[GPU] Allow host buffer access for Xe2+ iGPUs (#32912)

### Description of the issue
Integrated GPUs starting from Xe2 can benefit from reusing the
host-sided buffer for the weights. This allows to avoid the allocation
of the device-sided buffer in the same physical memory with significant
memory footprint reduction and no runtime penalty. Previously it was
enabled only for LNL (#31600), but for AI weights that don't benefit
from compression there's no need to limit this functionality only to
that platform.

#### Reproduction step and snapshot
- $ benchmark_app -d GPU -hint latency -nireq 1 -t 30 -b 1 -m <model>
-ip f32 -op f32
Check for the "Compile model ram used" metric. For an fp16 stable
diffusion model with size of 600MB, there is a ~600MB on multiple
platforms, more details in the ticket.

#### Checklist
- [x] Is it a proper fix? (not a workaround)
- [ ] Did you include test case for this fix, if necessary?
- [ ] Did you review existing test that can be extended to cover this
scenario? Which test did you review?

### Tickets:
 - [CVS-176845](https://jira.devtools.intel.com/browse/CVS-176845)

Author: mklimenk

src/plugins/intel_gpu/src/graph/network.cpp

@@ -1004,8 +1004,8 @@ void network::transfer_memory_to_device(std::shared_ptr<primitive_inst> instance
         return;
 
     if (alloc_type == allocation_type::usm_host || alloc_type == allocation_type::usm_shared) {
-        // usm_device memory does not provide performance benefits on the LNL platform
-        if (get_engine().get_device_info().arch == gpu_arch::xe2 &&
+        // usm_device memory does not provide performance benefits on the integrated Xe2+ platforms
+        if (get_engine().get_device_info().arch >= gpu_arch::xe2 &&
             get_engine().get_device_info().dev_type == device_type::integrated_gpu) {
             return;
         }

src/plugins/intel_gpu/src/graph/program.cpp

@@ -691,8 +691,8 @@ void program::transfer_memory_to_device() {
             }
 
             if (alloc_type == allocation_type::usm_host || alloc_type == allocation_type::usm_shared) {
-                // usm_device memory does not provide performance benefits on the LNL platform
-                if (get_engine().get_device_info().arch == gpu_arch::xe2 &&
+                // usm_device memory does not provide performance benefits on the integrated Xe2+ platforms
+                if (get_engine().get_device_info().arch >= gpu_arch::xe2 &&
                     get_engine().get_device_info().dev_type == device_type::integrated_gpu) {
                     return;
                 }