Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “domain compilation”

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 37 records · Page 2

Experience Report: A Do-It-Yourself High-Assurance Compiler

Embedded domain-specific languages (EDSLs) are an approach for quickly building new languages while maintaining the advantages of a rich metalanguage. We argue in this experience report that the "EDSL approach" can surprisingly ease the task of building a high-assurance compiler.We do not strive to build a fully formally-verified tool-chain, but take a "do-it-yourself" approach to increase our confidence in compiler-correctness without too much effort. Copilot is an EDSL developed by Galois, Inc. and the National Institute of Aerospace under contract to NASA for the purpose of runtime monitoring of flight-critical avionics. We report our experience in using type-checking, QuickCheck, and model-checking "off-the-shelf" to quickly increase confidence in our EDSL tool-chain.

Pike, Lee↗

StreamJIT: a commensal compiler for high-performance stream programming

There are many domain libraries, but despite the performance benefits of compilation, domain-specific languages are comparatively rare due to the high cost of implementing an optimizing compiler. We propose commensal compilation, a new strategy for compiling embedded domain-specific languages by reusing the massive investment in modern language virtual machine platforms. Commensal compilers use the host language's front-end, use host platform APIs that enable back-end optimizations by the host platform JIT, and use an autotuner for optimization selection. The cost of implementing a commensal compiler is only the cost of implementing the domain-specific optimizations. We demonstrate the concept by implementing a commensal compiler for the stream programming language StreamJIT atop the Java platform. Our compiler achieves performance 2.8 times better than the StreamIt native code (via GCC) compiler with considerably less implementation effort.

97 MATHEMATICS AND COMPUTING↗

Antiphase domains in lunar plagioclase

The paper is a compilation of data on antiphase domains in lunar plagioclase. New observations and reports in the literature are tabulated and discussed. In the pattern which emerges (but is still very incomplete), it appears that b-domains, which except for the An 82 bytownite from the Stillwater complex have only been observed in lunar feldspars, occur in the anorthite range An 80 to 95. Especially in the sodium rich part there seems to be a close relation between an exsolution structure and b-APB's. The c-APB's are found in anorthites An 95 to 100 and for a given An-content they are larger for metamorphic than for volcanic anorthites. Near An 95, c- and b-domains can be observed in the same crystal. The c-domains disappear when heated above 1200 C; they are not affected by heating below 600 C. This implies that calcic anorthite without c-domains must have been rapidly quenched from high temperatures.

Wenk, H.-R.↗

User Interface Technology for Formal Specification Development

Formal specification development and modification are an essential component of the knowledge-based software life cycle. User interface technology is needed to empower end-users to create their own formal specifications. This paper describes the advanced user interface for AMPHION1 a knowledge-based software engineering system that targets scientific subroutine libraries. AMPHION is a generic, domain-independent architecture that is specialized to an application domain through a declarative domain theory. Formal specification development and reuse is made accessible to end-users through an intuitive graphical interface that provides semantic guidance in creating diagrams denoting formal specifications in an application domain. The diagrams also serve to document the specifications. Automatic deductive program synthesis ensures that end-user specifications are correctly implemented. The tables that drive AMPHION's user interface are automatically compiled from a domain theory; portions of the interface can be customized by the end-user. The user interface facilitates formal specification development by hiding syntactic details, such as logical notation. It also turns some of the barriers for end-user specification development associated with strongly typed formal languages into active sources of guidance, without restricting advanced users. The interface is especially suited for specification modification. AMPHION has been applied to the domain of solar system kinematics through the development of a declarative domain theory. Testing over six months with planetary scientists indicates that AMPHION's interactive specification acquisition paradigm enables users to develop, modify, and reuse specifications at least an order of magnitude more rapidly than manual program development.

Lowry, Michael↗

QuYBE - An Algebraic Compiler for Quantum Circuit Compression

QuYBE is an open-source algebraic compiler for the compression of quantum circuits. It has been applied for the efficient simulation of the Heisenberg Hamiltonian on quantum computers. Currently, it can simulate the time dynamics of one-dimensional chains. It includes modules to generate the quantum circuits for the above as well as produce the compressed circuits, which are independent of the time step. It utilizes the Yang-Baxter equation (YBE) to perform the compression. QuYBE enables users to seamlessly design, execute, and analyze the time dynamics of the Heisenberg Hamiltonian on quantum computers. QuYBE is the first step toward making the YBE technique available to a broader community of scientists from multiple domains. The QuYBE compiler is available at https://github.com/ZichangHe/QuYBE.

Gulania, Sahil↗

Executing CLIPS expert systems in a distributed environment

This paper describes a framework for running cooperating agents in a distributed environment to support the Intelligent Computer Aided Design System (ICADS), a project in progress at the CAD Research Unit of the Design Institute at the California Polytechnic State University. Currently, the systems aids an architectural designer in creating a floor plan that satisfies some general architectural constraints and project specific requirements. At the core of ICADS is the Blackboard Control System. Connected to the blackboard are any number of domain experts called Intelligent Design Tools (IDT). The Blackboard Control System monitors the evolving design as it is being drawn and helps resolve conflicts from the domain experts. The user serves as a partner in this system by manipulating the floor plan in the CAD system and validating recommendations made by the domain experts. The primary components of the Blackboard Control System are two expert systems executed by a modified CLIPS shell. The first is the Message Handler. The second is the Conflict Resolver. The Conflict Resolver synthesizes the suggestions made by the domain experts, which can be either CLIPS expert systems, or compiled C programs. In DEMO1, the current ICADS prototype, the CLIPS domain expert systems are Acoustics, Lighting, Structural, and Thermal; the compiled C domain experts are the CAD system and the User Interface.

Taylor, James↗

Application of a Prize Mechanism to Address Data Utilization Challenges at Utilities

The electric industry sector is facing an “explosion” of data from a variety of sources. Electric sector stakeholders need to define how to capitalize on large datasets, both those they create and those from other sources (like data on weather, buildings, electric vehicles, etc.), to improve reliability and resilience and meet the changing system dynamics from renewable integration. For the electricity sector to fully utilize these vast new datasets, it must undergo a transformation in how it manages data quality, storage, and processing. The U.S. Department of Energy (DOE) Office of Electricity (OE) is committed to accelerating research, development, and demonstration of new technologies and tools within the electricity sector to advance reliability, resilience, and affordable operation of the power system. Through the prize mechanism, OE identified two widespread data-related challenges for utilities—load modeling and data analysis automation—and offered an opportunity for utilities and teams of software engineers to identify additional challenges faced by utilities. After completing one round of the American-Made Digitizing Utilities Prize, OE, the National Renewable Energy Laboratory (NREL) as the prize administrator, and Pacific Northwest National Laboratory (PNNL) as the domain experts have compiled the results and lessons learned to feed into the second round of the prize.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Kokkos GPU Compiler

The Kokkos Clang compiler is a version of the Clang C++ compiler that has been modified to perform targeted code generation for Kokkos constructs in the goal of generating highly optimized code and to provide semantic (domain) awareness throughout the compilation toolchain of these constructs such as parallel for and parallel reduce. This approach is taken to explore the possibilities of exposing the developer’s intentions to the underlying compiler infrastructure (e.g. optimization and analysis passes within the middle stages of the compiler) instead of relying solely on the restricted capabilities of C++ template metaprogramming. To date our current activities have focused on correct GPU code generation and thus we have not yet focused on improving overall performance. The compiler is implemented by recognizing specific (syntactic) Kokkos constructs in order to bypass normal template expansion mechanisms and instead use the semantic knowledge of Kokkos to directly generate code in the compiler’s intermediate representation (IR); which is then translated into an NVIDIA-centric GPU program and supporting runtime calls. In addition, by capturing and maintaining the higher-level semantics of Kokkos directly within the lower levels of the compiler has the potential for significantly improving the ability of the compiler to communicate with the developer in the terms of their original programming model/semantics.

Moss, Nicholas↗

Kokkos GPU Compiler

The Kokkos Clang compiler is a version of the Clang C++ compiler that has been modified to perform targeted code generation for Kokkos constructs in the goal of generating highly optimized code and to provide semantic (domain) awareness throughout the compilation toolchain of these constructs such as parallel for and parallel reduce. This approach is taken to explore the possibilities of exposing the developer’s intentions to the underlying compiler infrastructure (e.g. optimization and analysis passes within the middle stages of the compiler) instead of relying solely on the restricted capabilities of C++ template metaprogramming. To date our current activities have focused on correct GPU code generation and thus we have not yet focused on improving overall performance. The compiler is implemented by recognizing specific (syntactic) Kokkos constructs in order to bypass normal template expansion mechanisms and instead use the semantic knowledge of Kokkos to directly generate code in the compiler’s intermediate representation (IR); which is then translated into an NVIDIA-centric GPU program and supporting runtime calls. In addition, by capturing and maintaining the higher-level semantics of Kokkos directly within the lower levels of the compiler has the potential for significantly improving the ability of the compiler to communicate with the developer in the terms of their original programming model/semantics.

Moss, Nicholas↗

Model compilation: An approach to automated model derivation

An approach is introduced to automated model derivation for knowledge based systems. The approach, model compilation, involves procedurally generating the set of domain models used by a knowledge based system. With an implemented example, how this approach can be used to derive models of different precision and abstraction is illustrated, and models are tailored to different tasks, from a given set of base domain models. In particular, two implemented model compilers are described, each of which takes as input a base model that describes the structure and behavior of a simple electromechanical device, the Reaction Wheel Assembly of NASA's Hubble Space Telescope. The compilers transform this relatively general base model into simple task specific models for troubleshooting and redesign, respectively, by applying a sequence of model transformations. Each transformation in this sequence produces an increasingly more specialized model. The compilation approach lessens the burden of updating and maintaining consistency among models by enabling their automatic regeneration.

Keller, Richard M.↗

Cyanobacterial ultrastructure in light of genomic sequence data

Cyanobacteria are physiologically and morphologically diverse photosynthetic microbes that play major roles in the carbon and nitrogen cycles of the biosphere. Recently, they have gained attention as potential platforms for the production of biofuels and other renewable chemicals. Many cyanobacteria were characterized morphologically prior to the advent of genome sequencing. Here we catalog cyanobacterial ultrastructure within the context of genomic sequence information, including high magnification transmission electron micrographs of sequenced representatives of each of the five morphological Subsections. We place the image data in the context of tabulated protein domains--which are the structural, functional and evolutionary units of proteins--from the 126 cyanobacterial genomes comprising the CyanoGEBA dataset. In particular, we identify the correspondence between ultrastructure and the occurrence of protein domains related to the formation of cyanobacterial inclusions. This compilation of images and genome-level domain occurrence will prove useful for a variety of analyses of cyanobacterial sequence data and provide a guidebook to morphological features.

59 BASIC BIOLOGICAL SCIENCES↗

Modern data analytics approach to predict creep of high-temperature alloys

A breakthrough in alloy design often requires comprehensive understanding in complex multi-component/multi-phase systems to generate novel material hypotheses. We introduce a modern data analytics workflow that leverages high-quality experimental data augmented with advanced features obtained from high-fidelity models. Herein, we use an example of a consistently-measured creep dataset of developmental high-temperature alloy combined with scientific alloy features populated from a high-throughput computational thermodynamic approach. Extensive correlation analyses provide ranking insights for most impactful alloy features for creep resistance, evaluated from a large set of candidate features suggested by domain experts. We also show that we can accurately train machine learning models by integrating high-ranking features obtained from correlation analyses. Consequently, the demonstrated approach can be extended beyond incorporating thermodynamic features, with input from domain experts used to compile lists of features from other alloy physics, such as diffusion kinetics and microstructure evolution.

36 MATERIALS SCIENCE↗

Comparison of Satellite NO{sub 2} Observations with High Resolution Model Simulations over the Balkan Peninsula

High resolution model estimations of tropospheric NO{sub 2} column amounts from the Comprehensive Air Quality Model (CAMx) were simulated for the Balkan Peninsula and were compared with satellite data for a period of one year, in order to study the characteristics of the spatial and temporal variability of pollution in the area. The Balkan area is considered a crossroad of different pollution sources and therefore has been divided in urban, industrial and rural regions, aiming to investigate the consistency of satellite retrievals and model predictions at high spatial resolution. Satellite measurements of tropospheric NO{sub 2} are available daily at 13:30 LT since 2004 from OMI/Aura with a resolution of 13x24 km. The anthropogenic emissions used in CAMx for the domain under study, was compiled employing bottom-up approaches (road transport sector, off-road machinery) as well as other national registries and international databases. High resolution GIS maps (road network, landuses, population) were also used in order to achieve high spatial resolution. In most of the cases the model reveals similar spatial patterns with the satellite data, while over certain areas discrepancies were found and investigated.

54 ENVIRONMENTAL SCIENCES↗

Distributed Halide

Many image processing tasks are naturally expressed as a pipeline of small computational kernels known as stencils. Halide is a popular domain-specific language and compiler designed to implement image processing algorithms. Halide uses simple language constructs to express what to compute and a separate scheduling co-language for expressing when and where to perform the computation. This approach has demonstrated performance comparable to or better than hand-optimized code. Until now, however, Halide has been restricted to parallel shared memory execution, limiting its performance for memory-bandwidth-bound pipelines or large-scale image processing tasks. We present an extension to Halide to support distributed-memory parallel execution of complex stencil pipelines. These extensions compose with the existing scheduling constructs in Halide, allowing expression of complex computation and communication strategies. Existing Halide applications can be distributed with minimal changes, allowing programmers to explore the tradeoff between recomputation and communication with little effort. Approximately 10 new of lines code are needed even for a 200 line, 99 stage application. On nine image processing benchmarks, our extensions give up to a 1.4× speedup on a single node over regular multithreaded execution with the same number of cores, by mitigating the effects of non-uniform memory access. The distributed benchmarks achieve up to 18× speedup on a 16 node testing machine and up to 57× speedup on 64 nodes of the NERSC Cori supercomputer.

97 MATHEMATICS AND COMPUTING↗

Automatic Differentiation for Adjoint Stencil Loops

Stencil loops are a common motif in computations including convolutional neural networks, structured-mesh solvers for partial differential equations, and image processing. Stencil loops are easy to parallelise, and their fast execution is aided by compilers, libraries, and domain-specific languages. Reverse-mode automatic differentiation, also known as algorithmic differentiation, autodiff, adjoint differentiation, or back-propagation, is sometimes used to obtain gradients of programs that contain stencil loops. Unfortunately, conventional automatic differentiation results in a memory access pattern that is not stencil-like and not easily parallelisable. In this paper we present a novel combination of automatic differentiation and loop transformations that preserves the structure and memory access pattern of stencil loops, while computing fully consistent derivatives. The generated loops can be parallelised and optimised for performance in the same way and using the same tools as the original computation. We have implemented this new technique in the Python tool PerforAD, which we release with this paper along with test cases derived from seismic imaging and computational fluid dynamics applications.

Automatic Differentiation↗

Computing the Properties of Matter with Leadership Computing Resources (Closeout Report for DE-SC0018121)

In order to add more capabilities to Halide, we have designed a new framework called Tiramisu and integrated this framework into Halide. Since Tiramisu enables Halide to target heterogeneous architectures, our development efforts have been refocused on Tiramisu. Most high-performance computer systems today are complex and increasingly heterogeneous; they may have CPUs, GPUs and FPGAs. Achieving best performance requires taking full advantage of all these different architectures. To address this issue, we have designed Tiramisu, an optimization framework that enables Halide (and other DSLs) to target heterogeneous architectures. Tiramisu is an optimization framework that takes as input a high level, architecture-independent representation of code and a set of scheduling and data mapping commands that guide code transformation. The input can either be generated by a domain-specific language (DSL) compiler such as Halide or directly written by a programmer. Tiramisu then applies the user-specified code and data-layout transformations and generates an architecture-specific, low-level intermediate representation (IR) that takes advantage of modern architectural features such as multicore parallelism, non-uniform memory (NUMA) hierarchies, clusters, and accelerators like GPUs and FPGAs. We integrated Tiramisu within Halide and implemented a representative set of benchmarks to evaluate this integration. Tiramisu is now open source and is available for public use (http://tiramisu-compiler.org/). A paper about Tiramisu was published, it shows that Tiramisu extends Halide with many new capabilities and that Tiramisu can generate efficient code for multicores, GPUs, FPGAs and distributed heterogeneous systems. The performance of code generated by the Tiramisu backends matches or exceeds hand optimized reference implementations. For example, the multicore backend matches the highly optimized Intel MKL library on many kernels and shows speedups reaching 4x over the original Halide. In addition to making Tiramisu more robust, we have used Tiramisu to implement a set of representative tensor operation for constructing baryon building blocks required for multi baryon contractions in LQCD. In order to implement this code, we needed to generalize Tiramisu in two ways: first we needed to support indirect array accesses, and second, we needed to add support for complex numbers to Tiramisu. The code generated by Tiramisu is 6x faster than the reference code. Our efforts towards an MPI based multi-node version of tiramisu have matured and the resulting code scales well on multiple nodes (tests up to 512 KNL nodes have been undertaken).

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗