topic You may attach your matrix in Intel® oneAPI Math Kernel Library

The difference in the common sparse solver function result and cluster sparse solver function result

Anonymous100 — Mon, 30 Nov 2015 10:08:22 GMT

Hello.

I'm Using MKL Pardiso Sparse Solver (PARDISO).

Some time ago, I Using Intel Parallel Studio 2013 Version (MKL 11.2).

Recently, I'm Update Intel Parallel Studio 2016 (MKL 11.3).

This Version Support Cluster Sparse Solver. so I using this Function.

But Solving result is difference. (about 0.02)

Originally does the other result come out?

Or is there the condition getting the little more exact result?

You may attach your matrix

Zhang_Z_Intel — Mon, 30 Nov 2015 20:46:00 GMT

You may attach your matrix and your code here, so we can understand the situation better.

When you go from PARDISO to the cluster sparse solver, the level of parallelism may have changed. You were using multiple threads before and are now using multiple MPI processes with, potentially, multiple threads in each process. Can you describe the configuration of your cluster? What kind of CPUs? How many nodes and MPI processes? How many threads do you use for each process, etc.?