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

Posted to commits@mxnet.apache.org by gi...@git.apache.org on 2017/09/17 20:19:16 UTC

[GitHub] asmushetzel commented on a change in pull request #7883: cuda support for new linear algebra operators

asmushetzel commented on a change in pull request #7883: cuda support for new linear algebra operators
URL: https://github.com/apache/incubator-mxnet/pull/7883#discussion_r139320265
 
 

 ##########
 File path: src/operator/linalg_impl.h
 ##########
 @@ -519,7 +519,7 @@ void linalg_trmm<gpu, DType>(const Tensor<gpu, 2, DType>& A, const Tensor<gpu, 2
                             (rightside ? CUBLAS_SIDE_LEFT : CUBLAS_SIDE_RIGHT), \
                             (lower ? CUBLAS_FILL_MODE_UPPER : CUBLAS_FILL_MODE_LOWER), \
                             (transpose ? CUBLAS_OP_T : CUBLAS_OP_N), \
-                            CUBLAS_DIAG_NON_UNIT, B.size(0), B.size(1), &alpha, \
+                            CUBLAS_DIAG_NON_UNIT, B.size(1), B.size(0), &alpha, \
 
 Review comment:
   Yes. Found it during testing the other operators
 
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services