Community
Inventor Forum
Welcome to Autodesk’s Inventor Forums. Share your knowledge, ask questions, and explore popular Inventor topics.
cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 

How fast is your Inventor PC really?

2,218 REPLIES 2,218
SOLVED
Reply
Message 1 of 2,219
Raider_71
254327 Views, 2218 Replies

How fast is your Inventor PC really?

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: 32x32.png

 

 

My resluts:

HP Elitebook 8560w with an SSD upgrade.

Inventor Bench.jpg

 

 

2,218 REPLIES 2,218
Message 81 of 2,219
Neil_Cross
in reply to: blair

I suspect there's an alarming amount of people who might still not know that though, and need to see actual proof.

I imagine big businesses are going to always use the professional cards for the certification and peace of mind that is 'supposed' to come with that.

Message 82 of 2,219
hosford
in reply to: Neil_Cross

Neil

 

After watching your video I downloaded a new driver for my K3000M display card, was hoping for a greater performance boot, only incremented up about 3 or 4 frames per second. Decided to un dock from Dell E Dock, Wow, doubled the frame rate.

 

Thanks

 

Now if I could get my Dell R7610 to perform as well as this laptop.

 

undocked II.png

Thaddeus Hosford
NUC9i9QNX i9-9980HK, Win 10 Pro 64
Nvidia GTX 1650
Inventor 2021
Message 83 of 2,219
AlexFielder
in reply to: Raider_71

Great video @Neil_Cross!

 

I'm not too dissappointed to see my gaming system only reach third (I think it was) in the scheme of things.

 

Interesting that your R9 200 series gfx card outperformed my R9 390 - but it's not really a surprise since: 

 

1) IIRC the R9 300 series cards are exactly the same chipset as the R9 200 series albeit with better memory.

2) given the length of time the R9 200 series cards have been around, the optimization with the drivers they use should be streets ahead of those for the R9 300 series card I have.

 

@Raider_71: Do you think you will be able to include an actual rendering test at some point?

 

I fully intend to overclock my i7 6700K to around the 4.5GHz mark to see if that bumps up my score some.

 

Also, the resolution on my gaming system is currently 1680x1050 due to the crappy old Dell monitor I have- in theory, if I was to (for the purposes of comparative testing) plug the system solely into the 1080p Samsung tv I have should this increase the frames per second or reduce it?

 

I'm pretty sure there's something throttling back the FPS on my system, but have yet to discover what it may be.

 

🙂

Message 84 of 2,219
Neil_Cross
in reply to: AlexFielder

Thanks Alex.  In theory when you move to a higher resolution you'll drop FPS as your hardware is pushing more pixels, but it should be minimal.  When the GPU is spitting 150fps, the human eye is unlikely to see the difference if you get to increase that even further.  The benefits will come when you then work on something heavy, again in theory a PC which can spit out 200fps on a lightweight visual test should scale better with big assemblies than a PC which was pushing out 100fps on the test.  

 

I think, off memory, your PC beat both mine and Daniels on the Drawing Test Results which I believe is a multi-threaded operation

Message 85 of 2,219
Raider_71
in reply to: AlexFielder

Hi @AlexFielder

 

Thanks for that idea! I think it would be a great adition to InventorBench as the Inventor Studio rendering engine make use of multithreading so this would be a very nice multithreaded test to add for sure! I will look into it.

 

Cheers

 

Pieter

Message 86 of 2,219
Neil_Cross
in reply to: Raider_71

@Raider_71 in the manual benchmarking I was doing over xmas, one of my tests was ray tracing and obviously the PC with the highest total combined GHz won hands down.  Obviously it's entirely up to you which benchmarks you put in and how easy they are to code, but my testing was as follows:

 

1. Time it takes to simply enable ray tracing in the graphics window (not Inventor studio environment).  On larger models it took up to 2 minutes just to switch on ray tracingm that was before it began the ray tracing passing.

2. Time it takes to completely finish basic quality ray traving.

3. Enable High Quality, record time it takes to reach 'smooth' quality.  If you wait for some PCs to finish high quality ray tracing it could take hours!

4. Disable RT, make sure all shadows, reflections are on, perspective mode, Realistic visual mode, plain room IBL, then record FPS on a free orbit.  Note if visual effects are dropped or retained during orbit.

 

 

Message 87 of 2,219
AlexFielder
in reply to: Neil_Cross

We should ask Linus here:

 

 

to install Inventor and give this benchmark a run on the build in that video, the specs/hardware list for which can be found here:

 

http://linustechtips.com/main/topic/519293-7-gamers-1-cpu-ultimate-virtualized-gaming-build-log/

 

 😉

 

(As silly/expensive as it sounds, if you were to try and source "professional" systems for 7x Inventor users given the specifications we have seen in this thread already, you would probably come close to definitely exceed what they spent on the system in the YouTube video above!)

Message 88 of 2,219
Raider_71
in reply to: AlexFielder

I also like his video about the differences between Quadro and Geforce.

 

Makes for a good laugh... Smiley Happy

Message 89 of 2,219
Raider_71
in reply to: Neil_Cross

Hi @Neil_Cross

 

Yes I will investigate it and see what multithreaded test, that actually tests all cpu cores to the max, I can put in.

 

Message 90 of 2,219
Anonymous
in reply to: Raider_71

i have just run the bench mark test on new computer and quite happy considering iam not up on it all just threw some randoms parts together really. dont know why i still have 2 slots left could someone explain please?bench test results.jpg

Message 91 of 2,219
karthur1
in reply to: Anonymous

@Neil_Cross   Thats smoking..... Do we have a new champ?   

 

Looks like you only have two slots of ram filled.  How many are installed?  on keyboard, press Windows+Break.  What does it say for installed ram?

 

Kirk

Message 92 of 2,219
blair
in reply to: Anonymous

Nothing says you need to all your slots filled with memory, your 2 x 8Gb will still be 16gB, no different than if you had 4 x 4Gb to give you 16bGb


Inventor 2020, In-Cad, Simulation Mechanical

Just insert the picture rather than attaching it as a file
Did you find this reply helpful ? If so please use the Accept as Solution or Kudos button below.
Delta Tau Chi ΔΤΧ

Message 93 of 2,219
Ray_Feiler
in reply to: Raider_71

Here is my four year old gaming system.

 

Capture4.PNGCapture2.PNG


Product Design & Manufacturing Collection 2024
Sometimes you just need a good old reboot.
Message 94 of 2,219
Anonymous
in reply to: AlexFielder

 
Message 95 of 2,219
Anonymous
in reply to: karthur1

only got the 16gb installed I was just under the assumption it was better to fill all the slots even if it ment getting four smaller sized than two larger. but whoosh over my head
Message 96 of 2,219
karthur1
in reply to: Anonymous


@Anonymous wrote:
only got the 16gb installed I was just under the assumption it was better to fill all the slots even if it ment getting four smaller sized than two larger. but whoosh over my head

Since this is DDR4 RAM, its not necessary to fill all the slots.  Just when replacing/adding, purchase the sticks in sets.  Thats because they have been tested to run together.  If you just mix and match it might work but then again it might not.

 

Also since you are not filling all slots, read the motherboard info.  It will tell you what slots to fill first (usually 0 and 1).

 

Kirk

Message 97 of 2,219
Neil_Cross
in reply to: karthur1

I highly doubt it'll ever be a factor for the work that our PC's do, but there is slightly more strain put onto the memory controller with 4 sticks which in turn can take power away from the CPU if you're running quad channel.  But from what I've read, it's minimal, so minimal it's not going to be noticeable.  The biggest benefit of going with 2 sticks is that you have x2 empty slots to expand into when you feel like upgrading.  

Message 98 of 2,219
rhasell
in reply to: Neil_Cross

Hi

 

Has anyone been able to see if there is any difference between the various Windows operating systems?

 

Reason I ask, I want to do a rebuild, but am unsure whether to take the leap from Windows 7 to Windows 10.

 

Thanks guys.

Reg
2025.2
Message 99 of 2,219
blair
in reply to: rhasell

You might see some improvements in the DirectX from v10 to v11 but I don't think it would amount to much. Besides, M/S wants everyone to be on Win10 anyways and the older systems are being dropped from support.


Inventor 2020, In-Cad, Simulation Mechanical

Just insert the picture rather than attaching it as a file
Did you find this reply helpful ? If so please use the Accept as Solution or Kudos button below.
Delta Tau Chi ΔΤΧ

Message 100 of 2,219
Anonymous
in reply to: Raider_71

@Anonymous what do you have your 6700k overclocked to? You're beating my 4790k at 4.8GHz! Smiley Mad

 

14 Inventor Bench 4.8 OC, clean, 10% GPU OC.PNG

 

The results of this Benchmark tool certainly seem to suggest CPU speed > CPU cores. I turned my CPU down to just 2 cores without hyperthreading but kept the 4.8 GHz overclock and it still gave impressive results!

Spoiler
The FPS on this test was lower, however a previous test showed little FPS difference... I have no idea why.
31 Inventor Bench 4.8 OC, 2 core 2 thread, clean, 10% GPU OC.PNG

I overclocked my GPU by about 10% and saw a ~10% increase in FPS but this goes against @Neil_Cross findings... maybe it's because I'm running nearer to 60fps than 160??? Reducing my screen resolution from 4k to 1080p actually helped the CPU intensive tasks, I think this may be because less of the CPU's resources are spent feeding the GPU

Spoiler
42 Inventor Bench 4.8 OC, clean, 10% GPU OC, 1080p.PNG

I hope this was helpfull to you.

 

For anyone interested in my cpu specs:

i7 4790k at 4.8GHz 1.295v

Sapphire R9 290 TriX 1100MHz GPU and 1400MHz Memory

Samsung 840 Evo

Samsung XP941 (not used in these tests)

Can't find what you're looking for? Ask the community or share your knowledge.

Post to forums  

Autodesk Design & Make Report