13 citations · 51 across the 19 of their papers we have counts for
19 papers
MAD Max Beyond Single-Node: Enabling Large Machine Learning Model Acceleration on Distributed Systems
Samuel Hsia, Alicia Golden, Bilge Acun +5
Training and deploying large-scale machine learning models is time-consuming, requires significant distributed computing infrastructures, and incurs high operational costs. Our ana…
Guess & Sketch: Language Model Guided Transpilation
Celine Lee, Abdulrahman Mahmoud, Michal Kurek +5
Maintaining legacy software requires many software and systems engineering hours. Assembly code programs, which demand low-level control over the computer machine state and have no…
INT2.1: Towards Fine-Tunable Quantized Large Language Models with Error Correction through Low-Rank Adaptation
Yuji Chai, John Gkountouras, Glenn G. Ko +2
We introduce a method that dramatically reduces fine-tuning VRAM requirements and rectifies quantization errors in quantized Large Language Models. First, we develop an extremely m…
S: Increasing GPU Utilization during Generative Inference for Higher Throughput
Yunho Jin, Chun-Feng Wu, David Brooks +1
Generating texts with a large language model (LLM) consumes massive amounts of memory. Apart from the already-large model parameters, the key/value (KV) cache that holds informatio…
Design Space Exploration and Optimization for Carbon-Efficient Extended Reality Systems
Mariam Elgamal, Doug Carmean, Elnaz Ansari +8
As computing hardware becomes more specialized, designing environmentally sustainable computing systems requires accounting for both hardware and software parameters. Our goal is t…
MP-Rec: Hardware-Software Co-Design to Enable Multi-Path Recommendation
Samuel Hsia, Udit Gupta, Bilge Acun +5
Deep learning recommendation systems serve personalized content under diverse tail-latency targets and input-query loads. In order to do so, state-of-the-art recommendation models…
PerfSAGE: Generalized Inference Performance Predictor for Arbitrary Deep Learning Models on Edge Devices
Yuji Chai, Devashree Tripathy, Chuteng Zhou +6
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 p…
GPU-based Private Information Retrieval for On-Device Machine Learning Inference
Maximilian Lam, Jeff Johnson, Wenjie Xiong +11
On-device machine learning (ML) inference can enable the use of private user data on user devices without revealing them to remote servers. However, a pure on-device solution to pr…
Architectural Implications of Embedding Dimension during GCN on CPU and GPU
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 Convolutional Networks (GCNs) are a widely u…
SpeedLimit: Neural Architecture Search for Quantized Transformer Models
Yuji Chai, Luke Bailey, Yunho Jin +5
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 n…
Impala: Low-Latency, Communication-Efficient Private Deep Learning Inference
Woo-Seok Choi, Brandon Reagen, Gu-Yeon Wei +1
This paper proposes Impala, a new cryptographic protocol for private inference in the client-cloud setting. Impala builds upon recent solutions that combine the complementary stren…
Tabula: Efficiently Computing Nonlinear Activation Functions for Secure Neural Network Inference
Maximilian Lam, Michael Mitzenmacher, Vijay Janapa Reddi +2
Multiparty computation approaches to secure neural network inference commonly rely on garbled circuits for securely executing nonlinear activation functions. However, garbled circu…
Early DSE and Automatic Generation of Coarse Grained Merged Accelerators
Iulian Brumar, Georgios Zacharopoulos, Yuan Yao +3
Post-Moore's law area-constrained systems rely on accelerators to deliver performance enhancements. Coarse grained accelerators can offer substantial domain acceleration, but manua…
Boost Neural Networks by Checkpoints
Feng Wang, Guoyizhe Wei, Qiao Liu +3
Training multiple deep neural networks (DNNs) and averaging their outputs is a simple way to improve the predictive performance. Nevertheless, the multiplied training cost prevents…
Quantifying and Maximizing the Benefits of Back-End Noise Adaption on Attention-Based Speech Recognition Models
Coleman Hooper, Thierry Tambe, Gu-Yeon Wei
This work analyzes how attention-based Bidirectional Long Short-Term Memory (BLSTM) models adapt to noise-augmented speech. We identify crucial components for noise adaptation in B…
EdgeBERT: Sentence-Level Energy Optimizations for Latency-Aware Multi-Task NLP Inference
Thierry Tambe, Coleman Hooper, Lillian Pentecost +8
Transformer-based language models such as BERT provide significant accuracy improvement for a multitude of natural language processing (NLP) tasks. However, their hefty computation…
Learning Low-Rank Approximation for CNNs
Dongsoo Lee, Se Jung Kwon, Byeongwook Kim +1
Low-rank approximation is an effective model compression technique to not only reduce parameter storage requirements, but to also reduce computations. For convolutional neural netw…
Network Pruning for Low-Rank Binary Indexing
Dongsoo Lee, Se Jung Kwon, Byeongwook Kim +2
Pruning is an efficient model compression technique to remove redundancy in the connectivity of deep neural networks (DNNs). Computations using sparse matrices obtained by pruning…
Structured Compression by Weight Encryption for Unstructured Pruning and Quantization
Se Jung Kwon, Dongsoo Lee, Byeongwook Kim +3
Model compression techniques, such as pruning and quantization, are becoming increasingly important to reduce the memory footprints and the amount of computations. Despite model si…