jhuber6 created this revision.
jhuber6 added reviewers: jdoerfert, tianshilei1992, JonChesterfield, ABataev.
Herald added subscribers: guansong, inglorion, yaxunl.
Herald added a project: All.
jhuber6 requested review of this revision.
Herald added subscribers: cfe-commits, sstefan1, MaskRay.
Herald added a project: clang.
The previous patches allowed us to create a static library containing
all the device code. This patch uses that library to perform the device
runtime linking late when performing LTO. This in addition to
simplifying the libraries, allows us to transparently handle the runtime
library as-needed without needing Clang to manually pass the necessary
library in the linker wrapper job.
Depends on D125315 <https://reviews.llvm.org/D125315>
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D125333
Files:
clang/lib/Driver/ToolChains/Clang.cpp
clang/lib/Driver/ToolChains/CommonArgs.cpp
clang/test/Driver/openmp-offload-gpu-new.c
Index: clang/test/Driver/openmp-offload-gpu-new.c
===================================================================
--- clang/test/Driver/openmp-offload-gpu-new.c
+++ clang/test/Driver/openmp-offload-gpu-new.c
@@ -89,3 +89,8 @@
// RUN: %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings
-fopenmp -fopenmp-targets=nvptx64-nvidia-cuda \
// RUN: --offload-device-only -E -nogpulib %s 2>&1 | FileCheck %s
--check-prefix=CHECK-DEVICE-ONLY-PP
// CHECK-DEVICE-ONLY-PP: "nvptx64-nvidia-cuda" - "clang", inputs:
["[[INPUT:.*]]"], output: "-"
+
+// RUN: %clang -### --target=x86_64-unknown-linux-gnu -fopenmp
--offload-arch=sm_52 -nogpulib \
+// RUN: -foffload-lto %s 2>&1 | FileCheck --check-prefix=CHECK-LTO-LIBRARY
%s
+
+// CHECK-LTO-LIBRARY: {{.*}}-lomptarget{{.*}}-lomptarget.devicertl
Index: clang/lib/Driver/ToolChains/CommonArgs.cpp
===================================================================
--- clang/lib/Driver/ToolChains/CommonArgs.cpp
+++ clang/lib/Driver/ToolChains/CommonArgs.cpp
@@ -736,6 +736,9 @@
if (IsOffloadingHost)
CmdArgs.push_back("-lomptarget");
+ if (IsOffloadingHost && TC.getDriver().isUsingLTO(/* IsOffload */ true))
+ CmdArgs.push_back("-lomptarget.devicertl");
+
addArchSpecificRPath(TC, Args, CmdArgs);
if (RTKind == Driver::OMPRT_OMP)
Index: clang/lib/Driver/ToolChains/Clang.cpp
===================================================================
--- clang/lib/Driver/ToolChains/Clang.cpp
+++ clang/lib/Driver/ToolChains/Clang.cpp
@@ -8301,28 +8301,6 @@
"=" + *(FeatureIt + 1)));
}
- // Pass in the bitcode library to be linked during LTO.
- for (auto &I :
- llvm::make_range(OpenMPTCRange.first, OpenMPTCRange.second)) {
- const ToolChain *TC = I.second;
- if (!(TC->getTriple().isNVPTX() || TC->getTriple().isAMDGPU()))
- continue;
-
- const Driver &TCDriver = TC->getDriver();
- const ArgList &TCArgs = C.getArgsForToolChain(TC, "",
Action::OFK_OpenMP);
- StringRef Arch = TCArgs.getLastArgValue(options::OPT_march_EQ);
-
- ArgStringList BitcodeLibrary;
- addOpenMPDeviceRTL(TCDriver, TCArgs, BitcodeLibrary, Arch,
- TC->getTriple());
-
- if (!BitcodeLibrary.empty())
- CmdArgs.push_back(Args.MakeArgString(
- "-target-library=" +
- Action::GetOffloadKindName(Action::OFK_OpenMP) + "-" +
- TC->getTripleString() + "-" + Arch + "=" + BitcodeLibrary.back()));
- }
-
// Pass in the optimization level to use for LTO.
if (const Arg *A = Args.getLastArg(options::OPT_O_Group)) {
StringRef OOpt;
Index: clang/test/Driver/openmp-offload-gpu-new.c
===================================================================
--- clang/test/Driver/openmp-offload-gpu-new.c
+++ clang/test/Driver/openmp-offload-gpu-new.c
@@ -89,3 +89,8 @@
// RUN: %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings -fopenmp -fopenmp-targets=nvptx64-nvidia-cuda \
// RUN: --offload-device-only -E -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-DEVICE-ONLY-PP
// CHECK-DEVICE-ONLY-PP: "nvptx64-nvidia-cuda" - "clang", inputs: ["[[INPUT:.*]]"], output: "-"
+
+// RUN: %clang -### --target=x86_64-unknown-linux-gnu -fopenmp --offload-arch=sm_52 -nogpulib \
+// RUN: -foffload-lto %s 2>&1 | FileCheck --check-prefix=CHECK-LTO-LIBRARY %s
+
+// CHECK-LTO-LIBRARY: {{.*}}-lomptarget{{.*}}-lomptarget.devicertl
Index: clang/lib/Driver/ToolChains/CommonArgs.cpp
===================================================================
--- clang/lib/Driver/ToolChains/CommonArgs.cpp
+++ clang/lib/Driver/ToolChains/CommonArgs.cpp
@@ -736,6 +736,9 @@
if (IsOffloadingHost)
CmdArgs.push_back("-lomptarget");
+ if (IsOffloadingHost && TC.getDriver().isUsingLTO(/* IsOffload */ true))
+ CmdArgs.push_back("-lomptarget.devicertl");
+
addArchSpecificRPath(TC, Args, CmdArgs);
if (RTKind == Driver::OMPRT_OMP)
Index: clang/lib/Driver/ToolChains/Clang.cpp
===================================================================
--- clang/lib/Driver/ToolChains/Clang.cpp
+++ clang/lib/Driver/ToolChains/Clang.cpp
@@ -8301,28 +8301,6 @@
"=" + *(FeatureIt + 1)));
}
- // Pass in the bitcode library to be linked during LTO.
- for (auto &I :
- llvm::make_range(OpenMPTCRange.first, OpenMPTCRange.second)) {
- const ToolChain *TC = I.second;
- if (!(TC->getTriple().isNVPTX() || TC->getTriple().isAMDGPU()))
- continue;
-
- const Driver &TCDriver = TC->getDriver();
- const ArgList &TCArgs = C.getArgsForToolChain(TC, "", Action::OFK_OpenMP);
- StringRef Arch = TCArgs.getLastArgValue(options::OPT_march_EQ);
-
- ArgStringList BitcodeLibrary;
- addOpenMPDeviceRTL(TCDriver, TCArgs, BitcodeLibrary, Arch,
- TC->getTriple());
-
- if (!BitcodeLibrary.empty())
- CmdArgs.push_back(Args.MakeArgString(
- "-target-library=" +
- Action::GetOffloadKindName(Action::OFK_OpenMP) + "-" +
- TC->getTripleString() + "-" + Arch + "=" + BitcodeLibrary.back()));
- }
-
// Pass in the optimization level to use for LTO.
if (const Arg *A = Args.getLastArg(options::OPT_O_Group)) {
StringRef OOpt;
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
