Search Results - "Cowan, Meghan"

Automated Generation of Domain Specific Kernels by Cowan, Meghan

“…Seamless gains in performance from technology scaling is coming to an end, but many applications rely on hardware and their compilation stacks to continue…”
Get full text

Towards a Standardized Representation for Deep Learning Collective Algorithms by Yoo, Jinsun, Won, William, Cowan, Meghan, Jiang, Nan, Klenk, Benjamin, Sridharan, Srinivas, Krishna, Tushar

“…The explosion of machine learning model size has led to its execution on distributed clusters at a very large scale. Many works have tried to optimize the…”
Get full text

Towards a Standardized Representation for Deep Learning Collective Algorithms by Yoo, Jinsun, Won, William, Cowan, Meghan, Jiang, Nan, Klenk, Benjamin, Sridharan, Srinivas, Krishna, Tushar

“…The explosion of machine learning model size has led to its execution on distributed clusters at a very large scale. Many works have tried to optimize the…”
Get full text

GC3: An Optimizing Compiler for GPU Collective Communication by Cowan, Meghan, Maleki, Saeed, Musuvathi, Madanlal, Saarikivi, Olli, Xiong, Yifan

“…Machine learning models made up of millions or billions of parameters are trained and served on large multi-GPU systems. As models grow in size and execute on…”
Get full text

SoK: Opportunities for Software-Hardware-Security Codesign for Next Generation Secure Computing by Dangwal, Deeksha, Cowan, Meghan, Alaghi, Armin, Lee, Vincent T, Reagen, Brandon, Trippel, Caroline

“…Users are demanding increased data security. As a result, security is rapidly becoming a first-order design constraint in next generation computing systems…”
Get full text

Porcupine: A Synthesizing Compiler for Vectorized Homomorphic Encryption by Cowan, Meghan, Dangwal, Deeksha, Alaghi, Armin, Trippel, Caroline, Lee, Vincent T, Reagen, Brandon

“…Homomorphic encryption (HE) is a privacy-preserving technique that enables computation directly on encrypted data. Despite its promise, HE has seen limited use…”
Get full text

TACCL: Guiding Collective Algorithm Synthesis using Communication Sketches by Shah, Aashaka, Chidambaram, Vijay, Cowan, Meghan, Maleki, Saeed, Musuvathi, Madan, Mytkowicz, Todd, Nelson, Jacob, Saarikivi, Olli, Singh, Rachee

“…Machine learning models are increasingly being trained across multiple GPUs and servers. In this setting, data is transferred between GPUs using communication…”
Get full text

Automating Generation of Low Precision Deep Learning Operators by Cowan, Meghan, Moreau, Thierry, Chen, Tianqi, Ceze, Luis

“…State of the art deep learning models have made steady progress in the fields of computer vision and natural language processing, at the expense of growing…”
Get full text

Exploring computation-communication tradeoffs in camera systems by Mazumdar, Amrita, Moreau, Thierry, Sung Kim, Cowan, Meghan, Alaghi, Armin, Ceze, Luis, Oskin, Mark, Sathe, Visvesh

“…Cameras are the defacto sensor. The growing demand for real-time and low-power computer vision, coupled with trends towards high-efficiency heterogeneous…”
Get full text

Analysis and Mitigations of Reverse Engineering Attacks on Local Feature Descriptors by Dangwal, Deeksha, Lee, Vincent T, Kim, Hyo Jin, Shen, Tianwei, Cowan, Meghan, Shah, Rajvi, Trippel, Caroline, Reagen, Brandon, Sherwood, Timothy, Balntas, Vasileios, Alaghi, Armin, Ilg, Eddy

“…As autonomous driving and augmented reality evolve, a practical concern is data privacy. In particular, these applications rely on localization based on user…”
Get full text

Exploring Computation-Communication Tradeoffs in Camera Systems by Mazumdar, Amrita, Moreau, Thierry, Kim, Sung, Cowan, Meghan, Alaghi, Armin, Ceze, Luis, Oskin, Mark, Sathe, Visvesh

“…2017 IEEE International Symposium on Workload Characterization (IISWC) Cameras are the defacto sensor. The growing demand for real-time and low-power computer…”
Get full text

TVM: An Automated End-to-End Optimizing Compiler for Deep Learning by Chen, Tianqi, Moreau, Thierry, Jiang, Ziheng, Zheng, Lianmin, Yan, Eddie, Cowan, Meghan, Shen, Haichen, Wang, Leyuan, Hu, Yuwei, Ceze, Luis, Guestrin, Carlos, Krishnamurthy, Arvind

“…There is an increasing need to bring machine learning to a wide diversity of hardware devices. Current frameworks rely on vendor-specific operator libraries…”
Get full text