Existing distributed filesystem metadata services fundamentally rely on ordered metadata indexing, significantly limiting their performance under high-speed networks and persistent memory (PM). In this paper, we propose HMFS, an efficient distributed metadata service that decouples directory listing semantics from the underlying metadata indexing, thus eliminating the need for metadata indexing to organize metadata in an ordered but high-overhead manner. HMFS incorporates three key techniques. First, it proposes index-decoupled metadata organization, which indexes metadata with unordered indexes and preserves directory semantics with direct inter-object links. Second, it designs lightweight crash-consistent metadata updates to efficiently update these two independent data structures coherently with crash consistency. Third, it employs parallel directory listing to accelerate directory traversal. Experiments show that, compared to CephFS and InfiniFS (both deployed on PM) and SingularFS (a PM-optimized metadata service), HMFS reduces metadata operation latency by 92%, 62%, and 39%, and improves throughput by 20.5×, 7.5×, and 1.8×, respectively. At a scale of tens of billions of files, HMFS maintains scalable performance, sustaining 13.4 Mops/s for file create operations and 34.7 Mops/s for file stat operations.

Accurate imaging of converted S-waves is one of the key technical challenges in the processing of multicomponent ocean-bottom seismic data. The widespread presence of anisotropy in the seafloor environment, characterized by fluid-solid coupled media, leads to strong coupling between P- and S-waves. This coupling introduces significant crosstalk noise, which severely degrades the resolution of seismic imaging. To address this issue, we propose a vector wavefield decoupling method tailored for fluid-solid coupled media, aiming to achieve more accurate elastic vector wave imaging for ocean-bottom node data. Specifically, we simplify the existing acoustic-elastic coupled equations for vertically transverse isotropic media. Building upon the decoupling theory developed for purely elastic media — which is based on the normalized zero-order pseudo-Helmholtz operator — we derive explicit relationships between the first-order time derivative of the pseudo-stress components of quasi-P and quasi-S waves in the decoupled system and the first-order time derivative of the synthetic pressure and deviatoric stress components in the acoustoelastic coupling system. From these relationships, we obtain first-order time derivatives of the particle vibration velocity fields for quasi-P and quasi-S waves and express them explicitly in terms of the synthetic pressure and deviatoric stress, thus constructing first-order velocity-stress equations for vector quasi-P and quasi-S waves. Wavefield decoupling tests on both homogeneous and heterogeneous media models demonstrate that the proposed method effectively separates vector quasi-P and quasi-S waves. We further apply the decoupling scheme to elastic reverse time migration. Numerical experiments on simple and complex models show that our method significantly suppresses P-S wave crosstalk and mitigates the adverse effects of wave-mode coupling, thereby enabling high-quality imaging of multicomponent seismic data acquired at the seafloor.

Imaging using S-wave seismic data based on elastic media holds the potential to address certain critical issues that conventional P-wave imaging cannot resolve, thereby offering new opportunities for oil and gas exploration. In this article, we have developed a feasible S-wave reverse time migration (RTM) imaging technique. Based on nonconversion elastic wave theory, we introduce auxiliary variables to construct a first-order pure S-wave equation, which is used to simulate the extrapolation of source wavefields in S-wave RTM. In addition, we employ the first-order velocity-stress equation for backward propagation and use decoupled elastic operators for decoupling of receiver wavefields, and utilize vector cross-correlation imaging conditions to obtain scalar imaging results. Compared with traditional P-wave RTM, the proposed S-wave RTM in this article addresses the limitations of traditional P-wave RTM in processing S-wave seismic data, demonstrating its advantages in reacting to reservoir fluid in the field of oil and gas exploration.

In this work, we propose TARS, a Topology-aware AllReduce algorithm Synthesizer, to generate optimal execution plans for AllReduce workloads over arbitrary interconnection network structures. Distinguished from existing topology-aware synthesizers that formulate the two stages of AllReduce (e.g., ReduceScatter-then-AllGather, or Reduce-then-Broadcast) separately, the power of TARS stems from employing a comprehensive Integer Quadratic Programming (IQP) model to formulate the entire workflow precisely. Preliminary studies confirm that, compared with the state-of-the-art scheme, TARS could significantly reduce the completion time of AllReduce.

Time-of-flight magnetic resonance angiography (TOF-MRA) is the least invasive and ionizing radiation-free approach for cerebrovascular imaging, but variations in imaging artifacts across different clinical centers and imaging vendors result in inter-site and inter-vendor heterogeneity, making its accurate and robust cerebrovascular segmentation challenging. Moreover, the limited availability and quality of annotated data pose further challenges for segmentation methods to generalize well to unseen datasets. In this paper, we construct the largest and most diverse TOF-MRA dataset (COSTA) from 8 individual imaging centers, with all the volumes manually annotated. Then we propose a novel network for cerebrovascular segmentation, namely CESAR, with the ability to tackle feature granularity and image style heterogeneity issues. Specifically, a coarse-to-fine architecture is implemented to refine cerebrovascular segmentation in an iterative manner. An automatic feature selection module is proposed to selectively fuse global long-range dependencies and local contextual information of cerebrovascular structures. A style self-consistency loss is then introduced to explicitly align diverse styles of TOF-MRA images to a standardized one. Extensive experimental results on the COSTA dataset demonstrate the effectiveness of our CESAR network against state-of-the-art methods. We have made 6 subsets of COSTA with the source code online available, in order to promote relevant research in the community.