[AArch64]Fix PR21675, a bug about lowering llvm.ctpop.i32. We should noot use "DAG...

Patch by Wei-cheng Wang.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@227550 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/AArch64/AArch64ISelLowering.cpp b/lib/Target/AArch64/AArch64ISelLowering.cpp
index 64f6e5657683599ef5bf82b2bea4d154c67de269..37fe7714dd339862bda1021a3a47c1f02e992a0f 100644 (file)
--- a/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -3451,18 +3451,12 @@ SDValue AArch64TargetLowering::LowerCTPOP(SDValue Op, SelectionDAG &DAG) const {
   SDValue Val = Op.getOperand(0);
   SDLoc DL(Op);
   EVT VT = Op.getValueType();
-  SDValue ZeroVec = DAG.getUNDEF(MVT::v8i8);
 
-  SDValue VecVal;
-  if (VT == MVT::i32) {
-    VecVal = DAG.getNode(ISD::BITCAST, DL, MVT::f32, Val);
-    VecVal = DAG.getTargetInsertSubreg(AArch64::ssub, DL, MVT::v8i8, ZeroVec,
-                                       VecVal);
-  } else {
-    VecVal = DAG.getNode(ISD::BITCAST, DL, MVT::v8i8, Val);
-  }
+  if (VT == MVT::i32)
+    Val = DAG.getNode(ISD::ZERO_EXTEND, DL, MVT::i64, Val);
+  Val = DAG.getNode(ISD::BITCAST, DL, MVT::v8i8, Val);
 
-  SDValue CtPop = DAG.getNode(ISD::CTPOP, DL, MVT::v8i8, VecVal);
+  SDValue CtPop = DAG.getNode(ISD::CTPOP, DL, MVT::v8i8, Val);
   SDValue UaddLV = DAG.getNode(
       ISD::INTRINSIC_WO_CHAIN, DL, MVT::i32,
       DAG.getConstant(Intrinsic::aarch64_neon_uaddlv, MVT::i32), CtPop);

diff --git a/test/CodeGen/AArch64/arm64-popcnt.ll b/test/CodeGen/AArch64/arm64-popcnt.ll
index 117ab3a5e05a2b9ac894952ebda2febe2814a24f..b0b529a13f413905c6e1bd760649b28edb987343 100644 (file)
--- a/test/CodeGen/AArch64/arm64-popcnt.ll
+++ b/test/CodeGen/AArch64/arm64-popcnt.ll
@@ -4,7 +4,8 @@
 define i32 @cnt32_advsimd(i32 %x) nounwind readnone {
   %cnt = tail call i32 @llvm.ctpop.i32(i32 %x)
   ret i32 %cnt
-; CHECK: fmov  s0, w0
+; CHECK: ubfx  x{{[0-9]+}}
+; CHECK: fmov  d0, x{{[0-9]+}}
 ; CHECK: cnt.8b        v0, v0
 ; CHECK: uaddlv.8b     h0, v0
 ; CHECK: fmov w0, s0
@@ -15,7 +16,24 @@ define i32 @cnt32_advsimd(i32 %x) nounwind readnone {
 ; CHECK-NONEON: and w{{[0-9]+}}, w{{[0-9]+}}, #0x33333333
 ; CHECK-NONEON: and w{{[0-9]+}}, w{{[0-9]+}}, #0xf0f0f0f
 ; CHECK-NONEON: mul
+}
 
+define i32 @cnt32_advsimd_2(<2 x i32> %x) {
+  %1 = extractelement <2 x i32> %x, i64 0
+  %2 = tail call i32 @llvm.ctpop.i32(i32 %1)
+  ret i32 %2
+; CHECK: fmov  w0, s0
+; CHECK: fmov  d0, x0
+; CHECK: cnt.8b        v0, v0
+; CHECK: uaddlv.8b     h0, v0
+; CHECK: fmov w0, s0
+; CHECK: ret
+; CHECK-NONEON-LABEL: cnt32_advsimd_2
+; CHECK-NONEON-NOT: 8b
+; CHECK-NONEON: and w{{[0-9]+}}, w{{[0-9]+}}, #0x55555555
+; CHECK-NONEON: and w{{[0-9]+}}, w{{[0-9]+}}, #0x33333333
+; CHECK-NONEON: and w{{[0-9]+}}, w{{[0-9]+}}, #0xf0f0f0f
+; CHECK-NONEON: mul
 }
 
 define i64 @cnt64_advsimd(i64 %x) nounwind readnone {