Add option -fgpu-inline-threshold for inline threshold for device compilation only.
Reviewed by: Artem Belevich
Differential Revision: https://reviews.llvm.org/D99233
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">;
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
// 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"