Why Doesn't a Faster CPU Speed Up Certain Operations In Chief?


HumbleChief
 Share

Recommended Posts

This is so confusing for anyone interested in getting good performance from their computer and it's a complete mystery with absolutely no help, hints or advice from the good people at Chief.

 

I posted a plan that takes 5 seconds for any 3D move of the roof planes with my dual Xeon system. Not the fastest but pretty good. I also have an older i7 920, one of the original i7's and the operation is EXACTLY the same on that older, slower computer.

 

I am foolish enough to think that a faster CPU and GPU processor might speed up the operation but both hardware items seem to have virtually no effect on the 3D redraw speed. Instead there are magical settings one must locate, set, reset, experiment, test, retest and MAYBE those setting will speed the operation but throwing more hardware speed at the problem will not.

 

Sorry for the rant but this just seems a bit crazy. Is it just plain dumb to think that more CPU GPU power will speed Chief up? Why doesn't it? Where's the bottle neck? Is there any way to know without investing thousands only to find that the new system did nothing to boost performance?

 

How do we boost performance Chief? Is there simply a wall that Chief hits and once there - too bad too sad - deal with the slowness?

 

Hopefully some of the recent threads can serve as a notice to those who are looking to speed up their systems. First try and identify why the machine is slowing down - not easy but worth the effort. Second try and determine if a faster machine will help - even harder without investing in the faster hardware.

 

So just beware about the false notion that more CPU power will equate to faster Chief performance. Sometimes it might, other times it definitely will not.

 

https://www.dropbox.com/s/gx11twxukxd5zov/NICK CHEN PROPOSED 18.plan?dl=0

Link to comment
Share on other sites

I've been trying to understand what makes Chief faster as well.  Under the Windows Task Manager I can see that all cores are involved in things like regenerating elevations, so more or faster cores will make a difference.  Core memory speed also helped this system after I moved to M.2 memory. 3D rendering is all about OpenGL performance as best I can determine.  Ray trace rendering is CPU based using all available cores.  

 

I did a simple test on one roof panel of your plan and it took about 2 to 2.5 seconds to move this plane up 10'. 

 

Don't know if this will help but here is my build.

 

http://www.userbenchmark.com/UserRun/3591094

 

Good luck!

 

 

Capture.JPG

Link to comment
Share on other sites

...and why doesn't Chief at least throw us bone? Disk operations affect this; CPU operations affect this: GPU operations affect this. If you want faster 'this' then do 'this'.

 

There is obviously a LOT more going on than just CPU for RayTracing and GPU for 3D Rendering as is the common wisdom here.

Link to comment
Share on other sites

6 hours ago, HumbleChief said:

...and why doesn't Chief at least throw us bone? Disk operations affect this; CPU operations affect this: GPU operations affect this. If you want faster 'this' then do 'this'.

 

There is obviously a LOT more going on than just CPU for RayTracing and GPU for 3D Rendering as is the common wisdom here.

is your 850 pro fed into the red sata slot? or the black ones

Link to comment
Share on other sites

Larry - I believe a lot of what you are experiencing is related the difference between single threaded versus multi threaded operations. Your Xeons excel at multi threaded operations but are not the best choice for single threaded operations. As Ray Tracing is written to take full advantage of multi threading your system excels in this. However a lot of regular software and the shared routines they call upon are often single threaded, this puts you at a disadvantage as many I7's significantly out perform Xeon's in this type of operation.

 

If you review those CPU comparison reports you will see this very clearly in the single versus multi threading numbers. If I was making a recommendation on balanced CPU it would be to get the fastest single threaded capable processor with the most cores. Currently with Intel this means something like the I7 5960 or the I7 7700K. IF budget is of concern then the latter would be a great choice.

 

 

Link to comment
Share on other sites

Yes Graham, your analysis is correct and of course a new 7700K would be today's best choice but it still doesn't answer the question posed in the OP. I have an older i7 and the dual Xeons and they BOTH perform the same in certain operations. The CPU core speed and the number of cores has no effect. This is demonstrable and I just find that weird. There's something else going on behind the scenes where CPU speed has no effect.and I still wonder why. Is it simply a disk writing operation that can't be bypassed no matter how fast the processor? I am actually very happy with my system still but am curious about how Chief behaves and why out of simple curiosity.

Link to comment
Share on other sites

4 minutes ago, HumbleChief said:

Yes Graham, your analysis is correct and of course a new 7700K would be today's best choice but it still doesn't answer the question posed in the OP. I have an older i7 and the dual Xeons and they BOTH perform the same in certain operations. The CPU core speed and the number of cores has no effect. This is demonstrable and I just find that weird. There's something else going on behind the scenes where CPU speed has no effect.and I still wonder why. Is it simply a disk writing operation that can't be bypassed no matter how fast the processor? I am actually very happy with my system still but am curious about how Chief behaves and why out of simple curiosity.

 

The single thread (core) speed of your I7 920 is 1,959 and your Xeon L5639 is 2,085. They are virtually the same and as such both machines are equal in performance when a function is only single threaded. Be careful when you are watching your CPU monitor not to misinterpret the fact that you may see activity on all cores even though the system is just performing a single threaded operation. I believe this is just an internal management thing where it distributes the single threaded operation over the cores versus just dedicating it to only one core. 

Link to comment
Share on other sites

31 minutes ago, TheKitchenAbode said:

 

The single thread (core) speed of your I7 920 is 1,959 and your Xeon L5639 is 2,085. They are virtually the same and as such both machines are equal in performance when a function is only single threaded. Be careful when you are watching your CPU monitor not to misinterpret the fact that you may see activity on all cores even though the system is just performing a single threaded operation. I believe this is just an internal management thing where it distributes the single threaded operation over the cores versus just dedicating it to only one core. 

Interesting and I tend to agree with your premise and even though those number don't seem correct as the both faster i7960 and i7970 show 1388 and 1391 respectively (couldn't find the 920 or the 5690) on this chart, I don't think the numbers invalidate your point regarding singe threaded operations.

 

Here's another tidbit - Chief recommends more cores the better - why? Doesn't negate your theory, which again I think has merit, suggest that faster single threaded chips might be best? Or of course as suggested the fastest chip with the most cores, in that order of preference?

 

https://www.cpubenchmark.net/singleThread.html

 

BTW I am now running X5690's and they absolutely rip through RayTraces which should be expected. Too bad I don't RT much anymore.

Link to comment
Share on other sites

Larry - I got the numbers from CPU Boss. Minor differences will not be noticeable as these test are dedicated to access only one aspect under ideal conditions.

 

CA states that it is optimized for multi threaded operations, that does not mean that all operations are multi threaded. Most software calls upon routines outside of itself to perform many functions. These are written by Microsoft and many others, they are baked into the OS, drivers, memory controllers etc. Many of these are likely single threaded for which CA has no control over.

 

Ray Trace is a really good example of the performance that can be attained when a program can be written exclusively around multi threading. 

 

One thing to also keep in mind is that with dual processors some time will be consumed as the system tries to mange the flow between the two processors. If all the cores are built into a single processor then that process is eliminated. In general, a single processor with 12 cores should be faster than two 6 core processors if they both operate at the same GHz.

Link to comment
Share on other sites

4 hours ago, ComputerMaster86 said:

I am working on a computer build that has the 7700K.  It's rated at 4.2 ghz. with a max turbo of 4.5 ghz.  I can't wait to get the system up and running and try Chief out with i7-7700K.

If you can wait a few weeks for your next build, the new Intel CoffeeLake processors might be just what you are looking for.

 

http://wccftech.com/intel-coffee-lake-desktop-6-core-4-core-cpu-leaked/

Link to comment
Share on other sites

18 hours ago, HumbleChief said:

Red slot - is that good or bad? And if it's good how is it good and what operation(s) would it effect? Do you have a good guess? Or where might we find out how things are effected and by what?

The red slots are your Sata 3 slots, the blacks are the much slower sata 2... so it's good that you have them plugged into the red....

general note on this topic, I think it stands to reason that a heavier investment in coding from chief could speed everything up... ever notice how an apple iPhone can suddenly become faster or slower on each new iteration of its OS... they either fix or add bugs... cleaner codes, no redundancy, better implementation... you could see your hardware fly again if chief refined its coding... which it would probably happily do if it's client base met the demand... I hope we get there :)

on a side note, how is your dual processor set up? Do both processors compete for the ram and hard drive, I think I remember their being several ways to implement dual processors and sometimes they can be a detriment as they try and fight for resources dependent on the setup

Link to comment
Share on other sites

5 hours ago, Renerabbitt said:

on a side note, how is your dual processor set up? Do both processors compete for the ram and hard drive, I think I remember their being several ways to implement dual processors and sometimes they can be a detriment as they try and fight for resources dependent on the setup

Not sure about too much of the technicals but in general the dual setup is great for some tasks like Chief's CPU dependent RayTracing but really not that fast for every day Chief tasks. When I first set it up maximizing RT's was the goal 6 - 8 years ago and it shines in that department but it's complex (2 of everything) power hungry and just plain outdated by today's standards. Don't get me wrong it is VERY serviceable but I really need the fastest stuff out there for larger models and will upgrade as soon as the high end desktop market shows itself a little clearer.

Link to comment
Share on other sites

Larry - There is no doubt that it's a challenge to find the so called perfect solution. Ray Tracing is a much more simple thing to address as there are only two parameters one needs to consider CPU GHz and the number of cores, the higher the better. When it comes to CA's normal operations it becomes more difficult as it is not a true multi thread application and it also relies on the GPU and Disk Access. Given the current Chips, there are not really any that are perfect in every aspect. You can see from test reports that many of the high core count processors are not the best at single thread operations and vice versa. From my testing, it is also clear that the camera views are not just a GPU task, they also involve your CPU and as such there can be a bottleneck as one waits for the other, this is most likely why you did not see an improvement when you upgraded your graphics card, it was being held back by your CPU, low GHz and single thread processing.

 

Unless one builds two different machines it will always be a balancing act.

Link to comment
Share on other sites

  • 4 years later...

Please sign in to comment

You will be able to leave a comment after signing in



Sign In Now
 Share