diff --git a/llvm/lib/Target/VE/VECallingConv.td b/llvm/lib/Target/VE/VECallingConv.td
--- a/llvm/lib/Target/VE/VECallingConv.td
+++ b/llvm/lib/Target/VE/VECallingConv.td
@@ -116,7 +116,7 @@
   // pair of vector mask --> generic vector mask registers
   CCIfType<[v512i1],
            CCAssignToRegWithShadow<[VMP1, VMP2, VMP3],
-                                   [VM1, VM1, VM3]>>,
+                                   [VM1, VM3, VM5]>>,
 
   // Follow the standard C CC for scalars.
   CCDelegateTo<CC_VE_C>
@@ -137,7 +137,7 @@
   // pair of vector mask --> generic vector mask registers
   CCIfType<[v512i1],
            CCAssignToRegWithShadow<[VMP1, VMP2, VMP3],
-                                   [VM1, VM1, VM3]>>,
+                                   [VM1, VM3, VM5]>>,
 
   // Follow the standard C CC for scalars.
   CCDelegateTo<RetCC_VE_C>
diff --git a/llvm/test/CodeGen/VE/Vector/fastcc_callee.ll b/llvm/test/CodeGen/VE/Vector/fastcc_callee.ll
--- a/llvm/test/CodeGen/VE/Vector/fastcc_callee.ll
+++ b/llvm/test/CodeGen/VE/Vector/fastcc_callee.ll
@@ -137,3 +137,11 @@
 ; CHECK-NEXT:    b.l.t (, %s10)
   ret <512 x i1> %vmp3
 }
+
+define fastcc <256 x i1> @vmp_cc_bug(<256 x i1> %vm1, <256 x i1> %vm2, <512 x i1> %vmp2, <256 x i1> %vm6) {
+; CHECK-LABEL: vmp_cc_bug:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    andm %vm1, %vm0, %vm6
+; CHECK-NEXT:    b.l.t (, %s10)
+  ret <256 x i1> %vm6
+}