Efficient Processing of Image Processing Applications on CPU/GPU

Abstract

Heterogeneous systems have gained popularity due to the rapid growth in data and the need for processing this big data to extract useful information. In recent years, many healthcare applications have been developed which use machine learning algorithms to perform tasks such as image classification, object detection, image segmentation, and instance segmentation. The increasing amount of big visual data requires images to be processed efficiently. It is common that we use heterogeneous systems for such type of applications, as processing a huge number of images on a single PC may take months of computation. In heterogeneous systems, data are distributed on different nodes in the system. However, heterogeneous systems do not distribute images based on the computing capabilities of different types of processors in the node; therefore, a slow processor may take much longer to process an image compared to a faster processor. This imbalanced workload distribution observed in heterogeneous systems for image processing applications is the main cause of inefficient execution. In this paper, an efficient workload distribution mechanism for image processing applications is introduced. The proposed approach consists of two phases. In the first phase, image data are divided into an ideal split size and distributed amongst nodes, and in the second phase, image data are further distributed between CPU and GPU according to their computation speeds. Java bindings for OpenCL are used to configure both the CPU and GPU to execute the program. The results have demonstrated that the proposed workload distribution policy efficiently distributes the images in a heterogeneous system for image processing applications and achieves 50% improvements compared to the current state-of-the-art programming frameworks.

RETRACTED: Mixed-mode database miner classifier: Parallel computation of graphical processing unit mining

“…for scientific applications and comparison of computational speed-up and efficiency of a GPU with a CPU time. 22,23 In 2014, A.I.S Seyed uses neural networks and decision trees (including C5.0 and CHAID). It concluded that the CHAID classifier returns the best G-mean and AUC measures for top performing predictive models ranging from 76% to 85%, and 0.812 to 0.942 units, respectively.…”

Symmetric Quantile Quantizer Parameterization for the Laplacian Source: Qualification for Contemporary Quantization Solutions

“…(4) Since δ A and δ PD amount approximately less than or equal to 1% for N � 10 and N � 30, respectively, the correctness of the analysis performed for our SQQ model for small and medium bit rates is confirmed. is is of great importance since the accuracy of the asymptotic theory decreases noticeably for the classes of small or medium numbers of the quantization cells N. (5) e values of N at which relative error δ A increases steeply are in the very narrow range N ∈ [4,8]. (6) e largest relative error δ A � 3.68% occurs for the smallest observed number of levels N � 4.…”

“…A promising deployment of QNN in many contemporary approaches and artificial intelligence applications reduces the overall computational and memory cost [5]. As shown in [8], this is of great importance since the amount of data to be processed constantly grows so that more powerful hardware (CPU/GPU) is required. Moreover, the QNN approach addressed in [5] is particularly beneficial for implementing in models with the extreme memory requirements, such as mobile devices and edge devices.…”

Online Resource Allocation in Edge Computing Using Distributed Bidding Approaches

“…Thus, the small workload has a total of ≈ 800 jobs (a moderately loaded system), and the large workload a total of ≈ 1400 jobs (a congested system). Both workloads are based on [7], which details the amount of time required to perform edge detection on 1980 × 1020 images using a core i5 processor (hence the MB/s units for C i and K j ). We assume the time required scales linearly with the number of images being processed.…”