GPU implementation of belief propagation using CUDA for cloud tracking and reconstruction

Grauer-Gray, Scott; Kambhamettu, Chandra; Palaniappan, Kannappan

doi:10.1109/prrs.2008.4783169

Cited by 38 publications

(16 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [26], Yang implemented some of the best-known operators such as binarization and filtering by CUDA. Moreover, in [28], Gray uses CUDA for Motion Tracking. The next section presents the implementation of the parallel algorithm using the hamming network in CUDA.…”

Section: Using Cuda In Parallel Processingmentioning

confidence: 99%

Isolated Persian/Arabic handwriting characters: Derivative projection profile features, implemented on GPUs

Askari

Asadi

Bidgoli

et al. 2016

JAIDM

View full text Add to dashboard Cite

For many years, researchers have studied high accuracy methods for recognizing the handwriting and achieved many significant improvements. However, an issue that has rarely been studied is the speed of these methods. Considering the computer hardware limitations, it is necessary for these methods to run in high speed. One of the methods to increase the processing speed is to use the computer parallel processing power. This paper introduces one of the best feature extraction methods for the handwritten recognition, called DPP (Derivative Projection Profile), which is employed for isolated Persian handwritten recognition. In addition to achieving good results, this (computationally) light feature can easily be processed. Moreover, Hamming Neural Network is used to classify this system. To increase the speed, some part of the recognition method is executed on GPU (graphic processing unit) cores implemented by CUDA platform. HADAF database (Biggest isolated Persian character database) is utilized to evaluate the system. The results show 94.5% accuracy. We also achieved about 5.5 times speed-up using GPU.

show abstract

Section: Using Cuda In Parallel Processingmentioning

confidence: 99%

Isolated Persian/Arabic handwriting characters: Derivative projection profile features, implemented on GPUs

Askari

Asadi

Bidgoli

et al. 2016

JAIDM

View full text Add to dashboard Cite

show abstract

“…The implementation is run using a single level with 250 messagepassing iterations, with the optimized implementation determined in the same manner as in Section 5.3 using the transformations shown in Table 1. The CUDA and OpenCL results of the initial and best optimized HMPP implementations are in Figure 12 alongside results of a manual CUDA implementation developed by Grauer-Gray et al [15]. The speedup is relative to the initial sequential CPU implementation.…”

Section: Optimizing Belief Propagationmentioning

confidence: 99%

Auto-tuning a high-level language targeted to GPU codes

Grauer-Gray

Schleicher

et al. 2012

2012 Innovative Parallel Computing (InPar)

Self Cite

354

154

View full text Add to dashboard Cite

Determining the best set of optimizations to apply to a kernel to be executed on the graphics processing unit (GPU) is a challenging problem. There are large sets of possible optimization configurations that can be applied, and many applications have multiple kernels. Each kernel may require a specific configuration to achieve the best performance, and moving an application to new hardware often requires a new optimization configuration for each kernel.In this work, we apply optimizations to GPU code using HMPP, a high-level directive-based language and source-tosource compiler that can generate CUDA / OpenCL code. However, programming with high-level languages may mean a loss of performance compared to using low-level languages. Our work shows that it is possible to improve the performance of a high-level language by using auto-tuning. We perform auto-tuning on a large optimization space on GPU kernels, focusing on loop permutation, loop unrolling, tiling, and specifying which loop(s) to parallelize, and show results on convolution kernels, codes in the PolyBench suite, and an implementation of belief propagation for stereo vision. The results show that our auto-tuned HMPP-generated implementations are significantly faster than the default HMPP implementation and can meet or exceed the performance of manually coded CUDA / OpenCL implementations.

show abstract

“…Grauer-Gray [8] showed that each of the steps of the algorithm can be performed in parallel using the CUDA architecture, and the resulting disparity map is obtained more quickly using a CUDA implementation as compared to a sequential CPU implementation. However, that work does not discuss optimizations which can be applied to decrease the running time of the CUDA implementation.…”

Section: Cuda Belief Propagationmentioning

confidence: 99%

“…Brunton [2], Yang [18], Grauer-Gray ( [8] and [7]), Xu [19], Liang [10], and Ivanchenko [17] present implementations of belief propagation for stereo processing on the GPU. Brunton and Yang map their implementations to the graphics API, while Grauer-Gray, Xu, Liang, and Ivanchenko take advantage of the CUDA architecture.…”

Section: Introductionmentioning

confidence: 99%

Optimizing and Auto-tuning Belief Propagation on the GPU

Grauer-Gray

Cavazos

2011

Languages and Compilers for Parallel Computing

Self Cite

View full text Add to dashboard Cite

Abstract. A CUDA kernel will utilize high-latency local memory for storage when there are not enough registers to hold the required data or if the data is an array that is accessed using a variable index within a loop. However, accesses from local memory take longer than accesses from registers and shared memory, so it is desirable to minimize the use of local memory. This paper contains an analysis of strategies used to reduce the use of local memory in a CUDA implementation of belief propagation for stereo processing. We perform experiments using registers as well as shared memory as alternate locations for data initially placed in local memory, and then develop a hybrid implementation that allows the programmer to store an adjustable amount of data in shared, register, and local memory. We show results of running our optimized implementations on two different stereo sets and across three generations of nVidia GPUs, and introduce an auto-tuning implementation that generates an optimized belief propagation implementation on any input stereo set on any CUDA-capable GPU.

show abstract

GPU implementation of belief propagation using CUDA for cloud tracking and reconstruction

Abstract: Abstract

Cited by 38 publications

References 5 publications

Isolated Persian/Arabic handwriting characters: Derivative projection profile features, implemented on GPUs

Isolated Persian/Arabic handwriting characters: Derivative projection profile features, implemented on GPUs

Auto-tuning a high-level language targeted to GPU codes

Optimizing and Auto-tuning Belief Propagation on the GPU

Contact Info

Product

Resources

About