[PATCH] D77398: [cuda][hip] Fix `RegisterVar` function prototype.

[Michael Liao via Phabricator via cfe-commits]

hliao created this revision.
hliao added reviewers: tra, yaxunl.
Herald added a project: clang.
Herald added a subscriber: cfe-commits.

- `RegisterVar` has `void` return type and `size_t` in its variable size parameter in HIP or CUDA 9.0+.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D77398

Files:
  clang/include/clang/Basic/Cuda.h
  clang/lib/Basic/Cuda.cpp
  clang/lib/CodeGen/CGCUDANV.cpp
  clang/test/CodeGenCUDA/device-stub.cu


Index: clang/test/CodeGenCUDA/device-stub.cu
===================================================================
--- clang/test/CodeGenCUDA/device-stub.cu
+++ clang/test/CodeGenCUDA/device-stub.cu
@@ -181,10 +181,10 @@
 // Test that we've built a function to register kernels and global vars.
 // ALL: define internal void @__[[PREFIX]]_register_globals
 // ALL: call{{.*}}[[PREFIX]]RegisterFunction(i8** %0, {{.*}}kernelfunc{{[^,]*}}, {{[^@]*}}@0
-// ALL-DAG: call{{.*}}[[PREFIX]]RegisterVar(i8** %0, {{.*}}device_var{{[^,]*}}, {{[^@]*}}@1, {{.*}}i32 0, i32 4, i32 0, i32 0
-// ALL-DAG: call{{.*}}[[PREFIX]]RegisterVar(i8** %0, {{.*}}constant_var{{[^,]*}}, {{[^@]*}}@2, {{.*}}i32 0, i32 4, i32 1, i32 0
-// ALL-DAG: call{{.*}}[[PREFIX]]RegisterVar(i8** %0, {{.*}}ext_device_var_def{{[^,]*}}, {{[^@]*}}@3, {{.*}}i32 0, i32 4, i32 0, i32 0
-// ALL-DAG: call{{.*}}[[PREFIX]]RegisterVar(i8** %0, {{.*}}ext_constant_var_def{{[^,]*}}, {{[^@]*}}@4, {{.*}}i32 0, i32 4, i32 1, i32 0
+// ALL-DAG: call void {{.*}}[[PREFIX]]RegisterVar(i8** %0, {{.*}}device_var{{[^,]*}}, {{[^@]*}}@1, {{.*}}i32 0, {{i32|i64}} 4, i32 0, i32 0
+// ALL-DAG: call void {{.*}}[[PREFIX]]RegisterVar(i8** %0, {{.*}}constant_var{{[^,]*}}, {{[^@]*}}@2, {{.*}}i32 0, {{i32|i64}} 4, i32 1, i32 0
+// ALL-DAG: call void {{.*}}[[PREFIX]]RegisterVar(i8** %0, {{.*}}ext_device_var_def{{[^,]*}}, {{[^@]*}}@3, {{.*}}i32 0, {{i32|i64}} 4, i32 0, i32 0
+// ALL-DAG: call void {{.*}}[[PREFIX]]RegisterVar(i8** %0, {{.*}}ext_constant_var_def{{[^,]*}}, {{[^@]*}}@4, {{.*}}i32 0, {{i32|i64}} 4, i32 1, i32 0
 // ALL: ret void
 
 // Test that we've built a constructor.
Index: clang/lib/CodeGen/CGCUDANV.cpp
===================================================================
--- clang/lib/CodeGen/CGCUDANV.cpp
+++ clang/lib/CodeGen/CGCUDANV.cpp
@@ -440,13 +440,19 @@
     Builder.CreateCall(RegisterFunc, Args);
   }
 
+  llvm::Type *VarSizeTy = IntTy;
+  // For HIP or CUDA 9.0+, device variable size is type of `size_t`.
+  if (CGM.getLangOpts().HIP ||
+      ToCudaVersion(CGM.getTarget().getSDKVersion()) >= CudaVersion::CUDA_90)
+    VarSizeTy = SizeTy;
+
   // void __cudaRegisterVar(void **, char *, char *, const char *,
   //                        int, int, int, int)
   llvm::Type *RegisterVarParams[] = {VoidPtrPtrTy, CharPtrTy, CharPtrTy,
-                                     CharPtrTy,    IntTy,     IntTy,
+                                     CharPtrTy,    IntTy,     VarSizeTy,
                                      IntTy,        IntTy};
   llvm::FunctionCallee RegisterVar = CGM.CreateRuntimeFunction(
-      llvm::FunctionType::get(IntTy, RegisterVarParams, false),
+      llvm::FunctionType::get(VoidTy, RegisterVarParams, false),
       addUnderscoredPrefixToName("RegisterVar"));
   // void __cudaRegisterSurface(void **, const struct surfaceReference *,
   //                            const void **, const char *, int, int);
@@ -476,7 +482,7 @@
           VarName,
           VarName,
           llvm::ConstantInt::get(IntTy, Info.Flags.isExtern()),
-          llvm::ConstantInt::get(IntTy, VarSize),
+          llvm::ConstantInt::get(VarSizeTy, VarSize),
           llvm::ConstantInt::get(IntTy, Info.Flags.isConstant()),
           llvm::ConstantInt::get(IntTy, 0)};
       Builder.CreateCall(RegisterVar, Args);
Index: clang/lib/Basic/Cuda.cpp
===================================================================
--- clang/lib/Basic/Cuda.cpp
+++ clang/lib/Basic/Cuda.cpp
@@ -365,7 +365,7 @@
   }
 }
 
-static CudaVersion ToCudaVersion(llvm::VersionTuple Version) {
+CudaVersion ToCudaVersion(llvm::VersionTuple Version) {
   int IVer =
       Version.getMajor() * 10 + Version.getMinor().getValueOr(0);
   switch(IVer) {
Index: clang/include/clang/Basic/Cuda.h
===================================================================
--- clang/include/clang/Basic/Cuda.h
+++ clang/include/clang/Basic/Cuda.h
@@ -118,6 +118,7 @@
   CUDA_USES_FATBIN_REGISTER_END,
 };
 
+CudaVersion ToCudaVersion(llvm::VersionTuple);
 bool CudaFeatureEnabled(llvm::VersionTuple, CudaFeature);
 bool CudaFeatureEnabled(CudaVersion, CudaFeature);
 


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D77398.254796.patch
Type: text/x-patch
Size: 4104 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20200403/4267aa9d/attachment.bin>