jhuber6 created this revision.
jhuber6 added reviewers: JonChesterfield, carlo.bertolli, yaxunl, saiislam.
Herald added subscribers: sunshaoce, kerbowa, guansong, tpr, jvesely.
Herald added a project: All.
jhuber6 requested review of this revision.
Herald added subscribers: cfe-commits, jplehr, sstefan1, MaskRay.
Herald added a reviewer: jdoerfert.
Herald added a project: clang.
AMDGPU sometimes uses a novel formatting for their offloading
architecture called the target id. This merges the attributes and the
architecture name into a single string. Previously, we were passing this
as the canonical architecture name. This caused the linker wrapper to
fail to find relevant libraries and then pass an incalid CPU name. This
patch changes the handling in the offload packager to handle the
canonical architecture and then extract the features.
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D150998
Files:
clang/lib/Driver/ToolChains/Clang.cpp
clang/test/Driver/amdgpu-openmp-toolchain.c
Index: clang/test/Driver/amdgpu-openmp-toolchain.c
===================================================================
--- clang/test/Driver/amdgpu-openmp-toolchain.c
+++ clang/test/Driver/amdgpu-openmp-toolchain.c
@@ -62,3 +62,7 @@
// RUN: --rocm-device-lib-path=%S/Inputs/rocm/amdgcn/bitcode
-fopenmp-new-driver %s 2>&1 | \
// RUN: FileCheck %s --check-prefix=CHECK-LIB-DEVICE-NOGPULIB
// CHECK-LIB-DEVICE-NOGPULIB-NOT: "-cc1"
{{.*}}ocml.bc"{{.*}}ockl.bc"{{.*}}oclc_daz_opt_on.bc"{{.*}}oclc_unsafe_math_off.bc"{{.*}}oclc_finite_only_off.bc"{{.*}}oclc_correctly_rounded_sqrt_on.bc"{{.*}}oclc_wavefrontsize64_on.bc"{{.*}}oclc_isa_version_803.bc"
+
+// RUN: %clang -### -target x86_64-pc-linux-gnu -fopenmp
--offload-arch=gfx90a:sramecc-:xnack+ \
+// RUN: -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-TARGET-ID
+// CHECK-TARGET-ID:
clang-offload-packager{{.*}}arch=gfx90a,kind=openmp,feature=-sramecc,feature=+xnack
Index: clang/lib/Driver/ToolChains/Clang.cpp
===================================================================
--- clang/lib/Driver/ToolChains/Clang.cpp
+++ clang/lib/Driver/ToolChains/Clang.cpp
@@ -8449,7 +8449,7 @@
C.getArgsForToolChain(TC, OffloadAction->getOffloadingArch(),
OffloadAction->getOffloadingDeviceKind());
StringRef File = C.getArgs().MakeArgString(TC->getInputFilename(Input));
- StringRef Arch = (OffloadAction->getOffloadingArch())
+ StringRef Arch = OffloadAction->getOffloadingArch()
? OffloadAction->getOffloadingArch()
: TCArgs.getLastArgValue(options::OPT_march_EQ);
StringRef Kind =
@@ -8462,14 +8462,22 @@
llvm::copy_if(Features, std::back_inserter(FeatureArgs),
[](StringRef Arg) { return !Arg.startswith("-target"); });
+ if (TC->getTriple().isAMDGPU()) {
+ for (StringRef Feature : llvm::split(Arch.split(':').second, ':')) {
+ FeatureArgs.emplace_back(
+ Args.MakeArgString(Feature.take_back() + Feature.drop_back()));
+ }
+ }
+
SmallVector<std::string> Parts{
"file=" + File.str(),
"triple=" + TC->getTripleString(),
- "arch=" + Arch.str(),
+ "arch=" + getProcessorFromTargetID(TC->getTriple(), Arch).str(),
"kind=" + Kind.str(),
};
- if (TC->getDriver().isUsingLTO(/* IsOffload */ true))
+ if (TC->getDriver().isUsingLTO(/* IsOffload */ true) ||
+ TC->getTriple().isAMDGPU())
for (StringRef Feature : FeatureArgs)
Parts.emplace_back("feature=" + Feature.str());
Index: clang/test/Driver/amdgpu-openmp-toolchain.c
===================================================================
--- clang/test/Driver/amdgpu-openmp-toolchain.c
+++ clang/test/Driver/amdgpu-openmp-toolchain.c
@@ -62,3 +62,7 @@
// RUN: --rocm-device-lib-path=%S/Inputs/rocm/amdgcn/bitcode -fopenmp-new-driver %s 2>&1 | \
// RUN: FileCheck %s --check-prefix=CHECK-LIB-DEVICE-NOGPULIB
// CHECK-LIB-DEVICE-NOGPULIB-NOT: "-cc1" {{.*}}ocml.bc"{{.*}}ockl.bc"{{.*}}oclc_daz_opt_on.bc"{{.*}}oclc_unsafe_math_off.bc"{{.*}}oclc_finite_only_off.bc"{{.*}}oclc_correctly_rounded_sqrt_on.bc"{{.*}}oclc_wavefrontsize64_on.bc"{{.*}}oclc_isa_version_803.bc"
+
+// RUN: %clang -### -target x86_64-pc-linux-gnu -fopenmp --offload-arch=gfx90a:sramecc-:xnack+ \
+// RUN: -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-TARGET-ID
+// CHECK-TARGET-ID: clang-offload-packager{{.*}}arch=gfx90a,kind=openmp,feature=-sramecc,feature=+xnack
Index: clang/lib/Driver/ToolChains/Clang.cpp
===================================================================
--- clang/lib/Driver/ToolChains/Clang.cpp
+++ clang/lib/Driver/ToolChains/Clang.cpp
@@ -8449,7 +8449,7 @@
C.getArgsForToolChain(TC, OffloadAction->getOffloadingArch(),
OffloadAction->getOffloadingDeviceKind());
StringRef File = C.getArgs().MakeArgString(TC->getInputFilename(Input));
- StringRef Arch = (OffloadAction->getOffloadingArch())
+ StringRef Arch = OffloadAction->getOffloadingArch()
? OffloadAction->getOffloadingArch()
: TCArgs.getLastArgValue(options::OPT_march_EQ);
StringRef Kind =
@@ -8462,14 +8462,22 @@
llvm::copy_if(Features, std::back_inserter(FeatureArgs),
[](StringRef Arg) { return !Arg.startswith("-target"); });
+ if (TC->getTriple().isAMDGPU()) {
+ for (StringRef Feature : llvm::split(Arch.split(':').second, ':')) {
+ FeatureArgs.emplace_back(
+ Args.MakeArgString(Feature.take_back() + Feature.drop_back()));
+ }
+ }
+
SmallVector<std::string> Parts{
"file=" + File.str(),
"triple=" + TC->getTripleString(),
- "arch=" + Arch.str(),
+ "arch=" + getProcessorFromTargetID(TC->getTriple(), Arch).str(),
"kind=" + Kind.str(),
};
- if (TC->getDriver().isUsingLTO(/* IsOffload */ true))
+ if (TC->getDriver().isUsingLTO(/* IsOffload */ true) ||
+ TC->getTriple().isAMDGPU())
for (StringRef Feature : FeatureArgs)
Parts.emplace_back("feature=" + Feature.str());
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
