The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
We revisit the Wilson-Dirac operator, also referred as Dslash, on NUMA manycore vector machines and thereby seek an efficient supercomputing implementation. Quantum Chro- moDynamics (QCD) is the theory of the strong nuclear force and its discrete formalism is the so-called Lattice Quantum ChromoDynamics (LQCD). Wilson-Dirac is the major computing kernel in LQCD, where a special attention is paid to...
We propose a novel concept of asymmetric feature maps (AFM), which allows to evaluate multiple kernels between a query and database entries without increasing the memory requirements. To demonstrate the advantages of the AFM method, we derive a short vector image representation that, due to asymmetric feature maps, supports efficient scale and translation invariant sketch-based image retrieval. Unlike...
In this paper, we present a new methodology that provides i) a theoretical analysis of the two most commonly used approaches for effective shared cache management (i.e., cache partitioning and loop tiling) and ii) a unified framework to fine tuning those two mechanisms in tandem (not separately). Our approach manages to lower the number of main memory accesses by one order of magnitude keeping at...
This paper presents the design and implementation of a hardwired OS kernel circuitry inside a Java application processor to provide the system services that are traditionally implemented in software. The hardwired system functions in the proposed SoC include the thread manager, the memory manager, and the I/O subsystem interface. There are many advantages in making the OS kernel a hardware component,...
Convolutional neural networks (CNNs) have emerged as one of the most successful machine learning technologies for image and video processing. The most computationally-intensive parts of CNNs are the convolutional layers, which convolve multi-channel images with multiple kernels. A common approach to implementing convolutional layers is to expand the image into a column matrix (im2col) and perform...
The efficiency of datacenters is important consideration for cloud service providers to make their datacenters always ready for fulfilling the increasing demand for computing resources. Container-based virtualization is one approach to improving efficiency by reducing the overhead of virtualization. Resource overcommitment is another approach, but cloud providers tend to make conservative allocations...
This paper describes the implementation of approximate memory support in Linux operating system kernel. The new functionality allows the kernel to distinguish between normal memory banks, which are composed by standard memory cells that retain data without corruption, and approximate memory banks, where memory cells are subject to read/write faults with controlled probability. Approximate memories...
High-Level Synthesis (HLS) has been widely recognized as an efficient compilation process targeting FPGAs for algorithm evaluation and product prototyping. However, the massively parallel memory access demands and the extremely expensive cost of single-bank memory with multi-port have impeded loop pipelining performance. Thus, based on an alternative multi-bank memory architecture, a joint approach...
Deep learning is gaining popularity in the recent years due to its impressive performance in different application areas. Convolutional Neural Network (CNN) is the state-of-the-art deep learning architecture that is being used widely in the areas of image recognition, speech recognition and many other applications. CNN is computationally intensive and resource hungry architecture. Hence, its efficient...
In this paper, a novel fast support vector machine (SVM) method combining with the deep quasi-linear kernel (DQLK) learning is proposed for large scale image classification. This method can train large-scale dataset with SVM fast using less memory space and less training time. Since SVM classifiers are constructed by support vectors (SVs) that lie close to the separation boundary, removing the other...
A large number of cloud datastores have been developed to handle the cloud OLTP workload. Double caching problem where the same data resides both at the user buffer and the kernel buffer has been identified as one of the problems and has been largely solved by using direct I/O mode to bypass the kernel buffer. However, maintaining the caching layer only in user-level has the disadvantage that the...
This paper presents two approaches using a Block Low-Rank (BLR) compression technique to reduce the memory footprint and/or the time-to-solution of the sparse supernodal solver PASTIX. This flat, non-hierarchical, compression method allows to take advantage of the low-rank property of the blocks appearing during the factorization of sparse linear systems, which come from the discretization of partial...
GPUs are capable of running a variety of applications, however their generic parallel-architecture can lead to inefficient use of resources and reduced power efficiency, due to algorithmic or architectural constraints. In this work, taking inspiration from CGRAs (coarse-grained reconfigurable architectures), we demonstrate resource sharing and re-distribution as a solution that can be leveraged by...
There are various applications and operations in virtualized environments that rely on memory page stability to achieve satisfactory performance. These applications include VM live migration and memory deduplication. Unfortunately, there is a large gap between existing prediction mechanisms and actual behavior. This is the gap we hope to narrow.
Integrated CPU-GPU architecture provides excellent acceleration capabilities for data parallel applications on embedded platforms while meeting the size, weight and power (SWaP) requirements. However, sharing of main memory between CPU applications and GPU kernels can severely affect the execution of GPU kernels and diminish the performance gain provided by GPU. In the NVIDIA Tegra TK1 platform which...
An efficient lightweight forward static slicing tool is presented.The tool is implemented on top of srcML, an XML representation of source code.The approach does not compute the full program dependence graph but instead dependency information is computed as needed while computing the slice on a variable.The result is a list of line numbers, dependent variables, aliases, and function calls that are...
Deep convolutional neural networks (CNN) have shown their good performances in many computer vision tasks. However, the high computational complexity of CNN involves a huge amount of data movements between the computational processor core and memory hierarchy which occupies the major of the power consumption. This paper presents Chain-NN, a novel energy-efficient 1D chain architecture for accelerating...
Previous works in the literature have shown the feasibility of general purpose computations for non-visual applications on low-end mobile graphics processors using graphics APIs. These works focused only on the functional aspects of the software, ignoring the implementation details and therefore their performance implications due to their particular micro-architecture. Since various steps in such...
A booming number of computer vision, speech recognition, and signal processing applications, are increasingly benefiting from the use of deep convolutional neural networks (DCNN) stemming from the seminal work of Y. LeCun et al. [1] and others that led to winning the 2012 ImageNet Large Scale Visual Recognition Challenge with AlexNet [2], a DCNN significantly outperforming classical approaches for...
Graphics Processing Units (GPUs) are designed to exploit large amount of parallelism. However, warp-level divergence occurring due to different amounts of work, memory access latency experienced, etc., results in warps of a thread block (TB) finishing kernel execution at different points in time. This, in effect, reduces utilization of resources of SMs and hence performance of the GPU. We propose...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.