Intel® oneAPI Math Kernel Library
Ask questions and share information with other developers who use Intel® Math Kernel Library.

Multithreading lapack numeric differences

aurora
初学者
1,606 次查看

Hi,

I'm having different outputs with zgbsv LAPACK subroutine depending on the number of threads that are being used. My MKL dll version is 10.3.10.1. This numeric differences are in the order of the 10th decimal number, but they exist. Is this normal?

Thanks in advance,

Aurora

0 项奖励
3 回复数
Gennady_F_Intel
主持人
1,606 次查看
Hi, yes, this is the expected behaviour with floating point operations. for your information, the latest version 11.0 introduces new functionality allowing users to have reproducibility in floating point calculations. Please look at this material regarding this topic: http://software.intel.com/en-us/forums/topic/313020 --Gennady
0 项奖励
aurora
初学者
1,606 次查看
Still, using mkl_cbwr_set(MKL_CBWR_COMPATIBLE) before LAPACK, it returns me different results with 3 or 4 threads for example. Am I using it fine?
0 项奖励
Gennady_F_Intel
主持人
1,606 次查看
MKL's CNR guarantees the bit to bit output results only if with the same #of threads. Please participate this survey ( https://softwareproductsurvey.intel.com/survey/150072/1afd/ ) to influence how this feature will be extended in the future.
0 项奖励
回复