Energy Efficient Stencil Computations on the Low-Power Manycore MPPA-256 Processor

Podestá, Emmanuel; Nascimento, Bruno Marques do; Castro, Márcio

doi:10.1007/978-3-319-96983-1_46

Cited by 1 publication

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We differ from this work by not relying on sparse matrices to implement the Jacobi solver but by directly implementing the operators defined by those matrices. An implemenation on massively parallel processors of this solver is studied in [18] and also analyse the tradeoff between memory locality and overhead computa-tions. In [17], Nguyen et al compare several GPU solvers for fastest convergence and comes to similar conclusions as ours: more iterations on simpler solvers are more efficient on GPUs.…”

Section: Related Workmentioning

confidence: 99%

Real-time optical flow processing on embedded GPU: an hardware-aware algorithm to implementation strategy

Seznec

Gac

Orieux

et al. 2021

J Real-Time Image Proc

View full text Add to dashboard Cite

Determining the optical flow of a video is a compute-intensive task essential for computer vision. For achieving this processing in real-time, the whole algorithm deployment chain must be thought of for efficiency first. The development is usually divided into two parts: first, designing an algorithm that meets precision constraints, then, implementing and optimizing its execution on the targeted platform. We argue that unifying those operations enhances performance on the embedded processor.This paper is based on an industrial use case of computer vision. The objective is to determine dense optical flow in real-time on an embedded GPU platform: the Nvidia AGX Xavier. The CLG (Combined Local-Global) optical flow method, initially chosen, is analyzed to understand the convergence speed of its underlying optimization problem. The Jacobi solver is selected for implementation because of its parallel nature. The whole multi-level processing is then ported to the GPU, using several specific optimization strategies. In particular, we analyze the impact of fusing the solver's iterations with the roofline model.As a result, with a 30W power budget, our implementation runs at 60FPS, on 640 × 512 images, with a four-level processing. Hopefully, this example should provide feedback on the issues that arise when trying to port a method to a parallel platform and serve for further implementations of computer vision algorithms on specialized hardware.

show abstract

Section: Related Workmentioning

confidence: 99%