Hi Antony, > Is it possible to pass custom linear operators (like in CUSP > (http://cusplibrary.github.io/classcusp_1_1linear__operator.html)) to > ViennaCL's solvers?
Yes, it is possible for iterative solvers. An example can be found in examples/tutorial/matrix-free.cpp or here: http://viennacl.sourceforge.net/doc/matrix-free_8cpp-example.html > Specifically, my use-case would be a product of matrices involving a > prefix-sum (which I haven't seen mentioned in ViennaCL's docs either, so > help would be welcome too) at some point. Thanks for pointing out the missing documentation on prefix sums. I created an issue here so that documentation is added in the next release: https://github.com/viennacl/viennacl-dev/issues/180 You can see example usage in tests/src/scan.cpp. Use as follows: viennacl::linalg::inclusive_scan(input, output); viennacl::linalg::inclusive_scan(inout); //in-place and similarly for exclusive_scan. 'input', 'output', and 'inout' are of type viennacl::vector<T> (or subvectors defined via vector_range/vector_slice) Best regards, Karli ------------------------------------------------------------------------------ Site24x7 APM Insight: Get Deep Visibility into Application Performance APM + Mobile APM + RUM: Monitor 3 App instances at just $35/Month Monitor end-to-end web transactions and take corrective actions now Troubleshoot faster and improve end-user experience. Signup Now! http://pubads.g.doubleclick.net/gampad/clk?id=272487151&iu=/4140 _______________________________________________ ViennaCL-support mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/viennacl-support
