Index: llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
===================================================================
--- llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -14513,9 +14513,10 @@
     return SDValue();
 
   // Restricted the DAG combine to only cases where we're extracting from a
-  // flag-setting operation
-  auto *Idx = dyn_cast<ConstantSDNode>(N->getOperand(1));
-  if (!Idx || !Idx->isZero() || SetCC.getOpcode() != ISD::SETCC)
+  // flag-setting operation.
+  if (!isNullConstant(N->getOperand(1)) ||
+      (SetCC.getOpcode() != ISD::SETCC &&
+       SetCC.getOpcode() != ISD::INTRINSIC_WO_CHAIN))
     return SDValue();
 
   // Extracts of lane 0 for SVE can be expressed as PTEST(Op, FIRST) ? 1 : 0
Index: llvm/test/CodeGen/AArch64/sve-cmp-folds.ll
===================================================================
--- llvm/test/CodeGen/AArch64/sve-cmp-folds.ll
+++ llvm/test/CodeGen/AArch64/sve-cmp-folds.ll
@@ -30,5 +30,16 @@
   ret i1 %bit
 }
 
+define i1 @whilelo_first(i64 %next, i64 %end) {
+; CHECK-LABEL: whilelo_first:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    whilelo p0.s, x0, x1
+; CHECK-NEXT:    cset w0, mi
+; CHECK-NEXT:    ret
+  %predicate = call <vscale x 4 x i1> @llvm.aarch64.sve.whilelo.nxv4i1.i64(i64 %next, i64 %end)
+  %bit = extractelement <vscale x 4 x i1> %predicate, i64 0
+  ret i1 %bit
+}
 
 declare i64 @llvm.vscale.i64()
+declare <vscale x 4 x i1> @llvm.aarch64.sve.whilelo.nxv4i1.i64(i64, i64)