Index: llvm/trunk/lib/Target/X86/X86InstrAVX512.td
===================================================================
--- llvm/trunk/lib/Target/X86/X86InstrAVX512.td
+++ llvm/trunk/lib/Target/X86/X86InstrAVX512.td
@@ -1786,6 +1786,11 @@
             (KMOVBmk addr:$dst, VK8:$src)>;
   def : Pat<(v8i1 (bitconvert (i8 (load addr:$src)))),
             (KMOVBkm addr:$src)>;
+
+  def : Pat<(store VK4:$src, addr:$dst),
+            (KMOVBmk addr:$dst, (COPY_TO_REGCLASS VK4:$src, VK8))>;
+  def : Pat<(store VK2:$src, addr:$dst),
+            (KMOVBmk addr:$dst, (COPY_TO_REGCLASS VK2:$src, VK8))>;
 }
 let Predicates = [HasAVX512, NoDQI] in {
   def : Pat<(store (i8 (bitconvert (v8i1 VK8:$src))), addr:$dst),
Index: llvm/trunk/test/CodeGen/X86/avx512-mask-op.ll
===================================================================
--- llvm/trunk/test/CodeGen/X86/avx512-mask-op.ll
+++ llvm/trunk/test/CodeGen/X86/avx512-mask-op.ll
@@ -407,3 +407,17 @@
   %ret = select <32 x i1> %mask, <32 x i16> %x, <32 x i16> zeroinitializer
   ret <32 x i16> %ret
 }
+
+; SKX-LABEL: test22
+; SKX: kmovb
+define void @test22(<4 x i1> %a, <4 x i1>* %addr) {
+  store <4 x i1> %a, <4 x i1>* %addr
+  ret void
+}
+
+; SKX-LABEL: test23
+; SKX: kmovb
+define void @test23(<2 x i1> %a, <2 x i1>* %addr) {
+  store <2 x i1> %a, <2 x i1>* %addr
+  ret void
+}