diff --git a/lib/Target/X86/X86VZeroUpper.cpp b/lib/Target/X86/X86VZeroUpper.cpp
index c4a5887..0f77948 100644
--- a/lib/Target/X86/X86VZeroUpper.cpp
+++ b/lib/Target/X86/X86VZeroUpper.cpp
@@ -120,9 +120,19 @@
   return false;
 }
 
+static bool clobbersAllYmmRegs(const MachineOperand &MO) {
+  for (unsigned reg = X86::YMM0; reg < X86::YMM15; ++reg) {
+    if (!MO.clobbersPhysReg(reg))
+      return false;
+  }
+  return true;
+}
+
 static bool hasYmmReg(MachineInstr *MI) {
   for (unsigned i = 0, e = MI->getNumOperands(); i != e; ++i) {
     const MachineOperand &MO = MI->getOperand(i);
+    if (MI->isCall() && MO.isRegMask() && !clobbersAllYmmRegs(MO))
+      return true;
     if (!MO.isReg())
       continue;
     if (MO.isDebug())
diff --git a/test/CodeGen/X86/avx-intel-ocl.ll b/test/CodeGen/X86/avx-intel-ocl.ll
index 0fec965..0550720 100644
--- a/test/CodeGen/X86/avx-intel-ocl.ll
+++ b/test/CodeGen/X86/avx-intel-ocl.ll
@@ -127,3 +127,43 @@
     %c = add i32 %c2, %b
 	ret i32 %c
 }
+
+; WIN64: test_float4
+; WIN64-NOT: vzeroupper
+; WIN64: call
+; WIN64-NOT: vzeroupper
+; WIN64: call
+; WIN64: ret
+
+; X64: test_float4
+; X64-NOT: vzeroupper
+; X64: call
+; X64-NOT: vzeroupper
+; X64: call
+; X64: ret
+
+; X32: test_float4
+; X32: vzeroupper
+; X32: call
+; X32: vzeroupper
+; X32: call
+; X32: ret
+
+declare <4 x float> @func_float4(<4 x float>, <4 x float>, <4 x float>)
+
+define <8 x float> @test_float4(<8 x float> %a, <8 x float> %b, <8 x float> %c) nounwind readnone {
+entry:
+  %0 = shufflevector <8 x float> %a, <8 x float> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+  %1 = shufflevector <8 x float> %b, <8 x float> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+  %2 = shufflevector <8 x float> %c, <8 x float> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+  %call.i = tail call intel_ocl_bicc <4 x float> @func_float4(<4 x float> %0, <4 x float> %1, <4 x float> %2) nounwind
+  %3 = shufflevector <4 x float> %call.i, <4 x float> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
+  %4 = shufflevector <8 x float> %a, <8 x float> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+  %5 = shufflevector <8 x float> %b, <8 x float> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+  %6 = shufflevector <8 x float> %c, <8 x float> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+  %call.i2 = tail call intel_ocl_bicc <4 x float> @func_float4(<4 x float> %4, <4 x float> %5, <4 x float> %6) nounwind
+  %7 = shufflevector <4 x float> %call.i2, <4 x float> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
+  %8 = shufflevector <8 x float> %3, <8 x float> %7, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
+  ret <8 x float> %8
+}
+