[hip] Allow the declaration of functions with variadic arguments in HIP.

[hliao]

Summary

• As variadic parameters have the lowest rank in overload resolution, without real usage of va_arg, they are commonly used as the catch-all fallbacks in SFINAE. As the front-end still reports errors on calls to va_arg, the declaration of functions with variadic arguments should be allowed in general.

[hliao]

revise commit message

[tra]

clang/lib/CodeGen/TargetInfo.cpp

7764

llvm_unreachable() should be used to indicate an error in compiler's own code, not in the user code that we're compiling.

I think what you need to do is to issue a postponed diagnostics in Sema where we're currently checking for varargs functions and materialize them if we attempt to codegen such function.

[hliao]

clang/lib/CodeGen/TargetInfo.cpp

7764

this is just a stub to assert that there won't be codegen for va_arg. the real diagnosing is @ lib/Sema/SemaExpr.cpp around L14438. I just want to add an assertion to capture them if anything goes wrong. Error on va_arg use is already there for a while.

[tra]

Perhaps we should rename -fcuda-allow-variadic-functions to -fgpu-allow-variadic-functions after this patch.

clang/lib/CodeGen/TargetInfo.cpp

public:
   explicit AMDGPUABIInfo(CodeGen::CodeGenTypes &CGT) :
     DefaultABIInfo(CGT) {}
 
   ABIArgInfo classifyReturnType(QualType RetTy) const;
   ABIArgInfo classifyKernelArgumentType(QualType Ty) const;
   ABIArgInfo classifyArgumentType(QualType Ty, unsigned &NumRegsLeft) const;
 
   void computeInfo(CGFunctionInfo &FI) const override;
+  Address EmitVAArg(CodeGenFunction &CGF, Address VAListAddr,
+                    QualType Ty) const override;
 };
 
 bool AMDGPUABIInfo::isHomogeneousAggregateBaseType(QualType Ty) const {
   return true;
 }
 
 bool AMDGPUABIInfo::isHomogeneousAggregateSmallEnough(
   const Type *Base, uint64_t Members) const {
for (auto &Arg : FI.arguments()) {
     if (CC == llvm::CallingConv::AMDGPU_KERNEL) {
       Arg.info = classifyKernelArgumentType(Arg.type);
     } else {
       Arg.info = classifyArgumentType(Arg.type, NumRegsLeft);
     }
   }
 }
 
+Address AMDGPUABIInfo::EmitVAArg(CodeGenFunction &CGF, Address VAListAddr,
+                                 QualType Ty) const {
+  llvm_unreachable("AMDGPU does not support varargs");
+}
+
 ABIArgInfo AMDGPUABIInfo::classifyReturnType(QualType RetTy) const {
   if (isAggregateTypeForABI(RetTy)) {
     // Records with non-trivial destructors/copy-constructors should not be
     // returned by value.
     if (!getRecordArgABI(RetTy, getCXXABI())) {
       // Ignore empty structs/unions.
       if (isEmptyRecord(getContext(), RetTy, true))
         return ABIArgInfo::getIgnore();

clang/lib/Driver/ToolChains/Clang.cpp

   }
 
   if (IsCuda) {
     if (Args.hasFlag(options::OPT_fcuda_short_ptr,
                      options::OPT_fno_cuda_short_ptr, false))
       CmdArgs.push_back("-fcuda-short-ptr");
   }
 
+  if (IsHIP)
+    CmdArgs.push_back("-fcuda-allow-variadic-functions");
+
   // OpenMP offloading device jobs take the argument -fopenmp-host-ir-file-path
   // to specify the result of the compile phase on the host, so the meaningful
   // device declarations can be identified. Also, -fopenmp-is-device is passed
   // along to tell the frontend that it is generating code for a device, so that
   // only the relevant declarations are emitted.
   if (IsOpenMPDevice) {
     CmdArgs.push_back("-fopenmp-is-device");
     if (OpenMPDeviceInput) {

clang/lib/Driver/ToolChains/HIP.cpp

void HIPToolChain::addClangTargetOptions(
   if (DriverArgs.hasFlag(options::OPT_fgpu_rdc, options::OPT_fno_gpu_rdc,
                          false))
     CC1Args.push_back("-fgpu-rdc");
 
   if (DriverArgs.hasFlag(options::OPT_fgpu_allow_device_init,
                          options::OPT_fno_gpu_allow_device_init, false))
     CC1Args.push_back("-fgpu-allow-device-init");
 
+  CC1Args.push_back("-fcuda-allow-variadic-functions");
+
   // Default to "hidden" visibility, as object level linking will not be
   // supported for the foreseeable future.
   if (!DriverArgs.hasArg(options::OPT_fvisibility_EQ,
                          options::OPT_fvisibility_ms_compat)) {
     CC1Args.append({"-fvisibility", "hidden"});
     CC1Args.push_back("-fapply-global-visibility-to-externs");
   }
 

clang/test/Driver/hip-toolchain-no-rdc.hip

 //
 // Compile device code in a.cu to code object for gfx803.
 //
 
 // CHECK: [[CLANG:".*clang.*"]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // CHECK-SAME: "-emit-llvm-bc"
 // CHECK-SAME: {{.*}} "-main-file-name" "a.cu" {{.*}} "-target-cpu" "gfx803"
-// CHECK-SAME: "-fcuda-is-device" "-fvisibility" "hidden"
+// CHECK-SAME: "-fcuda-is-device" "-fcuda-allow-variadic-functions" "-fvisibility" "hidden"
 // CHECK-SAME: "-fapply-global-visibility-to-externs"
 // CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
 // CHECK-SAME: {{.*}} "-o" [[A_BC_803:".*bc"]] "-x" "hip"
 // CHECK-SAME: {{.*}} [[A_SRC:".*a.cu"]]
 
 // CHECK: [[LLVM_LINK:"*.llvm-link"]] [[A_BC_803]]
 // CHECK-SAME: "-o" [[LINKED_BC_DEV_A_803:".*-gfx803-linked-.*bc"]]
 

 //
 // Compile device code in a.cu to code object for gfx900.
 //
 
 // CHECK: [[CLANG:".*clang.*"]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // CHECK-SAME: "-emit-llvm-bc"
 // CHECK-SAME: {{.*}} "-main-file-name" "a.cu" {{.*}} "-target-cpu" "gfx900"
-// CHECK-SAME: "-fcuda-is-device" "-fvisibility" "hidden"
+// CHECK-SAME: "-fcuda-is-device" "-fcuda-allow-variadic-functions" "-fvisibility" "hidden"
 // CHECK-SAME: "-fapply-global-visibility-to-externs"
 // CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
 // CHECK-SAME: {{.*}} "-o" [[A_BC_900:".*bc"]] "-x" "hip"
 // CHECK-SAME: {{.*}} [[A_SRC]]
 
 // CHECK: [[LLVM_LINK:"*.llvm-link"]] [[A_BC_900]]
 // CHECK-SAME: "-o" [[LINKED_BC_DEV_A_900:".*-gfx900-linked-.*bc"]]
 

 //
 // Compile device code in b.hip to code object for gfx803.
 //
 
 // CHECK: [[CLANG:".*clang.*"]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // CHECK-SAME: "-emit-llvm-bc"
 // CHECK-SAME: {{.*}} "-main-file-name" "b.hip" {{.*}} "-target-cpu" "gfx803"
-// CHECK-SAME: "-fcuda-is-device" "-fvisibility" "hidden"
+// CHECK-SAME: "-fcuda-is-device" "-fcuda-allow-variadic-functions" "-fvisibility" "hidden"
 // CHECK-SAME: "-fapply-global-visibility-to-externs"
 // CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
 // CHECK-SAME: {{.*}} "-o" [[B_BC_803:".*bc"]] "-x" "hip"
 // CHECK-SAME: {{.*}} [[B_SRC:".*b.hip"]]
 
 // CHECK: [[LLVM_LINK:"*.llvm-link"]] [[B_BC_803]]
 // CHECK-SAME: "-o" [[LINKED_BC_DEV_B_803:".*-gfx803-linked-.*bc"]]
 

 //
 // Compile device code in b.hip to code object for gfx900.
 //
 
 // CHECK: [[CLANG:".*clang.*"]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // CHECK-SAME: "-emit-llvm-bc"
 // CHECK-SAME: {{.*}} "-main-file-name" "b.hip" {{.*}} "-target-cpu" "gfx900"
-// CHECK-SAME: "-fcuda-is-device" "-fvisibility" "hidden"
+// CHECK-SAME: "-fcuda-is-device" "-fcuda-allow-variadic-functions" "-fvisibility" "hidden"
 // CHECK-SAME: "-fapply-global-visibility-to-externs"
 // CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
 // CHECK-SAME: {{.*}} "-o" [[B_BC_900:".*bc"]] "-x" "hip"
 // CHECK-SAME: {{.*}} [[B_SRC]]
 
 // CHECK: [[LLVM_LINK:"*.llvm-link"]] [[B_BC_900]]
 // CHECK-SAME: "-o" [[LINKED_BC_DEV_B_900:".*-gfx900-linked-.*bc"]]
 

clang/test/Driver/hip-toolchain-rdc.hip

 // RUN:   %S/Inputs/hip_multiple_inputs/a.cu \
 // RUN:   %S/Inputs/hip_multiple_inputs/b.hip \
 // RUN: 2>&1 | FileCheck %s
 
 // CHECK: [[CLANG:".*clang.*"]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // CHECK-SAME: "-emit-llvm-bc"
 // CHECK-SAME: {{.*}} "-main-file-name" "a.cu" {{.*}} "-target-cpu" "gfx803"
-// CHECK-SAME: "-fcuda-is-device" "-fgpu-rdc" "-fvisibility" "hidden"
+// CHECK-SAME: "-fcuda-is-device" "-fgpu-rdc" "-fcuda-allow-variadic-functions" "-fvisibility" "hidden"
 // CHECK-SAME: "-fapply-global-visibility-to-externs"
 // CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
 // CHECK-SAME: {{.*}} "-o" [[A_BC:".*bc"]] "-x" "hip"
 // CHECK-SAME: {{.*}} [[A_SRC:".*a.cu"]]
 
 // CHECK: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // CHECK-SAME: "-emit-llvm-bc"
 // CHECK-SAME: {{.*}} "-main-file-name" "b.hip" {{.*}} "-target-cpu" "gfx803"
-// CHECK-SAME: "-fcuda-is-device" "-fgpu-rdc" "-fvisibility" "hidden"
+// CHECK-SAME: "-fcuda-is-device" "-fgpu-rdc" "-fcuda-allow-variadic-functions" "-fvisibility" "hidden"
 // CHECK-SAME: "-fapply-global-visibility-to-externs"
 // CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
 // CHECK-SAME: {{.*}} "-o" [[B_BC:".*bc"]] "-x" "hip"
 // CHECK-SAME: {{.*}} [[B_SRC:".*b.hip"]]
 
 // CHECK: [[LLVM_LINK:"*.llvm-link"]] [[A_BC]] [[B_BC]]
 // CHECK-SAME: "-o" [[LINKED_BC_DEV1:".*-gfx803-linked-.*bc"]]