Search NASA⌕ Search

SEARCH · Search NASA

Results for “Threading”

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 1,135 records · Page 63

Addressing Load Imbalance in Bioinformatics and Biomedical Applications: Efficient Scheduling across Multiple GPUs

Computational bioinformatics and biomedical applications frequently contain heterogeneously sized units of work or tasks, for instance due to variability in the sizes of biological sequences and molecules. Variable-sized workloads lead to load imbalances in parallel implementations which detract from efficiency and performance. Many modern computing resources now have multiple graphics processing units(GPUs) per computer for acceleration. These multiple GPU resources need to be used efficiently through balancing of workloads across the GPUs. OpenMP is a portable directive-based parallel programming API used ubiquitously in bioscience applications to program CPUs; recently, the use of OpenMP directives for GPU acceleration has become possible. Here, motivated by experiences with imbalanced loads in GPU-accelerated bioinformatics applications, we address the load balancing problem using OpenMP task-to-GPU scheduling combined with OpenMP GPU offloading for multiply heterogeneous workloads – loads with both variable input sizes, and simultaneously, variable convergence rates for algorithms with a stochastic component – scheduled across multiple GPUs. We aim to develop strategies which are both easy to use and have lower overheads, and may be incorporated incrementally in existing programs which already make use of OpenMP for CPU-based threading in order to make use of multi-GPU computers. We test different combinations of input size variability and convergence rate variability, and characterize the effects of these different scenarios on the performance of scheduling strategies across multiple GPUs with OpenMP. We present several dynamic scheduling solutions for different parallel patterns, explore optimizations, and provide publicly available example computational kernels to make these strategies easy to use in programs. This work will enable application developers to efficiently and easily use multiple GPUs for imbalanced workloads found in bioinformatics and biomedical applications.

Thavappiragasam, Mathialakan↗

A Flexible-blocking Based Approach for Performance Tuning of Matrix Multiplication Routines for Large Matrices with Edge Cases

Efficient and scalable matrix operations are being highly demanding in the recent era of Machine Learning, Deep Learning, and Big Data Analytics. The two commonly used matrix-matrix operations in the Basic Linear Algebra Subprograms (BLAS) specification are General Matrix-Matrix multiplication (GEMM) and Symmetric Rank-k update (SYRK). The SYRK routine is a specialization of the GEMM routine, where half of the multiplications are skipped as the resultant matrix is known to be symmetric. Fortunately, several linear algebra libraries implement these BLAS routines quite efficiently. The libraries usually partition the input matrices into blocks and place them in processor caches, thus improving performance by leveraging the caches. However, the contemporary libraries are highly optimized for squarish matrices, but the performance degrades significantly for the matrices with edge case (strictly thin or strictly fat shapes) in the multicore machine. The primary reason is that the current state-of-the-art libraries make fixed block shapes based on a processor architecture, and do not consider the shape of the input matrices. In this paper, we propose a new blocking approach, we name it Flexible-blocking, to mitigate the scalability issues. In contrast to the contemporary libraries, our approach formulates the blocks of the input matrices based on the shapes of the matrices as well as the number of threads used in the implementation. Our proposed technique shows noticeable performance improvement on multicore shared-memory machines for the edge case matrices.

Hossain, Md Mosharaf↗

Landrush: Rethinking In-Situ Analysis for GPGPU Workflows

In-situ analysis on the output data of scientific simulations has been made necessary by ever-growing output data volumes and increasing costs of data movement as supercomputing is moving towards exascale. With hardware accelerators like GPUs becoming increasingly common in high end machines, new opportunities arise to co-locate scientific simulations and online analysis performed on the scientific data generated by the simulations. However, the asynchronous nature of GPGPU programming models and the limited context-switching capabilities on the GPU pose challenges to co-locating the scientific simulation and analysis on the same GPU. This paper dives deeper into these challenges to understand how best to co-locate analysis with scientific simulations on the GPUs in HPC clusters. Specifically, our 'Landrush' approach to GPU sharing proposes a solution that utilizes idle cycles on the GPU to provide an improved time-to-answer, that is, the total time to run the scientific simulation and analysis of the generated data. Landrush is demonstrated with experimental results obtained from leadership high-end applications on ORNL's Titan supercomputer, which show that (i) GPU-based scientific simulations have varying degrees of idle cycles to afford useful analysis task co-location, and (ii) the inability to context switch on the GPU at instruction granularity can be overcome by careful control of the analysis kernel launches and software-controlled early completion of analysis kernel executions. Results show that Landrush is superior in terms of time-to-answer compared to serially running simulations followed by analysis or by relying on the GPU driver and hardwired thread dispatcher to run analysis concurrently on a single GPU.

Computer Science↗

AnalyzeThat: A Programmable Shared-Memory System for an Array of Processing-In-Memory Devices

Processing In Memory (PIM), the concept of integrating processing directly with memory, has been attracting a lot of attention since PIM can assist in overcoming the throughput limitation caused by data movement between CPU and memory. The challenge, however, is that it requires the programmers to have a deep understanding of the PIM architecture to maximize the benefits such as data locality and parallel thread execution on multiple PIM devices. In this study, we present AnalyzeThat, a programmable shared-memory system for parallel data processing with PIM devices. Thematic to AnalyzeThat is a rich PIM-Aware Data Structure (PADS), which is an encapsulation that integrally ties together the data, the analysis tasks and the runtime needed to interface with the PIM device array. The PADS abstraction provides (i) a key-value data container that allows programmers to easily store data on multiple PIMs, (ii) a suite of parallel operations with which users can easily implement data analysis applications, and (iii) a runtime, hidden to programmers, which provides the mechanisms needed to overlay both the data and the tasks on the PIM device array in an intelligent fashion, based on PIM-specific information collected from the hardware. We have developed a PIM emulation framework called AnalyzeThat. Our experimental evaluation with representative data analytics applications suggests that the proposed system can significantly reduce the PIM programming effort without losing its technology benefits.

97 MATHEMATICS AND COMPUTING↗

A Code Generator for High-Performance Tensor Contractions on GPUs

Tensor contractions are higher dimensional generalizations of matrix-matrix multiplication. They form the compute-intensive core for many applications in computational science and data science. Although high-performance library implementations are widely available for dense matrix-matrix multiplication on GPUs, the same is not true for contraction of dense tensors. In this paper, we describe a high- performance GPU code generator for arbitrary tensor contractions. It exploits domain-specific properties about data reuse in tensor contractions to devise an effective code generation schema, coupled with an effective model-driven search to determine parameters for mapping of computation to threads and staging of data through the GPU memory hierarchy. Experimental evaluation using a set of tensor contraction benchmarks demonstrates performance improvement and/or significantly reduced code generation time over other state-of-the-art tensor contraction libraries and code generators.

Kim, Jinsung↗

Acceleration of Streamed Tensor Contraction Expressions on GPGPU-based Clusters

Tensor contractions are generalized multidimensional matrix multiplication operations that widely occur in quantum chemistry. Efficient execution of tensor contractions on GPUs requires tackling several challenges to be addressed, including index permutation and small dimension-sizes reducing thread block utilization. In this paper, we present our approach to automatically generate CUDA code to execute tensor contractions on GPUs, including management of data movement between CPU and GPU. GPU-enabled code is generated for the most expensive contractions in CCSD(T) and incorporated into NWChem, a popular computational chemistry suite. We demonstrate speedup over a factor of 8.4 using one core per node and over 2.6 when utilizing the entire system using hybrid CPU+GPU solution with 2 GPUs and 5 cores. We finally analyze the behavior of the application on future GPU systems.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Making Corgis Important for Honeycomb Classification: Adversarial Attacks on Concept-based Explainability Tools

Methods for model explainability have become increasingly critical for testing the fairness and soundness of deep learning. Concept-based interpretability techniques, which use a small set of human-interpretable concept exemplars in order to measure the influence of a concept on a model's internal representation of input, are an important thread in this line of research. In this work we show that these explainability methods can suffer the same vulnerability to adversarial attacks as the models they are meant to analyze. We demonstrate this phenomenon on two well-known concept-based interpretability methods: TCAV and faceted feature visualization. We show that by leveraging the geometry of the problem and carefully perturbing the examples of the concept that is being investigated, we can radically change the output of the interpretability method. The attacks that we propose can either induce positive interpretations (polka dots are an important concept for a model when classifying zebras) or negative interpretations (stripes are not an important factor in identifying images of a zebra). Our work highlights the fact that in safety-critical applications, there is need for security around not only the machine learning pipeline but also the model interpretation process.

Brown, Davis R.↗

Educating HPC Users in the use of advanced computing technology

We examine a multi-modal approach to educating and training users of an advanced computing technology testbed at the Institute for Advanced Computational Science at Stony Brook University. Ookami provides researchers worldwide with access to 176 Fujitsu A64FX compute nodes, this being the same processor technology powering the Japanese Fugaku supercomputer, the fastest computer in the world since June 2020. However, achieving high-performance on this Arm-based, leadership computing technology requires that users be familiar with details of computer architecture, performance analysis and modeling, and high-performance programming models that are commonly omitted in introductory programming courses. Indeed, regardless of their seniority, many of the testbed users are surprisingly unfamiliar with basic concepts such as vectorization, pipelining, latency/bandwidth, roofline models, computing energy/power, threads, and non-uniform memory access. These same concepts also pervade mainstream x86 technologies, so this is of widespread concern. Due to the national/global nature of our user community that is also very diverse in both discipline and experience, the inability to offer formal classes, and our experience that most people do not tend to read online documentation or training materials in sufficient depth, we have consciously employed multiple approaches that heavily emphasize (online) personal interactions and transfer of skills. Online documentation has been organized around best-practices and FAQs; twice-weekly hackathons and office hours via Zoom enable deep dives by both the team and the user community with multiple broad benefits; a Slack channel provides both real time and archived answers and discussions; and workshops, training and webinars target community needs as they arise. Furthermore, the perspective that these tools are being used in an educational setting rather than just for project communication makes them more effective and contributes to community success.

A64FX↗

A High-Performance Design for Hierarchical Parallelism in the QMCPACK Monte Carlo code

We introduce a new high-performance design for parallelism within the Quantum Monte Carlo code QMCPACK. We demonstrate that the new design is better able to exploit the hierarchical parallelism of heterogeneous architectures compared to the previous GPU implementation. The new version is able to achieve higher GPU occupancy via the new concept of crowds of Monte Carlo walkers, and by enabling more host CPU threads to effectively offload to the GPU. The higher performance is expected to be achieved independent of the underlying hardware, significantly improving developer productivity and reducing code maintenance costs. Scientific productivity is also improved with full support for fallback to CPU execution when GPU implementations are not available or CPU execution is more optimal.

Luo, Ye↗

On the Suitability of MPI as a PGAS Runtime

Partitioned Global Address Space (PGAS) models are emerging as a popular alternative to MPI models for designing scalable applications. At the same time, MPI remains a ubiquitous communication subsystem due to its standardization, high performance, and availability on leading platforms. In this paper, we explore the suitability of using MPI as a scalable PGAS communication subsystem. We focus on the Remote Memory Access (RMA) communication in PGAS models which typically includes {\em get, put,} and {\em atomic memory operations}. We perform an in-depth exploration of design alternatives based on MPI. These alternatives include using a semantically-matching interface such as MPI-RMA, as well as not-so-intuitive interfaces such as MPI two-sided with a combination of multi-threading and dynamic process management. With an in-depth exploration of these alternatives and their shortcomings, we propose a novel design which is facilitated by the data-centric view in PGAS models. This design leverages a combination of highly tuned MPI two-sided semantics and an automatic, user-transparent split of MPI communicators to provide asynchronous progress. We implement the asynchronous progress ranks approach and other approaches within the Communication Runtime for Exascale which is a communication subsystem for Global Arrays. Our performance evaluation spans pure communication benchmarks, graph community detection and sparse matrix-vector multiplication kernels, and a computational chemistry application. The utility of our proposed PR-based approach is demonstrated by a 2.17x speed-up on 1008 processors over the other MPI-based designs.

Computational modeling↗

GPU-Centric Communication on NVIDIA GPU Clusters with InfiniBand: A Case Study with OpenSHMEM

GPUs have become an essential component for building compute clusters with high compute density and high performance per watt. As such clusters scale to have 1000s of GPUs, efficiently moving data between the GPUs becomes imperative to get maximum performance. NVSHMEM is an implementation of the OpenSHMEM standard for NVIDIA GPU clusters which allows communication to be issued from inside GPU kernels. In earlier work, we have shown how NVSHMEM can be used to achieve better application performance on GPUs connected through PCIe or NVLink. As part of this effort, we implement IB verbs for Mellanox InfiniBand adapters in CUDA. We evaluate different design alternatives, taking into consideration the relaxed memory model, automatic memory access coalescing and thread hierarchy on the GPU. We also consider correctness issues that arise in these designs. We take advantage of these designs transparently or through API extensions in NVSHMEM. With micro-benchmarks, we show that a Nvidia Pascal P100 GPU is able saturate the network bandwidth using only one or two of its 56 available streaming multiprocessors (SM). On a single GPU using a single IB EDR adapter, we achieve a throughput of around 90 million messages per second. In addition, we implement a 2dstencil application kernel using NVSHMEM and compare its performance with a CUDA-aware MPI-based implementation that uses GPUDirect RDMA. Speedups in the range of 23% to 42% are seen for input sizes large enough to fill the occupancy of Nvidia Pascal P100 GPUs on 2 to 4 nodes indicating that there are gains to be had by eliminating the CPU from the communication path when all computation runs on the GPU.

Potluri, Sreeram↗

Gregarious Data Re-structuring in a Many Core Architecture

this paper, we have developed a new methodology that takes in consideration the access patterns from a single parallel actor (e.g. a thread), as well as, the access patterns of “grouped” parallel actors that share a resource (e.g. a distributed Level 3 cache). We start with a hierarchical tile code for our target machine and apply a series of transformations at the tile level to improve data residence in a given memory hierarchy level. The contribution of this paper includes (a) collaborative data restructuring for group reuse and (b) low overhead transformation technique to improve access pattern and bring closely connected data elements together. Preliminary results in a many core architecture, Tilera TileGX, shows promising improvements over optimized OpenMP code (up to 31% increase in GFLOPS) and over our own previous work on fine grained runtimes (up to 16%) for selected kernels

data restructuring↗

High Level Synthesis of RDF Queries for Graph Analytics

In this paper we present a set of techniques that enable the synthesis of efficient custom accelerators for memory intensive, irregular applications. To address irregular applications challenges (large memory footprints, unpredictable fine- grained data accesses, and high synchronization intensity), and exploit their opportunities (thread level parallelism, memory level parallelism), we propose a novel accelerator design which take advantage of an adaptive and Distributed Controller (DC) architecture, and a Memory Interface (MI) that supports parallel memory subsystems. Among the multitude of algorithms that may benefit from our solution, we focus on the acceleration of graph analytics applications, and in particular, on the syn- thesis of SPARQL queries on Resource Description Framework (RDF) databases. We achieve this objective by incorporating the synthesis techniques into Bambu, an Open Source high- level synthesis tools, and interfacing the system with GEMS, the Graph database Engine for Multithreaded Systems. The front- end of GEMS generates optimized C implementations of the input queries, modeled as pattern matching routines, which are then automatically synthesized by Bambu. We validate our approach synthesizing several SPARQL queries from the Lehigh University Benchmark (LUBM).

HLS, FPGA, Convey, RDF, GEMS, Memory-intensive,↗

Performance Issues of SYRK Implementations in Shared Memory Environments for Edge Cases

The symmetric rank-k update (SYRK) is a level-3 BLAS routine commonly used by many Data Mining/Machine Learning(DM/ML) algorithms such as regression, dimensionality reduction algorithms like PCA, matrix factorization and k-mean clustering. This paper presents a comprehensive analysis of the SYRK routine under popular dense linear algebra libraries such as OpenBLAS, Intel MKL, and BLIS particularly focusing on edge cases of dense matrices (thin or fat shapes) that are common in DM/ML applications. Our work identifies some performance issues of the SYRK routine in multi-threaded shared memory environments for edge cases and discuss matrix dependent modifications for performance improvement.

Hossain, Md Mosharaf↗

Parallel k-means Clustering of Geospatial Data Sets Using Manycore CPU Architectures

The increasing availability of high-resolution geospatiotemporal data sets from sources such as observatory networks, remote sensing platforms, and computational Earth system models has opened new possibilities for knowledge discovery and mining of weather, climate, ecological, and other geoscientific data sets fused from disparate sources. Many of the standard tools used on individual workstations are impractical for the analysis and synthesis of data sets of this size; however, new algorithmic approaches that can effectively utilize the complex memory hierarchies and the extremely high levels of parallelism available in state-of-the-art high-performance computing platforms can enable such analysis. Here, we describe pKluster, an open-source tool we have developed for accelerated k-means clustering of geospatial and geospatiotemporal data, and discuss algorithmic modifications and code optimizations we have made to enable it to effectively use parallel machines based on novel CPU architectures—such as the Intel “Knights Landing” Xeon Phi and Skylake Xeon processors—with many cores and hardware threads, and employing significant single instruction, multiple data (SIMD) parallelism. We outline some applications of the code in ecology and climate science contexts and present a detailed discussion of the performance of the code for one such application, LiDAR-derived vertical vegetation structure classification.

Mills, Richard T↗

A Novel Multithreaded Algorithm For Extracting Maximal Chordal Subgraphs

Chordal graphs are triangulated graphs where any cycle larger than three is bisected by a chord. Many combinatorial optimization problems such as computing the minimum fill-in, the size of the maximum clique and the chromatic number are NP-hard on general graphs but have polynomial time solutions on chordal graphs. In this paper, we present a novel multithreaded algorithm to extract a maximal chordal subgraph from a general graph. Our algorithm is based on an iterative approach where each thread can asynchronously update a subset of edges that are dynamically assigned to it. We implement our algorithm on two different multithreaded architectures – Cray XMT, a massively multithreaded platform, and AMD Magny-Cours, a shared memory multicore platform. In addition to the proof of correctness, we present the performance of our algorithm using a testset of carefully generated synthetical graphs with up to half-a-billion edges and real world networks from gene correlation studies. We demonstrate that our algorithm achieves high scalability for all inputs on both types of architectures.

Halappanavar, Mahantesh↗

Argo NodeOS: Toward Unified Resource Management for Exascale

Exascale systems are expected to feature hundreds of thousands of compute nodes with hundreds of hardware threads and complex memory hierarchies with a mix of on-package and persistent memory modules. In this context, the Argo project is developing a new operating system for exascale machines. Targeting production workloads using workflows or coupled codes, we improve the Linux kernel on several fronts. We extend the memory management of Linux to be able to subdivide NUMA memory nodes, allowing better resource partitioning among processes running on the same node. We also add support for memory-mapped access to node- local, PCIe-attached NVRAM devices and introduce a new scheduling class targeted at parallel runtimes supporting user- level load balancing.

Perarnau, Swann↗

Towards Highly Scalable Ab Initio Molecular Dynamics (AIMD) Simulations on the Intel Knights Landing Manycore Processor

The Ab Initio Molecular Dynamics (AIMD) method allows scientists to treat the dynamics of molecular and condensed phase systems while retaining a first-principles-based description of their interactions. This extremely important method has tremendous computational requirements, because the electronic Schr¨odinger equation, approximated using Kohn-Sham Density Functional Theory (DFT), is solved at every time step. With the advent of manycore architectures, application developers have a significant amount of processing power within each compute node that can only be exploited through massive parallelism. A compute intensive application such as AIMD forms a good candidate to leverage this processing power. In this paper, we focus on adding thread level parallelism to the plane wave DFT methodology implemented in NWChem. Through a careful optimization of tall-skinny matrix products, which are at the heart of the Lagrange multiplier and nonlocal pseudopotential kernels, as well as 3D FFTs, our OpenMP implementation delivers excellent strong scaling on the latest Intel Knights Landing (KNL) processor. We assess the efficiency of our Lagrange multiplier kernels by building a Roofline model of the platform, and verify that our implementation is close to the roofline for various problem sizes. Finally, we present strong scaling results on the complete AIMD simulation for a 64 water molecules test case, that scales up to all 68 cores of the Knights Landing processor.

Environmental Molecular Sciences Laboratory↗