Inference using deep neural networks on mobile devices has been an active area of research in recent years. The design of a deep learning inference framework targeted for mobile devices needs to consider various factors, such as the limited computational capacity of the devices, low power budget, varied memory access methods, and I/O bus bandwidth governed by the underlying processor's architecture. Furthermore, integrating an inference framework with time-sensitive applications - such as games and video-based software to perform tasks like ray tracing denoising and video processing - introduces the need to minimize data movement between processors and increase data locality in the target processor. In this paper, we propose Shader Neural Network (ShaderNN), an OpenGL-based, fast, and power-efficient inference framework designed for mobile devices to address these challenges. Our contributions include the following: (1) the texture-based input/output provides an efficient, zero-copy integration with real-time graphics pipelines or image processing applications, thereby saving expensive data transfers between CPU and GPU, which are unavoidable in most existing inference engines; (2) we are the first to leverage fragment shaders based on the OpenGL backend in neural network inference operators, which has an advantage in deploying parametrically small neural network models; (3) a hybrid implementation of the compute shader and fragment shader is proposed that enables layer-level shader selection to boost performance; and (4) we utilize OpenGL features - such as normalization, interpolation and texture padding - to improve performance. Experiments illustrate the favorable performance of ShaderNN over other popular on-device deep learning frameworks such as TensorFlow-Lite on the latest mobile devices powered by Qualcomm and MediaTek chips. A case study further demonstrates the usability and integration of the ShaderNN framework with a media processing Android application seamlessly. ShaderNN is available open source at Github (https://github.com/inferenceengine/shadernn).

Supersampling has proven highly effective in enhancing visual fidelity by reducing aliasing, increasing resolution, and generating interpolated frames. It has become a standard component of modern real-time rendering pipelines. However, on mobile platforms, deep learning-based supersampling methods remain impractical due to stringent hardware constraints, while non-neural supersampling techniques often fall short in delivering perceptually high-quality results. In particular, producing visually pleasing reconstructions and temporally coherent interpolations is still a significant challenge in mobile settings. In this work, we present a novel, lightweight supersampling framework tailored for mobile devices. Our approach substantially improves both image reconstruction quality and temporal consistency while maintaining real-time performance. For super-resolution, we propose an intra-pixel object coverage estimation method for reconstructing high-quality anti-aliased pixels in edge regions, a gradient-guided strategy for non-edge areas, and a temporal sample accumulation approach to improve overall image quality. For frame interpolation, we develop an efficient motion estimation module coupled with a lightweight fusion scheme that integrates both estimated optical flow and rendered motion vectors, enabling temporally coherent interpolation of object dynamics and lighting variations. Extensive experiments demonstrate that our method consistently outperforms existing baselines in both perceptual image quality and temporal smoothness, while maintaining real-time performance on mobile GPUs. A demo application and supplementary materials are available on the project page.

In this paper, we address the issue of how to enhance the generalization performance of convolutional neural networks (CNN) in the early learning stage for image classification. This is motivated by real-time applications that require the generalization performance of CNN to be satisfactory within limited training time. In order to achieve this, a novel hierarchical transfer CNN framework is proposed. It consists of a group of shallow CNNs and a cloud CNN, where the shallow CNNs are trained firstly and then the first layers of the trained shallow CNNs are used to initialize the first layer of the cloud CNN. This method will boost the generalization performance of the cloud CNN significantly, especially during the early stage of training. Experiments using CIFAR-10 and ImageNet datasets are performed to examine the proposed method. Results demonstrate the improvement of testing accuracy is 12% on average and as much as 20% for the CIFAR-10 case while 5% testing accuracy improvement for the ImageNet case during the early stage of learning. It is also shown that universal improvements of testing accuracy are obtained across different settings of dropout and number of shallow CNNs.

High Performance Computing (HPC) has been a dominated technology used in seismic data processing at the petroleum industry. However, with the increasing data size and varieties, traditional HPC focusing on computation meets new challenges. Researchers are looking for new computing platforms with a balance of both performance and productivity, as well as featured with big data analytics capability. Apache Spark is a new big data analytics platform that supports more than map/reduce parallel execution mode with good scalability and fault tolerance. In this paper, we try to answer the question that if Apache Spark is scalable to process seismic data with its in-memory computation and data locality features. We use a few typical seismic data processing algorithms to study the performance and productivity. Our contributions include customized seismic data distributions in Spark, extraction of commonly used templates for seismic data processing algorithms, and performance analysis of several typical seismic processing algorithms.

The fast growing data volume poses significant challenges as well as opportunities to research and industry. Data scientists and domain experts demand high productive and high-performance data analytics platform, which will alleviate their work, tackle these challenges, and find more opportunities from data. The objective of our research is to build such a productive data analytics cloud platform by integrating a variety of data analytics tools and packages with a high-level workflow interface. Data scientists and domain experts are able to use the platform to process both big text and binary data with an interactive/batch/workflow interface to design their own applications in processing, analyzing, and visualizing data. In this paper, we present the current status of our big data analytics cloud at PVAMU as well as our research plan for future work. The usability and performance are main characteristics of this platform.