topic Multithreading lapack numeric differences in Intel® oneAPI Math Kernel Library

Multithreading lapack numeric differences

aurora — Wed, 17 Oct 2012 14:18:37 GMT

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

Hi,

Gennady_F_Intel — Wed, 17 Oct 2012 14:59:45 GMT

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

Still, using mkl_cbwr_set(MKL

aurora — Mon, 22 Oct 2012 12:31:14 GMT

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?

MKL's CNR guarantees the bit

Gennady_F_Intel — Mon, 22 Oct 2012 15:23:52 GMT

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.