Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Bandwidth”

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 847 records · Page 47

SU-C-17A-02: Sirius MRI Markers for Prostate Post-Implant Assessment: MR Protocol Development

Purpose: Currently, CT is used to visualize prostate brachytherapy sources, at the expense of accurate structure contouring. MRI is superior to CT for anatomical delineation, but the sources appear as voids on MRI images. Previously we have developed Sirius MRI markers (C4 Imaging) to replace spacers to assist source localization on MRI images. Here we develop an MRI pulse sequence protocol that enhances the signal of these markers to enable MRI-only post-implant prostate dosimetric analysis. Methods: To simulate a clinical scenario, a CIRS multi-modality prostate phantom was implanted with 66 markers and 86 sources. The implanted phantom was imaged on both 1.5T and 3.0T GE scanners under various conditions, different pulse sequences (2D fast spin echo [FSE], 3D balanced steadystate free precession [bSSFP] and 3D fast spoiled gradient echo [FSPGR]), as well as varying amount of padding to simulate various patient sizes and associated signal fall-off from the surface coil elements. Standard FSE sequences from the current clinical protocols were also evaluated. Marker visibility, marker size, intra-marker distance, total scan time and artifacts were evaluated for various combinations of echo time, repetition time, flip angle, number of excitations, bandwidth, slice thickness and spacing, fieldof- view, frequency/phase encoding steps and frequency direction. Results: We have developed a 3D FSPGR pulse sequence that enhances marker signal and ensures the integrity of the marker shape while maintaining reasonable scan time. For patients contraindicated for 3.0T, we have also developed a similar sequence for 1.5T scanners. Signal fall-off with distance from prostate to coil can be compensated mainly by decreasing bandwidth. The markers are not visible using standard FSE sequences. FSPGR sequences are more robust for consistent marker visualization as compared to bSSFP sequences. Conclusion: The developed MRI pulse sequence protocol for Sirius MRI markers assists source localization to enable MRIonly post-implant prostate dosimetric analysis. S.J. Frank is a co-founder of C4 Imaging (manufactures the MRI markers)

60 APPLIED LIFE SCIENCES↗

SU-F-J-28: Development of a New Imaging Filter to Remove the Shadows From the Carbon Fiber Grid Table Top

Purpose: For the image guided radiation therapy (IGRT), the shadows caused by the construction of the treatment couch top adversely affect the visual evaluation. Therefore, we developed the new imaging filter in order to remove the shadows. The performance of the new filter was evaluated using the clinical images. Methods: The new filter was composed of the band-pass filter (BPF) weighted by the k factor and the low-pass filter (LPF). In the frequency region, the stop bandwidth were 8.3×10{sup 3} mm{sup −1} on u direction and 11.1×10{sup 3} mm{sup −1} on v direction for the BPF, and the pass bandwidth were 8.3×10{sup 3} mm{sup −1} on u direction and 11.1×10{sup 3} mm{sup −1} on v direction for the LPF. After adding the filter, the shadows from the carbon fiber grid table top (CFGTT, Varian) on the kV-image was removed. To check the filter effect, we compared the clinical images, which are thorax and thoracoabdominal region, with to without the filter. The subjective evaluation tests was performed by adapting a three-point scale (agree, neither agree nor disagree, disagree) about the 15 persons in the department of radiation oncology. Results: We succeeded in removing all shadows of CFGTT using the new filter. This filter is very useful shown by the results of the subjective evaluation having the 23/30 persons agreed to the filtered clinical images. Conclusion: We concluded that the proposed method was useful tool for the IGRT and the new filter leads to improvement of the accuracy of radiation therapy.

60 APPLIED LIFE SCIENCES↗

Slow light engineering in a photonic crystal slab waveguide through optofluidic infiltration and geometric modulation

In this paper, a new type of flat-band slow light structure with high group index (n{sub g}) and large normalized delay-bandwidth product (NDBP) in a silicon on insulator (SOI) based photonic crystal (PC) slab waveguide with a triangular lattice of circular holes is demonstrated. The dispersion engineering is performed by infiltrating optical fluids with different refractive indices n{sub f} in the first row and shifting the second row of air holes adjacent to the PC waveguide (PCW) in the longitudinal direction. In the optimized case, a high NDBP of 0.32 with a group index of 54.55 and a bandwidth of 9.13 nm could be obtained. Furthermore, an ultra-low group velocity dispersion (GVD) in the range of 10{sup –20} s{sup 2}/m is achieved in all of the structures. These results are obtained by numerical simulations based on three-dimensional (3D) plane wave expansion (PWE) method.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Influence of Output Optical Losses on the Dynamic Characteristics of 1.55-μm Wafer-Fused Vertical-Cavity Surface-Emitting Lasers

The results of studying the dynamic characteristics of 1.55-μm single-mode vertical-cavity surface-emitting lasers (VCSELs) formed by the fusion of wafers of high-quality Bragg reflectors and an active region based on thin highly strained InGaAs/InAlGaAs quantum wells are presented. It is found that the proposed design of the active region and optical microcavity of the laser make it possible in principle to attain a high level of differential laser gain in the temperature range of 20°C–85°C, but weak electron localization leads to an increase in gain compression at elevated temperatures. Due to this fact, the VCSEL modulation bandwidth at 20°C can be increased from 9.2 to 11.5 GHz due to an increase in output optical losses, while the modulation bandwidth at 85°C does not exceed 8.5 GHz, depends weakly on the output optical losses, and is mainly limited by the optical-gain saturation.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Stability Analysis of Inline ZFP Compression for Floating-Point Data in Iterative Methods

Currently, the dominating constraint in many high performance computing applications is data capacity and bandwidth, in both internode communications and even moreso in intranode data motion. A new approach to address this limitation is to make use of data compression in the form of a compressed data array. Storing data in a compressed data array and converting to standard IEEE-754 types as needed during a computation can reduce the pressure on bandwidth and storage. However, repeated conversions (lossy compression and decompression) introduce additional approximation errors, which need to be shown to not significantly affect the simulation results. Here, we extend recent work that analyzed the error of a single use of compression and decompression of the ZFP compressed data array representation to the case of time-stepping and iterative schemes, where an advancement operator is repeatedly applied in addition to the conversions. We show that the accumulated error for iterative methods involving fixed-point and time evolving iterations is bounded under standard constraints. An upper bound is established on the number of additional iterations required for the convergence of stationary fixed-point iterations. An additional analysis of traditional forward and backward error of stationary iterative methods using ZFP compressed arrays is also presented. The results of several 1D, 2D, and 3D test problems are provided to demonstrate the correctness of the theoretical bounds.

97 MATHEMATICS AND COMPUTING↗

Exploiting communication concurrency on high performance computing systems

Although logically available, applications may not exploit enough instantaneous communication concurrency to maximize hardware utilization on HPC systems. This is exacerbated in hybrid programming models such as SPMD+OpenMP. 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 forwards communication requests from application level tasks to multiple communication servers. 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 4KB bytes messages on InfiniBand and by as much as 120% for 4KB byte 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 also observe as much as 76% speedup on 1,500 cores for an already optimized UPC+OpenMP geometric multigrid application using hybrid parallelism.

97 MATHEMATICS AND COMPUTING↗

An Elegant Sufficiency: Load-Aware Differentiated Scheduling of Data Transfers

We investigate the file transfer scheduling problem, where transfers among different endpoints must be scheduled to maximize pertinent metrics. We propose two new algorithms that exploit the fact that the aggregate bandwidth obtained over a network or at a storage system tends to increase with the number of concurrent transfers—but only up to a certain limit. The first algorithm, SEAL, uses runtime information and data-driven models to approximate system load and adapt transfer schedules and concurrency so as to maximize performance while avoiding saturation. We implement this algorithm using GridFTP as the transfer protocol and evaluate it using real transfer logs in a production WAN environment. Results show that SEAL can improve average slowdowns and turnaround times by up to 25% and worst-case slowdown and turnaround times by up to 50%, compared with the best-performing baseline scheme. Our second algorithm, STEAL, further leverages user-supplied categorization of transfers as either “interactive” (requiring immediate processing) or “batch” (less time-critical). Results show that STEAL reduces the average slowdown of interactive transfers by 63% compared to the best-performing baseline and by 21% compared to SEAL. For batch transfers, compared to the best-performing baseline, STEAL improves by 18% the utilization of the bandwidth unused by interactive transfers. By elegantly ensuring a sufficient, but not excessive, allocation of concurrency to the right transfers, we significantly improve overall performance despite constraints.

Kettimuthu, Rajkumar↗

Comparative I/O workload characterization of two leadership class storage clusters. In: PDSW '15 Proceedings of the 10th Parallel Data Storage Workshop

The Oak Ridge Leadership Computing Facility (OLCF) is a leader in large-scale parallel file system development, design, deployment and continuous operation. For the last decade, the OLCF has designed and deployed two large center-wide parallel file systems. The first instantiation, Spider 1, served the Jaguar supercomputer and its predecessor, Spider 2, now serves the Titan supercomputer, among many other OLCF computational resources. The OLCF has been rigorously collecting file and storage system statistics from these Spider systems since their transition to production state. In this paper we present the collected I/O workload statistics from the Spider 2 system and compare it to the Spider 1 data. Our analysis show that the Spider 2 workload is more more write-heavy I/O compared to Spider 1 (75% vs. 60%, respectively). The data also show the OLCF storage policies such as periodic purges are effectively managing the capacity resource of Spider 2. Furthermore, due to improvements in tdm_multipath and ib_srp software, we are utilizing the Spider 2 system bandwidth and latency resources more effectively. The Spider 2 bandwidth usage statistics shows that our system is working within the design specifications. However, it is also evident that our scientific applications can be more effectively served by a burst buffer storage layer. All the data has been collected by monitoring tools developed for the Spider ecosystem. We believe the observed data set and insights will help us better design the next-generation Spider file and storage system. It will also be helpful to the larger community for building more effective large-scale file and storage systems.

Gunasekaran, Raghul↗

Partitioning Models for Scaling Parallel Sparse Matrix-Matrix Multiplication

We investigate outer-product--parallel, inner-product--parallel, and row-by-row-product--parallel formulations of sparse matrix-matrix multiplication (SpGEMM) on distributed memory architectures. For each of these three formulations, we propose a hypergraph model and a bipartite graph model for distributing SpGEMM computations based on one-dimensional (1D) partitioning of input matrices. Here, we also propose a communication hypergraph model for each formulation for distributing communication operations. The computational graph and hypergraph models adopted in the first phase aim at minimizing the total message volume and balancing the computational loads of processors, whereas the communication hypergraph models adopted in the second phase aim at minimizing the total message count and balancing the message volume loads of processors. That is, the computational partitioning models reduce the bandwidth cost and the communication hypergraph models reduce the latency cost. Our extensive parallel experiments on up to 2048 processors for a wide range of realistic SpGEMM instances show that although the outer-product--parallel formulation scales better, the row-by-row-product--parallel formulation is more viable due to its significantly lower partitioning overhead and competitive scalability. For computational partitioning models, our experimental findings indicate that the proposed bipartite graph models are attractive alternatives to their hypergraph counterparts because of their lower partitioning overhead. Finally, we show that by reducing the latency cost besides the bandwidth cost through using the communication hypergraph models, the parallel SpGEMM time can be further improved up to 32%.

97 MATHEMATICS AND COMPUTING↗

PC-RPL: Joint Control of Routing Topology and Transmission Power in Real Low-Power and Lossy Networks

We present PC-RPL , a transmission power-controlled IPv6 routing protocol for low-power and lossy wireless networks that significantly improves the end-to-end packet delivery performance under heavy traffic compared to the standard RPL. We show through actual design, implementation, and experiments that a multihop wireless network can achieve better throughput and routing stability when transmission power and routing topology are “jointly and adaptively” controlled. Our experiments show that the predominant “fixed and uniform” transmission power strategy with “link quality and hop distance”–based routing topology construction (i.e., RPL) loses significant bandwidth due to hidden terminal and load imbalance problems. We design an adaptive and distributed control mechanism for transmission power and routing topology, named PC-RPL , on top of the standard RPL routing protocol for hidden terminal mitigation and load balancing. We implement PC-RPL on real embedded devices and evaluate its performance on a 49-node multihop testbed. PC-RPL reduces total end-to-end packet losses by approximately sevenfold without increasing hop distance compared to RPL with the highest transmission power, resulting in 17% improvement in aggregate bandwidth and 64% improvement for the worst-case node by successfully alleviating both hidden terminal and load imbalance problems.

Computer Science↗

Programming Strategies for Irregular Algorithms on the Emu Chick

The Emu Chick prototype implements migratory memory-side processing in a novel hardware system. Rather than transferring large amounts of data across the system interconnect, the Emu Chick moves lightweight thread contexts to near-memory cores before the beginning of each remote memory read. Previous work has characterized the performance of the Chick prototype in terms of memory bandwidth and programming differences from more typical, non-migratory platforms, but there has not yet been an analysis of algorithms on this system. This work evaluates irregular algorithms that could benefit from the lightweight, memory-side processing of the Chick and demonstrates techniques and optimization strategies for achieving performance in sparse matrix-vector multiply operation (SpMV), breadth-first search (BFS), and graph alignment across up to eight distributed nodes encompassing 64 nodelets in the Chick system. We also define and justify relative metrics to compare prototype FPGA-based hardware with established ASIC architectures. The Chick currently supports up to 68x scaling for graph alignment, 80 MTEPS for BFS on balanced graphs, and 50% of measured STREAM bandwidth for SpMV.

Hein, Eric↗

Mitigating Inter-Job Interference via Process-Level Quality-of-Service

Jobs on most high-performance computing (HPC) systems share the network with other concurrently executing jobs. Network sharing leads to contention that can severely degrade performance. Here we investigate the use of Quality of Service (QoS) mechanisms to reduce the negative impacts of network contention. QoS allows users to manage resource sharing between network flows and to provide bandwidth guarantees to specific flows. Our results show that careful use of QoS reduces the impact of network contention for specific jobs, resulting in up to a 40% performance improvement. In some cases, it completely eliminates the impact of contention. It achieves these improvements with limited negative impact to other jobs; any job that experiences performance loss typically degrades less than 5%, and often much less. Our approach can help ensure that HPC machines maintain high levels of throughput as per-node compute power continues to increase faster than network bandwidth.

97 MATHEMATICS AND COMPUTING↗

Single-node Partitioned-Memory for Huge Graph Analytics: Cost and Performance Trade-offs

Nonvolatile memory NVDIMMs, available as Intel Optane, are less expensive than DRAM and bring large byte-addressable storage within reach to many applications. Evaluations on graph analytics have shown promising performance only when DRAM is used as a hardware cache (Memory mode). An open question is whether graph applications can exploit Optane and DRAM directly (AppDirect mode) and achieving better-than-DRAM average bandwidth and run times. We evaluate Optane as a volatile pool on two large-scale graph applications with very different computational patterns, Grappolo and Ripples. We show that AppDirect mode can deliver better-than-DRAM performance, by allocating data structures to Optane and DRAM according to their access characteristics, resulting in higher average memory bandwidth and lower average latency. Memory mode provides DRAM-competitive performance with capacity equal to persistent memory. We demonstrate occasional 4x improvement using the latest AppDirect option and frequently observe competitive performance between Optane AppDirect Memory modes and DRAM.

Ghosh, Sayan↗

Access Patterns and Performance Behaviors of Multi-layer Supercomputer I/O Subsystems under Production Load

Scientific computing workloads at HPC facilities have been shifting from traditional numerical simulations to AI/ML applications for training and inference while processing and producing ever-increasing amounts of scientific data. To address the growing need for increased storage capacity, lower access latency, and higher bandwidth, emerging technologies such as non-volatile memory are integrated into supercomputer I/O subsystems. With these emerging trends, we need a better understanding of the multilayer supercomputer I/O systems and ways to use these subsystems efficiently. In this work, we study the I/O access patterns and performance characteristics of two representative supercomputer I/O subsystems. Through an extensive analysis of year-long I/O logs on each system, we report new observations in I/O reads and writes, unbalanced use of storage system layers, and new trends in user behaviors at the HPC I/O middleware stack.

Bez, JL↗

Scalable Incremental Checkpointing using GPU-Accelerated De-Duplication

Writing large amounts of data concurrently to stable storage is a typical I/O pattern of many HPC workflows. This pattern introduces high I/O overheads and results in increased storage space utilization especially for workflows that need to capture the evolution of data structures with high frequency as checkpoints. In this context, many applications, such as graph pattern matching, perform sparse updates to large data structures between checkpoints. For these applications, incremental checkpointing techniques that save only the differences from one checkpoint to another can dramatically reduce the checkpoint sizes, I/O bottlenecks, and storage space utilization. However, such techniques are not without challenges: it is non-trivial to transparently determine what data has changed since a previous checkpoint and assemble the differences in a compact fashion that does not result in excessive metadata. State-of-art data reduction techniques (e.g., compression and de-duplication) have significant limitations when applied to modern HPC applications that leverage GPUs: slow at detecting the differences, generate a large amount of metadata to keep track of the differences, and ignore crucial spatiotemporal checkpoint data redundancy. This paper addresses these challenges by proposing a Merkle tree-based incremental checkpointing method to exploit GPUs' high memory bandwidth and massive parallelism. Experimental results at scale show a significant reduction of the I/O overhead and space utilization of checkpointing compared with state-of-the-art incremental checkpointing and compression techniques.

Tan, Nigel↗

Tailor : Altering Skip Connections for Resource-Efficient Inference

Deep neural networks use skip connections to improve training convergence. However, these skip connections are costly in hardware, requiring extra buffers and increasing on- and off-chip memory utilization and bandwidth requirements. In this article, we show that skip connections can be optimized for hardware when tackled with a hardware-software codesign approach. We argue that while a network’s skip connections are needed for the network to learn, they can later be removed or shortened to provide a more hardware-efficient implementation with minimal to no accuracy loss. We introduceTailor, a codesign tool whose hardware-aware training algorithm gradually removes or shortens a fully trained network’s skip connections to lower the hardware cost.Tailorimproves resource utilization by up to 34% for block random access memories (BRAMs), 13% for flip-flops (FFs), and 16% for look-up tables (LUTs) for on-chip, dataflow-style architectures.Tailorincreases performance by 30% and reduces memory bandwidth by 45% for a two-dimensional processing element array architecture.

Computer Science↗

CommBench: Micro-Benchmarking Hierarchical Networks with Multi-GPU, Multi-NIC Nodes

Modern high-performance computing systems have multiple GPUs and network interface cards (NICs) per node. The resulting network architectures have multilevel hierarchies of subnetworks with different interconnect and software technologies. These systems offer multiple vendor-provided communication capabilities and library implementations (IPC, MPI, NCCL, RCCL, OneCCL) with APIs providing varying levels of performance across the different levels. Understanding this performance is currently difficult because of the wide range of architectures and programming models (CUDA, HIP, OneAPI). We present CommBench, a library with cross-system portability and a high-level API that enables developers to easily build microbenchmarks relevant to their use cases and gain insight into the performance (bandwidth & latency) of multiple implementation libraries on different networks. We demonstrate CommBench with three sets of microbenchmarks that profile the performance of six systems. Our experimental results reveal the effect of multiple NICs on optimizing the bandwidth across nodes and also present the performance characteristics of four available communication libraries within and across nodes of NVIDIA, AMD, and Intel GPU networks.

Hidayetoglu, Mert↗

Studying CPU and memory utilization of applications on Fujitsu A64FX and Nvidia Grace Superchip

ARM-based manycore CPU architectures are well-positioned to provide the rising memory throughput requirements of modern data intensive scientific applications in High Performance Computing (HPC). The Fujitsu A64FX CPU platform is based on the ARM v8.2A architecture, and is the processor of the flagship Japanese supercomputer - "Fugaku", which was previously ranked as the #1 supercomputer in the world according to the Top500 list. The Nvidia Grace superchip features 144 Neoverse V2 cores based on the ARMv9 architecture with 4x128b SVE2, providing exceptional computational power. The chip supports up to 480GB of memory, making it ideal for AI, machine learning, and scientific computing workloads. In this paper, we conduct a thorough performance exploration of a variety of parallel bandwidth-sensitive benchmarks and applications compiled with the native Fujitsu compiler on a Fugaku A64FX compute node and ARM (LLVM) Compiler on an NVIDIA Grace superchip compute node, engaging all the computational cores per cluster using OpenMP multithreading (assuming the cores can drive the available bandwidth). Our ultimate goals are to study the resource utilization of scientific applications and benchmarks on A64FX and Grace superchip, considering graph application scenarios ( GAP Benchmark suite) and eleven appli- cation proxies from the Rodinia heterogeneous benchmark suite (considering domains such as Data Mining, Bioinformatics, Fluid Dynamics, Pattern Recognition, etc.). Through exhaustive performance monitoring, we quantify the resource utilization of diverse OpenMP-based HPC applications on both the Fujitsu A64FX and the Nvidia Grace Superchip platforms.

benchmarking, Performance Analysis, High performan↗