[Openmp-commits] [PATCH] D132660: [openmp][amdgpu] Implement target_alloc_host as fine grain HSA memory

[Jon Chesterfield via Phabricator via Openmp-commits]

JonChesterfield updated this revision to Diff 455593.
JonChesterfield added a comment.

- managed_memory test cases crash so exclude those from this patch


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D132660/new/

https://reviews.llvm.org/D132660

Files:
  openmp/libomptarget/plugins/amdgpu/src/rtl.cpp
  openmp/libomptarget/test/api/omp_host_pinned_memory.c
  openmp/libomptarget/test/api/omp_host_pinned_memory_alloc.c


Index: openmp/libomptarget/test/api/omp_host_pinned_memory_alloc.c
===================================================================
--- openmp/libomptarget/test/api/omp_host_pinned_memory_alloc.c
+++ openmp/libomptarget/test/api/omp_host_pinned_memory_alloc.c
@@ -1,5 +1,4 @@
-// RUN: %libomptarget-compile-run-and-check-nvptx64-nvidia-cuda
-// REQUIRES: nvptx64-nvidia-cuda
+// RUN: %libomptarget-compile-run-and-check-generic
 
 #include <omp.h>
 #include <stdio.h>
Index: openmp/libomptarget/test/api/omp_host_pinned_memory.c
===================================================================
--- openmp/libomptarget/test/api/omp_host_pinned_memory.c
+++ openmp/libomptarget/test/api/omp_host_pinned_memory.c
@@ -1,5 +1,4 @@
-// RUN: %libomptarget-compile-run-and-check-nvptx64-nvidia-cuda
-// REQUIRES: nvptx64-nvidia-cuda
+// RUN: %libomptarget-compile-run-and-check-generic
 
 #include <omp.h>
 #include <stdio.h>
Index: openmp/libomptarget/plugins/amdgpu/src/rtl.cpp
===================================================================
--- openmp/libomptarget/plugins/amdgpu/src/rtl.cpp
+++ openmp/libomptarget/plugins/amdgpu/src/rtl.cpp
@@ -2620,13 +2620,22 @@
   void *Ptr = NULL;
   assert(DeviceId < DeviceInfo().NumberOfDevices && "Device ID too large");
 
-  if (Kind != TARGET_ALLOC_DEFAULT) {
+  hsa_amd_memory_pool_t MemoryPool;
+  switch (Kind) {
+  case TARGET_ALLOC_DEFAULT:
+    // GPU memory
+    MemoryPool = DeviceInfo().getDeviceMemoryPool(DeviceId);
+    break;
+  case TARGET_ALLOC_HOST:
+    // non-migratable memory accessible by host and device(s)
+    MemoryPool = DeviceInfo().getHostMemoryPool();
+    break;
+  default:
     REPORT("Invalid target data allocation kind or requested allocator not "
            "implemented yet\n");
     return NULL;
   }
 
-  hsa_amd_memory_pool_t MemoryPool = DeviceInfo().getDeviceMemoryPool(DeviceId);
   hsa_status_t Err = hsa_amd_memory_pool_allocate(MemoryPool, Size, 0, &Ptr);
   DP("Tgt alloc data %ld bytes, (tgt:%016llx).\n", Size,
      (long long unsigned)(Elf64_Addr)Ptr);
@@ -2677,6 +2686,7 @@
 
 int32_t __tgt_rtl_data_delete(int DeviceId, void *TgtPtr) {
   assert(DeviceId < DeviceInfo().NumberOfDevices && "Device ID too large");
+  // HSA can free pointers allocated from different types of memory pool.
   hsa_status_t Err;
   DP("Tgt free data (tgt:%016llx).\n", (long long unsigned)(Elf64_Addr)TgtPtr);
   Err = core::Runtime::Memfree(TgtPtr);


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D132660.455593.patch
Type: text/x-patch
Size: 2436 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/openmp-commits/attachments/20220825/31f69ef6/attachment-0001.bin>