| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
To make the license statement consistent to each other, adjust
all license versions to v2.1+. Thus beignet should have a pure
LGPL v2.1+ license.
Signed-off-by: Zhigang Gong <zhigang.gong@intel.com>
|
|
The intel gpgpu struct is destroyed when a new gpgpu struct needed. But in that time,
the command batch relative with the destroyed gpgpu may have not finish, and the resource
in gpgpu still used by gpgpu, can't be destroyed.
So, when delete a gpgpu, check the batch status, if have not complete, insert to list in intel driver,
and delete all finished gpgpu in that list.
V2: V1 assume all the gpgpu list would complete in order, but it is not true. The insert order in is the
gpgpu delete order, not the flush command batch order. So visit and delete all complete gpgpu in the list.
Signed-off-by: Yang Rong <rong.r.yang@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>
|
|
Fix libdrm warning about unmap the unmapped buffer, as when
batch terminate we will try to do unmap again, but batch has
already been unmapped.
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>
|
|
We should always check whether a dri_bo_map success or fail.
Signed-off-by: Zhigang Gong <zhigang.gong@intel.com>
Reviewed-by: Yang Rong <rong.r.yang@intel.com>
|
|
When pending a command queue, we need to record the whole gpgpu
structure not just the batch buffer. For the following reason:
1. We need to keep those private buffer, for example those printf buffers.
2. We need to make sure this gpgpu will not be reused by other enqueuement.
v2:
Don't try to flush all user event attached to the queue.
Just need to flush the current event when doing command queue flush.
Signed-off-by: Zhigang Gong <zhigang.gong@intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>
|
|
Clear the gpgpu's batch buffer when suspend to avoid potential issue.
Signed-off-by: Yang Rong <rong.r.yang@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>
|
|
Because LRI commands will be converted to NOOP, add the I915_EXEC_ENABLE_SLM
flag to the drm kernal driver, to enable SLM in the L3. Set the flag when
application use slm. Still keep the L3 config in the batch buffer for fulsim.
Also create and use the openCL own context when exec, to avoid affect the other context.
Signed-off-by: Yang Rong <rong.r.yang@intel.com>
Reviewed-by: Junyan He <junyan.he@inbox.com>
|
|
The previous implementation forget to set the last batch
buffer, so it always does nothing at clFinish(). Now we
move the gpu sync to driver side, and set the last batch
to proper buffer object and make clFinish work as expected.
Reported and tested by: Edward Ching <edward.k.ching@gmail.com>
Signed-off-by: Zou, Nanhai <nanhai.zou@intel.com>
Signed-off-by: Zhigang Gong <zhigang.gong@linux.intel.com>
|
|
everything is properly tracked
|
|
|
