Search

Hidayetoğlu et al. propose a novel memory-centric algorithm to reconstruct X-ray CT images in the SC19 article entitled “MemXCT: Memory-Centric X-ray CT Reconstruction with Massive Parallelization”. They formulate the reconstruction with several SpMVs, and propose two memory-centric optimizations to improve cache locality for better memory bandwidth utilization, i.e., a two-level pseudo-Hilbert ordering and a multi-stage input buffering. In this article, we present our results on reproducing that article to show its effectiveness and generality, as part of the SC20 Student Cluster Competition Reproducibility Challenge. We reproduce the execution time and memory bandwidth tests in that article on various architectures, including Intel CPUs, AMD CPUs, and NVIDIA GPUs. We further analyze the bottleneck on different architectures by comparing the achieved memory bandwidth with the peak bandwidth on those architectures. We then reproduce the strong scaling test on CPU and GPU clusters with different scales, and use the proposed algorithm to reconstruct three new X-ray computed tomograms. [ABSTRACT FROM AUTHOR]

Canonical polyadic decomposition (CPD) is one of the most common tensor computations adopted in many scientific applications. The major bottleneck of CPD is matricized tensor times Khatri-Rao product (MTTKRP). To optimize the performance of MTTKRP, various sparse tensor formats have been proposed such as CSF and HiCOO. However, due to the spatial complexity of the tensors, no single format fits all tensors. To address this problem, we propose SpTFS, a framework that automatically predicts the optimal storage format for an input sparse tensor. Specifically, SpTFS leverages a set of sampling methods to lower the sparse tensor to fixed-sized matrices and sparsity features. In addition, SpTFS adopts both supervised learning based and unsupervised learning based methods to predict the optimal sparse tensor storage formats. For supervised learning, we propose TnsNet that combines convolution neural network (CNN) and the feature layer, which effectively captures the sparsity patterns of the input tensors. Once trained, the TnsNet can be used with either density or histogram representation of the input tensor for optimal format prediction. Whereas for unsupervised learning, we propose TnsClustering that consists of a feature encoder using convolutional layers and fully connected layers, and a K-means++ model to cluster sparse tensors for optimal tensor format prediction, without massively profiling on the hardware platform. SpTFS can use the above two models to predict the optimal tensor storage format for accelerating MTTKRP accurately. The experimental results show that both TnsNet and TnsClustering can achieve higher prediction accuracy and performance speedup compared to the state-of-the-art works. [ABSTRACT FROM AUTHOR]

We investigate user activity detection (UAD) and symbol detection (SD) for grant-free communication in the presence of massive users that are actively connected to base station (BS), where a small portion of to-be-connected users wake up in a burst. The number of effective interfering connected users is reduced to only one, by applying a preconditioning matrix to the received signals from multiple antennas at BS. Subsequently, an iterative UAD and SD scheme is applied, where the priori information about the remaining interfering user is exploited and the symbols of the burst users as well as the signature connected user are simultaneously detected by iterative exchanging of the soft information of user activity and symbols. The proposed system outperforms the existing work in terms of the success rate of UAD and bit error rate. [ABSTRACT FROM AUTHOR]

The Community Atmosphere Model (CAM) has been ported, redesigned, and scaled to the full system of the Sunway TaihuLight, and provides peta-scale climate modeling performance. Based on a novel domain decomposition method, we have fully optimized the complete model code by using both OpenACC refactoring and more aggressive and finer-grained Athread approaches. The Athread approach enables us to achieve exceptional memory control and usage, efficient vectorization, and sophisticated utilization of the thread-level communication mechanism. We have also further refined the load-balance behaviors towards ultra-large-scale numerical simulation. By combining all these novelties, we achieved a simulation speed of 7.2 and 25.6 simulation-year-per-day (SYPD) for global 25-km and 100-km resolution, respectively (1.2- to 2.2-fold improvements over previous efforts), and a sustainable double-precision performance of 3.3 PFlops for a 750-m global simulation when using 10075000 cores. [ABSTRACT FROM AUTHOR]

Molecular dynamics (MD) simulations are playing an increasingly important role in many areas ranging from chemical materials to biological molecules. With the continuing development of MD models, the potentials are getting larger and more complex. In this article, we focus on the reactive force field (ReaxFF) potential from LAMMPS to optimize the computation of interactions. We present our efforts on refactoring for neighbor list building, bond order computation, as well as valence angles and torsion angles computation. After redesigning these kernels, we develop a vectorized implementation for non-bonded interactions, which is nearly $100 \times$ 100 × faster than the management processing element (MPE) on the Sunway TaihuLight supercomputer. Furthermore, we have implemented the three-body-list free torsion angles computation, and propose a line-locked software cache method to eliminate write conflicts in the torsion angle and valence angle interactions resulting in an order-of-magnitude speedup on a single Sunway TaihuLight node. In addition, we achieve a speedup of up to 3.5 compared to the KOKKOS package on an Intel Xeon Gold 6148 core. When executed on 1,024 processes, our implementation enables the simulation of 21,233,664 atoms on 66,560 cores with a performance of 0.032 ns/day and a weak scaling efficiency of 95.71 percent. [ABSTRACT FROM AUTHOR]

High-resolution land cover mapping over large areas is a challenging task due to the lack of high-quality labels. A potential solution is to leverage the existing knowledge contained in the freely available lower-resolution land cover products. However, the relatively low resolution and low accuracy of the products lead to numerous inaccurate labels, which harms the performance of the neural network. This article addresses the challenge by jointly optimizing the network parameters and correcting the noisy labels with a novel online noise correction approach and a synergistic noise correction loss. By incorporating the information entropy as a measurement to determine the probable correct labels, the proposed noise correction approach learns to make effective correction of the noisy labels during training and eventually boosts the performance with a training set containing less noisy labels. Experimental results show that the proposed method can effectively correct the noisy labels and reduce their negative impact on network training. By employing the proposed method, we produce a refined high-resolution (3-m) land cover map from a lower-resolution (10-m) product in China and improve the accuracy from 74.96% (10-m) to 81.32% (3-m). Such an approach that can effectively learn from noisy data sets leads to many potential opportunities for using and magnifying existing knowledge and results. [ABSTRACT FROM AUTHOR]

We experimentally demonstrate digital signal processing (DSP)-free 8 × 10 Gb/s 4-level pulse-amplitude modulation (PAM-4) transmission for cost-effective coherent wavelength division multiplexing passive optical network (WDM-PON) with 20 GHz channel spacing over the C-band. The polarization-independent coherent receiver at optical network unit (ONU) including a 3 × 3 fiber coupler and a polarization beam splitter (PBS) followed by three single-ended photodiodes (PDs), is simple and cost-effective, because neither DSP nor phase/frequency locking is necessary for the coherent detection of PAM-4 signal. We numerically compare the performance between the transmitted signal diversity and the local oscillator (LO) signal diversity schemes, and optimize the parameters of heterodyne detection, in order to enhance the power budget. Based on the LO signal diversity scheme, we can achieve an average receiver sensitivity of −26 dBm for eight wavelength channels at a bit error ratio (BER) below the hard-decision forward error correction (HD-FEC) threshold (i.e., 3.8 × 10−3), leading to a power budget of 29 dB after 25 km standard single-mode fiber (SSMF) transmission. Moreover, we verify an unequally spaced PAM-4 signaling, leading to contribution of 1 dB receiver sensitivity improvement for 10 Gb/s/λ PON. [ABSTRACT FROM AUTHOR]

To improve the performance of sparse Cholesky factorization, existing research divides the adjacent columns of the sparse matrix with the same nonzero patterns into supernodes for parallelization. However, due to the various structures of sparse matrices, the computation of the generated supernodes varies significantly, and thus hard to optimize when computed by dense matrix kernels. Therefore, how to efficiently map sparse Choleksy factorization to the emerging architectures, such as Sunway many-core processor, remains an active research direction. In this article, we propose swCholesky, which is a highly optimized implementation of sparse Cholesky factorization on Sunway processor. Specifically, we design three kernel task queues and a dense matrix library to dynamically adapt to the kernel characteristics and architecture features. In addition, we propose an auto-tuning mechanism to search for the optimal settings of the important parameters in swCholesky. Our experiments show that swCholesky achieves better performance than state-of-the-art implementations. [ABSTRACT FROM AUTHOR]

In recent years, several channel models for homogenous weakly coupled multicore fibers (WC-MCFs) have been proposed. To model the intercore crosstalk (XT) accurately, the amount of computation effort for numerical simulation becomes unacceptable because the calculation step size must be small enough to describe the XT that is occurring at each phase-matching point. In this paper, which is based on the nonlinear Schrodinger equations and utilizes the XT transfer function for downsampling XT in the frequency domain, we propose an efficient homogeneous WC-MCF channel model that can quickly and accurately describe the XT. The proposed channel model assumes that the WC-MCF operates in the phase-matching region and that the mean XT power is constant within the simulation time window. The relationship between the frequency-dependent characteristics of XT and the walk-off is confirmed by both simulations and experiments, which shows good agreement with the theoretical results. We also discuss the scope of the validity of the proposed channel model with different mean XT power and walk-off. In conclusion, the channel model shows good flexibility for different homogeneous WC-MCF-based transmission systems. [ABSTRACT FROM AUTHOR]

Common Midpoint (CMP) and Common Reflection Surface (CRS) are widely used methods for improving the signal-to-noise ratio in the field of seismic processing. These methods are computationally intensive and require high-performance computing. This article optimizes these methods on the Sunway many-core architecture and implements large-scale seismic processing on the Sunway Taihulight supercomputer. We propose the following three optimization techniques: 1) we propose a software cache method to reduce the overhead of memory accesses, and share data among CPEs via the register communication; 2) we re-design the semblance calculation procedure to further reduce the overhead of memory accesses; 3) we propose a vectorization method to improve the performance when processing the small volume of data within short loops. The experimental results show that our implementations of CMP and CRS methods on Sunway achieve 3.50× and 3.01× speedup on average compared to the-state-of-the-art implementations on CPU. In addition, our implementation is capable to run on more than one million cores of Sunway TaihuLight with good scalability. [ABSTRACT FROM AUTHOR]

Two-dimensional layered semiconductors have attracted a great deal of attention recently from many fields of science and technology. This article overviews the major progress from the perspective of light-emission properties and related device applications of such 2-D materials. We begin with the overview of basic optical properties, including emission features of various excitonic complexes, many-body effects, light-emission enhancement due to plasmonic coupling, and mechanisms of optical gain. This is followed by discussions of coupling of 2-D materials with an optical cavity, including cavity-enhanced emission due to the Purcell effect, strong and weak coupling, as well as lasing behavior. We then discuss the design and the fabrication of various heterostructures by stacking layers of different 2-D materials for the purpose of confining and injecting charge carriers. Such structures are indispensable for light-emitting devices under electrical injection, the ultimate goal of any semiconductor-based light-emitting diode (LED) or lasers. The progress in electrical injection devices is reviewed next, where LEDs under lateral and vertical electrical injection schemes are discussed. The review is concluded with an outlook and future perspectives. [ABSTRACT FROM AUTHOR]

As scientific applications are increasingly ported to GPUs to benefit from both the powerful computing capacity and high throughput, accelerating explicit solvers for GPU-based finite volume methods is gaining more and more attention. In this paper, based on the detailed analysis of the FVM algorithm, we present a set of novel optimization methods, including the explicit data cache mechanism, optimal global memory loading strategy, as well as the inner-thread rescheduling method, which derives a suitable mapping from the solver algorithm to the underlying GPU hardware architecture, so as to remarkably improve the solving performance of structured mesh based FVM. We demonstrate the impact of our tuning techniques on two widely-used atmospheric dynamic kernels (3-D Euler and 2-D SWE) on five kinds of mainstream GPU platforms, and make a detailed analysis of the different tuning methodologies so as to demonstrate how to select the proper tuning strategy to different applications on various GPU platforms. Specifically, 93.9x speedup is achieved for the 3D Euler solver on Nvidia V100 over one 12-core Intel E5-2697 (v2) CPU, which is a 77 percent improvement compared with the original speedup without adopting the tuning techniques presented in this work. [ABSTRACT FROM AUTHOR]