SWDEV-432174 - Change the fillBuffer kernel

- Add the new fillBuffer kernel, which allows to launch a limited
number of workgroups for memory fill operation
- Switch fill memory to 16 bytes write by default
- Allow to limit the workgroups with DEBUG_CLR_LIMIT_BLIT_WG

Change-Id: Ibad1822f2d42b2fc71bcfc1917c31409c0623e8e


[ROCm/clr commit: f1dc81f427]

projects/clr/rocclr/device/rocm/rocvirtual.cpp

@@ -2828,8 +2828,8 @@ bool VirtualGPU::createVirtualQueue(uint deviceQueueSize)
   // Add mask array for AmdAqlWrap slots
   allocSize += amd::alignUp(numSlots, DeviceQueueMaskSize) / 8;
 
-  // Make sure the allocation size aligns with DWORD.
-  allocSize = amd::alignUp(allocSize, sizeof(uint64_t));
+  // Align size to 64 bytes for more efficient fill operation
+  allocSize = amd::alignUp(allocSize, 8 * sizeof(uint64_t));
 
   // CL_MEM_ALLOC_HOST_PTR/CL_MEM_READ_WRITE
   virtualQueue_ = new (dev().context()) amd::Buffer(dev().context(), CL_MEM_READ_WRITE, allocSize);