S
Shubhabrata Sengupta
Researcher at University of California, Davis
Publications - 25
Citations - 2146
Shubhabrata Sengupta is an academic researcher from University of California, Davis. The author has contributed to research in topics: Data structure & Graphics hardware. The author has an hindex of 15, co-authored 25 publications receiving 2087 citations. Previous affiliations of Shubhabrata Sengupta include Baidu & Nvidia.
Papers
More filters
Patent
Systems and methods for a multi-core optimized recurrent neural network
Gregory Diamos,Awni Hannun,Bryan Catanzaro,Dario Amodei,Erich Elsen,Jesse Engel,Shubhabrata Sengupta +6 more
TL;DR: In this article, a multi-core optimized Recurrent Neural Network (RNN) architecture is proposed for speech recognition using the Multi-Bulk-Synchronous-Parallel (MBSP) model.
Patent
System, method, and computer program product for grouping linearly ordered primitives
TL;DR: In this article, a system, method, and computer program product are provided for grouping linearly ordered primitives, and at least one intersection query is performed, utilizing the grouping, and a plurality of primitives are grouped.
Patent
System, method, and computer program product for converting a scan algorithm to a segmented scan algorithm in an operator-independent manner
TL;DR: In this article, a system, method, and computer program product are provided for converting a scan algorithm to a segmented scan algorithm in an operator independent manner, using a limit index data structure.
Patent
System, method, and computer program product for converting a reduction algorithm to a segmented reduction algorithm
TL;DR: In this paper, a system, method, and computer program product are provided for converting a reduction algorithm to a segmented reduction algorithm, and the segmented algorithm is performed to produce an output.
Efficient primitives and algorithms for many-core architectures
TL;DR: This dissertation describes a library, CUDA Data Parallel Primitives Library (CUDPP), of building blocks called primitives for efficiently solving a broad range of problems on the GPU, and shows how sort is used to develop the first efficient algorithm for building spatial hierarchies on theGPU, thus showing how building spatial hierarchy is, in essence, sorting in three dimensions.