Search for: All records

Full-system simulation of computer systems is critical for capturing the complex interplay between various hard-ware and software components in future systems. Modeling the network subsystem is indispensable for the fidelity of full-system simulations due to the increasing importance of scale-out systems. Over the last decade, the network software stack has undergone major changes, with userspace networking stacks and data-plane networks rapidly replacing the conventional kernel network stack. Nevertheless, the current state-of-the-art architectural simulator, gem5, still employs kernel networking, which precludes realistic network application scenarios. In this work, we first demonstrate the limitations of gem5's current network stack in achieving high network bandwidth. Then, we enable a userspace networking stack on gem5. We extend gem5's NIC hardware model and device driver to sup-port userspace device drivers running the DPDK framework. Additionally, we implement a network load generator hardware model in gem5 to generate various traffic patterns and per-form per-packet timestamp and latency measurements without introducing packet loss. We develop a suite of six network-intensive benchmarks for stress testing the host network stack. These applications, based on DPDK, can run on both gem5 and real systems. Our experimental results show that enabling userspace networking improves gem5's network bandwidth by 6.3× compared with the current Linux kernel software stack. We characterize the performance of DPDK benchmarks running on both a real system and gem5, and evaluate the sensitivity of the applications to various system and microarchitecture parameters. This work marks the first step in refactoring the networking subsystem in gem5. 

Abstract Artificial biomolecular condensates are emerging as a versatile approach to organize molecular targets and reactions without the need for lipid membranes. Here we ask whether the temporal response of artificial condensates can be controlled via designed chemical reactions. We address this general question by considering a model problem in which a phase separating component participates in reactions that dynamically activate or deactivate its ability to self-attract. Through a theoretical model we illustrate the transient and equilibrium effects of reactions, linking condensate response and reaction parameters. We experimentally realize our model problem using star-shaped DNA motifs known as nanostars to generate condensates, and we take advantage of strand invasion and displacement reactions to kinetically control the capacity of nanostars to interact. We demonstrate reversible dissolution and growth of DNA condensates in the presence of specific DNA inputs, and we characterize the role of toehold domains, nanostar size, and nanostar valency. Our results will support the development of artificial biomolecular condensates that can adapt to environmental changes with prescribed temporal dynamics. 

Living cells regulate many of their vital functions through dynamic, membraneless compartments that phase separate (condense) in response to different types of stimuli. In synthetic cells, responsive condensates could similarly play a crucial role in sustaining their operations. Here we use DNA nanotechnology to design and characterize artificial condensates that respond to light. These condensates form via the programmable interactions of star-shaped DNA subunits (nanostars), which are engineered to include photo-responsive protection domains. In the absence of UV irradiation, the nanostar interactions are not conducive to the formation of condensates. UV irradiation cleaves the protection domains, increases the nanostar valency and enables condensation. We demonstrate that this approach makes it possible to tune precisely the kinetics of condensate formation by dosing UV exposure time. Our experimental observations are complemented by a computational model that characterizes phase transitions of mixtures of particles of different valency, under changes in the mixture composition and bond interaction energy. In addition, we illustrate how UV activation is a useful tool to control the formation and size of DNA condensates in emulsion droplets, as a prototype organelle in a synthetic cell. This research expands our capacity to remotely control the dynamics of DNA-based components via physical stimuli and is particularly relevant to the development of minimal artificial cells and responsive biomaterials.