Search:

Type: Posts; User: tmikov; Keyword(s):

Search: Search took 0.47 seconds.

  1. comparison against the regular backend

    Would be useful to see how LLVM compares against the conventional backend.
  2. Replies
    161
    Views
    48,557

    somebody needs to pay

    I am sad about Linux being abandoned by Xamarin too, but you guys are going overboard. Working full time on a project is expensive, very expensive. How Xamarin spend their money and resources is up...
  3. The hardware is allocated permanently to a single...

    The hardware is allocated permanently to a single VM while it is running. You can't switch between multiple VMs using the same graphics card.
  4. It is useful in highly specialized cases, but...

    It is useful in highly specialized cases, but definitely not as an universal way to meaningfully accelerate VM graphics.

    True, I could stick a second NVidia in and play Windows games in a VM,...
  5. not the right direction

    How is this the right direction? It is interesting technically, but not that useful. I don't want to give the VMs access to my hardware. I want them to have optimized para-virtualized drivers which...
  6. Replies
    16
    Views
    4,990

    Hmm, what OS are you running inside DosBox? :-)

    Hmm, what OS are you running inside DosBox? :-)
  7. 4 Ms is really a very long time, a huge amount of...

    4 Ms is really a very long time, a huge amount of CPU instructions. Plus CPU utilization is not high. This is not about code optimization. I am certain it is not a hundred little things, it must be a...
  8. Thank you for this generic armchair response, but...

    Thank you for this generic armchair response, but that's not really what I am looking for. I am trying to find our why the blob is much faster at rendering a single texture.

    All that talk about 15...
  9. Fair enough. But what would be a good synthetic...

    Fair enough. But what would be a good synthetic stress test?

    Also, do you have an idea why the blob is faster? Could it be memory clocks, power management, etc?
  10. This confirms what I am seeing with my silly "one...

    This confirms what I am seeing with my silly "one rotating static texture" test. No big improvement yet when I enable 2D tiling for textures and the frame buffer. Perhaps there is a specific usage...
  11. My test code is really basic but if anyone is...

    My test code is really basic but if anyone is interested I can post it. I posted an EGL version to the mesa list. Add it to the PTS perhaps? :-)
  12. Tiling is enabled, though I don't see a...

    Tiling is enabled, though I don't see a difference when I enable 2D tiling vs 1D.

    About EGL: I have applied a simple patch which enables tiling of the frame buffer. With that It matches the...
  13. The closed blob's perfirmance advantage is not...

    The closed blob's perfirmance advantage is not due to tweaks like this. I have an extremely simple test case which renders a single static rectangular texture and the open source driver is half the...
  14. Most of these cars have 3, 4 or even 6 outputs....

    Most of these cars have 3, 4 or even 6 outputs. So at the very least you need 60 FPS per output...
  15. I have been doing some tests myself with the...

    I have been doing some tests myself with the latest stuff from Git. Tiling is enabled. PCIe 2.0 is enabled too (you need a kernel parameter radeon.pcie_gen2=1), but it has no effect on my tests,...
  16. What is the fundamental reason for the difference?

    Does anybody know what the fundamental reason for the speed difference is? The proprietary driver is at least 3X faster on all tests - that is not something that you can achieve only with incremental...
Results 1 to 16 of 17