Flags<[CC1Option, NoArgumentUnused]>,
HelpText<"Do not create a host fallback if offloading to the device fails.">,
MarshallingInfoFlag<LangOpts<"OpenMPOffloadMandatory">>;
+def fopenmp_target_jit : Flag<["-"], "fopenmp-target-jit">, Group<f_Group>,
+ Flags<[CoreOption, NoArgumentUnused]>,
+ HelpText<"Emit code that can be JIT compiled for OpenMP offloading. Implies -foffload-lto=full">;
+def fno_openmp_target_jit : Flag<["-"], "fno-openmp-target-jit">, Group<f_Group>,
+ Flags<[CoreOption, NoArgumentUnused, HelpHidden]>;
def fopenmp_target_new_runtime : Flag<["-"], "fopenmp-target-new-runtime">,
Group<f_Group>, Flags<[CC1Option, HelpHidden]>;
def fno_openmp_target_new_runtime : Flag<["-"], "fno-openmp-target-new-runtime">,
OffloadLTOMode = parseLTOMode(*this, Args, options::OPT_foffload_lto_EQ,
options::OPT_fno_offload_lto);
+
+ // Try to enable `-foffload-lto=full` if `-fopenmp-target-jit` is on.
+ if (Args.hasFlag(options::OPT_fopenmp_target_jit,
+ options::OPT_fno_openmp_target_jit, false)) {
+ if (Arg *A = Args.getLastArg(options::OPT_foffload_lto_EQ,
+ options::OPT_fno_offload_lto))
+ if (OffloadLTOMode != LTOK_Full)
+ Diag(diag::err_drv_incompatible_options)
+ << A->getSpelling() << "-fopenmp-target-jit";
+ OffloadLTOMode = LTOK_Full;
+ }
}
/// Compute the desired OpenMP runtime from the flags provided.
--- /dev/null
+// REQUIRES: x86-registered-target
+// REQUIRES: nvptx-registered-target
+// REQUIRES: amdgpu-registered-target
+
+// Check that we enable LTO-mode properly with '-fopenmp-target-jit' and that it
+// still enabled LTO-mode if `-fno-offload-lto` is on.
+// RUN: %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-phases -fopenmp \
+// RUN: -fopenmp-targets=nvptx64-nvidia-cuda -fopenmp-target-jit %s 2>&1 \
+// RUN: | FileCheck -check-prefix=PHASES-JIT %s
+// RUN: %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-phases -fopenmp \
+// RUN: -fopenmp-targets=nvptx64-nvidia-cuda -foffload-lto -fopenmp-target-jit %s 2>&1 \
+// RUN: | FileCheck -check-prefix=PHASES-JIT %s
+// RUN: %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-phases -fopenmp \
+// RUN: -fopenmp-targets=amdgcn-amd-amdhsa -fopenmp-target-jit %s 2>&1 \
+// RUN: | FileCheck -check-prefix=PHASES-JIT %s
+// RUN: %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-phases -fopenmp \
+// RUN: -fopenmp-targets=amdgcn-amd-amdhsa -foffload-lto -fopenmp-target-jit %s 2>&1 \
+// RUN: | FileCheck -check-prefix=PHASES-JIT %s
+// RUN: %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-phases -fopenmp \
+// RUN: -fopenmp-targets=amdgcn-amd-amdhsa -fno-offload-lto -fopenmp-target-jit %s 2>&1 \
+// RUN: | FileCheck -check-prefix=PHASES-JIT %s
+//
+// PHASES-JIT: 0: input, "[[INPUT:.+]]", c, (host-openmp)
+// PHASES-JIT-NEXT: 1: preprocessor, {0}, cpp-output, (host-openmp)
+// PHASES-JIT-NEXT: 2: compiler, {1}, ir, (host-openmp)
+// PHASES-JIT-NEXT: 3: input, "[[INPUT]]", c, (device-openmp)
+// PHASES-JIT-NEXT: 4: preprocessor, {3}, cpp-output, (device-openmp)
+// PHASES-JIT-NEXT: 5: compiler, {4}, ir, (device-openmp)
+// PHASES-JIT-NEXT: 6: offload, "host-openmp (x86_64-unknown-linux-gnu)" {2}, "device-openmp ([[TARGET:.+]])" {5}, ir
+// PHASES-JIT-NEXT: 7: backend, {6}, lto-bc, (device-openmp)
+// PHASES-JIT-NEXT: 8: offload, "device-openmp ([[TARGET]])" {7}, lto-bc
+// PHASES-JIT-NEXT: 9: clang-offload-packager, {8}, image, (device-openmp)
+// PHASES-JIT-NEXT: 10: offload, "host-openmp (x86_64-unknown-linux-gnu)" {2}, "device-openmp (x86_64-unknown-linux-gnu)" {9}, ir
+// PHASES-JIT-NEXT: 11: backend, {10}, assembler, (host-openmp)
+// PHASES-JIT-NEXT: 12: assembler, {11}, object, (host-openmp)
+// PHASES-JIT-NEXT: 13: clang-linker-wrapper, {12}, image, (host-openmp)
+
+// Check that we add the `--embed-bitcode` flag to the linker wrapper.
+// RUN: %clang -### --target=x86_64-unknown-linux-gnu -fopenmp \
+// RUN: -fopenmp-targets=nvptx64-nvidia-cuda -fopenmp-target-jit %s 2>&1 \
+// RUN: | FileCheck -check-prefix=LINKER %s
+// LINKER: clang-linker-wrapper"{{.*}}"--embed-bitcode"
+
+// Check for incompatible combinations
+
+// RUN: %clang -### --target=x86_64-unknown-linux-gnu -fopenmp -fno-offload-lto \
+// RUN: -fopenmp-targets=nvptx64-nvidia-cuda -fopenmp-target-jit %s 2>&1 \
+// RUN: | FileCheck -check-prefix=NO-LTO %s
+// NO-LTO: error: The combination of '-fno-offload-lto' and '-fopenmp-target-jit' is incompatible
+
+// RUN: %clang -### --target=x86_64-unknown-linux-gnu -fopenmp -foffload-lto=thin \
+// RUN: -fopenmp-targets=nvptx64-nvidia-cuda -fopenmp-target-jit %s 2>&1 \
+// RUN: | FileCheck -check-prefix=THIN-LTO %s
+// THIN-LTO: error: The combination of '-foffload-lto=' and '-fopenmp-target-jit' is incompatible