Accelerated Connected Component Labeling Using CUDA Framework

Paravecino, Fanny Nina; Kaeli, David

doi:10.1007/978-3-319-11331-9_60

Cited by 10 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dynamic Parallelism is reported to boost the hierarchical clustering on K20c up to 3.03 times [5]. Accelerated Connected Component Labeling using Hyper-Q outperforms serial version by 26x [25].…”

Section: Related Workmentioning

confidence: 96%

High performance computing of fiber scattering simulation

Zhang

Gong

et al. 2015

Proceedings of the 8th Workshop on General Purpose Processing Using GPUs

Self Cite

View full text Add to dashboard Cite

Cellulose is one of the most promising energy resources that is waiting to be tapped. Harvesting energy from cellulose requires decoding its atomic structure. Some structural information can be exposed by modeling data produced by X-ray scattering. Forward simulation can be used to explore structural parameters of cellulose, including the diameter, twist and coiling, but modeling fiber scattering is computationally challenging.In this paper, we explore how to accelerate a molecular scattering algorithm by leveraging a modern high-end Graphic Processing Unit (GPU). A step-wise optimization approach is described in this work that considers memory utilization, math intrinsics, concurrent kernel execution and workload partitioning. Different caching strategies to manage the state of the atom volume in memory are taken into account. We have developed optimized cluster solutions for both CPUs and GPUs. Different workload distribution schemes and concurrent execution approaches for both CPUs and GPUs have been investigated. Leveraging accelerators hosted on a cluster, we have reduced days/weeks of intensive simulation to parallel execution of just a few minutes/seconds. Our GPU-integrated cluster solution can potentially support concurrent modeling of hundreds of cellulose fibril structures, opening up new avenues for energy research.

show abstract

Section: Related Workmentioning

confidence: 96%

High performance computing of fiber scattering simulation

Zhang

Gong

et al. 2015

Proceedings of the 8th Workshop on General Purpose Processing Using GPUs

Self Cite

View full text Add to dashboard Cite

show abstract

“…Our Accelerated CCL (ACCL) implementation uses two scanning phases [22]. The first phase scans the image in parallel in a row-wise fashion to find contiguous pixels in the same row that can be assigned the same label.…”

Section: Connected Component Labeling (Ccl)mentioning

confidence: 99%

Nupar

Ukidave

Paravecino

et al. 2015

Proceedings of the 6th ACM/SPEC International Conference on Performance Engineering

Self Cite

View full text Add to dashboard Cite

Heterogeneous systems consisting of multi-core CPUs, Graphics Processing Units (GPUs) and many-core accelerators have gained widespread use by application developers and data-center platform developers. Modern day heterogeneous systems have evolved to include advanced hardware and software features to support a spectrum of application patterns. Heterogeneous programming frameworks such as CUDA, OpenCL, and OpenACC have all introduced new interfaces to enable developers to utilize new features on these platforms. In emerging applications, performance optimization is not only limited to effectively exploiting data-level parallelism, but includes leveraging new degrees of concurrency and parallelism to accelerate the entire application.To aid hardware architects and application developers in effectively tuning performance on GPUs, we have developed the NUPAR benchmark suite. The NUPAR applications belong to a number of different scientific and commercial computing domains. These benchmarks exhibit a range of GPU computing characteristics that consider memory-bandwidth limitations, device occupancy and resource utilization, synchronization latency and device-specific compute optimizations. The NUPAR applications are specifically designed to stress new hardware and software features that include: nested parallelism, concurrent kernel execution, shared hostdevice memory and new instructions for precise computation and data movement. In this paper, we focus our discussion on applications developed in CUDA and OpenCL, and focus on high-end server class GPUs. We describe these benchmarks and evaluate their interaction with different architectural features on a GPU. Our evaluation examines the behavior of the advanced hardware features on recently-released GPU architectures.

show abstract

“…The first scan can run in parallel by using shared memory, while the second scan is a sequential operation. ACCL [37] is another parallelization algorithm that decomposes the image into rows. By defining a span as a group of pixels that are located contiguously in a row with the same intensity, it spawns two kernels, find spans and merge spans, to label an input image.…”

Section: Line-based CCL Algorithmmentioning

confidence: 99%

Efficient Parallel Connected Component Labeling With a Coarse-to-Fine Strategy

et al. 2018

View full text Add to dashboard Cite

This paper proposes a new parallel approach to solve connected components on a 2D binary image implemented with CUDA. We employ the following strategies to accelerate neighborhood exploration after dividing an input image into independent blocks. In the local labeling stage, a coarse-labeling algorithm, including row-column connection and label-equivalence list unification, is applied first to sort out the mess of an initialized local label map; a refinement algorithm is then introduced to merge separated sub-regions from a single component. In the block merge stage, we scan the pixels located on the boundary of each block instead of solving the connectivity of all the pixels. With the proposed method, the length of label-equivalence lists is compressed, and the number of memory accesses is reduced. Thus, the efficiency of connected components labeling is improved. Experimental results show that our method outperforms the other approaches between 29% and 80% on average.

show abstract

Accelerated Connected Component Labeling Using CUDA Framework

Cited by 10 publications

References 4 publications

High performance computing of fiber scattering simulation

High performance computing of fiber scattering simulation

Nupar

Efficient Parallel Connected Component Labeling With a Coarse-to-Fine Strategy

Contact Info

Product

Resources

About