [OK]

Common Mistakes:

• Assuming data is split in model parallelism
• Thinking each worker processes full data independently
• Confusing data parallelism with model parallelism

4. You tried to implement model parallelism but noticed workers are idle waiting for data. What is the likely cause?

medium

A. Model parts are not connected properly causing data flow delays.

B. Data is not being split correctly across workers.

C. Each worker is running the full model on the full data.

D. Data parallelism was used instead of model parallelism.

Solution

1. Step 1: Identify symptoms of idle workers in model parallelism

   Idle workers waiting for data usually mean data flow between model parts is blocked or delayed.

2. Step 2: Analyze model part connections

   If model parts are not connected properly, data cannot flow smoothly, causing some workers to wait.

3. Final Answer:

   Model parts are not connected properly causing data flow delays. -> Option A

4. Quick Check:

   Idle workers = broken model part connections [OK]

Hint: Idle workers? Check model part connections in model parallelism [OK]

Common Mistakes:

• Blaming data splitting in model parallelism
• Confusing full model runs with model splitting
• Mixing up data and model parallelism issues

5. You have a very large model that does not fit into one GPU memory. Which approach is best to train it efficiently?

hard

A. Use data parallelism by splitting data across GPUs, each with full model copy.

B. Train the model on CPU only to avoid GPU memory limits.

C. Use model parallelism by splitting the model across GPUs, each handling part of the model.

D. Reduce batch size and train on a single GPU.

Solution

1. Step 1: Understand GPU memory limits

   If the model is too large to fit in one GPU, copying full model to each GPU (data parallelism) is not possible.

2. Step 2: Choose model parallelism

   Splitting the model across GPUs allows each GPU to hold only a part of the model, enabling training of large models.

3. Final Answer:

   Use model parallelism by splitting the model across GPUs, each handling part of the model. -> Option C

4. Quick Check:

   Large model fits by splitting model [OK]

Hint: Large model? Split model across GPUs (model parallelism) [OK]

Common Mistakes:

• Trying data parallelism with too large model
• Ignoring GPU memory limits
• Reducing batch size instead of splitting model