Re: [PATCH 2/2] drm/amdgpu: disable gpu_sched load balancer for vcn jobs

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Am 13.03.20 um 14:59 schrieb Nirmoy Das:
VCN HW doesn't support dynamic load balance on multiple instances
for a context. This patch initializes VNC entities with only one
drm_gpu_scheduler picked by drm_sched_pick_best(). Picking a
drm_gpu_scheduler using drm_sched_pick_best() ensures that we
do load balance among multiple contexts but not among multiple
jobs in a context.

Signed-off-by: Nirmoy Das <nirmoy.das@xxxxxxx>
---
  drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c | 7 ++++++-
  1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index fa575bdc03c8..8f1e3c05812e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -121,12 +121,17 @@ static int amdgpu_ctx_init_entity(struct amdgpu_ctx *ctx, const u32 hw_ip, const
  			num_scheds = 1;
  			break;
  		case AMDGPU_HW_IP_VCN_DEC:
-			scheds = adev->vcn.vcn_dec_sched;
  			num_scheds =  adev->vcn.num_vcn_dec_sched;
+			sched = drm_sched_pick_best(adev->vcn.vcn_dec_sched,
+						    num_scheds);
+			scheds = &sched;
  			break;
  		case AMDGPU_HW_IP_VCN_ENC:
  			scheds = adev->vcn.vcn_enc_sched;
  			num_scheds =  adev->vcn.num_vcn_enc_sched;
+			sched = drm_sched_pick_best(adev->vcn.vcn_enc_sched,
+						    num_scheds);
+			scheds = &sched;

num_scheds need to be set to 1 here and above.

And maybe add a separate patch to fix the indentation of the case labels.

Christian.

  			break;
  		case AMDGPU_HW_IP_VCN_JPEG:
  			scheds = adev->jpeg.jpeg_sched;

_______________________________________________
amd-gfx mailing list
amd-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/amd-gfx



[Index of Archives]     [Linux USB Devel]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]

  Powered by Linux