[AArch64] Redundant store instructions should be removed as dead code

If there is a store followed by a store with the same value to the same location, then the store is dead/noop. It can be removed.

This problem is found in spec2006-197.parser.

For example,
  stur    w10, [x11, #-4]
  stur    w10, [x11, #-4]
Then one of the two stur instructions can be removed.

Patch by David Xu!

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218569 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index 34a0e04bc055c8bfe9c613160634f837ea44b52b..2b65cce970c2557cafd415780700b9b586fa36d6 100644 (file)
--- a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -9858,6 +9858,17 @@ SDValue DAGCombiner::visitSTORE(SDNode *N) {
     }
   }
 
+  // If this is a store followed by a store with the same value to the same
+  // location, then the store is dead/noop.
+  if (StoreSDNode *ST1 = dyn_cast<StoreSDNode>(Chain)) {
+    if (ST1->getBasePtr() == Ptr && ST->getMemoryVT() == ST1->getMemoryVT() &&
+        ST1->getValue() == Value && ST->isUnindexed() && !ST->isVolatile() &&
+        ST1->isUnindexed() && !ST1->isVolatile()) {
+      // The store is dead, remove it.
+      return Chain;
+    }
+  }
+
   // If this is an FP_ROUND or TRUNC followed by a store, fold this into a
   // truncating store.  We can do this even if this is already a truncstore.
   if ((Value.getOpcode() == ISD::FP_ROUND || Value.getOpcode() == ISD::TRUNCATE)

diff --git a/test/CodeGen/AArch64/Redundantstore.ll b/test/CodeGen/AArch64/Redundantstore.ll
new file mode 100644 (file)
index 0000000..72f7f46
--- /dev/null
+++ b/test/CodeGen/AArch64/Redundantstore.ll
@@ -0,0 +1,25 @@
+; RUN: llc -O3 -march=aarch64 < %s | FileCheck %s 
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+@end_of_array = common global i8* null, align 8
+
+; CHECK-LABEL: @test
+; CHECK: stur
+; CHECK-NOT: stur
+define i8* @test(i32 %size) {
+entry:
+  %0 = load i8** @end_of_array, align 8
+  %conv = sext i32 %size to i64
+  %and = and i64 %conv, -8
+  %conv2 = trunc i64 %and to i32
+  %add.ptr.sum = add nsw i64 %and, -4
+  %add.ptr3 = getelementptr inbounds i8* %0, i64 %add.ptr.sum
+  %size4 = bitcast i8* %add.ptr3 to i32*
+  store i32 %conv2, i32* %size4, align 4
+  %add.ptr.sum9 = add nsw i64 %and, -4
+  %add.ptr5 = getelementptr inbounds i8* %0, i64 %add.ptr.sum9
+  %size6 = bitcast i8* %add.ptr5 to i32*
+  store i32 %conv2, i32* %size6, align 4
+  ret i8* %0
+}
+