Do some peephole optimizations to remove pointless VMOVs from Neon to integer

registers that arise from argument shuffling with the soft float ABI. These
instructions are particularly slow on Cortex A8. This fixes one half of
<rdar://problem/8674845>.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@128759 91177308-0d34-0410-b5e6-96231b3b80d8

2 files changed, 42 insertions, 0 deletions

diff --git a/lib/Target/ARM/ARMISelLowering.cpp b/lib/Target/ARM/ARMISelLowering.cpp
index 5502ca4..d11c956 100644
--- a/lib/Target/ARM/ARMISelLowering.cpp
+++ b/lib/Target/ARM/ARMISelLowering.cpp
@@ -5561,6 +5561,37 @@ static SDValue PerformVMOVRRDCombine(SDNode *N,
   SDValue InDouble = N->getOperand(0);
   if (InDouble.getOpcode() == ARMISD::VMOVDRR)
     return DCI.CombineTo(N, InDouble.getOperand(0), InDouble.getOperand(1));
+
+  // vmovrrd(load f64) -> (load i32), (load i32)
+  SDNode *InNode = InDouble.getNode();
+  if (ISD::isNormalLoad(InNode) && InNode->hasOneUse() &&
+      InNode->getValueType(0) == MVT::f64 &&
+      InNode->getOperand(1).getOpcode() == ISD::FrameIndex &&
+      !cast<LoadSDNode>(InNode)->isVolatile()) {
+    // TODO: Should this be done for non-FrameIndex operands?
+    LoadSDNode *LD = cast<LoadSDNode>(InNode);
+
+    SelectionDAG &DAG = DCI.DAG;
+    DebugLoc DL = LD->getDebugLoc();
+    SDValue BasePtr = LD->getBasePtr();
+    SDValue NewLD1 = DAG.getLoad(MVT::i32, DL, LD->getChain(), BasePtr,
+                                 LD->getPointerInfo(), LD->isVolatile(),
+                                 LD->isNonTemporal(), LD->getAlignment());
+
+    SDValue OffsetPtr = DAG.getNode(ISD::ADD, DL, MVT::i32, BasePtr,
+                                    DAG.getConstant(4, MVT::i32));
+    SDValue NewLD2 = DAG.getLoad(MVT::i32, DL, NewLD1.getValue(1), OffsetPtr,
+                                 LD->getPointerInfo(), LD->isVolatile(),
+                                 LD->isNonTemporal(),
+                                 std::min(4U, LD->getAlignment() / 2));
+
+    DAG.ReplaceAllUsesOfValueWith(SDValue(LD, 1), NewLD2.getValue(1));
+    SDValue Result = DCI.CombineTo(N, NewLD1, NewLD2);
+    DCI.RemoveFromWorklist(LD);
+    DAG.DeleteNode(LD);
+    return Result;
+  }
+
   return SDValue();
 }
 
diff --git a/test/CodeGen/ARM/fp-arg-shuffle.ll b/test/CodeGen/ARM/fp-arg-shuffle.ll
new file mode 100644
index 0000000..59303ac
--- /dev/null
+++ b/test/CodeGen/ARM/fp-arg-shuffle.ll
@@ -0,0 +1,11 @@
+; RUN: llc < %s -march=arm -mattr=+neon -float-abi=soft | FileCheck %s
+
+; CHECK: function1
+; CHECK-NOT: vmov r
+define double @function1(double %a, double %b, double %c, double %d, double %e, double %f) nounwind noinline ssp {
+entry:
+  %call = tail call double @function2(double %f, double %e, double %d, double %c, double %b, double %a) nounwind
+  ret double %call
+}
+
+declare double @function2(double, double, double, double, double, double)