User Support for an MPP, JPL Begins the Process
At Supercomputing 92, it was announced that JPL/Caltech had entered into a collaborative agreement with Cray Research to become one of a few.
Cray user support planning collaboration↗
SEARCH · Search NASA
Results for “Cray”
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.
Interfacing HDF5 with a scalable object‐centric storage system on hierarchical storage
Summary Object storage technologies that take advantage of multitier storage on HPC systems are emerging. However, to use these technologies at present, applications have to be modified significantly from current I/O libraries. HDF5, a widely used I/O middleware on HPC systems, provides a virtual object layer (VOL) that allows applications to connect to different storage mechanisms transparently without requiring significant code modifications. We recently designed the proactive data containers (PDC) object‐centric storage system that provides the capabilities of transparent, asynchronous, and autonomous data movement taking advantage of multiple storage tiers—a decision that has so far been left upon the user on most current systems. To enable PDC's features through HDF5 without modifying application codes, we have developed an HDF5 VOL connector that interfaces with PDC. We present in this article the connector interface and evaluate its performance on Cori, a Cray XC40 supercomputer located at the National Energy Research Scientific Computing Center (NERSC). Our evaluation demonstrates up to an 8× improvement compared with HDF5 that has the most recent optimizations.
Mu, Jingqing↗
Utilizing ensemble learning for performance and power modeling and improvement of parallel cancer deep learning CANDLE benchmarks
Abstract Machine learning (ML) continues to grow in importance across nearly all domains in modeling to learn from data. Often a tradeoff exists between a model's ability to minimize bias and variance. In this article, we utilize ensemble learning to combine linear, nonlinear, and tree‐/rule‐based ML methods to cope with the bias‐variance tradeoff and result in more accurate models. We use the datasets collected for two parallel cancer deep learning CANDLE benchmarks, NT3 and P1B2, to build performance and power models based on hardware performance counters using single‐object and multiple‐objects ensemble learning to identify the most important counters for improvement on the Cray XC40 Theta at Argonne National Laboratory. Based on the insights from these models, we improve the performance and energy of P1B2 and NT3 by optimizing the deep learning environments TensorFlow, Keras, Horovod, and Python under the huge page size of 8 MB. Experimental results show that ensemble learning not only produces more accurate models but also provides more robust performance counter ranking. We achieve up to 61.15% performance improvement and up to 62.58% energy saving for P1B2 and up to 55.81% performance improvement and up to 52.60% energy saving for NT3 on up to 24,576 cores.
Wu, Xingfu↗
Performance and power modeling and prediction using MuMMI and 10 machine learning methods
Energy-efficient scientific applications require insight into how high performance computing system features impact the applications' power and performance. This insight can result from the development of performance and power models. Here, in this article, we use the modeling and prediction tool MuMMI (Multiple Metrics Modeling Infrastructure) and 10 machine learning methods to model and predict performance and power consumption and compare their prediction error rates. We use an algorithm-based fault-tolerant linear algebra code and a multilevel checkpointing fault-tolerant heat distribution code to conduct our modeling and prediction study on the Cray XC40 Theta and IBM BG/Q Mira at Argonne National Laboratory and the Intel Haswell cluster Shepard at Sandia National Laboratories. Our experimental results show that the prediction error rates in performance and power using MuMMI are less than 10% for most cases. By utilizing the models for runtime, node power, CPU power, and memory power, we identify the most significant performance counters for potential application optimizations, and we predict theoretical outcomes of the optimizations. Based on two collected datasets, we analyze and compare the prediction accuracy in performance and power consumption using MuMMI and 10 machine learning methods.
97 MATHEMATICS AND COMPUTING↗
Early experiences on the OLCF Frontier system with AthenaPK and Parthenon–Hydro
The Oak Ridge Leadership Computing Facility (OLCF) has been preparing the nation's first exascale system, Frontier, for production and end users. Frontier is based on HPE Cray's new EX architecture and Slingshot interconnect and features 74 cabinets of optimized 3rd Gen AMD EPYC CPUs for HPC and AI and AMD Instinct 250X accelerators. As a part of this preparation, “real-world” user codes have been selected to help assess the functionality, performance, and usability of the system. This article describes early experiences using the system in collaboration with the Hamburg Observatory for two selected codes, which have since been adopted in the OLCF test harness. Experiences discussed include efforts to resolve performance variability and per-cycle slowdowns. Results are shown for a performance portable astrophysical magnetohydronamics code, AthenaPK, and a mini-application stressing the core functionality of a performance portable block-structured adaptive mesh refinement framework, Parthenon-Hydro. Here, these results show good scaling characteristics to the full system. At the largest scale, the Parthenon-Hydro miniapp reaches a total of $1.7$ $\times$ $10^{13}$ zone-cycles/s on 9216 nodes (73,728 logical GPUs) at ≈92% weak scaling parallel efficiency (starting from a single node using a second-order, finite-volume method).
97 MATHEMATICS AND COMPUTING↗
Architecture and performance of Perlmutter's 35 PB ClusterStor E1000 all-flash file system
NERSC's newest system, Perlmutter, features a 35 PB all-flash Lustre file system built on HPE Cray ClusterStor E1000. Here, we present its architecture, early performance figures, and performance considerations unique to this architecture. We demonstrate the performance of E1000 OSSes through low-level Lustre tests that achieve over 90% of the theoretical bandwidth of the SSDs at the OST and LNet levels. We also show end-to-end performance for both traditional dimensions of I/O performance (peak bulk-synchronous bandwidth) and nonoptimal workloads endemic to production computing (small, incoherent I/Os at random offsets) and compare them to NERSC's previous system, Cori, to illustrate that Perlmutter achieves the performance of a burst buffer and the resilience of a scratch file system. Finally, we discuss performance considerations unique to all-flash Lustre and present ways in which users and HPC facilities can adjust their I/O patterns and operations to make optimal use of such architectures.
97 MATHEMATICS AND COMPUTING↗
Bringing HPE Slingshot 11 support to Open MPI
The Cray HPE Slingshot 11 network is used on the new exascale systems arriving at the U.S. Department of Energy (DoE) laboratories (e.g., Frontier, Aurora, Perlmutter). As such, the support of this network is an important capability to meet the needs of exascale applications. Here, this article highlights recent work to develop supporting infrastructure to enable Open MPI to efficiently support these new platforms. A key component of this effort involves development of a new Open Fabrics Interface (OFI) provider, LinkX. We discuss the design and development of enhancements that take advantage of the new Slingshot 11 network and AMD GPUs. We include performance data from tests on the Frontier supercomputer using synthetic communication benchmarks, and the vendor provided MPI as a baseline for comparison. The tests demonstrate full functionality of Open MPI on the system and initial results show favorable performance when compared to the highly tuned vendor implementation.
97 MATHEMATICS AND COMPUTING↗
Queue wait time prediction in high performance computing (HPC) systems
High Performance Computing (HPC) systems are critical enablers for groundbreaking scientific research across various domains. Efficient resource allocation, facilitated by job scheduling, is paramount for maximizing the utilization of HPC systems. However, the variability in wait times for queued jobs poses challenges for users, necessitating accurate job wait time estimation. This paper explores the influence of job characteristics, including job size (the number of nodes requested and walltime), the queue to which the job is submitted and other resource requirements, on job wait times in leadership-class HPC systems. Focusing on the Theta Cray XC40 and Polaris machines at Argonne National Laboratory, the study evaluates the performance of different supervised learning algorithms in predicting job wait times. It also evaluates the impact of data preprocessing, including outlier detection, Principal Component Analysis (PCA), and feature selection, on the performance of wait time prediction models. The findings reveal insights into the relationship between job characteristics and wait times, offering a foundation for optimizing resource allocation and enhancing user experience. The methodologies and tools developed in this study are adaptable to other leadership-class HPC systems, providing a valuable contribution to the broader HPC community aiming to improve job scheduling efficiency and user satisfaction.
Okafor, Nwamaka↗
Parallel algorithms for finding connected components using linear algebra
Finding connected components is one of the most widely used operations on a graph. Optimal serial algorithms for the problem have been known for half a century, and many competing parallel algorithms have been proposed over the last several decades under various different models of parallel computation. This paper presents a class of parallel connected-component algorithms designed using linear-algebraic primitives. These algorithms are based on a PRAM algorithm by Shiloach and Vishkin and can be designed using standard GraphBLAS operations. Here, we demonstrate two algorithms of this class, one named LACC for Linear Algebraic Connected Components, and the other named FastSV which can be regarded as LACC’s simplification. With the support of the highly-scalable Combinatorial BLAS library, LACC and FastSV outperform the previous state-of-the-art algorithm by a factor of up to 12x for small to medium scale graphs. For large graphs with more than 50B edges, LACC and FastSV scale to 4K nodes (262K cores) of a Cray XC40 supercomputer and outperform previous algorithms by a significant margin. This remarkable performance is accomplished by (1) exploiting sparsity that was not present in the original PRAM algorithm formulation, (2) using high-performance primitives of Combinatorial BLAS, and (3) identifying hot spots and optimizing them away by exploiting algorithmic insights.
97 MATHEMATICS AND COMPUTING↗
Enabling Fortran Standard Parallelism in GAMESS for Accelerated Quantum Chemistry Calculations
The performance of Fortran 2008 DO CONCURRENT (DC) relative to OpenACC and OpenMP target offloading (OTO) with different compilers is studied for the GAMESS quantum chemistry application. Specifically, DC and OTO are used to offload the Fock build, which is a computational bottleneck in most quantum chemistry codes, to GPUs. The DC Fock build performance is studied on NVIDIA A100 and V100 accelerators and compared with the OTO versions compiled by the NVIDIA HPC, IBM XL, and Cray Fortran compilers. The results show that DC can speed up the Fock build by 3.0× compared with that of the OTO model. Finally, with similar offloading efforts, DC is a compelling programming model for offloading Fortran applications to GPUs.
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
Energy dataset of Frontier supercomputer for waste heat recovery
The Hewlett Packard Enterprise–Cray EX Frontier is the world’s first and fastest exascale supercomputer, hosted at the Oak Ridge Leadership Computing Facility in Tennessee, United States. Frontier is a significant electricity consumer, drawing 8–30 MW; this massive energy demand produces significant waste heat, requiring extensive cooling measures. Although harnessing this waste heat for campus heating is a sustainability goal at Oak Ridge National Laboratory (ORNL), the 30 °C–38 °C waste heat temperature poses compatibility issues with standard HVAC systems. Heat pump systems, prevalent in residential settings and some industries, can efficiently upgrade low-quality heat to usable energy for buildings. Thus, heat pump technology powered by renewable electricity offers an efficient, cost-effective solution for substantial waste heat recovery. However, a major challenge is the absence of benchmark data on high-performance computing (HPC) heat generation and waste heat profiles. This paper reports power demand and waste heat measurements from an ORNL HPC data centre, aiming to guide future research on optimizing waste heat recovery in large-scale data centres, especially those of HPC calibre.
97 MATHEMATICS AND COMPUTING↗
Global adjoint tomography—model GLAD-M25
SUMMARY Building on global adjoint tomography model GLAD-M15, we present transversely isotropic global model GLAD-M25, which is the result of 10 quasi-Newton tomographic iterations with an earthquake database consisting of 1480 events in the magnitude range 5.5 ≤ Mw ≤ 7.2, an almost sixfold increase over the first-generation model. We calculated fully 3-D synthetic seismograms with a shortest period of 17 s based on a GPU-accelerated spectral-element wave propagation solver which accommodates effects due to 3-D anelastic crust and mantle structure, topography and bathymetry, the ocean load, ellipticity, rotation and self-gravitation. We used an adjoint-state method to calculate Fréchet derivatives in 3-D anelastic Earth models facilitated by a parsimonious storage algorithm. The simulations were performed on the Cray XK7 ‘Titan’ and the IBM Power 9 ‘Summit’ at the Oak Ridge Leadership Computing Facility. We quantitatively evaluated GLAD-M25 by assessing misfit reductions and traveltime anomaly histograms in 12 measurement categories. We performed similar assessments for a held-out data set consisting of 360 earthquakes, with results comparable to the actual inversion. We highlight the new model for a variety of plumes and subduction zones.
58 GEOSCIENCES↗
Communication-Avoiding and Memory-Constrained Sparse Matrix-Matrix Multiplication at Extreme Scale
Sparse matrix-matrix multiplication (SpGEMM) is a widely used kernel in various graph, scientific computing and machine learning algorithms. In this paper, we consider SpGEMMs performed on hundreds of thousands of processors generating trillions of nonzeros in the output matrix. Distributed SpGEMM at this extreme scale faces two key challenges: (1) high communication cost and (2) inadequate memory to generate the output. Furthermore, we address these challenges with an integrated communication-avoiding and memory-constrained SpGEMM algorithm that scales to 262,144 cores (more than 1 million hardware threads) and can multiply sparse matrices of any size as long as inputs and a fraction of output fit in the aggregated memory. As we go from 16,384 cores to 262,144 cores on a Cray XC40 supercomputer, the new SpGEMM algorithm runs 10x faster when multiplying large-scale protein-similarity matrices.
97 MATHEMATICS AND COMPUTING↗
Performance Evaluation of Adaptive Routing on Dragonfly-based Production Systems
Performance of applications in production environments can he sensitive to network congestion. Cray Aries supports adaptively routing each network packet independently based on the load or congestion encountered as a packet traverses the network. Software can dictate different routing policies, adjusting between minimal and non-minimal bias, for each posted message. We have extensively evaluated the sensitivity of the routing bias selection on application performance as well as whole system performance in both production and controlled conditions. We show that the default routing bias used in Aries-based systems is often sub-optimal and that using a higher bias towards minimal routes will not only reduce the congestion effects on the application but also will decrease the overall congestion on the network. This routing scheme results in not only improved mean performance (by up to 12%) of most production applications hut also reduced run-to-run variability. Our study prompted the two supercomputing facilities (ALCF and NERSC) to change the default routing mode on their Aries-based systems. We present the substantial improvement measured in the overall congestion management and interconnect performance in production after making this change.
Chunduri, Sudheer↗
GPU Lifetimes on Titan Supercomputer: Survival Analysis and Reliability
The Cray XK7 Titan was the top supercomputer system in the world for a long time and remained critically important throughout its nearly seven year life. It was an interesting machine from a reliability viewpoint as most of its power came from 18,688 GPUs whose operation was forced to execute three rework cycles, two on the GPU mechanical assembly and one on the GPU circuitboards. We write about the last rework cycle and a reliability analysis of over 100,000 years of GPU lifetimes during Titan’s 6-year-long productive period. Using time between failures analysis and statistical survival analysis techniques, we find that GPU reliability is dependent on heat dissipation to an extent that strongly correlates with detailed nuances of the cooling architecture and job scheduling. We describe the history, data collection, cleaning, and analysis and give recommendations for future supercomputing systems. We make the data and our analysis codes publicly available.
Ostrouchov, George↗
Improving MPI Collective I/O for High Volume Non-Contiguous Requests With Intra-Node Aggregation
Two-phase I/O is a well-known strategy for implementing collective MPI-IO functions. It redistributes I/O requests among the calling processes into a form that minimizes the file access costs. As modern parallel computers continue to grow into the exascale era, the communication cost of such request redistribution can quickly overwhelm collective I/O performance. In this study, this effect has been observed from parallel jobs that run on multiple compute nodes with a high count of MPI processes on each node. Furthermore, to reduce the communication cost, we present a new design for collective I/O by adding an extra communication layer that performs request aggregation among processes within the same compute nodes. This approach can significantly reduce inter-node communication contention when redistributing the I/O requests. We evaluate the performance and compare it with the original two-phase I/O on Cray XC40 parallel computers (Theta and Cori) with Intel KNL and Haswell processors. Using I/O patterns from two large-scale production applications and an I/O benchmark, we show our proposed method effectively reduces the communication cost and hence maintains the scalability for a large number of processes.
97 MATHEMATICS AND COMPUTING↗
Optimization and Portability of a Fusion OpenACC-based FORTRAN HPC Code from NVIDIA to AMD GPUs
NVIDIA has been the main provider of GPU hardware in HPC systems for over a decade. Most applications that benefit from GPUs have thus been developed and optimized for the NVIDIA software stack. Recent exascale HPC systems are, however, introducing GPUs from other vendors, e.g. with the AMD GPU-based OLCF Frontier system just becoming available. AMD GPUs cannot be directly accessed using the NVIDIA software stack, and require a porting effort by the application developers. This paper provides an overview of our experience porting and optimizing the CGYRO code, a widely-used fusion simulation tool based on FORTRAN with OpenACC-based GPU acceleration. While the porting from the NVIDIA compilers was relatively straightforward using the CRAY compilers on the AMD systems, the performance optimization required more fine-tuning. In the optimization effort, we uncovered code sections that had performed well on NVIDIA GPUs, but were unexpectedly slow on AMD GPUs. After AMD-targeted code optimizations, performance on AMD GPUs has increased to meet our expectations. Modest speed improvements were also seen on NVIDIA GPUs, which was an unexpected benefit of this exercise.
Sfiligoi, Igor↗
Fine-Grained Application Energy and Power Measurements on the Frontier Exascale System
The increasing complexity and power/energy demands of heterogeneous exascale systems, such as the Frontier supercomputer, present significant challenges for measuring and optimizing power consumption in applications. Current tools either lack the resolution to capture fine-grained power and energy measurements, fail to validate in-band measurements against out-of-band power sensors, or cannot integrate this information with application performance events in a scalable manner. This paper introduces a novel open-source performance toolkit that integrates extended PAPI components with Score-P plugins to enable in-band, fine-grained power and energy measurements, while also supporting validation using power meter measurements for both CPUs and GPUs. One key contribution is the ability to perform millisecond-level power and energy measurements for AMD MI250X GPUs, mapping them to application performance events within a single trace and measurement system that scales. Our toolkit combines coarse-grained measurements from cray_pm counters with high-resolution metrics from rocm_smi and RAPL, converting GPU instantaneous accumulated energy into power to capture both transient and steady-state power behavior, a capability often missed by out-of-band and monitoring tools. By mapping these metrics to specific application regions, developers can identify energy hotspots, address inefficiencies in GPU kernel execution, and validate in-band measurements against external measurements. We demonstrate the effectiveness of this approach through case studies using benchmarks such as GPU rocblas_sgemm, BLIS c_blas_dgemm, and rocHPL, highlighting the variability of the measurements and the impact of transient power spikes on kernel-level efficiency.
Hernandez Mendoza, Oscar [ORNL] (ORCID:00000002538↗