[DAG] Elide overlapping store

Summary:
Extend overlapping store elision to handle overwrites of stores by
larger stores.

Nontemporal tests have been modified to add memory dependencies to
prevent store elision.

Reviewers: craig.topper, rnk, t.p.northover

Subscribers: javed.absar, hiraditya, llvm-commits

Differential Revision: https://reviews.llvm.org/D40969

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@321089 91177308-0d34-0410-b5e6-96231b3b80d8

lib/CodeGen/SelectionDAG/DAGCombiner.cpp

@@ -13784,30 +13784,30 @@ SDValue DAGCombiner::visitSTORE(SDNode *N) {
     }
   }
 
-  if (StoreSDNode *ST1 = dyn_cast<StoreSDNode>(Chain)) {
-    if (ST->isUnindexed() && !ST->isVolatile() && ST1->isUnindexed() &&
-        !ST1->isVolatile() && ST1->getBasePtr() == Ptr &&
-        ST->getMemoryVT() == ST1->getMemoryVT()) {
-      // If this is a store followed by a store with the same value to the same
-      // location, then the store is dead/noop.
-      if (ST1->getValue() == Value) {
-        // The store is dead, remove it.
-        return Chain;
-      }
-
-      // If this is a store who's preceeding store to the same location
-      // and no one other node is chained to that store we can effectively
-      // drop the store. Do not remove stores to undef as they may be used as
-      // data sinks.
-      if (OptLevel != CodeGenOpt::None && ST1->hasOneUse() &&
-          !ST1->getBasePtr().isUndef()) {
-        // ST1 is fully overwritten and can be elided. Combine with it's chain
-        // value.
+  // Deal with elidable overlapping chained stores.
+  if (StoreSDNode *ST1 = dyn_cast<StoreSDNode>(Chain))
+    if (OptLevel != CodeGenOpt::None && ST1->isUnindexed() &&
+        !ST1->isVolatile() && ST1->hasOneUse() &&
+        !ST1->getBasePtr().isUndef() && !ST->isVolatile()) {
+      BaseIndexOffset STBasePtr = BaseIndexOffset::match(ST->getBasePtr(), DAG);
+      BaseIndexOffset ST1BasePtr =
+          BaseIndexOffset::match(ST1->getBasePtr(), DAG);
+      unsigned STBytes = ST->getMemoryVT().getStoreSize();
+      unsigned ST1Bytes = ST1->getMemoryVT().getStoreSize();
+      int64_t PtrDiff;
+      // If this is a store who's preceeding store to a subset of the same
+      // memory and no one other node is chained to that store we can
+      // effectively drop the store. Do not remove stores to undef as they may
+      // be used as data sinks.
+
+      if (((ST->getBasePtr() == ST1->getBasePtr()) &&
+           (ST->getValue() == ST1->getValue())) ||
+          (STBasePtr.equalBaseIndex(ST1BasePtr, DAG, PtrDiff) &&
+           (0 <= PtrDiff) && (PtrDiff + ST1Bytes <= STBytes))) {
         CombineTo(ST1, ST1->getChain());
-        return SDValue();
+        return SDValue(N, 0);
       }
     }
-  }
 
   // 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.

test/CodeGen/AArch64/ldst-paired-aliasing.ll

@@ -10,11 +10,10 @@ declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) #3
 define i32 @main() local_unnamed_addr #1 {
 ; Make sure the stores happen in the correct order (the exact instructions could change).
 ; CHECK-LABEL: main:
-; CHECK: stp xzr, xzr, [sp, #72]
+; CHECK: str xzr, [sp, #80]
 ; CHECK: str w9, [sp, #80]
-; CHECK: str q0, [sp, #48]
+; CHECK: stp q0, q0, [sp, #48]
 ; CHECK: ldr w8, [sp, #48]
-; CHECK: str q0, [sp, #64]
 
 for.body.lr.ph.i.i.i.i.i.i63:
   %b1 = alloca [10 x i32], align 16