[PGO][HIP] Linux HSA-introspection device drain on the profile_rocm reland

clang/lib/Driver/ToolChains/Clang.cpp

@@ -9864,6 +9864,21 @@ void LinkerWrapper::ConstructJob(Compilation &C, const JobAction &JA,
           (TC->getTriple().isAMDGPU() || TC->getTriple().isNVPTX()))
         LinkerArgs.emplace_back("-lompdevice");
 
+      // With PGO/coverage instrumentation, GPU device code references the
+      // device profile runtime (__llvm_profile_instrument_gpu and the
+      // __llvm_profile_sections bounds table emitted by
+      // InstrProfilingPlatformGPU). The offload device link does not otherwise
+      // pull it in, so forward the static device profile runtime to the GPU
+      // device linker. The archive is arch-suffixed, so pass its full path
+      // rather than a -l name.
+      if (ToolChain::needsProfileRT(Args) &&
+          (TC->getTriple().isAMDGPU() || TC->getTriple().isNVPTX())) {
+        std::string ProfileRT =
+            TC->getCompilerRT(Args, "profile", ToolChain::FT_Static);
+        if (TC->getVFS().exists(ProfileRT))
+          LinkerArgs.emplace_back(Args.MakeArgString(ProfileRT));
+      }
+
       // For SPIR-V, pass some extra flags to `spirv-link`, the out-of-tree
       // SPIR-V linker. `spirv-link` isn't called in LTO mode so restrict these
       // flags to normal compilation.

clang/lib/Driver/ToolChains/HIPAMD.cpp

@@ -19,6 +19,7 @@
 #include "clang/Options/Options.h"
 #include "llvm/Support/FileSystem.h"
 #include "llvm/Support/Path.h"
+#include "llvm/Support/VirtualFileSystem.h"
 #include "llvm/TargetParser/TargetParser.h"
 
 using namespace clang::driver;
@@ -152,6 +153,25 @@ void AMDGCN::Linker::constructLldCommand(Compilation &C, const JobAction &JA,
 
   LldArgs.push_back("--no-whole-archive");
 
+  // With PGO/coverage instrumentation, instrumented device code references the
+  // device profile runtime (__llvm_profile_instrument_gpu and the
+  // __llvm_profile_sections bounds table emitted by InstrProfilingPlatformGPU).
+  // The new-offload-driver path injects this in LinkerWrapper::ConstructJob, but
+  // HIP using the traditional offload path (e.g. on Windows, which does not
+  // route device linking through clang-linker-wrapper) reaches the device link
+  // here instead. Forward the static device profile runtime to this lld device
+  // link so the runtime is pulled in regardless of offload-driver/host OS. The
+  // archive is arch-suffixed, so pass its full path rather than a -l name.
+  if (ToolChain::needsProfileRT(Args)) {
+    std::string ProfileRT =
+        TC.getCompilerRT(Args, "profile", ToolChain::FT_Static);
+    // Use the ToolChain VFS (matches the new-offload-driver path in
+    // Clang.cpp) so overlay/virtual filesystems used by the driver are
+    // honored; llvm::sys::fs bypasses them and can wrongly skip the runtime.
+    if (TC.getVFS().exists(ProfileRT))
+      LldArgs.push_back(Args.MakeArgString(ProfileRT));
+  }
+
   const char *Lld = Args.MakeArgStringRef(getToolChain().GetProgramPath("lld"));
   C.addCommand(std::make_unique<Command>(JA, *this, ResponseFileSupport::None(),
                                          Lld, LldArgs, Inputs, Output));

compiler-rt/lib/profile/CMakeLists.txt

@@ -94,7 +94,12 @@ if (NOT COMPILER_RT_PROFILE_BAREMETAL)
     InstrProfilingValue.c
     )
   if(COMPILER_RT_BUILD_PROFILE_ROCM)
-    list(APPEND PROFILE_SOURCES InstrProfilingPlatformROCm.cpp)
+    # Linux uses HSA introspection (InstrProfilingPlatformROCm.cpp); Windows
+    # keeps the legacy host-shadow drain (InstrProfilingPlatformROCmWindows.cpp).
+    # Each is platform-guarded internally, so adding both is safe (the other
+    # platform compiles to an empty TU).
+    list(APPEND PROFILE_SOURCES InstrProfilingPlatformROCm.cpp
+         InstrProfilingPlatformROCmWindows.cpp)
   endif()
 endif()
 
@@ -181,7 +186,8 @@ if(COMPILER_RT_HAS_INTERCEPTION AND NOT COMPILER_RT_PROFILE_BAREMETAL
 endif()
 
 if(NOT PROFILE_HAS_HIP_INTERCEPTOR)
-  list(REMOVE_ITEM PROFILE_SOURCES InstrProfilingPlatformROCm.cpp)
+  list(REMOVE_ITEM PROFILE_SOURCES InstrProfilingPlatformROCm.cpp
+       InstrProfilingPlatformROCmWindows.cpp)
 endif()
 
 # Only advertise the ROCm interceptor to InstrProfilingFile.c when its
@@ -281,7 +287,8 @@ if(COMPILER_RT_BUILD_PROFILE_ROCM AND NOT COMPILER_RT_PROFILE_BAREMETAL
    AND TARGET RTSanitizerCommon.${COMPILER_RT_DEFAULT_TARGET_ARCH}
    AND TARGET RTSanitizerCommonLibc.${COMPILER_RT_DEFAULT_TARGET_ARCH})
 
-  set(PROFILE_ROCM_SOURCES ${PROFILE_SOURCES} InstrProfilingPlatformROCm.cpp)
+  set(PROFILE_ROCM_SOURCES ${PROFILE_SOURCES} InstrProfilingPlatformROCm.cpp
+      InstrProfilingPlatformROCmWindows.cpp)
 
   # Enables the device-collection call in InstrProfilingFile.c.
   set(PROFILE_ROCM_FLAGS ${EXTRA_FLAGS} -DCOMPILER_RT_BUILD_PROFILE_ROCM=1)