A5100430320- Interconnection Networks and Systems
- Parallel Computing and Optimization Techniques
- Advanced Data Storage Technologies
- Graph theory and applications
- Distributed systems and fault tolerance
- Distributed and Parallel Computing Systems
- Low-power high-performance VLSI design
- Supercapacitor Materials and Fabrication
- Cloud Computing and Resource Management
- Advancements in Battery Materials
- VLSI and Analog Circuit Testing
- Advanced Graph Theory Research
- Software-Defined Networks and 5G
- Embedded Systems Design Techniques
- Advanced Memory and Neural Computing
- Matrix Theory and Algorithms
- Plant-Microbe Interactions and Immunity
- Advanced Battery Technologies Research
- Nanocomposite Films for Food Packaging
- Real-Time Systems Scheduling
- Radiation Effects in Electronics
- Carbon and Quantum Dots Applications
- Cloud Data Security Solutions
- Stability and Controllability of Differential Equations
- VLSI and FPGA Design Techniques
Ningxia University
2025
Fujian Normal University
2021-2023
Argonne National Laboratory
2018-2023
Henan University of Economic and Law
2019-2023
Hefei University of Technology
2023
Hebei University
2022-2023
University of California, Berkeley
2022
Berkeley College
2022
Xinjiang University
2020
Jianghan University
2020
Natural rubber is an important industrial raw material and almost exclusively produced from Hevea brasiliensis latex. Because H. limited its cultivation to specific tropical regions, the insufficient capacity of natural has become increasingly urgent. To develop a novel alternative plant for production, we selected perennial shrub Periploca sepium, which widely distributed temperate regions. P. sepium can produce latex contains component polyisoprene with high-molecular-weight distribution...
Abstract Motivated by a multitude of practical applications, many distinct vulnerability parameters multiprocessor systems have been explored. Traditional connectivity and diagnosability are undoubtedly the most well investigated these metrics, but often fail to capture subtle differences system. Subsequently, it is necessary take into account minimum degree components, size components or number components. However, structure ignored in circumstances. In this work, we propose novel...
Emerging many-core CPU architectures with high degrees of single-instruction, multiple data (SIMD) parallelism promise to enable increasingly ambitious simulations based on partial differential equations (PDEs) via extreme-scale computing. However, such present several challenges their efficient use. Here, we explore the implementation sparse matrix-vector (SpMV) multiplications---a critical kernel for workhorse iterative linear solvers used in most PDE-based simulations---on recent from...
Connectivity is an important index to evaluate the reliability and fault tolerance of a graph. As natural extension connectivity graphs, [Formula: see text]-component graph text], denoted by minimum number vertices whose removal from text] results in disconnected with at least components. It scientific issue determine exact values for distinguishing tolerability networks. However, many well-known interconnection networks has not been explored even small text]. For text]-dimensional...
A key to good processor utilization for sparse matrix computations is storing the data in format that most conducive fast access by memory system. In particular, triangular solves traditional compressed poor, and minor adjustments structure can increase dramatically. Such involve L U factors separately rows ‘backwards' so they are accessed a simple streaming fashion during solves. Changes PETSc libraries use this modified storage resulted over twice floating-point rate some matrices. This...
Adaptive neural networks (NN) have been used to optimize OS kernel datapath functions because they can achieve superior performance under changing environments. However, how deploy these NNs remains a challenge. One approach is adaptive in the userspace. such userspace deployments suffer from either high cross-space communication overhead or low responsiveness, significantly compromising function performance. On other hand, pure kernel-space also incur large degradation computation logic of...
We present DMNetwork, a high-level package included in the PETSc library for simulation of multiphysics phenomena over large-scale networked systems. The aims at applications that have structures such as those electrical, gas, and water distribution DMNetwork provides data topology management, parallelization systems network, hierarchical composable solvers to exploit problem structure. eases development cycle by providing necessary infrastructure through simple abstractions define query...
Penicillium expansum is the main cause of apple rot. Besides, it can also produce mycotoxin patulin (PAT). Therefore, search for substances that inhibit activity and toxigenicity P. has become a hot research topic. This study investigates inhibitory effects fengycin on production in expansum. was cultured under different environments with concentrations fengycin. The content produced per unit weight mycelium detected determined by high pressure liquid chromatography (HPLC). Synergy brands...
The main goal of this paper is to describe and validate a specific hybrid dynamical model for NASA's recoverable computer system subjected simulated random upsets. closed-looped with Boeing 737 simulation which flying at cruising altitude. validation based on controlled experiment where the upsets are injected into desired rate, effects output tracking performance aircraft directly observed quantified. consists jump-linear driven by finite-state machine Markov input. models switched dynamics...
with the rapid development of mobile Internet, streaming media has been widely used in Internet users, and more bandwidth consumption resource occupation have brought great challenges to efficiency CDN server cache. To improve cache hit rate for resources, this paper improves traditional LFU replacement algorithm proposes a new LFU-SIZE algorithm. According user's playback record video heat, keep most commonly popular files, replace rarely combine size storage space eliminate one large file...
The methods of approximate query processing have been proposed for analytics over high-speed data streams, which compact continuous streams into a space-constrained sketch and provide reliable estimates different queries. Count-Min (CM) is the state-of-the-art sketching structure supporting many queries with error-guaranteed under limited space. However, we need to create counter table beforehand in CM according size while it usually unpredictable dynamic streams. In this paper, an approach,...
The Portable Extensible Toolkit for Scientific computation (PETSc) library delivers scalable solvers nonlinear time-dependent differential and algebraic equations numerical optimization.The PETSc design performance portability addresses fundamental GPU accelerator challenges stresses flexibility extensibility by separating the programming model used application from that library, it enables developers to use their preferred model, such as Kokkos, RAJA, SYCL, HIP, CUDA, or OpenCL, on upcoming...
Diagnosabilty is an important metric to the capability of fault identification for multiprocessor systems. However, most researches on diagnosability focus vertex fault. In real circumstances, not only faults take place but also malfunctions may arise. this paper, we study k-regular 2-cn graph with missing edges. Let Fe be a set edges in G |Fe|≤ k−5. We prove that G−Fe at δ(G−Fe) k≥5. Furthermore, obtain worst-case (h-edge tolerable diagnosability), denoted by the(G), maximum number faulty...