Research Areas

Ram Rangan

Daniel Johnson

Rishkul Kulkarni

Stephen W. Keckler

Proceedings of the International Symposium on High-Performance Computer Architecture (HPCA)

2021

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

Jacob R. Stevens

Steve Dai

Anand Raghunathan

Design Automation Conference (DAC) 2021

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

Yakun Sophia Shao

Jason Clemons

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

Alicia Klinefelter

Priyanka Raina

Communications of the ACM

Steve Dai

MLSys 2021

Learning Sparse Matrix Row Permutations for Efficient SpMM on GPU Architectures

Atefeh Mehrabi

Danial J. Sorin

Benjamin C. Lee

Proceedings of the International Symposium on Performance Analysis of Systems and Software (ISPASS)

PGZ: Automatic Zero-Value Code Specialization

Ram Rangan

International Conference on Compiler Construction (CC)

2020

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

Abdul Rehman Anwer

Guanpeng Li

Karthik Pattabiraman

Timothy Tsai

The International Conference for High Performance Computing, Networking, Storage, and Analysis

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

Dependable and Secure Machine Learning

Making Convolutions Resilient via Algorithm-Based Error Detection Techniques

arXiv

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

Esha Chouske

Mattan Erez

Jeff Pool

Proceedings of the 47th International Symposium on Computer Architecture (ISCA 2020)

Estimating Silent Data Corruption Rates Using a Two-Level Model

Paolo Rech

Arslan Zulfiqar

Philip Shirvani

Paul Racunas

Joel Emer

arxiv.org

Feature Map Vulnerability Evaluation in CNNS

Abdulrahman Mahmoud

Christopher W. Fletcher

Sarita V. Adve

Charbel Sakr

Naresh Shanbhag

Workshop on Secure and Resilient Autonomy

2019

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

Daichi Fujiki

Proceedings of the 2019 International Conference for High-Performance Computing, Networking, Storage, and Analysis (SC ’19)

MAGNet: A Modular Accelerator Generator for Neural Networks

Sophia Shao

Miaorong Wang

Alicia Klinefelter

Priyanka Raina

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

ACM International Symposium on Microarchitecture (MICRO)

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

Sophia Shao

Jason Clemons

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

Alicia Klinefelter

Priyanka Raina

52nd IEEE/ACM International Symposium on Microarchitecture

Sophia Shao

Alicia Klinefelter

Priyanka Raina

Hot Chips: A Symposium on High Performance Chips

GPU Snapshot: Checkpoint Offloading for GPU-Dense Systems

Kyushick Lee

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

Zbigniew T. Kalbarczyk

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

Ravishankar K. Iyer

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

On the Trend of Resilience for GPU-Dense Systems

Kyushick Lee

Mattan Erez

IEEE/IFIP International Conference on Dependable Systems and Networks

Sankug Lym

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

Mattan Erez

Proceedings of the 2019 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS 2019)

2018

Optimizing Software-Directed Instruction Replication for GPU Error Detection

Abdulrahman Mahmoud

International Conference for High-Performance Computing, Networking, Storage and Analysis (SC)

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, Networking, Storage, and Analysis (SC'18)

Saurabh Jha

Zbigniew Kalbarczyk

Ravishankar K. Iyer

Third IEEE International Workshop on Automotive Reliability & Test

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

The International Symposium on Microarchitecture (MICRO)

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

Neal Crago

ACM Transactions on Architecture and Code Optimization (TACO)

Software-Directed Techniques for Improved GPU Register File Utilization

Dani Voitsechov

Arslan Zulfiqar

Mark Ghebhart

ACM Transactions on Architecture and Code Optimization (TACO)

A Modular Digital VLSI Flow for High-Productivity SoC Design

Evgeni Krimer

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

Alicia Klinefelter

Sophia Shao

Shreesha Srinath

Christopher Torng

Sam (Likun) Xi

Yanqing Zhang

Brian Zimmer

Design Automation Conference (DAC)

Saugata Ghose

Abdullah Giray Yağlıkçı

Raghav Gupta

Kais Kudrolli

William X. Liu

Hasan Hassan

Kevin Chang

Aditya Agrawal

Onur Mutlu

Proceedings of the ACM International Conference on Measurement and Analysis of Computer Systems (SIGMETRICS 2018)

Reducing Data Transfer Energy by Exploiting Similarity within a Data Transaction

Proceedings of the 24th IEEE International Symposium on High Performance Computer Architecture (HPCA 2018)

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

Minsoo Rhu

Jeff Pool

Youngeun Kwon

Proceedings of the 24th IEEE International Symposium on High Performance Computer Architecture (HPCA 2018)

2017

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

Gwangsun Kim

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

Kevin Hsieh

Proceedings of the 2017 International Conference for High-Performance Computing, Networking, Storage, and Analysis (SC 2017)

Guanpeng Li

Karthik Pattabiraman

The International Conference for High Performance Computing, Networking, Storage and Analysis (SC)

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

Aditya Agrawal

Proceedings of the 50th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO 50)

Beyond the Socket: NUMA-Aware GPUs

Ugljesa Milic

Oreste Villa

Akhil Arunkumar

Eiman Ebrahimi

Aamer Jaleel

Alex Ramirez

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

IEEE/ACM International Symposium on Computer Architecture (ISCA)

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

Akhil Arunkumar

Benjamin Cho

Ugljesa Milic

Eiman Ebrahimi

Oreste Villa

Aamer Jaleel

Carole-Jean Wu

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

IEEE/ACM International Symposium on Computer Architecture (ISCA)

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

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 Systems (SIGMETRICS 2017)

Kevin Chang

Abdullah Giray Yağlıkçı

Saugata Ghose

Aditya Agrawal

Abhijith Kashyap

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

Hasan Hassan

Onur Mutlu

Proceedings of the ACM Conference on Measurement and Analysis of Computer Systems (SIGMETRICS 2017)

IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)

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

Caroline Trippel

Yatin A. Manerkar

Daniel Lustig

Michael Pellauer

Margaret Martonosi

22nd ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)

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 Languages and Operating Systems (ASPLOS)

Architecting an Energy-Efficient DRAM System for GPUs

Daniel Johnson

Minsoo Rhu

Approxilyzer: Towards A Systematic Framework for Instruction-Level Approximate Computing and its Application to Hardware Resiliency

Proceedings of the 23rd IEEE International Symposium on High Performance Computer Architecture (HPCA 2017)

2016

Radha Venkatagiri

Abdulrahman Mahmoud

Automatically Exploiting Implicit Pipeline Parallelism from Multiple Dependent Kernels for GPUs

Sarita Adve

Approxilyzer: Towards A Systematic Framework for Instruction-Level Approximate Computing and its Application to Hardware Resilie

CLARA: Circular Linked-List Auto- and Self-Refresh Architecture

Aditya Agrawal

The 2016 International Symposium on Memory Systems (MEMSYS'16)

Gwangsun Kim

Jiyun Jeong

John Kim

Transparent Offloading and Mapping (TOM): Enabling Programmer-Transparent Near-Data Processing in GPU Systems

International Conference on Parallel Architectures and Compilation

Kevin Hsieh

Eiman Ebrahimi

Gwangsun Kim

Nandita Vijaykumar

Onur Mutlu

43rd Annual International Symposium on Computer Architecture (ISCA 2016)

All-Inclusive ECC: Thorough End-to-End Protection for Reliable Computer Memory

Jungrae Kim

A Real-time Energy-Efficient Superpixel Hardware Accelerator for Mobile Computer Vision Applications

Sangkug Lym

Mattan Erez

Proceedings of the International Symposium on Computer Architecture (ISCA)

Injoon Hong

Jason Clemons

Iuri Frosio

Design Automation Conference (DAC) 2016

A Case for Toggle-Aware Compression for GPU Systems

Gennady Pekhimenko

Nandita Vijaykumar

Onur Mutlu

Todd C. Mowry

2016 IEEE International Symposium on High Performance Computer Architecture (HPCA)

An Analytical Model for Hardened Latch Selection and Exploration

Workshop on Silicon Errors in Logic--System Effects (SELSE)

2015

Exploiting Asymmetry in Booth-Encoded Multipliers for Reduced Energy Multiplication

Earl Swartzlander, Jr.

49th Asilomar Conference on Signals, Systems, and Computers

Anatomy of GPU Memory System for Multi-Application Execution

Adwait Jog

Onur Kayiran

Tuba Kesten

Ashutosh Pattnaik

Mahmut T. Kandemir

Chita R. Das

MEMSYS '15 Proceedings of the 2015 International Symposium on Memory Systems

MemcachedGPU: Scaling-up Scale-out Key-value Stores

Tayler Hetherington

Tor Aamodt

Sixth ACM Symposium on Cloud Computing (SoCC '15)

Designing Efficient Heterogeneous Memory Architectures

Alex Ramirez

IEEE Micro

Flexible Software Profiling of GPU Architectures

Yunsup Lee

Eiman Ebrahimi

Daniel Johnson

42nd Annual International Symposium on Computer Architecture (ISCA 2015)

A Variable Warp Size Architecture

Timothy Rogers

Daniel Johnson

42nd Annual International Symposium on Computer Architecture (ISCA 2015)

Toggle-aware Compression for GPUs

Gennady Pekhimenko

Onur Mutlu

Todd C. Mowry

IEEE Computer Architecture Letters ( Volume: 14, Issue: 2, July-Dec. 1 2015 )

Page Placement Strategies for GPUs within Heterogeneous Memory Systems

Neha Agarwal

20th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS 2015)

Unlocking Bandwidth for GPUs in CC-NUMA systems

Neha Agarwal

Thomas Wenisch

21st Annual International Symposium on High Performance Computer Architecture (HPCA 2015)

Priority-Based Cache Allocation in Throughput Processors

Dong Li

Minsoo Rhu

Daniel Johnson

Mattan Erez

Donald Fussell

21st IEEE International Symposium on High Performance Computer Architecture (HPCA 2015)

2014

Exploring the Design Space of SPMD Divergence Management on Data-Parallel Architectures

Yunsup Lee

Vinod Grover

Ronny Krashinsky

Krste Asanovic

IEEE/ACM International Symposium on Microarchitecture (MICRO)

Scaling the Power Wall: A Path to Exascale

Daniel Johnson

Justin Luitjens

Nikolai Sakharnykh

Peng Wang

Paulius Micikevicius

Anthony Scudiero

Application-aware Memory System for Fair and Efficient Execution of Concurrent GPGPU Applications

Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC'14)

Adwait Jog

Zvika Guz

Mike Parker

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

Ronny Krashinsky

A Hierarchical Thread Scheduler and Register File for Energy-Efficient Throughput Processors

International Symposium on Microarchitecture (MICRO)

Mark Gebhart

Daniel R. Johnson

David Tarjan

Erik Lindholm

Kevin Skadron

ACM Transactions on Computer Systems (TOCS)

2011

A Compile-Time Managed Multi-Level Register File Hierarchy

Mark Gebhart

International Symposium on Microarchitecture (MICRO)

GPUs and the Future of Parallel Computing

David Glasco

IEEE Micro

Energy-efficient Mechanisms for Managing Thread Context in Throughput Processors

Mark Gebhart

Daniel R. Johnson

David Tarjan