Engineering topics

Coletti, Mark

Publications and source records attributed to Coletti, Mark.

At least 19 records

DOE OSTI2024

Impacts of floating-point non-associativity on reproducibility for HPC and deep learning applications

Run to run variability in parallel programs caused by floating-point non-associativity has been known to significantly affect reproducibility in iterative algorithms, due to accumulating errors. Non-reproducibility can critically affect the efficiency and effectiveness of correctness testing for stochastic programs. Recently, the sensitivity of deep learning training and inference pipelines to floating-point non-associativity has been found to sometimes be extreme. It can prevent certification for commercial applications, accurate assessment of robustness and sensitivity, and bug detection. New approaches in scientific computing applications have coupled deep learning models with high-performance computing, leading to an aggravation of debugging and testing challenges. Here we perform an investigation of the statistical properties of floating-point non-associativity within modern parallel programming models, and analyze performance and productivity impacts of replacing atomic operations with deterministic alternatives on GPUs. We examine the recently-added deterministic options in PyTorch within the context of GPU deployment for deep learning, uncovering and quantifying the impacts of input parameters triggering run to run variability and reporting on the reliability and completeness of the documentation. Finally, we evaluate the strategy of exploiting automatic determinism that could be provided by deterministic hardware, using the Groq LPUTM accelerator for inference portions of the deep learning pipeline. We demonstrate the benefits that a hardware-based strategy can provide within reproducibility and correctness efforts.

Shanmugavelu, Sanjif↗

DOE OSTI2024

Workflow Provenance in the Computing Continuum for Responsible, Trustworthy, and Energy-Efficient AI

As Artificial Intelligence (AI) becomes more pervasive in our society, it is crucial to develop, deploy, and assess Responsible and Trustworthy AI (RTAI) models, i.e., those that consider not only accuracy but also other aspects, such as explainability, fairness, and energy efficiency. Workflow provenance data have historically enabled critical capabilities towards RTAI. Provenance data derivation paths contribute to responsible workflows through transparency in tracking artifacts and resource consumption. Provenance data are well-known for their trustworthiness helping explainability, reproducibility, and accountability. However, there are complex challenges to achieve RTAI, which are further complicated by the heterogeneous infrastructure in the computing continuum (Edge-Cloud-HPC) used to develop and deploy models. As a result, a significant research and development gap remains between workflow provenance data management and RTAI. In this paper, we present a vision of the pivotal role of workflow provenance in supporting RTAI and discuss related challenges. We present a schematic view between RTAI and provenance, and highlight open research directions.

Santos Souza, Renan↗

DOE OSTI2024

Towards Cross-Facility Workflows Orchestration through Distributed Automation

Modern science relies on end-to-end workflows that incorporate experimental instruments and utilize edge, cloud, or high-performance computing and storage resources. These components are geographically dispersed across various user facilities and interconnected through high-speed networks. In this paper, we present Zambeze, an automated distributed framework designed to facilitate this new class of cross-facility workflows. Utilizing swarm intelligence principles, Zambeze orchestrates science campaigns by managing distributed autonomous agents. These agents can offer a suite of services, including computing, storage, and data management. We demonstrate the feasibility of Zambeze through a real-world application involving electron microscopy, enhanced with Artificial Intelligence capabilities.

Skluzacek, Tyler↗

DOE OSTI2024

Efficacy of using a dynamic length representation vs. a fixed-length for neuroarchitecture search

Deep learning neuroarchitecture and hyperparameter search are important in finding the best configuration that maximizes learned model accuracy. However, the number of types of layers, their associated hyperparameters, and the myriad of ways to connect layers poses a significant computational challenge in discovering ideal model configurations. Here, we assess two different approaches for neuroarchitecture search for a LeNet style neural network, one that uses a fixed-length approach where there is a preset number of possible layers that can be toggled on or off via mutation, and a variable-length approach where layers can be freely added or removed via special mutation operators. We found that the variable-length implementation trained better models while discovering unusual layer configurations worth further exploration.

Coletti, Mark↗

DOE OSTI2024

SAGESim

SAGESim: Scalable Agent-based GPU-Enabled Simulator is a distributed GPU agent-based modeling framework in Python. SAGESim enables researchers to study complex adaptive systems at large scales on high-performance computing systems

Gunaratne, Chathika↗

DOE OSTI2024

A dataset of recorded electricity outages by United States county 2014–2022

In this Data Descriptor, we present county-level electricity outage estimates at 15-minute intervals from 2014 to 2022. By 2022 92% of customers in the 50 US States, Washington DC, and Puerto Rico are represented. These data have been produced by the Environment for Analysis of Geo-Located Energy Information (EAGLE-I TM ), a geographic information system and data visualization platform created at Oak Ridge National Laboratory to map the population experiencing electricity outages every 15 minutes at the county level. Although these data do not cover every US customer, they represent the most comprehensive outage information ever compiled for the United States. The rate of coverage increases through time between 2014 and 2022. We present a quantitative Data Quality Index for these data for the years 2018–2022 to demonstrate temporal changes in customer coverage rates by FEMA region and indicators of data collection gaps or other errors.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2023

Predicted structural proteome of Sphagnum divinum and proteome-scale annotation

Sphagnum-dominated peatlands store a substantial amount of terrestrial carbon. The genus is undersampled and under-studied. No experimental crystal structure from any Sphagnum species exists in the Protein Data Bank and fewer than 200 Sphagnum-related genes have structural models available in the AlphaFold Protein Structure Database. Tools and resources are needed to help bridge these gaps, and to enable the analysis of other structural proteomes now made possible by accurate structure prediction. We present the predicted structural proteome (25,134 primary transcripts) of Sphagnum divinum computed using AlphaFold, structural alignment results of all high-confidence models against an annotated nonredundant crystallographic database of over 90,000 structures, a structure-based classification of putative Enzyme Commission (EC) numbers across this proteome, and the computational method to perform this proteome-scale structure-based annotation.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2023

SuperNeuro: A Fast and Scalable Simulator for Neuromorphic Computing

In many neuromorphic workflows, simulators play a vital role for important tasks such as training spiking neural networks, running neuroscience simulations, and designing, implementing, and testing neuromorphic algorithms. Currently available simulators cater to either neuroscience workflows (e.g., NEST and Brian2) or deep learning workflows (e.g., BindsNET). Problematically, the neuroscience-based simulators are slow and not very scalable, and the deep learning-based simulators do not support certain functionalities that are typical of neuromorphic workloads (e.g., synaptic delay). In this paper, we address this gap in the literature and present SuperNeuro, which is a fast and scalable simulator for neuromorphic computing capable of both homogeneous and heterogeneous simulations as well as GPU acceleration. We also present preliminary results that compare SuperNeuro to widely used neuromorphic simulators such as NEST, Brian2, and BindsNET in terms of computation times. We demonstrate that SuperNeuro can be approximately 10×--300× faster than some of the other simulators for small sparse networks. On large sparse and large dense networks, SuperNeuro can be approximately 2.2×--3.4× faster than the other simulators, respectively.

Date, Prasanna↗

DOE OSTI2023

Multiobjective Hyperparameter Optimization for Deep Learning Interatomic Potential Training Using NSGA-II

Deep neural network (DNN) potentials are an emerging tool for simulation of dynamical atomistic systems, with the promise of quantum mechanical accuracy at speedups of 10000$\times$. As with other DNN methods, hyperparameters used during training can make a substantial difference in model accuracy, and optimal settings vary with dataset. To enable rapid tuning of hyperparameters for DNN potential training, we developed a scalable multiobjective optimization evolutionary algorithm for supercomputers and tested it on the Summit system at the Oak Ridge Leadership Computing Facility (OLCF). The multiobjective approach is required due to the coupling of two learned values defining the potential: the energy and force. Using a large-scale implementation of the NSGA-II algorithm adapted for training DNN potentials, we discovered several optimal multiobjective combinations, including best choices of activation functions, learning rate scaling scheme, and pairing of the two radial cutoffs used in the three dimensional descriptor function.

Coletti, Mark↗

DOE OSTI2023

Structural Models and Sequence Alignment Results of the Desulfovibrio vulgaris Proteome

This dataset contains the structural models for the primary transcripts of the Desulfovibrio vulgaris proteome as well as sequence alignment results for a subset of the encoded proteins. For each protein, the five models inferred from AlphaFold 2 are provided. The largest pTM-scoring model for each protein was energy minimized; this minimized structure as well as its AlphaFold pickle output file are also provided. This set of structures represent an alternate source of models for the D. vulgaris proteome to those available in the AlphaFold Protein Structure Database (AFDB). This is a bit more complicated since the proteins reporting in the AFDB originate from an outdated form of the D. vulgaris sequence. The different versions of the D. vulgaris gene annotation are collected in the Chronology subdirectory; further consideration of these changes on the structural space of the proteome are currently underway. For proteins that have been annotated as hypothetical, sequence alignment results from the HHblits and SAdLSA alignment methods are provided. These methods are often more capable to resolve sequence homology than other methods. Therefore, the results from both HHblits and SAdLSA are provided to identify possible homologs for these challenging proteins. Numerous sequence databases are utilized for these alignments. References AlphaFold v2 Multimer: https://doi.org/10.1101/2021.10.04.463034. References HHblits: hhtps://doi.org/10.1186/s12859-019-3019-7. References SAdLSA: hhtps://doi.org/10.3389/fbinf.2021.689960.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2023

Structural Models of the Rhodopseudomonas palustris Proteome

This dataset contains the structural models for the primary transcripts of the Rhodopseudomonas palustris proteome. For each protein, the five models inferred from AlphaFold 2 are provided. The largest pTM-scoring model for each protein was energy minimized; this minimized structure as well as its AlphaFold pickle output file are also provided. This set of structures represent an alternate source of models for the R. palustris proteome to those available in the AlphaFold Protein Structure Database.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2023

Structural Models and Sequence Alignment Results of the Rhodospirillum rubrum Proteome

This dataset contains the structural models for the primary transcripts of the Rhodospirillum rubrum proteome as well as sequence alignment results for a subset of the encoded proteins. For each protein, the five models inferred from AlphaFold 2 are provided. The largest pTM-scoring model for each protein was energy minimized; this minimized structure as well as its AlphaFold pickle output file are also provided. This set of structures represent an alternate source of models for the R. rubrum proteome to those available in the AlphaFold Protein Structure Database. For proteins that have been annotated as hypothetical, sequence alignment results from the HHblits and SAdLSA alignment methods are provided. These methods are often more capable to resolve sequence homology than other methods. Therefore, the results from both HHblits and SAdLSA are provided to identify possible homologs for these challenging proteins. Numerous sequence databases are utilized for these alignments. References AlphaFold v2 Multimer: https://doi.org/10.1101/2021.10.04.463034. References HHBlits: https://doi.org/10.1186/s12859-019-3019-7. References SAdLSA: https://doi.org/10.3389/fbinf.2021.689960.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2023

Structural models and functional annotations for the Sphagnum divinum proteome

This dataset contains the structural models for the primary transcripts of the Sphagnum divinum proteome. Additionally, for a subset of these proteins, sequence and structural alignment results are provided. This dataset represents the most thorough structural study of a Sphagnum species, also known as peat mosses, by providing three-dimensional atomic resolution structures of the majority of the encoded proteins as well as structural alignment results used in the application of annotating the proteome. References (DOI) AlphaFold v2 Monomer: https://doi.org/10.1038/s41586-021-03819-2. References (DOI) US-align2: https://doi.org/10.1038/s41592-022-01585-1

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2023

EAGLE-I Power Outage Data 2014 - 2022

The provided EAGLE-I historic dataset includes eight years of power outage information at the county level from 2014 to 2022 at 15-minute intervals collected by the EAGLE-I program at ORNL. The data has been collected from utility's public outage maps using an ETL process. The dataset details FIPS code, county name, state name, total number of customers without power, and a date/timestamp. Also included is the EAGLE-I coverage of each state for each year. For detailed metadata, refer to the metadata DOI.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2023

EAGLE-I Power Outage Data Information

This DOI contains information on the EAGLE-I power outage dataset and serves as a blanket DOI for all EAGLE-I historic data. Historic power outage data from specific years have been linked to this DOI.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2022

Neuromorphic Computing for Scientific Applications

Neuromorphic computing technology continues to make strides in the development of new algorithms, devices, and materials. In addition, applications have begun to emerge where neuromorphic computing shows promising results. However, numerous barriers to further development and application remain. In this work, we identify several science areas where neuromorphic computing can either make an immediate impact (within 1 to 3 years) or the societal impact would be extremely high if the technological barriers can be addressed. We identify both opportunities and hurdles to the development of neuromorphic computing technology for these areas. Finally, we discuss future directions that need to be addressed to expand both the development and application of neuromorphic computing.

Patton, Robert↗

DOE OSTI2022

Toward designing effective exascale scientific computing workflows: experiences and best practices

Many fields within scientific computing have embraced advances in big-data analysis and machine learning, which often requires the deployment of large, distributed and complicated workflows that may combine training neural networks, performing simulations, running inference, and performing database queries and data analysis in asynchronous, parallel and pipelined execution frameworks. Such a shift has brought into focus the need for scalable, efficient workflow management solutions with reproducibility, error and provenance handling, traceability, and checkpoint-restart capabilities, among other needs. Here, we discuss challenges and best-practices for deploying exascale-generation computational science workflows on resources at the Oak Ridge Leadership Computing Facility (OLCF). We present our experiences with large-scale deployment of distributed workflows on the Summit supercomputer, including for bioinformatics and computational biophysics, materials science, and deep learning model optimization. We also present problems and solutions created by working within a Python-centric software base on traditional HPC systems, and discuss steps that will be required before the convergence of HPC, AI, and data science can be fully realized. Our results point to a wealth of exciting new possibilities for harnessing this convergence to tackle new scientific challenges.

Coletti, Mark↗

DOE OSTI2022

Avoiding excess computation in asynchronous evolutionary algorithms

Abstract Asynchronous evolutionary algorithms are becoming increasingly popular as a means of making full use of many processors while solving computationally expensive search and optimization problems. These algorithms excel at keeping large clusters fully utilized, but may sometimes inefficiently sample an excess of fast‐evaluating solutions at the expense of higher‐quality, slow‐evaluating ones. We have previously introduced a steady‐state parent selection strategy, SWEET (“Selection whilE EvaluaTing”), that sometimes selects individuals that are still being evaluated and allows them to reproduce early. We perform a takeover‐time analysis that confirms that this strategy gives slow‐evaluating individuals that have higher fitnesses an increased ability to multiply in the population. We also find that SWEET appears effective at improving optimization performance on problems in which solution quality is positively correlated with evaluation time. We evaluate our approach on six simulated real‐valued optimization problems and three real‐world applications: an autonomous vehicle controller problem that involves tuning a spiking neural network and two adversarial EA problems. We further evaluate SWEET versus a basic asynchronous process in a simulated setting. We present evidence that SWEET outperforms basic asynchronous processes in a use‐case in which performance is positively correlated with evaluation time, and performs comparably (and often better) than basic asynchronous processes in several use‐cases where performance is negatively correlated with evaluation time. That said, in the cases where performance and evaluation time are negatively correlated the variance of outcomes for SWEET is notably high.

97 MATHEMATICS AND COMPUTING↗