yaxunl created this revision.
yaxunl added reviewers: t-tye, tra.
Add .stub to kernel stub function name so that it is different from kernel
name in device code. This is necessary to let debugger find correct symbol
for kernel
https://reviews.llvm.org/D58518
Files:
lib/CodeGen/CGCUDANV.cpp
test/CodeGenCUDA/device-stub.cu
Index: test/CodeGenCUDA/device-stub.cu
===================================================================
--- test/CodeGenCUDA/device-stub.cu
+++ test/CodeGenCUDA/device-stub.cu
@@ -145,7 +145,8 @@
// Test that we build the correct number of calls to cudaSetupArgument followed
// by a call to cudaLaunch.
-// LNX: define{{.*}}kernelfunc
+// CUDA-LABEL: define{{.*}}kernelfunc
+// HIP-LABEL: define{{.*}}@_Z10kernelfunciii.stub
// New launch sequence stores arguments into local buffer and passes array of
// pointers to them directly to cudaLaunchKernel
Index: lib/CodeGen/CGCUDANV.cpp
===================================================================
--- lib/CodeGen/CGCUDANV.cpp
+++ lib/CodeGen/CGCUDANV.cpp
@@ -227,6 +227,8 @@
emitDeviceStubBodyNew(CGF, Args);
else
emitDeviceStubBodyLegacy(CGF, Args);
+ if (CGF.getLangOpts().HIP)
+ CGF.CurFn->setName(CGF.CurFn->getName() + ".stub");
}
// CUDA 9.0+ uses new way to launch kernels. Parameters are packed in a local
Index: test/CodeGenCUDA/device-stub.cu
===================================================================
--- test/CodeGenCUDA/device-stub.cu
+++ test/CodeGenCUDA/device-stub.cu
@@ -145,7 +145,8 @@
// Test that we build the correct number of calls to cudaSetupArgument followed
// by a call to cudaLaunch.
-// LNX: define{{.*}}kernelfunc
+// CUDA-LABEL: define{{.*}}kernelfunc
+// HIP-LABEL: define{{.*}}@_Z10kernelfunciii.stub
// New launch sequence stores arguments into local buffer and passes array of
// pointers to them directly to cudaLaunchKernel
Index: lib/CodeGen/CGCUDANV.cpp
===================================================================
--- lib/CodeGen/CGCUDANV.cpp
+++ lib/CodeGen/CGCUDANV.cpp
@@ -227,6 +227,8 @@
emitDeviceStubBodyNew(CGF, Args);
else
emitDeviceStubBodyLegacy(CGF, Args);
+ if (CGF.getLangOpts().HIP)
+ CGF.CurFn->setName(CGF.CurFn->getName() + ".stub");
}
// CUDA 9.0+ uses new way to launch kernels. Parameters are packed in a local
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
