How fast is your Inventor PC really?

[Raider_71]

Hi guys,

We have had to do some testing on a bunch of Inventor PC's recently to determine which of the PC's needs to be replaced. Obviously we needed to find out which of the PC's are the worst eprformers as there was only budget to replace 50% of the design PC's. So we thought the Darwin theory will come in handy right... 🙂

Anyways I started searching on the net for toppics on how to benchmark an Inventor PC. Then I thought whats the point of using gaming benchmark tools because Inventor is not a game and there are more aspects than just graphics performance when it comes to percieved performance on an Inventor PC right.

So we decided to create our own Inventor benchmark tool which tests various aspects of an Inventor PC to give us an overview of our PC's performance. This then helped us make a decision as to whcih pc's to replace.

We have made the tool available free of charge to anyone interested in checking how their PC stacks up to their peers or friends. 🙂

Please download it here and post your results here as well if you want. Would be interesting to see what beast workstations are out there.

I would like to say thanks to Kirk #karthur1, for helping in testing the app.

Please feel free to send any suggestions our way. There is an email link in the app.

Download and Install

The application will work with Inventor 2014 to 2016 only.

IMPORTANT: After installation there will be an Inventor Bench icon on your desktop that looks like this: 

My resluts:

HP Elitebook 8560w with an SSD upgrade.

[Torben.pedersen]

no I have not overclocked my CPU, maybe it´s the cooling, if your CPU is getting to hot when i´ts working hard. I have liquid cooling I´m not sure if this is correct, I just guess 🙂 @Neil_Cross

[Neil_Cross]

@Torben.pedersen I have the Corsair H100i liquid cooler, my system never gets hot enough to thermal throttle.  But I don't think the results are different enough to be concerned 

@blair thanks, it should be your screen resolution causing that much of a dip... I ran my first test at 3440x1440 resolution and the difference between that and 1920x1080 was minimal, ~10fps on the graphics test

[CadUser46]

Neil.  I have some results im going to post up covering my works machine and my Macbook pro.  Before i do, how is everyone embedding the images in the post?  Is there some way to do it by uploading the pics to this forum or is everyone using dropbox or something similar and linking the IMG tags from there?

[Raider_71]

Hi this is what I do:

Use a screengrab tool like Windows Snipping tool or Snagit

Save the image you captured as a jpg or png file

Use the "Insert Image" command as below to select the file you would like to insert into your post

Thats it.

P

[Anonymous]

@Neil_Cross - No overclocking on this machine, just straight 4.0GHz.  My home office machine is a 3970k OC'd to 4.4GHz, have yet to run the test there.

[blair]

For some unknow reason this program is fighting me. I have Inventor opened but it's not finding Inventor. I did have a User Profile go bad on me just before New Years and I suspect this is the issue.

I'll keep working on it in my spare time.

Blair

[Raider_71]

Hi Blair,

There are a couple of things to overcome this issue. Most of the time this is caused because Inventor did not register itself properly with the operating system. This could have been because of User Account Control that was on during the installation of Inventor or some other reason perhaps.

Try this:

Close Inventor and other apps

Create a batch file and call it something like RegInv.bat

Edit the file and add this command:

"C:\Program Files\Autodesk\Inventor 2016\Bin\Inventor.exe" /install

Now right click on the batch file and "Run As Administrator"

It should fin in a few seconds.

Let me know if you don't come right I have a few other tricks you can try as well.

Pieter

[blair]

Here's my data with the screen set to a lower resolution simular to everyone else.

[Neil_Cross]

If anyone's interested, my TFI video based on this benchmark tool will be published within the hour.  All the scores as of this morning are included and compared, some are evaluated and commented on with obviously no personal information associated to the scores.  The idea being to partly educate the folk who are being told that throwing big money at a computer is a guaranteed performance boost that this isn't always the case, there are some results here which really emphasise that in a big way.  And to promote the use of this tool, it's genius.

I know it isn't a schlong measuring contest (although most of us would love to be first ) but so far @Daniel248 is top of the leaderboard across all scores with his gaming rig.

I'm second with my.... gaming rig 

[Neil_Cross]

Thanks Blair, I guess that only goes to reaffirm how important CPU is now over graphics card.  You have the 980, I have the lesser 970, yet I'm getting 100% increased visual performance on the frames per second test over your system.  Although I'd still be happy with 80 on the visual score, have you experienced any visual issues when you work on large assemblies?

@Raider_71 if you plan to support this tool moving forward, the kubas assembly would possibly be a good additional bench for visual stress tests.  Simply modifying a pattern allows you to take the occurrence count up by thousands at a time which can really then test those systems pushing 150-200fps on your existing test, see how those systems handle scalable resource demand.  

The video is now live here should anyone wish to see it:

[blair]

No slow downs that I can tell. I should re-run it with the AVG disabled. I might see a gain in the start-up times.

I should bench my home machine, a Mac Pro with AMD Fire graphics cards.

[karthur1]

Here is my "Work" machine using the latest benchmark build.

[karthur1]

Neil,

Your 4.0 Ghz machine ir pretty close to the 3.0 Ghz machine of Daneal248.  I think the difference is his fast ram (2133mhz).  Those two GPU tests are comparably the same.

My CPU is running at 2.8ghz... non-overclocked.  I could not get it stable when I try to over-clock, but that is another story. Pretty close to daniel248's speed, but my ram is half the speed .... and he killed me on the GPU test.  It seems like the fast ram in his system is what is making the most difference.

Kirk

[Neil_Cross]

Hi Kirk,

Honestly RAM frequencies won't make hardly any difference to overall system performance, even in gaming and mundane stuff.  The CPU labels are slightly inaccurate on this test too, for example Daniels PC is showing 3GHz but it's actually a 3.5GHz octacore CPU meaning he has 28GHz of CPU power, my CPU is 4.4GHz with 4 cores equalling 17.6GHz of processing power.  

With your PC, if you're referring to the PC with the GTS 250 card in, that'll be a huge bottleneck as it's an old card.  It's only got 128 CUDA cores for example in comparison to my GTX 970 with 1664 cores

[CadUser46]

OK here are the results from my three tests.  2 from work machine with Hyper-Threading disabled and enabled.  As well as my late 2013 rMBP.

I always thought HT disabled was gospel for IV but it doesnt appear to make any difference, certainly in 2016.

I did see 90 fps for the first three bench's in shaded edges but didnt save the screen print. I did also run it just within the laptop retina display but it doubled the seconds and halved the fps.

Craig

[-niels-]

Very nice video Neil and thanks for the shout-out 😄

I probably should run the benchmark again with slightly different settings, because i just ran it "as is" without putting the laptop in high performance or closing down all processes. (i left my alienware lights on, steam was probably still running, etc.)
Not sure if i will though, unless you'd like to put it into your comparison...

[Neil_Cross]

You wanna use them Alienware skills and get dat CPU overclocked and burning up! Surely Alienware comes with an overclocking facility even on the laptops?

I just overclocked my CPU by 400MHz to 4.8GHz and that's shaved some time off the scores, interestingly enough it also boosted the FPS whereas dramatically overclocking my graphics card didn't make the slightest bit difference to anything.

 

[blair]

WoW, quite the screen rates, I can almost hear components melting with the OverClock  🙂

I might need to do a clean-out of my box with the compressed air to help the cooling. It might be getting a bit dusty again and a good clean out is needed.

I might run the test on my Mac Pro at home after tonight football game and see how effecient the Boot Camp interface is and what type of numbers it kicks out.

[Neil_Cross]

Well here's another interesting result.  

If you look at the graphics card of my last score, 2 posts up, that was with a $300 gaming graphics card.

I've just taken that out, and put in an AMD FirePro W9100... it's one of the most powerful professional CAD/Workstation graphics cards in the world today.

Here's the scores with that.

The FPS has gone up, slightly, by around 5%.  If a salesman had convinced me to pay $3000 for a CAD graphics card and it yielded a 5% gain, I'd be throwing it through his car window!

Disclaimer* the W9100 isn't built for Inventor, it exists for a much higer purpose, if you want to run Showcase buttery smooth or power 6x 4k screens up onto the side of the Whitehouse then this is your card.

[blair]

If Inventor was still OpenGL, I could see spending the money (and did way back when) on Quadro and other OpenGL cards. Since ADSK switched to D3D back on release 11 (not 2011) there really is no reason for OpenGL cards.