topic Re:Tridiagonal solver in oneMKL for DPC++ in Intel® oneAPI Math Kernel Library

Tridiagonal solver in oneMKL for DPC++

Oluwatosin — Sat, 08 May 2021 16:01:58 GMT

Hello, is there are tridiagonal solver routine in oneMKL for data parallel c++ similar to dgtsv() routine in c/c++ intel mkl? Thank you.

Re: Tridiagonal solver in oneMKL for DPC++

Gennady_F_Intel — Sun, 09 May 2021 04:41:02 GMT

yes, please check the API description here: https://software.intel.com/content/www/us/en/develop/documentation/oneapi-mkl-dpcpp-developer-reference/top/lapack-routines/getrs.html

Re:Tridiagonal solver in oneMKL for DPC++

Gennady_F_Intel — Tue, 11 May 2021 11:25:38 GMT

is this what are you looking for?

Re: Tridiagonal solver in oneMKL for DPC++

Oluwatosin — Wed, 12 May 2021 06:27:08 GMT

Thanks for replying, I will work with the routine.

Re: Tridiagonal solver in oneMKL for DPC++

Oluwatosin — Wed, 12 May 2021 06:37:59 GMT

One more question, I would be comparing results of this routine with an algorithm based on cyclic reduction, it has been designed to execute with a size specified at compilation time. Maximum size is about 90,000,000 . Do I have to specify a memory size when requesting for a compute node (example- qsub -I -l nodes=1:gpu:ppn=2 -l mem=32G -d .) in order to execute the code with this size?

Re:Tridiagonal solver in oneMKL for DPC++

Gennady_F_Intel — Wed, 12 May 2021 06:55:42 GMT

I think yes, You have to estimate the memory requested by getrs for this case and specify this size when will make the queue submission.

-Gennady

Re: Re:Tridiagonal solver in oneMKL for DPC++

Oluwatosin — Wed, 12 May 2021 07:37:47 GMT

Alright, thank you!

Re:Tridiagonal solver in oneMKL for DPC++

Gennady_F_Intel — Thu, 20 May 2021 02:56:05 GMT

The issue is closing and we will no longer respond to this thread. If you require additional assistance from Intel, please start a new thread. Any further interaction in this thread will be considered community only.