<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
</head>
<body>
<p>I see the point.</p>
<p>I was thinking about using a small, simplified, reliable fixed
set of basic GPU functions which are always supported, and call
them from time to time to speed up some mass operations such as
texture scaling (instead of MMXing big textures on CPU, call
existing OpenGL driver and free the CPU for different operations
while GPU scales them). But it DOES involve lots of data exchange,
at least unless embedded GPU core can process them in the common
memory space).</p>
<p> So I see the point, the data exchange can "eat" all this profit.</p>
<p><br>
</p>
<p></p>
<div class="moz-cite-prefix">On 22.11.2022 14:06, Jose Fonseca
wrote:<br>
</div>
<blockquote type="cite"
cite="mid:BY3PR05MB8161B0D63001E816A1D5E580B60D9@BY3PR05MB8161.namprd05.prod.outlook.com">
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
<style type="text/css" style="display:none;">P {margin-top:0;margin-bottom:0;}</style>
<div style="font-family: Calibri, Helvetica, sans-serif;
font-size: 12pt; color: rgb(0, 0, 0); background-color: rgb(255,
255, 255);" class="elementToProof">
Trying to combine two OpenGL implementations it's technically
difficult. Furthermore one might thing combining two
implementations gives the best of both, but easily gives the
worst of both worlds, because there's overhead moving data
between them.</div>
<div style="font-family: Calibri, Helvetica, sans-serif;
font-size: 12pt; color: rgb(0, 0, 0); background-color: rgb(255,
255, 255);" class="elementToProof">
<br>
</div>
<div style="font-family: Calibri, Helvetica, sans-serif;
font-size: 12pt; color: rgb(0, 0, 0); background-color: rgb(255,
255, 255);" class="elementToProof">
Image the worst case scenario: draw on driver A, copy data to
driver B, draw on driver B, copy data to driver A. One might
devise a heuristic to avoid switching so often, but the end
result would end being the bulk of the rendering beind done on
the most capable drvier (llvmpipe in this case), so not much
better than always using llvmpipe.</div>
<div style="font-family: Calibri, Helvetica, sans-serif;
font-size: 12pt; color: rgb(0, 0, 0); background-color: rgb(255,
255, 255);" class="elementToProof">
<br>
</div>
<div style="font-family: Calibri, Helvetica, sans-serif;
font-size: 12pt; color: rgb(0, 0, 0); background-color: rgb(255,
255, 255);" class="elementToProof">
<br>
</div>
<div style="font-family: Calibri, Helvetica, sans-serif;
font-size: 12pt; color: rgb(0, 0, 0); background-color: rgb(255,
255, 255);" class="elementToProof">
<span style="color: rgb(0, 0, 0); font-family: Calibri,
Helvetica, sans-serif; font-size: 12pt;">This is why
technologies like NVIDIA SLI which divide the work across
multiple identical GPUs tend to split the work in a granular
fashion, like whole frames (GPU 1 draws frame 2*N, GPU 2 draws
frame 2*N + 1).</span><br>
</div>
<div style="font-family:Calibri,Helvetica,sans-serif;
font-size:12pt; color:rgb(0,0,0)" class="elementToProof">
<br>
</div>
<div style="font-family:Calibri,Helvetica,sans-serif;
font-size:12pt; color:rgb(0,0,0)" class="elementToProof">
<span style="font-size:12pt;margin:0px;background-color:rgb(255,
255, 255)" class="ContentPasted0">Furthermore, mixing
different implementations easily leads to artifacts, like
depth fighting, overlapped geometry or gaps between, because
3D APIs specification have somewhat lax rules about
rasterization, and float conversion.</span><br
class="ContentPasted0">
</div>
<div style="font-family:Calibri,Helvetica,sans-serif;
font-size:12pt; color:rgb(0,0,0)" class="elementToProof">
<span style="font-size:12pt;margin:0px;background-color:rgb(255,
255, 255)" class="ContentPasted0"><br>
</span></div>
<div style="font-family:Calibri,Helvetica,sans-serif;
font-size:12pt; color:rgb(0,0,0)" class="elementToProof">
<span style="font-size:12pt;margin:0px;background-color:rgb(255,
255, 255)" class="ContentPasted0">Honestly, it's more
effective to buy a more modern device.</span></div>
<div style="font-family:Calibri,Helvetica,sans-serif;
font-size:12pt; color:rgb(0,0,0)" class="elementToProof">
<br>
</div>
<div style="font-family:Calibri,Helvetica,sans-serif;
font-size:12pt; color:rgb(0,0,0)" class="elementToProof">
Jose</div>
<div style="font-family:Calibri,Helvetica,sans-serif;
font-size:12pt; color:rgb(0,0,0)" class="elementToProof">
<span style="font-size:12pt;margin:0px;background-color:rgb(255,
255, 255)"></span><br>
</div>
<div style="font-family:Calibri,Helvetica,sans-serif;
font-size:12pt; color:rgb(0,0,0)" class="elementToProof">
<br>
</div>
<hr tabindex="-1" style="display:inline-block; width:98%">
<div id="divRplyFwdMsg" dir="ltr"><font style="font-size:11pt"
face="Calibri, sans-serif" color="#000000"><b>From:</b>
mesa-dev <a class="moz-txt-link-rfc2396E" href="mailto:mesa-dev-bounces@lists.freedesktop.org"><mesa-dev-bounces@lists.freedesktop.org></a> on
behalf of <a class="moz-txt-link-abbreviated" href="mailto:test@profit-grand.ru">test@profit-grand.ru</a> <a class="moz-txt-link-rfc2396E" href="mailto:test@profit-grand.ru"><test@profit-grand.ru></a><br>
<b>Sent:</b> Tuesday, November 15, 2022 12:48<br>
<b>To:</b> <a class="moz-txt-link-abbreviated" href="mailto:mesa-dev@lists.freedesktop.org">mesa-dev@lists.freedesktop.org</a>
<a class="moz-txt-link-rfc2396E" href="mailto:mesa-dev@lists.freedesktop.org"><mesa-dev@lists.freedesktop.org></a><br>
<b>Subject:</b> LLVM-pipe: most powerful instructions set ;)</font>
<div> </div>
</div>
<div class="BodyFragment"><font size="2"><span
style="font-size:11pt">
<div class="PlainText">!! External Email<br>
<br>
First, thanks for saving my day. Software renderer works
way faster than<br>
no renderer at all :)<br>
<br>
But there are an "instruction set" which is way faster
than the MMX or<br>
SSE sets: it's an existing OpenGL 2.0 driver which is not
sufficient in<br>
most cases, because at least 3.0 is required nowadays.<br>
<br>
Of course, it's not literally an instruction set, but a
source of<br>
additional computing power for basic operations (assuming
advanced<br>
operations are not supported by the GPU, making LLVM-pipe
necessary for<br>
such systems).<br>
<br>
So, the actual question is:<br>
<br>
Can LLVM-pipe somehow support (today or in future
versions) a "bridge<br>
mode", relying on a different OpenGL driver for basic
operations<br>
(supported by some ancient GPU) and closing a gap between
that driver<br>
and the required OpenGL version it's usual way, by the
state-of-art<br>
software renderer?<br>
<br>
It's also somewhat related to my OGLOED driver idea (see
my Github), the<br>
difference is "bridge mode" is local, OGLOED is not. But
there are some<br>
diagrams which can help understanding my question :)<br>
<br>
<br>
!! External Email: This email originated from outside of
the organization. Do not click links or open attachments
unless you recognize the sender.<br>
</div>
</span></font></div>
</blockquote>
</body>
</html>