Quoting: dubigrasuWell, I believe that one thing we should do for obtaining meaningful easily comparable results is to use the same demo file as a kind of standard.
Any demo file should do, but personally I think that the one Michael is using is more suited to the job. He's doing frequent benchmarks with high coverage (you might want to compare with) and the file he's using can be easily found on the Dota 2 test profile: http://openbenchmarking.org/ [External Link] > Tests > Dota 2 > Revision history > latest release.
It is also the same file that Vulkan Source2 developers from Valve are recommending for testing, so it makes sense for me to use it as reference.

This is just a guide, people are free to use whatever demo file they choose.

Didn't know about the revision history, still should be listed on the page directly if one is out of date IMO.

As for Valve using the PTS demo, got a source for that, I would be more willing to use it if that is confirmed.

Sidenote: I appreciate the work Phoronix puts in, but I would rather not emulate eveything he does. This site exists for the very reason of doing our own thing. I prefer an independent approach.

View this comment - View article - View full comments

Quoting: wojtek88

Quoting: liamdawe

Quoting: wojtek88Hmmm hd to 4k comparison got you weird results. 4 times more pixels to render and only like 2-5 fps less?

For those seeing this comment, the tests had to be re-done. There's a greyed-out slider for graphical quality on Dota 2 that you don't really notice unless you go to advanced options. It changes when you change resolution.

The tests are correct as of this comment btw.

@liamdawe that's what I love on this page - we're all humans and if you or someone else make a mistake, it is not removed from the comments (of course if author does not demand it), nobody is pretending that some comments didn't exist and author is perfect.

Anyway, now results seems fine :P.

I'm not here to be right, just here to provide interesting stuff for people :)

The new guide has a command line option included to make sure Dota 2 settings stay the same: https://www.gamingonlinux.com/articles/want-to-benchmark-dota-2-on-linux-heres-how-to-do-it.7435

View this comment - View article - View full comments

Guide updated for some more explanations.

View this comment - View article - View full comments

Guide updated.

View this comment - View article - View full comments

Quoting: NyamiouPhoronix tests have "-autoconfig_level 3" in the command line as recommended by Valve (see here [External Link]) to have best looking settings every time.

Phoronix is not using it:
https://openbenchmarking.org/innhold/78bee2634b4c092f4978d416ccf6887ddbd1d86e [External Link]

Unless he has another Dota 2 test I am not aware of.

Edit: Okay so his new test does: https://openbenchmarking.org/innhold/6787c1cbb500e92a0b1e72fee354b026f6b29981 [External Link]

It would be nice if his site told you a newer build of a benchmark is available.

View this comment - View article - View full comments

The demo file needs to be in the main dota folder, not the replays folder which is where the error comes from.

Quoting: fabry92console give me this error >.<
timedemo benchvulkan2
CDemoFile:: Open: couldn't open file benchvulkan2.dem for reading.
ReadDemoHeader: invalid pBuffer.
benchvulkan2.dem: unable to extract addons from file

View this comment - View article - View full comments

Quoting: coruunWhy don't you run Dota2 directly via terminal as it was mentioned by dang_valve [External Link]?

That is not a direct terminal command, "dota2" is not a command by itself unless you specifically set something up to be called when you run "dota2". I imagine he has his own set of stuff for that.

That is what the script at the end of the guide is for. Not only that, but the other mentioned reasons (like checking graphical settings and so on). I do explain everything in the guide.

View this comment - View article - View full comments

Quoting: wolfyrionAlso can someone please post in details step by step how I can do this Dota 2 benchmarks?
I would like to do some benchmarks with my GTX980

Is weird that I cant find any info on this , on every benchmark site noone explains how they did their benchmarks step by step.

I am writing out a guide at the moment, I was also frustrated by the lack of a good guide to it all.

View this comment - View article - View full comments

Quoting: dubigrasu

Quoting: NyamiouThe resuls by dubigrasu already show that you can greatly change the results by using another demo :
https://www.gamingonlinux.com/articles/a-new-benchmark-video-shows-dota-2-with-vulkan-performing-better-on-windows-than-linux.7428/page=7#63762

Yeah, but which one is the good one ? :)
Personally I used what dang_valve told me to use (after all, he's the damn Source Vulkan dev) for relevant Vulkan benchmarks, but I ran other demos too before that and the results were very different.
So not sure what to believe.

Believe all of them. That's the point, each demo has a completely different set of actions going on.

I wouldn't just use the ones the Valve dev pointed out, there aren't any that are the "best".

View this comment - View article - View full comments

Quoting: NyamiouComparing your test to the test of the guy on the video, your video card is more powerful than a GTX 1080 (same average and better minimum).

The resuls by dubigrasu already show that you can greatly change the results by using another demo :
https://www.gamingonlinux.com/articles/a-new-benchmark-video-shows-dota-2-with-vulkan-performing-better-on-windows-than-linux.7428/page=7#63762

I'm happy that Phoronix will do those Windows vs Linux Vulkan benchmarks too soon, not that I doubt your abilities but I always prefer someone who's got some experience to do them, at least I would be more incline to make some conclusions about Vulkan on Linux with his results.

A GTX 1080 is a more powerful card than my Nvidia 980ti.

The results will change with every demo, which I did note in the article. I am also using a different distribution to others.

Phoronix knows plenty more than me that is true (his 4K results on Linux showed the same thing mine did, see previous comment). All I am doing is using the official benchmark tool with a demo, you can't do much else. The graphical settings were confirmed to be the same in every single run, I double checked.

View this comment - View article - View full comments