Our website uses cookies to enhance your browsing experience.
Accept
to the top
close form

Fill out the form in 2 simple steps below:

Your contact information:

Step 1
Congratulations! This is your promo code!

Desired license type:

Step 2
Team license
Enterprise license
** By clicking this button you agree to our Privacy Policy statement
close form
Request our prices
New License
License Renewal
--Select currency--
USD
EUR
* By clicking this button you agree to our Privacy Policy statement

close form
Free PVS‑Studio license for Microsoft MVP specialists
* By clicking this button you agree to our Privacy Policy statement

close form
To get the licence for your open-source project, please fill out this form
* By clicking this button you agree to our Privacy Policy statement

close form
I am interested to try it on the platforms:
* By clicking this button you agree to our Privacy Policy statement

close form
check circle
Message submitted.

Your message has been sent. We will email you at


If you haven't received our response, please do the following:
check your Spam/Junk folder and click the "Not Spam" button for our message.
This way, you won't miss messages from our team in the future.

>
>
The first impression of Intel Parallel …

The first impression of Intel Parallel Inspector

May 18 2009
Author:

I experimented with Intel Parallel Inspector in memory-error diagnosis mode. I can say that I liked the product and the work it does. I was especially impressed by perfect integration into Visual Studio and full support of 64-bit projects—which Bounds Checker users will appreciate.

Mostly, I experimented with the Viva64 project and managed to find one rather serious error.

I liked the graphical interface of the Parallel Inspector launch mode settings very much—it is simple and clear:

0011_The_first_impression_of_Intel_Parallel_Inspector/image1.png

I liked the indicator showing how much the current analysis type can slow down a program's execution. I liked this approach, the design and clearness of what to expect so much that I decided to check this indicator's accuracy on Viva64 project. Of course, the sampling is unrepresentative, but the check was still very interesting. Here are the results of launching the 64-bit debug-version of Viva64:

Launch mode

Expected slowdown, according to the Parallel Inspector scale

Actual slowdown when testing the Viva64 project

Without Parallel Inspector

No slowdown

(1.23 sec) – No slowdown

"Does my target leak memory?"

By 2 - 20 times

(17.70 sec) – by 14.4 times

"Does my target have memory access problems?"

By 10 - 40 times

(72.57 sec) – by 59 times

"Where are the memory access problems?"

By 20 - 80 times

(70.80 sec) – by 57.6 times

"Where are all the memory problems Inspector can find?"

By 40 - 160 times

(404.82 sec) - by 329.1 times

I think that the slowdown estimate is pretty close for cases when there is no information about the project. In the last mode, the figures I got exceeded the expected result. However, the Viva64 analyzer, compared to an average program, has a lot of memory allocation operations. Viva64 needs them when building and analyzing the syntax tree. So an increase in slowing, as compared to the estimate, is expected.

Using Intel Parallel Inspector leads to slowdowns, but they do not worry me. I consider them natural and not even that significant for a dynamic analysis tool that offers these features. However, it's a good thing to remember that it can be best to avoid running this tool for a program in real time. A more efficient approach would be to use packet launches or automated testing systems that will run at night and click all the buttons in an application. This way, you will not need to worry that the response may take minutes or hours.

All in all, I found Intel Parallel Inspector very useful and highly recommend it.

Popular related articles


Comments (0)

Next comments next comments
close comment form