You are viewing a plain text version of this content. The canonical link for it is here.

Posted to issues@systemml.apache.org by "Niketan Pansare (JIRA)" <ji...@apache.org> on 2016/10/12 22:29:21 UTC

[jira] [Created] (SYSTEMML-1034) Implement solve builtin function using cublas kernels

Niketan Pansare created SYSTEMML-1034:
-----------------------------------------

             Summary: Implement solve builtin function using cublas kernels
                 Key: SYSTEMML-1034
                 URL: https://issues.apache.org/jira/browse/SYSTEMML-1034
             Project: SystemML
          Issue Type: Sub-task
          Components: Runtime
            Reporter: Niketan Pansare


1. Extend BinaryOp to enable GPU for solve
2. Add MatrixMatrixBuiltinGPUInstruction and use JCuBlas2's cublasDtrsmBatched and cublasDgeqrfBatched (or cublasDgetrfBatched) methods.

For reference implementation, see https://github.com/apache/incubator-systemml/blob/master/src/main/java/org/apache/sysml/runtime/matrix/data/LibCommonsMath.java#L97



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)