[PATCH 2/2] drm/amdgpu/gfx: spread queues across pipes again for 1 MEC parts

Alex Deucher alexdeucher at gmail.com
Fri Jun 9 12:49:30 UTC 2017


Now that interrupts are properly enabled for all pipes, this
should be function properly.

Cc: Shirish S <shirish.s at amd.com>
Signed-off-by: Alex Deucher <alexander.deucher at amd.com>
---

Shirish,

Can you test this change on your Stoney setup?

drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c | 12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index dfbf027..03c23e3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -125,15 +125,9 @@ void amdgpu_gfx_compute_queue_acquire(struct amdgpu_device *adev)
 		if (mec >= adev->gfx.mec.num_mec)
 			break;
 
-		if (adev->gfx.mec.num_mec > 1) {
-			/* policy: amdgpu owns the first two queues of the first MEC */
-			if (mec == 0 && queue < 2)
-				set_bit(i, adev->gfx.mec.queue_bitmap);
-		} else {
-			/* policy: amdgpu owns all queues in the first pipe */
-			if (mec == 0 && pipe == 0)
-				set_bit(i, adev->gfx.mec.queue_bitmap);
-		}
+		/* policy: amdgpu owns the first two queues of the first MEC */
+		if (mec == 0 && queue < 2)
+			set_bit(i, adev->gfx.mec.queue_bitmap);
 	}
 
 	/* update the number of active compute rings */
-- 
2.5.5



More information about the amd-gfx mailing list