Many companies, such as Google, Facebook, and Amazon are building new specialized programming frameworks. This is because these companies need to allow their users to write simple, high-level code and run it efficiently on different hardware architectures. For example, Google has built TensorFlow, a framework for deep learning allowing users to run deep learning on multiple hardware architectures without changing the code. Our research team at NYUAD (New York University Abu Dhabi) in collaboration with MIT (Massachusetts Institute of Technology, USA), Google, and Adobe, is developing a new programming framework called Tiramisu [1]. Unlike existing frameworks, Tiramisu can perform advanced code optimizations that are hard to apply otherwise. Because of this, Tiramisu can generate fast code that outperforms highly optimized code written by expert programmers and can target different hardware architectures (multicore, GPUs, FPGAs, and distributed machines). Three projects related to Tiramisu are open to students. Building a Tiramisu Backend for a Deep Learning Accelerator The goal of this project is to build a compiler for a new deep learning hardware accelerator that is being developed at Harvard (FlexNLP). This project is a collaboration between NYUAD, MIT, and Harvard. The hardware accelerator is designed to be used to accelerate deep learning inference on mobile devices (in particular to accelerate Natural Language Processing and Speech to Text). Currently, Tiramisu is integrated into the PyTorch deep learning framework. It has a code generator that targets CPUs and GPUs. The goal of this topic is to add a new backend for the Tiramisu compiler to target FlexNLP. This backend will mainly translate the high-level PyTorch API to the equivalent FlexNLP API. Since Tiramisu is being integrated into PyTorch, the new backend will allow PyTorch users to target the FlexNLP accelerator and will allow us to co-design FlexNLP so that we get the best performance with the least amount of energy consumption. This will allow wide adoption of NLP deep learning accelerators in smartphones and embedded systems. Benefits The selected students will work on cutting edge projects with a very high practical impact on the areas of deep learning and nuclear physics (we are integrating Tiramisu in PyTorch, and in the USQCD frameworks, therefore, all future users of these frameworks will benefit from your contribution). The selected students will spend 3 months at NYUAD in Abu Dhabi and will receive a monthly salary of 2900$. Travel and VISA expenses will also be paid by NYUAD. The students will participate in writing papers and submit them to the best conferences in the field (NIPS, PLDI, ISCA, ...). The projects will include close collaboration with researchers from MIT and Harvard. Regular Skype calls will be organized with MIT and Harvard researchers. Application To apply, please send your CV and transcripts (with ranking) for the last two years and indicate when you'll be able to start. Being able to start as early as possible (after finishing your classes) is a plus. Please indicate which projects are interesting to you (it is Ok to express interest in all of them). Please also indicate any relevant technical skills that you have. Do not hesitate to ask questions by email: baghdadi@nyu.edu About NYUAD NYU Abu Dhabi is a degree-granting research university with a fully integrated liberal arts and science undergraduate program in the Arts, Sciences, Social Sciences, Humanities, and Engineering. NYU Abu Dhabi, NYU New York, and NYU Shanghai, form the backbone of NYU's global network university, an interconnected network of portal campuses and academic centers across six continents that enable seamless international mobility of students and faculty in their pursuit of academic and scholarly activity. This global university represents a transformative shift in higher education, one in which the intellectual and creative endeavors of academia are shaped and examined through an international and multicultural perspective. As a major intellectual hub at the crossroads of the Arab world, NYUAD serves as a center for scholarly thought, advanced research, knowledge creation, and sharing, through its academic, research, and creative activities. UAE Nationals are encouraged to apply. References [1] http://tiramisu-compiler.org/
|
This position is not located in the United States. You must be willing to relocate to Abu Dhabi, United Arab Emirates. For people in the EU, click here for information on your privacy rights under GDPR: www.nyu.edu/it/gdpr NYU is an equal opportunity employer committed to equity, diversity, and social inclusion. |