[Mesa-dev] [PATCH 2/2] radv: force-enable primitive binning for The Talos Principle

[Samuel Pitoiset]

On 11/15/18 12:16 AM, Bas Nieuwenhuizen wrote:
> On Wed, Nov 14, 2018 at 5:32 PM Samuel Pitoiset
> <samuel.pitoiset at gmail.com> wrote:
>>
>>
>>
>> On 11/14/18 5:28 PM, Bas Nieuwenhuizen wrote:
>>> On Wed, Nov 14, 2018 at 5:26 PM Samuel Pitoiset
>>> <samuel.pitoiset at gmail.com> wrote:
>>>>
>>>> +5% in ultra settings for both 4k and 1080p.
>>>>
>>>> Signed-off-by: Samuel Pitoiset <samuel.pitoiset at gmail.com>
>>>> ---
>>>>    src/amd/vulkan/radv_device.c | 3 +++
>>>>    1 file changed, 3 insertions(+)
>>>>
>>>> diff --git a/src/amd/vulkan/radv_device.c b/src/amd/vulkan/radv_device.c
>>>> index b2078975a8..5d212201ec 100644
>>>> --- a/src/amd/vulkan/radv_device.c
>>>> +++ b/src/amd/vulkan/radv_device.c
>>>> @@ -495,6 +495,9 @@ radv_handle_per_app_options(struct radv_instance *instance,
>>>>                            */
>>>>                           instance->perftest_flags |= RADV_PERFTEST_SISCHED;
>>>>                   }
>>>> +
>>>> +               if (!(instance->debug_flags & RADV_DEBUG_NOBINNING))
>>>> +                       instance->perftest_flags |= RADV_PERFTEST_BINNING;
>>>
>>> Just enable for everything? Unless you have something where it is clearly worse.
>>
>> I want to enable it incrementally and whitelist games for now. It's
>> still unclear if this will help all games.
> 
> IMO we really should avoid to introduce whitelisting stuff. I tested
> some games and while ti certainly did not help a lot of them (Talos
> confirmed helped) I saw no statistically significant regressions.

What games did you test?

> 
>>
>>>
>>>>           } else if (!strcmp(name, "DOOM_VFR")) {
>>>>                   /* Work around a Doom VFR game bug */
>>>>                   instance->debug_flags |= RADV_DEBUG_NO_DYNAMIC_BOUNDS;
>>>> --
>>>> 2.19.1
>>>>
>>>> _______________________________________________
>>>> mesa-dev mailing list
>>>> mesa-dev at lists.freedesktop.org
>>>> https://lists.freedesktop.org/mailman/listinfo/mesa-dev
>> _______________________________________________
>> mesa-dev mailing list
>> mesa-dev at lists.freedesktop.org
>> https://lists.freedesktop.org/mailman/listinfo/mesa-dev