SEARCH · Engineering Papers
Results for “INFINIBAND”
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.
Measuring Minimum Switch Port Metric Retrieval Time and Impact for Multi-Layer Infiniband Fabrics.
Abstract not provided.
Comprehensive Synchronous High Frequency Measurement of InfiniBand Networks in Production HPC Systems.
Abstract not provided.
A Dynamic Network-Native MPI Partitioned Aggregation Over InfiniBand Verbs
Explore the source record for details and available documents.
Energy–Performance Trade-offs in Privacy-Preserving Federated Learning on SmartNIC-Enabled HPC Systems
Federated learning (FL) is increasingly deployed on accelerator-rich high-performance computing (HPC) systems, yet the system-level energy cost of privacy-aware FL remains poorly understood, particularly across heterogeneous networking and server-placement options. We present a measurement-driven study of energy–performance trade-offs for FL on GH200-class nodes across three deployment configurations: CPU-Ethernet, CPU-InfiniBand (RDMA-capable), and a DPU-hosted FL server over InfiniBand using a BlueField-3 SmartNIC/DPU. Using NVIDIA FLARE (NVFLARE), we align node-level power telemetry with per-round timing extracted from NVFLARE logs to quantify time-to-solution (TTS), energy-to-solution (ETS), energy-delay product (EDP), and synchronization behavior for three transformer models (ALBERT, DistilBERT, BERT), trained with and without differential privacy (DP). We find that interconnect choice is the dominant driver of runtime and energy: host-managed InfiniBand consistently reduces communication overhead versus Ethernet, yielding lower TTS/ETS/EDP. In contrast, in our NVFLARE deployment, placing the FL server on the DPU does not consistently match CPU-InfiniBand performance and can be slower—especially for larger models—highlighting that server placement alone is not sufficient to guarantee end-to-end gains. Finally, under our fixed-round protocol, DP increases per-round cost and runtime variance; ETS increases largely in proportion to TTS because average node power remains relatively stable across configurations.
Final Report for Project DE-FC02-06ER25755 [Pmodels2]
In this report, we describe the research accomplished by the OSU team under the Pmodels2 project. The team has worked on various angles: designing high performance MPI implementations on modern networking technologies (Mellanox InfiniBand (including the new ConnectX2 architecture and Quad Data Rate), QLogic InfiniPath, the emerging 10GigE/iWARP and RDMA over Converged Enhanced Ethernet (RoCE) and Obsidian IB-WAN), studying MPI scalability issues for multi-thousand node clusters using XRC transport, scalable job start-up, dynamic process management support, efficient one-sided communication, protocol offloading and designing scalable collective communication libraries for emerging multi-core architectures. New designs conforming to the Argonne’s Nemesis interface have also been carried out. All of these above solutions have been integrated into the open-source MVAPICH/MVAPICH2 software. This software is currently being used by more than 2,100 organizations worldwide (in 71 countries). As of January ’14, more than 200,000 downloads have taken place from the OSU Web site. In addition, many InfiniBand vendors, server vendors, system integrators and Linux distributors have been incorporating MVAPICH/MVAPICH2 into their software stacks and distributing it. Several InfiniBand systems using MVAPICH/MVAPICH2 have obtained positions in the TOP500 ranking of supercomputers in the world. The latest November ’13 ranking include the following systems: 7th ranked Stampede system at TACC with 462,462 cores; 11th ranked Tsubame 2.5 system at Tokyo Institute of Technology with 74,358 cores; 16th ranked Pleiades system at NASA with 81,920 cores; Work on PGAS models has proceeded on multiple directions. The Scioto framework, which supports task-parallelism in one-sided and global-view parallel programming, has been extended to allow multi-processor tasks that are executed by processor groups. A quantum Monte Carlo application is being ported onto the extended Scioto framework. A public release of Global Trees (GT) has been made, along with the Global Chunks (GC) framework on which GT is built. The Global Chunks (GC) layer is also being used as the basis for the development of a higher level Global Graphs (GG) layer. The Global Graphs (GG) system will provide a global address space view of distributed graph data structures on distributed memory systems.
Expanding a Supercomputer Facility Using Modular Data Center Technology
With the expansion of high-end computing resources needed to support NASA's increasing demands for physics-based simulations, the facility housing Pleiades-the agency's largest supercomputer-recently reached its power and cooling capacity. In response, the NASA Advanced Supercomputing Division at Ames Research Center undertook a prototype project that resulted in a new facility based on modular data center technology. The facility, a ~1000 square-foot module on a concrete pad with room for 16-18 compute racks, was completed in fall 2016 and an SGI computer system, named Electra, was deployed there in early 2017. Cooling is performed via an evaporative system built into the module, and preliminary experience shows a Power Usage Effectiveness (PUE) of ~1.03. Electra achieved over a petaflop on the LINPACK benchmark, sufficient to rank number 96 on the November 2016 TOP500 list. The system consists of 1,152 InfiniBand-connected Intel Xeon Broadwell-based nodes. Its users access their files on a facility wide file system shared by all compute assets via Mellanox MetroX InfiniBand extenders, which connect the Electra fabric to Lustre routers InfiniBand fabric over fiber-optic links about 300 meters long. The prototype has exceeded expectations and is serving as a blueprint for future expansions.*†
Scripts for Scalable Monitoring of Parallel Filesystem Infrastructure
Scripts for scalable monitoring of parallel filesystem infrastructure provide frameworks for monitoring the health of block storage arrays and large InfiniBand fabrics. The block storage framework uses Python multiprocessing to within scale the number monitored arrays to scale with the number of processors in the system. This enables live monitoring of HPC-scale filesystem with 10-50 storage arrays. For InfiniBand monitoring, there are scripts included that monitor InfiniBand health of each host along with visualization tools for mapping the topology of complex fabric topologies.
Accelerating k-NN Algorithm with Hybrid MPI and OpenSHMEM
Machine Learning algorithms are benefiting from the continuous improvement of programming models, including MPI, MapReduce and PGAS. k-Nearest Neighbors (k-NN) algorithm is a widely used machine learning algorithm, applied to supervised learning tasks such as classification. Several parallel implementations of k-NN have been proposed in the literature and practice. However, on high-performance computing systems with high-speed interconnects, it is important to further accelerate existing designs of the k-NN algorithm through taking advantage of scalable programming models. To improve the performance of k-NN on large-scale environment with InfiniBand network, this paper proposes several alternative hybrid MPI+OpenSHMEM designs and performs a systemic evaluation and analysis on typical workloads. The hybrid designs leverage the one-sided memory access to better overlap communication with computation than the existing pure MPI design, and propose better schemes for efficient buffer management. The implementation based on k-NN program from MaTEx with MVAPICH2-X (Unified MPI+PGAS Communication Runtime over InfiniBand) shows up to 9.0% time reduction for training KDD Cup 2010 workload over 512 cores, and 27.6% time reduction for small workload with balanced communication and computation. Experiments of running with varied number of cores show that our design can maintain good scalability.
Exploring the All-to-All Collective Optimization Space with ConnectX CORE-Direct
The all-to-all collective communication operation is used by many scientific applications, and is one of the most time consuming and challenging collective operation to optimize. The algorithms for all-to-all operations typically fall into two classes, logarithmic and linear scaling algorithms, with Bruck's algorithm, a logarithmic scaling algorithm, used in many small-data all-to-all implementations. The recent addition of InfiniBand CORE-Direct support for network management of collective communications offers new opportunities for optimizing all-to-all operation as well as supporting truly asynchronous implementations of these operations. This paper presents several new enhancements to the Bruck small-data algorithm that leverage CORE-Direct and other InfiniBand network capabilities to produce efficient implementations of this collective operation. These include RDMA, SR-RNR, and SR-RTR algorithms. In addition, nonblocking implementations of these collective operations are also presented. Benchmark results show that the RDMA algorithm, which uses CORE-Direct capabilities to offload collective communication management to the Host Channel Adapter (HCA), hardware gather support for sending non-continuous data, and low-latency RDMA semantics, performs the best. For a 64 processes and 128 byte-per-process all-to-all, the RDMA algorithm performs 27% better than Bruck's algorithm implementation in Open MPI and 136% better than the SR-RTR algorithm. In addition, the nonblocking versions of these algorithms have the same performance characteristics as the blocking algorithms. Finally, measurements of computation/communication overlap capacity show that all offloaded algorithms achieve about 98% overlap for large data all-to-all, whereas implementations using host-based progress achieve only about 9.5% overlap.
Aho-Corasick String Matching on Shared and Distributed Memory Parallel Architectures
String matching is at the core of many critical applications, including network intrusion detection systems, search engines, virus scanners, spam filters, DNA and protein sequencing, and data mining. For all of these applications string matching requires a combination of (sometimes all) the following characteristics: high and/or predictable performance, support for large data sets and flexibility of integration and customization. Many software based implementations targeting conventional cache-based microprocessors fail to achieve high and predictable performance requirements, while Field-Programmable Gate Array (FPGA) implementations and dedicated hardware solutions fail to support large data sets (dictionary sizes) and are difficult to integrate and customize. The advent of multicore, multithreaded, and GPU-based systems is opening the possibility for software based solutions to reach very high performance at a sustained rate. This paper compares several software-based implementations of the Aho-Corasick string searching algorithm for high performance systems. We discuss the implementation of the algorithm on several types of shared-memory high-performance architectures (Niagara 2, large x86 SMPs and Cray XMT), distributed memory with homogeneous processing elements (InfiniBand cluster of x86 multicores) and heterogeneous processing elements (InfiniBand cluster of x86 multicores with NVIDIA Tesla C10 GPUs). We describe in detail how each solution achieves the objectives of supporting large dictionaries, sustaining high performance, and enabling customization and flexibility using various data sets.
Reaching bandwidth saturation using transparent injection parallelization
Although logically available, applications may not exploit enough instantaneous communication concurrency to maximize network utilization on HPC systems. This is exacerbated in hybrid programming models that combine single program multiple data with OpenMP or CUDA. We present the design of a “multi-threaded” runtime able to transparently increase the instantaneous network concurrency and to provide near saturation bandwidth, independent of the application configuration and dynamic behavior. The runtime offloads communication requests from application level tasks to multiple communication servers. The servers use system specific performance models to attain network saturation. Our techniques alleviate the need for spatial and temporal application level message concurrency optimizations. Experimental results show improved message throughput and bandwidth by as much as 150% for 4 KB messages on InfiniBand and by as much as 120% for 4 KB messages on Cray Aries. For more complex operations such as all-to-all collectives, we observe as much as 30% speedup. This translates into 23% speedup on 12,288 cores for a NAS FT implemented using FFTW. We observe as much as 76% speedup on 1500 cores for an already optimized UPC+OpenMP geometric multigrid application using hybrid parallelism. For the geometric multigrid GPU implementation, we observe as much as 44% speedup on 512 GPUs.
Software Defined Networking for HPC Interconnects and its Extension across Domains (Final Technical Report for DE-SC0016039)
This project seeks to incorporate OpenFlow-style Software Defined Networking capability into existing High Performance Computing (HPC) interconnect technology, InfiniBand, and to extend such capability beyond one domain. We develop SDN-enhanced InfiniBand that supports OpenFlow functionality for HPC interconnects, investigate the required techniques and the potential benefits for applying SDN on different types of HPC interconnects, and develop software to control the network and expose SDN capability to external networks through the OpenFlow interface. We have also developed techniques to evaluate communication characteristics of parallel applications, which determines the workload on interconnects, investigated newly proposed Interconnection network technologies including new network topologies and routing schemes, and designed novel interconnect routing and modeling techniques. Major activities and findings are summarized as follows.
An Application-Based Performance Characterization of the Columbia Supercluster
Columbia is a 10,240-processor supercluster consisting of 20 Altix nodes with 512 processors each, and currently ranked as the second-fastest computer in the world. In this paper, we present the performance characteristics of Columbia obtained on up to four computing nodes interconnected via the InfiniBand and/or NUMAlink4 communication fabrics. We evaluate floating-point performance, memory bandwidth, message passing communication speeds, and compilers using a subset of the HPC Challenge benchmarks, and some of the NAS Parallel Benchmarks including the multi-zone versions. We present detailed performance results for three scientific applications of interest to NASA, one from molecular dynamics, and two from computational fluid dynamics. Our results show that both the NUMAlink4 and the InfiniBand hold promise for application scaling to a large number of processors.