In this patch, we align up the allocation size to 2MB for all
image allocations >= 2MB located in local memory.
2MB alignment support is defined by function:
`is2MBLocalMemAlignmentEnabled`
Related-To: NEO-12287
Signed-off-by: Fabian Zwoliński <fabian.zwolinski@intel.com>
Allocations imported from shared handle are not using registerAlloc in drm
manager but on free, unregister was called.
This could lead to problems with allocation size tracking.
This change will skip the unregisterAllocation call if allocation is
imported from shared handle.
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
Modified sharedBoHandles to use the (boHandle, rootDeviceIndex) pair
as a key instead of boHandle, and added rootDeviceIndex variable in
the BufferObjectHandleWrapper class of drm_buffer_object.h.
Previously sharedBoHandles uses boHandle as a key. However, this will
not work with the system using multiple devices, because each devices
can return the same handle to refer different memory region.
Related-To: GSD-9024
Signed-off-by: Young Jin Yoon <young.jin.yoon@intel.com>
Get the local memory regions count from the primary source (MemoryInfo)
and store for further use when using DrmMemoryManager.
Add a point of dispatch (virtual `createStorageInfoFromProperties`) for
further Drm-specific customizations related to StorageInfo. As the
function became virtual, move one of its callers
(`isLocalMemoryUsedForIsa()`) from the constructor of `MemoryManager` to
respective constructors of all derivative classes. This prevents
bypassing the virtual call dispatch.
Related-To: NEO-9754
Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
Replace less type-safe uint32_t and reduce conversions between both
types.
Related-To: NEO-9754
Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
Implemented to go through entire contexts in the process and then query
reset status to check the unexpected GPU segfault.
Added a new debug variable GpuFaultCheckThreshold to change the checking
frequency for each hang check for performance analysis.
Related-To: GSD-5673
Signed-off-by: Young Jin Yoon <young.jin.yoon@intel.com>
Enable programming pat indexes on mtl linux for device buffers.
Change DrmMemoryManager::allocateMemoryByKMD to use gemCreateExt.
Set mmap flags based on coherency.
Map as write back on legacy and coherent.
On non-coherent map as write combined.
Changes currently disabled, to enable use debug keys:
DisableGemCreateExtSetPat=0
UseGemCreateExtInAllocateMemoryByKMD=1
Reorder BufferObject to decrease padding.
Related-To: NEO-7896
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
Modified ioctl_helper_prelim to support the extension of gem_create_ext,
i.e. prelim_drm_i915_gem_create_ext_mempolicy.
Added two debug variables to be used for the mempolicy extension.
Modified functions in memory_info and drm_memory_manager to support extension
Added numaif.h from https://github.com/numactl/numactl/tree/master,
v2.0.14
Related-To: NEO-8276
Signed-off-by: Young Jin Yoon <young.jin.yoon@intel.com>
Related-To: NEO-9127,NEO-9142
- Change the heap/pageSize used based on the size of the reservation
required and the device heaps available.
- Return the page size required based on the size requested by the user
for virtual reservation and the devices on the system.
- Check the size passed in by the user in memory map and physical memory
allocation is valid for the heap and page size that is required.
Signed-off-by: Spruit, Neil R <neil.r.spruit@intel.com>
- this method allocates System Memory
- argument is not needed - ExternalHeap is selected inside this function
- remove unneeded ults
- allocate memory in Device Pool for external heap allocation in
OsAgnosticMemoryManager
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
