[llvm] [AArch64] Improve scalar and Neon popcount with SVE CNT. (PR #143870)

[Paul Walker via llvm-commits]

================
@@ -10630,6 +10630,34 @@ SDValue AArch64TargetLowering::LowerCTPOP_PARITY(SDValue Op,
   if (VT == MVT::i32 && IsParity)
     return SDValue();
 
+  if (Subtarget->isSVEorStreamingSVEAvailable()) {
+    assert((VT == MVT::i32 || VT == MVT::i64 || VT == MVT::i128) &&
+           "Unexpected type for custom ctpop lowering.");
+    if (VT == MVT::i32 || VT == MVT::i64) {
+      EVT ContainerVT = VT == MVT::i32 ? MVT::nxv4i32 : MVT::nxv2i64;
+      Val = DAG.getNode(ISD::INSERT_VECTOR_ELT, DL, ContainerVT,
+                        DAG.getUNDEF(ContainerVT), Val,
+                        DAG.getVectorIdxConstant(0, DL));
+      Val = DAG.getNode(ISD::CTPOP, DL, ContainerVT, Val);
+      Val = DAG.getNode(ISD::EXTRACT_VECTOR_ELT, DL, VT, Val,
+                        DAG.getVectorIdxConstant(0, DL));
+    } else if (VT == MVT::i128) {
+      Val = DAG.getNode(ISD::BITCAST, DL, MVT::v2i64, Val);
+      Val = convertToScalableVector(DAG, MVT::nxv2i64, Val);
+      Val = DAG.getNode(ISD::CTPOP, DL, MVT::nxv2i64, Val);
+      Val = convertFromScalableVector(DAG, MVT::v2i64, Val);
+      Val = DAG.getNode(ISD::VECREDUCE_ADD, DL, MVT::i64, Val);
+      Val = DAG.getZExtOrTrunc(Val, DL, VT);
+    } else
+      llvm_unreachable("Unexpected type!");
----------------
paulwalker-arm wrote:

Works for me.

https://github.com/llvm/llvm-project/pull/143870