Terra: Imperative-Symbolic Co-Execution of Imperative Deep Learning Programs

Imperative programming allows users to implement their deep neural networks (DNNs) easily and has become an essential part of recent deep learning (DL) frameworks. Recently, several systems have been proposed to combine the usability of imperative programming with the optimized performance of symbolic graph execution. Such systems convert imperative Python DL programs to optimized symbolic graphs and execute them. However, they cannot fully support the usability of imperative programming. For example, if an imperative DL program contains a Python feature with no corresponding symbolic representation (e.g., third-party library calls or unsupported dynamic control flows) they fail to execute the program. To overcome this limitation, we propose Terra, an imperative-symbolic co-execution system that can handle any imperative DL programs while achieving the optimized performance of symbolic graph execution. To achieve this, Terra builds a symbolic graph by decoupling DL operations from Python features. Then, Terra conducts the imperative execution to support all Python features, while delegating the decoupled operations to the symbolic execution. We evaluated the performance improvement and coverage of Terra with ten imperative DL programs for several DNN architectures. The results show that Terra can speed up the execution of all ten imperative DL programs, whereas AutoGraph, one of the state-of-the-art systems, fails to execute five of them.

Nimble: Lightweight and Parallel GPU Task Scheduling for Deep Learning

Deep learning (DL) frameworks take advantage of GPUs to improve the speed of DL inference and training. Ideally, DL frameworks should be able to fully utilize the computation power of GPUs such that the running time depends on the amount of computation assigned to GPUs. Yet, we observe that in scheduling GPU tasks, existing DL frameworks suffer from inefficiencies such as large scheduling overhead and unnecessary serial execution. To this end, we propose Nimble, a DL execution engine that runs GPU tasks in parallel with minimal scheduling overhead. Nimble introduces a novel technique called ahead-of-time (AoT) scheduling. Here, the scheduling procedure finishes before executing the GPU kernel, thereby removing most of the scheduling overhead during run time. Furthermore, Nimble automatically parallelizes the execution of GPU tasks by exploiting multiple GPU streams in a single GPU. Evaluation on a variety of neural networks shows that compared to PyTorch, Nimble speeds up inference and training by up to 22.34$\times$ and 3.61$\times$, respectively. Moreover, Nimble outperforms state-of-the-art inference systems, TensorRT and TVM, by up to 2.81$\times$ and 1.70$\times$, respectively.

Accelerating Multi-Model Inference by Merging DNNs of Different Weights

Standardized DNN models that have been proved to perform well on machine learning tasks are widely used and often adopted as-is to solve downstream tasks, forming the transfer learning paradigm. However, when serving multiple instances of such DNN models from a cluster of GPU servers, existing techniques to improve GPU utilization such as batching are inapplicable because models often do not share weights due to fine-tuning. We propose NetFuse, a technique of merging multiple DNN models that share the same architecture but have different weights and different inputs. NetFuse is made possible by replacing operations with more general counterparts that allow a set of weights to be associated with only a certain set of inputs. Experiments on ResNet-50, ResNeXt-50, BERT, and XLNet show that NetFuse can speed up DNN inference time up to 3.6x on a NVIDIA V100 GPU, and up to 3.0x on a TITAN Xp GPU when merging 32 model instances, while only using up a small additional amount of GPU memory.

Hippo: Taming Hyper-parameter Optimization of Deep Learning with Stage Trees

Hyper-parameter optimization is crucial for pushing the accuracy of a deep learning model to its limits. A hyper-parameter optimization job, referred to as a study, involves numerous trials of training a model using different training knobs, and therefore is very computation-heavy, typically taking hours and days to finish. We observe that trials issued from hyper-parameter optimization algorithms often share common hyper-parameter sequence prefixes. Based on this observation, we propose Hippo, a hyper-parameter optimization system that removes redundancy in the training process to reduce the overall amount of computation significantly. Instead of executing each trial independently as in existing hyper-parameter optimization systems, Hippo breaks down the hyper-parameter sequences into stages and merges common stages to form a tree of stages (called a stage-tree), then executes a stage once per tree on a distributed GPU server environment. Hippo is applicable to not only single studies, but multi-study scenarios as well, where multiple studies of the same model and search space can be formulated as trees of stages. Evaluations show that Hippo's stage-based execution strategy outperforms trial-based methods such as Ray Tune for several models and hyper-parameter optimization algorithms, reducing GPU-hours and end-to-end training time significantly.

Stage-based Hyper-parameter Optimization for Deep Learning

As deep learning techniques advance more than ever, hyper-parameter optimization is the new major workload in deep learning clusters. Although hyper-parameter optimization is crucial in training deep learning models for high model performance, effectively executing such a computation-heavy workload still remains a challenge. We observe that numerous trials issued from existing hyper-parameter optimization algorithms share common hyper-parameter sequence prefixes, which implies that there are redundant computations from training the same hyper-parameter sequence multiple times. We propose a stage-based execution strategy for efficient execution of hyper-parameter optimization algorithms. Our strategy removes redundancy in the training process by splitting the hyper-parameter sequences of trials into homogeneous stages, and generating a tree of stages by merging the common prefixes. Our preliminary experiment results show that applying stage-based execution to hyper-parameter optimization algorithms outperforms the original trial-based method, saving required GPU-hours and end-to-end training time by up to 6.60 times and 4.13 times, respectively.

Making Classical Machine Learning Pipelines Differentiable: A Neural Translation Approach

Classical Machine Learning (ML) pipelines often comprise of multiple ML models where models, within a pipeline, are trained in isolation. Conversely, when training neural network models, layers composing the neural models are simultaneously trained using backpropagation. We argue that the isolated training scheme of ML pipelines is sub-optimal, since it cannot jointly optimize multiple components. To this end, we propose a framework that translates a pre-trained ML pipeline into a neural network and fine-tunes the ML models within the pipeline jointly using backpropagation. Our experiments show that fine-tuning of the translated pipelines is a promising technique able to increase the final accuracy.

JANUS: Fast and Flexible Deep Learning via Symbolic Graph Execution of Imperative Programs

The rapid evolution of deep neural networks is demanding deep learning (DL) frameworks not only to satisfy the traditional requirement of quickly executing large computations, but also to support straightforward programming models for quickly implementing and experimenting with complex network structures. However, existing frameworks fail to excel in both departments simultaneously, leading to diverged efforts for optimizing performance and improving usability. This paper presents JANUS, a system that combines the advantages from both sides by transparently converting an imperative DL program written in Python, the de-facto scripting language for DL, into an efficiently executable symbolic dataflow graph. JANUS can convert various dynamic features of Python, including dynamic control flow, dynamic types, and impure functions, into elements of a symbolic dataflow graph. Experiments demonstrate that JANUS can achieve fast DL training by exploiting the techniques imposed by symbolic graph-based DL frameworks, while maintaining the simple and flexible programmability of imperative DL frameworks at the same time.

PRETZEL: Opening the Black Box of Machine Learning Prediction Serving Systems

Machine Learning models are often composed of pipelines of transformations. While this design allows to efficiently execute single model components at training time, prediction serving has different requirements such as low latency, high throughput and graceful performance degradation under heavy load. Current prediction serving systems consider models as black boxes, whereby prediction-time-specific optimizations are ignored in favor of ease of deployment. In this paper, we present PRETZEL, a prediction serving system introducing a novel white box architecture enabling both end-to-end and multi-model optimizations. Using production-like model pipelines, our experiments show that PRETZEL is able to introduce performance improvements over different dimensions; compared to state-of-the-art approaches PRETZEL is on average able to reduce 99th percentile latency by 5.5x while reducing memory footprint by 25x, and increasing throughput by 4.7x.

Improving the Expressiveness of Deep Learning Frameworks with Recursion

Recursive neural networks have widely been used by researchers to handle applications with recursively or hierarchically structured data. However, embedded control flow deep learning frameworks such as TensorFlow, Theano, Caffe2, and MXNet fail to efficiently represent and execute such neural networks, due to lack of support for recursion. In this paper, we add recursion to the programming model of existing frameworks by complementing their design with recursive execution of dataflow graphs as well as additional APIs for recursive definitions. Unlike iterative implementations, which can only understand the topological index of each node in recursive data structures, our recursive implementation is able to exploit the recursive relationships between nodes for efficient execution based on parallel computation. We present an implementation on TensorFlow and evaluation results with various recursive neural network models, showing that our recursive implementation not only conveys the recursive nature of recursive neural networks better than other implementations, but also uses given resources more effectively to reduce training and inference time.

Mantis: Predicting System Performance through Program Analysis and Modeling

We present Mantis, a new framework that automatically predicts program performance with high accuracy. Mantis integrates techniques from programming language and machine learning for performance modeling, and is a radical departure from traditional approaches. Mantis extracts program features, which are information about program execution runs, through program instrumentation. It uses machine learning techniques to select features relevant to performance and creates prediction models as a function of the selected features. Through program analysis, it then generates compact code slices that compute these feature values for prediction. Our evaluation shows that Mantis can achieve more than 93% accuracy with less than 10% training data set, which is a significant improvement over models that are oblivious to program features. The system generates code slices that are cheap to compute feature values.