<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<html>
<head>
<meta name="generator" content=
"HTML Tidy for Linux (vers 1 September 2005), see www.w3.org">
<meta http-equiv="Content-Type" content=
"text/html; charset=us-ascii">
<title>Chapter 25. Configuring SLI and Multi-GPU
FrameRendering</title>
<meta name="generator" content="DocBook XSL Stylesheets V1.68.1">
<link rel="start" href="index.html" title=
"NVIDIA Accelerated Linux Graphics Driver README and Installation Guide">
<link rel="up" href="part-01.html" title=
"Part I. Installation and Configuration Instructions">
<link rel="prev" href="chapter-24.html" title=
"Chapter 24. Using the nvidia-settings Utility">
<link rel="next" href="chapter-26.html" title=
"Chapter 26. Configuring Frame Lock and Genlock">
</head>
<body>
<div class="navheader">
<table width="100%" summary="Navigation header">
<tr>
<th colspan="3" align="center">Chapter 25. Configuring
SLI and Multi-GPU FrameRendering</th>
</tr>
<tr>
<td width="20%" align="left"><a accesskey="p" href=
"chapter-24.html">Prev</a> </td>
<th width="60%" align="center">Part I. Installation and
Configuration Instructions</th>
<td width="20%" align="right"> <a accesskey="n" href=
"chapter-26.html">Next</a></td>
</tr>
</table>
<hr></div>
<div class="chapter" lang="en">
<div class="titlepage">
<div>
<div>
<h2 class="title"><a name="sli" id=
"sli"></a>Chapter 25. Configuring SLI and Multi-GPU
FrameRendering</h2>
</div>
</div>
</div>
<p>The NVIDIA Linux driver contains support for NVIDIA SLI
FrameRendering and NVIDIA Multi-GPU FrameRendering. Both of these
technologies allow an OpenGL application to take advantage of
multiple GPUs to improve visual performance.</p>
<p>The distinction between SLI and Multi-GPU is straightforward.
SLI is used to leverage the processing power of GPUs across two or
more graphics cards, while Multi-GPU is used to leverage the
processing power of two GPUs colocated on the same graphics card.
If you want to link together separate graphics cards, you should
use the "SLI" X config option. Likewise, if you want to link
together GPUs on the same graphics card, you should use the
"MultiGPU" X config option. If you have two cards, each with two
GPUs, and you wish to link them all together, you should use the
"SLI" option.</p>
<p>In Linux, with two GPUs SLI and Multi-GPU can both operate in
one of three modes: Alternate Frame Rendering (AFR), Split Frame
Rendering (SFR), and Antialiasing (AA). When AFR mode is active,
one GPU draws the next frame while the other one works on the frame
after that. In SFR mode, each frame is split horizontally into two
pieces, with one GPU rendering each piece. The split line is
adjusted to balance the load between the two GPUs. AA mode splits
antialiasing work between the two GPUs. Both GPUs work on the same
scene and the result is blended together to produce the final
frame. This mode is useful for applications that spend most of
their time processing with the CPU and cannot benefit from AFR.</p>
<p>With four GPUs, the same options are applicable. AFR mode cycles
through all four GPUs, each GPU rendering a frame in turn. SFR mode
splits the frame horizontally into four pieces. AA mode splits the
work between the four GPUs, allowing antialiasing up to 64x. With
four GPUs SLI can also operate in an additional mode, Alternate
Frame Rendering of Antialiasing. (AFR of AA). With AFR of AA, pairs
of GPUs render alternate frames, each GPU in a pair doing half of
the antialiasing work. Note that these scenarios apply whether you
have four separate cards or you have two cards, each with two
GPUs.</p>
<p>Multi-GPU is enabled by setting the "MultiGPU" option in the X
configuration file; see <a href="appendix-b.html" title=
"Appendix B. X Config Options">Appendix B, <i>X
Config Options</i></a> for details about the "MultiGPU" option.</p>
<p>The nvidia-xconfig utility can be used to set the "MultiGPU"
option, rather than modifying the X configuration file by hand. For
example:</p>
<pre class="screen">
% nvidia-xconfig --multigpu=on
</pre>
<p></p>
<p>SLI is enabled by setting the "SLI" option in the X
configuration file; see <a href="appendix-b.html" title=
"Appendix B. X Config Options">Appendix B, <i>X
Config Options</i></a> for details about the SLI option.</p>
<p>The nvidia-xconfig utility can be used to set the SLI option,
rather than modifying the X configuration file by hand. For
example:</p>
<pre class="screen">
% nvidia-xconfig --sli=on
</pre>
<p></p>
<h3>Hardware requirements</h3>
<p>SLI functionality requires:</p>
<div class="itemizedlist">
<ul type="disc">
<li>
<p>Identical PCI-Express graphics cards</p>
</li>
<li>
<p>A supported motherboard</p>
</li>
<li>
<p>In most cases, a video bridge connecting the two graphics
cards</p>
</li>
</ul>
</div>
<p>For the latest in supported SLI and Multi-GPU configurations,
including SLI- and Multi-GPU capable GPUs and SLI-capable
motherboards, see <a href="http://www.slizone.com" target=
"_top">http://www.slizone.com</a>.</p>
<h3>Other Notes and Requirements</h3>
<p>The following other requirements apply to SLI and Multi-GPU:</p>
<div class="itemizedlist">
<ul type="disc">
<li>
<p>Mobile GPUs are NOT supported</p>
</li>
<li>
<p>SLI on Quadro-based graphics cards always requires a video
bridge</p>
</li>
<li>
<p>TwinView is also not supported with SLI or Multi-GPU. Only one
display can be used when SLI or Multi-GPU is enabled.</p>
</li>
<li>
<p>If X is configured to use multiple screens and screen 0 has SLI
or Multi-GPU enabled, the other screens will be disabled. Note that
if SLI or Multi-GPU is enabled, the GPUs used by that configuration
will be unavailable for single GPU rendering.</p>
</li>
</ul>
</div>
<p></p>
<div class="qandaset">
<table border="0" summary="Q and A Set">
<col align="left" width="1%">
<tbody>
<tr class="qandadiv">
<td align="left" valign="top" colspan="2">
<h3 class="title"><a name="id317408" id="id317408"></a>25.1.
Frequently Asked SLI and Multi-GPU Questions</h3>
</td>
</tr>
<tr class="question">
<td align="left" valign="top"><a name="id317414" id=
"id317414"></a><a name="id317416" id="id317416"></a></td>
<td align="left" valign="top">
<p><b>Why is glxgears slower when SLI or Multi-GPU is
enabled?</b></p>
</td>
</tr>
<tr class="answer">
<td align="left" valign="top"></td>
<td align="left" valign="top">
<p>When SLI or Multi-GPU is enabled, the NVIDIA driver must
coordinate the operations of all GPUs when each new frame is
swapped (made visible). For most applications, this GPU
synchronization overhead is negligible. However, because glxgears
renders so many frames per second, the GPU synchronization overhead
consumes a significant portion of the total time, and the framerate
is reduced.</p>
</td>
</tr>
<tr class="question">
<td align="left" valign="top"><a name="id317430" id=
"id317430"></a><a name="id317432" id="id317432"></a></td>
<td align="left" valign="top">
<p><b>Why is Doom 3 slower when SLI or Multi-GPU is
enabled?</b></p>
</td>
</tr>
<tr class="answer">
<td align="left" valign="top"></td>
<td align="left" valign="top">
<p>The NVIDIA Accelerated Linux Graphics Driver does not
automatically detect the optimal SLI or Multi-GPU settings for
games such as Doom 3 and Quake 4. To work around this issue, the
environment variable __GL_DOOM3 can be set to tell OpenGL that Doom
3's optimal settings should be used. In Bash, this can be done in
the same command that launches Doom 3 so the environment variable
does not remain set for other OpenGL applications started in the
same session:</p>
<pre class="screen">
% __GL_DOOM3=1 doom3
</pre>
<p>Doom 3's startup script can also be modified to set this
environment variable:</p>
<pre class="screen">
#!/bin/sh
# Needed to make symlinks/shortcuts work.
# the binaries must run with correct working directory
cd "/usr/local/games/doom3/"
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:.
export __GL_DOOM3=1
exec ./doom.x86 "$@"
</pre>
<p>This environment variable is temporary and will be removed in
the future.</p>
</td>
</tr>
<tr class="question">
<td align="left" valign="top"><a name="id317774" id=
"id317774"></a><a name="id317776" id="id317776"></a></td>
<td align="left" valign="top">
<p><b>Why does SLI or MultiGPU fail to initialize?</b></p>
</td>
</tr>
<tr class="answer">
<td align="left" valign="top"></td>
<td align="left" valign="top">
<p>There are several reasons why SLI or MultiGPU may fail to
initialize. Most of these should be clear from the warning message
in the X log file; e.g.:</p>
<div class="itemizedlist">
<ul type="disc">
<li>
<p><code class="computeroutput">Unsupported bus type</code></p>
</li>
<li>
<p><code class="computeroutput">The video link was not
detected</code></p>
</li>
<li>
<p><code class="computeroutput">GPUs do not match</code></p>
</li>
<li>
<p><code class="computeroutput">Unsupported GPU video
BIOS</code></p>
</li>
<li>
<p><code class="computeroutput">Insufficient PCI-E link
width</code></p>
</li>
</ul>
</div>
<p>The warning message <code class="computeroutput">'Unsupported
PCI topology'</code> is likely due to problems with your Linux
kernel. The NVIDIA driver must have access to the PCI Bridge (often
called the Root Bridge) that each NVIDIA GPU is connected to in
order to configure SLI or MultiGPU correctly. There are many
kernels that do not properly recognize this bridge and, as a
result, do not allow the NVIDIA driver to access this bridge. See
the below "How can I determine if my kernel correctly detects my
PCI Bridge?" FAQ for details.</p>
<p>Below are some specific troubleshooting steps to help deal with
SLI and MultiGPU initialization failures.</p>
<div class="itemizedlist">
<ul type="disc">
<li>
<p>Make sure that ACPI is enabled in your kernel. NVIDIA's
experience has been that ACPI is needed for the kernel to correctly
recognize the Root Bridge. Note that in some cases, the kernel's
version of ACPI may still have problems and require an update to a
newer kernel.</p>
</li>
<li>
<p>Run <span><strong class="command">lspci</strong></span> to check
that multiple NVIDIA GPUs can be identified by the operating
system; e.g:</p>
<pre class="screen">
% /sbin/lspci | grep -i nvidia
</pre>
<p>If <span><strong class="command">lspci</strong></span> does not
report all the GPUs that are in your system, then this is a problem
with your Linux kernel, and it is recommended that you use a
different kernel.</p>
</li>
<li>
<p>Make sure you have the most recent SBIOS available for your
motherboard.</p>
</li>
<li>
<p>The PCI-Express slots on the motherboard must provide a minimum
link width. Please make sure that the PCI Express slot(s) on your
motherboard meet the following requirements and that you have
connected the graphics board to the correct PCI Express
slot(s):</p>
<div class="itemizedlist">
<ul type="circle">
<li>
<p>A dual-GPU board needs a minimum of 8 lanes (i.e. x8 or x16)</p>
</li>
<li>
<p>A pair of single-GPU boards requires one of the following
supported link width combinations:</p>
<div class="itemizedlist">
<ul type="square">
<li>
<p>x16 + x16</p>
</li>
<li>
<p>x16 + x8</p>
</li>
<li>
<p>x16 + x4</p>
</li>
<li>
<p>x8 + x8</p>
</li>
</ul>
</div>
<p></p>
</li>
</ul>
</div>
<p></p>
</li>
</ul>
</div>
<p></p>
</td>
</tr>
<tr class="question">
<td align="left" valign="top"><a name="id317917" id=
"id317917"></a><a name="id317919" id="id317919"></a></td>
<td align="left" valign="top">
<p><b>How can I determine if my kernel correctly detects my PCI
Bridge?</b></p>
</td>
</tr>
<tr class="answer">
<td align="left" valign="top"></td>
<td align="left" valign="top">
<p>As discussed above, the NVIDIA driver must have access to the
PCI Bridge that each NVIDIA GPU is connected to in order to
configure SLI or MultiGPU correctly. The following steps will
identify whether the kernel correctly recognizes the PCI
Bridge:</p>
<div class="itemizedlist">
<ul type="disc">
<li>
<p>Identify both NVIDIA GPUs:</p>
<pre class="screen">
% /sbin/lspci | grep -i vga
0a:00.0 VGA compatible controller: nVidia Corporation [...]
81:00.0 VGA compatible controller: nVidia Corporation [...]
</pre>
<p></p>
</li>
<li>
<p>Verify that each GPU is connected to a bus connected to the Root
Bridge (note that the GPUs in the above example are on buses 0a and
81):</p>
<pre class="screen">
% /sbin/lspci -t
</pre>
<p>good:</p>
<pre class="screen">
-+-[0000:80]-+-00.0
| +-01.0
| \-0e.0-[0000:81]----00.0
...
\-[0000:00]-+-00.0
+-01.0
+-01.1
+-0e.0-[0000:0a]----00.0
</pre>
<p>bad:</p>
<pre class="screen">
-+-[0000:81]---00.0
...
\-[0000:00]-+-00.0
+-01.0
+-01.1
+-0e.0-[0000:0a]----00.0
</pre>
<p>Note that in the first example, bus 81 is connected to Root
Bridge 80, but that in the second example there is no Root Bridge
80 and bus 81 is incorrectly connected at the base of the device
tree. In the bad case, the only solution is to upgrade your kernel
to one that properly detects your PCI bus layout.</p>
</li>
</ul>
</div>
<p></p>
</td>
</tr>
</tbody>
</table>
</div>
</div>
<div class="navfooter">
<hr>
<table width="100%" summary="Navigation footer">
<tr>
<td width="40%" align="left"><a accesskey="p" href=
"chapter-24.html">Prev</a> </td>
<td width="20%" align="center"><a accesskey="u" href=
"part-01.html">Up</a></td>
<td width="40%" align="right"> <a accesskey="n" href=
"chapter-26.html">Next</a></td>
</tr>
<tr>
<td width="40%" align="left" valign="top">
Chapter 24. Using the nvidia-settings Utility </td>
<td width="20%" align="center"><a accesskey="h" href=
"index.html">Home</a></td>
<td width="40%" align="right" valign="top">
Chapter 26. Configuring Frame Lock and Genlock</td>
</tr>
</table>
</div>
</body>
</html>
