Created attachment 120817 [details]
gpu crash dump

Hi,

DMesg gives me the following output:


[Di Jan  5 17:34:29 2016] [drm] GPU HANG: ecode 6:-1:0x00000000, reason: Kicking stuck semaphore on render ring, action: continue
[Di Jan  5 17:34:29 2016] [drm] GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace.
[Di Jan  5 17:34:29 2016] [drm] Please file a _new_ bug report on bugs.freedesktop.org against DRI -> DRM/Intel
[Di Jan  5 17:34:29 2016] [drm] drm/i915 developers can then reassign to the right component if it's not a kernel issue.
[Di Jan  5 17:34:29 2016] [drm] The gpu crash dump is required to analyze gpu hangs, so please always attach it.
[Di Jan  5 17:34:29 2016] [drm] GPU crash dump saved to /sys/class/drm/card0/error
[Di Jan  5 17:34:29 2016] [drm] enabling PCIE gen 2 link speeds, disable with radeon.pcie_gen2=0
[Di Jan  5 17:34:29 2016] [drm] PCIE GART of 1024M enabled (table at 0x0000000000274000).
[Di Jan  5 17:34:29 2016] radeon 0000:01:00.0: WB enabled
[Di Jan  5 17:34:29 2016] radeon 0000:01:00.0: fence driver on ring 0 use gpu addr 0x0000000040000c00 and cpu addr 0xffff8804492b2c00
[Di Jan  5 17:34:29 2016] radeon 0000:01:00.0: fence driver on ring 3 use gpu addr 0x0000000040000c0c and cpu addr 0xffff8804492b2c0c
[Di Jan  5 17:34:29 2016] radeon 0000:01:00.0: fence driver on ring 5 use gpu addr 0x0000000000072118 and cpu addr 0xffffc90002032118
[Di Jan  5 17:34:29 2016] [drm] ring test on 0 succeeded in 2 usecs
[Di Jan  5 17:34:29 2016] [drm] ring test on 3 succeeded in 20 usecs


the crash dump file is attached.