Classification training using libsvm

Question

I want to classify using libsvm. I have 9 training sets, each set has 144,000 marked instances, each instance has a variable number of functions. It takes about 12 hours to train one set (./svm-train with probabilistic estimates). Since I don't have much time, I would like to run more than one set at a time. I'm not sure if I can do this. Can I run all 9 processes simultaneously on different terminals?

./svm-train -b 1 feat1.txt
./svm-train -b 1 feat2.txt
      .
      .
      .
./svm-train -b 1 feat9.txt

(I am using fedora 5 core)

Answer 1

libsvm openmp . libsvm faq: http://www.csie.ntu.edu.tw/~cjlin/libsvm/faq.html#f432

Answer 2

, , . , EC2?

Infochimps MachetEC2 , : http://blog.infochimps.org/2009/02/06/start-hacking-machetec2-released/

Answer 3

Yes. But if you do not have a multi-core or multi-processor system, this may not save you a lot of time.