Zobrazeno 1 - 10
of 47
pro vyhledávání: '"Sen, Rathijit"'
Autor:
Zhu, Yiwen, Tian, Yuanyuan, Cahoon, Joyce, Krishnan, Subru, Agarwal, Ankita, Alotaibi, Rana, Camacho-Rodríguez, Jesús, Chundatt, Bibin, Chung, Andrew, Dutta, Niharika, Fogarty, Andrew, Gruenheid, Anja, Haynes, Brandon, Interlandi, Matteo, Iyer, Minu, Jurgens, Nick, Khushalani, Sumeet, Kroth, Brian, Kumar, Manoj, Leeka, Jyoti, Matusevych, Sergiy, Mittal, Minni, Mueller, Andreas, Muthyala, Kartheek, Nagulapalli, Harsha, Park, Yoonjae, Patel, Hiren, Pavlenko, Anna, Poppe, Olga, Ravindran, Santhosh, Saur, Karla, Sen, Rathijit, Suh, Steve, Tarafdar, Arijit, Waghray, Kunal, Wang, Demin, Curino, Carlo, Ramakrishnan, Raghu
Modern cloud has turned data services into easily accessible commodities. With just a few clicks, users are now able to access a catalog of data processing systems for a wide range of tasks. However, the cloud brings in both complexity and opportunit
Externí odkaz:
http://arxiv.org/abs/2405.01813
Publikováno v:
VLDB 2023
Although dominant for tabular data, ML libraries that train tree models over normalized databases (e.g., LightGBM, XGBoost) require the data to be denormalized as a single table, materialized, and exported. This process is not scalable, slow, and pos
Externí odkaz:
http://arxiv.org/abs/2307.00422
The dynamic nature of resource allocation and runtime conditions on Cloud can result in high variability in a job's runtime across multiple iterations, leading to a poor experience. Identifying the sources of such variation and being able to predict
Externí odkaz:
http://arxiv.org/abs/2304.03424
GPUs offer massive compute parallelism and high-bandwidth memory accesses. GPU database systems seek to exploit those capabilities to accelerate data analytics. Although modern GPUs have more resources (e.g., higher DRAM bandwidth) than ever before,
Externí odkaz:
http://arxiv.org/abs/2302.00734
Autor:
Gandhi, Apurva, Asada, Yuki, Fu, Victor, Gemawat, Advitya, Zhang, Lihao, Sen, Rathijit, Curino, Carlo, Camacho-Rodríguez, Jesús, Interlandi, Matteo
Database engines have historically absorbed many of the innovations in data processing, adding features to process graph data, XML, object oriented, and text among many others. In this paper, we make the case that it is time to do the same for AI --
Externí odkaz:
http://arxiv.org/abs/2211.02753
Autor:
Asada, Yuki, Fu, Victor, Gandhi, Apurva, Gemawat, Advitya, Zhang, Lihao, He, Dong, Gupta, Vivek, Nosakhare, Ehi, Banda, Dalitso, Sen, Rathijit, Interlandi, Matteo
Publikováno v:
PVLDB, 15(12): 3598 - 3601, 2022
We demonstrate Tensor Query Processor (TQP): a query processor that automatically compiles relational operators into tensor programs. By leveraging tensor runtimes such as PyTorch, TQP is able to: (1) integrate with ML tools (e.g., Pandas for data in
Externí odkaz:
http://arxiv.org/abs/2209.04579
Autor:
Park, Kwanghyun, Saur, Karla, Banda, Dalitso, Sen, Rathijit, Interlandi, Matteo, Karanasos, Konstantinos
Prediction queries are widely used across industries to perform advanced analytics and draw insights from data. They include a data processing part (e.g., for joining, filtering, cleaning, featurizing the datasets) and a machine learning (ML) part in
Externí odkaz:
http://arxiv.org/abs/2206.00136
Autor:
He, Dong, Nakandala, Supun, Banda, Dalitso, Sen, Rathijit, Saur, Karla, Park, Kwanghyun, Curino, Carlo, Camacho-Rodríguez, Jesús, Karanasos, Konstantinos, Interlandi, Matteo
Publikováno v:
Proceedings of the VLDB Endowment, 15(11): 2811 - 2825, 2022
The huge demand for computation in artificial intelligence (AI) is driving unparalleled investments in hardware and software systems for AI. This leads to an explosion in the number of specialized hardware devices, which are now offered by major clou
Externí odkaz:
http://arxiv.org/abs/2203.01877
Computer architecture design space is vast and complex. Tools are needed to explore new ideas and gain insights quickly, with low efforts and at a desired accuracy. We propose Calipers, a criticality-based framework to model key abstractions of compl
Externí odkaz:
http://arxiv.org/abs/2201.05884
We present an efficient, parametric modeling framework for predictive resource allocations, focusing on the amount of computational resources, that can optimize for a range of price-performance objectives for data analytics in serverless query proces
Externí odkaz:
http://arxiv.org/abs/2112.08572