[OpenMP] Try to simplify all loads in device code

Eliminating loads/stores in the device code is worth the extra effort,
especially for the new device runtime.

At the same time we do not compute AAExecutionDomain for non-device code
anymore, there is no point.

Differential Revision: https://reviews.llvm.org/D106845

include/llvm/Transforms/IPO/Attributor.h

@@ -1544,6 +1544,13 @@ struct Attributor {
                                 UsedAssumedInformation);
   }
 
+  /// If \p V is assumed simplified, return it, if it is unclear yet,
+  /// return None, otherwise return `nullptr`. Same as the public version
+  /// except that it can be used without recording dependences on any \p AA.
+  Optional<Value *> getAssumedSimplified(const IRPosition &V,
+                                         const AbstractAttribute *AA,
+                                         bool &UsedAssumedInformation);
+
   /// Register \p CB as a simplification callback.
   /// `Attributor::getAssumedSimplified` will use these callbacks before
   /// we it will ask `AAValueSimplify`. It is important to ensure this
@@ -1561,13 +1568,6 @@ private:
   DenseMap<IRPosition, SmallVector<SimplifictionCallbackTy, 1>>
       SimplificationCallbacks;
 
-  /// If \p V is assumed simplified, return it, if it is unclear yet,
-  /// return None, otherwise return `nullptr`. Same as the public version
-  /// except that it can be used without recording dependences on any \p AA.
-  Optional<Value *> getAssumedSimplified(const IRPosition &V,
-                                         const AbstractAttribute *AA,
-                                         bool &UsedAssumedInformation);
-
 public:
   /// Translate \p V from the callee context into the call site context.
   Optional<Value *>

lib/Transforms/IPO/OpenMPOpt.cpp

@@ -3991,11 +3991,23 @@ void OpenMPOpt::registerAAs(bool IsModulePass) {
 
   // Create an ExecutionDomain AA for every function and a HeapToStack AA for
   // every function if there is a device kernel.
+  if (!isOpenMPDevice(M))
+    return;
+
   for (auto *F : SCC) {
-    if (!F->isDeclaration())
-      A.getOrCreateAAFor<AAExecutionDomain>(IRPosition::function(*F));
-    if (isOpenMPDevice(M))
-      A.getOrCreateAAFor<AAHeapToStack>(IRPosition::function(*F));
+    if (F->isDeclaration())
+      continue;
+
+    A.getOrCreateAAFor<AAExecutionDomain>(IRPosition::function(*F));
+    A.getOrCreateAAFor<AAHeapToStack>(IRPosition::function(*F));
+
+    for (auto &I : instructions(*F)) {
+      if (auto *LI = dyn_cast<LoadInst>(&I)) {
+        bool UsedAssumedInformation = false;
+        A.getAssumedSimplified(IRPosition::value(*LI), /* AA */ nullptr,
+                               UsedAssumedInformation);
+      }
+    }
   }
 }