MKL and Atom D525

[hpweiss]

Please

1) Does MKL run on Intel Atom D525 (Linux)? Where might I find information relative to support for Intel Atom in MKL and/or IPP

2) What is performance (say for 2K 2D FFT) relative to Intel Celeron 420 @ 1.6GHz or Intel Core2 Duo Mobile T7600 @ 2.33 GHz

Thanks

[TimP]

MKL certainly should run OK on Atom with a gcc development system, and should give expected gains over generic compiled code. IPP should actually have been tested; you might ask on IPP forum. I don't know whether you can get an answer about MKL FFT performance without trying it yourself. If you can make a comparative performance test of your own on in-cache performance, you could hope for similar results with MKL.

[hpweiss]

Thank you for the prompt response.

1) Do you know if MKL would run in 64 bit Linux on the Atom D525?

2) Would MKL take advantage of SIMD instructions (SSE)?

3) Would MKL take advantage of dual CPU and hyperthreading?

Thanks.

[TimP]

1) MKL certainly ought to work with 64-bit linux, if such linux runs on your platform
2) 64-bit linux requires at least SSE2, no support for less; if MKL doesn't use SSE3 where applicable, that may be a reportable bug. SSE3 would be useful mainly for complex data types.
3) MKL is supposed to not use HT by default, see here
http://software.intel.com/en-us/forums/showthread.php?t=67622 so you'll need to test to find your best mode. Current MKL has both OpenMP and sequential library options so you can set how many threads are used. Dual core Atom may be too new to have been tested but again it seems to be a bug if it doesn't give good 2 thread performance.

You can get trial (or, if your usage qualifies, non-commercial) license to compiler/MKL packages http://software.intel.com/en-us/articles/tools-for-math-processing/

[Gennady_F_Intel]

regarding IPP:

yes, IPP is doing special optimization optimization for Atom CPU. IPP's dispather chooses which of these processor-specific optimized libraries to use when your application makes a call into the IPP library.

for more info how it works see here.

The official information you can find into IPP Release Notes.

regarding MKL:

MKL doesn't dispatch Atom CPU type but the MKL's code will run OK on Atom without anyconcerns.