Clarity-Lab to host an ASPLOS 2015 tutorial entitled “Sirius: An Open End-to-End Voice and Vision Personal Assistant like Apple’s Siri, Google Now, Microsoft’s Cortana, and Amazon’s Echo”

Posted on December 30, 2014 by admin

We are excited to announce that we will host a tutorial at ASPLOS 2015 to accompany the paper and release for Sirius [1].

A Sirius Pitch:

As user demand scales for intelligent personal assistants (IPAs) such as Apple’s Siri, Google’s Google Now, and Microsoft’s Cortana, we are approaching the computational limits of current datacenter system architectures. It is an open question how future server architectures should evolve to enable this emerging class of applications, and the lack of an open representative workload is an obstacle facing our community in addressing these questions.

In this tutorial, we present the design of Sirius, an open end-to-end IPA web service application that accepts queries in the form of voice and images, and responds with natural language. We then show how this workload can be used to investigate the implications of five points in the design space of future accelerator-based server architectures spanning GPUs, manycore throughput coprocessors such as Intel Phi, and FPGAs. To investigate future server designs for Sirius, we decompose Sirius into a suite of 7 benchmarks (Sirius Suite) comprising the computationally intensive bottlenecks of Sirius. We port Sirius Suite to our five accelerator platforms and use the performance and power trade-offs across these platforms to perform a total cost of ownership (TCO) analysis of various server design points.

[1]

Johann Hauswald, Michael A. Laurenzano, Yunqi Zhang, Cheng Li, Austin Rovinski, Arjun Khurana, Ron Dreslinski, Trevor Mudge, Vinicius Petrucci, Lingjia Tang, and Jason Mars. Sirius: An Open End-to-End Voice and Vision Personal Assistant and Its Implications for Future Warehouse Scale Computers. In Proceedings of the Twentieth International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), ASPLOS ’15, New York, NY, USA, 2015. ACM. Acceptance Rate: 17% (To Appear)
[Bibtex]

@inproceedings{hauswald15asplos,
author = {Hauswald, Johann and Laurenzano, Michael A. and Zhang, Yunqi and Li, Cheng and Rovinski, Austin and Khurana, Arjun and Dreslinski, Ron and Mudge, Trevor and Petrucci, Vinicius and Tang, Lingjia and Mars, Jason},
title = {Sirius: An Open End-to-End Voice and Vision Personal Assistant and Its Implications for Future Warehouse Scale Computers},
booktitle = {Proceedings of the Twentieth International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)},
series = {ASPLOS '15},
year = {2015},
numpages = {13},
publisher = {ACM},
address = {New York, NY, USA},
note = {Acceptance Rate: 17% (To Appear)},
}

Invited Talk at Baidu and ICT

Posted on December 30, 2014 by admin

Lingjia and I have been invited to give duet talks at Baidu and ICT (Institute of Computing Technology) in Beijing China on the 22nd of December. We will be discussing Protean Code [1], SMiTe [2], and Sirius [3].

[1]

Michael Laurenzano, Yunqi Zhang, Lingjia Tang, and Jason Mars. Protean Code: Achieving Near-Free Online Code Transformations for Warehouse Scale Computers. In Proceedings of the 47th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO), MICRO-47, New York, NY, USA, 2014. ACM. Acceptance Rate: 19%
[Bibtex]

@inproceedings{laurenzano14micro,
author = {Laurenzano, Michael and Zhang, Yunqi and Tang, Lingjia and Mars, Jason},
title = {Protean Code: Achieving Near-Free Online Code Transformations for Warehouse Scale Computers},
booktitle = {Proceedings of the 47th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO)},
series = {MICRO-47},
year = {2014},
publisher = {ACM},
address = {New York, NY, USA},
note = {Acceptance Rate: 19%}
}

[2]

Yunqi Zhang, Michael Laurenzano, Jason Mars, and Lingjia Tang. SMiTe: Precise QoS Prediction on Real System SMT Processors to Improve Utilization in Warehouse Scale Computers. In Proceedings of the 47th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO), MICRO-47, New York, NY, USA, 2014. ACM. Acceptance Rate: 19%
[Bibtex]

@inproceedings{zhang14micro,
author = {Zhang, Yunqi and Laurenzano, Michael and Mars, Jason and Tang, Lingjia},
title = {SMiTe: Precise QoS Prediction on Real System SMT Processors to Improve Utilization in Warehouse Scale Computers},
booktitle = {Proceedings of the 47th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO)},
series = {MICRO-47},
year = {2014},
publisher = {ACM},
address = {New York, NY, USA},
note = {Acceptance Rate: 19%}
}

[3]

@inproceedings{hauswald15asplos,
author = {Hauswald, Johann and Laurenzano, Michael A. and Zhang, Yunqi and Li, Cheng and Rovinski, Austin and Khurana, Arjun and Dreslinski, Ron and Mudge, Trevor and Petrucci, Vinicius and Tang, Lingjia and Mars, Jason},
title = {Sirius: An Open End-to-End Voice and Vision Personal Assistant and Its Implications for Future Warehouse Scale Computers},
booktitle = {Proceedings of the Twentieth International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)},
series = {ASPLOS '15},
year = {2015},
numpages = {13},
publisher = {ACM},
address = {New York, NY, USA},
note = {Acceptance Rate: 17% (To Appear)},
}

Johann from Clarity-Lab to present Sirius paper at ASPLOS 2015!

Posted on December 30, 2014 by admin

I’m very proud of Johann Hauswald along with Vinicius Petrucci and others from Clarity-Lab for publishing the Sirius paper [1] at ASPLOS 2015. I’m also excited about the big release the team has been working feverishly on. Keep up the great work guys! The conference will be held in Istanbul, Turkey. We’ll have to start thinking about getting our VISAs in order.

[1]

@inproceedings{hauswald15asplos,
author = {Hauswald, Johann and Laurenzano, Michael A. and Zhang, Yunqi and Li, Cheng and Rovinski, Austin and Khurana, Arjun and Dreslinski, Ron and Mudge, Trevor and Petrucci, Vinicius and Tang, Lingjia and Mars, Jason},
title = {Sirius: An Open End-to-End Voice and Vision Personal Assistant and Its Implications for Future Warehouse Scale Computers},
booktitle = {Proceedings of the Twentieth International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)},
series = {ASPLOS '15},
year = {2015},
numpages = {13},
publisher = {ACM},
address = {New York, NY, USA},
note = {Acceptance Rate: 17% (To Appear)},
}

Student and postdoc from Clarity-Lab to present papers at HPCA 2015!

Posted on December 30, 2014 by admin

I’m very proud of Chang-Hong Hsu and Vinicius Petrucci from our Clarity-Lab for publishing papers [1, 2] at HPCA 2015. I’m particularly impressed with Chang-Hong as he’s only been in our group for 6 months. Keep up the great work guys! The conference will be held in San Francisco, CA.

[1]

Chang-Hong Hsu, Yunqi Zhang, Michael A. Laurenzano, David Meisner, Thomas Wenisch, Lingjia Tang, Jason Mars, and Ron Dreslinski. Adrenaline: Pinpointing and Reining in Tail Queries with Quick Voltage Boosting. In Proceedings of the 2015 IEEE 21st International Symposium on High Performance Computer Architecture (HPCA), HPCA ’15, Washington, DC, USA, 2015. IEEE Computer Society. Acceptance Rate: 22% (To Appear)
[Bibtex]

@inproceedings{hsu15hpca,
author = {Hsu, Chang-Hong and Zhang, Yunqi and Laurenzano, Michael A. and Meisner, David and Wenisch, Thomas and Tang, Lingjia and Mars, Jason and Dreslinski, Ron},
title = {Adrenaline: Pinpointing and Reining in Tail Queries with Quick Voltage Boosting},
booktitle = {Proceedings of the 2015 IEEE 21st International Symposium on High Performance Computer Architecture (HPCA)},
series = {HPCA '15},
year = {2015},
numpages = {10},
publisher = {IEEE Computer Society},
address = {Washington, DC, USA},
note = {Acceptance Rate: 22% (To Appear)},
}

[2]

Vinicius Petrucci, Michael A. Laurenzano, John Doherty, Yunqi Zhang, Daniel Mosse, Jason Mars, and Lingjia Tang. Octopus-Man: QoS-Driven Task Management for Heterogeneous Multicore in Warehouse Scale Computers. In Proceedings of the 2015 IEEE 21st International Symposium on High Performance Computer Architecture (HPCA), HPCA ’15, Washington, DC, USA, 2015. IEEE Computer Society. Acceptance Rate: 22% (To Appear)
[Bibtex]

@inproceedings{petrucci15hpca,
author = {Petrucci, Vinicius and Laurenzano, Michael A. and Doherty, John and Zhang, Yunqi and Mosse, Daniel and Mars, Jason and Tang, Lingjia },
title = {Octopus-Man: QoS-Driven Task Management for Heterogeneous Multicore in Warehouse Scale Computers},
booktitle = {Proceedings of the 2015 IEEE 21st International Symposium on High Performance Computer Architecture (HPCA)},
series = {HPCA '15},
year = {2015},
numpages = {10},
publisher = {IEEE Computer Society},
address = {Washington, DC, USA},
note = {Acceptance Rate: 22% (To Appear)},
}

Protean Code

Posted on December 15, 2014 by admin

Invited Talk at Career Workshop for Women and Minorities in Computer Architecture (w/ MICRO 2014)

Posted on December 14, 2014 by admin

I’ve been invited to speak at this year’s Career Workshop for Women and Minorities in Computer Architecture (CWWMCA) held in conjunction with MICRO 2014. It’s an honor to be presenting alongside Kunle Olukotun, Margaret Martonosi, Ruby Lee, Lingjia Tang, Natalie Enright Jerger, and John Cavazos among others. My talk is entitled “The Secrets.” In this talk, I outline the key insights I feel are most responsible for getting me to where I am today. I will also be talking about one of my most controversial ideas for the success of PhD students, namely PLP.

Invited Talk to IBM Thomas J. Watson Research Center

Posted on October 10, 2014 by admin

I’ve been invited to speak at IBM Thomas J. Watson Research Center where I delivered a lecture on Protean Code[1]. It was an absolute pleasure to meet and chat with the wonderful folks over there.

[1]

@inproceedings{laurenzano14micro,
author = {Laurenzano, Michael and Zhang, Yunqi and Tang, Lingjia and Mars, Jason},
title = {Protean Code: Achieving Near-Free Online Code Transformations for Warehouse Scale Computers},
booktitle = {Proceedings of the 47th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO)},
series = {MICRO-47},
year = {2014},
publisher = {ACM},
address = {New York, NY, USA},
note = {Acceptance Rate: 19%}
}

Two students to present papers at Micro 2014!

Posted on September 6, 2014 by admin

I’m very proud of Mike Laurenzano and Yunqi Zhang for publishing their first papers [1, 2] since joining Clarity Lab. Keep up the great work guys! The conference will be held in Cambridge, UK.

[1]

@inproceedings{laurenzano14micro,
author = {Laurenzano, Michael and Zhang, Yunqi and Tang, Lingjia and Mars, Jason},
title = {Protean Code: Achieving Near-Free Online Code Transformations for Warehouse Scale Computers},
booktitle = {Proceedings of the 47th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO)},
series = {MICRO-47},
year = {2014},
publisher = {ACM},
address = {New York, NY, USA},
note = {Acceptance Rate: 19%}
}

[2]

@inproceedings{zhang14micro,
author = {Zhang, Yunqi and Laurenzano, Michael and Mars, Jason and Tang, Lingjia},
title = {SMiTe: Precise QoS Prediction on Real System SMT Processors to Improve Utilization in Warehouse Scale Computers},
booktitle = {Proceedings of the 47th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO)},
series = {MICRO-47},
year = {2014},
publisher = {ACM},
address = {New York, NY, USA},
note = {Acceptance Rate: 19%}
}

Serving as program committee co-chair for CGO 2015

Posted on September 6, 2014 by admin

Submit your best work!

About the Conference

The International Symposium on Code Generation and Optimization (CGO) provides a premier venue to bring together researchers and practitioners working at the interface of hardware and software on a wide range of optimization and code generation techniques and related issues. The conferences spans the spectrum from purely static to fully dynamic approaches, including techniques ranging from pure software-based methods to architectural features and support.

Visit http://cgo.org for more info.