Quoting Kenneth Graunke (2017-06-15 00:13:14)
> On Friday, June 9, 2017 6:01:38 AM PDT Chris Wilson wrote:
> > Ony non-llc architectures where we are primarily reading back the
> > results of the GPU queries, then we can improve performance by using a
> > cacheable mapping of the results. Unfortuna
On 06/09/2017 06:01 AM, Chris Wilson wrote:
> Ony non-llc architectures where we are primarily reading back the
On
> results of the GPU queries, then we can improve performance by using a
> cacheable mapping of the results. Unfortunately, enabling snooping makes
> the writes from the GPU slower
On Friday, June 9, 2017 6:01:38 AM PDT Chris Wilson wrote:
> Ony non-llc architectures where we are primarily reading back the
> results of the GPU queries, then we can improve performance by using a
> cacheable mapping of the results. Unfortunately, enabling snooping makes
> the writes from the GP
Ony non-llc architectures where we are primarily reading back the
results of the GPU queries, then we can improve performance by using a
cacheable mapping of the results. Unfortunately, enabling snooping makes
the writes from the GPU slower, which may adversely affect pipelined
query operations (wh