SEARCH · Search NASA
Results for “program compilers”
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.
A pervasive parallel framework for visualization: final report for FWP 10-014707
We are on the threshold of a transformative change in the basic architecture of highperformance computing. The use of accelerator processors, characterized by large core counts, shared but asymmetrical memory, and heavy thread loading, is quickly becoming the norm in high performance computing. These accelerators represent significant challenges in updating our existing base of software. An intrinsic problem with this transition is a fundamental programming shift from message passing processes to much more fine thread scheduling with memory sharing. Another problem is the lack of stability in accelerator implementation; processor and compiler technology is currently changing rapidly. This report documents the results of our three-year ASCR project to address these challenges. Our project includes the development of the Dax toolkit, which contains the beginnings of new algorithms for a new generation of computers and the underlying infrastructure to rapidly prototype and build further algorithms as necessary.
Personal Insights and Anecdotes about the Weatherization Assistance Program Process Field Study
The present report is based on the research conducted for the Process Field Study between March and September 2011. The Process Field Study documents how Weatherization Assistance Program (WAP) services were delivered to clients, and the quality with which those services were delivered. The assessments were conducted by visiting 19 agencies in 19 states around the country interviewing agency managers, staff, and contractors; observing program intake along, with 43 audits, 45 measure installation and 37 final inspections; and conducting debriefing interviews with clients and weatherization staff following the observation of service delivery. In this report, we turn to detailed observations of a few field interactions. The client stories from our observations illustrate some of the ways clients and crew interact to build the success of the program, but shows there will always be unanticipated obstacles to building trust and getting the program to the public. Stories of staff and crew career paths indicate that weatherization technology and techniques are being learned and used by technicians out of the new home construction industry and that their new knowledge provides them with technical tools and methods that many hope to take back into the construction industry if and when they return. This report is organized according to the four stages of weatherization: intake, audit, installation, and inspection. It contributes to our understanding of the area where policy, environment, culture, and individual decisions influence social innovation. The anecdotes reveal the realities of implementing programs for the benefit of the greater good at minimal cost and sacrifice in times of ever restricting budgets. As the authors revisited their field notes and compiled memorable narratives to communicate the essence of the weatherization experience, they identified three key takeaways that summarize the major issues. First, in WAP as in all services there will always be challenges to reaching the community needing to be served. Second, crew and staff learn new skills and gain experience that can be and are applied in jobs elsewhere. Finally, in the best cases, changes from the weatherization experience permeate communities in unanticipated ways.
Using a Large Language Model as a Building Block to Generate Usable Validation and Verification Suite for OpenMP
In the HPC area, both hardware and software move quickly. Often new hardware is developed and deployed, the corresponding software stack, including compilers and other tools, are under active development while leading edge software developers are working to port and tune their applications, all at the same time. While the software ecosystem is in flux, one of the key challenges for users is obtaining insight into the state of implementation of key features in the programming languages and models their applications are using – whether they have been implemented, and whether the implementation conforms to the specification, especially for newly implemented features (less tested by widespread use). OpenMP is one of the most prominent shared memory programming models used for on-node programming in HPC. With the shift towards accelerators (such as GPUs and FPGAs) and heterogeneous programming OpenMP features are getting more complex. It is natural to ask whether generative AI approaches, and large language models (LLMs) in particular, can help in producing validation and verification test suites to allow users better and faster insights into the availability and correctness of OpenMP features of interest. In this work, we explore the use of ChatGPT-4 to generate a suite of tests for OpenMP features. We have chosen a set of directives and clauses, a total of 78 combinations, which first appeared in OpenMP 3.0 (released in May 2008) but are also relevant for accelerators. We prompted ChatGPT to generate tests in the C and Fortran languages, for both host (CPU) and device (accelerator). On the Summit super-computer using the GNU implementation, we found that, of the 78 generated tests 67 C tests and 43 Fortran tests compiled successfully and fewer than those executed to completion. On further analysis we show that not all generated tests are valid. We document the process, results, and provide detailed analysis regarding the quality of tests generated. With the aim of providing input to a production quality validation and verification suite, we manually implement the corrections required to make the tests valid according to the current OpenMP specification. We quantify this effort as small, medium, or large, and record the lines of code changed to correct the invalid tests. With the corrected tests we validate recent implementations from HPE, AMD, and GNU on the Frontier supercomputer. Our experiment and subsequent analysis show that although LLMs are capable of producing HPC specific codes, they are limited by their understanding of the deeper semantics and restrictions of programming models such as OpenMP. Unsurprisingly more commonly used features have better support, while some OpenMP 3.0 directives such as sections and tasking are not universally supported on accelerators. We demonstrate that successful compilation and execution to completion are inadequate metrics for evaluating generated code and that, at this time, commodity LLMs require expert intervention for code verification. This points to gaps in the training data that is currently available for HPC. We demonstrate that with "small" effort 37% of generated invalid C tests and 63% of generated invalid Fortran tests could be corrected. This improves productivity of test generation as we circumvent writing from scratch and the common programming errors associated with it.
SPEL: Software tool for Porting E3SM Land Model with OpenACC in a Function Unit Test Framework
Most high-end computers adopt hybrid architecture, porting a large-scale scientific code onto accelerators is necessary. The paper presents a generic method for porting large-scale scientific code onto accelerators using compiler directives within a modularized function unit test platform. We have implemented the method and designed a software tool (SPEL) to port the E3SM Land Model (ELM) onto the GPUs in the Summit computer. SPEL automatically generates GPU-ready test modules for all ELM functions, such as CanopyFlux, SoilTemperature, and EcosystemDynamics. SPEL breaks the ELM into a collection of standalone unit test programs for easy code verification and further performance improvement. We further optimize several ELM test modules with advanced techniques, including memory reduction, reconstructed parallel loops, and asynchronous GPU kernel launch. We hope our study will inspire new toolkit developments that expedite large-scale scientific code porting with compiler directives.
Rainwater Harvesting State Regulations and Technical Resources
Pacific Northwest National Laboratory (PNNL) conducted in-depth research of state-level rainwater harvesting regulations for the Federal Energy Management Program (FEMP) to help federal agencies strategically identify locations conducive to rainwater harvesting projects. Currently, rainwater harvesting is not regulated by the federal government but rather it is up to individual states to regulate the collection and use of rainwater. There is no centralized information on state-level regulations on rainwater harvesting maintained by a federal agency or outside organization. To fill this information gap, PNNL performed detailed internet searches for each state, which included state agencies, universities, Cooperative Extension Offices, city governments, and related organizations. The state-by-state information on rainwater harvesting regulations was compiled and assembled into an interactive map that is color coded by state regulations. The map provides a visual representation of the general types of rainwater harvesting policies across the country as well as general information on the state programs if applicable. The map allows the user to quickly discern where rainwater harvesting is supported and regulated by the state. This map will be available on the FEMP website by September 2015.
Concepts and Meta-Programming Library
CAMP provides a portable optimized implementation of template meta-programming primitives. All capabilities found within are available in other open source projects, including metal and mpl among others, but no other library we know of supports all compilers required by LLNL codes. CAMP serves as an efficient facility for writing portable compile-time operations in C++ codes. It was developed as part of the RAJA project to facilitate more complex compile-time introspection and better error message delivery to users, but has since proven useful in Umpire, CHAI and other pre-release LLNL software projects and is thus being re-factored to stand alone. The CAMP library uses portable C++ template mechanisms almost exclusively, with the exception of intrinsics provided for performance by some compilers such as clang and gee. There are no private or protected interfaces and no proprietary information included in the source. Any and all future versions will limit themselves to implementing commonly available and well known primitives for compile-time manipulation of types. A new public github repository will be created to host the code independent of its current location in the raja repository, likely at github.com/llnl/camp.
Fusion Materials Semiannual Progress Report for the Period Ending December 31, 2022
This is the seventy-third in a series of semiannual technical progress reports on fusion materials science activity supported by the Fusion Energy Sciences Program of the U.S. Department of Energy. It covers the period ending December 31, 2022. This report focuses on research addressing the effects on materials properties and performance of exposure to the neutronic, thermal and chemical environments anticipated in the chambers of fusion experiments and energy systems. This research is a major element of the national effort to establish the materials knowledge base for an economically and environmentally attractive fusion energy source. Research activities on issues related to the interaction of materials with plasmas are reported separately. The results reported are the products of a national effort involving a number of national laboratories and universities. A large fraction of this work, particularly in relation to fission reactor irradiations, is carried out collaboratively with partners in Japan, Russia, and the European Union. The purpose of this series of reports is to provide a working technical record for the use of program participants, and to provide a means of communicating the efforts of fusion materials scientists to the broader fusion community, both nationally and worldwide. This report has been compiled by Stephanie Melton, Oak Ridge National Laboratory. Her efforts, and the efforts of the many persons who made technical contributions, are gratefully acknowledged.
Fusion Materials Semiannual Progress Report for the Period Ending June 30, 2024
This is the seventy-sixth in a series of semiannual technical progress reports on fusion materials science activity supported by the Fusion Energy Sciences Program of the U.S. Department of Energy. It covers the period ending June 30, 2024. This report focuses on research addressing the effects on materials properties and performance of exposure to the neutronic, thermal and chemical environments anticipated in the chambers of fusion experiments and energy systems. This research is a major element of the national effort to establish the materials knowledge base for an economically and environmentally attractive fusion energy source. Research activities on issues related to the interaction of materials with plasmas are reported separately. The results reported are the products of a national effort involving a number of national laboratories and universities. A large fraction of this work, particularly in relation to fission reactor irradiations, is carried out collaboratively with partners in Japan, Russia, and the European Union. The purpose of this series of reports is to provide a working technical record for the use of program participants, and to provide a means of communicating the efforts of fusion materials scientists to the broader fusion community, both nationally and worldwide. This report has been compiled by Stephanie Melton, Oak Ridge National Laboratory. Her efforts, and the efforts of the many persons who made technical contributions, are gratefully acknowledged.
Fusion Materials Semiannual Progress Report for the Period Ending June 30, 2025
This is the seventy-eighth in a series of semiannual technical progress reports on fusion materials science activity supported by the Fusion Energy Sciences Program of the U.S. Department of Energy. It covers the period ending June 30 th , 2025. This report focuses on research addressing the effects on materials properties and performance of exposure to the neutronic, thermal and chemical environments anticipated in the chambers of fusion experiments and energy systems. This research is a major element of the national effort to establish the materials knowledge base for an economically and environmentally attractive fusion energy source. Research activities on issues related to the interaction of materials with plasmas are reported separately. The results reported are the products of a national effort involving a number of national laboratories and universities. A large fraction of this work, particularly in relation to fission reactor irradiations, is carried out collaboratively with international partners, e.g., Japan and the UK. The purpose of this series of reports is to provide a working technical record for the use of program participants, and to provide a means of communicating the efforts of fusion materials scientists to the broader fusion community, both nationally and worldwide. This report has been compiled by Stephanie Melton, Oak Ridge National Laboratory. Her efforts, and the efforts of the many persons who made technical contributions, are gratefully acknowledged.
Radiological data consolidation and 3D modeling of a building - 15473
A portion of a building at an industrial facility that conducted monazite sands-processing operations in the 1950's under contract to the Atomic Energy Commission (AEC) became contaminated. Subsequently the U.S. Department of Energy designated the facility for remedial action under the Formerly Used Sites Remedial Action Program (FUSRAP). Remedial investigation, remedial actions and post-remediation surveys have been conducted in portions of the building. Radiological data for the interior of the building were compiled, evaluated and presented in a three dimensional (3-D) model (the model) created by AMEC Foster Wheeler in order to identify areas that meet the Record of Decision (ROD) cleanup criteria, and identity areas that may require remedial action or may require additional investigation due to data gaps. The data from different phases of investigation and remediation cover different portions of the building and in some cases overlap. In addition, the data were collected over a period of more than ten years, for different objectives, and thus the instruments and methods for establishing efficiency were not necessarily consistent. The data consolidation process included determining the relative quality of data points to include in the model and the development of rationale associated with assigning a quality level (i.e. ranking) to each data point. The rationale for ranking data quality included, as the primary determining factors, chronological order of the data (most recent was ranked as more reliable), certainty of the sample locations within the building, and analytical data quality. A 3-D model of the building was created using a laser point cloud scan which was then converted into a 3-D design model. Sample locations were then entered into the model and linked with the analytical database to allow display of the radiological results in the model. The visual model allows both strategic and tactical decisions to be made, depending on the level of detail examined. The evaluation process allowed maximum use of the historical data set, rather than requiring older data to be disregarded, and provided at a minimum a qualitative sense of data quality/confidence in the data. The (authors)process also highlights the importance of collecting high quality data from the very beginning with a consistent locational coordinate system, and the need for a good visualization model in order to assess contaminant locations during remedial action or post-remediation surveys.
Towards Automated Generation of Chiplet-Based Systems
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 high-level frontend, SODA-OPT, which leverages the multilevel intermediate representation (MLIR) framework to interface with productive programming tools (e.g., machine learning frameworks), 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 talk will discuss ongoing work on the SODA synthesizer to enable no-human-in-the-loop generation and design space exploration of the chiplets for highly specialized artificial intelligence accelerators. Connecting these highly specialized chiplets to general-purpose cores or programmable accelerators will allow to quickly deploy autonomous systems for scientific discovery.
Data Compilation for AGR-2 UCO Baseline Compact Lot LEU07-OP1-Z
This document is a compilation of characterization data for the candidate AGR-2 UCO Baseline fuel compact lot LEU07-OPI-Z. The compacts were produced by ORNL for the Advanced Gas Reactor Fuel Development and Qualification (AGR) program for the second AGR irradiation test (AGR-2). This compact lot was fabricated using particle composite LEU07. LEU07 came from Babcock and Wilcox (B&W) coated particle lot G73J-14-92072A, which was an upgraded batch of TRISO-coated 425 μm diameter, 14% low enrichment uranium oxide/uranium carbide kernels (LEUCO). The AGR-2 TRISO-coated particles consist of a spherical kernel coated with an ~50% dense carbon buffer layer (100 μm nominal thickness), followed by a SiC layer (35 μm nominal thickness), followed by another dense outer pyrocarbon layer (40 μm nominal thickness). The kernels were also manufactured by B&W and identified as kernel lot G73I-14-69307. Two data packages were submitted by B&W containing the acceptance testing results for the kernels and coated particles, these are identified by their lot numbers. A discussion on the coating of the B&W TRISO particles can also be found in INL report INL/EXT-09-16545. A data compilation of ORNL analysis of G73J-14-93072A can be found in ORNL/TM-2008/133. The AGR-2 Fuel Specification (INL SPC-923) provides the requirements necessary for acceptance of the fuel manufactured for the AGR-2 irradiation test. Section 3.3 of SPC-923 provides the property requirements for the heat treated compacts. The Statistical Sampling Plan for AGR-2 Fuel Materials (INL PLN-2691) provides additional guidance regarding statistical methods for product acceptance and recommended sample sizes. The procedures for characterizing and qualifying the compacts are outlined in ORNL product inspection plan AGR-CHAR-PIP-11 to obtain data needed for calculation of compacting charge weight and matrix density. Riffling of compact charges is also covered by this procedure. Prior to overcoating, the TRISO particles are characterized per ORNL product inspection plan AGR-CHAR-PIP-10 to determine uranium content, obtain data need for overcoating and compact fabrication, and obtain further data needed for calculation of matrix density. Riffling of overcoater charges is also covered by this procedure. This document contains all the inspection report forms and data report forms generated by these inspection plans. In addition to the characterization data, this report also contains other records relevant to the fuel product acceptance. A history of the material flow and sample naming is included. The overcoating and compacting process is summarized. A record of the materials use to make the matrix is also included. A Certificate of Conformance and any applicable Nonconformance Reports are attached as Appendices.
Data Compilation for AGR-2 UCO Variant Compact Lot LEU06-OP1-Z
This document is a compilation of characterization data for the candidate AGR-2 UCO Baseline fuel compact lot LEU07-OPI-Z. The compacts were produced by ORNL for the Advanced Gas Reactor Fuel Development and Qualification (AGR) program for the second AGR irradiation test (AGR-2). This compact lot was fabricated using particle composite LEU07. LEU07 came from Babcock and Wilcox (B&W) coated particle lot G73J-14-92072A, which was an upgraded batch of TRISO-coated 425 μm diameter, 14% low enrichment uranium oxide/uranium carbide kernels (LEUCO). The AGR-2 TRISO-coated particles consist of a spherical kernel coated with an ~50% dense carbon buffer layer (100 μm nominal thickness), followed by a SiC layer (35 μm nominal thickness), followed by another dense outer pyrocarbon layer (40 μm nominal thickness). The kernels were also manufactured by B&W and identified as kernel lot G73I-14-69307. Two data packages were submitted by B&W containing the acceptance testing results for the kernels and coated particles, these are identified by their lot numbers. A discussion on the coating of the B&W TRISO particles can also be found in INL report INL/EXT-09-16545. A data compilation of ORNL analysis of G73J-14-93072A can be found in ORNL/TM-2008/133. The AGR-2 Fuel Specification (INL SPC-923) provides the requirements necessary for acceptance of the fuel manufactured for the AGR-2 irradiation test. Section 3.3 of SPC-923 provides the property requirements for the heat treated compacts. The Statistical Sampling Plan for AGR-2 Fuel Materials (INL PLN-2691) provides additional guidance regarding statistical methods for product acceptance and recommended sample sizes. The procedures for characterizing and qualifying the compacts are outlined in ORNL product inspection plan AGR-CHAR-PIP-11 to obtain data needed for calculation of compacting charge weight and matrix density. Riffling of compact charges is also covered by this procedure. Prior to overcoating, the TRISO particles are characterized per ORNL product inspection plan AGR-CHAR-PIP-10 to determine uranium content, obtain data need for overcoating and compact fabrication, and obtain further data needed for calculation of matrix density. Riffling of overcoater charges is also covered by this procedure. This document contains all the inspection report forms and data report forms generated by these inspection plans. In addition to the characterization data, this report also contains other records relevant to the fuel product acceptance. A history of the material flow and sample naming is included. The overcoating and compacting process is summarized. A record of the materials use to make the matrix is also included. A Certificate of Conformance and any applicable Nonconformance Reports are attached as Appendices.
Rainwater Harvesting State Regulations and Technical Resources
Pacific Northwest National Laboratory (PNNL) conducted in-depth research of state-level rainwater harvesting regulations for the Federal Energy Management Program (FEMP) to help federal agencies strategically identify locations conducive to rainwater harvesting projects. Currently, rainwater harvesting is not regulated by the federal government; instead it is up to individual states to regulate the collection and use of rainwater. There is no centralized information about state-level regulations on rainwater harvesting maintained by a federal agency or outside organization. To fill this information gap, PNNL performed detailed internet searches for each state, which included researching regulations associated with state agencies, universities, Cooperative Extension Offices, city governments, and related organizations. The state-by-state information about rainwater harvesting regulations was compiled and assembled into an interactive map that is color coded by state regulations. The map provides a visual representation of the general types of rainwater harvesting policies across the country as well as general information about the state programs if applicable. The map allows the user to quickly discern where rainwater harvesting is supported and regulated by the state. This map was created in June 2015 and the data were updated in June 2019.
Data Compilation for AGR-2 UCO Variant Compact Lot LEU09-OP2-Z
This document is a compilation of characterization data for the candidate AGR-2 UCO Variant fuel compact lot LEU09-OP2-Z. The compacts were produced by ORNL for the Advanced Gas Reactor Fuel Development and Qualification (AGR) program for the second AGR irradiation test (AGR-2). This compact lot was fabricated using particle composite LEU09. LEU09 came from Babcock and Wilcox (B&W) coated particle lot G73J-14-93073A, which was an upgraded batch of TRISO-coated 425 μm diameter, 14% low enriched uranium oxide/uranium carbide kernels (LEUCO). The AGR-2 TRISO-coated particles consist of a spherical kernel coated with an ~50% dense carbon buffer layer (100 μm nominal thickness), followed by a dense inner pyrocarbon layer (40 μm nominal thickness), followed by a SiC layer (35 μm nominal thickness), followed by another dense outer pyrocarbon layer (40 μm nominal thickness). The kernels were also manufactured by B&W and identified as kernel lot G73I-14-69307. Two data packages were submitted by B&W containing the acceptance testing results for the kernels and coated particles, these are identified by their lot numbers. A discussion on the coating of the B&W TRISO particles can also be found in INL report INL/EXT-09-16545. A data compilation of ORNL analysis of G73J-14-93073A can be found in ORNL/TM-2008/134. The AGR-2 Fuel Specification (INL SPC-923) provides the requirements necessary for acceptance of the fuel manufactured for the AGR-2 irradiation test. Section 3.3 of SPC-923 provides the property requirements for the heat treated compacts. The Statistical Sampling Plan for AGR-2 Fuel Materials (INL PLN-2691) provides additional guidance regarding statistical methods for product acceptance and recommended sample sizes. The procedures for characterizing and qualifying the compacts are outlined in ORNL product inspection plan AGRCHAR- PIP-12. The inspection report forms generated by this product inspection plan document the product acceptance for the property requirements listed in section 3.3 of SPC-923. Prior to compacting, the overcoated particles are characterized per ORNL product inspection plan AGRCHAR- PIP-11 to obtain data needed for calculation of compacting charge weight and matrix density. Riffling of compact charges is also covered by this procedure. Prior to overcoating, the TRISO particles are characterized per ORNL product inspection plan AGR-CHAR-PIP-10 to determine uranium content, obtain data needed for overcoating and compact fabrication, and obtain further data needed for calculation of matrix density. Riffling of overcoater charges is also covered by this procedure. This document contains all the inspection report forms and data report forms generated by these inspection plans. In addition to the characterization data, this report also contains other records relevant to the fuel product acceptance. A history of the material flow and sample naming is included. The overcoating and compacting process is summarized, and a record of the materials used to make the matrix is included. A Certificate of Conformance and any applicable Nonconformance Reports are attached as Appendices.
Evaluating performance and portability of high-level programming models: Julia, Python/Numba, and Kokkos on exascale nodes
We explore the performance and portability of the high-level programming models: the LLVM-based Julia and Python/Numba, and Kokkos on high-performance computing (HPC) nodes: AMD Epyc CPUs and MI250X graphical processing units (GPUs) on Frontier’s test bed Crusher system and Ampere’s Arm-based CPUs and NVIDIA’s A100 GPUs on the Wombat system at the Oak Ridge Leadership Computing Facilities. We compare the default performance of a hand-rolled dense matrix multiplication algorithm on CPUs against vendor-compiled C/OpenMP implementations, and on each GPU against CUDA and HIP. Rather than focusing on the kernel optimization per-se, we select this naive approach to resemble exploratory work in science and as a lower-bound for performance to isolate the effect of each programming model. Julia and Kokkos perform comparably with C/OpenMP on CPUs, while Julia implementations are competitive with CUDA and HIP on GPUs. Performance gaps are identified on NVIDIA A100 GPUs for Julia’s single precision and Kokkos, and for Python/Numba in all scenarios. We also comment on half-precision support, productivity, performance portability metrics, and platform readiness. We expect to contribute to the understanding and direction for high-level, high-productivity languages in HPC as the first-generation exascale systems are deployed.
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.