Systems Reading Group

• [Aug 29, 2024] S-LoRA: Serving Thousands of Concurrent LoRA Adapters, MLSys 2024

  • Presented by Seunggon Jeon

• [Jul 23, 2024] Managing Memory Tiers with CXL in Virtualized Environments, OSDI 2024

  • Presented by Jongho Baik

• [Jul 04, 2024] GMLake: Efficient and Transparent GPU Memory Defragmentation for Large-scale DNN Training with Virtual Memory Stitching, ASPLOS 2024

  • Presented by Jinwoo Jeong

• [Jun 11, 2024] MATRYOSHKA: Non-Exclusive Memory Tiering via Transactional Page Migration, OSDI 2024

  • Presented by Jonghyeon Kim

• [May 30, 2024] IDYLL: Enhancing Page Translation in Multi-GPUs via Light Weight PTE Invalidations, MICRO 2023

  • Presented by Seungsu Baek

• [May 14, 2024] GRIT: Enhancing Multi-GPU Performance with Fine-Grained Dynamic Page Placement, HPCA 2024

  • Presented by Youngjoon Cheon

• [Sep 22, 2023] SHEPHERD: Serving DNNs in the wild, NSDI 2023

  • Presented by Seungsu Baek

• [Aug 31, 2023] Johnny Cache: the End of DRAM Cache Conflicts (in Tiered Main Memory Systems), OSDI 2023

  • Presented by Jonghyeon Kim

• [Aug 16, 2023] TRiM: Enhancing Processor-Memory Interfaces with Scalable Tensor Reduction in Memory, MICRO 2021

  • Presented by Youngjoon Cheon

• [Aug 03, 2023] FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU, ICML 2023

  • Presented by Woohyung Choi

• [Jul 27, 2023] Mobius: Fine Tuning Large-Scale Models on Commodity GPU Servers, ASPLOS 2023

  • Presented by Jinwoo Jeong

• [Jul 20, 2023] AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving, OSDI 2023

  • Presented by Seungsu Baek

• [May 19, 2023] DiLOS: Do Not Trade Compatibility for Performance in Memory Disaggregation, EuroSys 2023

  • Presented By Youngjoon Cheon

• [April 06, 2023] Optimus-CC: Efficient Large NLP Model Training with 3D Parallelism Aware Communication Compression, ASPLOS 2023

  • Presented by Jiho Park

• [Mar 16, 2023] DeepUM: Tensor Migration and Prefetching in Unified Memory, ASPLOS 2023

  • Presented by Woohyung Choi

• [Feb  23, 2023] FLAT: An Optimized Dataflow for Mitigating Attention Bottlenecks, ASPLOS 2023

  • Presented by Jinwoo Jeong

• [Feb 02, 2023] Trident: Harnessing Micro-architectural Resources for All Page Sizes in x86 Processors, MICRO 2021

  • Presented by Jonghyeon Kim

• [Jan 19, 2023] Enable Simultaneous DNN Services Based on Deterministic Operator Overlap and Precise Latency Prediction, SC 2021

  • Presented by Seungsu Baek

• [Jan 05, 2023] From Cloud Computing to Sky Computing, HotOS 2021

  • Presented by Jeongseob Ahn

• [Sep 28, 2022] Orca: A Distributed Serving System for Transformer-Based Generative Models, OSDI 2022

  • Presented by Jinwoo Jeong

• [Aug 19, 2022] Ribbon: Cost-Effective and QoS-Aware Deep Learning Model Inference Using a Diverse Pool of Cloud Computing Instances, SC 2022

  • Presented by Seungsu Baek

• [Aug 03, 2022] TMO: Transparent Memory Offloading in Datacenters, ASPLOS 2022

  • Presented by Jonghyeon Kim

• [Mar 16, 2022] HeMem: Scalable Tiered Memory Management for Big Data Applications and Real NVM, SOSP 2021

  • Presented by Suhyun Kim

• [Mar 02, 2022] Check-N-Run: a Checkpointing System for Training Deep Learning Recommendation Models, NSDI 2022

  • Presented by Seungsu Baek

• [Feb 23, 2022] Layerweaver: Maximizing Resource Utilization of Neural Processing Units via Layer-Wise Scheduling, HPCA 2021

  • Presented by Jinwoo Jeong

• [Feb 16, 2022] Don’t shoot down TLB shootdowns!, EuroSys 2020

  • Presented by Jonghyeon Kim

• [Jan 19, 2022] MobiSR: Efficient On-Device Super-Resolution through Heterogeneous Mobile Processors, MobiCom 2019

  • Presented by Jungmo Ahn

• [Apr 06, 2021] Serving DNNs like Clockwork: Performance Predictability from the Bottom Up, OSDI 2020

  • Presented by Jinwoo Jeong

• [Mar 23, 2021] Persistent State Machines for Recoverable In-memory Storage Systems with NVRam, OSDI 2020

  • Presented by Minjong Ha

• [Mar 09, 2021] A Comprehensive Analysis of Superpage Management Mechanisms and Policies, ATC 2020

  • Presented by Wonkyo Choe

• [Feb 19, 2021] Balancing Efficiency and Fairness in Heterogeneous GPU Clusters for Deep Learning. EuroSys 2020

  • Presented by Taeklim Kim

• [Feb 05, 2021]  HawkEye: Efficient Fine-grained OS Support for Huge Pages, ASPLOS 2019

  • Presented by Jonghyeon Kim

• [Jan 29, 2021] Fast RDMA-based Ordered Key-Value Store using Remote Learned Cache, OSDI 2020

  • Presented by Minjong Ha

• [Jan 22, 2021] AntMan: Dynamic Scaling on GPU Clusters for Deep Learning, OSDI 2020

  • Presented by Jinwoo Jeong

• [Nov 04, 2020]  Towards Real-time Cooperative Deep Inference over the Cloud and Edge End Devices, Ubicomp 2020

  • Presented by Jungmo Ahn

• [Oct 07, 2020] Effectively Prefetching Remote Memory with Leap, ATC 2020

  • Presented by Minjong Ha

• [Sep 16, 2020] Optimizing the TLB Shootdown Algorithm with Page Access Tracking, ATC 2017

  • Presented by Jonghyeon Kim

• [Jul 29, 2020] Pipelined Data-Parallel CPU/GPU Scheduling for Multi-DNN Real-Time Inference, RTSS 2019

  • Presented by Jungmo Ahn

• [Jul 15, 2020] Capuchin: Tensor-based GPU Memory Management for Deep Learning, ASPLOS 2020

  • Presented by Jinwoo Jeong

• [Jun 17, 2020] HotRing: A Hotspot-Aware In-Memory Key-Value Store,  FAST 2020

  • Presented by Minjong Ha

• [Jun 03, 2020] Enhancing and Exploiting Contiguity for Fast Memory Virtualization, ISCA 2020

  • Presented by Jonghyeon Kim

• [May 13, 2020] Towards Efficient NVDIMM-based Heterogeneous Storage Hierarchy Management for Big Data Workloads, MICRO 2019

  • Presented by Wonkyo Choe

• [Feb 19, 2020] Mitosis: Transparently Self-Replicating Page-Tables for Large-Memory Machines, ASPLOS 2020

  • Presented by Wonkyo Choe

• [Feb 12, 2020] DRAGON: Breaking GPU Memory Capacity Limits with Direct NVM Access, SC 2018

  • Presented by Taeklim Kim

• [Jan 29, 2020] Mosaic: A GPU Memory Manager with Application-Transparent Support for Multiple Page Sizes, MICRO 2017

  • Presented by Jinwoo Jeong

• [Jan 22, 2020] Unfair Scheduling Patterns in NUMA Architectures, PACT 2019

  • Presented by Jonghyeon Kim

• [Jan 15, 2020] Neurosurgeon: Collaborative Intelligence Between the Cloud and Mobile Edge, ASPLOS 2017

  • Presented by Jungmo Ahn

• [Jan 08, 2020] Making Huge Pages Actually Useful, ASPLOS 2018

  • Presented by Wonkyo Choe

[Dec 03, 2019] Baymax: QoS Awareness and Increased Utilization for Non-Preemptive Accelerators in Warehouse Scale Computers, ASPLOS 2016

• Presented by Jinwoo Hwang

[Nov 12, 2019] Interplay between hardware prefetcher and page eviction policy in CPU-GPU unified virtual memory, ISCA 2019

• Presented by Jinwoo Jeong

[Oct 08, 2019] A Framework for Memory Oversubscription Management in Graphics Processing Units, ASPLOS 2019

• Presented by Taeklim Kim

[Sep 17, 2019] Thermostat: Application-transparent Page Management for Two-tiered Main Memory, ASPLOS 2017

• Presented by Jonghyeon Kim

[Sep 04, 2019 ] Software-Defined Far Memory in Warehouse-Scale Computers, ASPLOS 2019

• Presented by Jinwoo Hwang

[Aug 28, 2019] Combining HW/SW Mechanisms to Improve NUMA Performance of Multi-GPU Systems, MICRO 2018

• Presented by Wonkyo Choe

[Aug 07, 2019] Gandiva: Introspective Cluster Scheduling for Deep Learning, OSDI 2018

• Presented by Jinwoo Jeong

[Jul 31, 2019] Reducing DRAM Footprint with NVM in Facebook, EuroSys 2018

• Presented by Jiwon Jeon

[Jul 25, 2019] vDNN: Virtualized Deep Neural Networks for Scalable, Memory-Efficient Neural Network Design, MICRO 2016

• Presented by Taeklim Kim

[Jul 17, 2019] Coordinated and Efficient Huge Page Management with Ingens, OSDI 2016

• Presented by Jonghyeon Kim

[Jul 03, 2019] Janus: Optimizing Memory and Storage Support for Non-Volatile Memory Systems, ISCA 2019

• Presented by Wonkyo Choe

[Jun 12, 2019] Introduction to Blackchain and HyperLedger

• Presented by Jinwoo Hwang

[May 15, 2019] PageSeer: Using Page Walks to Trigger Page Swaps in Hybrid Memory Systems, HPCA 2019

• Presented by Taeklim Kim

[Apr 10, 2019] Preemptive, Low Latency Datacenter Scheduling via Lightweight Virtualization, ATC 2017

• Presented by Jinwoo Jeong

[Apr 03, 2019] Nimble Page Management for Tiered Memory Systems, ASPLOS 2019

• Presented by Jiwon Jeon

[Mar 12, 2019] HeteroOS - OS Design for Heterogeneous Memory Management in Datacenter, ISCA 2017

• Presented by Jonghyeon Kim

[Feb 28, 2019] Reducing the harmful effects of last-level cache polluters with an OS-level, software-only pollute buffer, MICRO 2008

• Presented by Wonkyo Choe

[Feb 14, 2019] PageForge: A Near-Memory Content-Aware Page-Merging Architecture, MICRO 2017

• Presented by Taeklim Kim

[Jan 24, 2019] Inter-Core Cooperative TLB Prefetchers for Chip Multiprocessors, ASPLOS 2010

• Presented by Jonghyeon Kim

[Jan 10, 2019] Translation Caching: Skip, Don’t Walk (the Page Table), ISCA 2010

• Presented by Wonkyo Choe