Solutions for Optimizing the Stream Compaction Algorithmic Function Using the Compute Unified Device Architecture
نویسنده
چکیده
In this paper, I have researched and developed solutions for optimizing the stream compaction algorithmic function using the Compute Unified Device Architecture (CUDA). The stream compaction is a common parallel primitive, an essential building block for many data processing algorithms, whose optimization improves the performance of a wide class of parallel algorithms useful in data processing. A particular interest in this research was to develop solutions for optimizing the stream compaction algorithmic function that offers optimal solutions over an entire range of CUDA enabled GPUs: Tesla GT200, Fermi GF100 and the latest Kepler GK104 architecture, released on 22 March 2012. In order to confirm the utility of the developed optimization solutions, I have extensively benchmarked and evaluated the performance of the stream compaction algorithmic function in CUDA.
منابع مشابه
Experimental Investigation of Metal Powder Compaction without Using Lubricant
The main objective of this work was to design a novel device for compaction of metal powders so that the green parts could be ejected with applying a negligible force and without the need for any lubricant in either an admixed form or applied to the die wall. For this purpose a 40 mm diameter one-piece die was envisaged which would elastically contracted 0.076 mm before compaction and after com...
متن کاملNumerical Modelling of Dynamic Compaction in Dry Sandy Soils for Determination of Effective Print Spacing
Dynamic compaction (DC) is a widely used soil improvement method in dry and/or saturated soils. The design of DC treatment is usually carried out based on the past experiences and empirical relations. In order to clarify the ambiguities in DC processes, numerical modeling of DC in dry granular soils has been considered using a dynamic finite element code. Using the developed model, two design c...
متن کاملThe Role of Algorithmic Applications in the Development of Architectural Forms (Case Study:Nine High-Rise Buildings)
The process of developing architectural forms has greatly been changed by advances in digital technology, especially in design tools and applications. In recent years, the advent of graphical scripting languages in the design process has profoundly affected 3D modeling. Scripting languages help develop algorithms and geometrical grammar of shapes based on their constituent parameters. This stud...
متن کاملA comparative study between two numerical solutions of the Navier-Stokes equations
The present study aimed to investigate two numerical solutions of the Navier-Stokes equations. For this purpose, the mentioned flow equations were written in two different formulations, namely (i) velocity-pressure and (ii) vorticity-stream function formulations. Solution algorithms and boundary conditions were presented for both formulations and the efficiency of each formulation was investiga...
متن کاملRecognition of convolutional neural network based on CUDA Technology
For the problem whether Graphic Processing Unit(GPU),the stream processor with high performance of floating— point computing is applicable to neural networks, this paper proposes the parallel recognition algorithm of Convolutional Neural Networks(CNNs).It adopts Compute Unified Device Architecture(CUDA)technology, definite the parallel data structures, and describes the mapping mechanism for co...
متن کامل