OpenCL Framework Research Articles

PyRQA—Conducting recurrence quantification analysis on very long time series efficiently

PyRQA is a software package that efficiently conducts recurrence quantification analysis (RQA) on time series consisting of more than one million data points. RQA is a method from non-linear time series analysis that quantifies the recurrent behaviour of systems. Existing implementations to RQA are not capable of analysing such very long time series at all or require large amounts of time to calculate the quantitative measures. PyRQA overcomes their limitations by conducting the RQA computations in a highly parallel manner. Building on the OpenCL framework, PyRQA leverages the computing capabilities of a variety of parallel hardware architectures, such as GPUs. The underlying computing approach partitions the RQA computations and enables to employ multiple compute devices at the same time. The goal of this publication is to demonstrate the features and the runtime efficiency of PyRQA. For this purpose we employ a real-world example, comparing the dynamics of two climatological time series, and a synthetic example, reducing the runtime regarding the analysis of a series consisting of over one million data points from almost eight hours using state-of-the-art RQA software to roughly 69s using PyRQA.

Mobile 4K / 2K / HD video streaming supported by real-time FEC raptorQ codes

With the growth of packet-switch networks in the mobile consumer electronics market, fountain codes are coming to play an increasingly important role as they allow high packet loss rates while still supporting high QoS. This is particularly critical for video streaming in multimedia delivery on moving handheld mobile consumer devices. A powerful forward error-correction mechanism is the fountain coding scheme implemented by RaptorQ codes, defined over GF(256), whose decoding algorithms are very complex from a computational perspective, but highly suitable for parallelization. With multimedia delivery for handheld consumer electronics in mind, this paper proposes several decoding schemes for embedded mobile SoCs, exploiting both the parallel potential of the GPU and CPU, sharing a common memory space. The OpenCL and OpenMP frameworks are used to exploit both accelerators for the roles of matrix multiplication and inversion that comprise the bulk of computation in RaptorQ decoding. Reported results indicate low-power requirements within the range of typical handheld consumer devices (1.5~2.4W) for data processing rates of dozens of Mbit/s that are fully within the real-time requirements of HD, 2K and 4K coded video streaming resolutions and beyond.

Nested MC-Based Risk Measurement of Complex Portfolios: Acceleration and Energy Efficiency

Risk analysis and management currently have a strong presence in financial institutions, where high performance and energy efficiency are key requirements for acceleration systems, especially when it comes to intraday analysis. In this regard, we approach the estimation of the widely-employed portfolio risk metrics value-at-risk (VaR) and conditional value-at-risk (cVaR) by means of nested Monte Carlo (MC) simulations. We do so by combining theory and software/hardware implementation. This allows us for the first time to investigate their performance on heterogeneous compute systems and across different compute platforms, namely central processing unit (CPU), many integrated core (MIC) architecture XeonPhi, graphics processing unit (GPU), and field-programmable gate array (FPGA). To this end, the OpenCL framework is employed to generate portable code, and the size of the simulations is scaled in order to evaluate variations in performance. Furthermore, we assess different parallelization schemes, and the targeted platforms are evaluated and compared in terms of runtime and energy efficiency. Our implementation also allowed us to derive a new algorithmic optimization regarding the generation of the required random number sequences. Moreover, we provide specific guidelines on how to properly handle these sequences in portable code, and on how to efficiently implement nested MC-based VaR and cVaR simulations on heterogeneous compute systems.

OpenCL/CUDA algorithms for parallel decoding of any irregular LDPC code using GPU

The development of multicore architectures supporting parallel data processing has led to a paradigm shift, which affects communication systems significantly. This article provides a scalable parallel approach of an iterative LDPC decoder, presented in a tutorial-based style. It is suitable for decoding any irregular LDPC code without the limitation of the maximum node degree, and it includes a parallel calculation of the syndrome. This is the main difference from algorithms presented so far. The proposed approach can be implemented in applications supporting massive parallel computing, such as GPU or FPGA devices. The implementation of the LDPC decoder with the use the OpenCL and CUDA frameworks is discussed and the performance evaluation is given at the end of this contribution.

Parallel LDPC Decoding on a Heterogeneous Platform using OpenCL

Modern mobile devices are equipped with various accelerated processing units to handle computationally intensive applications; therefore, Open Computing Language (OpenCL) has been proposed to fully take advantage of the computational power in heterogeneous systems. This article introduces a parallel software decoder of Low Density Parity Check (LDPC) codes on an embedded heterogeneous platform using an OpenCL framework. The LDPC code is one of the most popular and strongest error correcting codes for mobile communication systems. Each step of LDPC decoding has different parallelization characteristics. In the proposed LDPC decoder, steps suitable for task-level parallelization are executed on the multi-core central processing unit (CPU), and steps suitable for data-level parallelization are processed by the graphics processing unit (GPU). To improve the performance of OpenCL kernels for LDPC decoding operations, explicit thread scheduling, vectorization, and effective data transfer techniques are applied. The proposed LDPC decoder achieves high performance and high power efficiency by using heterogeneous multi-core processors on a unified computing framework.

An OpenCL software compilation framework targeting an SoC-FPGA VLIW chip multiprocessor

Modern systems-on-chip augment their baseline CPU with coprocessors and accelerators to increase overall computational capability and power efficiency, and thus have evolved into heterogeneous multi-core systems. Several languages have been developed to enable this paradigm shift, including CUDA and OpenCL. This paper discusses a unified compilation environment to enable heterogeneous system design through the use of OpenCL and a highly configurable VLIW Chip Multiprocessor architecture known as the LE1. An LLVM compilation framework was researched and a prototype developed to enable the execution of OpenCL applications on a number of hardware configurations of the LE1 CMP. The presented OpenCL framework fully automates the compilation flow and supports work-item coalescing which better maps onto the ILP processor cores of the LE1 architecture. This paper discusses in detail both the software stack and target hardware architecture and evaluates the scalability of the proposed framework by running 12 industry-standard OpenCL benchmarks drawn from the AMD SDK and the Rodinia suites. The benchmarks are executed on 40 LE1 configurations with 10 implemented on an SoC-FPGA and the remaining on a cycle-accurate simulator. Across 12 OpenCL benchmarks results demonstrate near-linear wall-clock performance improvement of 1.8 × (using 2 dual-issue cores), up to 5.2 × (using 8 dual-issue cores) and on one case, super-linear improvement of 8.4 × (FixOffset kernel, 8 dual-issue cores). The number of OpenCL benchmarks evaluated makes this study one of the most complete in the literature.

A distributed OpenCL framework using redundant computation and data replication

Applications written solely in OpenCL or CUDA cannot execute on a cluster as a whole. Most previous approaches that extend these programming models to clusters are based on a common idea: designating a centralized host node and coordinating the other nodes with the host for computation. However, the centralized host node is a serious performance bottleneck when the number of nodes is large. In this paper, we propose a scalable and distributed OpenCL framework called SnuCL-D for large-scale clusters. SnuCL-D's remote device virtualization provides an OpenCL application with an illusion that all compute devices in a cluster are confined in a single node. To reduce the amount of control-message and data communication between nodes, SnuCL-D replicates the OpenCL host program execution and data in each node. We also propose a new OpenCL host API function and a queueing optimization technique that significantly reduce the overhead incurred by the previous centralized approaches. To show the effectiveness of SnuCL-D, we evaluate SnuCL-D with a microbenchmark and eleven benchmark applications on a large-scale CPU cluster and a medium-scale GPU cluster.

SU‐C‐BRC‐06: OpenCL‐Based Cross‐Platform Monte Carlo Simulation Package for Carbon Ion Therapy

Purpose:Monte Carlo (MC) simulation is considered to be the most accurate method for calculation of absorbed dose and fundamental physical quantities related to biological effects in carbon ion therapy. Its long computation time impedes clinical and research applications. We have developed an MC package, goCMC, on parallel processing platforms, aiming at achieving accurate and efficient simulations for carbon therapy.Methods:goCMC was developed under OpenCL framework. It supported transport simulation in voxelized geometry with kinetic energy up to 450 MeV/u. Class II condensed history algorithm was employed for charged particle transport with stopping power computed via Bethe‐Bloch equation. Secondary electrons were not transported with their energy locally deposited. Energy straggling and multiple scattering were modeled. Production of secondary charged particles from nuclear interactions was implemented based on cross section and yield data from Geant4. They were transported via the condensed history scheme. goCMC supported scoring various quantities of interest e.g. physical dose, particle fluence, spectrum, linear energy transfer, and positron emitting nuclei.Results:goCMC has been benchmarked against Geant4 with different phantoms and beam energies. For 100 MeV/u, 250 MeV/u and 400 MeV/u beams impinging to a water phantom, range difference was 0.03 mm, 0.20 mm and 0.53 mm, and mean dose difference was 0.47%, 0.72% and 0.79%, respectively. goCMC can run on various computing devices. Depending on the beam energy and voxel size, it took 20∼100 seconds to simulate 107 carbons on an AMD Radeon GPU card. The corresponding CPU time for Geant4 with the same setup was 60∼100 hours.Conclusion:We have developed an OpenCL‐based cross‐platform carbon MC simulation package, goCMC. Its accuracy, efficiency and portability make goCMC attractive for research and clinical applications in carbon therapy.

PARALLELISATION OF THE MODEL-BASED ITERATIVE RECONSTRUCTION ALGORITHM DIRA.

New paradigms for parallel programming have been devised to simplify software development on multi-core processors and many-core graphical processing units (GPU). Despite their obvious benefits, the parallelisation of existing computer programs is not an easy task. In this work, the use of the Open Multiprocessing (OpenMP) and Open Computing Language (OpenCL) frameworks is considered for the parallelisation of the model-based iterative reconstruction algorithm DIRA with the aim to significantly shorten the code's execution time. Selected routines were parallelised using OpenMP and OpenCL libraries; some routines were converted from MATLAB to C and optimised. Parallelisation of the code with the OpenMP was easy and resulted in an overall speedup of 15 on a 16-core computer. Parallelisation with OpenCL was more difficult owing to differences between the central processing unit and GPU architectures. The resulting speedup was substantially lower than the theoretical peak performance of the GPU; the cause was explained.

Large Scale Tissue Morphogenesis Simulation on Heterogenous Systems Based on a Flexible Biomechanical Cell Model.

The complexity of biological tissue morphogenesis makes in silico simulations of such system very interesting in order to gain a better understanding of the underlying mechanisms ruling the development of multicellular tissues. This complexity is mainly due to two elements: firstly, biological tissues comprise a large amount of cells; secondly, these cells exhibit complex interactions and behaviors. To address these two issues, we propose two tools: the first one is a virtual cell model that comprise two main elements: firstly, a mechanical structure (membrane, cytoskeleton, and cortex) and secondly, the main behaviors exhibited by biological cells, i.e., mitosis, growth, differentiation, molecule consumption, and production as well as the consideration of the physical constraints issued from the environment. An artificial chemistry is also included in the model. This virtual cell model is coupled to an agent-based formalism. The second tool is a simulator that relies on the OpenCL framework. It allows efficient parallel simulations on heterogenous devices such as micro-processors or graphics processors. We present two case studies validating the implementation of our model in our simulator: cellular proliferation controlled by cell signalling and limb growth in a virtual organism.

Near Video-Rate Optical Coherence Elastography by Acceleration With a Graphics Processing Unit

We present a graphics processing unit (GPU)-accelerated optical coherence elastography (OCE) system capable of generating strain images (elastograms) of soft tissue at near video-rates. The system implements phase-sensitive compression OCE using a pipeline of GPU kernel functions to enable a highly parallel implementation of OCE processing using the OpenCL framework. Developed on a commercial-grade GPU and desktop computer, the system achieves a processing rate of 21 elastograms per second at an image size of 960 × 400 pixels, enabling high-rate visualization during acquisition. The system is demonstrated on both tissue-simulating phantoms and fresh ex vivo mouse muscle. To the best of our knowledge, this is the first implementation of near video-rate OCE and the fastest reported OCE processing rate, enabling, for the first time, a system capable of computing and displaying OCE elastograms interactively during acquisition. This advance provides new opportunities for medical imaging of soft tissue stiffness using optical methods.

Optimization of operating and assembling mass properties of solid elements on heterogeneous platforms using OpenCL framework

Model sizes have increased significantly in the fields of engineering and scientific computation. Some additional computing devices such as GPU, accelerators and co-processors have been applied to improve the computation performance. This paper presents several strategies to optimize the computation performance. The first strategy is to combine a computation unit with multiple of 4-tetrahedrons to support AVX vectorization. The second strategy is to utilize a GPU device. Several techniques are proposed to reduce the time for data exchange between host and GPU memory spaces. The proposed techniques are implemented by using OpenCL framework. The mass property of many solid finite elements is calculated and its computation performances on various computation platforms are compared. Numerical experiments showed that computation performance has improved 26.47 times on CPU and 6.95 on GPU, compared to the version without using the proposed techniques.

AQUAgpusph, a new free 3D SPH solver accelerated with OpenCL

In this paper, AQUAgpusph, a new free Smoothed Particle Hydrodynamics (SPH) software accelerated with OpenCL, is described. The main differences and progress with respect to other existing alternatives are considered. These are the use of the Open Computing Language (OpenCL) framework instead of the Compute Unified Device Architecture (CUDA), the implementation of the most popular boundary conditions, the easy customization of the code to different problems, the extensibility with regard to Python scripts, and the runtime output which allows the tracking of simulations in real time, or a higher frequency in saving some results without a significant performance lost. These modifications are shown to improve the solver speed, the results quality, and allow for a wider areas of application. AQUAgpusph has been designed trying to provide researchers and engineers with a valuable tool to test and apply the SPH method. Three practical applications are discussed in detail. The evolution of a dam break is used to quantify and compare the computational performance and modeling accuracy with the most popular SPH Graphics Processing Unit (GPU) accelerated alternatives. The dynamics of a coupled system, a Tuned Liquid Damper (TLD), is discussed in order to show the integration capabilities of the solver with external dynamics. Finally, the sloshing flow inside a nuclear reactor is simulated in order to show the capabilities of the solver to treat 3-D problems with complex geometries and of industrial interest. Program summaryProgram title: AQUAgpusph 1.5Catalogue identifier: AEVG_v1_0Program summary URL:http://cpc.cs.qub.ac.uk/summaries/AEVG_v1_0.htmlProgram obtainable from: CPC Program Library, Queen’s University, Belfast, N. IrelandLicensing provisions: GNU General Public License, version 3No. of lines in distributed program, including test data, etc.: 1702666No. of bytes in distributed program, including test data, etc.: 75117178Distribution format: tar.gzProgramming language: C++, OpenCL, Python.Computer: Linux based computers with OpenCL support.Operating system: Linux.Has the code been vectorized or parallelized?: Code is parallelized with OpenCL.Classification: 1.5.Nature of problem: Complex geometry or heavily fragmented free surface fluid dynamics problems where mesh based method cannot be successfully applied.Solution method: SPH is a meshless method where the fluid domain is discretized as a set of fluid particles. The fields in the fluid domain are smoothed using a kernel function, that allows to develop differential operators from the flow field values in scattered sets of particles.Running time: Using an AMD HD-7970 graphic device 2×105 time steps of a 2-D simulation, with 105 particles and 8×102 neighs per particle, is requiring around 9 h of computation. A more detailed performance analysis will be carried out in the practical application section herein.

Accelerated gradient-based free form deformable registration for online adaptive radiotherapy

The registration of planning fan-beam computed tomography (FBCT) and daily cone-beam CT (CBCT) is a crucial step in adaptive radiation therapy. The current intensity-based registration algorithms, such as Demons, may fail when they are used to register FBCT and CBCT, because the CT numbers in CBCT cannot exactly correspond to the electron densities. In this paper, we investigated the effects of CBCT intensity inaccuracy on the registration accuracy and developed an accurate gradient-based free form deformation algorithm (GFFD). GFFD distinguishes itself from other free form deformable registration algorithms by (a) measuring the similarity using the 3D gradient vector fields to avoid the effect of inconsistent intensities between the two modalities; (b) accommodating image sampling anisotropy using the local polynomial approximation-intersection of confidence intervals (LPA-ICI) algorithm to ensure a smooth and continuous displacement field; and (c) introducing a ‘bi-directional’ force along with an adaptive force strength adjustment to accelerate the convergence process. It is expected that such a strategy can decrease the effect of the inconsistent intensities between the two modalities, thus improving the registration accuracy and robustness. Moreover, for clinical application, the algorithm was implemented by graphics processing units (GPU) through OpenCL framework. The registration time of the GFFD algorithm for each set of CT data ranges from 8 to 13 s. The applications of on-line adaptive image-guided radiation therapy, including auto-propagation of contours, aperture-optimization and dose volume histogram (DVH) in the course of radiation therapy were also studied by in-house-developed software.

PARALLEL KNN ON GPU ARCHITECTURE USING OPENCL

In data mining applications, one of the useful algorithms for classification is the kNN algorithm. The kNN search has a wide usage in many research and industrial domains like 3-dimensional object rendering, content-based image retrieval, statistics, biology (gene classification), etc. In spite of some improvements in the last decades, the computation time required by the kNN search remains the bottleneck for kNN classification, especially in high dimensional spaces. This bottleneck has created the necessity of the parallel kNN on commodity hardware. GPU and OpenCL architecture are the low cost high performance solutions for parallelising the kNN classifier. In regard to this, we have designed, implemented our proposed parallel kNN model to improve upon performance bottleneck issue of kNN algorithm. In this paper, we have proposed parallel kNN algorithm on GPU and OpenCL framework. In our approach, we distributed the distance computations of the data points among all GPU cores. Multiple threads invoked for each GPU core. We have implemented and tested our parallel kNN implementation on UCI datasets. The experimental results show that the speedup of the KNN algorithm is improved over the serial performance.

Parallel outlier detection on uncertain data for GPUs

Outlier detection, also known as anomaly detection, is a common data mining task in identifying data points that are outside expected patterns in a given dataset. It has useful applications such as network intrusion, system faults, and fraudulent activity. In addition, real world data are uncertain in nature and they may be represented as uncertain data. In this paper, we propose an improved parallel algorithm for outlier detection on uncertain data using density sampling and develop an implementation running on both GPUs and multi-core CPUs, using the OpenCL framework. Our main focus is on GPUs, as they are a cost effective massively parallel floating point processor that is suitable for many data mining applications. Our implementation exploits some key features in GPUs, and is significantly different from a traditional CPU implementation. We first present an improved uncertain outlier detection algorithm. Then, we demonstrate two parallel micro-clustering implementations. The performance and detection quality comparisons demonstrate the benefits of the improved algorithm and parallel implementation on GPUs.

Heterogeneous and Elastic Computation Framework for Mobile Cloud Computing

The number and variety of applications for mobile devices continue to grow. However, the resources on mobile devices including computation and storage do not keep pace with the growth. How to incorporate the computation capacity on cloud servers into mobile computing has been desired and challenge issues to resolve. In this work, we design an elastic computation framework to take advantage the heterogeneous computation capacity on cloud servers, which consist of CPUs and GPGPUs, to meet the computation demands of ever growing mobile applications. The computation framework extends OpenCL framework to link remote processors with local mobile applications. The framework is flexible in the sense that the computation can be stopped at any time and gains results, which is called imprecise computation in real-time computing literature. The framework has been evaluated against OpenCL benchmark and physical computation engine for gaming. The results show that the framework supports OpenCL benchmark, RODINIA, without modifying the codes with few exceptions. The elastic computation framework allows the cloud servers to support more mobile clients without sacrificing their QoS requirements. The experiment results also show that IO intensive applications do not perform well when the network capacity is insufficient or unreliable.

Parallel track reconstruction in CMS using the cellular automaton approach

The Compact Muon Solenoid (CMS) experiment at the Large Hadron Collider (LHC) is a general-purpose particle detector and comprises the largest silicon-based tracking system built to date with 75 million individual readout channels. The precise reconstruction of particle tracks from this tremendous amount of input channels is a compute-intensive task. The foreseen LHC beam parameters for the next data taking period, starting in 2015, will result in an increase in the number of simultaneous proton-proton interactions and hence the number of particle tracks per event. Due to the stagnating clock frequencies of individual CPU cores, new approaches to particle track reconstruction need to be evaluated in order to cope with this computational challenge. Track finding methods that are based on cellular automata (CA) offer a fast and parallelizable alternative to the well-established Kalman filter-based algorithms. We present a new cellular automaton based track reconstruction, which copes with the complex detector geometry of CMS. We detail the specific design choices made to allow for a high-performance computation on GPU and CPU devices using the OpenCL framework. We conclude by evaluating the physics performance, as well as the computational properties of our implementation on various hardware platforms and show that a significant speedup can be attained by using GPU architectures while achieving a reasonable physics performance at the same time.

Design of OpenCL framework for embedded multi-core processors

In modern mobile embedded systems, various energy-efficient hardware acceleration units are employed in addition to a multi-core CPU. To fully utilize the computational power in such heterogeneous systems, Open Computing Language (OpenCL) has been proposed. A key benefit of OpenCL is that it works on various computing platforms. However, most vendors offer OpenCL software development kits (SDKs) that support their own computing platforms. The study of the OpenCL framework for embedded multi-core CPUs is in a rudimentary stage. In this paper, an OpenCL framework for embedded multi-core CPUs that dynamically redistributes the time-varying workload to CPU cores in real time is proposed. A compilation environment for both host programs and OpenCL kernel programs was developed and OpenCL libraries were implemented. A performance evaluation was carried out with respect to various definitions of the device architecture and the execution model. When running on embedded multi-core CPUs, applications parallelized by OpenCL C showed much better performance than the applications written in C without parallelization. Furthermore, since programmers are capable of managing hardware resources and threads using OpenCL application programming interfaces (APIs) automatically, highly efficient computing both in terms of the performance and energy consumption on a heterogeneous computing platform can be easily achieved.

A GPGPU based program to solve the TDSE in intense laser fields through the finite difference approach

We present a General-purpose computing on graphics processing units (GPGPU) based computational program and framework for the electronic dynamics of atomic systems under intense laser fields. We present our results using the case of hydrogen, however the code is trivially extensible to tackle problems within the single-active electron (SAE) approximation. Building on our previous work, we introduce the first available GPGPU based implementation of the Taylor, Runge–Kutta and Lanczos based methods created with strong field ab-initio simulations specifically in mind; CLTDSE. The code makes use of finite difference methods and the OpenCL framework for GPU acceleration. The specific example system used is the classic test system; Hydrogen. After introducing the standard theory, and specific quantities which are calculated, the code, including installation and usage, is discussed in-depth. This is followed by some examples and a short benchmark between an 8 hardware thread (i.e. logical core) Intel Xeon CPU and an AMD 6970 GPU, where the parallel algorithm runs 10 times faster on the GPU than the CPU. Program summaryProgram title: CLTDSECatalogue identifier: AESM_v1_0Program summary URL:http://cpc.cs.qub.ac.uk/summaries/AESM_v1_0.htmlProgram obtainable from: CPC Program Library, Queen’s University, Belfast, N. IrelandLicensing provisions: GNU General Public License, version 3 and aboveNo. of lines in distributed program, including test data, etc.: 15988No. of bytes in distributed program, including test data, etc.: 233518Distribution format: tar.gzProgramming language: C99 and OpenCL C. C99 conformance is ensured through use of C99 and pedantic flags under GCC and Clang.Computer: Single compute node.Operating system: GNU/Linux. It should, in principle, work with little modification for other Unix-Like systems.Has the code been vectorised or parallelised?: OpenCL is a parallel language. Thus CLTDSE can use all cores on a processor or GPU. OpenCL supports using all available compute units (GPUs and CPUs etc.), although this is not currently implemented in CLTDSE.RAM: Negligible RAM and GPU global memory (20MiB)Classification: 2.5.External routines: An OpenCL library; the current major packages are APP by AMD (CPU and AMD GPU), the NVIDIA driver (GPU), and the Intel SDK for OpenCL Applications (CPU and Intel HD Graphics). libconfig for processing configuration files.Nature of problem:Describing the dynamics of electrons under intense laser fields in atoms or molecules.Solution method:Solving the discretised system through finite difference using the Lanczos, Runge–Kutta, and Taylor methods.Restrictions:The example problem which is implemented is under the single active electron approximation.Unusual features:Focused on GPGPU acceleration through OpenCL.Running time:The running time depends on the nature of the pulse. This can vary from seconds to tens of minutes.