Search NASA⌕ Search

SEARCH · Search NASA

Results for “runtime performance”

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 307 records · Page 17
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Experimental Characterization of OpenMP Offloading Memory Operations and Unified Shared Memory Support

The OpenMP specification recently introduced support for unified shared memory, allowing implementation to leverage underlying system software to provide a simpler GPU offloading model where explicit mapping of variables is optional. Support for this feature is becoming more available in different OpenMP implementations on several hardware platforms. A deeper understanding of the different implementation’s execution profile and performance is crucial for applications as they consider the performance portability implications of adopting a unified memory offloading programming style. This work introduces a benchmark tool to characterize unified memory support in several OepnMP compilers and runtimes, with emphasis on identifying discrepancies between different OpenMP implementations as to how they various memory allocation strategies interact with unified shared memory. The benchmark tool is used to characterize OpenMP compilers on three leading High Performance Computing platforms supporting different CPU and device architectures. The benchmark tool is used to assess the impact of enabling unified shared memory on the performance of memory-bound code, highlighting implementation differences that should be accounted for when applications consider performance portability across platforms and compilers.

Elwasif, Wael↗
DOE OSTI2017

Special Issue on Data-Intensive Scalable Computing Systems

Traditional high performance computing (HPC) systems were designed from a compute-centric perspective, with an emphasis on high floating point performance. As scientific and analytics applications become more data intensive, there is a need to rethink HPC system architectures, programming models, runtime systems, and tools with a focus on scalable data intensive computing. Industry approaches supporting data intensive applications have been highly successful, leading many in the HPC community to search for ways to adapt them to HPC hardware and software contexts. Conversely, industry looks to the HPC community for their expertise in designing, deploying, and using extremely large and high performance computing systems. This special issue contains seven articles, each of which is an extended version of a paper presented in the 2015 International Workshop on Data Intensive Scalable Computing Systems (DISCS-2015) held in Austin, Texas on November 15, 2015. The workshop program included papers that ranged from programming models to systems software to storage, each with a strong focus on data intensive computing.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

CodeFlow: A Code Generation System for Flash-X Orchestration Runtime

We propose the CodeFlow toolchain for Flash-X that realizes the “recipe-to-source” code transformation for Flash-X simulations and that is necessary to achive performance portability. We design a high-level language to express operations of simulations in so-called recipes, which are given as input to the toolchain. The tools of the CodeFlow pipeline include code transformation with tree-based source code representation techniques and code orchestration and generation based on control flow graphs. The generated source code utilizes a new runtime, developed for Flash-X, that orchestrates dynamic and asynchronous data movement and task execution. The functionality of CodeFlow is demonstrated using a hydrodynamic problem with a strong shock.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

Collaborative Research: Performance Retargeting of Instrumentation, Measurement, and Analysis Technologies for Exascale Computing: the PRIMA-X Project -- Final Technical Report

The PRIMA-X (Performance Retargeting of Instrumentation, Measurement, and Analysis Technologies for Exascale Computing) project was a collaborative research effort between the University of Oregon (UO) (Malony, PI) and the German Research School for Simulation Sciences GmbH (Wolf, PI) originally, later changed to the Technical University of Darmstadt. Our project aims addressed five areas -- scalability, dynamism, heterogeneity, locality, energy -- that present challenges to performance measurement systems at exascale, with emphasis placed on the first three. In essence, the general goal of the project was to prototype new technologies for performance measurement, analysis, and tuning on future exascale-enable computer systems. Each institution followed its research agena, with periodic coordination and sharing of ideas and results. After the 3-year funding, the PRIMA-X grant was extended beyond the 3-year period at no cost until the end of August 2018. This is the final technical report on the University of Oregon's progress during the entire project scope. Our main focus was to address the PRIMA-X challenges both through technological advancements in the TAU Performance System and their application, as well as prototypes developed in association with other exascale-directed research efforts (prior to the Exascale Computing Project (ECP)). Progress in Years 1 and 2 are summarized and our achievements in Year 3 (plus the extension) are discussed in more detail. This includes specific efforts on power, runtime systems, and monitoring infrastructure.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

ytopt: Autotuning Scientific Applications for Energy Efficiency at Large Scales

As we enter the exascale computing era, efficiently utilizing power and optimizing the performance of scientific applications under power and energy constraints has become critical and challenging. We propose a low-overhead autotuning framework to autotune performance and energy for various hybrid MPI/OpenMP scientific applications at large scales and to explore the tradeoffs between application runtime and power/energy for energy efficient application execution, then use this framework to autotune four ECP proxy applications—XSBench, AMG, SWFFT, and SW4lite. Our approach uses Bayesian optimization with a Random Forest surrogate model to effectively search parameter spaces with up to 6 million different configurations on two large-scale HPC production systems, Theta at Argonne National Laboratory and Summit at Oak Ridge National Laboratory. The experimental results show that our autotuning framework at large scales has low overhead and achieves good scalability. Using the proposed autotuning framework to identify the best configurations, we achieve up to 91.59% performance improvement, up to 21.2% energy savings, and up to 37.84% EDP (energy delay product) improvement on up to 4096 nodes.

Autotuning↗
DOE OSTI2015

TECA: Petascale pattern recognition for climate science

Climate Change is one of the most pressing challenges facing humanity in the 21st century. Climate simulations provide us with a unique opportunity to examine effects of anthropogenic emissions. Highresolution climate simulations produce “Big Data”: contemporary climate archives are ≈ 5PB in size and we expect future archives to measure on the order of Exa-Bytes. In this work, we present the successful application of TECA (Toolkit for Extreme Climate Analysis) framework, for extracting extreme weather patterns such as Tropical Cyclones, Atmospheric Rivers and Extra-Tropical Cyclones from TB-sized simulation datasets. TECA has been run at full-scale on Cray XE6 and IBM BG/Q systems, and has reduced the runtime for pattern detection tasks from years to hours. TECA has been utilized to evaluate the performance of various computational models in reproducing the statistics of extreme weather events, and for characterizing the change in frequency of storm systems in the future.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2015

eXascale PRogramming Environment and System Software (XPRESS)

Exascale systems, with a thousand times the compute capacity of today’s leading edge petascale computers, are expected to emerge during the next decade. Their software systems will need to facilitate the exploitation of exceptional amounts of concurrency in applications, and ensure that jobs continue to run despite the occurrence of system failures and other kinds of hard and soft errors. Adapting computations at runtime to cope with changes in the execution environment, as well as to improve power and performance characteristics, is likely to become the norm. As a result, considerable innovation is required to develop system support to meet the needs of future computing platforms. The XPRESS project aims to develop and prototype a revolutionary software system for extreme-­scale computing for both exascale and strong­scaled problems. The XPRESS collaborative research project will advance the state-­of-­the-­art in high performance computing and enable exascale computing for current and future DOE mission-­critical applications and supporting systems. The goals of the XPRESS research project are to: A. enable exascale performance capability for DOE applications, both current and future, B. develop and deliver a practical computing system software X-­stack, OpenX, for future practical DOE exascale computing systems, and C. provide programming methods and environments for effective means of expressing application and system software for portable exascale system execution.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Dynamic Species Reduction for Multi-Cycle CFD Simulations (Final Technical Report)

This project primarily sought to address some of the computational cost concerns of detailed simulations by developing improved methods of handling species transport, and chemical kinetics evaluation in a commercial 3D Computational Fluid Dynamics (CFD) environment. Secondary goals were to apply these techniques to fuels and conditions of interest to better understand the key species and reactions required to adequately capture cycle to cycle coupling. Improved modeling will lead to better understanding of these combustion modes and their dependence on fuel composition, which can then enable more clean and efficient engines, ultimately benefiting the consumer as well as the general public. Two approaches were used to address the computational cost. A “Dynamic Species Reduction” (DSR) procedure was developed to remove chemical species from the simulation during periods when chemical reactions were not expected to be important, particularly during gas exchange when temperatures are low and little fuel remains. This modelling procedure automatically detects relevant species to retain in the simulation domain based on their local concentration, removes species below a specified concentration threshold, and then adjusts the remaining species mass to conserve not only the number of H, C, and O atoms in each cell, but also the relative proportions between species and the heating value of the mixture in every cell. The second procedure was a “Product Directed Remapping” (PDR) updates the algorithm used to group individual computational cells for chemical kinetics evaluation to account for non-uniform temperature distributions and the CO to CO 2 ratio in the cells. The model techniques developed in this work successfully demonstrated computational performance improvements for a range of conditions relevant for Highly Dilute SI and HCCI engine operation. Runtime reductions of 10% were observed for small mechanisms, with further reductions of up to 36% observed for larger mechanisms. Improvements were primarily related to reducing the number of chemical species tracked during the gas exchange process using the Dynamic Species Reduction method. With smaller benefits observed from changes to the kinetics binning and evaluation strategy in the post combustion region using the PDR method. The results of this work show the potential for improved computational runtime for complicated simulations. They can and should be extended to additional conditions and new bio-derived and renewable fuels as they are developed and new kinetic mechanisms become available.

10 SYNTHETIC FUELS↗
DOE OSTI2017

XPRESS: eXascale PRogramming Environment and System Software

The XPRESS project is the research and development of a complete software architecture for Exascale computing. The four major R&D thrusts include: 1) an Exascale lightweight kernel operating system (LXK), based on the Kitten operating system (OS), to manage billion way hardware parallelism, management of faults and power, management of global virtual name space, and other features of future system architectures; 2) a runtime system (HPX-5), co-designed with LXK, based on the ParalleX execution model that supports dynamic resource management and task scheduling; 3) system interfaces for interoperability between the runtime system and both the OS and the runtime system (RIOS); 4) compilation strategies and systems to translate MPI and OpenMP legacy codes to a form that can be run with performance at least as good as a native code implementation. The software architecture development has been driven by performance evaluation of mini-applications developed at Department of Energy Co-Design Centers as well as ancillary in-house developed applications and benchmarks. Research on the ParalleX execution model has been driven by the development of formal semantics and model checkers for the execution model. The major components of the software architecture are: ParalleX execution model – guiding principles for co-design of components of the system stack with advances in locality management and task prioritization through introspection; HPX runtime system – support of application dynamic adaptive resource management, task scheduling, and introspective control policies; LXK operating system – lightweight kernel operating system for order-constant scalability and low/no noise to manage resources; RIOS – a realm of Exascale system operation unique in the XPRESS project that includes the relationship between the new generation of lightweight kernel operating systems and runtime system software; XPI advanced programming model – intermediate form and low-level (readable) programming interface reflecting the ParalleX model, providing a target for source-to- source high level parallel language translation, and supporting early direct programming experimentation and measurement; Performance models & metrics – providing parameters and their mutual sensitivities to guide co-design and quantify operational behavior; Legacy migration – ensuring seamless transition of legacy codes and programming methods to the future generation of ParalleX-based Exascale systems; . Experiments and evaluation – critical to determining degree of effectiveness and likelihood of ultimate success as well as guiding corrective design changes to achieve DOE objectives; and Applications – collaborations with Co-Design Centers and other mission critical codes. The exemplar implementation of the ParalleX execution model, HPX-5, has been released along with five fully ported applications (LULESH, HPCG, SSSP, WAMR, and DASHMM) and multiple microbenchmarks. Using these applications, the system architecture demonstrated dynamic load balancing through active migration, legacy code migration, and data-driven approaches to for graph-like applications. Crucially for Exascale and billion way parallelism, the needs and patterns of irregular applications in HPX-5 were addressed using local flow control rather than relying on globally synchronized data structures.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Faster Tensor Network Decoding for Topological Quantum Codes

We present a fast and Bayes-optimal-approximating tensor network decoder for planar quantum LDPC codes based on the tensor renormalization group algorithm, originally proposed by Levin, and Nave. By precomputing the renormalization group flow for the null syndrome, we need only recompute tensor contractions in the causal cone of the measured syndrome at the time of decoding. This allows us to achieve an overall runtime complexity of ($pnχ^6$) where p is the depolarizing noise rate, and χ is the cutoff value used to control singular value decomposition approximations used in the algorithm. We apply our decoder to the surface code in the code capacity noise model and compare its performance to the original matrix product state (MPS) tensor network decoder introduced by Bravyi, Suchara, and Vargo. The MPS decoder has a p-independent runtime complexity of $\mathcal{O}(nχ^3)$ resulting in significantly slower decoding times compared to our algorithm in the low-p regime.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Performance Optimization for Relative-Error-Bounded Lossy Compression on Scientific Data

Scientific simulations in high-performance computing (HPC) environments generate vast volume of data, which may cause a severe I/O bottleneck at runtime and a huge burden on storage space for postanalysis. Unlike traditional data reduction schemes such as deduplication or lossless compression, not only can error-controlled lossy compression significantly reduce the data size but it also holds the promise to satisfy user demand on error control. Pointwise relative error bounds (i.e., compression errors depends on the data values) are widely used by many scientific applications with lossy compression since error control can adapt to the error bound in the dataset automatically. Pointwise relative-error-bounded compression is complicated and time consuming. In this article, we develop efficient precomputation-based mechanisms based on the SZ lossy compression framework. Our mechanisms can avoid costly logarithmic transformation and identify quantization factor values via a fast table lookup, greatly accelerating the relative-error-bounded compression with excellent compression ratios. In addition, we reduce traversing operations for Huffman decoding, significantly accelerating the decompression process in SZ. Experiments with eight well-known real-world scientific simulation datasets show that our solution can improve the compression and decompression rates (i.e., the speed) by about 40 and 80 p, respectively, in most of cases, making our designed lossy compression strategy the best-in-class solution in most cases.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2018

Multi-Level Load Balancing with an Integrated Runtime Approach

The recent trend of increasing numbers of cores per chip has resulted in vast amounts of on-node parallelism. These high core counts result in hardware variability that introduces imbalance. Applications are also becoming more complex, re-sulting in dynamic load imbalance. Load imbalance of any kind can result in loss of performance and system utilization. We address the challenge of handling both transient and persistent load imbalances while maintaining locality with low overhead. In this paper, we propose an integrated runtime system that combines the Charm++ distributed programming model with concurrent tasks to mitigate load imbalances within and across shared memory address spaces. It utilizes a periodic assignment of work to cores based on load measurement, in combination with user created tasks to handle load imbalance. We integrate OpenMP with Charm++ to enable creation of potential tasks via OpenMP's parallel loop construct. This is also available to MPI applications through the Adaptive MPI implementation. We demonstrate the benefits of our work on three applications. We show improvements of Lassen by 29.6% on Cori and 46.5% on Theta. We also demonstrate the benefits on a Charm++ application, ChaNGa by 25.7% on Theta, as well as an MPI proxy application, Kripke, using Adaptive MPI.

Bak, Seonmyeong↗
DOE OSTI2019

PPT-GPU: Scalable GPU Performance Modeling

Performance modeling is a challenging problem due to the complexities of hardware architectures. In this paper, we present PPT-GPU, a scalable and accurate simulation framework that enables GPU code developers and architects to predict the performance of applications in a fast, and accurate manner on different GPU architectures. PPT-GPU is part of the open source project, Performance Prediction Toolkit (PPT) developed at the Los Alamos National Laboratory. We extend the old GPU model in PPT that predict the runtimes of computational physics codes to offer better prediction accuracy, for which, we add models for different memory hierarchies found in GPUs and latencies for different instructions. To further show the utility of PPT-GPU, we compare our model against real GPU device(s) and the widely used cycle-accurate simulator, GPGPU-Sim using different workloads from RODINIA and Parboil benchmarks. The results indicate that the predicted performance of PPT-GPU is within a 10% error compared to the real device(s). In addition, PPT-GPU is highly scalable, where it is up to 450x faster than GPGPU-Sim with more accurate results.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2014

ACDT: Architected Composite Data Types Trading-in Unfettered Data Access for Improved Execution

With Exascale performance and its challenges in mind, one ubiquitous concern among architects is energy efficiency. Petascale systems projected to Exascale systems are unsustainable at current power consumption rates. One major contributor to system-wide power consumption is the number of memory operations leading to data movement and management techniques applied by the runtime system. To address this problem, we present the concept of the Architected Composite Data Types (ACDT) framework. The framework is made aware of data composites, assigning them a specific layout, transformations and operators. Data manipulation overhead is amortized over a larger number of elements and program performance and power efficiency can be significantly improved. We developed the fundamentals of an ACDT framework on a massively multithreaded adaptive runtime system geared towards Exascale clusters. Showcasing the capability of ACDT, we exercised the framework with two representative processing kernels - Matrix Vector Multiply and the Cholesky Decomposition – applied to sparse matrices. As transformation modules, we applied optimized compress/decompress engines and configured invariant operators for maximum energy/performance efficiency. Additionally, we explored two different approaches based on transformation opaqueness in relation to the application. Under the first approach, the application is agnostic to compression and decompression activity. Such approach entails minimal changes to the original application code, but leaves out potential applicationspecific optimizations. The second approach exposes the decompression process to the application, hereby exposing optimization opportunities that can only be exploited with application knowledge. The experimental results show that the two approaches have their strengths in HW and SW respectively, where the SW approach can yield performance and power improvements that are an order of magnitude better than ACDT-oblivious, hand-optimized implementations.We consider the ACDT runtime framework an important component of compute nodes that will lead towards power efficient Exascale clusters.

exascale↗
DOE OSTI2016

Reducing I/O variability using dynamic I/O path characterization in petascale storage systems

In petascale systems with a million CPU cores, scalable and consistent I/O performance is becoming increasingly difficult to sustain mainly because of I/O variability. Furthermore, the I/O variability is caused by concurrently running processes/jobs competing for I/O or a RAID rebuild when a disk drive fails. We present a mechanism that stripes across a selected subset of I/O nodes with the lightest workload at runtime to achieve the highest I/O bandwidth available in the system. In this paper, we propose a probing mechanism to enable application-level dynamic file striping to mitigate I/O variability. We also implement the proposed mechanism in the high-level I/O library that enables memory-to-file data layout transformation and allows transparent file partitioning using subfiling. Subfiling is a technique that partitions data into a set of files of smaller size and manages file access to them, making data to be treated as a single, normal file to users. Here, we demonstrate that our bandwidth probing mechanism can successfully identify temporally slower I/O nodes without noticeable runtime overhead. Experimental results on NERSC’s systems also show that our approach isolates I/O variability effectively on shared systems and improves overall collective I/O performance with less variation.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

A Case Study with the HACCmk Kernel in SYCL

The SYCL standard specifies a cross-platform abstraction layer that enables programming of heterogeneous computing systems using standard C++ [1]. In the Open Computing Language (OpenCL) programming model, host and device codes are written in different languages [2 ]. To improve development productivity and performance portability, the SYCL programming model combines host and device codes for an application in a type-safe way. In this report, we are interested in applying the SYCL programming model to a computationally intensive routine derived from the Hardware Accelerated Cosmology Code (HACC) framework for a study on performance portability on a heterogeneous computing device. We use Intel® OneAPI toolkit [3] to build the OpenCL and SYCL programs, and evaluate the performance of both implementations on Intel® integrated GPUs. We find that the SYCL implementation can achieve the same performance as the OpenCL implementation after we specify a target backend for the compiler to build the SYCL program in offline compilation. Without the specification of a target backend, the runtime will have to compile intermediate device codes for a target platform. Such runtime overhead may become significant compared to the execution of a kernel on a target device. As the kernel routine is compute-bound, we evaluate the impact of the number of compute units upon the kernel’s raw performance using two GPUs. When the hardware resource is not underutilized, we can obtain almost linear performance speedup from 48 compute units to 72 compute units in offline compilation, which indicates that the number of compute units on a GPU are important to improving the raw performance of a compute-bound kernel. The experimental results show that SYCL is a promising programming model for heterogeneous computing. The remainder of the report is organized as follows: In Section II, we describe the SYCL programming model, the steps to map an OpenCL program to a SYCL program, and the architecture of an integrated GPU. Section III introduces the kernel routine, and presents the OpenCL and SYCL implementations of the kernel. In Section IV, we evaluate the performance of the implementations on the GPUs. Section V concludes the report.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Comparing the Performance of Julia on CPUs versus GPUs and Julia-MPI versus Fortran-MPI: a case study with MPAS-Ocean (Version 7.1)

Abstract. Some programming languages are easy to develop at the cost of slow execution, while others are fast at runtime but much more difficult to write. Julia is a programming language that aims to be the best of both worlds – a development and production language at the same time. To test Julia's utility in scientific high-performance computing (HPC), we built an unstructured-mesh shallow water model in Julia and compared it against an established Fortran-MPI ocean model, the Model for Prediction Across Scales–Ocean (MPAS-Ocean), as well as a Python shallow water code. Three versions of the Julia shallow water code were created: for single-core CPU, graphics processing unit (GPU), and Message Passing Interface (MPI) CPU clusters. Comparing identical simulations revealed that our first version of the Julia model was 13 times faster than Python using NumPy, where both used an unthreaded single-core CPU. Further Julia optimizations, including static typing and removing implicit memory allocations, provided an additional 10–20× speed-up of the single-core CPU Julia model. The GPU-accelerated Julia code was almost identical in terms of performance to the MPI parallelized code on 64 processes, an unexpected result for such different architectures. Parallelized Julia-MPI performance was identical to Fortran-MPI MPAS-Ocean for low processor counts and ranges from 2× faster to 2× slower for higher processor counts. Our experience is that Julia development is fast and convenient for prototyping but that Julia requires further investment and expertise to be competitive with compiled codes. We provide advice on Julia code optimization for HPC systems.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Comparison of nested geometry treatments within GPU-based Monte Carlo neutron transport simulations of fission reactors

Monte Carlo (MC) neutron transport provides detailed estimates of radiological quantities within fission reactors. This involves tracking individual neutrons through a computational geometry. CPU-based MC codes use multiple polymorphic tracker types with different tracking algorithms to exploit the repeated configurations of reactors, but virtual function calls have high overhead on the GPU. The Shift MC code was modified to support GPU-based tracking with three strategies: dynamic polymorphism with virtual functions, static polymorphism, and a single tracker type with tree-based acceleration. On the Frontier supercomputer these methods achieve 77.8%, 91.2%, and 83.4%, respectively, of the tracking rate obtained using a specialized tracker optimized for rectilinear-grid-based reactors. This indicates that all three methods are suitable for typical reactor problems in which tracking does not dominate runtime. The flexibility of the single tracker method is highlighted with a hexagonal-grid microreactor problem, performed without hexagonal-grid-specific tracking routines, providing a 2.19× speedup over CPU execution.

97 MATHEMATICS AND COMPUTING↗