Sponsored by:
- How does one bit-flip corrupt an entire deep neural network, and what to do about itSpeaker: Yanjing Li
Date: April 16, 2024 at 3:30pm
Location: EER 3.646
Past Semesters
Sponsored by:
2022 Fall
Sponsored by:
- HBM3 RAS: The Journey to Enhancing Die-Stacked DRAM Resilience at ScaleSpeaker: Sudhanva Gurumurthi (AMD)
Date: November 8, 2022 at 3:30pm
Location: EER 3.646 - Accelerating the Pace of AWS Inferentia Chip Development, From Concept to End Customer UseSpeaker: Randy Huang, Amazon AWS
Date: October 18, 2022 at 3:30pm
Location: EER 3.646 - Benchmarking a New Paradigm: An Experimental Analysis of a Real Processing-in-Memory Architecture
2020 Spring
| Date | Speaker | Title | Details | Sign up |
|---|---|---|---|---|
| February 4, 2020 | Andreas Herkersdorf, TU Munich | Tackling the MPSoC Data Locality Challenge with Regional Coherence and Near Memory Acceleration | Andreas Herkersdorf, TU Munich | |
| January 28, 2020 | Paul V Gratz, Texas A&M | SPIN, SWAP and DRAIN: A New Approach to Address Deadlocks in Interconnection Networks | Paul V Gratz, Texas A&M | |
| February 25, 2020 | Rob Schreiber, Cerebras Sys | Meeting the Systems Challenge of Deep Learning | Rob Schreiber, Cerebras Systems |
2019 Fall
Sponsored by:
| September 10, 2019 | Jishen Zhao, UCSD | Unlocking the Full Potential of Persistent Memory Technique with Software/Hardware Coordinated Design | Jishen Zhao |
| September 17, 2019 | Tushar Krishna, Georgia Tech | Enabling Continuous Learning through Synaptic Plasticity in Hardware | Tushar Krishna |
| September 17, 2019 | Arrvindh Shriraman, Simon Fraser Univ | µIRs-Intermediate Representation for Agile Design of Accelerators | Arrvindh Shriraman |
| September 17, 2019 | Yuhao Zhu, Univ of Rochester | The Next Quintillion Pixels: Architecting Next-Generation Mobile Visual Computing Systems. | Yuhao Zhu |
| September 24, 2019 | Sandhya Dwarkadas, Univ of Rochester | Toward Efficient and Protected Address Translation in Memory Management | Sandhya Dwarkadas |
| October 18, 2019 | Minsoo Rhu, KAIST | TensorDIMM: A Practical Near-Memory Processing Architecture for Sparse Embedding Layers in Deep Learning | Minsoo Rhu, KAIST |
| October 29, 2019 | Marc Snir, UIUC | LCI: a lightweight communication interface for HPC | Marc Snir |
| November 12, 2019 | Glenn Henry, Centaur Technology | Centaur Technology’s Deep-Learning Coprocessor Technology | Glenn Henry |
| November 5, 2019 | Vijay Janapa Reddi, Harvard | The Vision Behind MLPerf (mlperf.org): A Community-driven Benchmark Suite for ML Frameworks, ML Accelerators and ML Systems in Cloud and Edge Computing | Vijay Janapa Reddi |
2019 Spring
Sponsored by:
| January 22, 2019 | Bruce Jacob, UMD | All Tomorrow’s Memory Systems | Bruce Jacob, UMD |
| January 29, 2019 | Onur Mutlu, ETH Zurich | Memory Systems and Memory-Centric Computing Systems: Challenges and Opportunities | Onur Mutlu, ETH Zurich |
| February 26, 2019 | Doug Carmean, Microsoft | Architecting the Future with Humility from the Past | Doug Carmean, Microsoft |
2018 Fall
Sponsored by:
| November 9, 2018 | Xiaosong Ma, Qatar Computing Research Institute | Redesigning System Software for Shared Hardware | Xiaosong Ma, Qatar Computing Research Institute |
| October 2, 2018 | Ishwar Bhati, Intel | Architectural Tradeoffs in Designing NVM based LLC | Ishwar Bhati, Intel |
| October 16, 2018 | David Nellans, NVIDIA | Navigating the Challenges of Industrial Performance Simulation | David Nellans, NVIDIA |
| October 30, 2018 | Milad Hashemi | Redefining Interfaces: ML to Accelerate and Design Computer Systems | Milad Hashemi, Google |
| November 8, 2018 | Liu Xu, William and Mary | Squeezing Software Performance via Eliminating Wasteful Memory Operations | Liu Xu, William and Mary |
| November 13, 2018 | Mihai Christodorescu, Visa Research | Navigating the Challenges of Industrial Performance Simulation | Mihai Christodorescu |
| December 14, 2018 | Nader Bagherzadeh, UC Irvine | Deep Learning Opportunities and Limitations | Nader Bagherzadeh, UC Irvine |
2017 Fall
Sponsored by:
- Glaring Gaps in Neurally-Inspired ComputingSpeaker: Mikko Lipasti, University of Wisconsin Madison
Date: December 5, 2017 - Computer Systems for NeuroscienceSpeaker: Abhishek Bhattacharjee, Rutgers University
Date: November 28, 2017
Location:/ POB 2.402 - Teaching Deployed Data Centers New TricksSpeaker: Derek Chiou, Microsoft
Date: October 31, 2017
Location:POB 2.302 - Maximizing Server Efficiency: from microarchitecture to machine-learning acceleratorsSpeaker:Mike Ferdman, Stony Brook University
Date: October 31, 2017
Location:POB 2.402
2017 Spring
Sponsored by:
| February 21, 2017 | Richard Sites | Datacenter Computers: Modern Challenges in CPU design | Richard Sites |
| February 28, 2017 | Peter Hsu | A Convergent Architecture for Big Data, Machine Learning and Real-Time Computing | Peter Hsu |
| May 2, 2017 | Josep Torrellas, UIUC | Energy-Efficient Computer Architectures | Josep Torrellas, UIUC |
| May 1, 2017 | Vivienne Sze, MIT | Energy-Efficient Hardware for Embedded Vision and Deep Convolutional Neural Networks | Vivienne Sze, MIT |
2016 Fall
Sponsored by:
| November 29, 2016 | David Wentzlaff | Processors for the Data Center and Cloud of the Future | David Wentzlaff |
| September 6, 2016 | Josep Torrellas, University of Illinois Urbana-Champaign | Toward Extreme-Scale Manycore Architectures | Josep Torrellas |
| August 30, 2016 | Wen-mei Hwu | Innovative Applications and Technology Pivots – A Perfect Storm in Computing | Venue |
2016 Spring
Sponsored by:
| February 1, 2016 | John Kim (KAIST) | Security Vulnerability of Processor-Interconnect in NUMA Architecture | John Kim |
| March 8, 2016 | Yoav Etsion, Technion | Breaking away from von Neumann: A hybrid, dataflow/von Neumann GPGPU case study | Yoav Etsion |
| June 3, 2016 | Cristina Silvano, Politecnico di Milano | Design Space and Application Autotuning for Runtime Adaptivity in Multicore Architectures | Cristina Silvano, Politecnico di Milano |
| June 6, 2016 | Jürgen Teich, Friedrich-Alexander-Universität Erlangen-Nürnberg | Predictable MPSoC Stream Processing Using Invasive Computing | Juergen Teich, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) |