TRUNCATE constant folding - minor fix for rL233224

Fix for test case found by James Molloy - TRUNCATE of constant build vectors can be more simply achieved by simply replacing with a new build vector node with the truncated value type - no need to touch the scalar operands at all.

llvm-svn: 235079

2 files changed, 25 insertions, 1 deletions

diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
index 0a97ef81b3c..770f0b226ee 100644
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
@@ -2851,13 +2851,16 @@ SDValue SelectionDAG::getNode(unsigned Opcode, SDLoc DL,
         // FIXME: Entirely reasonable to perform folding of other unary
         // operations here as the need arises.
         break;
+      case ISD::TRUNCATE:
+        // Constant build vector truncation can be done with the original scalar
+        // operands but with a new build vector with the truncated value type.
+        return getNode(ISD::BUILD_VECTOR, DL, VT, BV->ops());
       case ISD::FNEG:
       case ISD::FABS:
       case ISD::FCEIL:
       case ISD::FTRUNC:
       case ISD::FFLOOR:
       case ISD::FP_EXTEND:
-      case ISD::TRUNCATE:
       case ISD::UINT_TO_FP:
       case ISD::SINT_TO_FP: {
         // Let the above scalar folding handle the folding of each element.
diff --git a/llvm/test/CodeGen/AArch64/fold-constants.ll b/llvm/test/CodeGen/AArch64/fold-constants.ll
new file mode 100644
index 00000000000..2dd0d124593
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/fold-constants.ll
@@ -0,0 +1,21 @@
+; RUN: llc -mtriple=aarch64-linux-gnu -o - %s | FileCheck %s
+
+define i64 @dotests_616() {
+; CHECK-LABEL: dotests_616
+; CHECK:       movi d0, #0000000000000000
+; CHECK-NEXT:  umov w8, v0.b[2]
+; CHECK-NEXT:  sbfx w8, w8, #0, #1
+; CHECK-NEXT:  fmov s0, w8
+; CHECK-NEXT:  fmov x0, d0
+; CHECK-NEXT:  ret
+entry:
+  %0 = bitcast <2 x i64> zeroinitializer to <8 x i16>
+  %1 = and <8 x i16> zeroinitializer, %0
+  %2 = icmp ne <8 x i16> %1, zeroinitializer
+  %3 = extractelement <8 x i1> %2, i32 2
+  %vgetq_lane285 = sext i1 %3 to i16
+  %vset_lane = insertelement <4 x i16> undef, i16 %vgetq_lane285, i32 0
+  %4 = bitcast <4 x i16> %vset_lane to <1 x i64>
+  %vget_lane = extractelement <1 x i64> %4, i32 0
+  ret i64 %vget_lane
+}