Search NASA⌕ Search

SEARCH · Search NASA

Results for “Compiler Optimizations”

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 217 records · Page 12
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Experiences in porting mini-applications to OpenACC and OpenMP on heterogeneous systems

This article studies mini-applications—Minisweep, GenASiS , GPP, and FF—that use computational methods commonly encountered in HPC. We have ported these applications to develop OpenACC and OpenMP versions, and evaluated their performance on Titan (Cray XK7 with K20x GPUs), Cori (Cray XC40 with Intel KNL), Summit (IBM AC922 with Volta GPUs), and Cori-GPU (Cray CS-Storm 500NX with Intel Skylake and Volta GPUs). Our goals are for these new ports to be useful to both application and compiler developers, to document and describe the lessons learned and the methodology to create optimized OpenMP and OpenACC versions, and to provide a description of possible migration paths between the two specifications. Cases where specific directives or code patterns result in improved performance for a given architecture are highlighted. Here, we also include discussions of the functionality and maturity of the latest compilers available on the above platforms with respect to OpenACC or OpenMP implementations.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2017

Optimizing Performance of Combustion Chemistry Solvers on Intel's Many Integrated Core (MIC) Architectures

This work investigates novel algorithm designs and optimization techniques for restructuring chemistry integrators in zero and multidimensional combustion solvers, which can then be effectively used on the emerging generation of Intel's Many Integrated Core/Xeon Phi processors. These processors offer increased computing performance via large number of lightweight cores at relatively lower clock speeds compared to traditional processors (e.g. Intel Sandybridge/Ivybridge) used in current supercomputers. This style of processor can be productively used for chemistry integrators that form a costly part of computational combustion codes, in spite of their relatively lower clock speeds. Performance commensurate with traditional processors is achieved here through the combination of careful memory layout, exposing multiple levels of fine grain parallelism and through extensive use of vendor supported libraries (Cilk Plus and Math Kernel Libraries). Important optimization techniques for efficient memory usage and vectorization have been identified and quantified. These optimizations resulted in a factor of ~ 3 speed-up using Intel 2013 compiler and ~ 1.5 using Intel 2017 compiler for large chemical mechanisms compared to the unoptimized version on the Intel Xeon Phi. The strategies, especially with respect to memory usage and vectorization, should also be beneficial for general purpose computational fluid dynamics codes.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1977

A survey of compiler development aids

A theoretical background was established for the compilation process by dividing it into five phases and explaining the concepts and algorithms that underpin each. The five selected phases were lexical analysis, syntax analysis, semantic analysis, optimization, and code generation. Graph theoretical optimization techniques were presented, and approaches to code generation were described for both one-pass and multipass compilation environments. Following the initial tutorial sections, more than 20 tools that were developed to aid in the process of writing compilers were surveyed. Eight of the more recent compiler development aids were selected for special attention - SIMCMP/STAGE2, LANG-PAK, COGENT, XPL, AED, CWIC, LIS, and JOCIT. The impact of compiler development aids were assessed some of their shortcomings and some of the areas of research currently in progress were inspected.

Buckles, B. P.↗
NASA NTRS1993

RIACS/USRA

The Research Institute for Advanced Computer Science (RIACS) was established by the Universities Space Research Association (USRA) at the NASA Ames Research Center (ARC) on 6 June 1983. RIACS is privately operated by USRA, a consortium of universities with research programs in the aerospace sciences, under contract with NASA. The primary mission of RIACS is to provide research and expertise in computer science and scientific computing to support the scientific missions of NASA ARC. The research carried out at RIACS must change its emphasis from year to year in response to NASA ARC's changing needs and technological opportunities. A flexible scientific staff is provided through a university faculty visitor program, a post doctoral program, and a student visitor program. Not only does this provide appropriate expertise but it also introduces scientists outside of NASA to NASA problems. A small group of core RIACS staff provides continuity and interacts with an ARC technical monitor and scientific advisory group to determine the RIACS mission. RIACS activities are reviewed and monitored by a USRA advisory council and ARC technical monitor. Research at RIACS is currently being done in the following areas: Parallel Computing, Advanced Methods for Scientific Computing, High Performance Networks and Technology, and Learning Systems. Parallel compiler techniques, adaptive numerical methods for flows in complicated geometries, and optimization were identified as important problems to investigate for ARC's involvement in the Computational Grand Challenges of the next decade.

Oliger, Joseph↗
NASA NTRS1996

Development and Demonstration of an Ada Test Generation System

In this project we have built a prototype system that performs Feasible Path Analysis on Ada programs: given a description of a set of control flow paths through a procedure, and a predicate at a program point feasible path analysis determines if there is input data which causes execution to flow down some path in the collection reaching the point so that tile predicate is true. Feasible path analysis can be applied to program testing, program slicing, array bounds checking, and other forms of anomaly checking. FPA is central to most applications of program analysis. But, because this problem is formally unsolvable, syntactic-based approximations are used in its place. For example, in dead-code analysis the problem is to determine if there are any input values which cause execution to reach a specified program point. Instead an approximation to this problem is computed: determine whether there is a control flow path from the start of the program to the point. This syntactic approximation is efficiently computable and conservative: if there is no such path the program point is clearly unreachable, but if there is such a path, the analysis is inconclusive, and the code is assumed to be live. Such conservative analysis too often yields unsatisfactory results because the approximation is too weak. As another example, consider data flow analysis. A du-pair is a pair of program points such that the first point is a definition of a variable and the second point a use and for which there exists a definition-free path from the definition to the use. The sharper, semantic definition of a du-pair requires that there be a feasible definition-free path from the definition to the use. A compiler using du-pairs for detecting dead variables may miss optimizations by not considering feasibility. Similarly, a program analyzer computing program slices to merge parallel versions may report conflicts where none exist. In the context of software testing, feasibility analysis plays an important role in identifying testing requirements which are infeasible. This is especially true for data flow testing and modified condition/decision coverage. Our system uses in an essential way symbolic analysis and theorem proving technology, and we believe this work represents one of the few successful uses of a theorem prover working in a completely automatic fashion to solve a problem of practical interest. We believe this work anticipates an important trend away from purely syntactic-based methods for program analysis to semantic methods based on symbolic processing and inference technology. Other results demonstrating the practical use of automatic inference is being reported in hardware verification, although there are significant differences between the hardware work and ours. However, what is common and important is that general purpose theorem provers are being integrated with more special-purpose decision procedures to solve problems in analysis and verification. We are pursuina commercial opportunities for this work, and will use and extend the work in other projects we are engaged in. Ultimately we would like to rework the system to analyze C, C++, or Java as a key step toward commercialization.

Source record↗
DOE OSTI2021

Optimized Quantum Program Execution Ordering to Mitigate Errors in Simulations of Quantum Systems

Simulating the time evolution of a physical system at quantum mechanical levels of detail - known as Hamiltonian Simulation (HS) - is an important and interesting problem across physics and chemistry. For this task, algorithms that run on quantum computers are known to be exponentially faster than classical algorithms; in fact, this application motivated Feynman to propose the construction of quantum computers. Nonetheless, there are challenges in reaching this performance potential. Prior work has focused on compiling circuits (quantum programs) for HS with the goal of maximizing either accuracy or gate cancellation. Our work proposes a compilation strategy that simultaneously advances both goals. At a high level, we use classical optimizations such as graph coloring and travelling salesperson to order the execution of quantum programs. Specifically, we group together mutually commuting terms in the Hamiltonian (a matrix characterizing the quantum mechanical system) to improve the accuracy of the simulation. We then rearrange the terms within each group to maximize gate cancellation in the final quantum circuit. Furthermore, these optimizations work together to improve HS performance and result in an average 40% reduction in circuit depth. This work advances the frontier of HS which in turn can advance physical and chemical modeling in both basic and applied sciences.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Optimized thermodynamic properties of REE aqueous species (REE 3+ and REEOH 2+ ) and experimental database for modeling the solubility of REE phosphate minerals (monazite, xenotime, and rhabdophane) from 25 to 300 °C

Rare earth elements (REE) are critical elements found in monazite, xenotime, and hydrated REE phosphates which typically form in hydrothermal mineral deposits. Accurate predictions of the solubility of these REE phosphates and the speciation of REE in aqueous fluids are both key to understanding the controls on the transport, fractionation, and deposition of REE in natural systems. Previous monazite and xenotime solubility experiments indicate the presence of large discrepancies between experimentally derived solubility constants versus calculated solubilities by combining different data sources for the thermodynamic properties of minerals and aqueous species at hydrothermal conditions. In this study, these discrepancies were resolved by using the program GEMSFITS to optimize the standard partial molal Gibbs energy of formation (Δ f G° 298 ) of REE aqueous species (REE 3+ and REE hydroxyl complexes) at 298.15 K and 1 bar while keeping the thermodynamic properties fixed for the REE phosphates. A comprehensive experimental database was compiled using solubility data available between 25 and 300 °C. The latter permits conducting thermodynamic parameter optimization of Δ f G° 298 for REE aqueous species. Optimal matching of the rhabdophane solubility data between 25 and 100 °C requires modifying the Δ f G° 298 values of REE 3+ by 1–6 kJ/mol, whereas matching of the monazite solubility data between 100 and 300 °C requires modifying the Δ f G° 298 values of both REE 3+ and REEOH 2+ by ~15–31 kJ/mol and ~2–10 kJ/mol, respectively. For xenotime, adjustments of Δ f G° 298 values by 1–26 kJ/mol are only necessary for the REE 3+ species. The optimizations indicate that the solubility of monazite in acidic solutions is controlled by the light (L)REE 3+ species at <150 °C and the LREEOH 2+ species at >150 °C, whereas the solubility of xenotime is controlled by the heavy (H)REE 3+ species between 25 and 300 °C. Based on the optimization results, we conclude that the revised Helgeson-Kirkham-Flowers equation of state does not reliably predict the thermodynamic properties of REE 3+ , REEOH 2+ , and likely other REE hydroxyl species at hydrothermal conditions. We therefore provide an experimental database (ThermoExp_REE) as a basic framework for future updates, extensions with other ligands, and optimizations as new experimental REE data become available. As a result, the optimized thermodynamic properties of aqueous species and minerals are available open access to accurately predict the solubility of REE phosphates in fluid-rock systems.

58 GEOSCIENCES↗
DOE OSTI2016

A combined experimental and computational thermodynamic investigation of the U-Th-O system

Here, the thermodynamics of the U–Th–O system have been assessed using the Calphad method. The compound energy formalism (CEF) and a partially ionic two-sublattice liquid model (TSLM) were used for the fluorite U 1–y Th y O 2±x , γ-(U,Th) 4 O 9 , and the U–Th–O melt. The O 2 activity of fluorite U 1–y Th y O 2±x with temperature and composition was determined by thermogravimetric analysis. Thermodynamic studies for the Th–O binary and U–Th–O ternary available in the open literature were critically reviewed. A self-consistent data set was selected and compiled with the equilibrium oxygen pressures determined by thermogravimetry in order to optimize the adjustable parameters of models selected to represent the phases in the Th–O and U–Th–O systems.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Software Defined Architectures for Portability and Performance

The Software Defined Architectures for Portability and Performance (SODAPOP) project developed a co-design framework to partition and map converged applications on specialized heterogeneous architectures. We started from key domain applications that combine scientific simulation with data analytics and machine learning as drivers to integrate our framework. The framework includes high-level compilers that interfaces with high-level programming frameworks, domain-specific optimization passes, and hardware-oriented optimizations. The framework leverages hardware generators to enable specialization and facilitate exploration of custom system designs.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1993

Mongoose: Creation of a Rad-Hard MIPS R3000

This paper describes the development of a 32 Bit, full MIPS R3000 code-compatible Rad-Hard CPU, code named Mongoose. Mongoose progressed from contract award, through the design cycle, to operational silicon in 12 months to meet a space mission for NASA. The goal was the creation of a fully static device capable of operation to the maximum Mil-883 derated speed, worst-case post-rad exposure with full operational integrity. This included consideration of features for functional enhancements relating to mission compatibility and removal of commercial practices not supported by Rad-Hard technology. 'Mongoose' developed from an evolution of LSI Logic's MIPS-I embedded processor, LR33000, code named Cobra, to its Rad-Hard 'equivalent', Mongoose. The term 'equivalent' is used to infer that the core of the processor is functionally identical, allowing the same use and optimizations of the MIPS-I Instruction Set software tool suite for compilation, software program trace, etc. This activity was started in September of 1991 under a contract from NASA-Goddard Space Flight Center (GSFC)-Flight Data Systems. The approach affected a teaming of NASA-GSFC for program development, LSI Logic for system and ASIC design coupled with the Rad-Hard process technology, and Harris (GASD) for Rad-Hard microprocessor design expertise. The program culminated with the generation of Rad-Hard Mongoose prototypes one year later.

Lincoln, Dan↗
NASA NTRS2012

Deconvolution Methods and Systems for the Mapping of Acoustic Sources from Phased Microphone Arrays

Mapping coherent/incoherent acoustic sources as determined from a phased microphone array. A linear configuration of equations and unknowns are formed by accounting for a reciprocal influence of one or more cross-beamforming characteristics thereof at varying grid locations among the plurality of grid locations. An equation derived from the linear configuration of equations and unknowns can then be iteratively determined. The equation can be attained by the solution requirement of a constraint equivalent to the physical assumption that the coherent sources have only in phase coherence. The size of the problem may then be reduced using zoning methods. An optimized noise source distribution is then generated over an identified aeroacoustic source region associated with a phased microphone array (microphones arranged in an optimized grid pattern including a plurality of grid locations) in order to compile an output presentation thereof, thereby removing beamforming characteristics from the resulting output presentation.

Brooks, Thomas F.↗
NASA NTRS2003

Domain compilation for embedded real-time planning

This paper presents a middle ground between these two extremes that uses plans, but also enables much larger control envelopes using a real-time planner that finds optimal n step plans to achieve a set of goals if one exists.

domain compilation imbedded real-time planning↗
DOE OSTI2026

Profile Generation for GPU Targets

GPU accelerators are ubiquitous, but their ecosystem is far less evolved than the host one. Compiler heuristics are often tuned for CPUs and reused for GPU. Similarly, tooling and more evolved optimization techniques are historically not available on GPU targets. In this work, we address one of these shortcomings and enable profile generation and profile-guided optimizations (PGO) for GPU targets. While this is only a single step towards a CPU equivalent ecosystem for offload devices, it shows how old misconceptions on the limitations of GPUs are often not warranted anymore. Through our implementation in LLVM/Offload, we enable device-side PGO for full scientific applications and open up tooling opportunities, including code coverage analysis and compiler-built-in roofline analysis. Our evaluation highlights the performance implications of profile generation, the insights gained from these profiles, and the (missed) opportunities in utilizing the information for GPU compilation.

McDonough, Ethan Luis [Lawrence Livermore National↗
DOE OSTI2015

Final report: Compiled MPI. Cost-Effective Exascale Application Development

This is the final report on Compiled MPI: Cost-Effective Exascale Application Development, and summarizes the results under this project. The project investigated runtime enviroments that improve the performance of MPI (Message-Passing Interface) programs; work at Illinois in the last period of this project looked at optimizing data access optimizations expressed with MPI datatypes.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Universal Compiling and (No-)Free-Lunch Theorems for Continuous-Variable Quantum Learning

Quantum compiling, where a parameterized quantum circuit is trained to learn a target unitary, is an important primitive for quantum computing that can be used as a subroutine to obtain optimal circuits or as a tomographic tool to study the dynamics of an experimental system. While much attention has been paid to quantum compiling on discrete-variable hardware, less has been paid to compiling in the continuous-variable paradigm. Here we motivate several, closely related, short-depth continuous-variable algorithms for quantum compilation. We analyze the trainability of our proposed cost functions and numerically demonstrate our algorithms by learning arbitrary Gaussian operations and Kerr nonlinearities. We further make connections between this framework and quantum learning theory in the continuous-variable setting by deriving no-free-lunch theorems. These generalization bounds demonstrate a linear resource reduction for learning Gaussian unitaries using entangled coherent-Fock states and an exponential resource reduction for learning arbitrary unitaries using two-mode-squeezed states.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2006

Architecture Adaptive Computing Environment

Architecture Adaptive Computing Environment (aCe) is a software system that includes a language, compiler, and run-time library for parallel computing. aCe was developed to enable programmers to write programs, more easily than was previously possible, for a variety of parallel computing architectures. Heretofore, it has been perceived to be difficult to write parallel programs for parallel computers and more difficult to port the programs to different parallel computing architectures. In contrast, aCe is supportable on all high-performance computing architectures. Currently, it is supported on LINUX clusters. aCe uses parallel programming constructs that facilitate writing of parallel programs. Such constructs were used in single-instruction/multiple-data (SIMD) programming languages of the 1980s, including Parallel Pascal, Parallel Forth, C*, *LISP, and MasPar MPL. In aCe, these constructs are extended and implemented for both SIMD and multiple- instruction/multiple-data (MIMD) architectures. Two new constructs incorporated in aCe are those of (1) scalar and virtual variables and (2) pre-computed paths. The scalar-and-virtual-variables construct increases flexibility in optimizing memory utilization in various architectures. The pre-computed-paths construct enables the compiler to pre-compute part of a communication operation once, rather than computing it every time the communication operation is performed.

Dorband, John E.↗
DOE OSTI2022

Portability for GPU-accelerated molecular docking applications for cloud and HPC: can portable compiler directives provide performance across all platforms?

High-throughput structure-based screening of drug-like molecules has become a common tool in biomedical research. Recently, acceleration with graphics processing units (GPUs) has provided a large performance boost for molecular docking programs. Both cloud and high-performance computing (HPC) resources have been used for large screens with molecular docking programs; while NVIDIA GPUs have dominated cloud and HPC resources, new vendors such as AMD and Intel are now entering the field, creating the problem of software portability across different GPUs. Ideally, software productivity could be maximized with portable programming models that are able to maintain high performance across architectures. While in many cases compiler directives have been used as an easy way to offload parallel regions of a CPU-based program to a GPU accelerator, they may also be an attractive programming model for providing portability across different GPU vendors, in which case the porting process may proceed in the reverse direction: from low-level, architecture-specific code to higher-level directive-based abstractions. MiniMDock is a new mini-application (miniapp) designed to capture the essential computational kernels found in molecular docking calculations, such as are used in phar-maceutical drug discovery efforts, in order to test different solutions for porting across GPU architectures. Here we extend MiniMDock to GPU offloading with OpenMP directives, and compare to performance of kernels using CUDA and HIP on NVIDIA and AMD GPUs, respectively, as well as across different compilers, exploring performance bottlenecks. We document this reverse-porting process, from highly optimized device code to a higher-level version using directives, compare code structure, and describe barriers that were overcome in this effort.

Thavappiragasam, Mathialakan↗
DOE OSTI2025

Feed the fish: A review of aquaculture feeders and their strategic implementation

Automatic feeders are revolutionizing aquaculture by enabling precise and controlled feeding regimens that optimize growth, reduce feed waste, and enhance the overall efficiency of farming operations. Demand feeders provide some similar benefits but with feeding tailored to fish appetites and, in some cases, feed dispersal without electricity. This review explores the evolution, technological advancements, and applications of these feeders with a survey of recent research. It looks at common feeder designs and compares the pros and cons of five automatic feeder configurations in commercial use today. The article contrasts feeders and feed sizes for farmed species in different life stages and facilities, from hatcheries to ponds and offshore cages. It discusses the importance of species-tailored feeding strategies as well as impacts on fish behavior and health, nutrient delivery, and environmental sustainability. Incorporating sensors and on-site computing enables optimization in feeding algorithms that feeders then implement precisely and reliably. The review compiles results from multiple studies comparing growth rate, weight, and feed conversion ratio (FCR) outcomes from automatic feeders and demand feeders versus traditional hand-feeding regimens. The integration of feeders with real-time monitoring and data analytics is also discussed, highlighting future directions for research and adoption across the industry.

42 ENGINEERING↗