While updating "[PATCH 5/6] drm/radeon: validate relocations in the order
determined by userspace" based on feedback, which should have been a harmless
change, I discovered that the performance dropped. The problem was that
list_add/move from one list to another reversed the list of relocations
On Mon, Feb 24, 2014 at 08:39:07PM +0100, Marek Ol??k wrote:
> On Mon, Feb 24, 2014 at 5:40 PM, Christian K?nig
> wrote:
> > Am 24.02.2014 16:20, schrieb Marek Ol??k:
> >> 1) Add virtual memory support for VRAM. Our GPUs support virtual memory,
> >> which not only solves fragmentation issues, but
On Tue, Feb 25, 2014 at 11:11 AM, Christian K?nig
wrote:
> Am 24.02.2014 20:39, schrieb Marek Ol??k:
>
>> On Mon, Feb 24, 2014 at 5:40 PM, Christian K?nig
>> wrote:
>>>
>>> Am 24.02.2014 16:20, schrieb Marek Ol??k:
1) Add virtual memory support for VRAM. Our GPUs support virtual
On Mon, 2014-02-24 at 16:20 +0100, Marek Ol??k wrote:
>
> 2) Add support for uncached GTT. I think it should improve performance
> for dGPUs under memory pressure, but some testing needs to be done to
> confirm that. Uncached GTT doesn't seem to work for me on Evergreen,
> but it's said to be
Am 24.02.2014 20:39, schrieb Marek Ol??k:
> On Mon, Feb 24, 2014 at 5:40 PM, Christian K?nig
> wrote:
>> Am 24.02.2014 16:20, schrieb Marek Ol??k:
>>> 1) Add virtual memory support for VRAM. Our GPUs support virtual memory,
>>> which not only solves fragmentation issues, but it also allows each
On Mon, Feb 24, 2014 at 5:40 PM, Christian K?nig
wrote:
> Am 24.02.2014 16:20, schrieb Marek Ol??k:
>> 1) Add virtual memory support for VRAM. Our GPUs support virtual memory,
>> which not only solves fragmentation issues, but it also allows each buffer
>> to be partially in VRAM and partially in
Hi Marek,
Some minor comments on patch 1, 2 and 5, but nothing serious. Patch 3, 4
and 6 are Reviewed-by: christian K?nig
See below for a few in line comments.
Am 24.02.2014 16:20, schrieb Marek Ol??k:
> This series improves performance for the cases when there is not enough VRAM
> for all
This series improves performance for the cases when there is not enough VRAM
for all buffers.
First of all, I'd like to mention that if you set both VRAM and GTT domains for
a buffer, you pretty much say you don't care where the buffer ends up. It
usually makes the performance even worse.
On Mon, Feb 24, 2014 at 11:40 AM, Christian K?nig
wrote:
> Hi Marek,
>
> Some minor comments on patch 1, 2 and 5, but nothing serious. Patch 3, 4 and
> 6 are Reviewed-by: christian K?nig
>
> See below for a few in line comments.
>
> Am 24.02.2014 16:20, schrieb Marek Ol??k:
>
>> This series
