This revision was landed with ongoing or failed builds.
This revision was automatically updated to reflect the committed changes.
Closed by commit rG12ae095bbb63: [OpenMP] Embed device files into the host IR
(authored by jhuber6).
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D116543/new/
https://reviews.llvm.org/D116543
Files:
clang/lib/Driver/ToolChains/Clang.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
@@ -360,3 +360,10 @@
// NEW_DRIVER: "nvptx64-nvidia-cuda" - "NVPTX::Assembler", inputs:
["[[DEVICE_ASM]]"], output: "[[DEVICE_OBJ:.+]]"
// NEW_DRIVER: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[HOST_BC]]",
"[[DEVICE_OBJ]]"], output: "[[HOST_OBJ:.+]]"
// NEW_DRIVER: "x86_64-unknown-linux-gnu" - "[[LINKER:.+]]", inputs:
["[[HOST_OBJ]]"], output: "openmp-offload-gpu"
+
+// 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: -fopenmp-new-driver -no-canonical-prefixes -nogpulib %s -o
openmp-offload-gpu 2>&1 \
+// RUN: | FileCheck -check-prefix=NEW_DRIVER_EMBEDDING %s
+
+// NEW_DRIVER_EMBEDDING:
-fembed-offload-object=[[CUBIN:.*\.cubin]],nvptx64-nvidia-cuda.sm_70
Index: clang/lib/Driver/ToolChains/Clang.cpp
===================================================================
--- clang/lib/Driver/ToolChains/Clang.cpp
+++ clang/lib/Driver/ToolChains/Clang.cpp
@@ -4370,9 +4370,9 @@
IsHeaderModulePrecompile ? HeaderModuleInput : Inputs[0];
InputInfoList ModuleHeaderInputs;
+ InputInfoList OpenMPHostInputs;
const InputInfo *CudaDeviceInput = nullptr;
const InputInfo *OpenMPDeviceInput = nullptr;
- const InputInfo *OpenMPHostInput = nullptr;
for (const InputInfo &I : Inputs) {
if (&I == &Input) {
// This is the primary input.
@@ -4389,8 +4389,8 @@
CudaDeviceInput = &I;
} else if (IsOpenMPDevice && !OpenMPDeviceInput) {
OpenMPDeviceInput = &I;
- } else if (IsOpenMPHost && !OpenMPHostInput) {
- OpenMPHostInput = &I;
+ } else if (IsOpenMPHost) {
+ OpenMPHostInputs.push_back(I);
} else {
llvm_unreachable("unexpectedly given multiple inputs");
}
@@ -6897,6 +6897,25 @@
}
}
+ // Host-side OpenMP offloading recieves the device object files and embeds it
+ // in a named section including the associated target triple and
architecture.
+ if (IsOpenMPHost && !OpenMPHostInputs.empty()) {
+ auto InputFile = OpenMPHostInputs.begin();
+ auto OpenMPTCs = C.getOffloadToolChains<Action::OFK_OpenMP>();
+ for (auto TI = OpenMPTCs.first, TE = OpenMPTCs.second; TI != TE;
+ ++TI, ++InputFile) {
+ const ToolChain *TC = TI->second;
+ const ArgList &TCArgs = C.getArgsForToolChain(TC, "",
Action::OFK_OpenMP);
+ StringRef File =
+ C.getArgs().MakeArgString(TC->getInputFilename(*InputFile));
+ StringRef InputName = Clang::getBaseInputStem(Args, Inputs);
+
+ CmdArgs.push_back(Args.MakeArgString(
+ "-fembed-offload-object=" + File + "," + TC->getTripleString() + "."
+
+ TCArgs.getLastArgValue(options::OPT_march_EQ) + "." + InputName));
+ }
+ }
+
if (Triple.isAMDGPU()) {
handleAMDGPUCodeObjectVersionOptions(D, Args, CmdArgs);
Index: clang/test/Driver/openmp-offload-gpu.c
===================================================================
--- clang/test/Driver/openmp-offload-gpu.c
+++ clang/test/Driver/openmp-offload-gpu.c
@@ -360,3 +360,10 @@
// NEW_DRIVER: "nvptx64-nvidia-cuda" - "NVPTX::Assembler", inputs: ["[[DEVICE_ASM]]"], output: "[[DEVICE_OBJ:.+]]"
// NEW_DRIVER: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[HOST_BC]]", "[[DEVICE_OBJ]]"], output: "[[HOST_OBJ:.+]]"
// NEW_DRIVER: "x86_64-unknown-linux-gnu" - "[[LINKER:.+]]", inputs: ["[[HOST_OBJ]]"], output: "openmp-offload-gpu"
+
+// 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: -fopenmp-new-driver -no-canonical-prefixes -nogpulib %s -o openmp-offload-gpu 2>&1 \
+// RUN: | FileCheck -check-prefix=NEW_DRIVER_EMBEDDING %s
+
+// NEW_DRIVER_EMBEDDING: -fembed-offload-object=[[CUBIN:.*\.cubin]],nvptx64-nvidia-cuda.sm_70
Index: clang/lib/Driver/ToolChains/Clang.cpp
===================================================================
--- clang/lib/Driver/ToolChains/Clang.cpp
+++ clang/lib/Driver/ToolChains/Clang.cpp
@@ -4370,9 +4370,9 @@
IsHeaderModulePrecompile ? HeaderModuleInput : Inputs[0];
InputInfoList ModuleHeaderInputs;
+ InputInfoList OpenMPHostInputs;
const InputInfo *CudaDeviceInput = nullptr;
const InputInfo *OpenMPDeviceInput = nullptr;
- const InputInfo *OpenMPHostInput = nullptr;
for (const InputInfo &I : Inputs) {
if (&I == &Input) {
// This is the primary input.
@@ -4389,8 +4389,8 @@
CudaDeviceInput = &I;
} else if (IsOpenMPDevice && !OpenMPDeviceInput) {
OpenMPDeviceInput = &I;
- } else if (IsOpenMPHost && !OpenMPHostInput) {
- OpenMPHostInput = &I;
+ } else if (IsOpenMPHost) {
+ OpenMPHostInputs.push_back(I);
} else {
llvm_unreachable("unexpectedly given multiple inputs");
}
@@ -6897,6 +6897,25 @@
}
}
+ // Host-side OpenMP offloading recieves the device object files and embeds it
+ // in a named section including the associated target triple and architecture.
+ if (IsOpenMPHost && !OpenMPHostInputs.empty()) {
+ auto InputFile = OpenMPHostInputs.begin();
+ auto OpenMPTCs = C.getOffloadToolChains<Action::OFK_OpenMP>();
+ for (auto TI = OpenMPTCs.first, TE = OpenMPTCs.second; TI != TE;
+ ++TI, ++InputFile) {
+ const ToolChain *TC = TI->second;
+ const ArgList &TCArgs = C.getArgsForToolChain(TC, "", Action::OFK_OpenMP);
+ StringRef File =
+ C.getArgs().MakeArgString(TC->getInputFilename(*InputFile));
+ StringRef InputName = Clang::getBaseInputStem(Args, Inputs);
+
+ CmdArgs.push_back(Args.MakeArgString(
+ "-fembed-offload-object=" + File + "," + TC->getTripleString() + "." +
+ TCArgs.getLastArgValue(options::OPT_march_EQ) + "." + InputName));
+ }
+ }
+
if (Triple.isAMDGPU()) {
handleAMDGPUCodeObjectVersionOptions(D, Args, CmdArgs);
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
