A GPU-accelerated algorithm for self-organizing maps in a distributed environment
نویسندگان
چکیده
In this paper we introduce a MapReduce-based implementation of self-organizing maps that performs compute-bound operations on distributed GPUs. The kernels are optimized to ensure coalesced memory access and effective use of shared memory. We have performed extensive tests of our algorithms on a cluster of eight nodes with two NVidia Tesla M2050 attached to each, and we achieve a 10x speedup for self-organizing maps over a distributed CPU algorithm.
منابع مشابه
Accelerating text mining workloads in a MapReduce-based distributed GPU environment
Scientific computations have been using GPU-enabled computers successfully, often relying on distributed nodes to overcome the limitations of device memory. Only a handful of text mining applications benefit from such infrastructure. Since the initial steps of text mining are typically data-intensive, and the ease of deployment of algorithms is an important factor in developing advanced applica...
متن کاملSelf-Organizing Maps computing on Graphic Process Unit
Self-Organizing Maps (SOM) is a widely used artificial neural network (ANN) model. Because of its heavy computation load when the map is big and inherent parallel, there is a need to apply a parallel algorithm on it. As a SIMD parallel processor, Graphic processing unit (GPU) shows a fast growing speed than CPU. And it also provides programmability recently. In this paper, the algorithm and res...
متن کاملLandforms identification using neural network-self organizing map and SRTM data
During an 11 days mission in February 2000 the Shuttle Radar Topography Mission (SRTM) collected data over 80% of the Earth's land surface, for all areas between 60 degrees N and 56 degrees S latitude. Since SRTM data became available, many studies utilized them for application in topography and morphometric landscape analysis. Exploiting SRTM data for recognition and extraction of topographic ...
متن کاملImplementation of the direction of arrival estimation algorithms by means of GPU-parallel processing in the Kuda environment (Research Article)
Direction-of-arrival (DOA) estimation of audio signals is critical in different areas, including electronic war, sonar, etc. The beamforming methods like Minimum Variance Distortionless Response (MVDR), Delay-and-Sum (DAS), and subspace-based Multiple Signal Classification (MUSIC) are the most known DOA estimation techniques. The mentioned methods have high computational complexity. Hence using...
متن کاملImplementations of asynchronous self-organizing maps on OpenMP and MPI parallel computers
In [1], we presented an asynchronous parallel algorithm for self-organizing maps based on a recently defined energy function which leads to a self-organizing map. We generalized the existing stochastic gradient approach to an asynchronous parallel stochastic gradient method for generating a topological map on a distributed computer system (MIMD). We theoretically proved that our algorithm was c...
متن کامل