#  Presentations 

 



 



  Search Within Results  

  Search Within Results search  

##  4 results 

  Show filters filter\_alt    Sort by Year of PublicationAlphabetical A-Z sort



 

##  4 results 

  Download 4 citations  download- [BibTeX](/node/1575576/export?format=bibtex)
- [EndNote X3 XML](/node/1575576/export?format=endnote8)
- [EndNote 7 XML](/node/1575576/export?format=endnote7)
- [Endnote tagged](/node/1575576/export?format=tagged)
- [Marc](/node/1575576/export?format=marc)
- [PubMedId](/node/1575576/export?format=pubmed_id)
- [RIS](/node/1575576/export?format=ris)
 


 

### 2022

2022. “[RecPipe: Co-Designing Models and HW to Jointly Optimize Recommendation Quality and Performance](/presentations/recpipe-co-designing-models-and-hw-jointly-optimize-recommendation-quality)”



 

 

2022. “[RecPipe: Co-Designing Models and HW to Jointly Optimize Recommendation Quality and Performance](/presentations/recpipe-co-designing-models-and-hw-jointly-optimize-recommendation-quality)”



 

 

 

- add\_circle\_outline do\_not\_disturb\_on Abstract
 


 

 Deep learning recommendation systems must provide high quality, personalized content under strict tail-latency targets and high system loads. This paper presents RecPipe, a system to jointly optimize recommendation quality and inference performance...



 

 

 

2022. “[Chasing Carbon: The Elusive Environmental Footprint of Computing ](/presentations/chasing-carbon-elusive-environmental-footprint-computing)”



 

 

2022. “[Chasing Carbon: The Elusive Environmental Footprint of Computing ](/presentations/chasing-carbon-elusive-environmental-footprint-computing)”



 

 

 

- add\_circle\_outline do\_not\_disturb\_on Abstract
 


 

 Given recent algorithm, software, and hardware innovation, computing has enabled a plethora of new applications. As computing becomes increasingly ubiquitous, however, so does its environmental impact. This paper brings the issue to the attention of...



 

 

 

 



### 2021

2021. “[A 16nm SoC for Noise-Robust Speech Recognition via Bayesian Denoising and Attention-Based DNNs.](/presentations/16nm-soc-noise-robust-speech-recognition-bayesian-denoising-and-attention)”



 

 

2021. “[A 16nm SoC for Noise-Robust Speech Recognition via Bayesian Denoising and Attention-Based DNNs.](/presentations/16nm-soc-noise-robust-speech-recognition-bayesian-denoising-and-attention)”



 

 

 

- add\_circle\_outline do\_not\_disturb\_on Abstract
 


 

 This work presents a 16nm SoC that executes a full speech-enhancing ASR pipeline in hardware, with the following key contributions: 1) unsupervised speech denoising using a Markov Source Separation Engine (MSSE) and 2) a reconfigurable accelerator...



 

 

 

2021. “[Cross-Stack Workload Characterization of Deep Recommendation Systems](/presentations/cross-stack-workload-characterization-deep-recommendation-systems)”



 

 

2021. “[Cross-Stack Workload Characterization of Deep Recommendation Systems](/presentations/cross-stack-workload-characterization-deep-recommendation-systems)”



 

 

 

- add\_circle\_outline do\_not\_disturb\_on Abstract
 


 

 Authors: Samuel Hsia, Udit Gupta, Mark Wilkening, Carole-Jean Wu , Gu-Yeon Wei, David Brooks

 Abstract: Deep learning based recommendation systems form the backbone of most personalized cloud services. Though the computer architecture community has...