Index: lib/Target/X86/X86ISelLowering.cpp
===================================================================
--- lib/Target/X86/X86ISelLowering.cpp
+++ lib/Target/X86/X86ISelLowering.cpp
@@ -18871,10 +18871,13 @@
       return DAG.getStore(Chain, dl, DataToCompress, Addr,
                           MemIntr->getMemOperand());
 
+    SDValue LoadAddress = DAG.getLoad(VT, SDLoc(Op), Chain, Addr,
+                         MemIntr->getPointerInfo(), MemIntr->getAlignment());
     SDValue Compressed =
       getVectorMaskingNode(DAG.getNode(IntrData->Opc0, dl, VT, DataToCompress),
-                           Mask, DAG.getUNDEF(VT), Subtarget, DAG);
-    return DAG.getStore(Chain, dl, Compressed, Addr,
+                           Mask, LoadAddress, Subtarget, DAG);
+    LoadSDNode* LoadInst = dyn_cast<LoadSDNode>(LoadAddress);
+    return DAG.getStore(LoadInst->getChain(), dl, Compressed, Addr,
                         MemIntr->getMemOperand());
   }
   case TRUNCATE_TO_MEM_VI8:
Index: lib/Target/X86/X86InstrAVX512.td
===================================================================
--- lib/Target/X86/X86InstrAVX512.td
+++ lib/Target/X86/X86InstrAVX512.td
@@ -7219,7 +7219,7 @@
               (ins _.MemOp:$dst, _.KRCWM:$mask, _.RC:$src),
               OpcodeStr # "\t{$src, $dst {${mask}}|$dst {${mask}}, $src}",
               [(store (_.VT (vselect _.KRCWM:$mask,
-                             (_.VT (X86compress  _.RC:$src)), _.ImmAllZerosV)),
+                             (_.VT (X86compress  _.RC:$src)), (_.VT (load addr:$dst)))),
                 addr:$dst)]>,
               EVEX_K, EVEX_CD8<_.EltSize, CD8VT1>;
 }
Index: test/CodeGen/X86/avx512vl-intrinsics.ll
===================================================================
--- test/CodeGen/X86/avx512vl-intrinsics.ll
+++ test/CodeGen/X86/avx512vl-intrinsics.ll
@@ -893,6 +893,38 @@
   ret <4 x i32> %res
 }
 
+@xmm = common global <4 x i32> zeroinitializer, align 16
+@k8 = common global i8 0, align 1
+@res = common global <4 x i32> zeroinitializer, align 16
+
+define i32 @compr11() {
+; CHECK-LABEL: compr11:
+; CHECK:       ## BB#0: ## %entry
+; CHECK-NEXT:    movq _xmm@{{.*}}(%rip), %rax ## encoding: [0x48,0x8b,0x05,A,A,A,A]
+; CHECK-NEXT:    ## fixup A - offset: 3, value: _xmm@GOTPCREL-4, kind: reloc_riprel_4byte_movq_load
+; CHECK-NEXT:    vmovdqa32 (%rax), %xmm0 ## encoding: [0x62,0xf1,0x7d,0x08,0x6f,0x00]
+; CHECK-NEXT:    movq _k8@{{.*}}(%rip), %rax ## encoding: [0x48,0x8b,0x05,A,A,A,A]
+; CHECK-NEXT:    ## fixup A - offset: 3, value: _k8@GOTPCREL-4, kind: reloc_riprel_4byte_movq_load
+; CHECK-NEXT:    movzbl (%rax), %eax ## encoding: [0x0f,0xb6,0x00]
+; CHECK-NEXT:    kmovw %eax, %k1 ## encoding: [0xc5,0xf8,0x92,0xc8]
+; CHECK-NEXT:    vpcompressd %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf2,0x7d,0x89,0x8b,0xc0]
+; CHECK-NEXT:    vpxord %xmm1, %xmm1, %xmm1 ## encoding: [0x62,0xf1,0x75,0x08,0xef,0xc9]
+; CHECK-NEXT:    vmovdqa32 %xmm0, -{{[0-9]+}}(%rsp) ## encoding: [0x62,0xf1,0x7d,0x08,0x7f,0x84,0x24,0xd8,0xff,0xff,0xff]
+; CHECK-NEXT:    vmovdqa32 %xmm1, -{{[0-9]+}}(%rsp) ## encoding: [0x62,0xf1,0x7d,0x08,0x7f,0x8c,0x24,0xe8,0xff,0xff,0xff]
+; CHECK-NEXT:    xorl %eax, %eax ## encoding: [0x31,0xc0]
+; CHECK-NEXT:    retq ## encoding: [0xc3]
+entry:
+  %.compoundliteral = alloca <2 x i64>, align 16
+  %res = alloca <4 x i32>, align 16
+  %a0 = load <4 x i32>, <4 x i32>* @xmm, align 16
+  %a2 = load i8, i8* @k8, align 1
+  %a21 = call <4 x i32> @llvm.x86.avx512.mask.compress.d.128(<4 x i32> %a0, <4 x i32> zeroinitializer, i8 %a2) #2
+  store volatile <4 x i32> %a21, <4 x i32>* %res, align 16
+  store <2 x i64> zeroinitializer, <2 x i64>* %.compoundliteral, align 16
+  ret i32 0
+}
+
+
 declare <4 x i32> @llvm.x86.avx512.mask.compress.d.128(<4 x i32> %data, <4 x i32> %src0, i8 %mask)
 
 ; Expand