Tomographic image reconstruction is computationally very demanding. In all cases the backprojection represents the performance bottleneck due to the high operational count and due to the high demand put on the memory subsystem. In the past, solving this problem has lead to the implementation of specific architectures, connecting Application Specific Integrated Circuits (ASICs) or Field Programm...

Discovering association rules that identify relationships among sets of items is an important problem in data mining. It’s a two steps process, the first step finds all frequent itemsets and the second one constructs association rules from these frequent sets. Finding frequent itemsets is computationally the most expensive step in association rules discovery algorithms. Utilizing parallel archi...

Metagenomic sequence classification is a procedure to assign sequences to their source genomes. It is one of the important steps for metagenomic sequence data analysis. Although many methods exist, classification of high-throughput metagenomic sequence data in a limited time is still a challenge. We present here an ultra-fast metagenomic sequence classification system (MetaBinG) using graphic p...

Convolutional neural networks (CNNs) are well known for producing state-of-the-art recognizers for document processing [1]. However, they can be difficult to implement and are usually slower than traditional multi-layer perceptrons (MLPs). We present three novel approaches to speeding up CNNs: a) unrolling convolution, b) using BLAS (basic linear algebra subroutines), and c) using GPUs (graphic...

PolyBench is a well-known set of benchmarks characterized by embarrassingly parallel kernels able to run on Graphic Processing Units (GPUs). While Polybench GPU leverage well-established GP-GPU APIs such as CUDA and OpenCL, in this paper we present vkpolybench, crossplatform PolyBench/GPU port built top Vulkan. Vulkan the recently released Khronos standard for heterogeneous CPU–GPU computing th...

More and more 3D terrain information is converted and stored in a digital format, and they have been used as a prim ary data source for a variety of spatial analyses in various application domains. One unsolved issue is that 3D spatial analyses (e.g., 3D ray tracing) often require huge computing cost in terms of processing time and hardware. This pap er presents a new technique for the fast 3D ...

This paper describes a novel agglutinative language modeling strategy for Uyghur with graphic language model as structure. In graphic modeling language model, sentences are organized by morphemes as a directed graph, which is different from the linear structure in n-gram language models. The graphic language model is verified in two typical natural language processing application scenarios, mor...

Patent images maintained by the U.S. patent database have figures and related description separated in different pages. This makes it difficult for users to refer to a figure while reading the description. In order to prepare these patent images for a friendly user interface, this paper presents a system, which is able to segment a mulitple-figure image page into individual figures and extract ...

Several observations made over the past year have forged strong molecular links between transcription by RNA polymerase II (Pol II) and pre-mRNA processing. The key findings support the view that the carboxy-terminal domain (CTD) of the large subunit of RNA polymerase II binds directly to protein factors essential for RNA processing. In some cases, there is a clear suggestion that the factors o...