arma-thesis

git clone https://git.igankevich.com/arma-thesis.git
Log | Files | Refs | LICENSE

commit b3bc215443956376db2508057e72be0b2d8c5af0
parent d5ca7544b2367bd68371b9acd56b634896ceca18
Author: Ivan Gankevich <igankevich@ya.ru>
Date:   Mon,  7 Aug 2017 14:18:04 +0300

Add platform configuration and model input parameters.

Diffstat:
arma-thesis.org | 28++++++++++++++++++++++++----
1 file changed, 24 insertions(+), 4 deletions(-)

diff --git a/arma-thesis.org b/arma-thesis.org @@ -3436,6 +3436,9 @@ kernel is routed to one of the thread from the device thread pool. Non-homogeneous kernels may be handled by predicting their execution time, but such kernels are not present in ARMA model implementation. +**** Parallel AR, MA and LH implementations. + + **** Performance of OpenMP and OpenCL implementations. :PROPERTIES: :header-args:R: :results output org @@ -3456,6 +3459,17 @@ transcendental functions and heavy use of FFT, not to mention that high convergence rate and non-existence of periodicity allows to use far fewer coefficients compared to LH model. +#+name: tab-gpulab +#+caption: GPU test platform configuration. +#+attr_latex: :booktabs t +| CPU | AMD FX-8370 | +| RAM | 16Gb | +| GPU | GeForce GTX 1060 | +| GPU memory | 6GB | +| HDD | WDC WD40EZRZ-00WN9B0, 5400rpm | +| No. of CPU cores | 4 | +| No. of threads per core | 2 | + ARMA implementation uses several libraries of mathematical functions, numerical algorithms and visualisation primitives (listed in table\nbsp{}[[tab-arma-libs]]), and was implemented using several parallel programming technologies (OpenMP, @@ -3467,10 +3481,16 @@ surface. For each technology the programme was recompiled and run multiple times and performance of each top-level subroutine was measured using system clock. Results of benchmarks of the technologies are summarised in table\nbsp{}[[tab-arma-performance]]. All benchmarks were run on a machine equipped -with a GPU, characteristics of which are summarised in table\nbsp{}. In all -benchmarks wavy surface generation takes the most of the running time, whereas -velocity potential calculation together with other subroutines only a small -fraction of it. +with a GPU, characteristics of which are summarised in table\nbsp{}[[tab-gpulab]]. +All benchmarks were run with the same input parameters for all the models: +realisation length 10000s and output grid size \(40\times40\)m. The only +parameter that was different is the order (the number of coefficients): order of +AR and MA model was \(7,7,7\) and order of LH model was \(40,40\). This is due +to higher number of coefficient for LH model to eliminate periodicity. + +In all benchmarks wavy surface generation takes the most of the running time, +whereas velocity potential calculation together with other subroutines only a +small fraction of it. #+name: tab-arma-libs #+caption: A list of mathematical libraries used in ARMA model implementation.