[PATCH] Improve pipe split between amdgpu and amdkfd v4

[Andres Rodriguez]

Hey Oded,

Let us know if you can reproduce the kfdtest results on your side.

Regards,
Andres

On 2017-04-21 04:02 PM, Andres Rodriguez wrote:
> V4 updates:
>  * Rebased onto latest 4.12-wip (ba16d6c), since I got test reports that the
>    patch series failed to apply
>
> V3 updates:
>  * Fixed kfd set resources grabbing MEC1 queues
>  * kfdtest now passes on Kaveri with the amdgpu or radeon driver
>
> V2 updates:
>  * Fixed wrong HPD offset in compute_pipe_init for gfx7
>  * Fixed compute_pipe_init using wrong ME for gfx7
>
>
> This is a split of patches that are ready to land from the series:
> Add support for high priority scheduling in amdgpu v8
>
> I've included Felix and Alex's feedback from the thread above. This includes:
>  * Separate MEC_HPD_SIZE rename into a separate patch (patch 01)
>  * Added a patch to fix the kgd_hqd_load bug Felix pointed out (patch 06)
>  * Fixes for various off-by-one errors
>  * Use gfx_v8_0_deactivate_hqd
>
> Only comment I didn't address was changing the queue allocation policy for
> gfx9 (similar to gfx7/8). See inline reply in that thread for more details
> on why this was skipped.
>
>
> Series available in the wip-queue-policy-v4 branch at:
> git at github.com:lostgoat/linux.git
> Or:
> https://github.com/lostgoat/linux.git
>
>