[CUDA] Add --cuda-compile-host-device, which overrides --cuda-host-only and --cuda...

Summary:
This completes the flag's tristate, letting you override it at will on
the command line.

Reviewers: tra

Subscribers: cfe-commits, jhen

Differential Revision: http://reviews.llvm.org/D19248

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@266707 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/clang/Driver/Options.td b/include/clang/Driver/Options.td
index a28518e8c665a70025c597482bb75a51b36b16ab..9c625a0cff750c4b9e7d607e844de7301da75e74 100644 (file)
--- a/include/clang/Driver/Options.td
+++ b/include/clang/Driver/Options.td
@@ -375,11 +375,15 @@ def cxx_isystem : JoinedOrSeparate<["-"], "cxx-isystem">, Group<clang_i_Group>,
 def c : Flag<["-"], "c">, Flags<[DriverOption]>,
   HelpText<"Only run preprocess, compile, and assemble steps">;
 def cuda_device_only : Flag<["--"], "cuda-device-only">,
-  HelpText<"Do device-side CUDA compilation only">;
+  HelpText<"Compile CUDA code for device only">;
+def cuda_host_only : Flag<["--"], "cuda-host-only">,
+  HelpText<"Compile CUDA code for host only.  Has no effect on non-CUDA "
+           "compilations.">;
+def cuda_compile_host_device : Flag<["--"], "cuda-compile-host-device">,
+  HelpText<"Compile CUDA code for both host and device (default).  Has no "
+           "effect on non-CUDA compilations.">;
 def cuda_gpu_arch_EQ : Joined<["--"], "cuda-gpu-arch=">, Flags<[DriverOption]>,
   HelpText<"CUDA GPU architecture (e.g. sm_35).  May be specified more than once.">;
-def cuda_host_only : Flag<["--"], "cuda-host-only">,
-  HelpText<"Do host-side CUDA compilation only">;
 def cuda_noopt_device_debug : Flag<["--"], "cuda-noopt-device-debug">,
   HelpText<"Enable device-side debug info generation. Disables ptxas optimizations.">;
 def cuda_path_EQ : Joined<["--"], "cuda-path=">, Group<i_Group>,

diff --git a/lib/Driver/Driver.cpp b/lib/Driver/Driver.cpp
index 989432320c5e0a46eee389725edd8a72ed7a7840..74121ecf51deb2efc8efa495b5c28cea918712cd 100644 (file)
--- a/lib/Driver/Driver.cpp
+++ b/lib/Driver/Driver.cpp
@@ -1316,11 +1316,17 @@ void Driver::BuildInputs(const ToolChain &TC, DerivedArgList &Args,
 static Action *buildCudaActions(Compilation &C, DerivedArgList &Args,
                                 const Arg *InputArg, Action *HostAction,
                                 ActionList &Actions) {
-  Arg *PartialCompilationArg = Args.getLastArg(options::OPT_cuda_host_only,
-                                               options::OPT_cuda_device_only);
-  // Host-only compilation case.
-  if (PartialCompilationArg &&
-      PartialCompilationArg->getOption().matches(options::OPT_cuda_host_only))
+  Arg *PartialCompilationArg = Args.getLastArg(
+      options::OPT_cuda_host_only, options::OPT_cuda_device_only,
+      options::OPT_cuda_compile_host_device);
+  bool CompileHostOnly =
+      PartialCompilationArg &&
+      PartialCompilationArg->getOption().matches(options::OPT_cuda_host_only);
+  bool CompileDeviceOnly =
+      PartialCompilationArg &&
+      PartialCompilationArg->getOption().matches(options::OPT_cuda_device_only);
+
+  if (CompileHostOnly)
     return C.MakeAction<CudaHostAction>(HostAction, ActionList());
 
   // Collect all cuda_gpu_arch parameters, removing duplicates.
@@ -1364,15 +1370,14 @@ static Action *buildCudaActions(Compilation &C, DerivedArgList &Args,
 
   // Figure out what to do with device actions -- pass them as inputs to the
   // host action or run each of them independently.
-  bool DeviceOnlyCompilation = PartialCompilationArg != nullptr;
-  if (PartialCompilation || DeviceOnlyCompilation) {
+  if (PartialCompilation || CompileDeviceOnly) {
     // In case of partial or device-only compilation results of device actions
     // are not consumed by the host action device actions have to be added to
     // top-level actions list with AtTopLevel=true and run independently.
 
     // -o is ambiguous if we have more than one top-level action.
     if (Args.hasArg(options::OPT_o) &&
-        (!DeviceOnlyCompilation || GpuArchList.size() > 1)) {
+        (!CompileDeviceOnly || GpuArchList.size() > 1)) {
       C.getDriver().Diag(
           clang::diag::err_drv_output_argument_with_multiple_files);
       return nullptr;
@@ -1383,7 +1388,7 @@ static Action *buildCudaActions(Compilation &C, DerivedArgList &Args,
                                                        GpuArchList[I],
                                                        /* AtTopLevel */ true));
     // Kill host action in case of device-only compilation.
-    if (DeviceOnlyCompilation)
+    if (CompileDeviceOnly)
       return nullptr;
     return HostAction;
   }
@@ -1647,9 +1652,10 @@ void Driver::BuildActions(Compilation &C, DerivedArgList &Args,
   // Claim ignored clang-cl options.
   Args.ClaimAllArgs(options::OPT_cl_ignored_Group);
 
-  // Claim --cuda-host-only arg which may be passed to non-CUDA
-  // compilations and should not trigger warnings there.
+  // Claim --cuda-host-only and --cuda-compile-host-device, which may be passed
+  // to non-CUDA compilations and should not trigger warnings there.
   Args.ClaimAllArgs(options::OPT_cuda_host_only);
+  Args.ClaimAllArgs(options::OPT_cuda_compile_host_device);
 }
 
 Action *Driver::ConstructPhaseAction(Compilation &C, const ArgList &Args,

diff --git a/test/Driver/cuda-options.cu b/test/Driver/cuda-options.cu
index d673ab2bb59af52e54c4ce8af745e4cf8d2e4f29..5d650761fb2280c29bf30ee96389fc4c6d031cb8 100644 (file)
--- a/test/Driver/cuda-options.cu
+++ b/test/Driver/cuda-options.cu
@@ -22,23 +22,46 @@
 // RUN: | FileCheck -check-prefix NODEVICE -check-prefix HOST \
 // RUN:    -check-prefix NOINCLUDES-DEVICE -check-prefix LINK %s
 
-// Same test as above, but with preceeding --cuda-device-only to make sure only
-// the last option has an effect.
-// RUN: %clang -### -target x86_64-linux-gnu --cuda-device-only --cuda-host-only %s 2>&1 \
+// Verify that --cuda-device-only disables host-side compilation and linking.
+// RUN: %clang -### -target x86_64-linux-gnu --cuda-device-only %s 2>&1 \
+// RUN: | FileCheck -check-prefix DEVICE -check-prefix DEVICE-NOSAVE \
+// RUN:    -check-prefix NOHOST -check-prefix NOLINK %s
+
+// Check that the last of --cuda-compile-host-device, --cuda-host-only, and
+// --cuda-device-only wins.
+
+// RUN: %clang -### -target x86_64-linux-gnu --cuda-device-only \
+// RUN:    --cuda-host-only %s 2>&1 \
 // RUN: | FileCheck -check-prefix NODEVICE -check-prefix HOST \
 // RUN:    -check-prefix NOINCLUDES-DEVICE -check-prefix LINK %s
 
-// Verify that --cuda-device-only disables host-side compilation and linking.
-// RUN: %clang -### -target x86_64-linux-gnu --cuda-device-only %s 2>&1 \
+// RUN: %clang -### -target x86_64-linux-gnu --cuda-compile-host-device \
+// RUN:    --cuda-host-only %s 2>&1 \
+// RUN: | FileCheck -check-prefix NODEVICE -check-prefix HOST \
+// RUN:    -check-prefix NOINCLUDES-DEVICE -check-prefix LINK %s
+
+// RUN: %clang -### -target x86_64-linux-gnu --cuda-host-only \
+// RUN:    --cuda-device-only %s 2>&1 \
 // RUN: | FileCheck -check-prefix DEVICE -check-prefix DEVICE-NOSAVE \
 // RUN:    -check-prefix NOHOST -check-prefix NOLINK %s
 
-// Same test as above, but with preceeding --cuda-host-only to make sure only
-// the last option has an effect.
-// RUN: %clang -### -target x86_64-linux-gnu --cuda-host-only --cuda-device-only %s 2>&1 \
+// RUN: %clang -### -target x86_64-linux-gnu --cuda-compile-host-device \
+// RUN:    --cuda-device-only %s 2>&1 \
 // RUN: | FileCheck -check-prefix DEVICE -check-prefix DEVICE-NOSAVE \
 // RUN:    -check-prefix NOHOST -check-prefix NOLINK %s
 
+// RUN: %clang -### -target x86_64-linux-gnu --cuda-host-only \
+// RUN:   --cuda-compile-host-device %s 2>&1 \
+// RUN: | FileCheck -check-prefix DEVICE -check-prefix DEVICE-NOSAVE \
+// RUN:    -check-prefix HOST -check-prefix INCLUDES-DEVICE \
+// RUN:    -check-prefix LINK %s
+
+// RUN: %clang -### -target x86_64-linux-gnu --cuda-device-only \
+// RUN:   --cuda-compile-host-device %s 2>&1 \
+// RUN: | FileCheck -check-prefix DEVICE -check-prefix DEVICE-NOSAVE \
+// RUN:    -check-prefix HOST -check-prefix INCLUDES-DEVICE \
+// RUN:    -check-prefix LINK %s
+
 // Verify that --cuda-gpu-arch option passes the correct GPU archtecture to
 // device compilation.
 // RUN: %clang -### -target x86_64-linux-gnu --cuda-gpu-arch=sm_35 -c %s 2>&1 \

diff --git a/test/Driver/cuda-unused-arg-warning.cu b/test/Driver/cuda-unused-arg-warning.cu
index e8daad6cdaf6b572a518dec7ea4b7836825e7dd4..cbbb893129b6f3886fa022e92dcc1e529a760bc2 100644 (file)
--- a/test/Driver/cuda-unused-arg-warning.cu
+++ b/test/Driver/cuda-unused-arg-warning.cu
@@ -4,11 +4,16 @@
 // REQUIRES: x86-registered-target
 // REQUIRES: nvptx-registered-target
 
-// --cuda-host-only should never trigger unused arg warning.
+// --cuda-host-only and --cuda-compile-host-device should never trigger an
+// unused arg warning.
 // RUN: %clang -### -target x86_64-linux-gnu --cuda-host-only -c %s 2>&1 | \
 // RUN:    FileCheck %s
 // RUN: %clang -### -target x86_64-linux-gnu --cuda-host-only -x c -c %s 2>&1 | \
 // RUN:    FileCheck %s
+// RUN: %clang -### -target x86_64-linux-gnu --cuda-compile-host-device -c %s 2>&1 | \
+// RUN:    FileCheck %s
+// RUN: %clang -### -target x86_64-linux-gnu --cuda-compile-host-device -x c -c %s 2>&1 | \
+// RUN:    FileCheck %s
 
 // --cuda-device-only should warn during non-CUDA compilation.
 // RUN: %clang -### -target x86_64-linux-gnu --cuda-device-only -x c -c %s 2>&1 | \
@@ -19,5 +24,6 @@
 // RUN:    FileCheck -check-prefix NO-UNUSED-WARNING %s
 
 // CHECK-NOT: warning: argument unused during compilation: '--cuda-host-only'
+// CHECK-NOT: warning: argument unused during compilation: '--cuda-compile-host-device'
 // UNUSED-WARNING: warning: argument unused during compilation: '--cuda-device-only'
 // NO-UNUSED-WARNING-NOT: warning: argument unused during compilation: '--cuda-device-only'