Výsledky vyhledávání - "Zheng, Bojian"

Report

Hidet: Task-Mapping Programming Paradigm for Deep Learning Tensor Programs

Autor: Ding, Yaoyao, Yu, Cody Hao, Zheng, Bojian, Liu, Yizhi, Wang, Yida, Pekhimenko, Gennady

Publikováno v: ASPLOS 2023: Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2, January 2023, Pages 370-384

As deep learning models nowadays are widely adopted by both cloud services and edge devices, reducing the latency of deep learning model inferences becomes crucial to provide efficient model serving. However, it is challenging to develop efficient te

Externí odkaz: http://arxiv.org/abs/2210.09603

Zobrazit plný text záznamu

Report

Tempo: Accelerating Transformer-Based Model Training through Memory Footprint Reduction

Autor: Andoorveedu, Muralidhar, Zhu, Zhanda, Zheng, Bojian, Pekhimenko, Gennady

Training deep learning models can be computationally expensive. Prior works have shown that increasing the batch size can potentially lead to better overall throughput. However, the batch size is frequently limited by the accelerator memory capacity

Externí odkaz: http://arxiv.org/abs/2210.10246

Zobrazit plný text záznamu

Report

Automatic Horizontal Fusion for GPU Kernels

Autor: Li, Ao, Zheng, Bojian, Pekhimenko, Gennady, Long, Fan

We present automatic horizontal fusion, a novel optimization technique that complements the standard kernel fusion techniques for GPU programs. Unlike the standard fusion, whose goal is to eliminate intermediate data round trips, our horizontal fusio

Externí odkaz: http://arxiv.org/abs/2007.01277

Zobrazit plný text záznamu

Report

Echo: Compiler-based GPU Memory Footprint Reduction for LSTM RNN Training

Autor: Zheng, Bojian, Tiwari, Abhishek, Vijaykumar, Nandita, Pekhimenko, Gennady

The Long-Short-Term-Memory Recurrent Neural Networks (LSTM RNNs) are a popular class of machine learning models for analyzing sequential data. Their training on modern GPUs, however, is limited by the GPU memory capacity. Our profiling results of the

Externí odkaz: http://arxiv.org/abs/1805.08899

Zobrazit plný text záznamu

Report

TBD: Benchmarking and Analyzing Deep Neural Network Training

Autor: Zhu, Hongyu, Akrout, Mohamed, Zheng, Bojian, Pelegris, Andrew, Phanishayee, Amar, Schroeder, Bianca, Pekhimenko, Gennady

The recent popularity of deep neural networks (DNNs) has generated a lot of research interest in performing DNN-related computation efficiently. However, the primary focus is usually very narrow and limited to (i) inference -- i.e. how to efficiently

Externí odkaz: http://arxiv.org/abs/1803.06905

Zobrazit plný text záznamu

A prospective study of rotavirus infections

Autor: Zheng, Bojian.

Publikováno v: View the Table of Contents & Abstract..

Thesis (Ph. D.)--University of Hong Kong, 1994.
Includes bibliographical references (leaves 249-266).

Externí odkaz: http://sunzi.lib.hku.hk/hkuto/record.jsp?B19671672

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání