IdTech 4, 15% frame rate increase through semiautomatic paralellization • Hacker News Board

Re: IdTech 4, 15% frame rate increase through semiautomatic paralellization

#11

Post by kevingadd » Tue, Oct 30, 2012, 8:50 PM UTC

jspthrowaway wrote: post #10

kevingadd wrote: post #9

Earlier quoted context omitted.

PC game development is about delivering a good experience for users on a wide range of hardware configurations. A given game is not going to automatically run perfect on every hardware configuration. When considering performance issues for a particular customer, you have to weigh the cost of improvement. 3 weeks of an engineer's time for 15% speedup (even if it were in elapsed frame time, which it's not) is NOT an ea…

All of what you say is wise, but the engineer doesn't work for the studio and isn't on Doom 3's release timeline. He made the game's frame rate 15% faster of his own volition simply because he could . So it's wrapped in a sales pitch, oh well. "I see something I can improve, but I had better not improve it; were I to work at id, my time would probably be more valuably spent on other things." I wish you'd just back of…

This article is clearly trying to sell licenses for a commercial product based on unsupported, possibly deceptive claims. I don't laud that. If the goal here is to prove the value of this analysis software, they should be proving it in terms of the value it will produce for an actual company developing software - if they're proving value for a game studio, it should probably be in the context I provided above. For other kinds of developers, maybe they have infinite time and their constrained resource is engineer knowledge - in that case this software could be valuable. But you don't demonstrate that using video games.

Hacker News isn't about selling things to managers who make purchasing decisions by lying to them, last time I checked.

Re: IdTech 4, 15% frame rate increase through semiautomatic paralellization

#12

Post by jspthrowaway » Tue, Oct 30, 2012, 8:57 PM UTC

kevingadd wrote: post #11

jspthrowaway wrote: post #10

Earlier quoted context omitted.

All of what you say is wise, but the engineer doesn't work for the studio and isn't on Doom 3's release timeline. He made the game's frame rate 15% faster of his own volition simply because he could . So it's wrapped in a sales pitch, oh well. "I see something I can improve, but I had better not improve it; were I to work at id, my time would probably be more valuably spent on other things." I wish you'd just back of…

This article is clearly trying to sell licenses for a commercial product based on unsupported, possibly deceptive claims. I don't laud that. If the goal here is to prove the value of this analysis software, they should be proving it in terms of the value it will produce for an actual company developing software - if they're proving value for a game studio, it should probably be in the context I provided above. For ot…

Oh, now they're lying? Care to back that one up? That's a steep accusation that you should probably reconsider attaching to your name.

They wrote a tool to find things to parallelize. They parallelize them, the code gets faster. I realize that it isn't the faster you would prefer, but they picked an accessible target that everybody could understand. It isn't as cool if they say "we made Excel render graphs 15% faster" or "we made MP3 transcoding 15% faster". They just made a code base faster using their tool, that's all.

If they had made a video editor faster and you'd worked on video editors all your life, I'm sure you'd be here shitting on the achievement as well. They're not a game development shop. They picked a game to screw around with. They made it quicker. It just happens to be your pet area, so you absolutely cannot stand that someone figured out how to do something in your little world that you wouldn't think of.

I'm impressed you've upgraded to outright calling them liars now rather than just admit, maybe, you might be wrong.

Re: IdTech 4, 15% frame rate increase through semiautomatic paralellization

#13

Post by jspthrowaway » Tue, Oct 30, 2012, 9:18 PM UTC

randallu wrote: post #5

So looking at the patch: 1. The allocator was a bottleneck; wonder if tcmalloc would have done better? 2. Computing what to draw? (idInteraction) was reduced to a for-loop and parallelized 3. ... lots more pre-rendering stuff ... Unfortunately they didn't annotate the patch with the size of the win for any given change, or write up an analysis on what the changes were (I'm unfamiliar with idTech, too). If they got th…

glibc's malloc() is known to be lackluster under parallel workloads. Alternatives do perform better in certain circumstances, but profile before making the switch -- your situation might not be one of them.

It's possible to inject tcmalloc into an executable using Linux's preloader, too, without recompiling[1].

[1]: http://gperftools.googlecode.com/svn/trunk/doc/heapprofile.h...

Re: IdTech 4, 15% frame rate increase through semiautomatic paralellization

#14

Post by ww520 » Tue, Oct 30, 2012, 9:30 PM UTC

kevingadd wrote: post #3

A 15% framerate increase from 3 weeks of work isn't particularly impressive. It would be more meaningful if the measurement was in terms of frametime (i.e. elapsed time per frame) since framerate is not linear. From looking at the patch (nice of them to provide it), it seems like most of the changes are putting mutexes around things to guard against simultaneous access and then parallelizing some loops. It seems to m…

Wow. You really invoked some hates. All your long and thoughtful comments have been voted down. I would say you have hit a nerve.

Re: IdTech 4, 15% frame rate increase through semiautomatic paralellization

#15

Post by jspthrowaway » Tue, Oct 30, 2012, 9:34 PM UTC

ww520 wrote: post #14

kevingadd wrote: post #3

A 15% framerate increase from 3 weeks of work isn't particularly impressive. It would be more meaningful if the measurement was in terms of frametime (i.e. elapsed time per frame) since framerate is not linear. From looking at the patch (nice of them to provide it), it seems like most of the changes are putting mutexes around things to guard against simultaneous access and then parallelizing some loops. It seems to m…

Wow. You really invoked some hates. All your long and thoughtful comments have been voted down. I would say you have hit a nerve.

I, like pg and hopefully other Hacker News readers, am pretty sick of every story about something cool being immediately derailed by a know-it-all in an industry dismissing the innovation as "not cool enough". pg calls it middlebrow dismissal[1]. Rather than being treated as an imperfect launching-off point for further innovation, everything has to be world-changing perfect to have a reasonably sane comments section.

I'm actually glad this thread got pushed down, so maybe some actually informative discussion can rise up rather than an analysis of how minutely the people behind this screwed up.

[1]: http://news.ycombinator.com/item?id=4693920

Re: IdTech 4, 15% frame rate increase through semiautomatic paralellization

#16

Post by bitwize » Tue, Oct 30, 2012, 9:41 PM UTC

jspthrowaway wrote: post #15

ww520 wrote: post #14

Earlier quoted context omitted.

Wow. You really invoked some hates. All your long and thoughtful comments have been voted down. I would say you have hit a nerve.

I, like pg and hopefully other Hacker News readers, am pretty sick of every story about something cool being immediately derailed by a know-it-all in an industry dismissing the innovation as "not cool enough". pg calls it middlebrow dismissal[1]. Rather than being treated as an imperfect launching-off point for further innovation, everything has to be world-changing perfect to have a reasonably sane comments section.…

Well, there are a lot of Apple fans here, and a core part of the Apple aesthetic is "if it isn't perfect and doesn't have that 'wow' factor, better to leave it out".

Re: IdTech 4, 15% frame rate increase through semiautomatic paralellization

#17

Post by taligent » Tue, Oct 30, 2012, 9:45 PM UTC

jspthrowaway wrote: post #15

ww520 wrote: post #14

Earlier quoted context omitted.

Wow. You really invoked some hates. All your long and thoughtful comments have been voted down. I would say you have hit a nerve.

I, like pg and hopefully other Hacker News readers, am pretty sick of every story about something cool being immediately derailed by a know-it-all in an industry dismissing the innovation as "not cool enough". pg calls it middlebrow dismissal[1]. Rather than being treated as an imperfect launching-off point for further innovation, everything has to be world-changing perfect to have a reasonably sane comments section.…

The only way you know if your product is imperfect is by other people constructively criticising it. But instead you would rather all of us stand around in a circle cheering them on about how wonderful it is and politely ignore any problems.

Sounds like a guaranteed way to fail.

Re: IdTech 4, 15% frame rate increase through semiautomatic paralellization

#18

Post by jspthrowaway » Tue, Oct 30, 2012, 9:47 PM UTC

taligent wrote: post #17

jspthrowaway wrote: post #15

Earlier quoted context omitted.

I, like pg and hopefully other Hacker News readers, am pretty sick of every story about something cool being immediately derailed by a know-it-all in an industry dismissing the innovation as "not cool enough". pg calls it middlebrow dismissal[1]. Rather than being treated as an imperfect launching-off point for further innovation, everything has to be world-changing perfect to have a reasonably sane comments section.…

The only way you know if your product is imperfect is by other people constructively criticising it. But instead you would rather all of us stand around in a circle cheering them on about how wonderful it is and politely ignore any problems. Sounds like a guaranteed way to fail.

Dismissal is not constructive criticism. There's a sizable difference between "meh, nothing to see here" (which is the original comment in this thread) and "here's how this could be better".

Re: IdTech 4, 15% frame rate increase through semiautomatic paralellization

#19

Post by taligent » Tue, Oct 30, 2012, 9:51 PM UTC

jspthrowaway wrote: post #10

kevingadd wrote: post #9

Earlier quoted context omitted.

PC game development is about delivering a good experience for users on a wide range of hardware configurations. A given game is not going to automatically run perfect on every hardware configuration. When considering performance issues for a particular customer, you have to weigh the cost of improvement. 3 weeks of an engineer's time for 15% speedup (even if it were in elapsed frame time, which it's not) is NOT an ea…

All of what you say is wise, but the engineer doesn't work for the studio and isn't on Doom 3's release timeline. He made the game's frame rate 15% faster of his own volition simply because he could . So it's wrapped in a sales pitch, oh well. "I see something I can improve, but I had better not improve it; were I to work at id, my time would probably be more valuably spent on other things." I wish you'd just back of…

> He made the game's frame rate 15% faster of his own volition simply because he could.

This isn't some lone engineer's noble cause. This is a sales product demonstration.

> Attitudes like yours hurt our industry as a whole.

No it doesn't. People SHOULD be critical of demonstrations like these because they are rarely representative of real world behaviour.

Re: IdTech 4, 15% frame rate increase through semiautomatic paralellization

#20

Post by KaeseEs » Tue, Oct 30, 2012, 9:55 PM UTC

jspthrowaway wrote: post #15

ww520 wrote: post #14

Earlier quoted context omitted.

Wow. You really invoked some hates. All your long and thoughtful comments have been voted down. I would say you have hit a nerve.

I, like pg and hopefully other Hacker News readers, am pretty sick of every story about something cool being immediately derailed by a know-it-all in an industry dismissing the innovation as "not cool enough". pg calls it middlebrow dismissal[1]. Rather than being treated as an imperfect launching-off point for further innovation, everything has to be world-changing perfect to have a reasonably sane comments section.…

Another negative trend that's clearly happened in this thread is drive-by voting: all of your interlocutor's posts have negative points, whereas the only posts in the thread that deserved any downvotes were the initial post (the only legitimate instance of the poorly-named 'middlebrow dismissal' that I can see) and the one where you put words in his mouth at the end ("Oh, so they're liars now?"). Postulate: very few people read anything but the first post and its reply, and upon doing so most upvoted all of your posts in the thread and downvoted all of your interlocutor's. Intelligent discussion indeed.