[DSE] Remove dead stores in end blocks containing fence

We can remove dead stores in the presence of fence instructions. Fence
does not change an otherwise thread local store to visible.

reviewers: reames, dexonsmith, jfb
Differential Revision: http://reviews.llvm.org/D22001

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@274795 91177308-0d34-0410-b5e6-96231b3b80d8

Author: annamthomas

lib/Transforms/Scalar/DeadStoreElimination.cpp

@@ -778,6 +778,14 @@ static bool handleEndBlock(BasicBlock &BB, AliasAnalysis *AA,
       continue;
     }
 
+    // We can remove the dead stores, irrespective of the fence and its ordering
+    // (release/acquire/seq_cst). Fences only constraints the ordering of
+    // already visible stores, it does not make a store visible to other
+    // threads. So, skipping over a fence does not change a store from being
+    // dead.
+    if (isa<FenceInst>(*BBI))
+      continue;
+
     MemoryLocation LoadedLoc;
 
     // If we encounter a use of the pointer, it is no longer considered dead

test/Transforms/DeadStoreElimination/fence.ll

@@ -46,3 +46,51 @@ define void @test2(i32* %addr.i) {
   store i32 5, i32* %addr.i, align 4
   ret void
 }
+
+; We DSE stack alloc'ed and byval locations, in the presence of fences.
+; Fence does not make an otherwise thread local store visible.
+; Right now the DSE in presence of fence is only done in end blocks (with no successors),
+; but the same logic applies to other basic blocks as well.
+; The store to %addr.i can be removed since it is a byval attribute
+define void @test3(i32* byval %addr.i) {
+; CHECK-LABEL: @test3
+; CHECK-NOT: store
+; CHECK: fence
+; CHECK: ret
+  store i32 5, i32* %addr.i, align 4
+  fence release
+  ret void
+}
+
+declare void @foo(i8* nocapture %p)
+
+declare noalias i8* @malloc(i32)
+
+; DSE of stores in locations allocated through library calls.
+define void @test_nocapture() {
+; CHECK-LABEL: @test_nocapture
+; CHECK: malloc
+; CHECK: foo
+; CHECK-NOT: store
+; CHECK: fence
+  %m  =  call i8* @malloc(i32 24)
+  call void @foo(i8* %m)
+  store i8 4, i8* %m
+  fence release
+  ret void
+}
+
+
+; This is a full fence, but it does not make a thread local store visible.
+; We can DSE the store in presence of the fence.
+define void @fence_seq_cst() {
+; CHECK-LABEL: @fence_seq_cst
+; CHECK-NEXT: fence seq_cst
+; CHECK-NEXT: ret void
+  %P1 = alloca i32
+  store i32 0, i32* %P1, align 4
+  fence seq_cst
+  store i32 4, i32* %P1, align 4
+  ret void
+}
+