Search for: All records

Not AvailableNext-generation HPC clusters are evolving into highly heterogeneous systems that integrate traditional computing resources with emerging accelerator technologies such as quantum processors, neuromorphic units, dataflow architectures, and specialized AI accelerators within a unified infrastructure. These advanced systems enable workloads to dynamically utilize different accelerators during various computation phases, creating complex execution patterns. The performance of the workloads can therefore be impacted by many factors, including how the accelerators are shared, their utilization, and their placement within the system. Moreover, effects such as the system and network state due to the overall system load can significantly impact the job completion rate. Understanding, identifying, and quantifying the impact of the most critical factors (e.g., the number of allocated accelerators) will help decide the investment decisions for accelerator acquisition and deployment that can improve the overall system throughput. This paper extensively studies these complex interactions among advanced accelerators within an HPC cluster and various workloads. We introduce a novel analytical model which predicts the speedup of a workload given an accelerator/system configuration. This model can be used to quantify the effect of augmenting additional accelerators on job performance running on an HPC cluster. We validate the model using both simulated and real environments. 

The nuclear lamina is an intermediate filament meshwork adjacent to the inner nuclear membrane (INM) that plays a critical role in maintaining nuclear shape and regulating gene expression through chromatin interactions. Studies have demonstrated that A- and B-type lamins, the filamentous proteins that make up the nuclear lamina, form independent but interacting networks. However, whether these lamin subtypes exhibit a distinct spatial organization or whether their organization has any functional consequences is unknown. Using stochastic optical reconstruction microscopy (STORM) our studies reveal that lamin B1 and lamin A/C form concentric but overlapping networks, with lamin B1 forming the outer concentric ring located adjacent to the INM. The more peripheral localization of lamin B1 is mediated by its carboxyl-terminal farnesyl group. Lamin B1 localization is also curvature- and strain-dependent, while the localization of lamin A/C is not. We also show that lamin B1’s outer-facing localization stabilizes nuclear shape by restraining outward protrusions of the lamin A/C network. These two findings, that lamin B1 forms an outer concentric ring and that its localization is energy-dependent, are significant as they suggest a distinct model for the nuclear lamina—one that is able to predict its behavior and clarifies the distinct roles of individual nuclear lamin proteins and the consequences of their perturbation.