Difference between revisions of "Resource:Seminar"

From MobiNetS
Jump to: navigation, search
 
(269 intermediate revisions by 7 users not shown)
Line 1: Line 1:
{{SemNote
{{SemNote
|time='''2021-12-24 9:00'''
|time='''2026-04-10 10:30'''
|addr=Main Building B1-612
|addr=4th Research Building A518
|note=Useful links: [[Resource:Reading_List|Readling list]]; [[Resource:Seminar_schedules|Schedules]]; [[Resource:Previous_Seminars|Previous seminars]].
|note=Useful links: [[Resource:Reading_List|📚 Readling list]]; [[Resource:Seminar_schedules|📆 Schedules]]; [[Resource:Previous_Seminars|🧐 Previous seminars]].
}}
}}


===Latest===
===Latest===
{{Latest_seminar
{{Latest_seminar
|abstract = Long-range wide-area network (LoRaWAN) is one of the most promising IoT technologies that are widely adopted in low-power wide-area networks (LPWANs). LoRaWAN faces scalability issues due to a large number of nodes connected to the same gateway and sharing the same channel. Therefore, LoRa networks seek to achieve two main objectives: 1) successful delivery rate and 2) efficient energy consumption. This article proposes a novel game-theoretic framework for LoRaWAN named best equal LoRa (BE-LoRa), to jointly optimize the packet delivery ratio and the energy efficiency (bit/Joule). The utility function of the LoRa node is defined as the ratio of the throughput to the transmit power. LoRa nodes act as rational users (players) which seek to maximize their utility. The aim of the BE-LoRa algorithm is to maximize the utility of LoRa nodes while maintaining the same signal-to-interference-and-noise-ratio (SINR) for each spreading factor (SF). The power allocation algorithm is implemented at the network server, which leads to an optimum SINR, SFs, and transmission power settings of all nodes. Numerical and simulation results show that the proposed BE-LoRa power allocation algorithm has a significant improvement in the packet delivery ratio and energy efficiency as compared to the adaptive data rate (ADR) algorithm of legacy LoRaWAN. For instance, in very dense networks (624 nodes), BE-LoRa can improve the delivery ratio by 17.44% and reduce power consumed by 46% compared to LoRaWAN ADR.
|abstract = To effectively utilize heterogeneous specialized hardware units in modern GPUs, such as TensorCores and Tensor Memory Accelerators, this paper introduces PipeThreader, a new DNN compiler. PipeThreader proposes shifting scheduling functionality from hardware to software so as to enable more efficient and sophisticated computation pipelining with minimal manual effort. This is achieved through sTask-graph, a new DNN computation abstraction, a hierarchical hardware abstraction that captures the capabilities of specialized units, and new scheduling primitives. As a result, PipeThreader can discover efficient pipeline scheduling for well-studied DNN architectures like FlashAttention, achieving comparable or even superior performance. Additionally, it can uncover novel pipeline schemes for emerging models like Mamba2, delivering significantly better performance compared to state-of-the-art hand-crafted implementations. The code is open-sourced at https://github.com/tile-ai/tilelang.
|confname= IoTJ 2022
|confname =OSDI'25
|link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9490646
|link = https://www.usenix.org/conference/osdi25/presentation/cheng
|title=Optimizing Power Allocation in LoRaWAN IoT Applications
|title= PipeThreader: Software-defined pipelining for efficient DNN execution
|speaker=Luwei
|speaker=Junzhe
}}
|date=2026-4-9
{{Latest_seminar
|abstract = Real-time on-device object detection for video analytics fails to meet the accuracy requirement due to limited resources of mobile devices while offloading object detection inference to edges is time-consuming due to the transference of video data over edge networks. Based on the system with both ondevice object tracking and edge-assisted analysis, we formulate a non linear time-coupled program over time, maximizing the overall accuracy of object detection by deciding the frequency of edge-assisted inference, under the consideration of both dynamic edge networks and the constrained detection latency. We then design a learning-based online algorithm to adjust the threshold for triggering edge-assisted inference on the fly in terms of the object tracking results, which essentially controls the deviation of on-device tracking between two consecutive frames in the video, by only taking previously observable inputs. We rigorously prove that our approach only incurs sub-linear dynamic regret for the optimality objective. At last, we implement our proposed online schema, and extensive testbed results with real-world traces confirm the empirical superiority over alternative algorithms, in terms of up to 36% improvement on detection accuracy with ensured detection latency.
|confname= INFOCOM 2021
|link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9488741
|title=Edge-assisted Online On-device Object Detection for Real-time Video Analytics
|speaker=Silence
}}
}}


=== History ===
{{Resource:Previous_Seminars}}
{{Resource:Previous_Seminars}}

Latest revision as of 10:37, 10 April 2026

Time: 2026-04-10 10:30
Address: 4th Research Building A518
Useful links: 📚 Readling list; 📆 Schedules; 🧐 Previous seminars.

Latest

  1. [OSDI'25] PipeThreader: Software-defined pipelining for efficient DNN execution, Junzhe
    Abstract: To effectively utilize heterogeneous specialized hardware units in modern GPUs, such as TensorCores and Tensor Memory Accelerators, this paper introduces PipeThreader, a new DNN compiler. PipeThreader proposes shifting scheduling functionality from hardware to software so as to enable more efficient and sophisticated computation pipelining with minimal manual effort. This is achieved through sTask-graph, a new DNN computation abstraction, a hierarchical hardware abstraction that captures the capabilities of specialized units, and new scheduling primitives. As a result, PipeThreader can discover efficient pipeline scheduling for well-studied DNN architectures like FlashAttention, achieving comparable or even superior performance. Additionally, it can uncover novel pipeline schemes for emerging models like Mamba2, delivering significantly better performance compared to state-of-the-art hand-crafted implementations. The code is open-sourced at https://github.com/tile-ai/tilelang.

History

2024

2023

2022

2021

2020

  • [Topic] [ The path planning algorithm for multiple mobile edge servers in EdgeGO], Rong Cong, 2020-11-18

2019

2018

2017

Instructions

请使用Latest_seminar和Hist_seminar模板更新本页信息.

    • 修改时间和地点信息
    • 将当前latest seminar部分的code复制到这个页面中
    • 将{{Latest_seminar... 修改为 {{Hist_seminar...，并增加对应的日期信息|date=
    • 填入latest seminar各字段信息
    • link请务必不要留空，如果没有link则填本页地址 https://mobinets.org/index.php?title=Resource:Seminar
  • 格式说明
    • Latest_seminar:

{{Latest_seminar
|confname=
|link=
|title=
|speaker=
}}

    • Hist_seminar

{{Hist_seminar
|confname=
|link=
|title=
|speaker=
|date=
}}

Retrieved from "http://mobinets.cn/site/index.php?title=Resource:Seminar&oldid=3511"