JAMPI: efficient matrix multiplication in Spark using Barrier Execution Mode
This work addresses performance bottlenecks in distributed deep learning training for users of Spark, though it is incremental as it adapts an existing algorithm to a new framework.
The paper tackled the problem of inefficient matrix multiplication in Apache Spark by implementing Cannon's algorithm using Barrier Execution Mode, resulting in up to a 24% performance increase on a 10,000x10,000 matrix with lower memory usage.
The new barrier mode in Apache Spark allows embedding distributed deep learning training as a Spark stage to simplify the distributed training workflow. In Spark, a task in a stage does not depend on any other tasks in the same stage, and hence it can be scheduled independently. However, several algorithms require more sophisticated inter-task communications, similar to the MPI paradigm. By combining distributed message passing (using asynchronous network IO), OpenJDK's new auto-vectorization and Spark's barrier execution mode, we can add non-map/reduce based algorithms, such as Cannon's distributed matrix multiplication to Spark. We document an efficient distributed matrix multiplication using Cannon's algorithm, which improves significantly on the performance of the existing MLlib implementation. Used within a barrier task, the algorithm described herein results in an up to 24 percent performance increase on a 10,000x10,000 square matrix with a significantly lower memory footprint. Applications of efficient matrix multiplication include, among others, accelerating the training and implementation of deep convolutional neural network based workloads, and thus such efficient algorithms can play a ground-breaking role in faster, more efficient execution of even the most complicated machine learning tasks.