Add missing allocation of kernel private memory for the scenario when
the private memory is not allocated within `KernelImp::initialize()` but
deferred until `appendLaunchKernelWithParams()` instead.
One kernel can never allocate more private/scratch memory than
`globalMemorySize`, that ends up in `ZE_RESULT_ERROR_OUT_OF_DEVICE_MEMORY`
being returned. However, several separate kernels can exceed the
`globalMemorySize` and then, the private region of each such kernel is
allocated at later stage, in `appendLaunchKernelWithParams()`.
Such mechanism was present on pre-xehp platforms and it is now added to
xehp-and-later.
See:
* ModuleImp::checkIfPrivateMemoryPerDispatchIsNeeded()
* Module::shouldAllocatePrivateMemoryPerDispatch()
Related-To: NEO-7398
Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
Limit the amount of times compare_exchange_weak is called,
to avoid issues with contention when multiple cpu cores request
the same address.
Related-To: NEO-7030
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
- cases with null lws should only fail when computed
lws sizes result in too big number of workgroups
Related-To: NEO-6976
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
- Set initial value for ArgIndexT index in
KernelArgMiscInfoT struct
- Add check for arg index in extended metadata in order to avoid OOB
accesses
- Fix missing: populating ArgTypeTraits + refactor ULTs in order to
check it
- Add missing ULTs for Program::callPopulateZebinExtendedArgsMetadataOnce
Signed-off-by: Kacper Nowak <kacper.nowak@intel.com>
This commit switches the device ID logic from the deprecated
to the new one, so that if the user passes a hex value to the -device
parameter, ocloc will use the new implementation in the product config
helper.
Signed-off-by: Daria Hinz <daria.hinz@intel.com>
Related-To: NEO-7487
This change extends the logic of opening IPC
memory handles and fills the gap between this
logic and allocation of USM device buffers.
When HEAP_EXTENDED is available, then it is
preferred.
Signed-off-by: Wrobel, Patryk <patryk.wrobel@intel.com>
Related-To: NEO-6853
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
- Added HwInfoConfig getter in RootDeviceEnvironment,
which temporarily takes HwInfoConfig from the global array
- use HwInfoConfig from RootDeviceEnvironment to
call ConfigureHardwareCustom function
- Added getHwInfoConfig in DeviceFixture
- ConfigureHardwareCustom function and few others changed to const
- Small code cleanup
This fixes several bugs in previous (reverted) implementation.
We use correct RTStack pointer offset, and a larger RTStack size.
Related-To: LOCI-2966
Signed-off-by: Jim Snow <jim.m.snow@intel.com>
ray tracing tests
engine node helper xehp and later tests
hw helper tests
move shared ult from command queue to helpers
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
- Do not use precompiled binaries in clCreateKernelsInProgramTests.
This change is required in order to enable zebin switch by default.
Related-To: NEO-7281
Signed-off-by: Kacper Nowak <kacper.nowak@intel.com>
Unrecoverable abort will be invoked when drm ioctls fail during
device destruction.
Remove abort for case where i915 is unbinded.
Related-To: LOCI-3139
Signed-off-by: Bellekallu Rajkiran <bellekallu.rajkiran@intel.com>
also move hwhelper tests from opencl to shared folder
Related-To: HSD-18025130857
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
- Do not use precompiled binaries in clBuildProgramTests.
This change is required in order to enable zebin switch by default.
Related-To: NEO-7281
Signed-off-by: Kacper Nowak <kacper.nowak@intel.com>
