OpenMP Code Offloading: Splitting GPU Kernels, Pipelining Communication and Computation, and Selecting Better Grid Geometries

Chikin, Artem; Gobran, Tyler; Amaral, José Nelson

doi:10.1007/978-3-030-12274-4_3

Cited by 1 publication

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to take advantage of modern computing resources, scientific application developers need to make significant changes to their implementations. There are many benchmarks and applications in computer vision that are built with OpenMP 4.x and 5.x [1][2][3], which provide an excellent opportunity to get access to the noticeable computational power of the GPUs through a directive based deployment. However, this programming style generally yields some unnecessary overhead that is inherent to the paradigm, thus the programmer needs to consider this aspect beside its application driven optimizations.…”

Section: Introductionmentioning

confidence: 99%

Memory Efficient Deployment of an Optical Flow Algorithm on GPU Using OpenMP

Haggui

Tadonki

Sayadi

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

In this paper, we consider the recent set of OpenMP directives related to GPU deployment and seek an evaluation through the case of an optical flow algorithm. We start by investigating various agnostic transformations that attempt to improve memory efficiency. Our case study is the so-called Lucas-Kanade algorithm, which is typically composed of a series of convolution masks (approximation of the derivatives) followed by 2 × 2 linear systems for the optical flow vectors. Since, we are dealing with a stencil computation for each stage of the algorithm, the overhead of memory accesses together with the impact on parallel scalability are expected to be noticeable, especially with the complexity of the GPU memory system. We compare our OpenMP implementation with an OpenACC one from our previous work, both on a Quadro P5000.

show abstract

Section: Introductionmentioning

confidence: 99%