[ISel] Match all bits when merge undef(s) for DAG combine

2 files changed, 21 insertions, 6 deletions

diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
index bc1011b..b3b8756 100644
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
@@ -2712,7 +2712,16 @@ bool SelectionDAG::isSplatValue(SDValue V, const APInt &DemandedElts,
         SubDemandedElts &= ScaledDemandedElts;
         if (!isSplatValue(Src, SubDemandedElts, SubUndefElts, Depth + 1))
           return false;
-        UndefElts |= APIntOps::ScaleBitMask(SubUndefElts, NumElts);
+
+        // Here we can't do "MatchAnyBits" operation merge for undef bits.
+        // Because some operation only use part value of the source.
+        // Take llvm.fshl.* for example:
+        // t1: v4i32 = Constant:i32<12>, undef:i32, Constant:i32<12>, undef:i32
+        // t2: v2i64 = bitcast t1
+        // t5: v2i64 = fshl t3, t4, t2
+        // We can not convert t2 to {i64 undef, i64 undef}
+        UndefElts |= APIntOps::ScaleBitMask(SubUndefElts, NumElts,
+                                            /*MatchAllBits=*/true);
       }
       return true;
     }
diff --git a/llvm/lib/Support/APInt.cpp b/llvm/lib/Support/APInt.cpp
index acc68fe..f74178b 100644
--- a/llvm/lib/Support/APInt.cpp
+++ b/llvm/lib/Support/APInt.cpp
@@ -2968,7 +2968,8 @@ llvm::APIntOps::GetMostSignificantDifferentBit(const APInt &A, const APInt &B) {
   return A.getBitWidth() - ((A ^ B).countLeadingZeros() + 1);
 }
 
-APInt llvm::APIntOps::ScaleBitMask(const APInt &A, unsigned NewBitWidth) {
+APInt llvm::APIntOps::ScaleBitMask(const APInt &A, unsigned NewBitWidth,
+                                   bool MatchAllBits) {
   unsigned OldBitWidth = A.getBitWidth();
   assert((((OldBitWidth % NewBitWidth) == 0) ||
           ((NewBitWidth % OldBitWidth) == 0)) &&
@@ -2992,11 +2993,16 @@ APInt llvm::APIntOps::ScaleBitMask(const APInt &A, unsigned NewBitWidth) {
       if (A[i])
         NewA.setBits(i * Scale, (i + 1) * Scale);
   } else {
-    // Merge bits - if any old bit is set, then set scale equivalent new bit.
     unsigned Scale = OldBitWidth / NewBitWidth;
-    for (unsigned i = 0; i != NewBitWidth; ++i)
-      if (!A.extractBits(Scale, i * Scale).isZero())
-        NewA.setBit(i);
+    for (unsigned i = 0; i != NewBitWidth; ++i) {
+      if (MatchAllBits) {
+        if (A.extractBits(Scale, i * Scale).isAllOnes())
+          NewA.setBit(i);
+      } else {
+        if (!A.extractBits(Scale, i * Scale).isZero())
+          NewA.setBit(i);
+      }
+    }
   }
 
   return NewA;