[clang] 5a2d78b - [HIP] Add option -fgpu-inline-threshold

[Yaxun Liu via cfe-commits]

Author: Yaxun (Sam) Liu
Date: 2021-04-21T17:18:18-04:00
New Revision: 5a2d78b1639738fbde85248413c1cfd2df55683a

URL: https://github.com/llvm/llvm-project/commit/5a2d78b1639738fbde85248413c1cfd2df55683a
DIFF: https://github.com/llvm/llvm-project/commit/5a2d78b1639738fbde85248413c1cfd2df55683a.diff

LOG: [HIP] Add option -fgpu-inline-threshold

Add option -fgpu-inline-threshold for inline threshold for device compilation only.

Reviewed by: Artem Belevich

Differential Revision: https://reviews.llvm.org/D99233

Added: 
    

Modified: 
    clang/include/clang/Driver/Options.td
    clang/lib/Driver/ToolChains/Clang.cpp
    clang/test/Driver/hip-options.hip

Removed: 
    


################################################################################
diff  --git a/clang/include/clang/Driver/Options.td b/clang/include/clang/Driver/Options.td
index 648cfb0522e14..d17486b13504d 100644
--- a/clang/include/clang/Driver/Options.td
+++ b/clang/include/clang/Driver/Options.td
@@ -956,6 +956,9 @@ def gpu_max_threads_per_block_EQ : Joined<["--"], "gpu-max-threads-per-block=">,
   HelpText<"Default max threads per block for kernel launch bounds for HIP">,
   MarshallingInfoInt<LangOpts<"GPUMaxThreadsPerBlock">, "1024">,
   ShouldParseIf<hip.KeyPath>;
+def fgpu_inline_threshold_EQ : Joined<["-"], "fgpu-inline-threshold=">,
+  Flags<[HelpHidden]>,
+  HelpText<"Inline threshold for device compilation for CUDA/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">;

diff  --git a/clang/lib/Driver/ToolChains/Clang.cpp b/clang/lib/Driver/ToolChains/Clang.cpp
index 95ca99565351c..ddfdda82193fa 100644
--- a/clang/lib/Driver/ToolChains/Clang.cpp
+++ b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -6473,6 +6473,16 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
   if (IsHIP)
     CmdArgs.push_back("-fcuda-allow-variadic-functions");
 
+  if (IsCudaDevice || IsHIPDevice) {
+    StringRef InlineThresh =
+        Args.getLastArgValue(options::OPT_fgpu_inline_threshold_EQ);
+    if (!InlineThresh.empty()) {
+      std::string ArgStr =
+          std::string("-inline-threshold=") + InlineThresh.str();
+      CmdArgs.append({"-mllvm", Args.MakeArgStringRef(ArgStr)});
+    }
+  }
+
   // 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

diff  --git a/clang/test/Driver/hip-options.hip b/clang/test/Driver/hip-options.hip
index 99e9f0c247198..b592a9c837528 100644
--- a/clang/test/Driver/hip-options.hip
+++ b/clang/test/Driver/hip-options.hip
@@ -51,3 +51,8 @@
 // RUN:   --cuda-gpu-arch=gfx906  %s 2>&1 | FileCheck -check-prefix=CTA %s
 // CTA: clang{{.*}} "-triple" "x86_64-unknown-linux-gnu" {{.*}} "-mconstructor-aliases"
 // CTA-NOT: clang{{.*}} "-triple" "amdgcn-amd-amdhsa" {{.*}} "-mconstructor-aliases"
+
+// RUN: %clang -### -target x86_64-unknown-linux-gnu -nogpuinc -nogpulib \
+// RUN:   --offload-arch=gfx906 -fgpu-inline-threshold=1000 %s 2>&1 | FileCheck -check-prefix=THRESH %s
+// THRESH: clang{{.*}} "-triple" "amdgcn-amd-amdhsa" {{.*}} "-mllvm" "-inline-threshold=1000"
+// THRESH-NOT: clang{{.*}} "-triple" "x86_64-unknown-linux-gnu" {{.*}} "-inline-threshold=1000"