LabVIEW

cancel
Showing results for 
Search instead for 
Did you mean: 

Intel i7 processor with hyper-threading (only every second core is used)

Solved!
Go to solution

Dear users,

 

the "CPU Information.vi" gives me the following output (see "CPU Information.png"). When I run a Labview vi, only four cores are used (see "CPU usage.png"). I believe that my processor has 4 physical cores and a hyper-threading feature: http://ark.intel.com/products/48500/Intel-Core-i7-880-Processor-8M-Cache-3_06-GHz

 

Do you have any idea how to use also the other virtual cores as well, please?

 

Kind regards,

M

Download All
0 Kudos
Message 1 of 20
(3,717 Views)
Are you running a parallell loop? Check your loop setup.
/Y
G# - Award winning reference based OOP for LV, for free! - Qestit VIPM GitHub

Qestit Systems
Certified-LabVIEW-Developer
0 Kudos
Message 2 of 20
(3,708 Views)

Tha "parallel" option for for-loops is enabled on multiple places within my program.

0 Kudos
Message 3 of 20
(3,696 Views)
In "CPU usage.png" I can swipe over the green area and it says all over it "LabVIEW" (with about 12% utilization). The red area are system applications.
0 Kudos
Message 4 of 20
(3,687 Views)

Can you post your VI?  Otherwise we are totally shooting in the dark.


GCentral
There are only two ways to tell somebody thanks: Kudos and Marked Solutions
Unofficial Forum Rules and Guidelines
"Not that we are sufficient in ourselves to claim anything as coming from us, but our sufficiency is from God" - 2 Corinthians 3:5
0 Kudos
Message 5 of 20
(3,684 Views)

Unfortunatelly, I am not allowed and not able to post any of my code (besides, they are dependent on my local data). I am trying to assemble a vi for testing a multi-core processor PC. (any help or hint to a page with example is appreciated). So far I assembled a few for-loops but they all run too quick, so I cannot take any meaningful snapshot.

0 Kudos
Message 6 of 20
(3,678 Views)

There are plenty of ways to use 100% of all CPU cores but there are also plenty of ways to get less than 100%. There can be many reasons for lower utilization.

 

Is there shared code (e.g. non-reentrant subVIs). Is the data in processed in large chunks or does each code nibble on scalars? Is more data processed than fits in the CPU cache? Is it all pure math or is there synchronous code (e.g. lots of property nodes). Does the code operate mostly "in place" or are there constanty new memory allocations?

 

 Can you explain exactly what the program does?

0 Kudos
Message 7 of 20
(3,666 Views)

Thank you for your suggestions, dear all. Let's talk about an existing valid example. I read the [link removed]  article, and afterwards I found the "PI Day (LV 2012).zip" at https://forums.ni.com/t5/Example-Code/%CF%80-Pi-Day/ta-p/3500611 Next I've ran the "4 Calculate N Digits of Pi.vi" with N set to 10000 (ten thousand). The result was, that only four cores out of eight were engaged. Do you get similar or different results please? KR, M

 

 

0 Kudos
Message 8 of 20
(3,616 Views)

You only have four real cores. What else do you expect?

0 Kudos
Message 9 of 20
(3,590 Views)

If you turn off parallelization, how much slower is it?

0 Kudos
Message 10 of 20
(3,584 Views)