 |
|
|
|
|
|
| |
| |
|
|
|
|
| |
| |
|
|
On 13-1-2010 20:16, nemesis wrote:
> andrel escreveu:
>> You will still have the general increase in power, so if you need a 30
>> time increase, just wait 7.5 years.
>
> in 7.5 years, assuming intel don't buy nvidia, I'll be using the whole
> sheer processing power available rather than just CPU. So, you may have
> your 30x speedup, while your GPU sits idle, but I'll be making it sweat
> to give me 500-1000x speedups.
>
>>> This is the future: tapping all that hidden power that was being
>>> ignored so far
>>> because we insist on using a lame-O chip geared at word processing to
>>> do math
>>> operations.
>>
>> That remark merely shows that you don't know anything about the
>> history and design of computers, or choose to ignore that.
>
> It was obviously an over-the-top remark, but you get the point.
>
> > Hopefully there will be an
> > offspring (possibly GPU based) that will be able to parse POV scenes and
> > generate a preview of less quality but in much smaller time. When that
>
> This makes no sense at all: people aren't getting into GPU to get
> lame-O real-time previews of less quality, but to speed up final renders
> by a few orders of magnitude.
That may vary between persons. For me the most time consuming is finding
the right viewpoint, testing textures and lighting. That takes more than
an order of magnitude more time than the final render.
>
> If you think GPU = game-like graphic quality,
No
> you're very dead wrong.
So I might not be.
> General Purpose GPU programming is all about using that huge available
> power for general purpose computations. Power that you don't use at all
> if you're not a gamer right now.
What I think is that ATM GPU's are useful for trangulations and that the
result is near real life. As far as I have heard the rendering is less
physical correct and more is faked. I though they were a bit lacking in
multiple reflection and refraction, in media and possibly also in
versatility of procedural textures. I am not a gamer, so I don't
actually know for sure.
Post a reply to this message
|
|
| |
| |
|
|
|
|
| |
| |
|
|
andrel escreveu:
> That may vary between persons. For me the most time consuming is finding
> the right viewpoint, testing textures and lighting. That takes more than
> an order of magnitude more time than the final render.
ah, yes, forgot there's no OpenGL viewport... well, those with one only
care for faster final renders.
>> If you think GPU = game-like graphic quality,
> No
>> you're very dead wrong.
> So I might not be.
you say that but then you also say:
> What I think is that ATM GPU's are useful for trangulations and that the
> result is near real life. As far as I have heard the rendering is less
> physical correct and more is faked. I though they were a bit lacking in
> multiple reflection and refraction, in media and possibly also in
> versatility of procedural textures. I am not a gamer, so I don't
> actually know for sure.
I show you a link for a video of a physically-based path tracer running
on GPU and yet you talk about limited game tech...
--
a game sig: http://tinyurl.com/d3rxz9
Post a reply to this message
|
|
| |
| |
|
|
|
|
| |
| |
|
|
On 13-1-2010 20:59, nemesis wrote:
> andrel escreveu:
>> That may vary between persons. For me the most time consuming is
>> finding the right viewpoint, testing textures and lighting. That takes
>> more than an order of magnitude more time than the final render.
>
> ah, yes, forgot there's no OpenGL viewport... well, those with one only
> care for faster final renders.
>
>>> If you think GPU = game-like graphic quality,
>> No
>>> you're very dead wrong.
>> So I might not be.
>
> you say that but then you also say:
>
>> What I think is that ATM GPU's are useful for trangulations and that
>> the result is near real life. As far as I have heard the rendering is
>> less physical correct and more is faked. I though they were a bit
>> lacking in multiple reflection and refraction, in media and possibly
>> also in versatility of procedural textures. I am not a gamer, so I
>> don't actually know for sure.
>
> I show you a link for a video of a physically-based path tracer running
> on GPU and yet you talk about limited game tech...
>
No I didn't.
Post a reply to this message
|
|
| |
| |
|
|
|
|
| |
| |
|
|
andrel escreveu:
>>> What I think is that ATM GPU's are useful for trangulations and that
>>> the result is near real life. As far as I have heard the rendering
>>> is less physical correct and more is faked. I though they were a bit
>>> lacking in multiple reflection and refraction, in media and possibly
>>> also in versatility of procedural textures. I am not a gamer, so I
>>> don't actually know for sure.
>>
>> I show you a link for a video of a physically-based path tracer
>> running on GPU and yet you talk about limited game tech...
>>
> No I didn't.
Those words are yours.
--
a game sig: http://tinyurl.com/d3rxz9
Post a reply to this message
|
|
| |
| |
|
|
|
|
| |
| |
|
|
On 13-1-2010 21:52, nemesis wrote:
> andrel escreveu:
>>>> What I think is that ATM GPU's are useful for trangulations and that
>>>> the result is near real life. As far as I have heard the rendering
>>>> is less physical correct and more is faked. I though they were a bit
>>>> lacking in multiple reflection and refraction, in media and possibly
>>>> also in versatility of procedural textures. I am not a gamer, so I
>>>> don't actually know for sure.
>>>
>>> I show you a link for a video of a physically-based path tracer
>>> running on GPU and yet you talk about limited game tech...
>>>
>> No I didn't.
>
> Those words are yours.
>
Which?
Post a reply to this message
|
|
| |
| |
|
|
|
|
| |
| |
|
|
scott wrote:
>>> If you converted POV to run on the GPU then it would take a huge
>>> amount of work and would no longer be as portable as it is today.
>>
>> But would be much faster! Take a look here:
>
> Sure, but there simply aren't the people willing to do the work for
> free. Look how long it's taken from 3.6 to 3.7 beta, what hope is there
> of a complete rewrite for the GPU before 2020?
>
I finally got some free time. CUDA and OpenCL are both on my 'to learn'
list. POV-Ray seems like a good code base to start from, once I get my
brain back around parallel processing. So, that is at least one more
person available to work for free.
Post a reply to this message
|
|
| |
| |
|
|
|
|
| |
| |
|
|
andrel escreveu:
> On 13-1-2010 21:52, nemesis wrote:
>> andrel escreveu:
>>>>> What I think is that ATM GPU's are useful for trangulations and
>>>>> that the result is near real life. As far as I have heard the
>>>>> rendering is less physical correct and more is faked. I though they
>>>>> were a bit lacking in multiple reflection and refraction, in media
>>>>> and possibly also in versatility of procedural textures. I am not a
>>>>> gamer, so I don't actually know for sure.
>>>>
>>>> I show you a link for a video of a physically-based path tracer
>>>> running on GPU and yet you talk about limited game tech...
>>>>
>>> No I didn't.
>>
>> Those words are yours.
>>
> Which?
I think is that ATM GPU's are useful for trangulations and
that the result is near real life. As far as I have heard the
rendering is less physical correct and more is faked. I though they
were a bit lacking in multiple reflection and refraction, in media
and possibly also in versatility of procedural textures. I am not a
gamer, so I don't actually know for sure.
--
a game sig: http://tinyurl.com/d3rxz9
Post a reply to this message
|
|
| |
| |
|
|
|
|
| |
| |
|
|
nemesis wrote:
> Amazing the amount of self-denial one has to go in order to cope with excuses
> for why his favorite rendering engine should not evolve.
>
That isn't an arguement; it borders on insult. I offered you reasons.
Not vague reasons, but reasons why there is no man-power to divert to
this path you, who admit you do not have the skills to contribute, think
will bring a dramatic speed increase.
> Sabrina Kilian <ski### [at] vt edu> wrote:
>>> Can you imagine what povray could do comparatively without getting
>>> boiled down by unbiased techniques?!
>>>
>> Those unbiased techniques are what allows them to appear so fast. The
>> video appears to be getting 10fps tops, and between 2 and 4 the rest of
>> the time. Yes, unbiased rendering is slower to achieve the same image as
>> a biased renderer, however you can stop it much sooner and get a full
>> resolution picture. That picture just has more noise.
>>
>> Your question comes out as if you were asking "Could you imagine what
>> povray could do by using unbiased techniques for single sample speed
>> increases without being unbiased?" I think the quickest answer would be
>> "Not really, but set the max depth to 1 and lets see what the pictures
>> look like."
>
> No, my question is merely like: "hey, I can render scenes in povray in seconds
> rather than dozens of minutes. And truly complex ones in a few hours rather
> than days."
>
Right, and as I said, the bandwidth of the PCI-E bus may or may not
allow for those truly complex scenes. Look at these demos, check out the
rather simplistic geometry being used. Now pick a scene from the POV HOF.
My suspicion right now, is that those complex scenes would choke the bus
in one setup, or choke the GPU in another. This is based on knowledge of
the principle and some skill at parallel programing and low level code
design, but little in either the POV-Ray code base or GPGPU. If one of
the experts would like to chime in before I get some tests written,
please do.
> I'm not impressed with that demo's noisy 4fps display. I'm impressed to see
> scenes with full light transport phenomena set that usually take 1 hour to
> denoise being noise-free in a couple of minutes.
>
> This is the future: tapping all that hidden power that was being ignored so far
> because we insist on using a lame-O chip geared at word processing to do math
> operations.
Yes, it is. But that is not what you are asking for. You are asking for
it to be the immediate future of POV-Ray.
At this point in time, both OpenCL and CUDA have no enforced double
precision float variables. They are optional in OpenCL, and only
available on certain cards in CUDA. In a raytracer that does not care
about this, or that is rewritten to not care, this would not be a
problem. However, since POV-Ray uses them for a lot of things
internally, there is a major problem in off-loading just part to the
GPU. The parts on the GPU will only be using standard floats, while the
CPU is using doubles, which will result in noticeable precision loss. If
you think the solar system scale issue is bad, right now, then wait
until you lose a portion of that and are stuck dealing with it on a much
smaller scale. And you might as well go back to running the older 16 bit
versions if you just change the CPU to only use single precision floats.
Or, if you insist on forcing the GPU to do the extra math to fake double
precision values, then you have lost all of the speed increase.
Will POV-Ray move to GPU? Of course, once there is a good assurance that
the code will not have to be rewritten for 8 different APIs, and will
not lose the precision that it is known for now. And all of the multiple
other problems that you seem to think are just fan-boys' "self-denial" .
. . "in order to cope with excuses for why his favorite rendering engine
should not evolve."
Post a reply to this message
|
|
| |
| |
|
|
|
|
| |
| |
|
|
On 13-1-2010 22:29, nemesis wrote:
> andrel escreveu:
>> On 13-1-2010 21:52, nemesis wrote:
>>> andrel escreveu:
>>>>>> What I think is that ATM GPU's are useful for trangulations and
>>>>>> that the result is near real life. As far as I have heard the
>>>>>> rendering is less physical correct and more is faked. I though
>>>>>> they were a bit lacking in multiple reflection and refraction, in
>>>>>> media and possibly also in versatility of procedural textures. I
>>>>>> am not a gamer, so I don't actually know for sure.
>>>>>
>>>>> I show you a link for a video of a physically-based path tracer
>>>>> running on GPU and yet you talk about limited game tech...
>>>>>
>>>> No I didn't.
>>>
>>> Those words are yours.
>>>
>> Which?
>
> I think is that ATM GPU's are useful for trangulations and
> that the result is near real life. As far as I have heard the
> rendering is less physical correct and more is faked. I though they
> were a bit lacking in multiple reflection and refraction, in media
> and possibly also in versatility of procedural textures. I am not a
> gamer, so I don't actually know for sure.
>
So, point me to where I talked exclusively about game tech.
But let me try to explain again: what you pointed at and other things I
have seen so far is that GPUs are used for a limited set of primitives
only, modelling a subset of physical behaviour. Even if they claim to be
physically accurate in practice they aren't, nor is POV for that matter.
Again what I have seen and understood is that up till now POV is more
physical complete (disclaimer: I have not seen everything that is out
there.). Hence POV still has a place.
In order to get more 'realistic' games the GPUs have been optimized to
render textures and fake reflections and shadows. They can be used as
FPU replacement for certain tasks, but they are not perfect for general
processing (yet). That is as far as I know. There may have been
significant advances that I have missed because I am not a gamer and
hence do not follow the developments closely. OTOH with every new
development in GPUs there is bound to be a POVer somewhere to draw
attention to the fact that POV is still not using GPUs.
Post a reply to this message
|
|
| |
| |
|
|
|
|
| |
| |
|
|
On 13-1-2010 22:17, Sabrina Kilian wrote:
> scott wrote:
>>>> If you converted POV to run on the GPU then it would take a huge
>>>> amount of work and would no longer be as portable as it is today.
>>> But would be much faster! Take a look here:
>> Sure, but there simply aren't the people willing to do the work for
>> free. Look how long it's taken from 3.6 to 3.7 beta, what hope is there
>> of a complete rewrite for the GPU before 2020?
>>
>
> I finally got some free time.
Sounds good.
> CUDA and OpenCL are both on my 'to learn' list.
They are on my list of things to do when I get a less demanding job.
> POV-Ray seems like a good code base to start from, once I get my
> brain back around parallel processing. So, that is at least one more
> person available to work for free.
Not really for free. You get nice pictures as reward. ;)
Post a reply to this message
|
|
| |
| |
|
|
|
|
| |
|
|
