[OpenMP][libomptarget] Enable usage of unified memory for declare target link variables

Summary: This patch enables the usage of a host variable on the device for declare target link variables when unified memory is available.

Reviewers: ABataev, caomhin, grokos

Reviewed By: grokos

Subscribers: Hahnfeld, guansong, jdoerfert, openmp-commits

Tags: #openmp

Differential Revision: https://reviews.llvm.org/D60884

llvm-svn: 362505

1 files changed, 23 insertions, 0 deletions

diff --git a/openmp/libomptarget/plugins/cuda/src/rtl.cpp b/openmp/libomptarget/plugins/cuda/src/rtl.cpp
index fc0c1ecd187..844afa107bb 100644
--- a/openmp/libomptarget/plugins/cuda/src/rtl.cpp
+++ b/openmp/libomptarget/plugins/cuda/src/rtl.cpp
@@ -111,6 +111,9 @@ public:
   int EnvNumTeams;
   int EnvTeamLimit;
 
+  // OpenMP Requires Flags
+  int64_t RequiresFlags;
+
   //static int EnvNumThreads;
   static const int HardTeamLimit = 1<<16; // 64k
   static const int HardThreadLimit = 1024;
@@ -227,6 +230,9 @@ public:
     } else {
       EnvNumTeams = -1;
     }
+
+    // Default state.
+    RequiresFlags = OMP_REQ_UNDEFINED;
   }
 
   ~RTLDeviceInfoTy() {
@@ -264,6 +270,12 @@ int32_t __tgt_rtl_is_valid_binary(__tgt_device_image *image) {
 
 int32_t __tgt_rtl_number_of_devices() { return DeviceInfo.NumberOfDevices; }
 
+int64_t __tgt_rtl_init_requires(int64_t RequiresFlags) {
+  DP("Init requires flags to %ld\n", RequiresFlags);
+  DeviceInfo.RequiresFlags = RequiresFlags;
+  return RequiresFlags;
+}
+
 int32_t __tgt_rtl_init_device(int32_t device_id) {
 
   CUdevice cuDevice;
@@ -436,6 +448,17 @@ __tgt_target_table *__tgt_rtl_load_binary(int32_t device_id,
           DPxPTR(e - HostBegin), e->name, DPxPTR(cuptr));
       entry.addr = (void *)cuptr;
 
+      if (DeviceInfo.RequiresFlags & OMP_REQ_UNIFIED_SHARED_MEMORY &&
+          e->flags & OMP_DECLARE_TARGET_LINK) {
+        // If unified memory is present any target link variables
+        // can access host addresses directly. There is no longer a
+        // need for device copies.
+        cuMemcpyHtoD(cuptr, e->addr, sizeof(void *));
+        DP("Copy linked variable host address (" DPxMOD ")"
+           "to device address (" DPxMOD ")\n",
+          DPxPTR(*((void**)e->addr)), DPxPTR(cuptr));
+      }
+
       DeviceInfo.addOffloadEntry(device_id, entry);
 
       continue;