jhuber6 created this revision.
jhuber6 added reviewers: jdoerfert, JonChesterfield, MaskRay, ggeorgakoudis,
tianshilei1992.
Herald added subscribers: StephenFan, guansong, yaxunl.
Herald added a project: All.
jhuber6 requested review of this revision.
Herald added subscribers: cfe-commits, sstefan1.
Herald added a project: clang.
JIT support for OpenMP offloading was introduced in D139287
<https://reviews.llvm.org/D139287>. This patch
adds a simple flag that enables this mode. It simply requires enabling
`-foffload-lto` mode and `--embed-bitcode` in the linker wrapper. This
option implies LTO if it is not enabled.
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D141158
Files:
clang/include/clang/Driver/Options.td
clang/lib/Driver/Driver.cpp
clang/lib/Driver/ToolChains/Clang.cpp
clang/test/Driver/openmp-offload-jit.c
Index: clang/test/Driver/openmp-offload-jit.c
===================================================================
--- /dev/null
+++ clang/test/Driver/openmp-offload-jit.c
@@ -0,0 +1,42 @@
+// 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"
Index: clang/lib/Driver/ToolChains/Clang.cpp
===================================================================
--- clang/lib/Driver/ToolChains/Clang.cpp
+++ clang/lib/Driver/ToolChains/Clang.cpp
@@ -8428,6 +8428,10 @@
}
Args.ClaimAllArgs(options::OPT_Xoffload_linker);
+ // Embed bitcode instead of an object in JIT mode.
+ if (const Arg *A = Args.getLastArg(options::OPT_fopenmp_target_jit))
+ CmdArgs.push_back("--embed-bitcode");
+
// Forward `-mllvm` arguments to the LLVM invocations if present.
for (Arg *A : Args.filtered(options::OPT_mllvm)) {
CmdArgs.push_back("-mllvm");
Index: clang/lib/Driver/Driver.cpp
===================================================================
--- clang/lib/Driver/Driver.cpp
+++ clang/lib/Driver/Driver.cpp
@@ -721,6 +721,13 @@
OffloadLTOMode = parseLTOMode(*this, Args, options::OPT_foffload_lto_EQ,
options::OPT_fno_offload_lto);
+
+ // Enable `-foffload-lto=full` if `-fopenmp-target-jit` is on.
+ if (OffloadLTOMode == LTOK_None || OffloadLTOMode == LTOK_Unknown)
+ OffloadLTOMode = Args.hasFlag(options::OPT_fopenmp_target_jit,
+ options::OPT_fno_openmp_target_jit, false)
+ ? LTOK_Full
+ : OffloadLTOMode;
}
/// Compute the desired OpenMP runtime from the flags provided.
Index: clang/include/clang/Driver/Options.td
===================================================================
--- clang/include/clang/Driver/Options.td
+++ clang/include/clang/Driver/Options.td
@@ -2652,6 +2652,11 @@
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">,
Index: clang/test/Driver/openmp-offload-jit.c
===================================================================
--- /dev/null
+++ clang/test/Driver/openmp-offload-jit.c
@@ -0,0 +1,42 @@
+// 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"
Index: clang/lib/Driver/ToolChains/Clang.cpp
===================================================================
--- clang/lib/Driver/ToolChains/Clang.cpp
+++ clang/lib/Driver/ToolChains/Clang.cpp
@@ -8428,6 +8428,10 @@
}
Args.ClaimAllArgs(options::OPT_Xoffload_linker);
+ // Embed bitcode instead of an object in JIT mode.
+ if (const Arg *A = Args.getLastArg(options::OPT_fopenmp_target_jit))
+ CmdArgs.push_back("--embed-bitcode");
+
// Forward `-mllvm` arguments to the LLVM invocations if present.
for (Arg *A : Args.filtered(options::OPT_mllvm)) {
CmdArgs.push_back("-mllvm");
Index: clang/lib/Driver/Driver.cpp
===================================================================
--- clang/lib/Driver/Driver.cpp
+++ clang/lib/Driver/Driver.cpp
@@ -721,6 +721,13 @@
OffloadLTOMode = parseLTOMode(*this, Args, options::OPT_foffload_lto_EQ,
options::OPT_fno_offload_lto);
+
+ // Enable `-foffload-lto=full` if `-fopenmp-target-jit` is on.
+ if (OffloadLTOMode == LTOK_None || OffloadLTOMode == LTOK_Unknown)
+ OffloadLTOMode = Args.hasFlag(options::OPT_fopenmp_target_jit,
+ options::OPT_fno_openmp_target_jit, false)
+ ? LTOK_Full
+ : OffloadLTOMode;
}
/// Compute the desired OpenMP runtime from the flags provided.
Index: clang/include/clang/Driver/Options.td
===================================================================
--- clang/include/clang/Driver/Options.td
+++ clang/include/clang/Driver/Options.td
@@ -2652,6 +2652,11 @@
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">,
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
