Index: lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp
===================================================================
--- lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp
+++ lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp
@@ -1235,7 +1235,15 @@
     NewOps[OpNo] = PromoteTargetBoolean(N->getOperand(OpNo), DataVT);
   } else
     NewOps[OpNo] = GetPromotedInteger(N->getOperand(OpNo));
-  return SDValue(DAG.UpdateNodeOperands(N, NewOps), 0);
+
+  SDValue Res = SDValue(DAG.UpdateNodeOperands(N, NewOps), 0);
+  // updated in place.
+  if (Res.getNode() == N)
+    return Res;
+
+  ReplaceValueWith(SDValue(N, 0), Res.getValue(0));
+  ReplaceValueWith(SDValue(N, 1), Res.getValue(1));
+  return SDValue();
 }
 
 SDValue DAGTypeLegalizer::PromoteIntOp_MSCATTER(MaskedScatterSDNode *N,
Index: test/CodeGen/X86/pr28312.ll
===================================================================
--- test/CodeGen/X86/pr28312.ll
+++ test/CodeGen/X86/pr28312.ll
@@ -0,0 +1,39 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=x86_64-unknown-linux-gnu  -mcpu=skx < %s | FileCheck %s --check-prefix=SKX
+; RUN: llc -mtriple=x86_64-unknown-linux-gnu  -mcpu=knl < %s | FileCheck %s --check-prefix=KNL
+
+define <4 x i64> @test(<4 x i64*> %p1, <4 x i1> %k, <4 x i1> %k2,<4 x i64> %d) {
+; SKX-LABEL: test:
+; SKX:       # BB#0:
+; SKX-NEXT:    vpslld $31, %xmm1, %xmm1
+; SKX-NEXT:    vptestmd %xmm1, %xmm1, %k1
+; SKX-NEXT:    vpgatherqq (,%ymm0), %ymm1 {%k1}
+; SKX-NEXT:    vpaddq %ymm1, %ymm1, %ymm0
+; SKX-NEXT:    vpaddq %ymm1, %ymm0, %ymm0
+; SKX-NEXT:    retq
+;
+; KNL-LABEL: test:
+; KNL:       # BB#0:
+; KNL-NEXT:    # kill: %YMM0<def> %YMM0<kill> %ZMM0<def>
+; KNL-NEXT:    vpslld $31, %xmm1, %xmm1
+; KNL-NEXT:    vpsrad $31, %xmm1, %xmm1
+; KNL-NEXT:    vpmovsxdq %xmm1, %ymm1
+; KNL-NEXT:    vpxord %zmm2, %zmm2, %zmm2
+; KNL-NEXT:    vinserti64x4 $0, %ymm1, %zmm2, %zmm1
+; KNL-NEXT:    vpsllq $63, %zmm1, %zmm1
+; KNL-NEXT:    vptestmq %zmm1, %zmm1, %k1
+; KNL-NEXT:    vpgatherqq (,%zmm0), %zmm1 {%k1}
+; KNL-NEXT:    vpaddq %ymm1, %ymm1, %ymm0
+; KNL-NEXT:    vpaddq %ymm1, %ymm0, %ymm0
+; KNL-NEXT:    retq
+  %g1 = call <4 x i64> @llvm.masked.gather.v4i64(<4 x i64*> %p1, i32 8, <4 x i1> %k, <4 x i64> undef)
+  %g2 = call <4 x i64> @llvm.masked.gather.v4i64(<4 x i64*> %p1, i32 8, <4 x i1> %k, <4 x i64> undef)
+  %g3 = call <4 x i64> @llvm.masked.gather.v4i64(<4 x i64*> %p1, i32 8, <4 x i1> %k, <4 x i64> undef)
+  %a = add <4 x i64> %g1, %g2
+  %b = add <4 x i64> %a, %g3
+  ret <4 x i64> %b
+}
+
+declare <4 x i64> @llvm.masked.gather.v4i64(<4 x i64*>, i32, <4 x i1>, <4 x i64>)
+declare void @llvm.masked.scatter.v4i64(<4 x i64>, <4 x i64*>, i32, <4 x i1>)
+