Graphics Processing Unit (GPU)

The OD detection is a mainly step in many methods for ophthalmic diseases diagnosis. The work described in [7] proposes a performance optic disk detection approach based on blood vessel tracking and optic disk contrast. However, the method is characterized by a higher execution time which is about 10 s in STARE DB images. Moreover, the execution time increases proportionally with the fundus image resolution. This computational performance is a limiting factor to employ the method in diagnosis systems of ophthalmic diseases. This paper aims to optimize the method processing in order to enhance the computational performance. The first contribution consists of optimizing repet itive steps with the aim of reducing times. Thereafter, all processing steps are implemented in GPU architectures. The experimental results indicate that each one of the contributions insures enhancing computational performance with speedup equal to 1.7 and 2.5, respectively. The implementation with combined cont...

Military training, concept design, and pre-acquisition studies often are carried out in virtual settings in which one can experience that which is, in the real world, too dangerous, too costly, or even beyond current technology. Purely virtual environments, however, have limitations in that they remove the participant from the physical world with its visual, auditory, and tactile complexities. In contrast, mixed reality (MR) seeks to blend the real and synthetic. How well that blending works is critical to the effectiveness of a user's experience within an MR scenario. The focus of this paper is on the visual aspects of this blending or more specifically on the interactions between the real and virtual in the contexts of proper inter-occlusion, illumination, and inter-shadowing. This means that the virtual objects must react properly to changes in real lighting and that the real must react properly to the insertion of virtual lights (e.g., a virtual flashlight or a simulated cha...

 Couplings between fluid flow, heat transport and reactions in the Lusi system solved with multi-GPU technology  High-Performance Computing with 3D numerical models using multi-GPU processing  Fluid pressure build-up due to clay dehydration controls hydrothermal system fluid outflow

Although deconvolution can improve the quality of any type of microscope, the high computational time required has so far limited its massive spreading. Here we demonstrate the ability of the scaled-gradient-projection (SGP) method to provide accelerated versions of the most used algorithms in microscopy. To achieve further increases in efficiency, we also consider implementations on graphic processing units (GPUs). We test the proposed algorithms both on synthetic and real data of confocal and STED microscopy. Combining the SGP method with the GPU implementation we achieve a speed-up factor from about a factor 25 to 690 (with respect the conventional algorithm). The excellent results obtained on STED microscopy images demonstrate the synergy between super-resolution techniques and image-deconvolution. Further, the real-time processing allows conserving one of the most important property of STED microscopy, i.e the ability to provide fast sub-diffraction resolution recordings. I mage deconvolution is a computational technique that mitigates the distortions created by an optical system. Agard first applied image deconvolution to fluorescence microscopy in the early 1980s 1. In this seminal paper Agard proposed different algorithms for deconvolving images acquired as three-dimensional (3D) stacks using wide-field microscopy (WFM). In a nutshell, the focal plane of the objective lens moves along the thickness of the specimen and for each position the microscope generates a bi-dimensional (2D) image. Due to the diffraction phenomena, each 2D image, also called optical section, includes considerable out-of-focus light originating from regions of the specimen above and below the focal plane. Image deconvolution uses information describing how the microscope produces the image (forward model) as the basis of a mathematical transformation that reassigns the out-of-focus light to the points of origin. Later, many new optical methods have been proposed to remove out-of-focus light and to generate directly true optical sections. Without pretending to be exhaustive, we mention confocal laser scanning microscopy (CLSM) 2,3 , two-photon excitation microscopy (TPEM) 2,4 and selective plane illumination microscopy (SPIM) 5,6. All these methods remove out-of-focus light by rejecting such light before it reaches the detector or by precluding its generation. Further hybrid techniques, which remove out-of-focus light by combining optical and computational methods are 4Pi microscopy 7,8 and structured illumination microscopy (SIM) 9,10. Since CLSM, TPEM and SPIM have considerably smaller contribution of out-of-focus light they are sometimes considered as pure alternatives to the deconvolution and WFM combo. However, it has been shown that also these techniques can strongly benefit from image deconvolution 11-14. Although out-of-focus background is reduced, the images produced by such systems are still blurred versions of the specimen's structures in the focal plane and are contaminated by noise, thereby deconvolution can improve their contrast and signal-to-noise ratio. Similarly, also single 2D image can benefit of deconvolution, especially when obtained from thin specimen, where out-of-focus background vanishes. More recently new super-resolution fluorescence microscopy approaches (usually referred to as nanoscopy) have enlarged the portfolio of tools for investigating biological samples 15. The nanoscopy techniques have effectively break the diffraction barrier and moved the spatial resolution of fluorescence microscopy down to the nanoscale 16. Importantly, also in these cases image deconvolution can help to improve the quality of their images. This has been demonstrated both for stimulated emission depletion (STED) microscopy 17 , which at moment can be considered as the method of choice between the targeted nanoscopy techniques, and, more

Although deconvolution can improve the quality of any type of microscope, the high computational time required has so far limited its massive spreading. Here we demonstrate the ability of the scaled-gradient-projection (SGP) method to provide accelerated versions of the most used algorithms in microscopy. To achieve further increases in efficiency, we also consider implementations on graphic processing units (GPUs). We test the proposed algorithms both on synthetic and real data of confocal and STED microscopy. Combining the SGP method with the GPU implementation we achieve a speed-up factor from about a factor 25 to 690 (with respect the conventional algorithm). The excellent results obtained on STED microscopy images demonstrate the synergy between super-resolution techniques and image-deconvolution. Further, the real-time processing allows conserving one of the most important property of STED microscopy, i.e the ability to provide fast sub-diffraction resolution recordings. I mage deconvolution is a computational technique that mitigates the distortions created by an optical system. Agard first applied image deconvolution to fluorescence microscopy in the early 1980s 1. In this seminal paper Agard proposed different algorithms for deconvolving images acquired as three-dimensional (3D) stacks using wide-field microscopy (WFM). In a nutshell, the focal plane of the objective lens moves along the thickness of the specimen and for each position the microscope generates a bi-dimensional (2D) image. Due to the diffraction phenomena, each 2D image, also called optical section, includes considerable out-of-focus light originating from regions of the specimen above and below the focal plane. Image deconvolution uses information describing how the microscope produces the image (forward model) as the basis of a mathematical transformation that reassigns the out-of-focus light to the points of origin. Later, many new optical methods have been proposed to remove out-of-focus light and to generate directly true optical sections. Without pretending to be exhaustive, we mention confocal laser scanning microscopy (CLSM) 2,3 , two-photon excitation microscopy (TPEM) 2,4 and selective plane illumination microscopy (SPIM) 5,6. All these methods remove out-of-focus light by rejecting such light before it reaches the detector or by precluding its generation. Further hybrid techniques, which remove out-of-focus light by combining optical and computational methods are 4Pi microscopy 7,8 and structured illumination microscopy (SIM) 9,10. Since CLSM, TPEM and SPIM have considerably smaller contribution of out-of-focus light they are sometimes considered as pure alternatives to the deconvolution and WFM combo. However, it has been shown that also these techniques can strongly benefit from image deconvolution 11-14. Although out-of-focus background is reduced, the images produced by such systems are still blurred versions of the specimen's structures in the focal plane and are contaminated by noise, thereby deconvolution can improve their contrast and signal-to-noise ratio. Similarly, also single 2D image can benefit of deconvolution, especially when obtained from thin specimen, where out-of-focus background vanishes. More recently new super-resolution fluorescence microscopy approaches (usually referred to as nanoscopy) have enlarged the portfolio of tools for investigating biological samples 15. The nanoscopy techniques have effectively break the diffraction barrier and moved the spatial resolution of fluorescence microscopy down to the nanoscale 16. Importantly, also in these cases image deconvolution can help to improve the quality of their images. This has been demonstrated both for stimulated emission depletion (STED) microscopy 17 , which at moment can be considered as the method of choice between the targeted nanoscopy techniques, and, more

This paper presents a GPU-based parallelized and a CPU-based serial Monte-Carlo method for breakage of a particle. We compare the efficiency of the graphic card's graphics processing unit (GPU) and the general-purpose central processing unit (CPU), in a simulation using Monte Carlo (MC) methods for processing the particle breakage. Three applications are used to compare the computational performance times, clock cycles and speedup factors, to find which platform is faster under which conditions. The architecture of the GPU is becoming increasingly programmable; it represents a potential speedup for many applications compared to the modern CPU. The objective of the paper is to compare the performance of the GPU and Intel Core i7-4790 multicore CPU. The implementation for the CPU was written in the C programming language, and the GPU implemented the kernel using Nvidia's CUDA (Compute Unified Device Architecture). This paper compares the computational times, clock cycles and the speedup factor for a GPU and a CPU, with various simulation settings such as the number of simulation entries (SEs), for a better understanding of the GPU and CPU computational efficiency. It has been found that the number of SEs directly affects the speedup factor.

About 25 seismic events in Cangar hot spring, Arjuno-Welirang Complex has been presented to identify its dynamic process. The delay time has been identified using autocorrelation and embedding dimension has been determined by selecting the False Nearest Neighbour equal to zero. Both of these parameters used to reconstructive the attractor diagram at phase space and to calculate the lyapunov exponent value. The results show the lyapunov exponent in study area are positive and they associated with the chaotic and deterministic system of hydrothermal area.

We propose to employ bilateral filters to solve the problem of edge detection. The proposed methodology presents an efficient and noise robust method for detecting edges. Classical bilateral filters smooth images without distorting edges. In this paper, we modify the bilateral filter to perform edge detection, which is the opposite of bilateral smoothing. The Gaussian domain kernel of the bilateral filter is replaced with an edge detection mask, and Gaussian range kernel is replaced with an inverted Gaussian kernel. The modified range kernel serves to emphasize dissimilar regions. The resulting approach effectively adapts the detection mask according as the pixel intensity differences. The results of the proposed algorithm are compared with those of standard edge detection masks. Comparisons of the bilateral edge detector with Canny edge detection algorithm, both after non-maximal suppression, are also provided. The results of our technique are observed to be better and noise-robust than those offered by methods employing masks alone, and are also comparable to the results from Canny edge detector, outperforming it in certain cases.

This paper presents a GPU-based parallelized and a CPU-based serial Monte-Carlo method for breakage of a particle. We compare the efficiency of the graphic card's graphics processing unit (GPU) and the general-purpose central processing unit (CPU), in a simulation using Monte Carlo (MC) methods for processing the particle breakage. Three applications are used to compare the computational performance times, clock cycles and speedup factors, to find which platform is faster under which conditions. The architecture of the GPU is becoming increasingly programmable; it represents a potential speedup for many applications compared to the modern CPU. The objective of the paper is to compare the performance of the GPU and Intel Core i7-4790 multicore CPU. The implementation for the CPU was written in the C programming language, and the GPU implemented the kernel using Nvidia's CUDA (Compute Unified Device Architecture). This paper compares the computational times, clock cycles and the speedup factor for a GPU and a CPU, with various simulation settings such as the number of simulation entries (SEs), for a better understanding of the GPU and CPU computational efficiency. It has been found that the number of SEs directly affects the speedup factor.

Low-Density Parity-Check (LDPC) codes are powerful error correcting codes adopted by recent communication standards. LDPC decoders are based on belief propagation algorithms, which make use of a Tanner graph and very intensive message-passing computation, and usually require hardware-based dedicated solutions. With the exponential increase of the computational power of commodity graphics processing units (GPUs), new opportunities have arisen to develop general purpose processing on GPUs. This paper proposes the use of GPUs for implementing flexible and programmable LDPC decoders. A new stream-based approach is proposed, based on compact data structures to represent the Tanner graph. It is shown that such a challenging application for stream-based computing, because of irregular memory access patterns, memory bandwidth and recursive flow control constraints, can be efficiently implemented on GPUs. The proposal was experimentally evaluated by programming LDPC decoders on GPUs using the Caravela platform, a generic interface tool for managing the kernels' execution regardless of the GPU manufacturer and operating system. Moreover, to relatively assess the obtained results, we have also implemented LDPC decoders on general purpose processors with Streaming Single Instruction Multiple Data (SIMD) Extensions. Experimental results show that the solution proposed here efficiently decodes several codewords simultaneously, reducing the processing time by one order of magnitude.

The increasing amount of network throughput and security threat makes intrusion detection a major research problem. In the literature, intrusion detection has been approached by either a hardware or software technique. This work reviews and compares hardware based techniques that are commonly used in intrusion detection systems (IDS) with a special emphasis on modern hardware platforms such as FPGA, GPU, MCP andASIC.

The OD detection is a mainly step in many methods for ophthalmic diseases diagnosis. The work described in [7] proposes a performance optic disk detection approach based on blood vessel tracking and optic disk contrast. However, the method is characterized by a higher execution time which is about 10 s in STARE DB images. Moreover, the execution time increases proportionally with the fundus image resolution. This computational performance is a limiting factor to employ the method in diagnosis systems of ophthalmic diseases. This paper aims to optimize the method processing in order to enhance the computational performance. The first contribution consists of optimizing repet itive steps with the aim of reducing times. Thereafter, all processing steps are implemented in GPU architectures. The experimental results indicate that each one of the contributions insures enhancing computational performance with speedup equal to 1.7 and 2.5, respectively. The implementation with combined cont...

Several leading-edge applications such as pathology detection, biometric identification and face recognition are mainly based on blob and line detection. To address this problem, the Eigen value computing has been commonly employed due to its accuracy and robustness. However, the Eigen value computing requires a raised computational processing, an intensive memory data access and a data overlapping which involve higher execution times. To overcome these limitations, we propose in this paper a new parallel strategy to implement the Eigen value computing using a GPU. Our contributions are: (1) to optimize instruction scheduling in order to reduce the computation time, (2) to efficiently partition processing into blocks in order to increase the occupancy of streaming multiprocessors, (3) to provide efficient input data splitting on shared memory to take benefit from its lower access time, (4) and to propose new data management of shared memory so as to avoid access memory conflict and reduce memory bank accesses. Experimental results show that our proposed GPU parallel strategy for Eigen value computing achieves speedups of 27 compared to a multithreaded implementation, of 16 compared to a predefined function in the OpenCV library, and of 8 compared to a predefined function in the Cublas library, which are performed into a quad core multi-CPU platform. Next, our parallel strategy is evaluated through an Eigen value based method for retinal thick vessel segmentation which is essential for detecting ocular pathologies. The Eigen value computing is executed in 0.017 seconds, when using STARE database images. Accordingly, we have achieved real-time thick retinal vessel segmentation where average execution time is about 0.039 seconds.

Motion compensation is one of the most computeintensive parts in H.264/AVC video decoding. It exposes massive parallelism which can reap the benefit from Graphics Processing Units (GPUs). Control and memory divergence, however, may lead to performance penalties on GPUs. In this paper, we propose two GPU motion compensation kernels, implemented with OpenCL, that mitigate the divergence effect. In addition, the motion compensation kernels have been integrated into a complete and optimized H.264/AVC decoder that supports H.264/AVC high profile. We evaluated our kernels on GPUs with different architectures from AMD, Intel, and Nvidia. Compared to the fastest CPU used in this paper, our kernel achieves 2.0 speedup on a discrete Nvidia GPU at kernel level. However, when the overheads of memory copy and OpenCL runtime are included, no speedup is gained at application level.

This paper presents a GPU-based parallelized and a CPU-based serial Monte-Carlo method for breakage of a particle. We compare the efficiency of the graphic card's graphics processing unit (GPU) and the general-purpose central processing unit (CPU), in a simulation using Monte Carlo (MC) methods for processing the particle breakage. Three applications are used to compare the computational performance times, clock cycles and speedup factors, to find which platform is faster under which conditions. The architecture of the GPU is becoming increasingly programmable; it represents a potential speedup for many applications compared to the modern CPU. The objective of the paper is to compare the performance of the GPU and Intel Core i7-4790 multicore CPU. The implementation for the CPU was written in the C programming language, and the GPU implemented the kernel using Nvidia's CUDA (Compute Unified Device Architecture). This paper compares the computational times, clock cycles and the speedup factor for a GPU and a CPU, with various simulation settings such as the number of simulation entries (SEs), for a better understanding of the GPU and CPU computational efficiency. It has been found that the number of SEs directly affects the speedup factor.

Optic disc (OD) detection is a basic procedure for the image processing algorithms which intend to diagnose and track retinal disorders. In this study, a new OD localization approach is proposed, based on color and shape properties of OD as well as the convergence point of the main vessels. This study is comprised of two successive fundamental steps. At the first step, an algorithm finding the approximate convergent point of the vessels is used in order to roughly localize OD. At the second step, three new features are suggested and a fuzzy logic controller (FLC) whose input membership functions are designed based on these features is proposed. The proposed method is applied to the DRIVE, STARE, DIARETDB0 and DIRETDB1 datasets and the obtained results validate the improvement in the performance by attaining success rate of 100%, 91,35%, 90% and 100% respectively and detecting OD centers and contours precisely in a reasonable execution time.

 Couplings between fluid flow, heat transport and reactions in the Lusi system solved with multi-GPU technology  High-Performance Computing with 3D numerical models using multi-GPU processing  Fluid pressure build-up due to clay dehydration controls hydrothermal system fluid outflow

Graphics Processing Units (GPUs) have been recently used as coprocessors capable of performing tasks that are not necessarily related to graphics processing in order to optimize computing resources. The use of GPUs has being extended to a wide variety of intensive-computation applications among which audio processing is included. However data transactions between the CPU and the GPU and vice versa have questioned the viability of GPUs for applications in which direct and real-time interaction between microphone and loudspeaker is required. One of the audio applications that requires real-time feedback is adaptive channel identification. Particularly, when the partitioned Least Mean Squares (LMS) algorithm is used in the frequency domain, the size of input-data buffers and filters and how they can be managed in order to successfully exploit the GPU resources is an important key in the design process. This paper discusses the design and implementation of all the processing blocks of an adaptive channel identification system on a GPU, proposing a GPU implementation that can be easily adapted to any acoustic scenario, while freeing up CPU resources for other tasks.

In this article, some instances of well known combinatorial optimization NP-Hard problems are solved by using Koopmans and Beckmann formulation of the quadratic assignment problem (QAP). These instances are solved by using an Embarrassingly Parallel Genetic Algorithm or by using an Island Parallel Genetic Algorithm; in both cases, the implementation is carried out on Graphics Processing Units (GPUs).

Medical imaging is fundamental for improvements in diagnostic accuracy. However, noise frequently corrupts the images acquired, and this can lead to erroneous diagnoses. Fortunately, image preprocessing algorithms can enhance corrupted images, particularly in noise smoothing and removal. In the medical field, time is always a very critical factor, and so there is a need for implementations which are fast and, if possible, in real time. This study presents and discusses an implementation of a highly efficient algorithm for image noise smoothing based on general purpose computing on graphics processing units techniques. The use of these techniques facilitates the quick and efficient smoothing of images corrupted by noise, even when performed on large-dimensional data sets. This is particularly relevant since GPU cards are becoming more affordable, powerful and common in medical environments.

Motion compensation is one of the most computeintensive parts in H.264/AVC video decoding. It exposes massive parallelism which can reap the benefit from Graphics Processing Units (GPUs). Control and memory divergence, however, may lead to performance penalties on GPUs. In this paper, we propose two GPU motion compensation kernels, implemented with OpenCL, that mitigate the divergence effect. In addition, the motion compensation kernels have been integrated into a complete and optimized H.264/AVC decoder that supports H.264/AVC high profile. We evaluated our kernels on GPUs with different architectures from AMD, Intel, and Nvidia. Compared to the fastest CPU used in this paper, our kernel achieves 2.0 speedup on a discrete Nvidia GPU at kernel level. However, when the overheads of memory copy and OpenCL runtime are included, no speedup is gained at application level.

The increasing amount of network throughput and security threat makes intrusion detection a major research problem. In the literature, intrusion detection has been approached by either a hardware or software technique. This work reviews and compares hardware based techniques that are commonly used in intrusion detection systems (IDS) with a special emphasis on modern hardware platforms such as FPGA, GPU, MCP andASIC.

Motion compensation is one of the most computeintensive parts in H.264/AVC video decoding. It exposes massive parallelism which can reap the benefit from Graphics Processing Units (GPUs). Control and memory divergence, however, may lead to performance penalties on GPUs. In this paper, we propose two GPU motion compensation kernels, implemented with OpenCL, that mitigate the divergence effect. In addition, the motion compensation kernels have been integrated into a complete and optimized H.264/AVC decoder that supports H.264/AVC high profile. We evaluated our kernels on GPUs with different architectures from AMD, Intel, and Nvidia. Compared to the fastest CPU used in this paper, our kernel achieves 2.0 speedup on a discrete Nvidia GPU at kernel level. However, when the overheads of memory copy and OpenCL runtime are included, no speedup is gained at application level.

Graphics Processing Units (GPUs) have been recently used as coprocessors capable of performing tasks that are not necessarily related to graphics processing in order to optimize computing resources. The use of GPUs has being extended to a wide variety of intensive-computation applications among which audio processing is included. However data transactions between the CPU and the GPU and vice versa have questioned the viability of GPUs for applications in which direct and real-time interaction between microphone and loudspeaker is required. One of the audio applications that requires real-time feedback is adaptive channel identification. Particularly, when the partitioned Least Mean Squares (LMS) algorithm is used in the frequency domain, the size of input-data buffers and filters and how they can be managed in order to successfully exploit the GPU resources is an important key in the design process. This paper discusses the design and implementation of all the processing blocks of an adaptive channel identification system on a GPU, proposing a GPU implementation that can be easily adapted to any acoustic scenario, while freeing up CPU resources for other tasks.

The OD detection is a mainly step in many methods for ophthalmic diseases diagnosis. The work described in [7] proposes a performance optic disk detection approach based on blood vessel tracking and optic disk contrast. However, the method is characterized by a higher execution time which is about 10 s in STARE DB images. Moreover, the execution time increases proportionally with the fundus image resolution. This computational performance is a limiting factor to employ the method in diagnosis systems of ophthalmic diseases. This paper aims to optimize the method processing in order to enhance the computational performance. The first contribution consists of optimizing repet itive steps with the aim of reducing times. Thereafter, all processing steps are implemented in GPU architectures. The experimental results indicate that each one of the contributions insures enhancing computational performance with speedup equal to 1.7 and 2.5, respectively. The implementation with combined cont...

Parametric statistical methods, such asZ-,t-, andF-values, are traditionally employed in functional magnetic resonance imaging (fMRI) for identifying areas in the brain that are active with a certain degree of statistical significance. These parametric methods, however, have two major drawbacks. First, it is assumed that the observed data are Gaussian distributed and independent; assumptions that generally are not valid for fMRI data. Second, the statistical test distribution can be derived theoretically only for very simple linear detection statistics. With nonparametric statistical methods, the two limitations described above can be overcome. The major drawback of non-parametric methods is the computational burden with processing times ranging from hours to days, which so far have made them impractical for routine use in single-subject fMRI analysis. In this work, it is shown how the computational power of cost-efficient graphics processing units (GPUs) can be used to speed up ran...

This paper describes a hybrid multicore/GPU solver for the incompressible Navier-Stokes equations with constant coefficients, discretized by the finite difference method. By applying the prediction-projection method, the Navier-Stokes equations are transformed into a combination of Helmholtzlike and Poisson equations for which we describe efficient solvers. As an extension of our previous paper [1], this paper proposes a new implementation that takes advantage of GPU accelerators. We present numerical experiments on a current hybrid machine. 2. SOLVING THE HELMHOLTZ AND POISSON EQUATIONS According to the prediction-projection method, the Navier-Stokes Eq. (1) is transformed into a Helmholtz-like equation for the velocity field and a Poisson equation for the pressure. In this section, we present the numerical methods used for solving these equations and the resulting structures.

Motion compensation is one of the most computeintensive parts in H.264/AVC video decoding. It exposes massive parallelism which can reap the benefit from Graphics Processing Units (GPUs). Control and memory divergence, however, may lead to performance penalties on GPUs. In this paper, we propose two GPU motion compensation kernels, implemented with OpenCL, that mitigate the divergence effect. In addition, the motion compensation kernels have been integrated into a complete and optimized H.264/AVC decoder that supports H.264/AVC high profile. We evaluated our kernels on GPUs with different architectures from AMD, Intel, and Nvidia. Compared to the fastest CPU used in this paper, our kernel achieves 2.0 speedup on a discrete Nvidia GPU at kernel level. However, when the overheads of memory copy and OpenCL runtime are included, no speedup is gained at application level.

In the field of video compression, motion estimation (ME) is a process that leads to high computational complexity. Implementation of ME block-matching (BM) algorithms on general purpose Central Processing Unit (CPU), has resulted in poor performance. In this paper we investigate the performance of two BM ME algorithms: Three Step Search (TSS) and Four Step Search (4SS) on Graphics Processing Unit (GPU) NVIDIA Quadro 400 using the Compute Unified Device Architecture (CUDA) platform. Both algorithms perform motion estimation on a block-by-block basis, which is considered the simplest way in terms of hardware and software implementation. The focus is to achieve parallelization of the algorithms for a real time execution. We consider two well-known test sequences: "football" and "mad900", with different image resolution. The results show that the implementation on a GPU card can improve the performance in terms of execution time, by a factor of 1000.

Low-Density Parity-Check (LDPC) codes are powerful error correcting codes adopted by recent communication standards. LDPC decoders are based on belief propagation algorithms, which make use of a Tanner graph and very intensive message-passing computation, and usually require hardware-based dedicated solutions. With the exponential increase of the computational power of commodity graphics processing units (GPUs), new opportunities have arisen to develop general purpose processing on GPUs. This paper proposes the use of GPUs for implementing flexible and programmable LDPC decoders. A new stream-based approach is proposed, based on compact data structures to represent the Tanner graph. It is shown that such a challenging application for stream-based computing, because of irregular memory access patterns, memory bandwidth and recursive flow control constraints, can be efficiently implemented on GPUs. The proposal was experimentally evaluated by programming LDPC decoders on GPUs using the Caravela platform, a generic interface tool for managing the kernels' execution regardless of the GPU manufacturer and operating system. Moreover, to relatively assess the obtained results, we have also implemented LDPC decoders on general purpose processors with Streaming Single Instruction Multiple Data (SIMD) Extensions. Experimental results show that the solution proposed here efficiently decodes several codewords simultaneously, reducing the processing time by one order of magnitude.

Motion compensation is one of the most computeintensive parts in H.264/AVC video decoding. It exposes massive parallelism which can reap the benefit from Graphics Processing Units (GPUs). Control and memory divergence, however, may lead to performance penalties on GPUs. In this paper, we propose two GPU motion compensation kernels, implemented with OpenCL, that mitigate the divergence effect. In addition, the motion compensation kernels have been integrated into a complete and optimized H.264/AVC decoder that supports H.264/AVC high profile. We evaluated our kernels on GPUs with different architectures from AMD, Intel, and Nvidia. Compared to the fastest CPU used in this paper, our kernel achieves 2.0 speedup on a discrete Nvidia GPU at kernel level. However, when the overheads of memory copy and OpenCL runtime are included, no speedup is gained at application level.

Although deconvolution can improve the quality of any type of microscope, the high computational time required has so far limited its massive spreading. Here we demonstrate the ability of the scaled-gradient-projection (SGP) method to provide accelerated versions of the most used algorithms in microscopy. To achieve further increases in efficiency, we also consider implementations on graphic processing units (GPUs). We test the proposed algorithms both on synthetic and real data of confocal and STED microscopy. Combining the SGP method with the GPU implementation we achieve a speed-up factor from about a factor 25 to 690 (with respect the conventional algorithm). The excellent results obtained on STED microscopy images demonstrate the synergy between super-resolution techniques and image-deconvolution. Further, the real-time processing allows conserving one of the most important property of STED microscopy, i.e the ability to provide fast sub-diffraction resolution recordings. I mage deconvolution is a computational technique that mitigates the distortions created by an optical system. Agard first applied image deconvolution to fluorescence microscopy in the early 1980s 1. In this seminal paper Agard proposed different algorithms for deconvolving images acquired as three-dimensional (3D) stacks using wide-field microscopy (WFM). In a nutshell, the focal plane of the objective lens moves along the thickness of the specimen and for each position the microscope generates a bi-dimensional (2D) image. Due to the diffraction phenomena, each 2D image, also called optical section, includes considerable out-of-focus light originating from regions of the specimen above and below the focal plane. Image deconvolution uses information describing how the microscope produces the image (forward model) as the basis of a mathematical transformation that reassigns the out-of-focus light to the points of origin. Later, many new optical methods have been proposed to remove out-of-focus light and to generate directly true optical sections. Without pretending to be exhaustive, we mention confocal laser scanning microscopy (CLSM) 2,3 , two-photon excitation microscopy (TPEM) 2,4 and selective plane illumination microscopy (SPIM) 5,6. All these methods remove out-of-focus light by rejecting such light before it reaches the detector or by precluding its generation. Further hybrid techniques, which remove out-of-focus light by combining optical and computational methods are 4Pi microscopy 7,8 and structured illumination microscopy (SIM) 9,10. Since CLSM, TPEM and SPIM have considerably smaller contribution of out-of-focus light they are sometimes considered as pure alternatives to the deconvolution and WFM combo. However, it has been shown that also these techniques can strongly benefit from image deconvolution 11-14. Although out-of-focus background is reduced, the images produced by such systems are still blurred versions of the specimen's structures in the focal plane and are contaminated by noise, thereby deconvolution can improve their contrast and signal-to-noise ratio. Similarly, also single 2D image can benefit of deconvolution, especially when obtained from thin specimen, where out-of-focus background vanishes. More recently new super-resolution fluorescence microscopy approaches (usually referred to as nanoscopy) have enlarged the portfolio of tools for investigating biological samples 15. The nanoscopy techniques have effectively break the diffraction barrier and moved the spatial resolution of fluorescence microscopy down to the nanoscale 16. Importantly, also in these cases image deconvolution can help to improve the quality of their images. This has been demonstrated both for stimulated emission depletion (STED) microscopy 17 , which at moment can be considered as the method of choice between the targeted nanoscopy techniques, and, more

Purpose: Optoacoustic tomography (OAT) is inherently a three-dimensional (3D) inverse problem. However, most studies of OAT image reconstruction still employ two-dimensional (2D) imaging models. One important reason is because 3D image reconstruction is computationally burdensome. The aim of this work is to accelerate existing image reconstruction algorithms for 3D OAT by use of parallel programming techniques. Methods: Parallelization strategies are proposed to accelerate a filtered backprojection (FBP) algorithm and two different pairs of projection/backprojection operations that correspond to two different numerical imaging models. The algorithms are designed to fully exploit the parallel computing power of graphic processing units (GPUs). In order to evaluate the parallelization strategies for the projection/backprojection pairs, an iterative image reconstruction algorithm is implemented. Computer-simulation and experimental studies are conducted to investigate the computational efficiency and numerical accuracy of the developed algorithms. Results: The GPU implementations improve the computational efficiency by factors of 1, 000, 125, and 250 for the FBP algorithm and the two pairs of projection/backprojection operators, respectively. Accurate images are reconstructed by use of the FBP and iterative image reconstruction algorithms from both computersimulated and experimental data. Conclusions: Parallelization strategies for 3D OAT image reconstruction are proposed for the first time. These GPU-based implementations significantly reduce the computational time for 3D image reconstruction, complementing our earlier work on 3D OAT iterative image reconstruction.

Purpose: Optoacoustic tomography (OAT) is inherently a three-dimensional (3D) inverse problem. However, most studies of OAT image reconstruction still employ two-dimensional (2D) imaging models. One important reason is because 3D image reconstruction is computationally burdensome. The aim of this work is to accelerate existing image reconstruction algorithms for 3D OAT by use of parallel programming techniques. Methods: Parallelization strategies are proposed to accelerate a filtered backprojection (FBP) algorithm and two different pairs of projection/backprojection operations that correspond to two different numerical imaging models. The algorithms are designed to fully exploit the parallel computing power of graphic processing units (GPUs). In order to evaluate the parallelization strategies for the projection/backprojection pairs, an iterative image reconstruction algorithm is implemented. Computer-simulation and experimental studies are conducted to investigate the computational efficiency and numerical accuracy of the developed algorithms. The GPU implementations improve the computational efficiency by factors of 1, 000, 125, and 250 for the FBP algorithm and the two pairs of projection/backprojection operators, respectively. Accurate images are reconstructed by use of the FBP and iterative image reconstruction algorithms from both computersimulated and experimental data. Conclusions: Parallelization strategies for 3D OAT image reconstruction are proposed for the first time. These GPU-based implementations significantly reduce the computational time for 3D image reconstruction, complementing our earlier work on 3D OAT iterative image reconstruction.

Purpose: Optoacoustic tomography (OAT) is inherently a three-dimensional (3D) inverse problem. However, most studies of OAT image reconstruction still employ two-dimensional (2D) imaging models. One important reason is because 3D image reconstruction is computationally burdensome. The aim of this work is to accelerate existing image reconstruction algorithms for 3D OAT by use of parallel programming techniques. Methods: Parallelization strategies are proposed to accelerate a filtered backprojection (FBP) algorithm and two different pairs of projection/backprojection operations that correspond to two different numerical imaging models. The algorithms are designed to fully exploit the parallel computing power of graphic processing units (GPUs). In order to evaluate the parallelization strategies for the projection/backprojection pairs, an iterative image reconstruction algorithm is implemented. Computer-simulation and experimental studies are conducted to investigate the computational efficiency and numerical accuracy of the developed algorithms. The GPU implementations improve the computational efficiency by factors of 1, 000, 125, and 250 for the FBP algorithm and the two pairs of projection/backprojection operators, respectively. Accurate images are reconstructed by use of the FBP and iterative image reconstruction algorithms from both computersimulated and experimental data. Conclusions: Parallelization strategies for 3D OAT image reconstruction are proposed for the first time. These GPU-based implementations significantly reduce the computational time for 3D image reconstruction, complementing our earlier work on 3D OAT iterative image reconstruction.

In the field of video compression, motion estimation (ME) is a process that leads to high computational complexity. Implementation of ME block-matching (BM) algorithms on general purpose Central Processing Unit (CPU), has resulted in poor performance. In this paper we investigate the performance of two BM ME algorithms: Three Step Search (TSS) and Four Step Search (4SS) on Graphics Processing Unit (GPU) NVIDIA Quadro 400 using the Compute Unified Device Architecture (CUDA) platform. Both algorithms perform motion estimation on a block-by-block basis, which is considered the simplest way in terms of hardware and software implementation. The focus is to achieve parallelization of the algorithms for a real time execution. We consider two well-known test sequences: "football" and "mad900", with different image resolution. The results show that the implementation on a GPU card can improve the performance in terms of execution time, by a factor of 100.

In this article, some instances of well known combinatorial optimization NP-Hard problems are solved by using Koopmans and Beckmann formulation of the quadratic assignment problem (QAP). These instances are solved by using an Embarrassingly Parallel Genetic Algorithm or by using an Island Parallel Genetic Algorithm; in both cases, the implementation is carried out on Graphics Processing Units (GPUs).

In this article, some instances of well known combinatorial optimization NP-Hard problems are solved by using Koopmans and Beckmann formulation of the quadratic assignment problem (QAP). These instances are solved by using an Embarrassingly Parallel Genetic Algorithm or by using an Island Parallel Genetic Algorithm; in both cases, the implementation is carried out on Graphics Processing Units (GPUs).