E7-8870 linpack

[idata]

I am trying to do some benchmark on a compute node using the linpack benchmark included in mkl.

The node contain 4 Intel® Xeon® Processor E7-8870 v3 and 3072 Go of RAM.

I am obtaining

40 Gflops on 1 core

1800 Gflops for the whole node

When I compare to this site http://www.nextplatform.com/2015/05/05/intel-puts-more-compute-behind-xeon-e7-big-memory/ http://www.nextplatform.com/2015/05/05/intel-puts-more-compute-behind-xeon-e7-big-memory/

I am too low (it present 1 Xeon E7-8870 v3 processor at between 2073 and 2880 Gflpos).

Can I trust this site?

I saw on another site that for a Xeon E5, it had 16flops/cycle.

If I use that number I get :

40GFlops / (2.9 GHz*16flops/cycle) ~ 85% efficiency for 1 core.

1800 Gflops / (2.9 GHz*16flops/cycle*72cores) ~ 55% efficiency for the node with turbo.

1800 Gflops / (2.1 GHz*16flops/cycle*72cores) ~ 75% efficiency for the node no turbo.

Which seems reasonable, but is it exact?

Thank you.

[idata]

Hello, @Eric_G:

I am going to review this information and as soon as I have an answer I will update this thread.

Regards,

Amy.

[idata]

Thank you for your patience.

I am going to need more time in order to review your inquiry in regard to the Gflops. However, what I can tell you is that our processors are made with high quality materials so we can ensure the best performance, but we cannot guarantee that these benchmark tests will provide the accurate information for our products, they may vary the results on your product and this is why we do not recommend taking them into consideration.

Regards,

Amy.

[idata]

Hello, @Eric_G:

I just wanted to check if the information posted before helped you, I would also like to share the following information with you; http://www.intel.com/content/www/us/en/support/processors/000005755.html Export Compliance Metrics for Intel® Microprocessors.

Regards,

Amy.