Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “end-to-end”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 289 records · Page 16
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Meta-optic accelerators for object classifiers

Rapid advances in deep learning have led to paradigm shifts in a number of fields, from medical image analysis to autonomous systems. These advances, however, have resulted in digital neural networks with large computational requirements, resulting in high energy consumption and limitations in real-time decision-making when computation resources are limited. Here, we demonstrate a meta-optic–based neural network accelerator that can off-load computationally expensive convolution operations into high-speed and low-power optics. In this architecture, metasurfaces enable both spatial multiplexing and additional information channels, such as polarization, in object classification. End-to-end design is used to co-optimize the optical and digital systems, resulting in a robust classifier that achieves 93.1% accurate classification of handwriting digits and 93.8% accuracy in classifying both the digit and its polarization state. This approach could enable compact, high-speed, and low-power image and information processing systems for a wide range of applications in machine vision and artificial intelligence.

42 ENGINEERING↗
DOE OSTI2022

Leakless end-to-end transport of small molecules through micron-length DNA nanochannels

Designed and engineered protein and DNA nanopores can be used to sense and characterize single molecules and control transmembrane transport of molecular species. However, designed biomolecular pores are less than 100 nm in length and are used primarily for transport across lipid membranes. Nanochannels that span longer distances could be used as conduits for molecules between nonadjacent compartments or cells. We design micrometer-long, 7-nm-diameter DNA nanochannels that small molecules can traverse according to the laws of continuum diffusion. Binding DNA origami caps to channel ends eliminates transport and demonstrates that molecules diffuse from one channel end to the other rather than permeating through channel walls. These micrometer-length nanochannels can also grow, form interconnects, and interface with living cells. This work thus shows how to construct multifunctional, dynamic agents that control molecular transport, opening ways of studying intercellular signaling and modulating molecular transport between synthetic and living cells.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

ForceGen: End-to-end de novo protein generation based on nonlinear mechanical unfolding responses using a language diffusion model

Through evolution, nature has presented a set of remarkable protein materials, including elastins, silks, keratins and collagens with superior mechanical performances that play crucial roles in mechanobiology. However, going beyond natural designs to discover proteins that meet specified mechanical properties remains challenging. Here, we report a generative model that predicts protein designs to meet complex nonlinear mechanical property-design objectives. Our model leverages deep knowledge on protein sequences from a pretrained protein language model and maps mechanical unfolding responses to create proteins. Via full-atom molecular simulations for direct validation, we demonstrate that the designed proteins are de novo, and fulfill the targeted mechanical properties, including unfolding energy and mechanical strength, as well as the detailed unfolding force-separation curves. Our model offers rapid pathways to explore the enormous mechanobiological protein sequence space unconstrained by biological synthesis, using mechanical features as the target to enable the discovery of protein materials with superior mechanical properties.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Molecular insights into the complex mechanics of plant epidermal cell walls

Computational analysis of cell walls Layers of intertwined fibers make up plant cell walls. The various types of fibers respond differently to deformation. Cellulose microfibrils, for example, can stretch or curve, changing their end-to-end length, and can also slide past each other, reorient relative directions, and bundle with neighboring microfibrils. Zhang et al. developed a computational model based on observations of onion skin epidermis that describes how these complex changes in space govern cell wall mechanics. The results inform ways to engineer multifunctional fibrous materials. Science , this issue p. 706

Science & Technology - Other Topics↗
DOE OSTI2022

Towards Compact Neural Networks via End-to-End Training: A Bayesian Tensor Approach with Automatic Rank Determination

Post-training model compression can reduce the inference costs of deep neural networks, but uncompressed training still consumes enormous hardware resources and energy. To enable low-energy training on edge devices, it is highly desirable to directly train a compact neural network from scratch with a low memory cost. Low-rank tensor decomposition is an effective approach to reduce the memory and computing costs of large neural networks. However, directly training low-rank tensorized neural networks is a very challenging task because it is hard to determine a proper tensor rank a priori, and the tensor rank controls both model complexity and accuracy. Here, this paper presents a novel end-to-end framework for low-rank tensorized training. We first develop a Bayesian model that supports various low-rank tensor formats (e.g., CANDECOMP/PARAFAC, Tucker, tensor-train, and tensor-train matrix) and reduces neural network parameters with automatic rank determination during training. Then we develop a customized Bayesian solver to train large-scale tensorized neural networks. Our training methods shows orders-of-magnitude parameter reduction and little accuracy loss (or even better accuracy) in the experiments. On a very large deep learning recommendation system with over 4.2 ×10 9 model parameters, our method can reduce the parameter number to 1.6 ×10 5 automatically in the training process (i.e., by 2.6 ×10 4 times) while achieving almost the same accuracy. Code is available at https://github.com/colehawkins/bayesian-tensor-rank-determination.

compact neural networks↗
DOE OSTI2020

Calorimetry with deep learning: particle simulation and reconstruction for collider physics

Using detailed simulations of calorimeter showers as training data, we investigate the use of deep learning algorithms for the simulation and reconstruction of single isolated particles produced in high-energy physics collisions. We train neural networks on single-particle shower data at the calorimeter-cell level, and show significant improvements for simulation and reconstruction when using these networks compared to methods which rely on currently-used state-of-the-art algorithms. We define two models: an end-to-end reconstruction network which performs simultaneous particle identification and energy regression of particles when given calorimeter shower data, and a generative network which can provide reasonable modeling of calorimeter showers for different particle types at specified angles and energies. We investigate the optimization of our models with hyperparameter scans. Furthermore, we demonstrate the applicability of the reconstruction model to shower inputs from other detector geometries, specifically ATLAS-like and CMS-like geometries. These networks can serve as fast and computationally light methods for particle shower simulation and reconstruction for current and future experiments at particle colliders.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2021

MLPF: efficient machine-learned particle-flow reconstruction using graph neural networks

In general-purpose particle detectors, the particle-flow algorithm may be used to reconstruct a comprehensive particle-level view of the event by combining information from the calorimeters and the trackers, significantly improving the detector resolution for jets and the missing transverse momentum. In view of the planned high-luminosity upgrade of the CERN Large Hadron Collider (LHC), it is necessary to revisit existing reconstruction algorithms and ensure that both the physics and computational performance are sufficient in an environment with many simultaneous proton–proton interactions (pileup). Machine learning may offer a prospect for computationally efficient event reconstruction that is well-suited to heterogeneous computing platforms, while significantly improving the reconstruction quality over rule-based algorithms for granular detectors. We introduce MLPF, a novel, end-to-end trainable, machine-learned particle-flow algorithm based on parallelizable, computationally efficient, and scalable graph neural network optimized using a multi-task objective on simulated events. We report the physics and computational performance of the MLPF algorithm on a Monte Carlo dataset of top quark–antiquark pairs produced in proton–proton collisions in conditions similar to those expected for the high-luminosity LHC. The MLPF algorithm improves the physics response with respect to a rule-based benchmark algorithm and demonstrates computationally scalable particle-flow reconstruction in a high-pileup environment.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2020

Policy Considerations When Federating Facilities for Experimental and Observational Data Analysis

Today’s computational, experimental, and observational facilities afford us tremendous opportunities to couple theory and experiment at increasingly large scales. Empirical sensing capabilities are growing dramatically with beam line and detector improvements, and with advances in our ability to deploy large-scale data gathering observations of the natural world. The coupling of computational simulations and analysis to process the data from experimental and observational facilities is giving rise to cross-facility workflows. Such federations of facilities are in fact becoming an explicit requirement for large-scale scientific discovery. As we scale up these pipelines of scientific discovery, each participating facility needs to establish and align policies so that the federation can work seamlessly in an end-to-end manner. This chapter outlines specific policy considerations in enabling the federation of facilities for data analysis. Design choices and vital policy decisions cover the areas of data acquisition and storage, data transfer, computational resource allocation and co-scheduling, seamless federated user access, and cross-cutting governance. By highlighting the explicit and implicit interdependencies between facilities, we aim to provide facility designers and policymakers the information on policy issues to address early in a facility’s operations, thus enabling successful cross-facility federation and improved experimental and observational data analysis outcomes.

Shankar, Mallikarjun (Arjun)↗
DOE OSTI2024

Jet quenching: From theory to simulation

With the explosion of data on jet-based observables in relativistic heavy-ion collisions at the Large Hadron Collider and the Relativistic Heavy-Ion Collider, perturbative Quantum Chromodynamics (pQCD)-based simulations of these processes, often interacting with an expanding viscous fluid dynamical background, have taken center stage. This review is meant to bridge the gap between theory, simulation and phenomenology of jet modification in a dense medium. We will demonstrate how the existence of such end-to-end event generators with semi-realistic or even fully realistic final states allows for the most rigorous comparisons between pQCD-based jet modification theory and experiment. State-of-the-art calculations of several jet-based observables are presented. Extensions of this theory to jets in the small systems of p–A and e–A collisions are discussed.

Physics↗
DOE OSTI2020

PC-RPL: Joint Control of Routing Topology and Transmission Power in Real Low-Power and Lossy Networks

We present PC-RPL , a transmission power-controlled IPv6 routing protocol for low-power and lossy wireless networks that significantly improves the end-to-end packet delivery performance under heavy traffic compared to the standard RPL. We show through actual design, implementation, and experiments that a multihop wireless network can achieve better throughput and routing stability when transmission power and routing topology are “jointly and adaptively” controlled. Our experiments show that the predominant “fixed and uniform” transmission power strategy with “link quality and hop distance”–based routing topology construction (i.e., RPL) loses significant bandwidth due to hidden terminal and load imbalance problems. We design an adaptive and distributed control mechanism for transmission power and routing topology, named PC-RPL , on top of the standard RPL routing protocol for hidden terminal mitigation and load balancing. We implement PC-RPL on real embedded devices and evaluate its performance on a 49-node multihop testbed. PC-RPL reduces total end-to-end packet losses by approximately sevenfold without increasing hop distance compared to RPL with the highest transmission power, resulting in 17% improvement in aggregate bandwidth and 64% improvement for the worst-case node by successfully alleviating both hidden terminal and load imbalance problems.

Computer Science↗
DOE OSTI2021

Scalable FBP decomposition for cone-beam CT reconstruction

Filtered Back-Projection (FBP) is a fundamental compute intense algorithm used in tomographic image reconstruction. Cone-Beam Computed Tomography (CBCT) devices use a cone-shaped X-ray beam, in comparison to the parallel beam used in older CT generations. Distributed image reconstruction of cone-beam datasets typically relies on dividing batches of images into different nodes. This simple input decomposition, however, introduces limits on input/output sizes and scalability.We propose a novel decomposition scheme and reconstruction algorithm for distributed FPB. This scheme enables arbitrarily large input/output sizes, eliminates the redundancy arising in the end-to-end pipeline and improves the scalability by replacing two communication collectives with only one segmented reduction. Finally, we implement the proposed decomposition scheme in a framework that is useful for all current-generation CT devices (7th gen). In our experiments using up to 1024 GPUs, our framework can construct 40963 volumes, for real-world datasets, in under 16 seconds (including I/O).

Chen, Peng↗
DOE OSTI2022

DFSynthesizer: Dataflow-based Synthesis of Spiking Neural Networks to Neuromorphic Hardware

Spiking Neural Networks (SNNs) are an emerging computation model that uses event-driven activation and bio-inspired learning algorithms. SNN-based machine learning programs are typically executed on tile-based neuromorphic hardware platforms, where each tile consists of a computation unit called a crossbar, which maps neurons and synapses of the program. However, synthesizing such programs on an off-the-shelf neuromorphic hardware is challenging. This is because of the inherent resource and latency limitations of the hardware, which impact both model performance, e.g., accuracy, and hardware performance, e.g., throughput. We propose DFSynthesizer, an end-to-end framework for synthesizing SNN-based machine learning programs to neuromorphic hardware. The proposed framework works in four steps. First, it analyzes a machine learning program and generates SNN workload using representative data. Second, it partitions the SNN workload and generates clusters that fit on crossbars of the target neuromorphic hardware. Third, it exploits the rich semantics of the Synchronous Dataflow Graph (SDFG) to represent a clustered SNN program, allowing for performance analysis in terms of key hardware constraints such as number of crossbars, dimension of each crossbar, buffer space on tiles, and tile communication bandwidth. Finally, it uses a novel scheduling algorithm to execute clusters on crossbars of the hardware, guaranteeing hardware performance. We evaluate DFSynthesizer with 10 commonly used machine learning programs. Our results demonstrate that DFSynthesizer provides a much tighter performance guarantee compared to current mapping approaches.

Computer Science↗
DOE OSTI2022

The SODA Approach: Leveraging High-Level Synthesis for Hardware/Software Co-design and Hardware Specialization: Invited

Novel "converged" applications combine phases of scientific simulation with data analysis and machine learning. Each computational phase can benefit from specialized accelerators. However, algorithms evolve so quickly that mapping them on existing accelerators is suboptimal or even impossible. This paper presents the SODA (Software Defined Accelerators) framework, a modular, multi-level, open-source, no-human-in-the-loop, hardware synthesizer that enables end-to-end generation of specialized accelerators. SODA is composed of SODA-Opt, a high-level frontend developed in MLIR that interfaces with domain-specific programming frameworks and allows performing system level design, and Bambu, a state-of-the-art high-level synthesis engine that can target different device technologies. The framework implements design space exploration as compiler optimization passes. We show how the modular, yet tight, integration of the high-level optimizer and lower-level HLS tools enables the generation of accelerators optimized for the computational patterns of converged applications. We then discuss some of the research opportunities that such a framework allows, including system-level design, profile driven optimization, and supporting new optimization metrics.

Bohm Agostini, Nicolas↗
DOE OSTI2022

Machine Learning Assisted HPC Workload Trace Generation for Leadership Scale Storage Systems

Monitoring and analyzing a wide range of I/O activities in an HPC cluster is important in maintaining mission-critical performance in a large-scale, multi-user, parallel storage system. Center-wide I/O traces can provide high-level information and fine-grained activities per application or per user running in the system. Studying such large-scale traces can provide helpful insights into the system. It can be used to develop predictive methods for making predictive decisions, adjusting scheduling policies, or providing decisions for the design of next-generation systems. However, sharing real-world I/O traces to expedite such research efforts leaves a few concerns; i) the cost of sharing the large traces is expensive due to this large size, and ii) privacy concern is an issue.We address such issues by building an end-to-end machine learn- ing (ML) workflow that can generate I/O traces for large-scale HPC applications. We leverage ML based feature selection and gener- ative models for I/O trace generation. The generative models are trained on I/O traces collected by the darshan I/O characterization tool over a period of one year. We present a two-step generation process consisting of two deep-learning models, called the feature generator and the trace generator. The combination of two-step generative models provides robustness by reducing the bias of the model and accounting for the stochastic nature of the I/O traces across different runs of an application. We evaluate the performance of the generative models and show that the two-step model can generate time-series I/O traces with less than 20% root mean square error.

Paul, Arnab↗
DOE OSTI2022

SODA Synthesizer: an Open-source, Multi-level, Modular, Extensible Compiler from High-level Frameworks to Silicon

The SODA Synthesizer is an open-source modular, end-to-end hardware compiler framework. The SODA frontend, developed in MLIR, performs system-level design, code partitioning, and high-level optimizations to prepare the specifications for the hardware synthesis. The backend is based on a state-of-the-art high-level synthesis tool, and generates the final hardware design. The backend can interface with logic synthesis tools for field programmable gate arrays or with commercial and open-source logic synthesis tools for application-specific integrated circuits. We discuss the opportunities and challenges in integrating with commercial and open-source tools both at the frontend and backend, and the unique opportunities that an open-source hardware design ecosystem provides.

Bohm Agostini, Nicolas↗
DOE OSTI2022

Tensor Network Quantum Virtual Machine for Simulating Quantum Circuits at Exascale

The numerical simulation of quantum circuits is an indispensable tool for development, verification, and validation of hybrid quantum-classical algorithms intended for near-term quantum co-processors. The emergence of exascale high-performance computing (HPC) platforms presents new opportunities for pushing the boundaries of quantum circuit simulation. Here, we present a modernized version of the Tensor Network Quantum Virtual Machine (TNQVM) that serves as the quantum circuit simulation backend in the eXtreme-scale ACCelerator (XACC) framework. The new version is based on the scalable tensor network processing library ExaTN (Exascale Tensor Networks). It provides multiple configurable quantum circuit simulators that perform either an exact quantum circuit simulation via the full tensor network contraction or an approximate simulation via a suitably chosen tensor factorization scheme. Upon necessity, stochastic noise modeling from real quantum processors is incorporated into the simulations by modeling quantum channels with Kraus tensors. By combining the portable XACC quantum programming frontend and the scalable ExaTN numerical processing backend, we introduce an end-to-end virtual quantum development environment that can scale from laptops to future exascale platforms. We report initial benchmarks of our framework, which include a demonstration of the distributed execution, incorporation of quantum decoherence models, and simulation of the random quantum circuits used for the certification of quantum supremacy on Google’s Sycamore superconducting architecture.

Nguyen, Thien↗
DOE OSTI2023

Towards On-Chip Learning for Low Latency Reasoning with End-to-End Synthesis

The Software Defined Architectures (SODA) Synthesizer is an open-source compiler-based tool able to automatically generate domain-specialized systems targeting Application-Specific Integrated Circuits (ASICs) or Field Programmable Gate Arrays (FPGAs) starting from high-level programming. SODA is composed of a frontend, SODA-OPT, which leverages the multilevel intermediate representation (MLIR) framework to interface with productive programming tools (e.g., machine learning frame-works), identify kernels suitable for acceleration, and perform high-level optimizations, and of a state-of-the-art high-level synthesis backend, Bambu from the PandA framework, to generate custom accelerators. One specific application of the SODA Synthesizer is the generation of accelerators to enable ultra-low latency inference and control on autonomous systems for scientific discovery (e.g., electron microscopes, sensors in particle accelerators, etc.). This paper provides an overview of the flow in the context of the generation of accelerators for edge processing to be integrated in transmission electron microscopy (TEM) devices, focusing on use cases from precision material synthesis. We show the tool in action with an example of design space exploration for inference on reconfigurable devices with a conventional deep neural network model (LeNet). Finally, we discuss the research directions and opportunities enabled by SODA in the area of autonomous control for scientific experimental workflows.

Castellana, Vito G.↗