Index: lib/Driver/ToolChain.cpp
===================================================================
--- lib/Driver/ToolChain.cpp
+++ lib/Driver/ToolChain.cpp
@@ -807,16 +807,19 @@
   if (DeviceOffloadKind == Action::OFK_OpenMP) {
     DerivedArgList *DAL = new DerivedArgList(Args.getBaseArgs());
     const OptTable &Opts = getDriver().getOpts();
-    bool NewArgAdded = false;
+    bool Modified = false;
 
     // Handle -Xopenmp-target flags
     for (Arg *A : Args) {
       // Exclude flags which may only apply to the host toolchain.
-      // Do not exclude flags when the host triple (AuxTriple),
-      // matches the current toolchain triple.
+      // Do not exclude flags when the host triple (AuxTriple)
+      // matches the current toolchain triple. If it is not present
+      // at all, target and host share a toolchain.
       if (A->getOption().matches(options::OPT_m_Group)) {
-        if (getAuxTriple() && getAuxTriple()->str() == getTriple().str())
+        if (!getAuxTriple() || getAuxTriple()->str() == getTriple().str())
           DAL->append(A);
+        else
+          Modified = true;
         continue;
       }
 
@@ -857,10 +860,10 @@
       A = XOpenMPTargetArg.release();
       AllocatedArgs.push_back(A);
       DAL->append(A);
-      NewArgAdded = true;
+      Modified = true;
     }
 
-    if (NewArgAdded) {
+    if (Modified) {
       return DAL;
     } else {
       delete DAL;
Index: test/Driver/openmp-offload-gpu.c
===================================================================
--- test/Driver/openmp-offload-gpu.c
+++ test/Driver/openmp-offload-gpu.c
@@ -9,38 +9,6 @@
 
 /// ###########################################################################
 
-/// Check -Xopenmp-target=powerpc64le-ibm-linux-gnu -march=pwr7 is passed when compiling for the device.
-// RUN:   %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=powerpc64le-ibm-linux-gnu -Xopenmp-target=powerpc64le-ibm-linux-gnu -mcpu=pwr7 %s 2>&1 \
-// RUN:   | FileCheck -check-prefix=CHK-FOPENMP-EQ-TARGET %s
-
-// CHK-FOPENMP-EQ-TARGET: clang{{.*}} "-target-cpu" "pwr7"
-
-/// ###########################################################################
-
-/// Check -Xopenmp-target -march=pwr7 is passed when compiling for the device.
-// RUN:   %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=powerpc64le-ibm-linux-gnu -Xopenmp-target -mcpu=pwr7 %s 2>&1 \
-// RUN:   | FileCheck -check-prefix=CHK-FOPENMP-TARGET %s
-
-// CHK-FOPENMP-TARGET: clang{{.*}} "-target-cpu" "pwr7"
-
-/// ###########################################################################
-
-/// Check -Xopenmp-target triggers error when multiple triples are used.
-// RUN:   %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=powerpc64le-ibm-linux-gnu,powerpc64le-unknown-linux-gnu -Xopenmp-target -mcpu=pwr8 %s 2>&1 \
-// RUN:   | FileCheck -check-prefix=CHK-FOPENMP-TARGET-AMBIGUOUS-ERROR %s
-
-// CHK-FOPENMP-TARGET-AMBIGUOUS-ERROR: clang{{.*}} error: cannot deduce implicit triple value for -Xopenmp-target, specify triple using -Xopenmp-target=<triple>
-
-/// ###########################################################################
-
-/// Check -Xopenmp-target triggers error when an option requiring arguments is passed to it.
-// RUN:   %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=powerpc64le-ibm-linux-gnu -Xopenmp-target -Xopenmp-target -mcpu=pwr8 %s 2>&1 \
-// RUN:   | FileCheck -check-prefix=CHK-FOPENMP-TARGET-NESTED-ERROR %s
-
-// CHK-FOPENMP-TARGET-NESTED-ERROR: clang{{.*}} error: invalid -Xopenmp-target argument: '-Xopenmp-target -Xopenmp-target', options requiring arguments are unsupported
-
-/// ###########################################################################
-
 /// Check -Xopenmp-target uses one of the archs provided when several archs are used.
 // RUN:   %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_35 -Xopenmp-target -march=sm_60 %s 2>&1 \
 // RUN:   | FileCheck -check-prefix=CHK-FOPENMP-TARGET-ARCHS %s
Index: test/Driver/openmp-offload.c
===================================================================
--- test/Driver/openmp-offload.c
+++ test/Driver/openmp-offload.c
@@ -39,6 +39,54 @@
 
 /// ###########################################################################
 
+/// Check -Xopenmp-target=powerpc64le-ibm-linux-gnu -mcpu=pwr7 is passed when compiling for the device.
+// RUN:   %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=powerpc64le-ibm-linux-gnu -Xopenmp-target=powerpc64le-ibm-linux-gnu -mcpu=pwr7 %s 2>&1 \
+// RUN:   | FileCheck -check-prefix=CHK-FOPENMP-EQ-TARGET %s
+
+// CHK-FOPENMP-EQ-TARGET: clang{{.*}} "-target-cpu" "pwr7" {{.*}}"-fopenmp-is-device"
+
+/// ###########################################################################
+
+/// Check -Xopenmp-target -mcpu=pwr7 is passed when compiling for the device.
+// RUN:   %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=powerpc64le-ibm-linux-gnu -Xopenmp-target -mcpu=pwr7 %s 2>&1 \
+// RUN:   | FileCheck -check-prefix=CHK-FOPENMP-TARGET %s
+
+// CHK-FOPENMP-TARGET: clang{{.*}} "-target-cpu" "pwr7" {{.*}}"-fopenmp-is-device"
+
+/// ##########################################################################
+
+/// Check -mcpu=pwr7 is passed to the same triple.
+// RUN:    %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=powerpc64le-ibm-linux-gnu -target powerpc64le-ibm-linux-gnu -mcpu=pwr7 %s 2>&1 \
+// RUN:    | FileCheck -check-prefix=CHK-FOPENMP-MCPU-TO-SAME-TRIPLE %s
+
+// CHK-FOPENMP-MCPU-TO-SAME-TRIPLE: clang{{.*}} "-target-cpu" "pwr7" {{.*}}"-fopenmp-is-device"
+
+/// ##########################################################################
+
+/// Check -march=pwr7 is NOT passed to nvptx64-nvidia-cuda.
+// RUN:    %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -march=pwr7 %s 2>&1 \
+// RUN:    | FileCheck -check-prefix=CHK-FOPENMP-MARCH-TO-GPU %s
+
+// CHK-FOPENMP-MARCH-TO-GPU-NOT: clang{{.*}} "-target-cpu" "pwr7" {{.*}}"-fopenmp-is-device"
+
+/// ###########################################################################
+
+/// Check -Xopenmp-target triggers error when multiple triples are used.
+// RUN:   %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=powerpc64le-ibm-linux-gnu,powerpc64le-unknown-linux-gnu -Xopenmp-target -mcpu=pwr8 %s 2>&1 \
+// RUN:   | FileCheck -check-prefix=CHK-FOPENMP-TARGET-AMBIGUOUS-ERROR %s
+
+// CHK-FOPENMP-TARGET-AMBIGUOUS-ERROR: clang{{.*}} error: cannot deduce implicit triple value for -Xopenmp-target, specify triple using -Xopenmp-target=<triple>
+
+/// ###########################################################################
+
+/// Check -Xopenmp-target triggers error when an option requiring arguments is passed to it.
+// RUN:   %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=powerpc64le-ibm-linux-gnu -Xopenmp-target -Xopenmp-target -mcpu=pwr8 %s 2>&1 \
+// RUN:   | FileCheck -check-prefix=CHK-FOPENMP-TARGET-NESTED-ERROR %s
+
+// CHK-FOPENMP-TARGET-NESTED-ERROR: clang{{.*}} error: invalid -Xopenmp-target argument: '-Xopenmp-target -Xopenmp-target', options requiring arguments are unsupported
+
+/// ###########################################################################
+
 /// Check the phases graph when using a single target, different from the host.
 /// We should have an offload action joining the host compile and device
 /// preprocessor and another one joining the device linking outputs to the host