yaxunl created this revision.
yaxunl added reviewers: tra, b-sumner.
Herald added subscribers: dang, kerbowa, t-tye, tpr, dstuttard, jvesely,
kzhuravl.
yaxunl requested review of this revision.
Herald added a subscriber: wdng.
code object version determines ABI, therefore should not be mixed.
This patch emits amdgpu_code_object_version module flag in LLVM IR
based on code object version (default 4).
The amdgpu_code_object_version value is code object version times 100.
LLVM IR with different amdgpu_code_object_version module flag cannot
be linked.
The -cc1 option -mcode-object-version=none is for ROCm device library use
only, which supports multiple ABI.
https://reviews.llvm.org/D119026
Files:
clang/include/clang/Basic/TargetOptions.h
clang/include/clang/Driver/Options.td
clang/lib/CodeGen/CodeGenModule.cpp
clang/lib/Driver/ToolChains/Clang.cpp
clang/test/CodeGenCUDA/amdgpu-asan-printf.cu
clang/test/CodeGenCUDA/amdgpu-asan.cu
clang/test/CodeGenCUDA/amdgpu-code-object-version.cu
clang/test/Driver/hip-code-object-version.hip
Index: clang/test/Driver/hip-code-object-version.hip
===================================================================
--- clang/test/Driver/hip-code-object-version.hip
+++ clang/test/Driver/hip-code-object-version.hip
@@ -34,6 +34,7 @@
// RUN: %s 2>&1 | FileCheck -check-prefix=V3 %s
// V3-WARN: warning: argument '-mcode-object-v3' is deprecated, use '-mcode-object-version=3' instead [-Wdeprecated]
+// V3: "-mcode-object-version=3"
// V3: "-mllvm" "--amdhsa-code-object-version=3"
// V3: "-targets=host-x86_64-unknown-linux,hip-amdgcn-amd-amdhsa--gfx906"
@@ -44,6 +45,7 @@
// RUN: --offload-arch=gfx906 -nogpulib \
// RUN: %s 2>&1 | FileCheck -check-prefix=V4 %s
+// V4: "-mcode-object-version=4"
// V4: "-mllvm" "--amdhsa-code-object-version=4"
// V4: "-targets=host-x86_64-unknown-linux,hipv4-amdgcn-amd-amdhsa--gfx906"
@@ -54,6 +56,7 @@
// RUN: --offload-arch=gfx906 -nogpulib \
// RUN: %s 2>&1 | FileCheck -check-prefix=V5 %s
+// V5: "-mcode-object-version=5"
// V5: "-mllvm" "--amdhsa-code-object-version=5"
// V5: "-targets=host-x86_64-unknown-linux,hipv4-amdgcn-amd-amdhsa--gfx906"
Index: clang/test/CodeGenCUDA/amdgpu-code-object-version.cu
===================================================================
--- /dev/null
+++ clang/test/CodeGenCUDA/amdgpu-code-object-version.cu
@@ -0,0 +1,25 @@
+// Create module flag for code object version.
+
+// RUN: %clang_cc1 -fcuda-is-device -triple amdgcn-amd-amdhsa -emit-llvm \
+// RUN: -o - %s | FileCheck %s -check-prefix=V4
+
+// RUN: %clang_cc1 -fcuda-is-device -triple amdgcn-amd-amdhsa -emit-llvm \
+// RUN: -mcode-object-version=2 -o - %s | FileCheck -check-prefix=V2 %s
+
+// RUN: %clang_cc1 -fcuda-is-device -triple amdgcn-amd-amdhsa -emit-llvm \
+// RUN: -mcode-object-version=3 -o - %s | FileCheck -check-prefix=V3 %s
+
+// RUN: %clang_cc1 -fcuda-is-device -triple amdgcn-amd-amdhsa -emit-llvm \
+// RUN: -mcode-object-version=4 -o - %s | FileCheck -check-prefix=V4 %s
+
+// RUN: %clang_cc1 -fcuda-is-device -triple amdgcn-amd-amdhsa -emit-llvm \
+// RUN: -mcode-object-version=5 -o - %s | FileCheck -check-prefix=V5 %s
+
+// RUN: %clang_cc1 -fcuda-is-device -triple amdgcn-amd-amdhsa -emit-llvm \
+// RUN: -mcode-object-version=none -o - %s | FileCheck %s -check-prefix=NONE
+
+// V2: !{{.*}} = !{i32 1, !"amdgpu_code_object_version", i32 200}
+// V3: !{{.*}} = !{i32 1, !"amdgpu_code_object_version", i32 300}
+// V4: !{{.*}} = !{i32 1, !"amdgpu_code_object_version", i32 400}
+// V5: !{{.*}} = !{i32 1, !"amdgpu_code_object_version", i32 500}
+// NONE-NOT: !{{.*}} = !{i32 1, !"amdgpu_code_object_version",
Index: clang/test/CodeGenCUDA/amdgpu-asan.cu
===================================================================
--- clang/test/CodeGenCUDA/amdgpu-asan.cu
+++ clang/test/CodeGenCUDA/amdgpu-asan.cu
@@ -27,8 +27,7 @@
// ASAN-DAG: @llvm.compiler.used = {{.*}}@__amdgpu_device_library_preserve_asan_functions_ptr
// ASAN-DAG: define weak void @__asan_report_load1(i64 %{{.*}})
-// MFCHECK: !llvm.module.flags = !{![[FLAG1:[0-9]+]], ![[FLAG2:[0-9]+]]}
-// MFCHECK: ![[FLAG1]] = !{i32 4, !"amdgpu_hostcall", i32 1}
+// MFCHECK: !{{.*}} = !{i32 4, !"amdgpu_hostcall", i32 1}
// CHECK-NOT: @__amdgpu_device_library_preserve_asan_functions
// CHECK-NOT: @__asan_report_load1
Index: clang/test/CodeGenCUDA/amdgpu-asan-printf.cu
===================================================================
--- clang/test/CodeGenCUDA/amdgpu-asan-printf.cu
+++ clang/test/CodeGenCUDA/amdgpu-asan-printf.cu
@@ -2,8 +2,7 @@
// RUN: -fcuda-is-device -target-cpu gfx906 -fsanitize=address \
// RUN: -O3 -x hip | FileCheck -check-prefixes=MFCHECK %s
-// MFCHECK: !llvm.module.flags = !{![[FLAG1:[0-9]+]], ![[FLAG2:[0-9]+]]}
-// MFCHECK: ![[FLAG1]] = !{i32 4, !"amdgpu_hostcall", i32 1}
+// MFCHECK: !{{.*}} = !{i32 4, !"amdgpu_hostcall", i32 1}
// Test to check hostcall module flag metadata is generated correctly
// when a program has printf call and compiled with -fsanitize=address.
Index: clang/lib/Driver/ToolChains/Clang.cpp
===================================================================
--- clang/lib/Driver/ToolChains/Clang.cpp
+++ clang/lib/Driver/ToolChains/Clang.cpp
@@ -1162,6 +1162,9 @@
Args.MakeArgString(Twine("--amdhsa-code-object-version=") +
Twine(CodeObjVer)));
CmdArgs.insert(CmdArgs.begin() + 1, "-mllvm");
+ CmdArgs.insert(CmdArgs.begin() + 1,
+ Args.MakeArgString(Twine("-mcode-object-version=") +
+ Twine(CodeObjVer)));
}
}
Index: clang/lib/CodeGen/CodeGenModule.cpp
===================================================================
--- clang/lib/CodeGen/CodeGenModule.cpp
+++ clang/lib/CodeGen/CodeGenModule.cpp
@@ -552,21 +552,32 @@
EmitMainVoidAlias();
}
- // Emit reference of __amdgpu_device_library_preserve_asan_functions to
- // preserve ASAN functions in bitcode libraries.
- if (LangOpts.Sanitize.has(SanitizerKind::Address) && getTriple().isAMDGPU()) {
- auto *FT = llvm::FunctionType::get(VoidTy, {});
- auto *F = llvm::Function::Create(
- FT, llvm::GlobalValue::ExternalLinkage,
- "__amdgpu_device_library_preserve_asan_functions", &getModule());
- auto *Var = new llvm::GlobalVariable(
- getModule(), FT->getPointerTo(),
- /*isConstant=*/true, llvm::GlobalValue::WeakAnyLinkage, F,
- "__amdgpu_device_library_preserve_asan_functions_ptr", nullptr,
- llvm::GlobalVariable::NotThreadLocal);
- addCompilerUsedGlobal(Var);
- if (!getModule().getModuleFlag("amdgpu_hostcall")) {
- getModule().addModuleFlag(llvm::Module::Override, "amdgpu_hostcall", 1);
+ if (getTriple().isAMDGPU()) {
+ // Emit reference of __amdgpu_device_library_preserve_asan_functions to
+ // preserve ASAN functions in bitcode libraries.
+ if (LangOpts.Sanitize.has(SanitizerKind::Address)) {
+ auto *FT = llvm::FunctionType::get(VoidTy, {});
+ auto *F = llvm::Function::Create(
+ FT, llvm::GlobalValue::ExternalLinkage,
+ "__amdgpu_device_library_preserve_asan_functions", &getModule());
+ auto *Var = new llvm::GlobalVariable(
+ getModule(), FT->getPointerTo(),
+ /*isConstant=*/true, llvm::GlobalValue::WeakAnyLinkage, F,
+ "__amdgpu_device_library_preserve_asan_functions_ptr", nullptr,
+ llvm::GlobalVariable::NotThreadLocal);
+ addCompilerUsedGlobal(Var);
+ if (!getModule().getModuleFlag("amdgpu_hostcall")) {
+ getModule().addModuleFlag(llvm::Module::Override, "amdgpu_hostcall", 1);
+ }
+ }
+ // Emit amdgpu_code_object_version module flag, which is code object version
+ // times 100.
+ if (getTarget().getTargetOpts().CodeObjectVersion != "none") {
+ unsigned CodeObjVer;
+ StringRef(getTarget().getTargetOpts().CodeObjectVersion)
+ .getAsInteger(/*radix=*/0, CodeObjVer);
+ getModule().addModuleFlag(llvm::Module::Error,
+ "amdgpu_code_object_version", CodeObjVer * 100);
}
}
Index: clang/include/clang/Driver/Options.td
===================================================================
--- clang/include/clang/Driver/Options.td
+++ clang/include/clang/Driver/Options.td
@@ -3441,6 +3441,7 @@
def mcode_object_version_EQ : Joined<["-"], "mcode-object-version=">, Group<m_Group>,
HelpText<"Specify code object ABI version. Defaults to 4. (AMDGPU only)">,
+ Flags<[CC1Option]>, MarshallingInfoString<TargetOpts<"CodeObjectVersion">, "\"4\"">,
MetaVarName<"<version>">, Values<"2,3,4,5">;
defm code_object_v3_legacy : SimpleMFlag<"code-object-v3",
Index: clang/include/clang/Basic/TargetOptions.h
===================================================================
--- clang/include/clang/Basic/TargetOptions.h
+++ clang/include/clang/Basic/TargetOptions.h
@@ -78,6 +78,9 @@
/// \brief If enabled, allow AMDGPU unsafe floating point atomics.
bool AllowAMDGPUUnsafeFPAtomics = false;
+ /// \brief Code object version for AMDGPU.
+ std::string CodeObjectVersion;
+
// The code model to be used as specified by the user. Corresponds to
// CodeModel::Model enum defined in include/llvm/Support/CodeGen.h, plus
// "default" for the case when the user has not explicitly specified a
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
