From SNIC Documentation
MKL (math kernel library) is an efficient mathematics library, which many softwares can be compiled against for increased efficiency.
|Abisko||HPC2N||capability resource of 153 TFLOPS with full bisectional infiniband interconnect|
|Akka||HPC2N||capability cluster resource of 54 TFLOPS with infiniband interconnect|
|Alarik||LUNARC||throughput cluster resource of 40 TFLOPS|
|Aurora||LUNARC||throughput/general purpose cluster resource|
|Kappa||NSC||throughput cluster resource of 26 TFLOPS|
|Lindgren||PDC||Cray XE6 capability cluster with 305 TFLOPS peak performance|
|Matter||NSC||cluster resource of 37 TFLOPS dedicated to materials science|
|Triolith||NSC||Capability cluster with 338 TFLOPS peak and 1:2 Infiniband fat-tree|
MKL is actually included as a component in the latest release of the Intel compiler suite, and may therefore be available on further resources than indicated here. Please contact centre support for details. Much of the functionality of MKL is also offered by ACML from AMD. In particular on architectures utilising AMD processors, it is often worthwhile to assess whether MKL or ACML offer better performance for the given software.
License: Site license.
No experts have currently registered expertise on this specific subject. Currently no experts have registered special competence on this subject.