<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Re: vmware SVGA memory size (&amp;gt;8GB) and General Performance Improvement Question (host mem bandwid in VMware Workstation Pro Discussions</title>
    <link>https://communities.vmware.com/t5/VMware-Workstation-Pro/vmware-SVGA-memory-size-gt-8GB-and-General-Performance/m-p/2978029#M182049</link>
    <description>&lt;P&gt;&lt;BR /&gt;Umm. There are these things called 'Textures'. &lt;img class="lia-deferred-image lia-image-emoji" src="https://communities.vmware.com/html/@DCF4E2F7991292CEECF250394DB2C2BC/emoticons/1f642.png" alt=":slightly_smiling_face:" title=":slightly_smiling_face:" /&gt; so it's more than just pixel space. Sorry, couldn't resist a snarky response.&lt;/P&gt;&lt;P&gt;Anyway, what I'm seeing is that textures do not have enough space to load in for detailed CAD, rendering, and game development work. Native function on 24GB or more cards I don't see this. This was similar back when I had to move from 4 and 8GB native cards to ones with larger memory. Since workstation *appears* to be using the host's physical ram as a shared memory buffer that then ?maps that? to the host's gpu figure it would be possible to allow a larger reserve space for that mapping. I mean it is relatively easy to have a host that has 256GB or more ram in it so to dedicate say 64GB ram to a guest (32GB for shared memory) for an example, is not really a hardware issue.&lt;/P&gt;&lt;P&gt;So was just trying to see if there was a way remove or expand the software limit.&lt;/P&gt;</description>
    <pubDate>Tue, 18 Jul 2023 22:29:14 GMT</pubDate>
    <dc:creator>stevecs</dc:creator>
    <dc:date>2023-07-18T22:29:14Z</dc:date>
    <item>
      <title>vmware SVGA memory size (&gt;8GB) and General Performance Improvement Question (host mem bandwidth?)</title>
      <link>https://communities.vmware.com/t5/VMware-Workstation-Pro/vmware-SVGA-memory-size-gt-8GB-and-General-Performance/m-p/2972627#M181650</link>
      <description>&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;I have/use VM's as my primary desktop (my host is ubuntu 22.04 or windows server 2022 and 2019).&amp;nbsp;&amp;nbsp; I am a *VERY* heavy multi-task worker and have numerous applications and VM's running.&amp;nbsp;&amp;nbsp; On a single VM I have the screen spanned across 5 2560x1440 displays (in vertical mode) so 7200x2560 resolution to the guest (s).&amp;nbsp;&lt;/P&gt;&lt;P&gt;Even with 8GB of sVGA memory I see issues where not everything can be stored in shared graphics on the guest.&amp;nbsp; It's close, and depends on the applications I'm running.&amp;nbsp;&amp;nbsp; Does anyone know if you can override this to the guest to provide more sVGA memory?&lt;/P&gt;&lt;P&gt;Second but related question.&amp;nbsp; Since this is 'shared graphics memory' on the guest, I am assuming here that this is stored in the host's RAM and not directly mapped to the Host's GPU?&amp;nbsp; I.e. the host may map this to the gpu at a later point but, the guest/hypervisor stores this in the host's main memory?&lt;/P&gt;&lt;P&gt;Reason why I'm asking this is, IF the hypothesis is true, would changing the host hardware to use a platform that has more memory bandwidth help in performance for graphics on the guest?&amp;nbsp;&amp;nbsp; i.e.&amp;nbsp; Opposed to a consumer platform of 2 channel memory, going to a server/workstation platform with 4-12 channel memory help here?&amp;nbsp; As the memory bandwidth would be greatly increased. &amp;nbsp;&lt;/P&gt;&lt;P&gt;Has anyone done any testing with this?&lt;/P&gt;</description>
      <pubDate>Sun, 11 Jun 2023 13:30:51 GMT</pubDate>
      <guid>https://communities.vmware.com/t5/VMware-Workstation-Pro/vmware-SVGA-memory-size-gt-8GB-and-General-Performance/m-p/2972627#M181650</guid>
      <dc:creator>stevecs</dc:creator>
      <dc:date>2023-06-11T13:30:51Z</dc:date>
    </item>
    <item>
      <title>Re: vmware SVGA memory size (&gt;8GB) and General Performance Improvement Question (host mem bandwid</title>
      <link>https://communities.vmware.com/t5/VMware-Workstation-Pro/vmware-SVGA-memory-size-gt-8GB-and-General-Performance/m-p/2978026#M182048</link>
      <description>&lt;P&gt;5 * 2560 * 1440 = 18432000 pixels, so at 4-bytes a pixel, that's only ~70MB ?&amp;nbsp; So we shouldn't have a problem just fitting the screens in.&lt;/P&gt;&lt;P&gt;When you say you see issues, what kinds of problems are you seeing specifically?&lt;/P&gt;&lt;P&gt;But no, our virtual graphics device doesn't support more than 8GB of graphics memory at a time.&amp;nbsp; The Guest and Host have some ability to swap things in and out of the GPU, so with multiple applications it should be more of a soft limit than a hard limit.&lt;/P&gt;&lt;P&gt;As far as how much does memory bandwidth help, it's very workload dependent, so it's hard to say generally.&lt;/P&gt;</description>
      <pubDate>Tue, 18 Jul 2023 22:17:59 GMT</pubDate>
      <guid>https://communities.vmware.com/t5/VMware-Workstation-Pro/vmware-SVGA-memory-size-gt-8GB-and-General-Performance/m-p/2978026#M182048</guid>
      <dc:creator>banackm</dc:creator>
      <dc:date>2023-07-18T22:17:59Z</dc:date>
    </item>
    <item>
      <title>Re: vmware SVGA memory size (&gt;8GB) and General Performance Improvement Question (host mem bandwid</title>
      <link>https://communities.vmware.com/t5/VMware-Workstation-Pro/vmware-SVGA-memory-size-gt-8GB-and-General-Performance/m-p/2978029#M182049</link>
      <description>&lt;P&gt;&lt;BR /&gt;Umm. There are these things called 'Textures'. &lt;img class="lia-deferred-image lia-image-emoji" src="https://communities.vmware.com/html/@DCF4E2F7991292CEECF250394DB2C2BC/emoticons/1f642.png" alt=":slightly_smiling_face:" title=":slightly_smiling_face:" /&gt; so it's more than just pixel space. Sorry, couldn't resist a snarky response.&lt;/P&gt;&lt;P&gt;Anyway, what I'm seeing is that textures do not have enough space to load in for detailed CAD, rendering, and game development work. Native function on 24GB or more cards I don't see this. This was similar back when I had to move from 4 and 8GB native cards to ones with larger memory. Since workstation *appears* to be using the host's physical ram as a shared memory buffer that then ?maps that? to the host's gpu figure it would be possible to allow a larger reserve space for that mapping. I mean it is relatively easy to have a host that has 256GB or more ram in it so to dedicate say 64GB ram to a guest (32GB for shared memory) for an example, is not really a hardware issue.&lt;/P&gt;&lt;P&gt;So was just trying to see if there was a way remove or expand the software limit.&lt;/P&gt;</description>
      <pubDate>Tue, 18 Jul 2023 22:29:14 GMT</pubDate>
      <guid>https://communities.vmware.com/t5/VMware-Workstation-Pro/vmware-SVGA-memory-size-gt-8GB-and-General-Performance/m-p/2978029#M182049</guid>
      <dc:creator>stevecs</dc:creator>
      <dc:date>2023-07-18T22:29:14Z</dc:date>
    </item>
  </channel>
</rss>

