[R-SIG-Finance] Exploratory analyses: Experience using gputools-package for Nvidia graphics-accellerators?

[Dirk Eddelbuettel]

On 16 October 2009 at 20:10, Gero Schwenk wrote:
| Hi, dear finance modelers!
| I want to employ some systematic approach to explore promising 
| predictors for trading models. Therefore I think about experimenting 
| with parallel-processing on GPU's (Nvidia graphics accellerators) - 
| these are quite cheap (150-300€) and contain usually more than 240 
| processing units.
| 
| There is a package called "gputools" ( 
| http://cran.r-project.org/web/packages/gputools/index.html ) which seems 
| to originate from the bioinformatics-community and implements very 
| interesting functionality for exploratory analysis and large scale 
| predictive modeling. Among these are calculation of distance metrics for 
| clustering, tests for granger causality, approximation of the mutual 
| information, calculation of correlation coefficients, estimating and 
| predicting support vector machines and support vector regression.
| 
| Now my question: Does anybody have experience using this package or GPU- 
| resp. parallel-processing for exploration? Or do you use other 
| environments, resp. approaches?

For what it is worth I started looking into this two days ago when I took
possession of such an NVidia card (with a list price considerably above EUR
300 for its 192 cores) and I also started with the (nice) gputools package as
a starting point.

However, I'd say that this belongs onto r-sig-hpc.  "Just because" you (and
even I) would like to use it in Finance doesn't make it Finance. It is still
a methodological question somewhat orthogonal to what we do here, and more at
home on the High-Performance Computing list.

Again, those disagreeing with me are kindly invited to let me know off-list
if there was in fact a consensus to having such a discussion here.

Dirk

-- 
Three out of two people have difficulties with fractions.