Avoid creating BUILD_VECTOR of all zero elements of "non-normalized" type (e.g. v8i16...

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@48136 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index 963a1feba8a20a2b892212520875cbc9dcbc2ca1..1b00855a671aad781dda47b5edbd43aae4130d00 100644 (file)
--- a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -1103,6 +1103,10 @@ SDOperand DAGCombiner::visitSUB(SDNode *N) {
   
   // fold (sub x, x) -> 0
   if (N0 == N1)
+    if (ISD::isBuildVectorAllZeros(N0.Val))
+      // Zero vectors might be normalized to a particular vector type to ensure
+      // they are CSE'd. Return it as it is.
+      return N0;
     return DAG.getConstant(0, N->getValueType(0));
   // fold (sub c1, c2) -> c1-c2
   if (N0C && N1C)

diff --git a/test/CodeGen/X86/vec_zero-2.ll b/test/CodeGen/X86/vec_zero-2.ll
new file mode 100644 (file)
index 0000000..efdf564
--- /dev/null
+++ b/test/CodeGen/X86/vec_zero-2.ll
@@ -0,0 +1,24 @@
+; RUN: llvm-as < %s | llc -march=x86 -mattr=+sse2
+
+define i32 @t() {
+entry:
+       br i1 true, label %bb4743, label %bb1656
+bb1656:                ; preds = %entry
+       ret i32 0
+bb1664:                ; preds = %entry
+       br i1 false, label %bb5310, label %bb4743
+bb4743:                ; preds = %bb1664
+       %tmp5256 = bitcast <2 x i64> zeroinitializer to <8 x i16>               ; <<8 x i16>> [#uses=1]
+       %tmp5257 = sub <8 x i16> %tmp5256, zeroinitializer              ; <<8 x i16>> [#uses=1]
+       %tmp5258 = bitcast <8 x i16> %tmp5257 to <2 x i64>              ; <<2 x i64>> [#uses=1]
+       %tmp5265 = bitcast <2 x i64> %tmp5258 to <8 x i16>              ; <<8 x i16>> [#uses=1]
+       %tmp5266 = call <8 x i16> @llvm.x86.sse2.packuswb.128( <8 x i16> %tmp5265, <8 x i16> zeroinitializer ) nounwind readnone                ; <<8 x i16>> [#uses=1]
+       %tmp5267 = bitcast <8 x i16> %tmp5266 to <2 x i64>              ; <<2 x i64>> [#uses=1]
+       %tmp5294 = and <2 x i64> zeroinitializer, %tmp5267              ; <<2 x i64>> [#uses=1]
+       br label %bb5310
+bb5310:                ; preds = %bb4743, %bb1664
+       %tmp5294.pn = phi <2 x i64> [ %tmp5294, %bb4743 ], [ zeroinitializer, %bb1664 ]         ; <<2 x i64>> [#uses=0]
+       ret i32 0
+}
+
+declare <8 x i16> @llvm.x86.sse2.packuswb.128(<8 x i16>, <8 x i16>) nounwind readnone