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
Make synchronous mode default
Add asynchronous mode switch for both immediate and regular command lists
Show all invalid data in verbose mode
Add switch for allocation flag
Do not use uncached host allocations as default
Initialize local variables
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
- Properly check for IPC event handle flag to determine if the event
pool memory is sharable between processes.
- Given Host Visible Event Pool, a check is done to determine if the
Host memory can be shared between the processes.
- Enabled handling if Event Host Memory is shareable for DRM
- If Event Pool Memory is Not shareable, then retrieving the IPC Event
Pool Handle returns unsupported.
Signed-off-by: Neil R Spruit <neil.r.spruit@intel.com>
Implementation was assuming that if HasRTCalls is true then the
RTDispatchGlobals patch token is also valid, but that isn't the case
when the application is using its own RTDispatchGlobals instead of the
one provided by the L0 UMD.
Related-To: LOCI-3323
Signed-off-by: Jim Snow <jim.m.snow@intel.com>
optimization available under flag
ForceCsrLockInBcsEnqueueOnlyForGpgpuSubmission
Related-To: NEO-7011
Signed-off-by: Cencelewska, Katarzyna <katarzyna.cencelewska@intel.com>
destroy event and event pool resources
destroy kernel and module resources
pass context handle as reference
change function variable's name and comments to kernel
change variable names to more appropriate
drop driver from function argument in image test
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
With this change, init for sysman Scheduler/Memory API would
not be done during zeInit.
init and thereby Scheduler/Memory API handle creation would be done
only when user explicitly requests to enumerate handles
using zesDeviceEnumSchedulers/zesDeviceEnumMemory.
Related-To: LOCI-3127
Signed-off-by: Kulkarni, Ashwin Kumar <ashwin.kumar.kulkarni@intel.com>
Use cl_intel_subgroup_matrix_multiply_accumulate in place
of previous cl_intel_subgroup_matrix_multiply_accumulate_for_PVC
Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
With this change, init for sysman PCI, Global operations and Events
API would not be done during zeInit.
init and thereby PCI, Global operations and Events API handle creation
would be done implicitly only when user explicitly calls any APIs.
Related-To: LOCI-3127
Signed-off-by: Kulkarni, Ashwin Kumar <ashwin.kumar.kulkarni@intel.com>
add aub mode where it is missing
add missing result checks
unify printing device properties
add printing kernel properties
use unified test result print when applicable
add module creation error handling
make OS agnostic global work offset test
use correct API to retrieve extension in global work offset test
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
