Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “workload”

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 649 records · Page 36

SpectralFly: Ramanujan Graphs as Flexible and Efficient Interconnection Networks

In recent years, graph theoretic considerations have become increasingly important in the design of HPC interconnection topologies. One approach is to seek optimal or near-optimal families of graphs with respect to a particular graph theoretic property, such as diameter. For example, the SlimFly topology is based on a construction of McKay, Miller, and \v{S}ir\'{a}\v{n} which produces a diameter two graph on a number of nodes approaching the Moore bound, i.e. the largest possible diameter two graph with a fixed radix. Motivated by recent work of Aksoy, Bruillard, Young, and Raugas, we consider topologies which optimize the spectral gap rather than the diameter. In particular, we introduce a novel HPC topology, SpectralFly, designed around the Ramanujan graph construction of Lubotzky, Phillips, and Sarnak (LPS). In this work, we show that the combinatorial properties, such as diameter, bisection bandwidth, average path length, and resilience to link failure, of SpectralFly topologies are better than, or comparable to, similarly constrained DragonFly, SlimFly, and BundleFly topologies. Additionally, we simulate the performance of SpectralFly topologies on a representative sample of physics-inspired HPC workloads using the Structure Simulation Toolkit Macroscale Element Library simulator and demonstrate considerable benefit to using LPS construction as the basis of the SpectralFly topology.

graphs and networks, network topology, interconnec↗

Graph Analytics on Jellyfish topology

Because large unstructured datasets is important for many science domains, distributed graph analytics is critical to many scientists. Unfortunately, obtaining scaling and performance for irregular communication is challenging because contemporary network interconnects are primarily designed to maximize bandwidths of fixed-neighborhoods large-message exchanges (e.g., stencils). Although there is no consensus on the “best” network topologies for irregular communication, unstructured graph-based interconnects can be more suitable. We analyze three popular graph workloads – clustering, pattern enumeration, and traversal — on comparable networks (in terms of resources and costs) constructed from Jellyfish Random Regular, Dragonfly and Fat tree topologies, varying the routing algorithms. Using packet-level simulations, we demonstrate up to 60% improvement in communication time with Jellyfish due to diversity of the short paths between arbitrary endpoints, which can reduce overall network stalls and congestion.

Graph Analytics, network topology, interconnect, H↗

LibraryX: A Framework for Cross-Library-Call Optimization

Scientific applications utilize performance libraries as a software engineering concept: these libraries encapsulate important and well-understood (mathematical) operations, allow for reuse, and are implemented and tuned by experts. Domain scientists then implement complex algorithms based on these domainspecific libraries. While individual library calls are optimized, larger performance gains across sequences of calls—sometimes spanning multiple libraries—are often unrealized, forcing a trade-off between performance and implementation complexity.To overcome this issue, we propose LibraryX, an approach and a system that allows for cross-library-call optimization even when library calls stem from multiple performance libraries. LibraryX annotates library calls with semantic information and optimizes entire directed acyclic graphs (DAGs) of calls dynamically using the SPIRAL code generation system. We demonstrate its effectiveness across a range of memory bound workloads, achieving significant speedups on Nvidia, AMD, and Intel accelerators compared to code using native libraries without cross-call optimization.

Rao, Sanil [Carnegie Mellon University,Department ↗

Modeling and Predicting Performance of High Performance Computing Applications on Hardware Accelerators

Computers with hardware accelerators, also referred to as hybrid-core systems, speedup applications by offloading certain compute operations that can run faster on accelerators. Thus, it is not surprising that many of top500 supercomputers use accelerators. However, in addition to procurement cost, significant programming and porting effort is required to realize the potential benefit of such accelerators. Hence, before building such a system it is prudent to answer the question 'what is the projected performance benefit from accelerators for the workloads of interest?'. We address this question by way of a performance-modeling framework that predicts realizable application performance on accelerators rapidly and accurately without going to the considerable effort of porting and tuning. The modeling framework first automatically identifies commonly found compute patterns in scientific applications which we term idioms, which may benefit by accelerator technology. Next the framework models the predicted speedup of those idioms if they were to be ported to and run on hardware accelerators. As a proof of concept we characterize two kinds of accelerators 1) the FPGA accelerators on a Convey HC-1 system and 2) an NVIDIA FERMI GPU accelerator. We model performance of the idioms gather/scatter and stream and our predictions show that where these occur in two full-scale HPC applications, Milc and HYCOM, gather/scatter speeds up by as much as 15X, and stream by as much as 14X, whereas the overall compute time of Milc improves by 3.4% and HYCOM by 20%.

Computer Science↗

Improving High-Performance Sparse Libraries Using Compiler-Assisted Specialization: A PETSc Case Study

Computers with hardware accelerators, also referred to as hybrid-core systems, speedup applications by offloading certain compute operations that can run faster on accelerators. Thus, it is not surprising that many of top500 supercomputers use accelerators. However, in addition to procurement cost, significant programming and porting effort is required to realize the potential benefit of such accelerators. Hence, before building such a system it is prudent to answer the question 'what is the projected performance benefit from accelerators for the workloads of interest?'. We address this question by way of a performance-modeling framework that predicts realizable application performance on accelerators rapidly and accurately without going to the considerable effort of porting and tuning. The modeling framework first automatically identifies commonly found compute patterns in scientific applications which we term idioms, which may benefit by accelerator technology. Next the framework models the predicted speedup of those idioms if they were to be ported to and run on hardware accelerators. As a proof of concept we characterize two kinds of accelerators 1) the FPGA accelerators on a Convey HC-1 system and 2) an NVIDIA FERMI GPU accelerator. We model performance of the idioms gather/scatter and stream and our predictions show that where these occur in two full-scale HPC applications, Milc and HYCOM, gather/scatter speeds up by as much as 15X, and stream by as much as 14X, whereas the overall compute time of Milc improves by 3.4% and HYCOM by 20%.

Computer Science↗

A multi-platform evaluation of the randomized CX low-rank matrix factorization in Spark

We investigate the performance and scalability of the randomized CX low-rank matrix factorization and demonstrate its applicability through the analysis of a 1TB mass spectrometry imaging (MSI) dataset, using Apache Spark on an Amazon EC2 cluster, a Cray XC40 system, and an experimental Cray cluster. We implemented this factorization both as a parallelized C implementation with hand-tuned optimizations and in Scala using the Apache Spark high-level cluster computing framework. We obtained consistent performance across the three platforms: using Spark we were able to process the 1TB size dataset in under 30 minutes with 960 cores on all systems, with the fastest times obtained on the experimental Cray cluster. In comparison, the C implementation was 21X faster on the Amazon EC2 system, due to careful cache optimizations, bandwidth-friendly access of matrices and vector computation using SIMD units. We report these results and their implications on the hardware and software issues arising in supporting data-centric workloads in parallel and distributed environments.

Gittens, Alex↗

A Locality-Based Threading Algorithm for the Configuration-Interaction Method

The Configuration Interaction (CI) method has been widely used to solve the non-relativistic many-body Schrodinger equation. One great challenge to implementing it efficiently on manycore architectures is its immense memory and data movement requirements. To address this issue, within each node, we exploit a hybrid MPI+OpenMP programming model in lieu of the traditional flat MPI programming model. Here in this paper, we develop optimizations that partition the workloads among OpenMP threads based on data locality,-which is essential in ensuring applications with complex data access patterns scale well on manycore architectures. The new algorithm scales to 256 threadson the 64-core Intel Knights Landing (KNL) manycore processor and 24 threads on dual-socket Ivy Bridge (Xeon) nodes. Compared with the original implementation, the performance has been improved by up to 7× on theKnights Landing processor and 3× on the dual-socket Ivy Bridge node.

97 MATHEMATICS AND COMPUTING↗

Population Count on Intel® CPU, GPU, and FPGA

Population count is a primitive used in many applications. Commodity processors have dedicated instructions for achieving high-performance population count. Motivated by the productivity of high-level synthesis and the importance of population count, in this paper we investigated the OpenCL implementations of population count algorithms, and evaluated their performance and resource utilizations on an FPGA. Based on the results, we select the most efficient implementation. Then we derived a reduction pattern from a representative application of population count. We parallelized the reduction with atomic functions, and optimized it with vectorized memory accesses, tree reduction, and compute-unit duplication. We evaluated the performance of the reduction kernel on an Intel (R) Xeon (R) CPU and an Intel (R) IrisT Pro integrated GPU, and an FPGA card that features an Intel (R) Arria (R) 10 FPGA. When DRAM memory bandwidth is comparable on the three computing platforms, the FPGA can achieve the highest kernel performance for large workload. On the other hand, we described performance bottlenecks on the FPGA. To make FPGAs more competitive in raw performance compared to high-performant CPU and GPU platforms, it is important to increase external memory bandwidth, minimize data movement between a host and a device, and reduce OpenCL runtime overhead on an FPGA.

heterogeneous computing↗

Evaluating the Performance of Integer Sum Reduction on an Intel GPU

Sum reduction is a primitive operation in parallel computing while SYCL is a promising heterogeneous programming language. In this paper, we describe the SYCL implementations of integer sum reduction using atomic functions, shared local memory, vectorized memory accesses, and parameterized workload sizes. Evaluating the reduction kernels shows that we can achieve 1.4X speedup over the open-source implementations of sum reduction for a sufficiently large number of integers on an Intel integrated GPU.

Jin, Zheming↗

Learning to Scale the Summit: AI for Science on a Leadership Supercomputer

The Summit system at Oak Ridge National Lab-oratory (ORNL) has been the world's top AI for science su-percomputer for several years, ranked world's fastest computer at its 2018 launch and currently top system in the US and #2 on the TOP5OO list. Summit's purposeful design to handle both conventional modeling and simulation science and emerging AI workloads has made it a leading destination for AI-powered computational science. We report here on AI for science usage on Summit near the midpoint of its lifespan. We review AI usage across the many science projects that have used Summit. We then examine in detail a set of applications scaling AI to full system as well as projects implementing AI-coordinated science discovery workflows on Summit. Finally, we offer some observations regarding the future of advancing scientific knowledge and understanding via AI, especially in the context of leadership-class scientific computing.

Joubert, Wayne↗

Strategies for Integrating Deep Learning Surrogate Models with HPC Simulation Applications

The emerging trend of the convergence of high performance computing (HPC), machine learning/deep learning (ML/DL), and big data analytics presents a host of challenges for large-scale computing campaigns that seek best practices to interleave traditional scientific simulation-based workloads with ML/DL models. A portfolio of systematic approaches to incorporate deep learning into modeling and simulation serves a vital need when we support AI for science at a computing facility. In this paper, we evaluate several strategies for deploying deep learning surrogate models in a representative physics application on supercomputers at the Oak Ridge Leadership Computing Facility (OLCF). We discuss a set of recommended deployment architectures and implementation approaches. We analyze and evaluate these alternatives and show their performance and scalability up to 1000 GPUs on two mainstream platforms equipped with different deep learning hardware and software stacks.

Yin, Junqi↗

Pretraining Billion-Scale Geospatial Foundational Models on Frontier

As AI workloads increase in scope, generalization capability becomes challenging for small task-specific models and their demand for large amounts of labeled training samples increases. On the contrary, Foundation Models (FMs) are trained with internet-scale unlabeled data via self-supervised learning and have been shown to adapt to various tasks with minimal fine-tuning. Although large FMs have demonstrated significant impact in natural language processing and computer vision, efforts toward FMs for geospatial applications have been restricted to smaller size models, as pretraining larger models requires very large computing resources equipped with state-of-the-art hardware accelerators. Current satellite constellations collect 100+TBs of data a day, resulting in images that are billions of pixels and multimodal in nature. Such geospatial data poses unique challenges opening up new opportunities to develop FMs. We investigate billion scale FMs and HPC training profiles for geospatial applications by pretraining on publicly available data. We studied from end-to-end the performance and impact in the solution by scaling the model size. Our larger 3B parameter size model achieves up to 30% improvement in top1 scene classification accuracy when comparing a 100M parameter model. Moreover, we detail performance experiments on the Frontier supercomputer, America's first exascale system, where we study different model and data parallel approaches using PyTorch's Fully Sharded Data Parallel library. Specifically, we study variants of the Vision Transformer architecture (ViT), conducting performance analysis for ViT models with size up to 15B parameters. By discussing throughput and performance bottlenecks under different parallelism configurations, we offer insights on how to leverage such leadership-class HPC resources when developing large models for geospatial imagery applications.

Tsaris, Aristeidis (aris)↗

SQUARE: Strategic Quantum Ancilla Reuse for Modular Quantum Programs via Cost-Effective Uncomputation

Compiling high-level quantum programs to machines that are size constrained (i.e. limited number of quantum bits) and time constrained (i.e. limited number of quantum operations) is challenging. In this paper, we present SQUARE (Strategic QUantum Ancilla REuse), a compilation infrastructure that tackles allocation and reclamation of scratch qubits (called ancilla) in modular quantum programs. At its core, SQUARE strategically performs uncomputation to create opportunities for qubit reuse. Current Noisy Intermediate-Scale Quantum (NISQ) computers and forward-looking Fault-Tolerant (FT) quantum computers have fundamentally different constraints such as data locality, instruction parallelism, and communication overhead. Our heuristic-based ancilla-reuse algorithm balances these considerations and fits computations into resource-constrained NISQ or FT quantum machines, throttling parallelism when necessary. To precisely capture the workload of a program, we propose an improved metric, the "active quantum volume," and use this metric to evaluate the effectiveness of our algorithm. Furthermore, our results show that SQUARE improves the average success rate of NISQ applications by 1.47X. Surprisingly, the additional gates for uncomputation create ancilla with better locality, and result in substantially fewer swap gates and less gate noise overall. SQUARE also achieves an average reduction of 1.5X (and up to 9.6X) in active quantum volume for FT machines.

compiler optimization↗

High Performance Molecular Dynamic Simulation on Single and Multi-GPU Systems

The programming techniques supported and employed on these GPUs and Multi-GPUs systems are not sufficient to address problems exhibiting irregular, and unbalanced workload such as Molecular Dynamic (MD) simulations of systems with non-uniform densities. In this paper, we propose a task-based dynamic load-balancing solution to employ on MD simulations for single- and multi-GPU systems. The solution allows load balancing at a finer granularity than what is supported in existing APIs such as NVIDIA’s CUDA. Experimental results with a single-GPU configuration show that our fine-grained task solution can utilize the hardware more efficiently than the CUDA scheduler. On multi-GPU systems, our solution achieves near-linear speedup, load balance, and significant performance improvement over techniques based on standard CUDA APIs.

97 MATHEMATICS AND COMPUTING↗

Performance Analysis of Data Processing in Distributed File Systems with Near Data Processing

In the era of big data, the escalating volume and velocity of data generation pose significant challenges in data processing. Traditional systems like Spark and Hadoop manage the increasing amount and velocity of data by improving data placement and processing speeds. However, they face inherent limitations due to the essential data movement required for processing. In this paper, we explore the Skyhook framework, a novel extension of the Ceph distributed system, which significantly reduces the need for data movement. We present an extensive case study using the Skyhook framework, applying it with the TPC-H and K-means clustering algorithms. More specifically, we leverage the TPC-H benchmark to distinguish between CPU-intensive and I/O-intensive tasks. We explore the integration of K-means clustering into SQL, coupled with a near-data processing system to offload the computational burden of the K-means clustering algorithm to storage nodes. We conduct a comprehensive performance evaluation of distributed data processing applications across three processing approaches: traditional layout (baseline), optimized layout, and near-data processing. Additionally, we introduce the use of the FIO tool to simulate real-world system workloads, enabling the measurement of performance metrics such as average latency and CPU utilization. Our research is a significant advance in understanding how to optimize data processing systems to meet the demands of the modern data landscape.

Hou, Shiyue↗

Situational Awareness as a Measure of Performance in Cyber Security Collaborative Work

Cyber defense competitions arising from U.S. service academy exercises, offer a platform for collecting data that can inform research that ranges from characterizing the ideal cyber warrior to describing behaviors during certain challenging cyber defense situations. This knowledge in turn could lead to better preparation of cyber defenders in both military and civilian settings. We conducted proof of concept experimentation to collect data during the Pacific-rim Regional Collegiate Cyber Defense Competition (PRCCDC) and analyzed it to study the behavior of cyber defenders. We propose that situational awareness predicts performance of cyber security professionals, and in this paper we focus on our collection and analysis of competition data to determine whether it supports our hypothesis. In addition to normal cyber data, we collected situational awareness and workload data and compared it against the performance of cyber defenders as indicated by their competition score. We conclude that there is a weak correlation between our measure of situational awareness and performance that we hope to exploit in further studies.

99 GENERAL AND MISCELLANEOUS↗

Bristol Ridge: A 28-nm $\times$ 86 Performance-Enhanced Microprocessor Through System Power Management

Power management techniques can be effective at extracting more performance and energy efficiency out of mature systems on chip (SoCs). For instance, the peak performance of microprocessors is often limited by worst case technology (Vmax), infrastructure (thermal/electrical), and microprocessor usage assumptions. Performance/watt of microprocessors also typically suffers from guard bands associated with the test and binning processes as well as worst case aging/lifetime degradation. Similarly, on multicore processors, shared voltage rails tend to limit the peak performance achievable in low thread count workloads. In this paper, we describe five power management techniques that maximize the per-part performance under the before-mentioned constraints. Using these techniques, we demonstrate a net performance increase of up to 15% depending on the application and TDP of the SoC, implemented on 'Bristol Ridge,' a 28-nm CMOS, dual-core x 86 accelerated processing unit.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Synchronous I/O Scheduling of Independent Write Caches for an Array of SSDs

Solid-state drives (SSD) offer a significant performance improvement over the hard disk drives (HDD), however, it can exhibit a significant variance in latency and throughput due to internal garbage collection (GC) process on the SSD. When the SSDs are configured in a RAID, the performance variance of individual SSDs could significantly degrade the overall performance of the RAID of SSDs. The internal cache on the RAID controller can help mitigate the performance variability issues of SSDs in the array; however, the state-of-the-art cache algorithm of the RAID controller does not consider the characteristics of SSDs. In this paper, we examine the most recent write cache algorithm for the array of disks, and propose a synchronous independent write cache (SIW) algorithm. We also present a pre-parity-computation technique for the RAID of SSDs with parity computations, which calculates parities of blocks in advance before they are stored in the write cache. With this new technique, we propose a complete paradigm shift in the design of write cache. In our evaluation study, large write requests dominant workloads show up to about 50 and 20 percent improvements in average response times on RAID-0 and RAID-5 respectively as compared to the state-of-the-art write cache algorithm.

97 MATHEMATICS AND COMPUTING↗