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 235 records · Page 13
All sourcesNASA NTRSDOE OSTI
DOE OSTI2015

Helium: lifting high-performance stencil kernels from stripped x86 binaries to halide DSL code

Highly optimized programs are prone to bit rot, where performance quickly becomes suboptimal in the face of new hardware and compiler techniques. In this paper we show how to automatically lift performance-critical stencil kernels from a stripped x86 binary and generate the corresponding code in the high-level domain-specific language Halide. Using Halide's state-of-the-art optimizations targeting current hardware, we show that new optimized versions of these kernels can replace the originals to rejuvenate the application for newer hardware. The original optimized code for kernels in stripped binaries is nearly impossible to analyze statically. Instead, we rely on dynamic traces to regenerate the kernels. We perform buffer structure reconstruction to identify input, intermediate and output buffer shapes. Here, we abstract from a forest of concrete dependency trees which contain absolute memory addresses to symbolic trees suitable for high-level code generation. This is done by canonicalizing trees, clustering them based on structure, inferring higher-dimensional buffer accesses and finally by solving a set of linear equations based on buffer accesses to lift them up to simple, high-level expressions. Helium can handle highly optimized, complex stencil kernels with input-dependent conditionals. We lift seven kernels from Adobe Photoshop giving a 75 % performance improvement, four kernels from Irfan View, leading to 4.97 x performance, and one stencil from the mini GMG multigrid benchmark netting a 4.25 x improvement in performance. We manually rejuvenated Photoshop by replacing eleven of Photoshop's filters with our lifted implementations, giving 1.12 x speedup without affecting the user experience.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Performance of an Astrophysical Radiation Hydrodynamics Code under Scalable Vector Extension Optimization

We present results of a performance study of an astrophysical radiation hydrodynamics code, V2D, on the Arm-based A64FX processor developed by Fujitsu. The code solves sparse linear systems, a task for which the A64FX architecture should be well suited. Here, we performed the performance analysis study on Ookami, an Apollo 80 platform utilizing the A64FX processor. We explored several compilers and performance anal-ysis packages and found the code did not perform as expected under scalable vector extension optimization, suggesting that a “deeper dive” into analyzing the code is worthwhile. However, a simple driver program that exercised basic sparse linear algebra routines used by V2D did show significant speedup with the use of the scalable vector extension optimization. We present the initial results from the study which used V2D on a relatively simple test problem that emphasized the repeated solution of sparse linear systems.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2018

Manage OpenMP GPU Data Environment Under Unified Address Space

OpenMP has supported the offload of computations to accelerators such as GPUs since version 4.0. A crucial aspect in OpenMP offloading is to manage the accelerator data environment. Currently, this has to be explicitly programmed by users, which is non-trival and often results in suboptimal performance. The unified memory feature available in recent GPU architectures introduces another option, implicit management. However, our experiments show that it incurs several performance issues, especially under GPU memory oversubscription. In this paper, we propose a compiler and runtime collaborative approach to manage OpenMP GPU data under unified memory. In our framework, the compiler performs data reuse analysis to assist runtime data management. The runtime combines static and dynamic information to make optimized data management decisions.We have implement the proposed technology in the LLVM framework. The evaluation shows our method can achieve significant performance improvement for OpenMP GPU offloading.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1986

Tectonic evaluation of the Nubian shield of Northeastern Sudan using thematic mapper imagery

Bechtel is nearing completion of a one-year program that uses digitally enhanced LANDSAT Thematic Mapper (TM) data to compile the first comprehensive regional tectonic map of the Proterozoic Nubian Shield exposed in the northern Red Sea Hills of northeastern Sudan. The status of significant objectives of this study are given. Pertinent published and unpublished geologic literature and maps of the northern Red Sea Hills to establish the geologic framework of the region were reviewed. Thematic mapper imagery for optimal base-map enhancements was processed. Photo mosaics of enhanced images to serve as base maps for compilation of geologic information were completed. Interpretation of TM imagery to define and delineate structural and lithogologic provinces was completed. Geologic information (petrologic, and radiometric data) was compiled from the literature review onto base-map overlays. Evaluation of the tectonic evolution of the Nubian Shield based on the image interpretation and the compiled tectonic maps is continuing.

Source record↗
DOE OSTI2020

Solution-Based, Anion-Doping of Li 4 Ti 5 O 12 Nanoflowers for Lithium-Ion Battery Applications

Solution–based, anionic doping represents a convenient strategy with which to improve upon the conductivity of candidate anode materials such as Li 4 Ti 5 O 12 (LTO). As such, novel synthetic hydrothermally–inspired protocols have primarily been devised herein, aimed at the large–scale production of unique halogen–doped, micron–scale, three–dimensional, hierarchical LTO flower–like motifs. Although fluorine (F) doping has been explored, the use of chlorine (Cl) dopants is the primary focus here. Several experimental variables, such as dopant amount, lithium hydroxide concentration, and titanium butoxide purity, were probed and perfected. Furthermore, the Cl doping process did not damage the intrinsic LTO morphology. The analysis, based on interpreting a compilation of SEM, XRD, XPS, and TEM–EDS results, was used to determine an optimized dopant concentration of Cl. Electrochemical tests demonstrated an increased capacity via cycling of 12 % for a Cl–doped sample as compared with pristine LTO. Moreover, the Cl–doped LTO sample described in this study exhibited the highest discharge capacity yet reported at an observed rate of 2C for this material at 143mAh g –1 . Overall, these data suggest that the Cl dopant likely enhances not only the ion transport capabilities, but also the overall electrical conductivity of our as–prepared structures. Furthermore, to help explain these favorable findings, theoretical DFT calculations were used to postulate that the electronic conductivity and Li diffusion were likely improved by the presence of increased Ti 3+ ion concentration coupled with widening of the Li migration channel.

25 ENERGY STORAGE↗
DOE OSTI2021

Toward Evaluating High-Level Synthesis Portability and Performance between Intel and Xilinx FPGAs

Offloading computation from a CPU to a hardware accelerator is becoming a more common solution for improving performance because traditional gains enabled by Moore’s law and Dennard scaling have slowed. GPUs are often used as hardware accelerators, but field-programmable gate arrays (FPGAs) are gaining traction. FPGAs are beneficial because they allow hardware specific to a particular application to be created. However, they are notoriously difficult to program. To this end, two of the main FPGA manufacturers, Intel and Xilinx, have created tools and frameworks that enable the use of higher level languages to design FPGA hardware. Although Xilinx kernels can be designed by using C/C++, both Intel and Xilinx support the use of OpenCL C to architect FPGA hardware. However, not much is known about the portability and performance between these two device families other than the fact that it is theoretically possible to synthesize a kernel meant for Intel to Xilinx and vice versa.In this work, we evaluate the portability and performance of Intel and Xilinx kernels. We use OpenCL C implementations of a subset of the Rodinia benchmarking suite that were designed for an Intel FPGA and make the necessary modifications to create synthesizable OpenCL C kernels for a Xilinx FPGA. We find that the difficulty of porting certain kernel optimizations varies, depending on the construct. Once the minimum amount of modifications is made to create synthesizable hardware for the Xilinx platform, more nontrivial work is needed to improve performance. However, we find that constructs that are known to be performant for an FPGA should improve performance regardless of the platform; the difficulty comes in deciding how to invoke certain kernel optimizations while also abiding by the constraints enforced by a given platform’s hardware compiler.

Cabrera, Anthony↗
DOE OSTI2018

Potential Ideas for an El Capitan Center of Excellence (COE) Around Intelligent Simulation

Proposing a Center of Excellence under the CORAL-2 NRE is a mandatory requirement. The current Sierra COE (CORAL-1) is largely focused on helping LLNL applications make the disruptive transition to a heterogeneous GPU-based system by 2018. We expect a continuation of COE activities around optimizing our broad and diverse application base (of so-called “traditional” simulation codes) optimized for the El Capitan architecture, as well as supporting the underlying software stack (compilers, tools, programming models, etc.) – but do not expect this to require as much effort in the El Capitan COE (assuming a heterogeneous node architecture). What follows are some thoughts on 3 potential topics of interest for an El Capitan COE at LLNL – largely focused around AI and machine learning and the concept of advancing our goal of intelligent simulation or cognitive computing in the timeframe of deployment and production use of El Capitan (2023-2038). We believe vendor engagement through a COE in this area will provide a natural point-of-interest between LLNL and our vendor partner for common advancement of machine learning capabilities focused on scientific data – potentially greatly broadening the ecosystem around HPC architectures and the supporting software stack for scientific simulation-based AI.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

DOE Express Quantum Computing Application Teams (QCAT FY20 Report)

The QCOR project consists of 4 main research tasks: 1) scientific applications and algorithm development for machine learning (ML) and quantum theories of condensed matter systems and lattice gauge theories; 2) high-level quantum-classical (HLQC) language and domain specific language (DSL) development; 3) compiler and interfaces development for the HLQC language; and 4) hardware-level control, optimization, and algorithms libraries. In the succeeding sections we report on progress towards our research tasks during the 2020 calendar year.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2024

Applications of Artificial Intelligence to Radar

In this report, we survey the current intersection between the fields of radar technology and artificial intelligence. Three main areas are highlighted - synthetic aperture radar automatic target detection, waveform optimization, and antenna design. Literature relevant to these applications and beyond are discussed and compiled in an annotated bibliography.

47 OTHER INSTRUMENTATION↗
NASA NTRS2004

Understanding the Cray X1 System

This paper helps the reader understand the characteristics of the Cray X1 vector supercomputer system, and provides hints and information to enable the reader to port codes to the system. It provides a comparison between the basic performance of the X1 platform and other platforms that are available at NASA Ames Research Center. A set of codes, solving the Laplacian equation with different parallel paradigms, is used to understand some features of the X1 compiler. An example code from the NAS Parallel Benchmarks is used to demonstrate performance optimization on the X1 platform.

Cheung, Samson↗
NASA NTRS1998

Performance Modeling and Measurement of Parallelized Code for Distributed Shared Memory Multiprocessors

This paper presents a model to evaluate the performance and overhead of parallelizing sequential code using compiler directives for multiprocessing on distributed shared memory (DSM) systems. With increasing popularity of shared address space architectures, it is essential to understand their performance impact on programs that benefit from shared memory multiprocessing. We present a simple model to characterize the performance of programs that are parallelized using compiler directives for shared memory multiprocessing. We parallelized the sequential implementation of NAS benchmarks using native Fortran77 compiler directives for an Origin2000, which is a DSM system based on a cache-coherent Non Uniform Memory Access (ccNUMA) architecture. We report measurement based performance of these parallelized benchmarks from four perspectives: efficacy of parallelization process; scalability; parallelization overhead; and comparison with hand-parallelized and -optimized version of the same benchmarks. Our results indicate that sequential programs can conveniently be parallelized for DSM systems using compiler directives but realizing performance gains as predicted by the performance model depends primarily on minimizing architecture-specific data locality overhead.

Waheed, Abdul↗
DOE OSTI2018

Regenerator design optimization: Results from REGEN 3.3

The results from an extensive parametric study using the most recent version of the regenerator design software tool, REGEN3.3, are presented. By compiling the results from more than 10,000 applications of REGEN3.3 for three different temperatures (35 K, 60 K and 80 K), a wide range of frequencies (30–300 Hz), and a variety of regenerator length, inverse mass flux, and cold end phase angles, a group of performance maps have been generated that will enable regenerator optimization without having to learn REGEN3.3. Optimum results, defined by maximum COP values, are also provided in the form of a convenient correlation whereby the COP can be calculated directly from chosen values of cold end temperature, frequency, inverse mass flux, length, and cold end phase angle. Here one of the more interesting results revealed by this study is that the optimum value of COP is very broad. That is, changes by as much as 15% to 20% in the length, inverse mass flux, or cold end phase away from their optimized values degrade the COP by only 2%.

42 ENGINEERING↗
DOE OSTI2017

Roofline Analysis in the Intel® Advisor to Deliver Optimized Performance for applications on Intel® Xeon Phi™ Processor

In this session we show, in two case studies, how the roofline feature of Intel Advisor has been utilized to optimize the performance of kernels of the XGC1 and PICSAR codes in preparation for Intel Knights Landing architecture. The impact of the implemented optimizations and the benefits of using the automatic roofline feature of Intel Advisor to study performance of large applications will be presented. This demonstrates an effective optimization strategy that has enabled these science applications to achieve up to 4.6 times speed-up and prepare for future exascale architectures. # Goal/Relevance of Session The roofline model [1,2] is a powerful tool for analyzing the performance of applications with respect to the theoretical peak achievable on a given computer architecture. It allows one to graphically represent the performance of an application in terms of operational intensity, i.e. the ratio of flops performed and bytes moved from memory in order to guide optimization efforts. Given the scale and complexity of modern science applications, it can often be a tedious task for the user to perform the analysis on the level of functions or loops to identify where performance gains can be made. With new Intel tools, it is now possible to automate this task, as well as base the estimates of peak performance on measurements rather than vendor specifications. The goal of this session is to demonstrate how the roofline feature of Intel Advisor can be used to balance memory vs. computation related optimization efforts and effectively identify performance bottlenecks. A series of typical optimization techniques: cache blocking, structure refactoring, data alignment, and vectorization illustrated by the kernel cases will be addressed. # Description of the codes ## XGC1 The XGC1 code [3] is a magnetic fusion Particle-In-Cell code that uses an unstructured mesh for its Poisson solver that allows it to accurately resolve the edge plasma of a magnetic fusion device. After recent optimizations to its collision kernel [4], most of the computing time is spent in the electron push (pushe) kernel, where these optimization efforts have been focused. The kernel code scaled well with MPI+OpenMP but had almost no automatic compiler vectorization, in part due to indirect memory addresses and in part due to low trip counts of low-level loops that would be candidates for vectorization. Particle blocking and sorting have been implemented to increase trip counts of low-level loops and improve memory locality, and OpenMP directives have been added to vectorize compute-intensive loops that were identified by Advisor. The optimizations have improved the performance of the pushe kernel 2x on Haswell processors and 1.7x on KNL. The KNL node-for-node performance has been brought to within 30% of a NERSC Cori phase I Haswell node and we expect to bridge this gap by reducing the memory footprint of compute intensive routines to improve cache reuse. ## PICSAR is a Fortran/Python high-performance Particle-In-Cell library targeting at MIC architectures first designed to be coupled with the PIC code WARP for the simulation of laser-matter interaction and particle accelerators. PICSAR also contains a FORTRAN stand-alone kernel for performance studies and benchmarks. A MPI domain decomposition is used between NUMA domains and a tile decomposition (cache-blocking) handled by OpenMP has been added for shared-memory parallelism and better cache management. The so-called current deposition and field gathering steps that compose the PIC time loop constitute major hotspots that have been rewritten to enable more efficient vectorization. Particle communications between tiles and MPI domain has been merged and parallelized. All considered, these improvements provide speedups of 3.1 for order 1 and 4.6 for order 3 interpolation shape factors on KNL configured in SNC4 quadrant flat mode. Performance is similar between a node of cori phase 1 and KNL at order 1 and better on KNL by a factor 1.6 at order 3 with the considered test case (homogeneous thermal plasma).

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1991

Lanczos eigensolution method for high-performance computers

The theory, computational analysis, and applications are presented of a Lanczos algorithm on high performance computers. The computationally intensive steps of the algorithm are identified as: the matrix factorization, the forward/backward equation solution, and the matrix vector multiples. These computational steps are optimized to exploit the vector and parallel capabilities of high performance computers. The savings in computational time from applying optimization techniques such as: variable band and sparse data storage and access, loop unrolling, use of local memory, and compiler directives are presented. Two large scale structural analysis applications are described: the buckling of a composite blade stiffened panel with a cutout, and the vibration analysis of a high speed civil transport. The sequential computational time for the panel problem executed on a CONVEX computer of 181.6 seconds was decreased to 14.1 seconds with the optimized vector algorithm. The best computational time of 23 seconds for the transport problem with 17,000 degs of freedom was on the the Cray-YMP using an average of 3.63 processors.

Bostic, Susan W.↗
DOE OSTI2024

eCC++ : A Compiler Construction Framework for Embedded Domain-Specific Languages

eCC++ is a new compiler construction framework for embedding domain-specific programming languages within C++. That is, the host language is C++, the guest language is the DSL to be embedded in C++, and eCC++ is the tool that enables the embedding. The eCC++ framework is composed of three main components: a front-end, an API for program verification based on a functional and declarative intermediate representation (IR), and a Multi-Level Intermediate Representation (MLIR) code generator. The eCC++ front-end consists of a library of C++ classes and operators that can be used to define the guest language. Guest sources are compiled with any standard C++ compiler, and when run, the resulting executable generates an eCC++ IR representation of the program, which can be verified within the eCC++ framework. Finally, eCC++ allows for high-level and domain-specific optimizations before generating MLIR. In summary, eCC++ aims to act as a generic front-end that enables embedding guest languages into C++, and provides necessary compiler technology for program verification, targeting the existing capabilities in the MLIR infrastructure. The paper evaluates the eCC++ expressiveness and usability describing the process of embedding GraphIt, a high-performance graph language in C++.

Gonzalez Tallada, Marc↗
DOE OSTI2015

Sealing Shales versus Brittle Shales: A Sharp Threshold in the Material Properties and Energy Technology Uses of Fine-Grained Sedimentary Rocks

Fine-grained sedimentary rocks (shale and mudstone) play important roles in global CO 2 abatement efforts through their uses in carbon capture and storage (CCS), radioactive waste storage, and shale gas extraction. These different technologies, however, rely on seemingly conflicting premises regarding the sealing properties of shale and mudstone, suggesting that those rocks that lend themselves to hydrocarbon extraction may not be optimal seals for CCS or radioactive waste storage, and vice versa. In this paper, a compilation of experimental data on the properties of well-characterized shale and mudstone formations is used to demonstrate that clay mineral mass fraction, X clay , is a very important variable the controls key material properties of these formations and that a remarkably sharp threshold at X clay ~ 1/3 separates fine-grained rocks with very different properties. Finally, this threshold coincides with the predictions of a simple conceptual model of the microstructure of sedimentary rocks and is reflected in the uses of shale and mudstone formations for CCS, radioactive waste storage, and shale gas extraction.

58 GEOSCIENCES↗
DOE OSTI2021

Random circuit block-encoded matrix and a proposal of quantum LINPACK benchmark

The LINPACK benchmark reports the performance of a computer for solving a system of linear equations with dense random matrices. Although this task was not designed with a real application directly in mind, the LINPACK benchmark has been used to define the list of TOP500 supercomputers since the debut of the list in 1993. We propose that a similar benchmark, called the quantum LINPACK benchmark, could be used to measure the whole machine performance of quantum computers. The success of the quantum LINPACK benchmark should be viewed as the minimal requirement for a quantum computer to perform a useful task of solving linear algebra problems, such as linear systems of equations. We propose an input model called the Random Circuit Block-Encoded Matrix (RACBEM), which is a proper generalization of a dense random matrix in the quantum setting. The RACBEM model is efficient to be implemented on a quantum computer and can be designed to optimally adapt to any given quantum architecture, with relying on a black-box quantum compiler. Besides solving linear systems, the RACBEM model can be used to perform a variety of linear algebra tasks relevant to many physical applications, such as computing spectral measures, time series generated by a Hamiltonian simulation, and thermal averages of the energy. We implement these linear algebra operations on IBM Q quantum devices as well as quantum virtual machines, and demonstrate their performance in solving scientific computing problems.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2020

Invited: Software defined accelerators from learning tools environment

Next generation systems, such as edge devices, will need to provide efficient processing of machine learning (ML) algorithms along several metrics, including energy, performance, area, and latency. However, the quickly evolving field of ML makes it extremely difficult to generate accelerators able to support a wide variety of algorithms. At the same time, designing accelerators in hardware description languages (HDLs) by hand is hard and time consuming, and does not allow quick exploration of the design space. In this paper we present the Software Defined Accelerators From Learning Tools Environment (SODALITE), an automated open source high-level ML framework-to-verilog compiler targeting ML Application-Specific Integrated Circuits (ASICs) chiplets. The SODALITE approach will implement optimal designs by seamlessly combining custom components generated through high-level synthesis (HLS) with templated and fully tunable Intellectural Properties (IPs) and macros, integrated in an extendable resource library. Through a closed loop design space exploration engine, developers will be able to quickly explore their hardware designs along different dimensions.

High-Level Synthesis, Accelerators, Hardware-Softw↗