Jan Ciger wrote:
Did you try to call glFlush() at the end of the each frame in your OpenGL
application? That should force the driver to not buffer but to actually hold
your program until the vsync event. Right now you are rendering much faster
than the GPU can scan out, so your program
Hi again,
I repeated my measurements with a pure OpenGL application and compared them to
the previously recorded data from OSG:
OpenGL + Nvidia Defaults + Vsync On Min: 56.7 Max: 65.0 Avg: 60.8
OpenGL + Nvidia Defaults + Vsync Off Min: 2.9 Max: 25.0 Avg: 14.6
OSG 3.2.1 + Nvidia Defaults + VSync
Hello Björn,
On Tue, May 12, 2015 at 4:20 PM, Björn Blissing bjorn.bliss...@vti.se
wrote:
Hi again,
I repeated my measurements with a pure OpenGL application and compared
them to the previously recorded data from OSG:
OpenGL + Nvidia Defaults + Vsync On Min: 56.7 Max: 65.0 Avg: 60.8
On Mon, Apr 27, 2015 at 3:20 PM, Björn Blissing bjorn.bliss...@vti.se
wrote:
Well, this is pretty much exactly my method. But instead of an
oscilloscope I sample the signal with a A/D capture card at 10KHz.
Here is the promised data about the Oculus Rift DK1 DK2:
Oculus Rift DK1 + Vsync
d_a_heitbrink wrote:
What we did for our test was trigger a A/D deviceto I think a go from 0 to
5v, and a we added a line in our fragment shader to over ride the color and
set it to white, or black depending on a value of a uniform. We change the
Uniform to 1 (to set it to white) and
Some minor notes about the latest numbers.
First of all, the Oculus units were used as pure screens, i.e. no lens
distortion shaders. For DK2 this means running the unit in extended mode. (To
be able to run via Direct Mode I would have to modify my test program to use
the Oculus SDK.)
On Mon, Apr 20, 2015 at 1:28 AM, David Heitbrink david-heitbr...@uiowa.edu
wrote:
If I remember from my conversations with people at NVidia, the least
amount of latency you can get is 2-3 frames I cannot remember the exact
number. If you select the additional per-rendered frames, this will
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
On 04/18/2015 04:30 PM, Björn Blissing wrote:
Although very interesting, this discussion regarding minimum
latency is a bit of a tangent from my initial questions. Rendering
with VSync Off is not normally what you do in a production
environment.
If I remember from my conversations with people at NVidia, the least amount of
latency you can get is 2-3 frames I cannot remember the exact number. If you
select the additional per-rendered frames, this will increase this. Also
remember your display will also add some additional latency as
Jan Ciger wrote:
Depends on what you define as production environment. Consumer GPUs have
drivers optimized for games and there it is a common (and default) setting to
have vsync off for the sake of the highest frame rate and lowest latencies.
It is also a frequent recommendation to turn
Jan Ciger wrote:
I find these techniques to be really fragile kludges and not really
worth the effort most of the time - the saved 16ms of latency is
imperceptible for the most people and most LCDs have response times
(the time it physically takes to change the colour of a pixel) around
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
On 04/17/2015 06:55 PM, Björn Blissing wrote:
Valve is using another idea, which Alex Vlachos presented at GDC.
They start rendering of a new frame 2 ms before VSync. Using some
clever tricks to detect when Vsync is about to occur:
See page
On Thu, Apr 16, 2015 at 7:43 PM, Björn Blissing bjorn.bliss...@vti.se
wrote:
That does not seem entirely correct, if you look at the values for running
without Vsync I have managed to get down to 4 ms and a mean of 14 ms. So I
guess that my screen has a scan out time of ~4ms and since I am
Hi again,
I also tried Roberts suggestion about using the trunk and
OSG_SYNC_SWAP_BUFFERS=ON.
To get better averages I took the measurements over 100 cycles:
Recorded data:
=
OSG 3.2.1 + Nvidia Defaults + VSync On:
min_latency = 59ms
max_latency = 65ms
mean_latency = 62ms
OSG Trunk
Hi Björn,
What happens when using use Custom NVidia settings and SYNC_SWAP_BUFFERS=ON ?
Robert.
On 17 April 2015 at 13:58, Björn Blissing bjorn.bliss...@vti.se wrote:
Hi again,
I also tried Roberts suggestion about using the trunk and
OSG_SYNC_SWAP_BUFFERS=ON.
To get better averages I
robertosfield wrote:
Hi Björn,
What happens when using use Custom NVidia settings and SYNC_SWAP_BUFFERS=ON ?
Robert.
Hi Robert,
The latency values for SYNC_SWAP_BUFFERS=ON and OFF where exactly the same for
the custom settings.
Regards
Björn
--
Read this topic
Jan Ciger wrote:
That actually sounds odd, because the monitor will not refresh the image
faster than its fixed refresh rate. 4ms would require 250Hz refresh, I am not
aware of any commonly sold LCD that could go that fast. Even 120Hz ones are
quite rare. Are you sure it is not an
On Fri, Apr 17, 2015 at 1:57 PM, Björn Blissing bjorn.bliss...@vti.se
wrote:
Looking at this plot it seems like the latency times are varying according
to a pattern. My guess is that the screen runs asynchronously with the GPU.
That it certainly does. Modern LCDs are not tied to the
On Fri, Apr 17, 2015 at 6:10 PM, Björn Blissing bjorn.bliss...@vti.se
wrote:
But my main point still stands; it is possible to record latencies that
are close to the scanout time of the screen with VSync Off (albeit for very
simple rendering).
Yes, but not consistently for every frame.
Jan Ciger wrote:
Yes, but not consistently for every frame. Assuming that each frame you are
drawing takes the same time, you need to get lucky for that to happen and
then the next frame is going to have a much higher latency.
Of course! I am certainly not claiming that hitting optimal
Jan Ciger wrote:
What happens is that sometimes your program gets lucky and tells the GPU to
swap buffers just in time before the start of the next frame - then you
have very little latency, because the change gets visible almost immediately
(modulo the input latency of the monitor
Hi,
I have made some experiments in regards to rendering latency in OpenSceneGraph.
I have written a small test program which just shows one quad. During program
execution the quad changes color from black to white 20 times. To my computer I
have connected a light-to-voltage sensor which is
Hello Björn,
On Thu, Apr 16, 2015 at 2:59 PM, Björn Blissing bjorn.bliss...@vti.se
wrote:
With these settings I have recorded the following latencies:
Custom settings: min = 17ms, max = 42ms, mean = 30ms
The mean difference between VSync OFF and this custom setting is 16 ms,
i.e. about 1
Hi Björn,
The driver will be queuing up multiple frames in the FIFO, something it
does to help improve the framerate, but increases frame latency.
We aren't powerless in this though, modern drivers and hardware support
putting fences into the pipeline and waiting on these to be completed on
the
robertosfield wrote:
Hi Björn,
The driver will be queuing up multiple frames in the FIFO, something it does
to help improve the framerate, but increases frame latency.
We aren't powerless in this though, modern drivers and hardware support
putting fences into the pipeline and waiting
25 matches
Mail list logo
