A number of technologies have emerged for accelerating similarity search algorithms in bioinformatics, including the use of field programmable gate arrays (FPGA), graphics processing units (GPU), and clusters of standard multicore CPUs. Here we present Tera-BLASTTM, an FPGA-accelerated implementation of the BLAST algorithm, and compare the performance to GPU-accelerated BLAST and the industry s...

GPU-to-CPU translation may extend Graphics Processing Units (GPU) programs executions to multi-/many-core CPUs, and hence enable cross-device task migration and promote whole-system synergy. This paper describes some of our findings in treatment to GPU synchronizations during the translation process. We show that careful dependence analysis may allow a fine-grained treatment to synchronizations...

We study two different techniques for the computation of a matrix inverse, the traditional approach based on Gaussian factorization and the Gauss-Jordan elimination alternative more suitable for parallel architectures. The target architecture is a current general-purpose multi-core processor (CPU) connected to a graphics processor (GPU). Parallelism is obtained from the use of libraries MKL (fo...

This paper presents an efficient technique for fast generation of sparse systems of linear equations arising in computational electromagnetics in a finite element method using higher order elements. The proposed approach employs a graphics processing unit (GPU) for both numerical integration and matrix assembly. The performance results obtained on a test platform consisting of a Fermi GPU (1x T...

We present efficient algorithms to build data structures and the lists needed for fast multipole methods. The algorithms are capable of being efficiently implemented on both serial, data parallel GPU and on distributed architectures. With these algorithms it is possible to map the FMM efficiently on to the GPU or distributed heterogeneous CPU-GPU systems. Further, in dynamic problems, as the di...

Agglomerative clustering is an effective greedy way to quickly generate graph clusterings of high modularity in a small amount of time. In an effort to use the power offered by multi-core CPU and GPU hardware to solve the clustering problem, we introduce a fine-grained shared-memory parallel graph coarsening algorithm and use this to implement a parallel agglomerative clustering heuristic on bo...

The efficiency of the simulations with discrete element method (DEM) is significantly improved using a novel computational strategy. new developed focus on platforms equipped multi-core central processing units (CPU) and general-purpose graphics (GPU). DEM calculations are performed in parallel CPU GPU pre-calculated Verlet lists posteriori analysis their consistency. operations related to sear...

Improving terrain tile data selection efficiency, real-time loading of visible tile data and building GPU-based continuous Level of Details (LOD) are the key technologies for large scale terrain rendering on GPU. In this article, in order to reduce terrain tile data selection time, we build double layers tile quad tree for massive terrain data and organize tile data by designing Z-order space f...

This paper discusses necessary components of a GPU-assisted traffic classification method, which is capable of multi-Gbps speeds on commodity hardware. The majority of the traffic classification is pushed to the GPU to offload the CPU, which then may serve other processing intensive tasks, e.g., traffic capture. The paper presents two massively parallelizable algorithms suitable for GPUs. The f...

In this work, we consider a standard architecture [1] trained on the Imagenet dataset [2] for classification and investigate methods to speed convergence by parallelizing training across multiple GPUs. In this work, we used up to 4 NVIDIA TITAN GPUs with 6GB of RAM. While our experiments are performed on a single server, our GPUs have disjoint memory spaces, and just as in the distributed setti...