Search Results for author: David Brooks

Found 40 papers, 15 papers with code

Fathom: Reference Workloads for Modern Deep Learning Methods

1 code implementation23 Aug 2016 Robert Adolf, Saketh Rama, Brandon Reagen, Gu-Yeon Wei, David Brooks

Fathom has been released online, and this paper focuses on understanding the fundamental performance characteristics of each model.

Specificity

Cloud No Longer a Silver Bullet, Edge to the Rescue

no code implementations15 Feb 2018 Yuhao Zhu, Gu-Yeon Wei, David Brooks

This paper takes the position that, while cognitive computing today relies heavily on the cloud, we will soon see a paradigm shift where cognitive computing primarily happens on network edges.

Position

Benchmarking TPU, GPU, and CPU Platforms for Deep Learning

1 code implementation24 Jul 2019 Yu Emma Wang, Gu-Yeon Wei, David Brooks

Training deep learning models is compute-intensive and there is an industry-wide trend towards hardware specialization to improve performance.

Benchmarking

Exploiting Parallelism Opportunities with Deep Learning Frameworks

1 code implementation13 Aug 2019 Yu Emma Wang, Carole-Jean Wu, Xiaodong Wang, Kim Hazelwood, David Brooks

State-of-the-art machine learning frameworks support a wide variety of design features to enable a flexible machine learning programming interface and to ease the programmability burden on machine learning developers.

BIG-bench Machine Learning

MASR: A Modular Accelerator for Sparse RNNs

no code implementations23 Aug 2019 Udit Gupta, Brandon Reagen, Lillian Pentecost, Marco Donato, Thierry Tambe, Alexander M. Rush, Gu-Yeon Wei, David Brooks

The architecture is enhanced by a series of dynamic activation optimizations that enable compact storage, ensure no energy is wasted computing null operations, and maintain high MAC utilization for highly parallel accelerator designs.

speech-recognition Speech Recognition

AdaptivFloat: A Floating-point based Data Type for Resilient Deep Learning Inference

no code implementations29 Sep 2019 Thierry Tambe, En-Yu Yang, Zishen Wan, Yuntian Deng, Vijay Janapa Reddi, Alexander Rush, David Brooks, Gu-Yeon Wei

Conventional hardware-friendly quantization methods, such as fixed-point or integer, tend to perform poorly at very low word sizes as their shrinking dynamic ranges cannot adequately capture the wide data distributions commonly seen in sequence transduction models.

Quantization

A binary-activation, multi-level weight RNN and training algorithm for ADC-/DAC-free and noise-resilient processing-in-memory inference with eNVM

no code implementations30 Nov 2019 Siming Ma, David Brooks, Gu-Yeon Wei

We propose a new algorithm for training neural networks with binary activations and multi-level weights, which enables efficient processing-in-memory circuits with embedded nonvolatile memories (eNVM).

Quantization

SMAUG: End-to-End Full-Stack Simulation Infrastructure for Deep Learning Workloads

no code implementations10 Dec 2019 Sam Likun Xi, Yuan YAO, Kshitij Bhardwaj, Paul Whatmough, Gu-Yeon Wei, David Brooks

In recent years, there has been tremendous advances in hardware acceleration of deep neural networks.

DeepRecSys: A System for Optimizing End-To-End At-scale Neural Recommendation Inference

no code implementations8 Jan 2020 Udit Gupta, Samuel Hsia, Vikram Saraph, Xiaodong Wang, Brandon Reagen, Gu-Yeon Wei, Hsien-Hsin S. Lee, David Brooks, Carole-Jean Wu

Neural personalized recommendation is the corner-stone of a wide collection of cloud services and products, constituting significant compute demand of the cloud infrastructure.

Distributed, Parallel, and Cluster Computing

CHIPKIT: An agile, reusable open-source framework for rapid test chip development

2 code implementations13 Jan 2020 Paul Whatmough, Marco Donato, Glenn Ko, Sae-Kyu Lee, David Brooks, Gu-Yeon Wei

The current trend for domain-specific architectures (DSAs) has led to renewed interest in research test chips to demonstrate new specialized hardware.

Hardware Architecture

Dark Energy Survey Year 1 Results: Cosmological Constraints from Cluster Abundances and Weak Lensing

no code implementations25 Feb 2020 DES Collaboration, Tim Abbott, Michel Aguena, Alex Alarcon, Sahar Allam, Steve Allen, James Annis, Santiago Avila, David Bacon, Alberto Bermeo, Gary Bernstein, Emmanuel Bertin, Sunayana Bhargava, Sebastian Bocquet, David Brooks, Dillon Brout, Elizabeth Buckley-Geer, David Burke, Aurelio Carnero Rosell, Matias Carrasco Kind, Jorge Carretero, Francisco Javier Castander, Ross Cawthon, Chihway Chang, Xinyi Chen, Ami Choi, Matteo Costanzi, Martin Crocce, Luiz da Costa, Tamara Davis, Juan De Vicente, Joseph DeRose, Shantanu Desai, H. Thomas Diehl, Jörg Dietrich, Scott Dodelson, Peter Doel, Alex Drlica-Wagner, Kathleen Eckert, Tim Eifler, Jack Elvin-Poole, Juan Estrada, Spencer Everett, August Evrard, Arya Farahi, Ismael Ferrero, Brenna Flaugher, Pablo Fosalba, Josh Frieman, Juan Garcia-Bellido, Marco Gatti, Enrique Gaztanaga, David Gerdes, Tommaso Giannantonio, Paul Giles, Sebastian Grandis, Daniel Gruen, Robert Gruendl, Julia Gschwend, Gaston Gutierrez, Will Hartley, Samuel Hinton, Devon L. Hollowood, Klaus Honscheid, Ben Hoyle, Dragan Huterer, David James, Mike Jarvis, Tesla Jeltema, Margaret Johnson, Stephen Kent, Elisabeth Krause, Richard Kron, Kyler Kuehn, Nikolay Kuropatkin, Ofer Lahav, Ting Li, Christopher Lidman, Marcos Lima, Huan Lin, Niall MacCrann, Marcio Maia, Adam Mantz, Jennifer Marshall, Paul Martini, Julian Mayers, Peter Melchior, Juan Mena, Felipe Menanteau, Ramon Miquel, Joe Mohr, Robert Nichol, Brian Nord, Ricardo Ogando, Antonella Palmese, Francisco Paz-Chinchon, Andrés Plazas Malagón, Judit Prat, Markus Michael Rau, Kathy Romer, Aaron Roodman, Philip Rooney, Eduardo Rozo, Eli Rykoff, Masao Sako, Simon Samuroff, Carles Sanchez, Alexandro Saro, Vic Scarpine, Michael Schubnell, Daniel Scolnic, Santiago Serrano, Ignacio Sevilla, Erin Sheldon, J. Allyn Smith, Eric Suchyta, Molly Swanson, Gregory Tarle, Daniel Thomas, Chun-Hao To, Michael A. Troxel, Douglas Tucker, Tamas Norbert Varga, Anja von der Linden, Alistair Walker, Risa Wechsler, Jochen Weller, Reese Wilkinson, Hao-Yi Wu, Brian Yanny, Zhuowen Zhang, Joe Zuntz

We perform a joint analysis of the counts and weak lensing signal of redMaPPer clusters selected from the Dark Energy Survey (DES) Year 1 dataset.

Cosmology and Nongalactic Astrophysics

Candidate Periodically Variable Quasars from the Dark Energy Survey and the Sloan Digital Sky Survey

no code implementations27 Aug 2020 Yu-Ching Chen, Xin Liu, Wei-Ting Liao, A. Miguel Holgado, Hengxiao Guo, Robert A. Gruendl, Eric Morganson, Yue Shen, Kaiwen Zhang, Tim M. C. Abbott, Michel Aguena, Sahar Allam, Santiago Avila, Emmanuel Bertin, Sunayana Bhargava, David Brooks, David L. Burke, Aurelio Carnero Rosell, Daniela Carollo, Matias Carrasco Kind, Jorge Carretero, Matteo Costanzi, Luiz N. da Costa, Tamara M. Davis, Juan De Vicente, Shantanu Desai, H. Thomas Diehl, Peter Doel, Spencer Everett, Brenna Flaugher, Douglas Friedel, Joshua Frieman, Juan García-Bellido, Enrique Gaztanaga, Karl Glazebrook, Daniel Gruen, Gaston Gutierrez, Samuel R. Hinton, Devon L. Hollowood, David J. James, Alex G. Kim, Kyler Kuehn, Nikolay Kuropatkin, Geraint F. Lewis, Christopher Lidman, Marcos Lima, Marcio A. G. Maia, Marisa March, Jennifer L. Marshall, Felipe Menanteau, Ramon Miquel, Antonella Palmese, Francisco Paz-Chinchón, Andrés A. Plazas, Eusebio Sanchez, Michael Schubnell, Santiago Serrano, Ignacio Sevilla-Noarbe, Mathew Smith, Eric Suchyta, Molly E. C. Swanson, Gregory Tarle, Brad E. Tucker, Tamas Norbert Varga, Alistair R. Walker

We present a systematic search for periodic light curves in 625 spectroscopically confirmed quasars with a median redshift of 1. 8 in a 4. 6 deg$^2$ overlapping region of the Dark Energy Survey Supernova (DES-SN) fields and the Sloan Digital Sky Survey Stripe 82 (SDSS-S82).

High Energy Astrophysical Phenomena Astrophysics of Galaxies

Performance of the Dark Energy Spectroscopic Instrument(DESI) Fiber System

no code implementations27 Jan 2021 Claire Poppett, Patrick Jelinsky, Julien Guy, Jerry Edelstein, Sharon Jelinsky, Jessica Aguilar, Ray Sharples, Jurgen Schmoll, David Bramall, Luke Tyas, Paul Martini, Kevin Fanning, Michael Levi, David Brooks, Peter Doel, Duan Yutong, Gregory Tarle, Erique Gaztanaga, Francisco Prada, the DESI Collaboration

The recently commissioned Dark Energy Spectroscopic Instrument (DESI) will measure the expansion historyof the universe using the Baryon Acoustic Oscillation technique.

Instrumentation and Methods for Astrophysics

RecSSD: Near Data Processing for Solid State Drive Based Recommendation Inference

no code implementations29 Jan 2021 Mark Wilkening, Udit Gupta, Samuel Hsia, Caroline Trippel, Carole-Jean Wu, David Brooks, Gu-Yeon Wei

Neural personalized recommendation models are used across a wide variety of datacenter applications including search, social media, and entertainment.

AutoPilot: Automating SoC Design Space Exploration for SWaP Constrained Autonomous UAVs

no code implementations5 Feb 2021 Srivatsan Krishnan, Zishen Wan, Kshitij Bhardwaj, Paul Whatmough, Aleksandra Faust, Sabrina Neuman, Gu-Yeon Wei, David Brooks, Vijay Janapa Reddi

Balancing a computing system for a UAV requires considering both the cyber (e. g., sensor rate, compute performance) and physical (e. g., payload weight) characteristics that affect overall performance.

Bayesian Optimization BIG-bench Machine Learning +1

Tabula: Efficiently Computing Nonlinear Activation Functions for Private Neural Network Inference

1 code implementation29 Sep 2021 Max Lam, Michael Mitzenmacher, Vijay Janapa Reddi, Gu-Yeon Wei, David Brooks

Multiparty computation approaches to private neural network inference require significant communication between server and client, incur tremendous runtime penalties, and cost massive storage overheads.

Tabula: Efficiently Computing Nonlinear Activation Functions for Secure Neural Network Inference

no code implementations5 Mar 2022 Maximilian Lam, Michael Mitzenmacher, Vijay Janapa Reddi, Gu-Yeon Wei, David Brooks

Multiparty computation approaches to secure neural network inference traditionally rely on garbled circuits for securely executing nonlinear activation functions.

BioSimulators: a central registry of simulation engines and services for recommending specific tools

no code implementations13 Mar 2022 Bilal Shaikh, Lucian P. Smith, Dan Vasilescu, Gnaneswara Marupilla, Michael Wilson, Eran Agmon, Henry Agnew, Steven S. Andrews, Azraf Anwar, Moritz E. Beber, Frank T. Bergmann, David Brooks, Lutz Brusch, Laurence Calzone, Kiri Choi, Joshua Cooper, John Detloff, Brian Drawert, Michel Dumontier, G. Bard Ermentrout, James R. Faeder, Andrew P. Freiburger, Fabian Fröhlich, Akira Funahashi, Alan Garny, John H. Gennari, Padraig Gleeson, Anne Goelzer, Zachary Haiman, Joseph L. Hellerstein, Stefan Hoops, Jon C. Ison, Diego Jahn, Henry V. Jakubowski, Ryann Jordan, Matúš Kalaš, Matthias König, Wolfram Liebermeister, Synchon Mandal, Robert McDougal, J. Kyle Medley, Pedro Mendes, Robert Müller, Chris J. Myers, Aurelien Naldi, Tung V. N. Nguyen, David P. Nickerson, Brett G. Olivier, Drashti Patoliya, Loïc Paulevé, Linda R. Petzold, Ankita Priya, Anand K. Rampadarath, Johann M. Rohwer, Ali S. Saglam, Dilawar Singh, Ankur Sinha, Jacky Snoep, Hugh Sorby, Ryan Spangler, Jörn Starruß, Payton J. Thomas, David van Niekerk, Daniel Weindl, Fengkai Zhang, Anna Zhukova, Arthur P. Goldberg, Michael L. Blinov, Herbert M. Sauro, Ion I. Moraru, Jonathan R. Karr

To help investigators find and use simulation tools, we developed BioSimulators (https://biosimulators. org), a central registry of the capabilities of simulation tools and consistent Python, command-line, and containerized interfaces to each version of each tool.

SpeedLimit: Neural Architecture Search for Quantized Transformer Models

no code implementations25 Sep 2022 Yuji Chai, Luke Bailey, Yunho Jin, Matthew Karle, Glenn G. Ko, David Brooks, Gu-Yeon Wei, H. T. Kung

While research in the field of transformer models has primarily focused on enhancing performance metrics such as accuracy and perplexity, practical applications in industry often necessitate a rigorous consideration of inference latency constraints.

Neural Architecture Search Quantization +1

Architectural Implications of Embedding Dimension during GCN on CPU and GPU

no code implementations1 Dec 2022 Matthew Adiletta, David Brooks, Gu-Yeon Wei

Graph Neural Networks (GNNs) are a class of neural networks designed to extract information from the graphical structure of data.

Graph Learning

PerfSAGE: Generalized Inference Performance Predictor for Arbitrary Deep Learning Models on Edge Devices

no code implementations26 Jan 2023 Yuji Chai, Devashree Tripathy, Chuteng Zhou, Dibakar Gope, Igor Fedorov, Ramon Matas, David Brooks, Gu-Yeon Wei, Paul Whatmough

The ability to accurately predict deep neural network (DNN) inference performance metrics, such as latency, power, and memory footprint, for an arbitrary DNN on a target hardware platform is essential to the design of DNN based models.

GPU-based Private Information Retrieval for On-Device Machine Learning Inference

1 code implementation26 Jan 2023 Maximilian Lam, Jeff Johnson, Wenjie Xiong, Kiwan Maeng, Udit Gupta, Yang Li, Liangzhen Lai, Ilias Leontiadis, Minsoo Rhu, Hsien-Hsin S. Lee, Vijay Janapa Reddi, Gu-Yeon Wei, David Brooks, G. Edward Suh

Together, for various on-device ML applications such as recommendation and language modeling, our system on a single V100 GPU can serve up to $100, 000$ queries per second -- a $>100 \times$ throughput improvement over a CPU-based baseline -- while maintaining model accuracy.

Information Retrieval Language Modelling +1

MP-Rec: Hardware-Software Co-Design to Enable Multi-Path Recommendation

no code implementations21 Feb 2023 Samuel Hsia, Udit Gupta, Bilge Acun, Newsha Ardalani, Pan Zhong, Gu-Yeon Wei, David Brooks, Carole-Jean Wu

Based on our characterization of various embedding representations, we propose a hybrid embedding representation that achieves higher quality embeddings at the cost of increased memory and compute requirements.

Recommendation Systems

CAMEL: Co-Designing AI Models and Embedded DRAMs for Efficient On-Device Learning

no code implementations4 May 2023 Sai Qian Zhang, Thierry Tambe, Nestor Cuevas, Gu-Yeon Wei, David Brooks

To minimize the occurrence of expensive eDRAM refresh operations, it is beneficial to shorten the lifetime of stored data during the training process.

INT2.1: Towards Fine-Tunable Quantized Large Language Models with Error Correction through Low-Rank Adaptation

1 code implementation13 Jun 2023 Yuji Chai, John Gkountouras, Glenn G. Ko, David Brooks, Gu-Yeon Wei

We introduce a method that dramatically reduces fine-tuning VRAM requirements and rectifies quantization errors in quantized Large Language Models.

Language Modelling Large Language Model +1

Guess & Sketch: Language Model Guided Transpilation

no code implementations25 Sep 2023 Celine Lee, Abdulrahman Mahmoud, Michal Kurek, Simone Campanoni, David Brooks, Stephen Chong, Gu-Yeon Wei, Alexander M. Rush

In this work, we leverage the strengths of LMs and symbolic solvers in a neurosymbolic approach to learned transpilation for assembly code.

Language Modelling Translation

Hardware Resilience Properties of Text-Guided Image Classifiers

1 code implementation NeurIPS 2023 Syed Talal Wasim, Kabila Haile Soboka, Abdulrahman Mahmoud, Salman Khan, David Brooks, Gu-Yeon Wei

This paper presents a novel method to enhance the reliability of image classification models during deployment in the face of transient hardware errors.

Classification Image Classification

Generative AI Beyond LLMs: System Implications of Multi-Modal Generation

no code implementations22 Dec 2023 Alicia Golden, Samuel Hsia, Fei Sun, Bilge Acun, Basil Hosmer, Yejin Lee, Zachary DeVito, Jeff Johnson, Gu-Yeon Wei, David Brooks, Carole-Jean Wu

As the development of large-scale Generative AI models evolve beyond text (1D) generation to include image (2D) and video (3D) generation, processing spatial and temporal information presents unique challenges to quality, performance, and efficiency.

Cannot find the paper you are looking for? You can Submit a new open access paper.