diff --git a/clang/lib/Driver/Driver.cpp b/clang/lib/Driver/Driver.cpp
--- a/clang/lib/Driver/Driver.cpp
+++ b/clang/lib/Driver/Driver.cpp
@@ -4520,6 +4520,7 @@
   llvm::PrettyStackTraceString CrashInfo("Building compilation jobs");
 
   Arg *FinalOutput = C.getArgs().getLastArg(options::OPT_o);
+  bool SyntaxOnly = C.getArgs().getLastArg(options::OPT_fsyntax_only);
 
   // It is an error to provide a -o option if we are making multiple output
   // files. There are exceptions:
@@ -4536,7 +4537,8 @@
   //
   // OffloadClass of type TY_Nothing: device-only output will place many outputs
   // into a single offloading action. We should count all inputs to the action
-  // as outputs.
+  // as outputs. Also ignore device-only outputs if we're compiling with
+  // -fsyntax-only.
   if (FinalOutput) {
     unsigned NumOutputs = 0;
     unsigned NumIfsOutputs = 0;
@@ -4550,7 +4552,7 @@
              A->getInputs().front()->getKind() == Action::IfsMergeJobClass)))
         ++NumOutputs;
       else if (A->getKind() == Action::OffloadClass &&
-               A->getType() == types::TY_Nothing)
+               A->getType() == types::TY_Nothing && !SyntaxOnly)
         NumOutputs += A->size();
     }
 
diff --git a/clang/test/Driver/cuda-bindings.cu b/clang/test/Driver/cuda-bindings.cu
--- a/clang/test/Driver/cuda-bindings.cu
+++ b/clang/test/Driver/cuda-bindings.cu
@@ -39,9 +39,19 @@
 //
 // Test two gpu architectures with complete compilation.
 //
-// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings --cuda-gpu-arch=sm_30 --cuda-gpu-arch=sm_35 %s 2>&1 \
-// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings --offload-arch=sm_30,sm_35 %s 2>&1 \
-// RUN: | FileCheck -check-prefix=BIN2 %s
+// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings \
+// RUN:        --cuda-gpu-arch=sm_30 --cuda-gpu-arch=sm_35 %s 2>&1 \
+// RUN: | FileCheck -check-prefixes=BIN2,AOUT %s
+// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings \
+// RUN:       --offload-arch=sm_30,sm_35 %s 2>&1 \
+// RUN: | FileCheck -check-prefixes=BIN2,AOUT %s
+// .. same, but with explicitly specified output.
+// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings \
+// RUN:       --cuda-gpu-arch=sm_30 --cuda-gpu-arch=sm_35 %s -o %t/out 2>&1 \
+// RUN: | FileCheck -check-prefixes=BIN2,TOUT %s
+// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings \
+// RUN:        --offload-arch=sm_30,sm_35 %s -o %t/out 2>&1 \
+// RUN: | FileCheck -check-prefixes=BIN2,TOUT %s
 // BIN2: # "nvptx64-nvidia-cuda" - "clang",{{.*}} output:
 // BIN2-NOT: cuda-bindings-device-cuda-nvptx64
 // BIN2: # "nvptx64-nvidia-cuda" - "NVPTX::Assembler",{{.*}} output:
@@ -54,7 +64,25 @@
 // BIN2-NOT: cuda-bindings-device-cuda-nvptx64
 // BIN2: # "powerpc64le-ibm-linux-gnu" - "clang",{{.*}}  output:
 // BIN2-NOT: cuda-bindings-device-cuda-nvptx64
-// BIN2: # "powerpc64le-ibm-linux-gnu" - "GNU::Linker", inputs:{{.*}}, output: "a.out"
+// AOUT: # "powerpc64le-ibm-linux-gnu" - "GNU::Linker", inputs:{{.*}}, output: "a.out"
+// TOUT: # "powerpc64le-ibm-linux-gnu" - "GNU::Linker", inputs:{{.*}}, output: "{{.*}}/out"
+
+// .. same, but with -fsyntax-only
+// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings -fsyntax-only \
+// RUN:       --cuda-gpu-arch=sm_30 --cuda-gpu-arch=sm_35 %s 2>&1 \
+// RUN: | FileCheck -check-prefix=SYN %s
+// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings -fsyntax-only \
+// RUN:        --offload-arch=sm_30,sm_35 %s -o %t/out 2>&1 \
+// RUN: | FileCheck -check-prefix=SYN %s
+// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings -fsyntax-only \
+// RUN:       --cuda-gpu-arch=sm_30 --cuda-gpu-arch=sm_35 %s 2>&1 \
+// RUN: | FileCheck -check-prefix=SYN %s
+// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings -fsyntax-only \
+// RUN:        --offload-arch=sm_30,sm_35 %s -o %t/out 2>&1 \
+// RUN: | FileCheck -check-prefix=SYN %s
+// SYN-DAG: # "powerpc64le-ibm-linux-gnu" - "clang", inputs: [{{.*}}], output: (nothing)
+// SYN-DAG: # "nvptx64-nvidia-cuda" - "clang", inputs: [{{.*}}], output: (nothing)
+// SYN-DAG: # "nvptx64-nvidia-cuda" - "clang", inputs: [{{.*}}], output: (nothing)
 
 //
 // Test two gpu architectures up to the assemble phase.