On 01/25/2013 09:31 AM, Eric Anholt wrote:
Kenneth Graunke writes:
On 01/20/2013 02:59 PM, Eric Anholt wrote:
Before, we were keeping a CPU-only buffer to accumulate the batchbuffer in,
which was an improvement over mapping the batch through the GTT directly
(since any readback or other failu
Kenneth Graunke writes:
> On 01/20/2013 02:59 PM, Eric Anholt wrote:
>> Before, we were keeping a CPU-only buffer to accumulate the batchbuffer in,
>> which was an improvement over mapping the batch through the GTT directly
>> (since any readback or other failure to stream through write combining
On 01/20/2013 02:59 PM, Eric Anholt wrote:
Before, we were keeping a CPU-only buffer to accumulate the batchbuffer in,
which was an improvement over mapping the batch through the GTT directly
(since any readback or other failure to stream through write combining
correctly would hurt). However, o
Before, we were keeping a CPU-only buffer to accumulate the batchbuffer in,
which was an improvement over mapping the batch through the GTT directly
(since any readback or other failure to stream through write combining
correctly would hurt). However, on LLC-sharing architectures we can do better
