Use cpu copy for globals surface when allocated through svm, allocation
not set as lockable but locking allocation succeeds.
Related-To: NEO-7796
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
When state base address tracking is enabled and command list use private heaps
then command list at destroy time must calls all compute CSRs that were using
that heap to invalidate state caches.
This allows new command list to reuse the same heap allocation for different
surface states, so before new use cached states are invalidated.
Related-To: NEO-5055
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
Allows the user to use alignments > 64KB in `createUnifiedMemoryAllocation`
So that the restriction in `piextUSMDeviceAlloc` of the DPC++ runtime
could be lifted
Related-To: LOCI-4168
Signed-off-by: Lu, Wenbin <wenbin.lu@intel.com>
zeCommandQueueExecuteCommandLists return ZE_RESULT_ERROR_UNKNOWN when OOM
in some scenario of direct submission.
Related-To: NEO-7840
Signed-off-by: Pan Zhenjie <zhenjie.pan@intel.com>
Keep resolving with semaphores if multiple (>2) queues are submitting to
the same CSR. In such case, semaphores allow concurrent execution while
pipecontrols would serialize it.
Related-To: NEO-7321
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
Topology map was only being created when ZET_ENABLE_PROGAM_DEBUGGING was
set. This was not correct. Now it is unconditionally created at init,
and debug attach will fail if it is not valid.
Related-to: LOCI-3937
Signed-off-by: Yates, Brandon <brandon.yates@intel.com>
- Fix potential memleak in case ASSERT returns false and test gets
aborted
- Remove not needed function argument
Signed-off-by: Kacper Nowak <kacper.nowak@intel.com>
As the fan component is not supported on Linux, hence for the ULTs a
fan handle is created and used which improves the coverage for the Fan
component.
Related-To: LOCI-2113
Signed-off-by: Bari, Pratik <pratik.bari@intel.com>
Pass resolveDependenciesByPipecontrol bool value to get command stream
methods instead of reevaluating the condition.
Related-To: NEO-7321
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
Enables P2P Copy support for all Image API related calls:
- zeCommandListAppendImageCopy
- zeCommandListAppendImageCopyRegion
- zeCommandListAppendImageCopyToMemory
- zeCommandListAppendImageCopyFromMemory
Related-To: LOCI-4112
Signed-off-by: Raiyan Latif <raiyan.latif@intel.com>
The memoryBusWidth used for the computation of maxBandwidth has been
changed to 128 bytes from 128 bits. Hence the final maxBandwidth need
not be further divided by 8 to convert it into bytes/sec.
Related-To: LOCI-3833
Signed-off-by: Bari, Pratik <pratik.bari@intel.com>
- Added support for the Frequency APIs in the new sysman design.
- Added ULTs for the Frequency APIs in the new sysman design.
Related-To: LOCI-4096
Signed-off-by: Bari, Pratik <pratik.bari@intel.com>
- Explicitly force unbind of Buffer Objects during unmap to ensure that
Buffer Objects can be reused in the same application.
Related-To: LOCI-4162
Signed-off-by: Spruit, Neil R <neil.r.spruit@intel.com>
It is possible that a module has so many kernels that the 4GB limit of
GPU VA is depleted when each kernel allocates a 64 KB page for its own
ISA. In such case, propagate the ZE_RESULT_ERROR_OUT_OF_DEVICE_MEMORY to
the API caller to indicate the actual problem.
Currently such scenario is not detected, the execution advances a bit
further and the following crashes do not let the user to easily
understand what happened.
Related-To: NEO-7788
Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
Remove blocking condition disallowing GTPin instrumentation using OCL interface
for stateless kernels (where SSH size == 0). It is required in order to
reintroduce support for GTPin on platforms supporting stateless
addressing model only.
- Always allow for adding surface state for GTPin use, even if kernel
SSH size == 0,
- Correct addSurfaceState function logic
- Remove and/or modify GTPin unit tests based on previous approach
- Wrap logic for pushing BT and SSH into separate function
- Minor code refactor; remove not needed test function
Signed-off-by: Kacper Nowak <kacper.nowak@intel.com>
After resolving NEO-7684 in turns out that `zeKernelGetProperties`
is still returning wrong value for `maxNumSubgroups` since it
did not take into account `LargeGRF & SIMD` limitation.
Related-To: NEO-7829
Signed-off-by: Krzysztof Gibala <krzysztof.gibala@intel.com>
