Adds CustomAllocator interface and Sample App

 * Updates the runtime options with a CustomAllocatorMap which allows to define a CustomAllocator for specific backends
 * Change IBackendInternal interface to use a shared pointer to a custom allocator
 * Update ClBackend.hpp/cpp to use the CustomAllocator
 * Adds an example application and unit test which uses a CustomAllocator for GpuAcc
 * Refactor of the interface to use MemorySource instead of the user Mapping cl_mem directly
 * Modify the BackendRegistry to also hold a registry of CustomAllocators
 * BackendRegistry Deregister will also deregister any allocators associated with that backend id
 * set_global_allocator within the BaseMemoryManager so that it always matches the currently used allocator

Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I156d819686021865f4375e6cb7a5c5dec8fee9e8
Signed-off-by: David Monahan <david.monahan@arm.com>

1 files changed, 8 insertions, 2 deletions

diff --git a/src/backends/cl/ClImportTensorHandle.hpp b/src/backends/cl/ClImportTensorHandle.hpp
index 3fca7cb127..69cd4a6d81 100644
--- a/src/backends/cl/ClImportTensorHandle.hpp
+++ b/src/backends/cl/ClImportTensorHandle.hpp
@@ -140,10 +140,16 @@ public:
 private:
     bool ClImport(const cl_import_properties_arm* importProperties, void* memory)
     {
-        const size_t totalBytes = m_Tensor.info()->total_size();
+        size_t totalBytes = m_Tensor.info()->total_size();
+
+        // Round the size of the buffer to a multiple of the CL_DEVICE_GLOBAL_MEM_CACHELINE_SIZE
+        auto cachelineAlignment =
+                arm_compute::CLKernelLibrary::get().get_device().getInfo<CL_DEVICE_GLOBAL_MEM_CACHELINE_SIZE>();
+        auto roundedSize = cachelineAlignment + totalBytes - (totalBytes % cachelineAlignment);
+
         cl_int error = CL_SUCCESS;
         cl_mem buffer = clImportMemoryARM(arm_compute::CLKernelLibrary::get().context().get(),
-                                          CL_MEM_READ_WRITE, importProperties, memory, totalBytes, &error);
+                                          CL_MEM_READ_WRITE, importProperties, memory, roundedSize, &error);
         if (error != CL_SUCCESS)
         {
             throw MemoryImportException("ClImportTensorHandle::Invalid imported memory" + std::to_string(error));