伊利诺伊大学香槟分校

We study the weighted average consensus problem for a gossip network of agents with vector-valued states. For a given matrix-weighted graph, the gossip process is described by a sequence of pairs of adjacent agents communicating and updating their states based on the edge matrix weight. Our key contribution is providing conditions for the convergence of this non-homogeneous Markov process as well as the characterization of its limit set. To this end, we introduce the notion of "w-holonomy" of a set of stochastic matrices, which enables the characterization of sequences of gossiping pairs resulting in reaching a desired consensus in a decentralized manner. Stated otherwise, our result characterizes the limiting behavior of infinite products of (non-commuting, possibly with absorbing states) stochastic matrices.

This chapter introduces the on-chip memory architecture of GPUs, the concept of memory-bound applications, and techniques for improving the performance of memory-bound applications. The chapter uses matrix multiplication to illustrate opportunities for reducing the number of global memory accesses. It then introduces the tiling technique by which barrier synchronization is used to coordinate the timing of executing threads for improved locality and reduced global memory accesses. However, the tiling techniques involve additional complexities in boundary checks. The chapter uses matrix multiplication to illustrate the additional boundary checks that are needed for a tiled kernel to be applicable to arbitrary matrix sizes. The chapter concludes with an overview of how usage of shared memory and registers can affect the number of thread blocks that can be accommodated in each streaming multiprocessor.

Dual-fuel combustion strategy with ammonia (NH3)-hydrocarbon fuel blends has been found to be quite effective in reducing emissions from diesel engines. In this work, a detailed investigation of transient ignition and flame processes under compression ignition (CI) conditions is conducted via large-eddy simulations (LES) of n-heptane/ NH3 sprays in a constant volume reactor. The numerical model considers injection of n-heptane in a mixture of NH3, air, and combustion products. Single-fuel (SF) and dual-fuel (DF) sprays are simulated using a validated detailed chemistry model. Transient processes starting from ignition kernel formation, growth and transition to flame propagation in turbulent sprays are analyzed in both physical space and mixture fraction space. Results indicate that these processes are markedly altered by NH3 concentration and ambient temperature (Ta). Ignition in SF spray involves the generation of small ignition spots, which grow and merge to form one identifiable ignition kernel located near the spray tip. Its subsequent growth then involves a continuous formation of ignition spots that merge with it. In contrast, ignition in DF sprays involves the formation of one ignition spot away from the spray center, which then grows slowly similar to a propagating flame in n-heptane/NH3 mixture. With increase in Ta, the number of ignition spots in SF sprays increases. Consequently, the ignition kernel volume and rate of growth increase, thereby reducing ignition delay time (IDT). In contrast, in DF sprays, with increase in Ta or reduction in NH3 concentration, the size of the ignition spot and its growth increase, and IDT decreases. Most reactive mixture fraction (Zmr) and scalar dissipation rate (chi) are used to further characterize the detailed behavior and underlying physics of the ignition kernel and flame dynamics in diesel and diesel-NH3 sprays for a wide range of conditions. The analysis indicates that ignition kernels are located near Zmr and in regions of low chi. Further, the effect of Ta and NH3 concentration on ignition kernel dynamics is investigated by analyzing their impact on Zmr and chi. The LES results are found to be consistent with those reported in recent experimental and direct numerical simulation studies.

Concerns over the potential over-pathologization of generative AI (GenAI) use and the lack of conceptual clarity surrounding GenAI addiction call for empirical tools and theoretical refinement. This study developed and validated the PUGenAIS-9 (Problematic Use of Generative Artificial Intelligence Scale-9 items) and examined whether PUGenAIS reflects addiction-like patterns under the Internet Gaming Disorder (IGD) framework. Using samples from China and the United States (N = 1508), we conducted confirmatory factor analysis and identified a robust 31-item structure across nine IGD-based dimensions. We then derived the PUGenAIS-9 by selecting the highest-loading items from each dimension and validated its structure in an independent sample (N = 1426). Measurement invariance tests confirmed its stability across nationality and gender. Person-centered (latent profile analysis) and variable-centered (network analysis) approaches revealed a 5–10% prevalence rate, a symptom network structure similar to IGD, and predictive factors related to psychological distress and functional impairment. These findings indicate that PUGenAI shares features of the emotionally vulnerable subtype of IGD rather than the competence-based type. These results support using PUGenAIS-9 to identify problematic GenAI use and show the need to rethink digital addiction with an IDC (Infrastructure-Device-Content) model. This keeps addiction research responsive to new media while avoiding over-pathologizing.

This chapter introduces key concepts in the compute architectures of modern GPUs that are important to CUDA C programmers. It first gives an overview of the GPU execution resources, such as streaming multiprocessors (SMs). It then discusses how the blocks are assigned to SMs and divided into warps for scheduling purposes. It then gives more details about single-instruction, multiple-data execution hardware, warp scheduling, latency tolerance, control divergence, and effects of resource limitations. The chapter concludes with an introduction to the concept of resource queries.