Maksim Levental

Maksim Levental, Arham Khan, Ryan Chard et al.

In many experiment-driven scientific domains, such as high-energy physics, material science, and cosmology, high data rate experiments impose hard constraints on data acquisition systems: collected data must either be indiscriminately stored for post-processing and analysis, thereby necessitating large storage capacity, or accurately filtered in real-time, thereby necessitating low-latency processing. Deep neural networks, effective in other filtering tasks, have not been widely employed in such data acquisition systems, due to design and deployment difficulties. We present an open source, lightweight, compiler framework, without any proprietary dependencies, OpenHLS, based on high-level synthesis techniques, for translating high-level representations of deep neural networks to low-level representations, suitable for deployment to near-sensor devices such as field-programmable gate arrays. We evaluate OpenHLS on various workloads and present a case-study implementation of a deep neural network for Bragg peak detection in the context of high-energy diffraction microscopy. We show OpenHLS is able to produce an implementation of the network with a throughput 4.8 $μ$s/sample, which is approximately a 4$\times$ improvement over the existing implementation

Nathaniel Hudson, J. Gregory Pauloski, Matt Baughman et al.

Deep learning methods are transforming research, enabling new techniques, and ultimately leading to new discoveries. As the demand for more capable AI models continues to grow, we are now entering an era of Trillion Parameter Models (TPM), or models with more than a trillion parameters -- such as Huawei's PanGu-$Σ$. We describe a vision for the ecosystem of TPM users and providers that caters to the specific needs of the scientific community. We then outline the significant technical challenges and open problems in system design for serving TPMs to enable scientific research and discovery. Specifically, we describe the requirements of a comprehensive software stack and interfaces to support the diverse and flexible requirements of researchers.

Maksim Levental

We study memory allocation patterns in DNNs during inference, in the context of large-scale systems. We observe that such memory allocation patterns, in the context of multi-threading, are subject to high latencies, due to \texttt{mutex} contention in the system memory allocator. Latencies incurred due to such \texttt{mutex} contention produce undesirable bottlenecks in user-facing services. Thus, we propose a "memorization" based technique, \texttt{MemoMalloc}, for optimizing overall latency, with only moderate increases in peak memory usage. Specifically, our technique consists of a runtime component, which captures all allocations and uniquely associates them with their high-level source operation, and a static analysis component, which constructs an efficient allocation "plan". We present an implementation of \texttt{MemoMalloc} in the PyTorch deep learning framework and evaluate memory consumption and execution performance on a wide range of DNN architectures. We find that \texttt{MemoMalloc} outperforms state-of-the-art general purpose memory allocators, with respect to DNN inference latency, by as much as 40\%.

Maksim Levental, Ryan Chard, Kyle Chard et al.

Technological advancements in modern scientific instruments, such as scanning electron microscopes (SEMs), have significantly increased data acquisition rates and image resolutions enabling new questions to be explored; however, the resulting data volumes and velocities, combined with automated experiments, are quickly overwhelming scientists as there remain crucial steps that require human intervention, for example reviewing image focus. We present a fast out-of-focus detection algorithm for electron microscopy images collected serially and demonstrate that it can be used to provide near-real-time quality control for neuroscience workflows. Our technique, \textit{Multi-scale Histologic Feature Detection}, adapts classical computer vision techniques and is based on detecting various fine-grained histologic features. We exploit the inherent parallelism in the technique to employ GPU primitives in order to accelerate characterization. We show that our method can detect of out-of-focus conditions within just 20ms. To make these capabilities generally available, we deploy our feature detector as an on-demand service and show that it can be used to determine the degree of focus in approximately 230ms, enabling near-real-time use.

E. A. Huerta, Asad Khan, Xiaobo Huang et al.

The development of reusable artificial intelligence (AI) models for wider use and rigorous validation by the community promises to unlock new opportunities in multi-messenger astrophysics. Here we develop a workflow that connects the Data and Learning Hub for Science, a repository for publishing AI models, with the Hardware Accelerated Learning (HAL) cluster, using funcX as a universal distributed computing service. Using this workflow, an ensemble of four openly available AI models can be run on HAL to process an entire month's worth (August 2017) of advanced Laser Interferometer Gravitational-Wave Observatory data in just seven minutes, identifying all four all four binary black hole mergers previously identified in this dataset and reporting no misclassifications. This approach combines advances in AI, distributed computing, and scientific data infrastructure to open new pathways to conduct reproducible, accelerated, data-driven discovery.

Maksim Levental, Elena Orlova

High level abstractions for implementing, training, and testing Deep Learning (DL) models abound. Such frameworks function primarily by abstracting away the implementation details of arbitrary neural architectures, thereby enabling researchers and engineers to focus on design. In principle, such frameworks could be "zero-cost abstractions"; in practice, they incur translation and indirection overheads. We study at which points exactly in the engineering life-cycle of a DL model the highest costs are paid and whether they can be mitigated. We train, test, and evaluate a representative DL model using PyTorch, LibTorch, TorchScript, and cuDNN on representative datasets, comparing accuracy, execution time and memory efficiency.

Maksim Levental, Ryan Chard, Joseph A. Libera et al.

Flame Spray Pyrolysis (FSP) is a manufacturing technique to mass produce engineered nanoparticles for applications in catalysis, energy materials, composites, and more. FSP instruments are highly dependent on a number of adjustable parameters, including fuel injection rate, fuel-oxygen mixtures, and temperature, which can greatly affect the quality, quantity, and properties of the yielded nanoparticles. Optimizing FSP synthesis requires monitoring, analyzing, characterizing, and modifying experimental conditions.Here, we propose a hybrid CPU-GPU Difference of Gaussians (DoG)method for characterizing the volume distribution of unburnt solution, so as to enable near-real-time optimization and steering of FSP experiments. Comparisons against standard implementations show our method to be an order of magnitude more efficient. This surrogate signal can be deployed as a component of an online end-to-end pipeline that maximizes the synthesis yield.