Computer Architecture

Associated Publications

2022

Saving PAM4 Bus Energy with SMOREs: Sparse Multi-level Opportunistic Restricted Encodings

Mike O'Connor, Donghyuk Lee, Niladrish Chatterjee, Mike Sullivan, Steve Keckler

IEEE International Symposium on High-Performance Computer Architecture (HPCA)

GPU Subwarp Interleaving

Sana Damani, Mark Stephenson, Ram Rangan, Daniel Johnson, Rishkul Kulkarni, Steve Keckler

Proceedings of the International Symposium on High-Performance Computer Archite…

2021

Softermax: Hardware/Software Co-Design of an Efficient Softmax for Transformers

Jacob R. Stevens, Rangharajan Venkatesan, Steve Dai, Brucek Khailany, Anand Raghunathan

Design Automation Conference (DAC) 2021

Evolution of the Graphics Processing Unit (GPU)

William Dally, Steve Keckler, David B. Kirk

IEEE Micro Special Issue of the 50th Anniversary of the Microprocessor

Optimizing Selective Protection for CNN Resilience

Abdulrahman Mahmoud, Siva Hari, Christopher W. Fletcher, Sarita V. Adve, Charbel Sakr, Naresh Shanbhag, Pavlo Molchanov, Mike Sullivan, Timothy Tsai, Steve Keckler

IEEE 32nd International Symposium on Software Reliability Engineering (ISSRE)

Suraksha: A Framework to Analyze the Safety Implications of Perception Design Choices in AVs

Hengyu Zhao, Siva Hari, Timothy Tsai, Mike Sullivan, Steve Keckler, Jishen Zhao

IEEE 32nd International Symposium on Software Reliability Engineering (ISSRE)

Characterizing and Mitigating Soft Errors in GPU DRAM

Mike Sullivan, Nirmal Saxena, Mike O'Connor, Donghyuk Lee, Paul Racunas, Saurabh Hukerikar, Timothy Tsai, Siva Hari, Steve Keckler

IEEE/ACM International Symposium on Microarchitecture (MICRO)

NVBitFI: Dynamic Fault Injection for GPUs

Timothy Tsai, Siva Hari, Mike Sullivan, Oreste Villa, Steve Keckler

IEEE/IFIP International Conference on Dependable Systems and Networks (DSN)

Simba: scaling deep-learning inference with chiplet-based architecture

Yakun Sophia Shao, Jason Clemons, Rangharajan Venkatesan, Brian Zimmer, Matt Fojtik, Ted Jiang, Ben Keller, Alicia Klinefelter, Nathaniel Pinckney, Priyanka Raina, Stephen Tell, Yanqing Zhang, William Dally, Joel Emer, Tom Gray, Brucek Khailany, Steve Keckler

Communications of the ACM

VS-QUANT: Per-Vector Scaled Quantization for Accurate Low-Precision Neural Network Inference

Steve Dai, Rangharajan Venkatesan, Mark Ren, Brian Zimmer, William Dally, Brucek Khailany

MLSys 2021

Learning Sparse Matrix Row Permutations for Efficient SpMM on GPU Architectures

Atefeh Mehrabi, Donghyuk Lee, Niladrish Chatterjee, Danial J. Sorin, Benjamin C. Lee, Mike O'Connor

Proceedings of the International Symposium on Performance Analysis of Systems a…

PGZ: Automatic Zero-Value Code Specialization

Mark Stephenson, Ram Rangan

International Conference on Compiler Construction (CC)

Making Convolutions Resilient via Algorithm-Based Error Detection Techniques

Siva Hari, Mike Sullivan, Timothy Tsai, Steve Keckler

IEEE Transactions on Dependable and Secure Computing (TDSC)

2020

GPU-Trident: Efficient Modeling of Error Propagation in GPU Programs

Abdul Rehman Anwer, Guanpeng Li, Karthik Pattabiraman, Mike Sullivan, Timothy Tsai, Siva Hari

The International Conference for High Performance Computing, Networking, Storag…

PyTorchFI: A Runtime Perturbation Tool for DNNs

Abdulrahman Mahmoud, Neeraj Aggarwal, Alex Nobbe, Jose Rodrigo Sanchez Vicarte, Sarita V. Adve, Christopher W. Fletcher, Iuri Frosio, Siva Hari

Dependable and Secure Machine Learning

Making Convolutions Resilient via Algorithm-Based Error Detection Techniques

Siva Hari, Mike Sullivan, Timothy Tsai, Steve Keckler

arXiv

Buddy Compression: Enabling Larger Memory for Deep Learning and HPC Workloads on GPUs

Esha Chouske, Mike Sullivan, Mike O'Connor, Mattan Erez, Jeff Pool, David Nellans, Steve Keckler

Proceedings of the 47th International Symposium on Computer Architecture (ISCA …

An In-Network Architecture for Accelerating Shared-Memory Multiprocessor Collectives

Benjamin Klenk, Ted Jiang, Greg Thorson, Larry Dennison

2020 ACM/IEEE 47th Annual International Symposium on Computer Architecture (ISC…

Estimating Silent Data Corruption Rates Using a Two-Level Model

Siva Hari, Paolo Rech, Timothy Tsai, Mark Stephenson, Arslan Zulfiqar, Mike Sullivan, Philip Shirvani, Paul Racunas, Joel Emer, Steve Keckler

arxiv.org

Feature Map Vulnerability Evaluation in CNNS

Abdulrahman Mahmoud, Siva Hari, Christopher W. Fletcher, Sarita V. Adve, Charbel Sakr, Naresh Shanbhag, Pavlo Molchanov, Mike Sullivan, Timothy Tsai, Steve Keckler

Workshop on Secure and Resilient Autonomy

2019

Near-Memory Data Transformation for Efficient Sparse Matrix Multi-Vector Multiplication

Daichi Fujiki, Niladrish Chatterjee, Donghyuk Lee, Mike O'Connor

Proceedings of the 2019 International Conference for High-Performance Computing…

MAGNet: A Modular Accelerator Generator for Neural Networks

Rangharajan Venkatesan, Sophia Shao, Miaorong Wang, Jason Clemons, Steve Dai, Matt Fojtik, Ben Keller, Alicia Klinefelter, Nathaniel Pinckney, Priyanka Raina, Yanqing Zhang, Brian Zimmer, William Dally, Joel Emer, Steve Keckler, Brucek Khailany

International Conference On Computer Aided Design

Accelergy: An Architecture-Level Energy Estimation Methodology for Accelerator Designs

Yannan Nellie Wu, Joel Emer, Vivienne Sze

International Conference on Computer Aided Design (ICCAD)

NVBit: A Dynamic Binary Instrumentation Framework for NVIDIA GPUs

Oreste Villa, Mark Stephenson, David Nellans, Steve Keckler

ACM International Symposium on Microarchitecture (MICRO)

Simba: Scaling Deep-Learning Inference withMulti-Chip-Module-Based Architecture

Sophia Shao, Jason Clemons, Rangharajan Venkatesan, Brian Zimmer, Matt Fojtik, Ted Jiang, Ben Keller, Alicia Klinefelter, Nathaniel Pinckney, Priyanka Raina, Stephen Tell, Yanqing Zhang, William Dally, Joel Emer, Tom Gray, Brucek Khailany, Steve Keckler

52nd IEEE/ACM International Symposium on Microarchitecture

MICRO52 Best Paper Award

A 0.11 pJ/Op, 0.32-128 TOPS, Scalable Multi-Chip-Module-based Deep Neural Network Accelerator Designed with a High-Productivity VLSI Methodology

Rangharajan Venkatesan, Sophia Shao, Brian Zimmer, Jason Clemons, Matt Fojtik, Ted Jiang, Ben Keller, Alicia Klinefelter, Nathaniel Pinckney, Priyanka Raina, Stephen Tell, Yanqing Zhang, William Dally, Joel Emer, Tom Gray, Steve Keckler, Brucek Khailany

Hot Chips: A Symposium on High Performance Chips

GPU Snapshot: Checkpoint Offloading for GPU-Dense Systems

Kyushick Lee, Mike Sullivan, Siva Hari, Timothy Tsai, Steve Keckler, Mattan Erez

International Conference on Supercomputing

On the Trend of Resilience for GPU-Dense Systems

Kyushick Lee, Mike Sullivan, Siva Hari, Timothy Tsai, Steve Keckler, Mattan Erez

IEEE/IFIP International Conference on Dependable Systems and Networks

ML-based Fault Injection for Autonomous Vehicles: A Case for Bayesian Fault Injection

Saurabh Jha, Subho Banerjee, Timothy Tsai, Siva Hari, Mike Sullivan, Zbigniew T. Kalbarczyk, Steve Keckler, Ravishankar K. Iyer

International Conference on Dependable Systems and Networks (DSN-2019)

DeLTA: GPU Performance Model for Deep Learning Applications with In-depth Memory System Traffic Analysis

Sankug Lym, Donghyuk Lee, Niladrish Chatterjee, Mike O'Connor, Mattan Erez

Proceedings of the 2019 IEEE International Symposium on Performance Analysis of…

2018

Optimizing Software-Directed Instruction Replication for GPU Error Detection

Abdulrahman Mahmoud, Siva Hari, Mike Sullivan, Timothy Tsai, Steve Keckler

International Conference for High-Performance Computing, Networking, Storage a…

Exploiting Idle Resources in a High-Radix Switch for Supplemental Storage

Matthias Blumrich, Ted Jiang, Larry Dennison

Proceedings of the International Conference for High Performance Computing, Net…

Kayotee: A Fault Injection-based System to Assess the Safety and Reliability of Autonomous Vehicles to Faults and Errors

Saurabh Jha, Timothy Tsai, Siva Hari, Mike Sullivan, Zbigniew Kalbarczyk, Steve Keckler, Ravishankar K. Iyer

Third IEEE International Workshop on Automotive Reliability & Test

SwapCodes: Error Codes for Hardware-Software Cooperative GPU Pipeline Error Detection

Mike Sullivan, Siva Hari, Brian Zimmer, Timothy Tsai, Steve Keckler

The International Symposium on Microarchitecture (MICRO)

Exposing Memory Access Patterns to Improve Instruction and Memory Efficiency in GPUs

Neal Crago, Mark Stephenson, Steve Keckler

ACM Transactions on Architecture and Code Optimization (TACO)

Software-Directed Techniques for Improved GPU Register File Utilization

Dani Voitsechov, Arslan Zulfiqar, Mark Stephenson, Mark Gebhart, Steve Keckler

ACM Transactions on Architecture and Code Optimization (TACO)

A Modular Digital VLSI Flow for High-Productivity SoC Design

Brucek Khailany, Evgeni Krimer, Rangharajan Venkatesan, Jason Clemons, Joel Emer, Matt Fojtik, Alicia Klinefelter, Michael Pellauer, Nathaniel Pinckney, Sophia Shao, Shreesha Srinath, Christopher Torng, Sam (Likun) Xi, Yanqing Zhang, Brian Zimmer

Design Automation Conference (DAC)

What Your DRAM Power Models Aren’t Telling You: Lessons from a Detailed Experimental Study

Saugata Ghose, Abdullah Giray Yağlıkçı, Raghav Gupta, Donghyuk Lee, Kais Kudrolli, William X. Liu, Hasan Hassan, Kevin Chang, Niladrish Chatterjee, Aditya Agrawal, Mike O'Connor, Onur Mutlu

Proceedings of the ACM International Conference on Measurement and Analysis of …

Compressing DMA Engine: Leveraging Activation Sparsity for Training Deep Neural Networks

Minsoo Rhu, Mike O'Connor, Niladrish Chatterjee, Jeff Pool, Youngeun Kwon, Steve Keckler

Proceedings of the 24th IEEE International Symposium on High Performance Comput…

Reducing Data Transfer Energy by Exploiting Similarity within a Data Transaction

Donghyuk Lee, Mike O'Connor, Niladrish Chatterjee

Proceedings of the 24th IEEE International Symposium on High Performance Comput…

2017

Toward Standardized Near-Data Processing with Unrestricted Data Placement for GPUs

Gwangsun Kim, Niladrish Chatterjee, Mike O'Connor, Kevin Hsieh

Proceedings of the 2017 International Conference for High-Performance Computing…

Understanding Error Propagation in Deep Learning Neural Network (DNN) Accelerators and Applications

Guanpeng Li, Siva Hari, Mike Sullivan, Timothy Tsai, Karthik Pattabiraman, Joel Emer, Steve Keckler

The International Conference for High Performance Computing, Networking, Storag…

Fine-Grained DRAM: Energy-Efficient DRAM for Extreme Bandwidth Systems

Mike O'Connor, Niladrish Chatterjee, Donghyuk Lee, John Wilson, Aditya Agrawal, Steve Keckler, William Dally

Proceedings of the 50th Annual IEEE/ACM International Symposium on Microarchite…

Beyond the Socket: NUMA-Aware GPUs

Ugljesa Milic, Oreste Villa, Evgeny Bolotin, Akhil Arunkumar, Eiman Ebrahimi, Aamer Jaleel, Alex Ramirez, David Nellans

50th Annual IEEE/ACM International Symposium on Microarchitecture

SCNN: An Accelerator for Compressed-sparse Convolutional Neural Networks

Angshuman Parashar, Minsoo Rhu, Anurag Mukkara, Antonio Puglielli, Rangharajan Venkatesan, Brucek Khailany, Joel Emer, Steve Keckler, William Dally

IEEE/ACM International Symposium on Computer Architecture (ISCA)

MCM-GPU: Multi-Chip-Module GPUs for Continued Performance Scalability

Akhil Arunkumar , Evgeny Bolotin, Benjamin Cho, Ugljesa Milic , Eiman Ebrahimi, Oreste Villa, Aamer Jaleel, Carole-Jean Wu , David Nellans

IEEE/ACM International Symposium on Computer Architecture (ISCA)

Understanding Reduced-Voltage Operation in Modern DRAM Devices: Experimental Characterization, Analysis, and Mechanisms

Kevin Chang, Abdullah Giray Yağlıkçı, Saugata Ghose, Aditya Agrawal, Niladrish Chatterjee, Abhijith Kashyap, Donghyuk Lee, Mike O'Connor, Hasan Hassan, Onur Mutlu

Proceedings of the ACM Conference on Measurement and Analysis of Computer Syste…

Design-Induced Latency Variation in Modern DRAM Chips: Characterization, Analysis, and Latency Reduction Mechanisms

Donghyuk Lee, Samira Khan, Lavanya Subramanian, Saugata Ghose, Rachata Ausavarungnirun, Gennady Pekhimenko, Vivek Seshadri, Onur Mutlu

Proceedings of the ACM Conference on Measurement and Analysis of Computer Syste…

SASSIFI: An Architecture-level Fault Injection Tool for GPU Application Resilience Evaluation

Siva Hari, Timothy Tsai, Mark Stephenson, Steve Keckler, Joel Emer

IEEE International Symposium on Performance Analysis of Systems and Software (I…

Automated Synthesis of Comprehensive Memory Model Litmus Test Suites

Daniel Lustig, Andrew Wright, Alexandros Papakonstantinou, Olivier Giroux

22nd ACM International Conference on Architectural Support for Programming Lang…

TriCheck: Memory Model Verification at the Trisection of Software, Hardware, and ISA

Caroline Trippel, Yatin A. Manerkar, Daniel Lustig, Michael Pellauer, Margaret Martonosi