Discrete event network simulator (DES) is a fundamental service for the design, validation and optimization of various networked systems, including traditional computer networks and the recent LLM training/inference systems. Efficient DES is strongly demanded by the community yet not delivered. The reason is: while DES allows for node-level parallelism, its concurrency potential has been significantly under-utilized (usually <5%) due to the limited number of CPU cores. Meanwhile, GPUs, with thousands of cores, have long been overlooked in the design of DES systems due to the incompatibility between GPUs' SIMT architecture and DES's sequential model. In this paper, we aim to achieve ground-breaking performance improvement for DES by designing a novel GPU-driven simulation engine. By carefully manipulating the life cycles of network events and orchestrating them with long- and short-term alignments, we overcome the incompatibility barriers and established GeDES, a high-level parallel and cost-effective DES system. Extensive simulation experiments show that GeDES significantly boosts DES by 33-2400X speedups compared to the SOTA works Unison and DONS. The code is available at https://github.com/mobinets/GeDES.

The rapid development of large language models (LLMs) has prompted researchers to explore the potential applications, especially for human interaction scenarios.Among these, facilitating meaningful and efficient communication stands out as a critical area, which is especially relevant in elder care. Meanwhile The increasing ratio of elder population highlights the urgent need for personalized care for elders. In this paper, we propose a multi-LLM approach to combine the strengths of multiple LLMs, where LLMs generate complementary answers to the same question, and the final answer is selected based on the combined relevance scores. To assist the answer selection, we provide a comprehensive evaluation of the current state-of-the-art LLMs on elderly care, incorporating real-world feedback from 30 elderly participants on various types of questions. We summarize LLMs’ strengths and weaknesses facing distinct elderly care scenarios, and highlight potential challenges and opportunities for future research.