People

Steve Keckler

Steve Keckler joined NVIDIA in 2009 and leads the Architecture Research Group. He is also an Adjunct Professor of Computer Science at the University of Texas at Austin, where he served on the faculty from 1998-2012. His research interests include parallel computer architectures, high-performance computing, energy-efficient architectures, and embedded computing.  Dr. Keckler was previously at the Massachusetts Institute of Technology from 1990 to 1998, where he led the development of the M-Machine experimental parallel computer system. He is a Fellow of the ACM, a Fellow of the IEEE, an Alfred P. Sloan Research Fellow, and a recipient of the NSF CAREER award, the ACM Grace Murray Hopper award, the President's Associates Teaching Excellence Award at UT-Austin, and the Edith and Peter O’Donnell award for Engineering. He earned a B.S. in Electrical Engineering from Stanford University and an M.S. and a Ph.D. in Computer Science from the Massachusetts Institute of Technology. Full list of publications

Research Area(s)
Computer Architecture
Computer Vision
High Performance Computing
Artificial Intelligence and Machine Learning
Resilience and Safety
Main Field of Interest
Computer Architecture
Google Scholar
https://scholar.google.com/citations?user=PpjjRvoAAAAJ&hl=en

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

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)
Generating and Characterizing Scenarios for Safety Testing of Autonomous Vehicles
Zahra Ghodsi, Siva Hari, Iuri Frosio, Timothy Tsai, Alejandro Troccoli, Steve Keckler, Siddharth Garg, Anima Anandkumar
IEEE Intelligent Vehicles Symposium (IV)
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
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

Generating and Characterizing Scenarios for Safety Testing of Autonomous Vehicles
Zahra Ghodsi, Siva Hari, Iuri Frosio, Timothy Tsai, Alejandro Troccoli, Steve Keckler, Siddharth Garg, Anima Anandkumar
IEEE Automotive Reliability and Test workshop
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 …
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
Speculative Reconvergence for Improved SIMT Efficiency
Sana Damani, Daniel Johnson, Mark Stephenson, Eddie Yan, Olivier Giroux, Michael McKeown, Steve Keckler
Proceedings of the 18th ACM/IEEE International Symposium on Code Generation and…
A 0.32–128 TOPS, Scalable Multi-Chip-Module-Based Deep Neural Network Inference Accelerator With Ground-Referenced Signaling in 16 nm
Brian Zimmer, Rangharajan Venkatesan, Yakun Sophia Shao, 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
IEEE Journal of Solid-State Circuits (JSSC)
JSSC 2020 Best Paper Award

2019

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
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
NVBit: A Dynamic Binary Instrumentation Framework for NVIDIA GPUs
Oreste Villa, Mark Stephenson, David Nellans, Steve Keckler
ACM International Symposium on Microarchitecture (MICRO)
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
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)
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
A 0.11 pJ/Op, 0.32-128 TOPS, Scalable Multi-Chip-Module-based Deep Neural Network Accelerator with Ground-Reference Signaling in 16nm
Brian Zimmer, Rangharajan Venkatesan, Sophia Shao, 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
Symposium on VLSI Circuits Digest of Technical Papers

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…
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)
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…

2017

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…
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)
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…
Architecting an Energy-Efficient DRAM System for GPUs
Niladrish Chatterjee, Mike O'Connor, Donghyuk Lee, Daniel Johnson, Minsoo Rhu, Steve Keckler, William Dally
Proceedings of the 23rd IEEE International Symposium on High Performance Comput…

2016

CLARA: Circular Linked-List Auto- and Self-Refresh Architecture
Aditya Agrawal, Mike O'Connor, Evgeny Bolotin, Niladrish Chatterjee, Joel Emer, Steve Keckler
The 2016 International Symposium on Memory Systems (MEMSYS'16)
Transparent Offloading and Mapping (TOM): Enabling Programmer-Transparent Near-Data Processing in GPU Systems
Kevin Hsieh, Eiman Ebrahimi, Gwangsun Kim, Niladrish Chatterjee, Mike O'Connor, Nandita Vijaykumar, Onur Mutlu, Steve Keckler
43rd Annual International Symposium on Computer Architecture (ISCA 2016)
A Real-time Energy-Efficient Superpixel Hardware Accelerator for Mobile Computer Vision Applications
Injoon Hong, Jason Clemons, Rangharajan Venkatesan, Iuri Frosio, Brucek Khailany, Steve Keckler
Design Automation Conference (DAC) 2016
A Case for Toggle-Aware Compression for GPU Systems
Gennady Pekhimenko, Evgeny Bolotin, Nandita Vijaykumar, Onur Mutlu, Todd C. Mowry, Steve Keckler
2016 IEEE International Symposium on High Performance Computer Architecture (HP…
An Analytical Model for Hardened Latch Selection and Exploration
Mike Sullivan, Brian Zimmer, Siva Hari, Timothy Tsai, Steve Keckler
Workshop on Silicon Errors in Logic--System Effects (SELSE)

2015

Anatomy of GPU Memory System for Multi-Application Execution
Adwait Jog, Onur Kayiran, Tuba Kesten, Ashutosh Pattnaik, Evgeny Bolotin, Niladrish Chatterjee, Steve Keckler, Mahmut T. Kandemir, Chita R. Das
MEMSYS '15 Proceedings of the 2015 International Symposium on Memory Systems
Designing Efficient Heterogeneous Memory Architectures
Evgeny Bolotin, David Nellans, Oreste Villa, Mike O'Connor, Alex Ramirez, Steve Keckler, Mike O'Connor
IEEE Micro
Flexible Software Profiling of GPU Architectures
Mark Stephenson, Siva Hari, Yunsup Lee, Eiman Ebrahimi, Daniel Johnson, David Nellans, Mike O'Connor, Steve Keckler
42nd Annual International Symposium on Computer Architecture (ISCA 2015)
A Variable Warp Size Architecture
Timothy Rogers, Daniel Johnson, Mike O'Connor, Steve Keckler
42nd Annual International Symposium on Computer Architecture (ISCA 2015)
Toggle-aware Compression for GPUs
Gennady Pekhimenko, Evgeny Bolotin, Mike O'Connor, Onur Mutlu, Todd C. Mowry, Steve Keckler
IEEE Computer Architecture Letters ( Volume: 14, Issue: 2, July-Dec. 1 2015 )
Page Placement Strategies for GPUs within Heterogeneous Memory Systems
Neha Agarwal, David Nellans, Mark Stephenson, Mike O'Connor, Steve Keckler
20th International Conference on Architectural Support for Programming Language…
Priority-Based Cache Allocation in Throughput Processors
Dong Li, Minsoo Rhu, Daniel Johnson, Mike O'Connor, Mattan Erez, Donald Fussell, Steve Keckler
21st IEEE International Symposium on High Performance Computer Architecture (HP…
Unlocking Bandwidth for GPUs in CC-NUMA systems
Neha Agarwal, David Nellans, Mike O'Connor, Steve Keckler, Thomas Wenisch
21st Annual International Symposium on High Performance Computer Architecture (…

2014

Exploring the Design Space of SPMD Divergence Management on Data-Parallel Architectures
Yunsup Lee, Vinod Grover, Ronny Krashinsky, Mark Stephenson, Steve Keckler, Krste Asanovic
IEEE/ACM International Symposium on Microarchitecture (MICRO)
Scaling the Power Wall: A Path to Exascale
Oreste Villa, Daniel Johnson, Mike O'Connor, Evgeny Bolotin, David Nellans, Justin Luitjens, Nikolai Sakharnykh, Peng Wang, Paulius Micikevicius, Anthony Scudiero, Steve Keckler, William Dally
Proceedings of the International Conference for High Performance Computing, Net…
Application-aware Memory System for Fair and Efficient Execution of Concurrent GPGPU Applications
Adwait Jog, Evgeny Bolotin, Zvika Guz, Mike Parker, Steve Keckler, Mahmut T. Kandemir, Chita R. Das
GPGPU-7 Proceedings of Workshop on General Purpose Processing Using GPUs

2012

Unifying Primary Cache, Scratch, and Register File Memories in a Throughput Processor
Mark Gebhart, Steve Keckler, Brucek Khailany, Ronny Krashinsky, William Dally
International Symposium on Microarchitecture (MICRO)
A Hierarchical Thread Scheduler and Register File for Energy-Efficient Throughput Processors
Mark Gebhart, Daniel R. Johnson, David Tarjan, Steve Keckler, William Dally, Erik Lindholm, Kevin Skadron
ACM Transactions on Computer Systems (TOCS)

2011

A Compile-Time Managed Multi-Level Register File Hierarchy
Mark Gebhart, Steve Keckler, William Dally
International Symposium on Microarchitecture (MICRO)
GPUs and the Future of Parallel Computing
Steve Keckler, William Dally, Brucek Khailany, Michael Garland, David Glasco
IEEE Micro
Energy-efficient Mechanisms for Managing Thread Context in Throughput Processors
Mark Gebhart, Daniel R. Johnson, David Tarjan, Steve Keckler, William Dally, Erik Lindholm, Kevin Skadron
Proceedings of the 38th International Symposium on Computer Architecture (ISCA)