Teach DAG combine to fold (trunc (fptoXi x)) to (fptoXi x)

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166049 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index 8846247090c5c8c2fe117ffef775e0a6bc6199ef..6e4a772a89d19f0fade508e58708261e1f76344f 100644 (file)
--- a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -5308,6 +5308,52 @@ SDValue DAGCombiner::visitTRUNCATE(SDNode *N) {
     if (Reduced.getNode())
       return Reduced;
   }
+  // fold (trunc (fptoXi x)) -> (smaller fptoXi x)
+  if ((N0.getOpcode() == ISD::FP_TO_UINT ||
+       N0.getOpcode() == ISD::FP_TO_SINT) && !LegalTypes)
+    return DAG.getNode(N0.getOpcode(), N->getDebugLoc(), VT, N0.getOperand(0));
+  // fold (trunc (concat ... x ...)) -> (concat ..., (trunc x), ...)),
+  // where ... are all 'undef'.
+  if (N0.getOpcode() == ISD::CONCAT_VECTORS && !LegalTypes) {
+    SmallVector<EVT, 8> VTs;
+    SDValue V;
+    unsigned Idx = 0;
+    unsigned NumDefs = 0;
+
+    for (unsigned i = 0, e = N0.getNumOperands(); i != e; ++i) {
+      SDValue X = N0.getOperand(i);
+      if (X.getOpcode() != ISD::UNDEF) {
+        V = X;
+        Idx = i;
+        NumDefs++;
+      }
+      // Stop if more than one members are non-undef.
+      if (NumDefs > 1)
+        break;
+      VTs.push_back(EVT::getVectorVT(*DAG.getContext(),
+                                     VT.getVectorElementType(),
+                                     X.getValueType().getVectorNumElements()));
+    }
+
+    if (NumDefs == 0)
+      return DAG.getUNDEF(VT);
+
+    if (NumDefs == 1) {
+      assert(V.getNode() && "The single defined operand is empty!");
+      SmallVector<SDValue, 8> Opnds;
+      for (unsigned i = 0, e = VTs.size(); i != e; ++i) {
+        if (i != Idx) {
+          Opnds.push_back(DAG.getUNDEF(VTs[i]));
+          continue;
+        }
+        SDValue NV = DAG.getNode(ISD::TRUNCATE, V.getDebugLoc(), VTs[i], V);
+        AddToWorkList(NV.getNode());
+        Opnds.push_back(NV);
+      }
+      return DAG.getNode(ISD::CONCAT_VECTORS, N->getDebugLoc(), VT,
+                         &Opnds[0], Opnds.size());
+    }
+  }
 
   // Simplify the operands using demanded-bits information.
   if (!VT.isVector() &&

diff --git a/test/CodeGen/X86/trunc-fp2int.ll b/test/CodeGen/X86/trunc-fp2int.ll
new file mode 100644 (file)
index 0000000..792af16
--- /dev/null
+++ b/test/CodeGen/X86/trunc-fp2int.ll
@@ -0,0 +1,18 @@
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=corei7 | FileCheck %s
+
+define <4 x i8> @bar(<4 x float> %in) nounwind readnone alwaysinline {
+  %1 = fptoui <4 x float> %in to <4 x i8>
+  ret <4 x i8> %1
+; CHECK: bar
+; CHECK: cvttps2dq
+}
+define <4 x i8> @foo(<4 x float> %in) nounwind readnone alwaysinline {
+  %1 = fptoui <4 x float> %in to <4 x i32>
+  %2 = trunc <4 x i32> %1 to <4 x i16>
+  %3 = shufflevector <4 x i16> %2, <4 x i16> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  %4 = trunc <8 x i16> %3 to <8 x i8>
+  %5 = shufflevector <8 x i8> %4, <8 x i8> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+  ret <4 x i8> %5
+; CHECK: foo
+; CHECK: cvttps2dq
+}