Re-apply "[GVNHoist] Move GVNHoist to function simplification part of pipeline."

This re-applies r289696, which caused TSan perf regression, which has
since been addressed in separate changes (see PR for details).

See PR31382.

llvm-svn: 296759

llvm/lib/Transforms/IPO/PassManagerBuilder.cpp

@@ -244,8 +244,6 @@ void PassManagerBuilder::populateFunctionPassManager(
   FPM.add(createCFGSimplificationPass());
   FPM.add(createSROAPass());
   FPM.add(createEarlyCSEPass());
-  if(EnableGVNHoist)
-    FPM.add(createGVNHoistPass());
   FPM.add(createLowerExpectIntrinsicPass());
 }
 
@@ -290,6 +288,8 @@ void PassManagerBuilder::addFunctionSimplificationPasses(
   // Break up aggregate allocas, using SSAUpdater.
   MPM.add(createSROAPass());
   MPM.add(createEarlyCSEPass());              // Catch trivial redundancies
+  if(EnableGVNHoist)
+    MPM.add(createGVNHoistPass());
   // Speculative execution if the target has divergent branches; otherwise nop.
   MPM.add(createSpeculativeExecutionIfHasBranchDivergencePass());
   MPM.add(createJumpThreadingPass());         // Thread jumps.

llvm/test/Transforms/GVNHoist/hoist-inline.ll

@@ -0,0 +1,38 @@
+; RUN: opt -S -O2 < %s | FileCheck %s
+
+; Check that the inlined loads are hoisted.
+; CHECK-LABEL: define i32 @fun(
+; CHECK-LABEL: entry:
+; CHECK: load i32, i32* @A
+; CHECK: if.then:
+
+@A = external global i32
+@B = external global i32
+@C = external global i32
+
+define i32 @loadA() {
+   %a = load i32, i32* @A
+   ret i32 %a
+}
+
+define i32 @fun(i1 %c) {
+entry:
+  br i1 %c, label %if.then, label %if.else
+
+if.then:
+  store i32 1, i32* @B
+  %call1 = call i32 @loadA()
+  store i32 2, i32* @C
+  br label %if.endif
+
+if.else:
+  store i32 2, i32* @C
+  %call2 = call i32 @loadA()
+  store i32 1, i32* @B
+  br label %if.endif
+
+if.endif:
+  %ret = phi i32 [ %call1, %if.then ], [ %call2, %if.else ]
+  ret i32 %ret
+}
+