[Libomptarget] Implement the host memory allocator with fine grained memory

This patch should enable the "Host" allocation using fine-grained
memory. As far as I understand, this is HSA managed memory that is
availible to the host, but can be accessed by the device as well.
The original patch that introduced these extensions just stipulated that
it's "non-migratable" memory, which is most likely true because it's
managed by the host but accessible by the device. This should work
sufficiently well for what we expect the "host" allocation to do.

Depends on D143771

Reviewed By: kevinsala

Differential Revision: https://reviews.llvm.org/D143775

Author: jhuber6

openmp/libomptarget/plugins-nextgen/amdgpu/src/rtl.cpp

@@ -1485,6 +1485,12 @@ struct AMDHostDeviceTy : public AMDGenericDeviceTy {
     return *FineGrainedMemoryPools[0];
   }
 
+  AMDGPUMemoryPoolTy &getCoarseGrainedMemoryPool() {
+    assert(!CoarseGrainedMemoryPools.empty() && "No coarse-grained mempool");
+    // Retrive any memory pool.
+    return *CoarseGrainedMemoryPools[0];
+  }
+
   /// Get a memory pool for kernel args allocations.
   AMDGPUMemoryPoolTy &getArgsMemoryPool() {
     assert(!ArgsMemoryPools.empty() && "No kernelargs mempool");
@@ -1762,6 +1768,7 @@ struct AMDGPUDeviceTy : public GenericDeviceTy, AMDGenericDeviceTy {
       MemoryPool = CoarseGrainedMemoryPools[0];
       break;
     case TARGET_ALLOC_HOST:
+      MemoryPool = &HostDevice.getFineGrainedMemoryPool();
       break;
     case TARGET_ALLOC_SHARED:
       MemoryPool = &HostDevice.getFineGrainedMemoryPool();
@@ -2623,6 +2630,7 @@ void *AMDGPUDeviceTy::allocate(size_t Size, void *, TargetAllocTy Kind) {
     MemoryPool = CoarseGrainedMemoryPools[0];
     break;
   case TARGET_ALLOC_HOST:
+    MemoryPool = &HostDevice.getFineGrainedMemoryPool();
     break;
   case TARGET_ALLOC_SHARED:
     MemoryPool = &HostDevice.getFineGrainedMemoryPool();

openmp/libomptarget/test/api/omp_host_pinned_memory.c

@@ -1,5 +1,4 @@
 // RUN: %libomptarget-compile-run-and-check-generic
-// UNSUPPORTED: amdgcn-amd-amdhsa
 
 #include <omp.h>
 #include <stdio.h>

openmp/libomptarget/test/api/omp_host_pinned_memory_alloc.c

@@ -1,5 +1,4 @@
 // RUN: %libomptarget-compile-run-and-check-generic
-// UNSUPPORTED: amdgcn-amd-amdhsa
 
 #include <omp.h>
 #include <stdio.h>
@@ -20,7 +19,7 @@ int main() {
   for (int i = 0; i < N; ++i)
     sum += hst_ptr[i];
 
-  omp_free(hst_ptr, llvm_omp_target_shared_mem_alloc);
+  omp_free(hst_ptr, llvm_omp_target_host_mem_alloc);
   // CHECK: PASS
   if (sum == N)
     printf("PASS\n");