Recommit "[HIP] Add option --gpu-instrument-lib="

recommit 64f7790 after
fixing hip-device-libs.hip.

Author: yxsamliu

clang/include/clang/Driver/Options.td

@@ -672,6 +672,9 @@ defm gpu_allow_device_init : OptInFFlag<"gpu-allow-device-init",
 def gpu_max_threads_per_block_EQ : Joined<["--"], "gpu-max-threads-per-block=">,
   Flags<[CC1Option]>,
   HelpText<"Default max threads per block for kernel launch bounds for HIP">;
+def gpu_instrument_lib_EQ : Joined<["--"], "gpu-instrument-lib=">,
+  HelpText<"Instrument device library for HIP, which is a LLVM bitcode containing "
+  "__cyg_profile_func_enter and __cyg_profile_func_exit">;
 def libomptarget_nvptx_path_EQ : Joined<["--"], "libomptarget-nvptx-path=">, Group<i_Group>,
   HelpText<"Path to libomptarget-nvptx libraries">;
 def dD : Flag<["-"], "dD">, Group<d_Group>, Flags<[CC1Option]>,

clang/lib/Driver/ToolChains/HIP.cpp

@@ -330,6 +330,17 @@ void HIPToolChain::addClangTargetOptions(
     RocmInstallation.addCommonBitcodeLibCC1Args(
       DriverArgs, CC1Args, LibDeviceFile, Wave64, DAZ, FiniteOnly,
       UnsafeMathOpt, FastRelaxedMath, CorrectSqrt);
+
+    // Add instrument lib.
+    auto InstLib =
+        DriverArgs.getLastArgValue(options::OPT_gpu_instrument_lib_EQ);
+    if (InstLib.empty())
+      return;
+    if (llvm::sys::fs::exists(InstLib)) {
+      CC1Args.push_back("-mlink-builtin-bitcode");
+      CC1Args.push_back(DriverArgs.MakeArgString(InstLib));
+    } else
+      getDriver().Diag(diag::err_drv_no_such_file) << InstLib;
   }
 }
 

clang/test/Driver/Inputs/hip_multiple_inputs/instrument.bc

@@ -92,7 +92,7 @@
 
 // Test --hip-device-lib-path flag
 // RUN: %clang -### -target x86_64-linux-gnu \
-// RUN:   --cuda-gpu-arch=gfx803 \
+// RUN:   --cuda-gpu-arch=gfx803 -nogpuinc \
 // RUN:   --hip-device-lib-path=%S/Inputs/rocm/amdgcn/bitcode   \
 // RUN:   %S/Inputs/hip_multiple_inputs/b.hip \
 // RUN: 2>&1 | FileCheck %s --check-prefixes=ALL,FLUSHD
@@ -101,10 +101,19 @@
 // Test environment variable HIP_DEVICE_LIB_PATH
 // RUN: env HIP_DEVICE_LIB_PATH=%S/Inputs/rocm/amdgcn/bitcode \
 // RUN:   %clang -### -target x86_64-linux-gnu \
-// RUN:   --cuda-gpu-arch=gfx900 \
+// RUN:   --cuda-gpu-arch=gfx900 -nogpuinc \
 // RUN:   %S/Inputs/hip_multiple_inputs/b.hip \
 // RUN: 2>&1 | FileCheck %s --check-prefixes=ALL
 
+// Test --gpu-instrument-lib
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   --cuda-gpu-arch=gfx900 \
+// RUN:   --rocm-path=%S/Inputs/rocm \
+// RUN:   --gpu-instrument-lib=%S/Inputs/hip_multiple_inputs/instrument.bc \
+// RUN:   %S/Inputs/hip_multiple_inputs/b.hip \
+// RUN: 2>&1 | FileCheck %s --check-prefixes=ALL,INST
+
+// ALL-NOT: error:
 // ALL: {{"[^"]*clang[^"]*"}}
 // ALL-SAME: "-mlink-builtin-bitcode" "{{.*}}hip.bc"
 // ALL-SAME: "-mlink-builtin-bitcode" "{{.*}}ocml.bc"
@@ -118,3 +127,4 @@
 // ALL-SAME: "-mlink-builtin-bitcode" "{{.*}}oclc_correctly_rounded_sqrt_on.bc"
 // ALL-SAME: "-mlink-builtin-bitcode" "{{.*}}oclc_wavefrontsize64_on.bc"
 // ALL-SAME: "-mlink-builtin-bitcode" "{{.*}}oclc_isa_version_{{[0-9]+}}.bc"
+// INST-SAME: "-mlink-builtin-bitcode" "{{.*}}instrument.bc"