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
@@ -5261,20 +5261,21 @@
     //                      \
     //    Device Action 1  ---> OffloadAction -> Device Action 2
     //
-    // For a) and b), we just return the job generated for the dependence. For
+    // For a) and b), we just return the job generated for the dependences. For
     // c) and d) we override the current action with the host/device dependence
     // if the current toolchain is host/device and set the offload dependences
     // info with the jobs obtained from the device/host dependence(s).
 
-    // If there is a single device option, just generate the job for it.
-    if (OA->hasSingleDeviceDependence()) {
+    // If there is a single device option or has no host action, just generate
+    // the job for it.
+    if (OA->hasSingleDeviceDependence() || !OA->hasHostDependence()) {
       InputInfoList DevA;
       OA->doOnEachDeviceDependence([&](Action *DepA, const ToolChain *DepTC,
                                        const char *DepBoundArch) {
-        DevA =
-            BuildJobsForAction(C, DepA, DepTC, DepBoundArch, AtTopLevel,
-                               /*MultipleArchs*/ !!DepBoundArch, LinkingOutput,
-                               CachedResults, DepA->getOffloadingDeviceKind());
+        DevA.append(BuildJobsForAction(C, DepA, DepTC, DepBoundArch, AtTopLevel,
+                                       /*MultipleArchs*/ !!DepBoundArch,
+                                       LinkingOutput, CachedResults,
+                                       DepA->getOffloadingDeviceKind()));
       });
       return DevA;
     }
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
@@ -146,3 +146,15 @@
 // RUN:        --cuda-gpu-arch=sm_52 --cuda-device-only -c -o foo.o %s 2>&1 \
 // RUN: | FileCheck -check-prefix=D_ONLY %s
 // D_ONLY: "foo.o"
+
+//
+// Check to make sure we can generate multiple outputs for device-only
+// compilation.
+//
+// RUN: %clang -### -target powerpc64le-ibm-linux-gnu -ccc-print-bindings \
+// RUN:        --offload-arch=sm_70 --offload-arch=sm_52 --offload-device-only -c -o foo.o %s 2>&1 \
+// RUN: | FileCheck -check-prefix=MULTI-D-ONLY %s
+//      MULTI-D-ONLY: # "nvptx64-nvidia-cuda" - "clang", inputs: ["[[INPUT:.+]]"], output: "[[PTX_70:.+]]"
+// MULTI-D-ONLY-NEXT: # "nvptx64-nvidia-cuda" - "NVPTX::Assembler", inputs: ["[[PTX_70]]"], output: "[[CUBIN_70:.+]]"
+// MULTI-D-ONLY-NEXT: # "nvptx64-nvidia-cuda" - "clang", inputs: ["[[INPUT]]"], output: "[[PTX_52:.+]]"
+// MULTI-D-ONLY-NEXT: # "nvptx64-nvidia-cuda" - "NVPTX::Assembler", inputs: ["[[PTX_52]]"], output: "[[CUBIN_52:.+]]"