SkePU is a C++ template library with a simple and unified interface for expressing data parallel computations in terms of generic components, called skeletons, on multi-GPU systems using CUDA and OpenCL. The smart containers in SkePU, such as Matrix and Vector, perform data management with a lazy memory copying mechanism that reduces redundant data communication. SkePU provides programmability,...

Existing formats for SparseMatrix-Vector Multiplication (SpMV) on the GPU are outperforming their corresponding implementations on multi-core CPUs. In this paper, we present a new format called Sliced COO (SCOO) and an efficient CUDA implementation to perform SpMV on the GPU. While previous work shows experiments on small to medium-sized sparse matrices, we perform evaluations on large sparse m...

Much of the current focus in high-performance computing is on multi-threading, multi-computing, and graphics processing unit (GPU) computing. However, vectorization and non-parallel optimization techniques, which can often be employed additionally, are less frequently discussed. In this paper, we present an analysis of several optimizations done on both central processing unit (CPU) and GPU imp...

This paper studies the performance of separable 2D convolution on multi-lane Polymorphic Register Files (PRFs). We present a matrix transposition algorithm optimized for PRFs, and a 2D vectorized convolution algorithm which avoids strided memory accesses. We compare the throughput of our PRF to the nVidia Tesla C2050 GPU. The results show that even in bandwidth constrained systems, multi-lane P...

Medical image registration is time-consuming but can be sped up employing parallel processing on the GPU. Normalized mutual information (NMI) is a well performing similarity measure for performing multi-modal registration. We present CUDA based solutions for computing NMI on the GPU and compare the results obtained by rigidly registering multi-modal data sets with a CPU based implementation. Ou...

Due to the power and frequency walls, the trend is now to use multiple GPUs on a given system, much like you will find multiple cores on CPU-based systems. However, increasing the hierarchy of resource widens the spectrum of factors that may impact on the performance of the system. The goal of this paper is to analyze such factors by investigating and benchmarking the NVIDIA Tesla S1070. This s...

We analyze two parallel finite element implementations of the 2D time-dependent advection diffusion problem, one for multi-core clusters and one for CUDA-enabled GPUs, and compare their performances in terms of time and energy consumption. The parallel CUDA-enabled GPU implementation was derived from the multi-core cluster version. Our experimental results show that a desktop machine with a sin...

The computational performance of multi-GPU applications can be degraded by the data communication between each GPU. To realize high-speed computation with multiple GPUs, we should minimize the cost of this data communication. In this paper, I propose a multiple GPU computing method for the Swendsen–Wang (SW) multi-cluster algorithm that reduces the data traffic between each GPU. I realize this ...