Niketan Pansare created SYSTEMML-932:
----------------------------------------
Summary: Improve the performance of copyUpperToLowerTriangleDense
kernel
Key: SYSTEMML-932
URL: https://issues.apache.org/jira/browse/SYSTEMML-932
Project: SystemML
Issue Type: Improvement
Reporter: Niketan Pansare
This requires minimum knowledge of SystemML internal and can be treated as
beginner's task.
Modify SystemML.cu's copyUpperToLowerTriangleDense to reduce the number of
threads by half.
Test case before merging:
org.apache.sysml.test.integration.functions.binary.matrix_full_other
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
