Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “compiler”

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 1,027 records · Page 57

Health Benefits of Particle Filtration

The evidence of health benefits of particle filtration in homes and commercial buildings is reviewed. Prior reviews of papers published before 2000 are summarized. The results of 16 more recent intervention studies are compiled and analyzed. Also, reviewed are four studies that modeled health benefits of using filtration to reduce indoor exposures to particles from outdoors. Prior reviews generally concluded that particle filtration is, at best, a source of small improvements in allergy and asthma health effects; however, many early studies had weak designs. A majority of recent intervention studies employed strong designs and more of these studies report statistically significant improvements in health symptoms or objective health outcomes, particularly for subjects with allergies or asthma. The percent age improvement in health outcomes is typically modest, for example, 7percent to 25percent. Delivery of filtered air to the breathing zone of sleeping allergic or asthmatic persons may be more consistently effective in improving health than room air filtration. Notable are two studies that report statistically significant improvements, with filtration, in markers that predict future adverse coronary events. From modeling, the largest potential benefits of indoor particle filtration may be reductions in morbidity and mortality from reducing indoor exposures to particles from outdoor air.

54 ENVIRONMENTAL SCIENCES↗

Toward Understanding the Effect of Low-Activity Waste Glass Composition on Sulfur Solubility

The concentration of sulfur in nuclear waste glass melter feed must be maintained below the point where salt accumulates on the melt surface. The allowable concentrations may range from 0.37 to over 2.05 weight percent (of SO3 on a calcined oxide basis). If the amount of sulfur exceeds its tolerance level a molten salt will accumulate and upset melter operations and potentially shorten melter useful life. Therefore relatively conservative limits have been placed on sulfur loading in melter feed which in-turn significantly impacts the amount of glass that will be produced, in particular at the Hanford site. Crucible-scale sulfur solubility data and scaled melter sulfur tolerance data have been collected on simulated Hanford waste glasses over the last 15 years. These data were compiled and analyzed. A model was developed to predict the solubility of SO3 in glass based on 312 individual glass compositions. This model was shown to well represent the data, accounting for over 80% of the variation in data and was well validated. The model was also found to accurately predict the tolerance for sulfur in melter feed based on 19 scaled melter tests. The model is appropriate for control of waste glass processing which includes uncertainty quantification. The model also gives quantitative estimates of component concentration effects on sulfur solubility. The components that most increase sulfur solubility are Li2O > V2O5 ≈ TiO2 < CaO < P2O5 ≈ ZnO. The components that most decrease sulfur solubility are Cl > Cr2O3 > SiO2 ≈ ZrO2 > Al2O3.

Borosilicate↗

Predicting nepheline precipitation in waste glasses using ternary submixture model and machine learning

Nepheline precipitation in nuclear waste glasses during vitrification can be detrimental due to its negative effect on chemical durability. Developing models to accurately predict nepheline precipitation from compositions is important to increase waste loading since existing models can be overly conservative. In this study, an expanded dataset containing 955 glasses was compiled from literature data, where 355 glasses are for high-level waste (HLW). Previously developed submixture models were refitted using the new dataset, where a misclassification rate of 7.8% was achieved. Nine machine learning (ML) algorithms (e.g., k-nearest neighbor, Gaussian process regression, artificial neural network, support vector machine, decision tree, etc.) were applied to evaluate their ability of predicting nepheline precipitation from compositions. Model accuracy, precision, recall/sensitivity, and F1 score were systemically compared between different ML algorithms and modeling protocols. Good model prediction with an accuracy ~0.9 (misclassification rate of ~10%) was observed with different algorithms under certain protocol. This study evaluated various ML models to predict nepheline precipitations in waste glasses, highlighting the importance of data preparation, modeling protocol, and their effect on model stability and reproducibility. The results provide insights into applying ML to predict glass properties and suggest areas for future research on modeling nepheline precipitations.

Lu, Xiaonan↗

A Critical Review of Heliostat Design for Concentrating Solar Thermal Technologies

Heliostat designs have undergone a widespread and eclectic development process, with many unique designs demonstrated. However, recent developments do not show the overall cohort converging toward a globally accepted universal design. Here, this study characterizes heliostats by breaking down and evaluating design traits based on emergent patterns from a comprehensive compilation of known heliostat designs spanning several decades. Four main categories for evaluation emerged: heliostat base, heliostat primary axis, heliostat drive, and facet support. Each of these four categories is further defined by four subtypes so that all heliostats fall into a single subtype within each category. The classified heliostats are ranked, yielding several view slices into the heliostat compilation or a breakdown of heliostats by type. An analysis of the breakdown shows several trends: a scale-up of established designs, new approaches at small to medium scales, and a movement toward greater adoption of linear drives. These trends reflect the most meaningful contributing factors to a proposed trajectory for a new era of heliostat designs striving to meet widely considered cost targets of $\$$50/m 2 or $\$$75/m 2 .

14 SOLAR ENERGY↗

SU-E-J-104: Single Photon Image From PET with Insertable SPECT Collimator for Boron Neutron Capture Therapy: A Feasibility Study

Purpose: The aim of our proposed system is to confirm the feasibility of extraction of two types of images from one positron emission tomography (PET) module with an insertable collimator for brain tumor treatment during the BNCT. Methods: Data from the PET module, neutron source, and collimator was entered in the Monte Carlo n-particle extended (MCNPX) source code. The coincidence events were first compiled on the PET detector, and then, the events of the prompt gamma ray were collected after neutron emission by using a single photon emission computed tomography (SPECT) collimator on the PET. The obtaining of full width at half maximum (FWHM) values from the energy spectrum was performed to collect effective events for reconstructed image. In order to evaluate the images easily, five boron regions in a brain phantom were used. The image profiles were extracted from the region of interest (ROI) of a phantom. The image was reconstructed using the ordered subsets expectation maximization (OSEM) reconstruction algorithm. The image profiles and the receiver operating characteristic (ROC) curve were compiled for quantitative analysis from the two kinds of reconstructed image. Results: The prompt gamma ray energy peak of 478 keV appeared in the energy spectrum with a FWHM of 41 keV (6.4%). On the basis of the ROC curve in Region A to Region E, the differences in the area under the curve (AUC) of the PET and SPECT images were found to be 10.2%, 11.7%, 8.2% (center, Region C), 12.6%, and 10.5%, respectively. Conclusion: We attempted to acquire the PET and SPECT images simultaneously using only PET without an additional isotope. Single photon images were acquired using an insertable collimator on a PET detector. This research was supported by the Leading Foreign Research Institute Recruitment Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science, Information and Communication Technologies (ICT) and Future Planning (MSIP)(Grant No.2009 00420) and the Radiation Technology R and D program (Grant No.2013M2A2A7043498), Republic of Korea.

07 ISOTOPE AND RADIATION SOURCES↗

TH-E-BRD-01: Innovation in (gold) Nanoparticle-Enhanced Therapy

Radiation therapy relies on the concept of delivering high dose to tumor volumes whilst simultaneously aiming to minimize irradiation of healthy tissue. Gold and other metallic nanoparticles (GNPs) have the potential to greatly enhance dose depositions in their close proximity. While it was originally thought that this effect would only be significant for kV photon beams, it has been shown that GNPs also enhance dose and increase cell killing and survival fraction for MV photons as well as protons. GNPs have been shown to be preferentially taken up in tumors, depending on the GNP properties either internalized in the tumor cells or clustering in the tumor vasculature. Therefore GNPs offer an intriguing additional option to target the tumor while sparing healthy tissue. While a growing amount of research shows GNP induced enhancement factors in the order of 1.5 and higher, GNPs have not yet entered into clinical routine. In this symposium we will have three presentations discussing the current status of GNP based research, the potential to include GNPs in radiation therapy and the limitations and problems to use GNPs in the clinic. Physical and biological underpinnings of radiosensitization with gold nano particles An evolving body of recent literature alludes to the potential to sensitize tumors to radiation therapy using metallic nanoparticles. In preclinical studies, the techniques that hold promise for eventual clinical deployment are nanoparticle-assisted radiation dose enhancement and hyperthermic radiosensitization. To understand the underlying nanoparticle-radiation interactions, computational techniques offer an explanation for and predict the biophysical consequences at a nano-/meso-scopic scale. Nonetheless, there are persisting gaps in knowledge relating to the molecular mechanism of action of these radiosensitization approaches — some of these issues will be addressed. Since the literature relating to the diverse disciplines involved in these efforts spans across multiple specialties (clinical radiation oncology, radiation physics, radiation biology, nanotechnology, material science, biomedical engineering, pharmacology, chemistry, and tumor biology) and numerous specialty journals, there is no single compilation of extant research in this arena or forum for merging analogous concepts and paradigms. This symposium will provide such a venue — my presentation will start with familiarizing the audience with the potential applications of metallic nanoparticles in radiation therapy using specific illustrative examples and begin to explore ways to understand the underlying mechanisms of the effects observed. Biological effects of Gold nanoparticles in radiation therapy Gold nanoparticles (GNP) have been investigated as platforms to carry drugs or radio-sensitizing agents to tumors due to the biocompatibility of gold and relative ease of conjugation with therapeutic and targeting moieties. Recently, there has been interest in exploiting the physical properties of gold, specifically the high atomic number, to enhance radiation therapy. When irradiated, gold atoms will produce low energy electrons, depositing energy within a short distance. The ratio of dose deposited in the presence of the GNP to the dose deposited in the absence of GNP is referred to as the dose enhancement factor (DEF). This factor has been shown to depend on the concentration of GNP and the energy of the incident photons. The physics of this process, preliminary in vitro and in vivo experiments and future directions for this nascent field are described in this presentation. Gold Nanoparticles for improved therapeutic outcome in radiation therapy The application of nanoparticles (NPs) for improved therapeutics is at the forefront of cancer nanotechnology. Among other NP systems, gold nanoparticles (GNPs) are extensively used due to its impressive ability to act as both an anticancer drug carrier in chemotherapy and as a dose enhancer in radiotherapy. Cellular uptake of GNPs was dependent on their size. Among GNPs of diameter between 14–74 nm, GNPs of size 50 nm has the highest uptake. Radiosensitization was dependent on the size of the GNPs as well. GNPs of size 50-nm showed the highest radiosensitization enhancement factor compared to GNPs of 14 and 74 nm for lower- (105 kVp) and higher- (6 MVp) energy photons. GNPs used in those studies were predominantly localized in the cell cytoplasm. However, the therapeutic response can be further enhanced if NPs can be effectively targeted into the nucleus. Here, we present an effective strategy for designing a GNP-peptide complex for nuclear targeting. Two peptides were conjugated onto a GNP: One peptide enhanced the uptake while the other peptide enhanced the nuclear delivery. The nuclear-targeted cells displayed a fourfold increase in the therapeutic response when treated with radiation as compared to untargeted ones. DNA double-strand breaks were quantified using radiation-induced foci of γ- H2AX and 53BP1, and a modest increase in the number of foci per nucleus was observed in irradiated cell populations with internalized GNPs. This research will establish a more aggressive NP-based treatment approach for improved outcome in cancer therapy. Learning Objectives: Introduce radiosensitization concepts of metallic nanoparticle and provide the theoretical basis Provide an overview over the size and coating dependence for GNP uptake in cells Provide a compilation of the extant, multi-discipline research on metallic nanoparticles Understand the prospects for future studies and innovations and the potential for applications of metallic nanoparticles in radiation therapy.

60 APPLIED LIFE SCIENCES↗

Building a genome-based understanding of bacterial pH preferences

The environmental preferences of many microbes remain undetermined. This is the case for bacterial pH preferences, which can be difficult to predict a priori despite the importance of pH as a factor structuring bacterial communities in many systems. We compiled data on bacterial distributions from five datasets spanning pH gradients in soil and freshwater systems (1470 samples), quantified the pH preferences of bacterial taxa across these datasets, and compiled genomic data from representative bacterial taxa. While taxonomic and phylogenetic information were generally poor predictors of bacterial pH preferences, we identified genes consistently associated with pH preference across environments. We then developed and validated a machine learning model to estimate bacterial pH preferences from genomic information alone, a model that could aid in the selection of microbial inoculants, improve species distribution models, or help design effective cultivation strategies. More generally, we demonstrate the value of combining biogeographic and genomic data to infer and predict the environmental preferences of diverse bacterial taxa.

59 BASIC BIOLOGICAL SCIENCES↗

A local-view array library for partitioned global address space C++programs

Multidimensional arrays are an important data structure in many scientific applications. Unfortunately, built-in support for such arrays is inadequate in C++, particularly in the distributed setting where bulk communication operations are required for good performance. In this paper, we present a multidimensional library for partitioned global address space (PGAS) programs, supporting the one-sided remote access and bulk operations of the PGAS model. The library is based on Titanium arrays, which have proven to provide good productivity and performance. These arrays provide a local view of data, where each rank constructs its own portion of a global data structure, matching the local view of execution common to PGAS programs and providing maximum flexibility in structuring global data. Unlike Titanium, which has its own compiler with array-specific analyses, optimizations, and code generation, we implement multidimensional arrays solely through a C++library. The main goal of this effort is to provide a library-based implementation that can match the productivity and performance of a compiler-based approach. We implement the array library as an extension to UPC++, a C++library for PGAS programs, and we extend Titanium arrays with specializations to improve performance. We evaluate the array library by porting four Titanium benchmarks to UPC++, demonstrating that it can achieve up to 25% better performance than Titanium without a significant increase in programmer effort..

Kamil, A↗

Trace-Driven Memory Access Pattern Recognition in Computational Kernels. In: WOSC '14 Proceedings of the Second Workshop on Optimizing Stencil Computations

Classifying memory access patterns is paramount to the selection of the right set of optimizations and determination of the parallelization strategy. Static analyses suffer from ambiguities present in source code, which modern compilation techniques, such as profile-guided optimization, alleviate by observing runtime behavior and feeding back into the compilation flow. This paper discusses a dynamic analysis technique for recognizing memory access patterns, with application to the stencils domain, and presents our design and C++ implementation using the memory-tracing tool Gleipnir. Finally, we evaluate and discuss the performance and matching capability of our classifiers in the context of the Polybench scientific benchmark suite, which includes both stencil and matrix computations.

Park, Eunjung↗

Experiences in extending parallware to support OpenACC. In: WACCPD '15 Proceedings of the Second Workshop on Accelerator Programming using Directives, Article No. 4

Porting scientific codes to accelerator-based computers using OpenACC and OpenMP is an important topic for the HPC community. Programmability, performance portability and developer productivity are key issues for the widespread use of these systems. In the scope of general-purpose parallel computing, Parallware is a new commercial OpenMP-enabling source-to-source compiler that automatically adds OpenMP capabilities in scientific programs. Thus, extending Parallware with OpenACC or OpenMP 4.x support would contribute to improve programmability and developer productivity. In contrast, the performance portability of such approach needs to be demonstrated in practice. This paper presents a preliminary study to extend Parallware with OpenACC support for GPU devices. A simple benchmark suite has been designed to mimic important features and computational patterns of real scientific applications. Handcoded OpenACC versions are compared to OpenMP versions automatically generated by Parallware. Performance is evaluated with the PGI OpenACC compiler on systems accelerated with NVIDIA GPUs.

Lobeiras, Jacobo↗

PolyCheck: Dynamic Verification of Iteration Space Transformations on Affine Programs

High-level compiler transformations, especially loop transformations, are widely recognized as critical optimizations to restructure programs to improve data locality and expose parallelism. Guaranteeing the correctness of program transformations is essential, and to date three main approaches have been developed: proof of equivalence of affine programs, matching the execution traces of programs, and checking bit-by-bit equivalence of the outputs of the programs. Each technique suffers from limitations in either the kind of transformations supported, space complexity, or the sensitivity to the testing dataset. In this paper, we take a novel approach addressing all three limitations to provide an automatic bug checker to verify any iteration reordering transformations on affine programs, including non-affine transformations, with space consumption proportional to the original program data, and robust to arbitrary datasets of a given size. We achieve this by exploiting the structure of affine program control- and data-flow to generate at compile-time lightweight checker code to be executed within the transformed program. Experimental results assess the correctness and effectiveness of our method, and its increased coverage over previous approaches.

affine programs↗

Simit: A Language for Physical Simulation

With existing programming tools, writing high-performance simulation code is labor intensive and requires sacrificing readability and portability. Here, the alternative is to prototype simulations in a high-level language like Matlab, thereby sacrificing performance. The Matlab programming model naturally describes the behavior of an entire physical system using the language of linear algebra. However, simulations also manipulate individual geometric elements, which are best represented using linked data structures like meshes. Translating between the linked data structures and linear algebra comes at significant cost, both to the programmer and to the machine. High-performance implementations avoid the cost by rephrasing the computation in terms of linked or index data structures, leaving the code complicated and monolithic, often increasing its size by an order of magnitude. In this article, we present Simit, a new language for physical simulations that lets the programmer view the system both as a linked data structure in the form of a hypergraph and as a set of global vectors, matrices, and tensors depending on what is convenient at any given time. Simit provides a novel assembly construct that makes it conceptually easy and computationally efficient to move between the two abstractions. Using the information provided by the assembly construct, the compiler generates efficient in-place computation on the graph. We demonstrate that Simit is easy to use: a Simit program is typically shorter than a Matlab program; that it is high performance: a Simit program running sequentially on a CPU performs comparably to hand-optimized simulations; and that it is portable: Simit programs can be compiled for GPUs with no change to the program, delivering 4 to 20× speedups over our optimized CPU code.

97 MATHEMATICS AND COMPUTING↗

Verified lifting of stencil computations

This paper demonstrates a novel combination of program synthesis and verification to lift stencil computations from low-level Fortran code to a high-level summary expressed using a predicate language. The technique is sound and mostly automated, and leverages counter-example guided inductive synthesis (CEGIS) to find provably correct translations. Lifting existing code to a high-performance description language has a number of benefits, including maintainability and performance portability. For example, our experiments show that the lifted summaries can enable domain specific compilers to do a better job of parallelization as compared to an off-the-shelf compiler working on the original code, and can even support fully automatic migration to hardware accelerators such as GPUs. We have implemented verified lifting in a system called STNG and have evaluated it using microbenchmarks, mini-apps, and real-world applications. Here, we demonstrate the benefits of verified lifting by first automatically summarizing Fortran source code into a high-level predicate language, and subsequently translating the lifted summaries into Halide, with the translated code achieving median performance speedups of 4.1X and up to 24X for non-trivial stencils as compared to the original implementation.

97 MATHEMATICS AND COMPUTING↗

Static and Dynamic Frequency Scaling on Multicore CPUs

Dynamic voltage and frequency scaling (DVFS) adapts CPU power consumption by modifying a processor’s operating frequency (and the associated voltage). Typical approaches employing DVFS involve default strategies such as running at the lowest or the highest frequency, or observing the CPU’s runtime behavior and dynamically adapting the voltage/frequency configuration based on CPU usage. In this paper, we argue that many previous approaches suffer from inherent limitations, such as not account- ing for processor-specific impact of frequency changes on energy for different workload types. We first propose a lightweight runtime-based approach to automatically adapt the frequency based on the CPU workload, that is agnostic of the processor characteristics. We then show that further improvements can be achieved for affine kernels in the application, using a compile-time characterization instead of run-time monitoring to select the frequency and number of CPU cores to use. Our framework relies on a one-time energy characterization of CPU-specific DVFS profiles followed by a compile-time categorization of loop-based code segments in the application. These are combined to determine a priori of the frequency and the number of cores to use to execute the application so as to optimize energy or energy-delay product, outperforming runtime approach. Extensive evaluation on 60 benchmarks and five multi-core CPUs show that our approach systematically outperforms the powersave Linux governor, while improving overall performance.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Directive-Based, High-Level Programming and Optimizations for High-Performance Computing with FPGAs

Reconfigurable architectures like Field Programmable Gate Arrays (FPGAs) have been used for accelerating computations from several domains because of their unique combination of flexibility, performance, and power efficiency. However, FPGAs have not been widely used for high-performance computing, primarily because of their programming complexity and difficulties in optimizing performance. In this paper, we present a directive-based, high-level optimization framework for high-performance computing with FPGAs, built on top of an OpenACC-to-FPGA translation framework called OpenARC. We propose directive extensions and correspond- ing compile-time optimization techniques to enable the compiler to generate more efficient FPGA hardware configuration files. Empirical evaluation of the proposed framework on an Intel Stratix V with five OpenACC benchmarks from various application domains shows that FPGA-specific optimizations can lead to significant increases in performance across all tested applications. We also demonstrate that applying these high-level directive-based optimizations can allow OpenACC applications to perform similarly to lower-level OpenCL applications with hand-written FPGA-specific optimizations, and offer runtime and power performance benefits compared to CPUs and GPUs.

Lambert, Jacob↗

Optimization and Portability of a Fusion OpenACC-based FORTRAN HPC Code from NVIDIA to AMD GPUs

NVIDIA has been the main provider of GPU hardware in HPC systems for over a decade. Most applications that benefit from GPUs have thus been developed and optimized for the NVIDIA software stack. Recent exascale HPC systems are, however, introducing GPUs from other vendors, e.g. with the AMD GPU-based OLCF Frontier system just becoming available. AMD GPUs cannot be directly accessed using the NVIDIA software stack, and require a porting effort by the application developers. This paper provides an overview of our experience porting and optimizing the CGYRO code, a widely-used fusion simulation tool based on FORTRAN with OpenACC-based GPU acceleration. While the porting from the NVIDIA compilers was relatively straightforward using the CRAY compilers on the AMD systems, the performance optimization required more fine-tuning. In the optimization effort, we uncovered code sections that had performed well on NVIDIA GPUs, but were unexpectedly slow on AMD GPUs. After AMD-targeted code optimizations, performance on AMD GPUs has increased to meet our expectations. Modest speed improvements were also seen on NVIDIA GPUs, which was an unexpected benefit of this exercise.

Sfiligoi, Igor↗

ARQUIN: Architectures for Multinode Superconducting Quantum Computers

Many proposals to scale quantum technology rely on modular or distributed designs wherein individual quantum processors, called nodes, are linked together to form one large multinode quantum computer (MNQC). One scalable method to construct an MNQC is using superconducting quantum systems with optical interconnects. However, internode gates in these systems may be two to three orders of magnitude noisier and slower than local operations. Surmounting the limitations of internode gates will require improvements in entanglement generation, use of entanglement distillation, and optimized software and compilers. Still, it remains unclear what performance is possible with current hardware and what performance algorithms require. In this article, we employ a systems analysis approach to quantify overall MNQC performance in terms of hardware models of internode links, entanglement distillation, and local architecture. We show how to navigate tradeoffs in entanglement generation and distillation in the context of algorithm performance, lay out how compilers and software should balance between local and internode gates, and discuss when noisy quantum internode links have an advantage over purely classical links. Here, we find that a factor of 10–100× better link performance is required and introduce a research roadmap for the co-design of hardware and software towards the realization of early MNQCs. While we focus on superconducting devices with optical interconnects, our approach is general across MNQC implementations.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Mojo: MLIR-based Performance-Portable HPC Science Kernels on GPUs for the Python Ecosystem

We explore the performance and portability of the novel Mojo language for scientific computing workloads on GPUs. As the first language based on the LLVM’s Multi-Level Intermediate Representation (MLIR) compiler infrastructure, Mojo aims to close performance and productivity gaps by combining Python’s interoperability and CUDA-like syntax for compile-time portable GPU programming. We target four scientific workloads: a seven-point stencil (memory-bound), BabelStream (memory-bound), miniBUDE (compute-bound), and Hartree–Fock (compute-bound with atomic operations); and compare their performance against vendor baselines on NVIDIA H100 and AMD MI300A GPUs. We show that Mojo’s performance is competitive with CUDA and HIP for memory-bound kernels, whereas gaps exist on AMD GPUs for atomic operations and for fast-math compute-bound kernels on both AMD and NVIDIA GPUs. Although the learning curve and programming requirements are still fairly low-level, Mojo can close significant gaps in the fragmented Python ecosystem in the convergence of scientific computing and AI.

Godoy, William [ORNL] (ORCID:0000000225905178)↗