use cpu copy with locked pointer if possible
because this is faster than copy on gpu
limit to buffers of size at most 64kb
Related-To: NEO-7332
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
Introduce debug variable to control which engines
the tranfser will be split into
Related-To: NEO-7173
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
The default TG dispatch size can be changed
to a better value based on number of threads in TG or
currently available amount of threads on GPU.
Decision on what TG dispatch size should be are based on
implemented heuristics.
Signed-off-by: Rafal Maziejuk <rafal.maziejuk@intel.com>
Related-To: NEO-6989
optimization available under flag
ForceCsrLockInBcsEnqueueOnlyForGpgpuSubmission
Related-To: NEO-7011
Signed-off-by: Cencelewska, Katarzyna <katarzyna.cencelewska@intel.com>
Previous fix was causing the runtime to get buffer size
without gfx allocation, causing a seg fault.
This commit moves the fix logic to enqueue handler,
only changing the enqueueProperties.
Related-To: NEO-6948
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
This commit fixes problem with untransfered shared usm memory to gpu
when there is submit to gpu trigerred by user event. Also there is a fix
for dead lock problem caused by mixed orders of locking mutexes in csr
and in direct submission controller.
Related-To: NEO-6762
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
On multi device contexts we allocate svm in system memory.
This caused svmMap calls to assume no copy is needed and
no cache flush was sent to gpu and data modified by earlier
gpu commands was not being visible on host.
This change will add pipecontrol with dcFlush on svmMap
calls when task count from wait is enabled.
Related-To: NEO-6948
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
With this commit on DG2 32bit driver will check if passed host ptr for
clEnqueueReadBuffer is write combined memory. If check will be true copy
will be make on CPU.
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
-engineGroupTyp to engineGroupType
-remove gap between commits to use same desc.ordinal in createCommandQueue
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
Notify gtpin onContextDestroy before SVM Allocations are deleted.
Resolves: NEO-6985
Signed-off-by: Sebastian Luzynski <sebastian.jozef.luzynski@intel.com>
There is not need to enable batching in this case as we do not have
synchronization points between enqueues.
Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
This change introduces detection of GPU hangs in flushBcsTask()
function. The new code has been covered with ULTs.
Related-To: NEO-6681
Signed-off-by: Patryk Wrobel <patryk.wrobel@intel.com>
Define single .clang-tidy configuration with all used checks and use
NOLINT to selectively silence tool. That way cleanup should be easier.
third_part/ has its own configuration that disables clang-tidy for this
folder.
Signed-off-by: Artur Harasimiuk <artur.harasimiuk@intel.com>
