[DAG] Improve store merge candidate pruning.

Remove non-consecutive stores from store merge candidate search as
they cannot be merged and will prevent us from finding subsequent
mergeable store cases.

Reviewers: jyknight, bogner, javed.absar, spatel

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D32086

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@300561 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index 4d468551ae24e80925e7944a0ef7cabf1245566e..c947a36e89f9e50414d893c0f9e7b97b18e81b0b 100644 (file)
--- a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -12375,6 +12375,27 @@ bool DAGCombiner::MergeConsecutiveStores(StoreSDNode *St) {
               return LHS.OffsetFromBase < RHS.OffsetFromBase;
             });
 
+  // Store Merge attempts to merge the lowest stores. This generally
+  // works out as if successful, as the remaining stores are checked
+  // after the first collection of stores is merged. However, in the
+  // case that a non-mergeable store is found first, e.g., {p[-2],
+  // p[0], p[1], p[2], p[3]}, we would fail and miss the subsequent
+  // mergeable cases. To prevent this, we prune such stores from the
+  // front of StoreNodes here.
+
+  unsigned StartIdx = 0;
+  while ((StartIdx + 1 < StoreNodes.size()) &&
+         StoreNodes[StartIdx].OffsetFromBase + ElementSizeBytes !=
+             StoreNodes[StartIdx + 1].OffsetFromBase)
+    ++StartIdx;
+
+  // Bail if we don't have enough candidates to merge.
+  if (StartIdx + 1 >= StoreNodes.size())
+    return false;
+
+  if (StartIdx)
+    StoreNodes.erase(StoreNodes.begin(), StoreNodes.begin() + StartIdx);
+
   // Scan the memory operations on the chain and find the first non-consecutive
   // store memory address.
   unsigned NumConsecutiveStores = 0;

diff --git a/test/CodeGen/AArch64/arm64-abi.ll b/test/CodeGen/AArch64/arm64-abi.ll
index 6cf0ab35b9b527c12b29d7b0365810a366ed7718..5be84b7d493b7998923023b33a4b5e065e8e0988 100644 (file)
--- a/test/CodeGen/AArch64/arm64-abi.ll
+++ b/test/CodeGen/AArch64/arm64-abi.ll
@@ -43,9 +43,7 @@ entry:
 ; CHECK-LABEL: i8i16caller
 ; The 8th, 9th, 10th and 11th arguments are passed at sp, sp+2, sp+4, sp+5.
 ; They are i8, i16, i8 and i8.
-; CHECK-DAG: strb {{w[0-9]+}}, [sp, #5]
-; CHECK-DAG: strb {{w[0-9]+}}, [sp, #4]
-; CHECK-DAG: strh {{w[0-9]+}}, [sp, #2]
+; CHECK-DAG: stur {{w[0-9]+}}, [sp, #2]
 ; CHECK-DAG: strb {{w[0-9]+}}, [sp]
 ; CHECK: bl
 ; FAST-LABEL: i8i16caller

diff --git a/test/CodeGen/X86/MergeConsecutiveStores.ll b/test/CodeGen/X86/MergeConsecutiveStores.ll
index 906ca2fef689fbf1aa484be824bedf4833a66e10..f89f6e1de1abe27b8bf6b686d6ba2e216e8cfa05 100644 (file)
--- a/test/CodeGen/X86/MergeConsecutiveStores.ll
+++ b/test/CodeGen/X86/MergeConsecutiveStores.ll
@@ -596,14 +596,8 @@ define void @almost_consecutive_stores(i8* %p) {
   store i8 3, i8* %p3
   ret void
 ; CHECK-LABEL: almost_consecutive_stores
-; CHECK-DAG: movb      $0, (%rdi)
-; CHECK-DAG: movb      $1, 42(%rdi)
-; CHECK-DAG: movb      $2, 2(%rdi)
-; CHECK-DAG: movb      $3, 3(%rdi)
+; CHECK-DAG: movb $0, (%rdi)
+; CHECK-DAG: movb $1, 42(%rdi)
+; CHECK-DAG: movw $770, 2(%rdi)
 ; CHECK: retq
-
-; We should able to merge the final two stores into a 16-bit store
-; FIXMECHECK-DAG: movw $770, 2(%rdi)
-
-
 }