jhuber6 created this revision.
jhuber6 added reviewers: jdoerfert, tianshilei1992, tra, yaxunl,
JonChesterfield.
Herald added a project: All.
jhuber6 requested review of this revision.
Herald added subscribers: cfe-commits, sstefan1, MaskRay.
Herald added a project: clang.
Currently, we embed device code into the host to perform
multi-architecture linking and handling of device code. If the user
specified `-S -emit-llvm` then the embedded output will be textual
LLVM-IR. This is a problem because it can't be used by the LTO backend
and it makes reading the file confusing.
This patch changes the behaviour to only emit textual device IR if we
are in device only mode, that is, if the device code is presented
directly to the user instead of being embedded. Otherwise we should
always embed device bitcode instead.
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D141717
Files:
clang/lib/Driver/Driver.cpp
clang/test/Driver/openmp-offload-gpu.c
Index: clang/test/Driver/openmp-offload-gpu.c
===================================================================
--- clang/test/Driver/openmp-offload-gpu.c
+++ clang/test/Driver/openmp-offload-gpu.c
@@ -304,9 +304,16 @@
// CHECK-IR: "x86_64-unknown-linux-gnu" - "clang", inputs:
["[[INPUT_IR:.+]]"], output: "[[OBJECT:.+]]"
// CHECK-IR: "x86_64-unknown-linux-gnu" - "Offload::Linker", inputs:
["[[OBJECT]]"], output: "a.out"
-// RUN: %clang -### --target=x86_64-unknown-linux-gnu -emit-llvm -S
-fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda
-Xopenmp-target=nvptx64-nvidia-cuda -march=sm_52 -nogpulib %s 2>&1 | FileCheck
%s --check-prefix=CHECK-EMIT-LLVM-IR
+// RUN: %clang -### --target=x86_64-unknown-linux-gnu -emit-llvm -S
-fopenmp=libomp --offload-device-only \
+// RUN: -fopenmp-targets=nvptx64-nvidia-cuda
-Xopenmp-target=nvptx64-nvidia-cuda -march=sm_52 -nogpulib %s 2>&1 \
+// RUN: | FileCheck %s --check-prefix=CHECK-EMIT-LLVM-IR
// CHECK-EMIT-LLVM-IR: "-cc1"{{.*}}"-triple"
"nvptx64-nvidia-cuda"{{.*}}"-emit-llvm"
+// RUN: %clang -### --target=x86_64-unknown-linux-gnu -emit-llvm -S
-fopenmp=libomp \
+// RUN: -fopenmp-targets=nvptx64-nvidia-cuda
-Xopenmp-target=nvptx64-nvidia-cuda -march=sm_52 -nogpulib %s 2>&1 \
+// RUN: | FileCheck %s --check-prefix=CHECK-EMIT-LLVM-IR-BC
+// CHECK-EMIT-LLVM-IR-BC: "-cc1"{{.*}}"-triple"
"nvptx64-nvidia-cuda"{{.*}}"-emit-llvm-bc"
+
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda
-Xopenmp-target=nvptx64-nvida-cuda -march=sm_70 \
// RUN:
--libomptarget-nvptx-bc-path=%S/Inputs/libomptarget/libomptarget-new-nvptx-test.bc
\
// RUN: -nogpulib %s -o openmp-offload-gpu 2>&1 \
Index: clang/lib/Driver/Driver.cpp
===================================================================
--- clang/lib/Driver/Driver.cpp
+++ clang/lib/Driver/Driver.cpp
@@ -4633,8 +4633,11 @@
(Args.hasFlag(options::OPT_fgpu_rdc, options::OPT_fno_gpu_rdc,
false) ||
TargetDeviceOffloadKind == Action::OFK_OpenMP))) {
- types::ID Output =
- Args.hasArg(options::OPT_S) ? types::TY_LLVM_IR : types::TY_LLVM_BC;
+ types::ID Output = Args.hasArg(options::OPT_S) &&
+ (TargetDeviceOffloadKind == Action::OFK_None
||
+ offloadDeviceOnly())
+ ? types::TY_LLVM_IR
+ : types::TY_LLVM_BC;
return C.MakeAction<BackendJobAction>(Input, Output);
}
return C.MakeAction<BackendJobAction>(Input, types::TY_PP_Asm);
Index: clang/test/Driver/openmp-offload-gpu.c
===================================================================
--- clang/test/Driver/openmp-offload-gpu.c
+++ clang/test/Driver/openmp-offload-gpu.c
@@ -304,9 +304,16 @@
// CHECK-IR: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[INPUT_IR:.+]]"], output: "[[OBJECT:.+]]"
// CHECK-IR: "x86_64-unknown-linux-gnu" - "Offload::Linker", inputs: ["[[OBJECT]]"], output: "a.out"
-// RUN: %clang -### --target=x86_64-unknown-linux-gnu -emit-llvm -S -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target=nvptx64-nvidia-cuda -march=sm_52 -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-EMIT-LLVM-IR
+// RUN: %clang -### --target=x86_64-unknown-linux-gnu -emit-llvm -S -fopenmp=libomp --offload-device-only \
+// RUN: -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target=nvptx64-nvidia-cuda -march=sm_52 -nogpulib %s 2>&1 \
+// RUN: | FileCheck %s --check-prefix=CHECK-EMIT-LLVM-IR
// CHECK-EMIT-LLVM-IR: "-cc1"{{.*}}"-triple" "nvptx64-nvidia-cuda"{{.*}}"-emit-llvm"
+// RUN: %clang -### --target=x86_64-unknown-linux-gnu -emit-llvm -S -fopenmp=libomp \
+// RUN: -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target=nvptx64-nvidia-cuda -march=sm_52 -nogpulib %s 2>&1 \
+// RUN: | FileCheck %s --check-prefix=CHECK-EMIT-LLVM-IR-BC
+// CHECK-EMIT-LLVM-IR-BC: "-cc1"{{.*}}"-triple" "nvptx64-nvidia-cuda"{{.*}}"-emit-llvm-bc"
+
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target=nvptx64-nvida-cuda -march=sm_70 \
// RUN: --libomptarget-nvptx-bc-path=%S/Inputs/libomptarget/libomptarget-new-nvptx-test.bc \
// RUN: -nogpulib %s -o openmp-offload-gpu 2>&1 \
Index: clang/lib/Driver/Driver.cpp
===================================================================
--- clang/lib/Driver/Driver.cpp
+++ clang/lib/Driver/Driver.cpp
@@ -4633,8 +4633,11 @@
(Args.hasFlag(options::OPT_fgpu_rdc, options::OPT_fno_gpu_rdc,
false) ||
TargetDeviceOffloadKind == Action::OFK_OpenMP))) {
- types::ID Output =
- Args.hasArg(options::OPT_S) ? types::TY_LLVM_IR : types::TY_LLVM_BC;
+ types::ID Output = Args.hasArg(options::OPT_S) &&
+ (TargetDeviceOffloadKind == Action::OFK_None ||
+ offloadDeviceOnly())
+ ? types::TY_LLVM_IR
+ : types::TY_LLVM_BC;
return C.MakeAction<BackendJobAction>(Input, Output);
}
return C.MakeAction<BackendJobAction>(Input, types::TY_PP_Asm);
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
