Twilight Render User Forum

Got it, thanks! Will continue some testing.

Chris wrote: ↑Sat Dec 22, 2018 7:48 pm I believe you are correct. When running a CPU core at 100%, hyper threading is not effective. And if there is only one floating point processor per core, all the more reason to just run 1 thread per core for rendering.

Hi! I've been comparing rendering times on various cloud computing configurations (Google Compute Engine and Amazon EC2 so far). Since I'd like to use progressive render (easy 09 interior) on these, I'm wondering if it's possible to compare rendering times with this setting? I know it's a progressiv...

Correction: Windows EC2 instances don't have per second billing. Looks like hourly. That might be the end of my testing for now until they have per minute billing at least. Oh well, fun while it lasted :). Edit: Looks like Google has some good options which I'll check out next. c5.18xlarge with Win...

Pricing here: https://aws.amazon.com/ec2/pricing/on-demand/ + GPU: https://aws.amazon.com/ec2/elastic-graphics/ My understanding is that the best systems for rendering are the "Compute Optimized" systems, specially c5.large to c5.18xlarge. The GPU addon is required to get SketchUp to load ...

That makes sense, ya. I plan on using Easy09 on this system for production rendering. I actually can increase the threads to 72 manually, just noticed that. However on the lamp speed test model this increases rendering times considerably. The system is (reported to be) dual CPU, each 18 core / 36 th...

Amazon Web Services EC2 c5.18xlarge with eg1.medium attached graphics.

I'm a bit disappointed this isn't winning here, but it's still a lot faster than my computer (i5-2500k).

Low: 12 seconds
Medium: 47 seconds
High: 2 minutes

Hi,

Wondering if rendering is limited to 36 threads or whether I'm missing something here. See attached.

This is Amazon EC2 c5.18xlarge. I want to do some render time comparisons on various EC2 configurations .

thanks!
brook