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.

[bwatson1967]

You were right again @Neil_Cross 10 Gen rules. I did pay for it though getting the over hyped Alienware. But thi is amazing for a laptop.

[leowarren34]

Wow, @bwatson1967 Is that the highest score so far?

I am noticing a RAID 0 array, did that make any difference to your score?

[Neil_Cross]

Can't wait to get my benchmark test out into machines like this, it'll really change the landscape.  Some of my tests are designed to be affected by thermal throttling, so if a laptop has a ridiculous unsustainable overclock... that'll never get picked up by InventorBench as the test doesn't stress the hardware enough, but you won't be able to brute force my test with an overclock unless you've got a well designed and reliable cooling solution to go with it.  And if you do, congrats, you've got a great system that can compute high demand sustained workloads!

[Anonymous]

🙂 Paitenly waiting with our next-gen Stryker III.

[Neil_Cross]

I really doubt a RAID array makes any much difference to this.  Where we're at with this test is the difference between a posted 18.66 and 19.22 result, is the drawing test finishing a whole 0.3s faster, the modeling test 0.26s faster, and graphics 0.1s faster, that's the margin between an 18.66 and 19.22.  With both those tests finishing in 26 seconds, separated by tenths of a second over the whole test duration.  

In contrast, my test InvMark in total takes 11 minutes (so far) to execute and benchmark on a system which has posted an 18.66 in InventorBench 😈

[leowarren34]

Neil - I am on the same page in terms of RAID (just wondering at the time) - in most cases, it tends to hurt write speeds due to overhead, RAID 0 is an exception here since you essentially get a faster drive at the cost of reliability. I did think that would be strange since effectively halving your reliability isn't great unless you backup regularly or only work on network/cloud storage.

I'm definitely excited to test your benchmark when it releases, my computer is definitely in need of an upgrade in the CPU department within the next year or so.

[Raider_71]

Hi guys, I thought I'd update everyone just to let you know InventorBench HD is busy being created and I think it's going to be a nice improvement to V1. It will focus a lot more on generic design workflows to test your system accordingly. Anyways I don't want to say too much just yet as there is still some work to be done and I cant wait to have both Neil's version and mine out there to compare results.

Here is a teaser:

[Neil_Cross]

Looking good! Love the name!

It's exciting times, having two tests out there is only going to be a bonus and benefit for everyone, can't wait to have these out into the wild!

My developer has been tied up participating in the Forge event last week so he's been offline from working on the last bits and pieces, but my tests are 100% locked in and finalised, working, we've just got the superficial cosmetic things to sort out now and delivery etc.

Good job Pieter and thanks again for starting all this, albeit probably unintentionally! 

[Anonymous]

All good things are worth the wait...

[Raider_71]

Thanks @Neil_Cross  yeah its a load of work and there are so many things I would like to build in but I would have to hold off a bit otherwise I keep on moving the goalpost and never get there...

But this will be the platform to add more test sequences as we go on.

[Anonymous]

That is the biggest challenge to building a solid benchmark. Building
scripts is easy but not stable. Once you build the platform, you can make
it sing. Then it comes down to development hours and tests that make sense
and Inventor has a multitude. Revit is a little bit more straight forward.
🙂 We shall be patient. 🙌💪

[Neil_Cross]

Wow don't I know how you feel there! Some tests start out as a little tiny idea and before you know it, you've exploded off into all kinds of directions.  

@Anonymous indeed reliability is super important, not just stability but also consistency.  Inventor is a nightmare for that, you have document vs system settings to consider as well as application options that differ from system to system.  Making sure dozens of tests open and perform consistently regardless of the installation is one of the biggest challenges I've found, then there's multi-monitor setups, different resolutions and display scaling, handling potentially interfering addons that people might have that would halt a running test, putting everything back to the way it was before your test came along...! etc etc etc etc etc I've really enjoyed it, not sure my developer has! 😁

[Raider_71]

Yeah, I hear you, plus I am looking at catering for Inventor 2019 and up... 😬

[Neil_Cross]

You got one up on me there, one of the tests I have uses a feature which was new in 2020 so rather than go through a heck load of hassle to make all my datasets 1 platform old, I just hit the reset switch and started from 2021.  

Love that propeller assembly that you've got there, looks like a solid foundation to do all kinds of stuff with!

[Anonymous]

I have a graphic station DELL T3600 and after Inventor Bench  test I get a very low index. It is a hardware issue or some wrong settings of the graphic card? A little  help please?!

 

[vmcarbonneau]

Seems you have "software graphic" enabled.

[Anonymous]

Indeed, this was the problem. Probably 1: 6.42 is the max. performance of  my present  system. Thank you very much for help.

 

[Raider_71]

Quite excited that we have managed to get the GPU usage up to +/- 55% with the new version of InventorBench (less now while recording the screen). This is quite a bit more than what we could do with the previous version. Being able to utilise and test the graphics hardware is key.

We are busy finalising all the tests in the next week then its "packaging" and beta testing.

[Anonymous]

I am purchasing a new computer and need some advice on the processor. The Xeon W-1250P has a base clock speed of 4.1 and a turbo of 4.8 but only 6 cores. The I9 -10900K Tenth Gen has a base speed of 3.7 and a turbo of 5.3. but 10 cores. Which processor will run Inventor the fastest? I am running Inventor 2018 and use it to design fire trucks.

My assembly can have up to 4000 files. The model is composed of converted Catia and step files, surfaces and solids. Drawings can be very time consuming if not impossible. 

I am looking at purchasing 64GB of RAM with a speed of 3200Mhz

Graphics card will be Quadro RTX 4000 or 5000 how important is GPU memory?

2 - 1 TB NVMe SSD drives