[DAG][X86] expandABD - add branchless abds/abdu expansion for 0/-1 co…

…mparison result cases If the comparison results are allbits masks, we can expand as "abd(lhs, rhs) -> sub(cmpgt(lhs, rhs), xor(sub(lhs, rhs), cmpgt(lhs, rhs)))", replacing a sub+sub+select pattern with the simpler sub+xor+sub pattern. This allows us to remove a lot of X86 specific legalization code, and will be useful in future generic expansion for the legalization work in #92576 Alive2: https://alive2.llvm.org/ce/z/sj863C
llvm · May 23, 2024 · 6005fa9 · 6005fa9
1 parent ae3f680
commit 6005fa9
Show file tree

Hide file tree

Showing 8 changed files with 741 additions and 902 deletions.
diff --git a/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp b/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
@@ -9228,11 +9228,21 @@ SDValue TargetLowering::expandABD(SDNode *N, SelectionDAG &DAG) const {
                        DAG.getNode(ISD::USUBSAT, dl, VT, LHS, RHS),
                        DAG.getNode(ISD::USUBSAT, dl, VT, RHS, LHS));
 
-  // abds(lhs, rhs) -> select(sgt(lhs,rhs), sub(lhs,rhs), sub(rhs,lhs))
-  // abdu(lhs, rhs) -> select(ugt(lhs,rhs), sub(lhs,rhs), sub(rhs,lhs))
   EVT CCVT = getSetCCResultType(DAG.getDataLayout(), *DAG.getContext(), VT);
   ISD::CondCode CC = IsSigned ? ISD::CondCode::SETGT : ISD::CondCode::SETUGT;
   SDValue Cmp = DAG.getSetCC(dl, CCVT, LHS, RHS, CC);
+
+  // Branchless expansion iif cmp result is allbits:
+  // abds(lhs, rhs) -> sub(sgt(lhs, rhs), xor(sgt(lhs, rhs), sub(lhs, rhs)))
+  // abdu(lhs, rhs) -> sub(ugt(lhs, rhs), xor(ugt(lhs, rhs), sub(lhs, rhs)))
+  if (CCVT == VT && getBooleanContents(VT) == ZeroOrNegativeOneBooleanContent) {
+    SDValue Diff = DAG.getNode(ISD::SUB, dl, VT, LHS, RHS);
+    SDValue Xor = DAG.getNode(ISD::XOR, dl, VT, Diff, Cmp);
+    return DAG.getNode(ISD::SUB, dl, VT, Cmp, Xor);
+  }
+
+  // abds(lhs, rhs) -> select(sgt(lhs,rhs), sub(lhs,rhs), sub(rhs,lhs))
+  // abdu(lhs, rhs) -> select(ugt(lhs,rhs), sub(lhs,rhs), sub(rhs,lhs))
   return DAG.getSelect(dl, VT, Cmp, DAG.getNode(ISD::SUB, dl, VT, LHS, RHS),
                        DAG.getNode(ISD::SUB, dl, VT, RHS, LHS));
 }

diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -1108,13 +1108,6 @@ X86TargetLowering::X86TargetLowering(const X86TargetMachine &TM,
       setOperationAction(ISD::UMIN, VT, VT == MVT::v16i8 ? Legal : Custom);
     }
 
-    setOperationAction(ISD::ABDU,               MVT::v16i8, Custom);
-    setOperationAction(ISD::ABDS,               MVT::v16i8, Custom);
-    setOperationAction(ISD::ABDU,               MVT::v8i16, Custom);
-    setOperationAction(ISD::ABDS,               MVT::v8i16, Custom);
-    setOperationAction(ISD::ABDU,               MVT::v4i32, Custom);
-    setOperationAction(ISD::ABDS,               MVT::v4i32, Custom);
-
     setOperationAction(ISD::UADDSAT,            MVT::v16i8, Legal);
     setOperationAction(ISD::SADDSAT,            MVT::v16i8, Legal);
     setOperationAction(ISD::USUBSAT,            MVT::v16i8, Legal);
@@ -1132,9 +1125,11 @@ X86TargetLowering::X86TargetLowering(const X86TargetMachine &TM,
     setOperationAction(ISD::INSERT_VECTOR_ELT,  MVT::v4f32, Custom);
 
     for (auto VT : { MVT::v16i8, MVT::v8i16, MVT::v4i32, MVT::v2i64 }) {
-      setOperationAction(ISD::SETCC,              VT, Custom);
-      setOperationAction(ISD::CTPOP,              VT, Custom);
-      setOperationAction(ISD::ABS,                VT, Custom);
+      setOperationAction(ISD::SETCC, VT, Custom);
+      setOperationAction(ISD::CTPOP, VT, Custom);
+      setOperationAction(ISD::ABS, VT, Custom);
+      setOperationAction(ISD::ABDS, VT, Custom);
+      setOperationAction(ISD::ABDU, VT, Custom);
 
       // The condition codes aren't legal in SSE/AVX and under AVX512 we use
       // setcc all the way to isel and prefer SETGT in some isel patterns.
@@ -1336,11 +1331,6 @@ X86TargetLowering::X86TargetLowering(const X86TargetMachine &TM,
     setOperationAction(ISD::UMIN,               MVT::v8i16, Legal);
     setOperationAction(ISD::UMIN,               MVT::v4i32, Legal);
 
-    for (auto VT : {MVT::v16i8, MVT::v8i16, MVT::v4i32, MVT::v2i64}) {
-      setOperationAction(ISD::ABDS,             VT, Custom);
-      setOperationAction(ISD::ABDU,             VT, Custom);
-    }
-
     setOperationAction(ISD::UADDSAT,            MVT::v4i32, Custom);
     setOperationAction(ISD::SADDSAT,            MVT::v2i64, Custom);
     setOperationAction(ISD::SSUBSAT,            MVT::v2i64, Custom);
@@ -28421,18 +28411,6 @@ static SDValue LowerABD(SDValue Op, const X86Subtarget &Subtarget,
     }
   }
 
-  // TODO: Move to TargetLowering expandABD().
-  if (!Subtarget.hasSSE41() &&
-      ((IsSigned && VT == MVT::v16i8) || VT == MVT::v4i32)) {
-    SDValue LHS = DAG.getFreeze(Op.getOperand(0));
-    SDValue RHS = DAG.getFreeze(Op.getOperand(1));
-    ISD::CondCode CC = IsSigned ? ISD::CondCode::SETGT : ISD::CondCode::SETUGT;
-    SDValue Cmp = DAG.getSetCC(dl, VT, LHS, RHS, CC);
-    SDValue Diff0 = DAG.getNode(ISD::SUB, dl, VT, LHS, RHS);
-    SDValue Diff1 = DAG.getNode(ISD::SUB, dl, VT, RHS, LHS);
-    return getBitSelect(dl, VT, Diff0, Diff1, Cmp, DAG);
-  }
-
   // Default to expand.
   return SDValue();
 }