Difference between revisions of "Resource:Seminar"

From MobiNetS
Jump to: navigation, search
 
(274 intermediate revisions by 7 users not shown)
Line 1: Line 1:
{{SemNote
{{SemNote
|time='''2021-12-24 9:40'''
|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
|abstract = Object detection is a fundamental building block of video analytics applications. While Neural Networks (NNs)-based object detection models have shown excellent accuracy on benchmark datasets, they are not well positioned for high-resolution images inference on resource-constrained edge devices. Common approaches, including down-sampling inputs and scaling up neural networks, fall short of adapting to video content changes and various latency requirements. This paper presents Remix, a flexible framework for high-resolution object detection on edge devices. Remix takes as input a latency budget, and come up with an image partition and model execution plan which runs off-the-shelf neural networks on non-uniformly partitioned image blocks. As a result, it maximizes the overall detection accuracy by allocating various amount of compute power onto different areas of an image. We evaluate Remix on public dataset as well as real-world videos collected by ourselves. Experimental results show that Remix can either improve the detection accuracy by 18%-120% for a given latency budget, or achieve up to 8.1× inference speedup with accuracy on par with the state-of-the-art NNs.
|confname= MobiCom 2021
|link=https://dl.acm.org/doi/abs/10.1145/3447993.3483274
|title=Flexible high-resolution object detection on edge devices with tunable latency
|speaker=Rong
}}


{{Latest_seminar
{{Latest_seminar
|abstract = Data collection with mobile elements can improve energy efficiency and balance load distribution in wireless sensor networks (WSNs). However, complex network environments bring about inconvenience of path design. This work addresses the network environment issue, by presenting an objective-variable tour planning (OVTP) strategy for mobile data gathering in partitioned WSNs. Unlike existing studies of connected networks, our work focuses on disjoint networks with connectivity requirement and serves delay-hash applications as well as energy-efficient scenarios respectively. We first design a converging-aware location selection mechanism, which macroscopically converges rendezvous points (RPs) to lay a foundation of a short tour. We then develop a delay-aware path formation mechanism, which constructs a short tour connecting all segments by a new convex hull algorithm and a new genetic operation. In addition, we devise an energy-aware path extension mechanism, which selects appropriate extra RPs according to specific metrics in order to reduce the energy depletion of data transmission. Extensive simulations demonstrate the effectiveness and advantages of the new strategy in terms of path length, energy depletion, and data collection ratio.
|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= TMC 2022
|confname =OSDI'25
|link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9119834
|link = https://www.usenix.org/conference/osdi25/presentation/cheng
|title=Objective-Variable Tour Planning for Mobile Data Collection in Partitioned Sensor Networks
|title= PipeThreader: Software-defined pipelining for efficient DNN execution
|speaker=Zhuoliu
|speaker=Junzhe
|date=2026-4-9
}}
}}


=== 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"