[LegalizeDAG] Don't bother with final MUL+SRL stage for byte CTPOP.

The final stage of CTPOP expansion (v = (v * 0x01010101...) >> (Len - 8)) is completely pointless for the byte (Len = 8) case as it reduces to (v = (v * 0x01...) >> 0), but annoyingly this doesn't always get optimized away. 

Found while investigating generic vector CTPOP expansion (PR32655).

llvm-svn: 344477

1 files changed, 4 insertions, 3 deletions

diff --git a/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp b/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp
index bb2c76a6a41..175df889ef2 100644
--- a/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp
@@ -2750,9 +2750,10 @@ SDValue SelectionDAGLegalize::ExpandBitCount(unsigned Opc, SDValue Op,
                                              DAG.getConstant(4, dl, ShVT))),
                      Mask0F);
     // v = (v * 0x01010101...) >> (Len - 8)
-    Op = DAG.getNode(ISD::SRL, dl, VT,
-                     DAG.getNode(ISD::MUL, dl, VT, Op, Mask01),
-                     DAG.getConstant(Len - 8, dl, ShVT));
+    if (Len > 8)
+      Op = DAG.getNode(ISD::SRL, dl, VT,
+                       DAG.getNode(ISD::MUL, dl, VT, Op, Mask01),
+                       DAG.getConstant(Len - 8, dl, ShVT));
 
     return Op;
   }