https://github.com/yxsamliu updated
https://github.com/llvm/llvm-project/pull/143964
>From 5f3cc287ff2c3c84ba840ebaa0931773341a02b2 Mon Sep 17 00:00:00 2001
From: "Yaxun (Sam) Liu" <yaxun....@amd.com>
Date: Wed, 11 Jun 2025 14:02:59 -0400
Subject: [PATCH 1/3] Revert "Revert "[HIP] use offload wrapper for
non-device-only non-rdc (#132869)" (#143432)"
This reverts commit f5e499a3383c1e3b9f60e60151075e8d9c1c3166.
---
clang/lib/CodeGen/CGCUDANV.cpp | 3 +-
clang/lib/Driver/Driver.cpp | 59 +++++++++++-----
clang/lib/Driver/ToolChains/Clang.cpp | 18 ++++-
clang/test/Driver/hip-binding.hip | 6 +-
clang/test/Driver/hip-phases.hip | 51 ++++++++------
clang/test/Driver/hip-toolchain-no-rdc.hip | 81 +++++++++++++---------
6 files changed, 142 insertions(+), 76 deletions(-)
diff --git a/clang/lib/CodeGen/CGCUDANV.cpp b/clang/lib/CodeGen/CGCUDANV.cpp
index 38f514304df5e..dd26be74e561b 100644
--- a/clang/lib/CodeGen/CGCUDANV.cpp
+++ b/clang/lib/CodeGen/CGCUDANV.cpp
@@ -1280,7 +1280,8 @@ llvm::Function *CGNVCUDARuntime::finalizeModule() {
return nullptr;
}
if (CGM.getLangOpts().OffloadViaLLVM ||
- (CGM.getLangOpts().OffloadingNewDriver && RelocatableDeviceCode))
+ (CGM.getLangOpts().OffloadingNewDriver &&
+ (CGM.getLangOpts().HIP || RelocatableDeviceCode)))
createOffloadingEntries();
else
return makeModuleCtorFunction();
diff --git a/clang/lib/Driver/Driver.cpp b/clang/lib/Driver/Driver.cpp
index eb60d907d2218..98bc4b91a0bcd 100644
--- a/clang/lib/Driver/Driver.cpp
+++ b/clang/lib/Driver/Driver.cpp
@@ -4423,6 +4423,10 @@ void Driver::BuildActions(Compilation &C, DerivedArgList
&Args,
options::OPT_no_offload_new_driver,
C.isOffloadingHostKind(Action::OFK_Cuda));
+ bool HIPNoRDC =
+ C.isOffloadingHostKind(Action::OFK_HIP) &&
+ !Args.hasFlag(options::OPT_fgpu_rdc, options::OPT_fno_gpu_rdc, false);
+
// Builder to be used to build offloading actions.
std::unique_ptr<OffloadingActionBuilder> OffloadBuilder =
!UseNewOffloadingDriver
@@ -4556,7 +4560,7 @@ void Driver::BuildActions(Compilation &C, DerivedArgList
&Args,
// Check if this Linker Job should emit a static library.
if (ShouldEmitStaticLibrary(Args)) {
LA = C.MakeAction<StaticLibJobAction>(LinkerInputs, types::TY_Image);
- } else if (UseNewOffloadingDriver ||
+ } else if ((UseNewOffloadingDriver && !HIPNoRDC) ||
Args.hasArg(options::OPT_offload_link)) {
LA = C.MakeAction<LinkerWrapperJobAction>(LinkerInputs, types::TY_Image);
LA->propagateHostOffloadInfo(C.getActiveOffloadKinds(),
@@ -4867,10 +4871,28 @@ Action *Driver::BuildOffloadingActions(Compilation &C,
const InputTy &Input, StringRef CUID,
Action *HostAction) const {
// Don't build offloading actions if explicitly disabled or we do not have a
- // valid source input and compile action to embed it in. If preprocessing
only
- // ignore embedding.
- if (offloadHostOnly() || !types::isSrcFile(Input.first) ||
- !(isa<CompileJobAction>(HostAction) ||
+ // valid source input.
+ if (offloadHostOnly() || !types::isSrcFile(Input.first))
+ return HostAction;
+
+ bool HIPNoRDC =
+ C.isOffloadingHostKind(Action::OFK_HIP) &&
+ !Args.hasFlag(options::OPT_fgpu_rdc, options::OPT_fno_gpu_rdc, false);
+
+ // For HIP non-rdc non-device-only compilation, create a linker wrapper
+ // action for each host object to link, bundle and wrap device files in
+ // it.
+ if (isa<AssembleJobAction>(HostAction) && HIPNoRDC && !offloadDeviceOnly()) {
+ ActionList AL{HostAction};
+ HostAction = C.MakeAction<LinkerWrapperJobAction>(AL, types::TY_Object);
+ HostAction->propagateHostOffloadInfo(C.getActiveOffloadKinds(),
+ /*BoundArch=*/nullptr);
+ return HostAction;
+ }
+
+ // Don't build offloading actions if we do not have a compile action. If
+ // preprocessing only ignore embedding.
+ if (!(isa<CompileJobAction>(HostAction) ||
getFinalPhase(Args) == phases::Preprocess))
return HostAction;
@@ -4966,12 +4988,12 @@ Action *Driver::BuildOffloadingActions(Compilation &C,
}
}
- // Compiling HIP in non-RDC mode requires linking each action individually.
+ // Compiling HIP in device-only non-RDC mode requires linking each action
+ // individually.
for (Action *&A : DeviceActions) {
if ((A->getType() != types::TY_Object &&
A->getType() != types::TY_LTO_BC) ||
- Kind != Action::OFK_HIP ||
- Args.hasFlag(options::OPT_fgpu_rdc, options::OPT_fno_gpu_rdc, false))
+ !HIPNoRDC || !offloadDeviceOnly())
continue;
ActionList LinkerInput = {A};
A = C.MakeAction<LinkJobAction>(LinkerInput, types::TY_Image);
@@ -4995,12 +5017,12 @@ Action *Driver::BuildOffloadingActions(Compilation &C,
}
}
- // HIP code in non-RDC mode will bundle the output if it invoked the linker.
+ // HIP code in device-only non-RDC mode will bundle the output if it invoked
+ // the linker.
bool ShouldBundleHIP =
- C.isOffloadingHostKind(Action::OFK_HIP) &&
+ HIPNoRDC && offloadDeviceOnly() &&
Args.hasFlag(options::OPT_gpu_bundle_output,
options::OPT_no_gpu_bundle_output, true) &&
- !Args.hasFlag(options::OPT_fgpu_rdc, options::OPT_fno_gpu_rdc, false) &&
!llvm::any_of(OffloadActions,
[](Action *A) { return A->getType() != types::TY_Image; });
@@ -5020,11 +5042,9 @@ Action *Driver::BuildOffloadingActions(Compilation &C,
C.MakeAction<LinkJobAction>(OffloadActions, types::TY_CUDA_FATBIN);
DDep.add(*FatbinAction, *C.getSingleOffloadToolChain<Action::OFK_Cuda>(),
nullptr, Action::OFK_Cuda);
- } else if (C.isOffloadingHostKind(Action::OFK_HIP) &&
- !Args.hasFlag(options::OPT_fgpu_rdc, options::OPT_fno_gpu_rdc,
- false)) {
- // If we are not in RDC-mode we just emit the final HIP fatbinary for each
- // translation unit, linking each input individually.
+ } else if (HIPNoRDC && offloadDeviceOnly()) {
+ // If we are in device-only non-RDC-mode we just emit the final HIP
+ // fatbinary for each translation unit, linking each input individually.
Action *FatbinAction =
C.MakeAction<LinkJobAction>(OffloadActions, types::TY_HIP_FATBIN);
DDep.add(*FatbinAction, *C.getSingleOffloadToolChain<Action::OFK_HIP>(),
@@ -5177,8 +5197,11 @@ Action *Driver::ConstructPhaseAction(
(((Input->getOffloadingToolChain() &&
Input->getOffloadingToolChain()->getTriple().isAMDGPU()) ||
TargetDeviceOffloadKind == Action::OFK_HIP) &&
- (Args.hasFlag(options::OPT_fgpu_rdc, options::OPT_fno_gpu_rdc,
- false) ||
+ ((Args.hasFlag(options::OPT_fgpu_rdc, options::OPT_fno_gpu_rdc,
+ false) ||
+ (Args.hasFlag(options::OPT_offload_new_driver,
+ options::OPT_no_offload_new_driver, false) &&
+ !offloadDeviceOnly())) ||
TargetDeviceOffloadKind == Action::OFK_OpenMP))) {
types::ID Output =
Args.hasArg(options::OPT_S) &&
diff --git a/clang/lib/Driver/ToolChains/Clang.cpp
b/clang/lib/Driver/ToolChains/Clang.cpp
index 1d11be1d82be8..d6b89c324936f 100644
--- a/clang/lib/Driver/ToolChains/Clang.cpp
+++ b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -7702,7 +7702,7 @@ void Clang::ConstructJob(Compilation &C, const JobAction
&JA,
CmdArgs.push_back("-fcuda-include-gpubinary");
CmdArgs.push_back(CudaDeviceInput->getFilename());
} else if (!HostOffloadingInputs.empty()) {
- if ((IsCuda || IsHIP) && !IsRDCMode) {
+ if (IsCuda && !IsRDCMode) {
assert(HostOffloadingInputs.size() == 1 && "Only one input expected");
CmdArgs.push_back("-fcuda-include-gpubinary");
CmdArgs.push_back(HostOffloadingInputs.front().getFilename());
@@ -9249,8 +9249,20 @@ void LinkerWrapper::ConstructJob(Compilation &C, const
JobAction &JA,
// Add the linker arguments to be forwarded by the wrapper.
CmdArgs.push_back(Args.MakeArgString(Twine("--linker-path=") +
LinkCommand->getExecutable()));
- for (const char *LinkArg : LinkCommand->getArguments())
- CmdArgs.push_back(LinkArg);
+
+ // We use action type to differentiate two use cases of the linker wrapper.
+ // TY_Image for normal linker wrapper work.
+ // TY_Object for HIP fno-gpu-rdc embedding device binary in a relocatable
+ // object.
+ assert(JA.getType() == types::TY_Object || JA.getType() == types::TY_Image);
+ if (JA.getType() == types::TY_Object) {
+ CmdArgs.append({"-o", Output.getFilename()});
+ for (auto Input : Inputs)
+ CmdArgs.push_back(Input.getFilename());
+ CmdArgs.push_back("-r");
+ } else
+ for (const char *LinkArg : LinkCommand->getArguments())
+ CmdArgs.push_back(LinkArg);
addOffloadCompressArgs(Args, CmdArgs);
diff --git a/clang/test/Driver/hip-binding.hip
b/clang/test/Driver/hip-binding.hip
index 57e57194ec87b..d8b3f1e242018 100644
--- a/clang/test/Driver/hip-binding.hip
+++ b/clang/test/Driver/hip-binding.hip
@@ -93,7 +93,7 @@
// RUN: -nogpulib -nogpuinc -foffload-lto --offload-arch=gfx90a
--offload-arch=gfx908 -c %s 2>&1 \
// RUN: | FileCheck -check-prefix=LTO-NO-RDC %s
// LTO-NO-RDC: # "amdgcn-amd-amdhsa" - "clang", inputs: ["[[INPUT:.+]]"],
output: "[[LTO_908:.+]]"
-// LTO-NO-RDC-NEXT: # "amdgcn-amd-amdhsa" - "AMDGCN::Linker", inputs:
["[[LTO_908]]"], output: "[[OBJ_908:.+]]"
// LTO-NO-RDC-NEXT: # "amdgcn-amd-amdhsa" - "clang", inputs: ["[[INPUT]]"],
output: "[[LTO_90A:.+]]"
-// LTO-NO-RDC-NEXT: # "amdgcn-amd-amdhsa" - "AMDGCN::Linker", inputs:
["[[LTO_90A]]"], output: "[[OBJ_90A:.+]]"
-// LTO-NO-RDC-NEXT: # "amdgcn-amd-amdhsa" - "AMDGCN::Linker", inputs:
["[[OBJ_908]]", "[[OBJ_90A]]"], output: "[[HIPFB:.+]]"
+// LTO-NO-RDC-NEXT: # "x86_64-unknown-linux-gnu" - "Offload::Packager",
inputs: ["[[LTO_908]]", "[[LTO_90A]]"], output: "[[PKG:.+]]"
+// LTO-NO-RDC-NEXT: # "x86_64-unknown-linux-gnu" - "clang", inputs:
["[[INPUT]]", "[[PKG]]"], output: "[[OBJ:.+]]"
+// LTO-NO-RDC-NEXT: # "x86_64-unknown-linux-gnu" - "Offload::Linker", inputs:
["[[OBJ]]"], output: "hip-binding.o"
diff --git a/clang/test/Driver/hip-phases.hip b/clang/test/Driver/hip-phases.hip
index 5fd2c0216ccc3..996d72e58755a 100644
--- a/clang/test/Driver/hip-phases.hip
+++ b/clang/test/Driver/hip-phases.hip
@@ -8,39 +8,50 @@
//
// RUN: %clang -x hip --target=x86_64-unknown-linux-gnu -ccc-print-phases \
// RUN: --no-offload-new-driver --cuda-gpu-arch=gfx803 %s 2>&1 \
-// RUN: | FileCheck -check-prefixes=BIN,NRD,OLD %s
+// RUN: | FileCheck -check-prefixes=BIN,OLD,OLDN %s
// RUN: %clang -x hip --target=x86_64-unknown-linux-gnu -ccc-print-phases \
// RUN: --offload-new-driver --cuda-gpu-arch=gfx803 %s 2>&1 \
-// RUN: | FileCheck -check-prefixes=BIN,NRD,NEW %s
+// RUN: | FileCheck -check-prefixes=BIN,NEW,NEWN %s
//
// RUN: %clang -x hip --target=x86_64-unknown-linux-gnu -ccc-print-phases \
// RUN: --no-offload-new-driver --cuda-gpu-arch=gfx803 -fgpu-rdc %s 2>&1 \
-// RUN: | FileCheck -check-prefixes=BIN,RDC %s
+// RUN: | FileCheck -check-prefixes=BIN,OLD,OLDR %s
+// RUN: %clang -x hip --target=x86_64-unknown-linux-gnu -ccc-print-phases \
+// RUN: --offload-new-driver --cuda-gpu-arch=gfx803 -fgpu-rdc %s 2>&1 \
+// RUN: | FileCheck -check-prefixes=BIN,NEW,NEWR %s
//
// BIN-DAG: [[P0:[0-9]+]]: input, "{{.*}}hip-phases.hip", [[T:hip]],
(host-[[T]])
// BIN-DAG: [[P1:[0-9]+]]: preprocessor, {[[P0]]}, [[T]]-cpp-output,
(host-[[T]])
// BIN-DAG: [[P2:[0-9]+]]: compiler, {[[P1]]}, ir, (host-[[T]])
-// RDC-DAG: [[P12:[0-9]+]]: backend, {[[P2]]}, assembler, (host-[[T]])
-// RDC-DAG: [[P13:[0-9]+]]: assembler, {[[P12]]}, object, (host-[[T]])
+// OLDR-DAG: [[P12:[0-9]+]]: backend, {[[P2]]}, assembler, (host-[[T]])
+// OLDR-DAG: [[P13:[0-9]+]]: assembler, {[[P12]]}, object, (host-[[T]])
// BIN-DAG: [[P3:[0-9]+]]: input, "{{.*}}hip-phases.hip", [[T]],
(device-[[T]], [[ARCH:gfx803]])
// BIN-DAG: [[P4:[0-9]+]]: preprocessor, {[[P3]]}, [[T]]-cpp-output,
(device-[[T]], [[ARCH]])
// BIN-DAG: [[P5:[0-9]+]]: compiler, {[[P4]]}, ir, (device-[[T]], [[ARCH]])
-// NRD-DAG: [[P6:[0-9]+]]: backend, {[[P5]]}, assembler, (device-[[T]],
[[ARCH]])
-// NRD-DAG: [[P7:[0-9]+]]: assembler, {[[P6]]}, object, (device-[[T]],
[[ARCH]])
-// RDC-DAG: [[P7:[0-9]+]]: backend, {[[P5]]}, ir, (device-[[T]], [[ARCH]])
-// BIN-DAG: [[P8:[0-9]+]]: linker, {[[P7]]}, image, (device-[[T]], [[ARCH]])
-// BIN-DAG: [[P9:[0-9]+]]: offload, "device-[[T]]
(amdgcn-amd-amdhsa:[[ARCH]])" {[[P8]]}, image
-// NRD-DAG: [[P10:[0-9]+]]: linker, {[[P9]]}, hip-fatbin, (device-[[T]])
-// RDC-DAG: [[P10:[0-9]+]]: linker, {[[P9]]}, object, (device-[[T]])
-
-// NRD-DAG: [[P11:[0-9]+]]: offload, "host-[[T]] (x86_64-unknown-linux-gnu)"
{[[P2]]}, "device-[[T]] (amdgcn-amd-amdhsa)" {[[P10]]}, ir
-// RDC-DAG: [[P11:[0-9]+]]: offload, "device-[[T]] (amdgcn-amd-amdhsa)"
{[[P10]]}, object
-// NRD-DAG: [[P12:[0-9]+]]: backend, {[[P11]]}, assembler, (host-[[T]])
-// NRD-DAG: [[P13:[0-9]+]]: assembler, {[[P12]]}, object, (host-[[T]])
-// OLD-DAG: [[P14:[0-9]+]]: linker, {[[P13]]}, image, (host-[[T]])
-// NEW-DAG: [[P14:[0-9]+]]: clang-linker-wrapper, {[[P13]]}, image,
(host-[[T]])
-// RDC-DAG: [[P14:[0-9]+]]: linker, {[[P13]], [[P11]]}, image, (host-[[T]])
+// OLDN-DAG: [[P6:[0-9]+]]: backend, {[[P5]]}, assembler, (device-[[T]],
[[ARCH]])
+// NEW-DAG: [[P6:[0-9]+]]: backend, {[[P5]]}, ir, (device-[[T]], [[ARCH]])
+// OLDN-DAG: [[P7:[0-9]+]]: assembler, {[[P6]]}, object, (device-[[T]],
[[ARCH]])
+// OLDR-DAG: [[P7:[0-9]+]]: backend, {[[P5]]}, ir, (device-[[T]], [[ARCH]])
+// OLD-DAG: [[P8:[0-9]+]]: linker, {[[P7]]}, image, (device-[[T]], [[ARCH]])
+// OLD-DAG: [[P9:[0-9]+]]: offload, "device-[[T]]
(amdgcn-amd-amdhsa:[[ARCH]])" {[[P8]]}, image
+// NEW-DAG: [[P9:[0-9]+]]: offload, "device-[[T]]
(amdgcn-amd-amdhsa:[[ARCH]])" {[[P6]]}, ir
+// OLDN-DAG: [[P10:[0-9]+]]: linker, {[[P9]]}, hip-fatbin, (device-[[T]])
+// NEW-DAG: [[P10:[0-9]+]]: clang-offload-packager, {[[P9]]}, image,
(device-[[T]])
+// OLDR-DAG: [[P10:[0-9]+]]: linker, {[[P9]]}, object, (device-[[T]])
+
+// OLDN-DAG: [[P11:[0-9]+]]: offload, "host-[[T]] (x86_64-unknown-linux-gnu)"
{[[P2]]}, "device-[[T]] (amdgcn-amd-amdhsa)" {[[P10]]}, ir
+// NEW-DAG: [[P11:[0-9]+]]: offload, "host-[[T]] (x86_64-unknown-linux-gnu)"
{[[P2]]}, "device-[[T]] (x86_64-unknown-linux-gnu)" {[[P10]]}, ir
+// OLDR-DAG: [[P11:[0-9]+]]: offload, "device-[[T]] (amdgcn-amd-amdhsa)"
{[[P10]]}, object
+// OLDN-DAG: [[P12:[0-9]+]]: backend, {[[P11]]}, assembler, (host-[[T]])
+// OLDN-DAG: [[P13:[0-9]+]]: assembler, {[[P12]]}, object, (host-[[T]])
+// NEW-DAG: [[P12:[0-9]+]]: backend, {[[P11]]}, assembler, (host-[[T]])
+// NEW-DAG: [[P13:[0-9]+]]: assembler, {[[P12]]}, object, (host-[[T]])
+// OLDN-DAG: [[P14:[0-9]+]]: linker, {[[P13]]}, image, (host-[[T]])
+// NEWN-DAG: [[P14:[0-9]+]]: clang-linker-wrapper, {[[P13]]}, object,
(host-[[T]])
+// OLDR-DAG: [[P14:[0-9]+]]: linker, {[[P13]], [[P11]]}, image, (host-[[T]])
+// NEWR-DAG: [[P14:[0-9]+]]: clang-linker-wrapper, {[[P13]]}, image,
(host-[[T]])
+// NEWN-DAG: [[P15:[0-9]+]]: linker, {[[P14]]}, image
//
// Test single gpu architecture up to the assemble phase.
diff --git a/clang/test/Driver/hip-toolchain-no-rdc.hip
b/clang/test/Driver/hip-toolchain-no-rdc.hip
index 6c69d1d51a260..ddd251b67cc57 100644
--- a/clang/test/Driver/hip-toolchain-no-rdc.hip
+++ b/clang/test/Driver/hip-toolchain-no-rdc.hip
@@ -7,7 +7,7 @@
// RUN: -fuse-ld=lld -B%S/Inputs/lld -nogpuinc \
// RUN: %S/Inputs/hip_multiple_inputs/a.cu \
// RUN: %S/Inputs/hip_multiple_inputs/b.hip \
-// RUN: 2>&1 | FileCheck -check-prefixes=CHECK,LINK %s
+// RUN: 2>&1 | FileCheck -check-prefixes=CHECK,LINK,OLD %s
// RUN: %clang -### --target=x86_64-linux-gnu -fno-gpu-rdc \
// RUN: -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
@@ -17,7 +17,7 @@
// RUN: -fuse-ld=lld -B%S/Inputs/lld -nogpuinc -c \
// RUN: %S/Inputs/hip_multiple_inputs/a.cu \
// RUN: %S/Inputs/hip_multiple_inputs/b.hip \
-// RUN: 2>&1 | FileCheck -check-prefixes=CHECK %s
+// RUN: 2>&1 | FileCheck -check-prefixes=CHECK,OLD %s
// RUN: %clang -### --target=x86_64-linux-gnu -fno-gpu-rdc \
// RUN: -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
@@ -27,7 +27,7 @@
// RUN: -fuse-ld=lld -B%S/Inputs/lld -nogpuinc --offload-new-driver -c \
// RUN: %S/Inputs/hip_multiple_inputs/a.cu \
// RUN: %S/Inputs/hip_multiple_inputs/b.hip \
-// RUN: 2>&1 | FileCheck -check-prefixes=CHECK %s
+// RUN: 2>&1 | FileCheck -check-prefixes=CHECK,NEW %s
// RUN: touch %t/a.o %t/b.o
// RUN: %clang -### --target=x86_64-linux-gnu \
@@ -47,22 +47,23 @@
// CHECK: [[CLANG:".*clang.*"]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
// CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
-// CHECK-SAME: "-emit-obj"
+// OLD-SAME: "-emit-obj"
+// NEW-SAME: "-emit-llvm-bc"
// CHECK-SAME: {{.*}} "-main-file-name" "a.cu"
// CHECK-SAME: "-fcuda-is-device" "-fno-threadsafe-statics" "-mllvm"
"-amdgpu-internalize-symbols"
// CHECK-SAME: "-fcuda-allow-variadic-functions" "-fvisibility=hidden"
// CHECK-SAME: "-fapply-global-visibility-to-externs"
// CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
// CHECK-SAME: "-target-cpu" "gfx803"
-// CHECK-SAME: {{.*}} "-o" [[OBJ_DEV_A_803:".*o"]] "-x" "hip"
+// CHECK-SAME: {{.*}} "-o" "[[OBJ_DEV_A_803:.*(o|bc)]]" "-x" "hip"
// CHECK-SAME: {{.*}} [[A_SRC:".*a.cu"]]
// CHECK-NOT: {{".*llvm-link"}}
// CHECK-NOT: {{".*opt"}}
// CHECK-NOT: {{".*llc"}}
-// CHECK: [[LLD: ".*lld.*"]] "-flavor" "gnu" "-m" "elf64_amdgpu"
"--no-undefined" "-shared"
-// CHECK-SAME: "-o" "[[IMG_DEV_A_803:.*out]]" [[OBJ_DEV_A_803]]
+// OLD: [[LLD: ".*lld.*"]] "-flavor" "gnu" "-m" "elf64_amdgpu"
"--no-undefined" "-shared"
+// OLD-SAME: "-o" "[[IMG_DEV_A_803:.*out]]" "[[OBJ_DEV_A_803]]"
//
// Compile device code in a.cu to code object for gfx900.
@@ -70,62 +71,71 @@
// CHECK: [[CLANG:".*clang.*"]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
// CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
-// CHECK-SAME: "-emit-obj"
+// CHECK-SAME: "-emit-{{(obj|llvm-bc)}}"
// CHECK-SAME: {{.*}} "-main-file-name" "a.cu"
// CHECK-SAME: "-fcuda-is-device" "-fno-threadsafe-statics" "-mllvm"
"-amdgpu-internalize-symbols"
// CHECK-SAME: "-fcuda-allow-variadic-functions" "-fvisibility=hidden"
// CHECK-SAME: "-fapply-global-visibility-to-externs"
// CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
// CHECK-SAME: "-target-cpu" "gfx900"
-// CHECK-SAME: {{.*}} "-o" [[OBJ_DEV_A_900:".*o"]] "-x" "hip"
+// CHECK-SAME: {{.*}} "-o" "[[OBJ_DEV_A_900:.*(o|bc)]]" "-x" "hip"
// CHECK-SAME: {{.*}} [[A_SRC]]
// CHECK-NOT: {{".*llvm-link"}}
// CHECK-NOT: {{".*opt"}}
// CHECK-NOT: {{".*llc"}}
-// CHECK: [[LLD]] "-flavor" "gnu" "-m" "elf64_amdgpu" "--no-undefined"
"-shared"
-// CHECK-SAME: "-o" "[[IMG_DEV_A_900:.*out]]" [[OBJ_DEV_A_900]]
+// OLD: [[LLD]] "-flavor" "gnu" "-m" "elf64_amdgpu" "--no-undefined" "-shared"
+// OLD-SAME: "-o" "[[IMG_DEV_A_900:.*out]]" "[[OBJ_DEV_A_900]]"
//
// Bundle and embed device code in host object for a.cu.
//
-// CHECK: [[BUNDLER:".*clang-offload-bundler"]] "-type=o"
-// CHECK-SAME: "-bundle-align=4096"
-// CHECK-SAME:
"-targets={{.*}},hipv4-amdgcn-amd-amdhsa--gfx803,hipv4-amdgcn-amd-amdhsa--gfx900"
-// CHECK-SAME: "-input={{.*}}" "-input=[[IMG_DEV_A_803]]"
"-input=[[IMG_DEV_A_900]]" "-output=[[BUNDLE_A:.*hipfb]]"
+// OLD: [[BUNDLER:".*clang-offload-bundler"]] "-type=o"
+// OLD-SAME: "-bundle-align=4096"
+// OLD-SAME:
"-targets={{.*}},hipv4-amdgcn-amd-amdhsa--gfx803,hipv4-amdgcn-amd-amdhsa--gfx900"
+// OLD-SAME: "-input={{.*}}" "-input=[[IMG_DEV_A_803]]"
"-input=[[IMG_DEV_A_900]]" "-output=[[BUNDLE_A:.*hipfb]]"
+
+// NEW: [[PACKAGER:".*clang-offload-packager"]] "-o" "[[PACKAGE_A:.*.out]]"
+// NEW-SAME:
"--image=file=[[OBJ_DEV_A_803]],triple=amdgcn-amd-amdhsa,arch=gfx803,kind=hip"
+// NEW-SAME:
"--image=file=[[OBJ_DEV_A_900]],triple=amdgcn-amd-amdhsa,arch=gfx900,kind=hip"
// CHECK: [[CLANG]] "-cc1" "-triple" "x86_64-unknown-linux-gnu"
// CHECK-SAME: "-aux-triple" "amdgcn-amd-amdhsa"
// CHECK-SAME: "-emit-obj"
// CHECK-SAME: {{.*}} "-main-file-name" "a.cu"
-// CHECK-SAME: {{.*}} "-fcuda-include-gpubinary" "[[BUNDLE_A]]"
-// CHECK-SAME: {{.*}} "-o" [[A_OBJ_HOST:".*o"]] "-x" "hip"
+// OLD-SAME: {{.*}} "-fcuda-include-gpubinary" "[[BUNDLE_A]]"
+// NEW-SAME: {{.*}} "-fembed-offload-object=[[PACKAGE_A]]"
+// OLD-SAME: {{.*}} "-o" [[A_OBJ_HOST:".*o"]] "-x" "hip"
+// NEW-SAME: {{.*}} "-o" [[A_OBJ_HOST_TMP:".*o"]] "-x" "hip"
// CHECK-SAME: {{.*}} [[A_SRC]]
+// NEW: [[WRAPPER:".*clang-linker-wrapper]]"
{{.*}}"--host-triple=x86_64-unknown-linux-gnu"
+// NEW: "--linker-path={{.*}}" "-o" [[A_OBJ_HOST:".*o"]] [[A_OBJ_HOST_TMP]]
"-r"
+
//
// Compile device code in b.hip to code object for gfx803.
//
// CHECK: [[CLANG:".*clang.*"]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
// CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
-// CHECK-SAME: "-emit-obj"
+// CHECK-SAME: "-emit-{{(obj|llvm-bc)}}"
// CHECK-SAME: {{.*}} "-main-file-name" "b.hip"
// CHECK-SAME: "-fcuda-is-device" "-fno-threadsafe-statics" "-mllvm"
"-amdgpu-internalize-symbols"
// CHECK-SAME: "-fcuda-allow-variadic-functions" "-fvisibility=hidden"
// CHECK-SAME: "-fapply-global-visibility-to-externs"
// CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
// CHECK-SAME: "-target-cpu" "gfx803"
-// CHECK-SAME: {{.*}} "-o" [[OBJ_DEV_B_803:".*o"]] "-x" "hip"
+// CHECK-SAME: {{.*}} "-o" "[[OBJ_DEV_B_803:.*(o|bc)]]" "-x" "hip"
// CHECK-SAME: {{.*}} [[B_SRC:".*b.hip"]]
// CHECK-NOT: {{".*llvm-link"}}
// CHECK-NOT: {{".*opt"}}
// CHECK-NOT: {{".*llc"}}
-// CHECK: [[LLD]] "-flavor" "gnu" "-m" "elf64_amdgpu" "--no-undefined"
"-shared"
-// CHECK-SAME: "-o" "[[IMG_DEV_B_803:.*out]]" [[OBJ_DEV_B_803]]
+// OLD: [[LLD]] "-flavor" "gnu" "-m" "elf64_amdgpu" "--no-undefined" "-shared"
+// OLD-SAME: "-o" "[[IMG_DEV_B_803:.*out]]" "[[OBJ_DEV_B_803]]"
//
// Compile device code in b.hip to code object for gfx900.
@@ -133,40 +143,49 @@
// CHECK: [[CLANG:".*clang.*"]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
// CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
-// CHECK-SAME: "-emit-obj"
+// CHECK-SAME: "-emit-{{(obj|llvm-bc)}}"
// CHECK-SAME: {{.*}} "-main-file-name" "b.hip"
// CHECK-SAME: "-fcuda-is-device" "-fno-threadsafe-statics" "-mllvm"
"-amdgpu-internalize-symbols"
// CHECK-SAME: "-fcuda-allow-variadic-functions" "-fvisibility=hidden"
// CHECK-SAME: "-fapply-global-visibility-to-externs"
// CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
// CHECK-SAME: "-target-cpu" "gfx900"
-// CHECK-SAME: {{.*}} "-o" [[OBJ_DEV_B_900:".*o"]] "-x" "hip"
+// CHECK-SAME: {{.*}} "-o" "[[OBJ_DEV_B_900:.*(o|bc)]]" "-x" "hip"
// CHECK-SAME: {{.*}} [[B_SRC]]
// CHECK-NOT: {{".*llvm-link"}}
// CHECK-NOT: {{".*opt"}}
// CHECK-NOT: {{".*llc"}}
-// CHECK: [[LLD]] "-flavor" "gnu" "-m" "elf64_amdgpu" "--no-undefined"
"-shared"
-// CHECK-SAME: "-o" "[[IMG_DEV_B_900:.*out]]" [[OBJ_DEV_B_900]]
+// OLD: [[LLD]] "-flavor" "gnu" "-m" "elf64_amdgpu" "--no-undefined" "-shared"
+// OLD-SAME: "-o" "[[IMG_DEV_B_900:.*out]]" "[[OBJ_DEV_B_900]]"
//
// Bundle and embed device code in host object for b.hip.
//
-// CHECK: [[BUNDLER:".*clang-offload-bundler"]] "-type=o"
-// CHECK-SAME: "-bundle-align=4096"
-// CHECK-SAME:
"-targets={{.*}},hipv4-amdgcn-amd-amdhsa--gfx803,hipv4-amdgcn-amd-amdhsa--gfx900"
-// CHECK-SAME: "-input={{.*}}" "-input=[[IMG_DEV_B_803]]"
"-input=[[IMG_DEV_B_900]]" "-output=[[BUNDLE_A:.*hipfb]]"
+// OLD: [[BUNDLER:".*clang-offload-bundler"]] "-type=o"
+// OLD-SAME: "-bundle-align=4096"
+// OLD-SAME:
"-targets={{.*}},hipv4-amdgcn-amd-amdhsa--gfx803,hipv4-amdgcn-amd-amdhsa--gfx900"
+// OLD-SAME: "-input={{.*}}" "-input=[[IMG_DEV_B_803]]"
"-input=[[IMG_DEV_B_900]]" "-output=[[BUNDLE_B:.*hipfb]]"
+
+// NEW: [[PACKAGER:".*clang-offload-packager"]] "-o" "[[PACKAGE_B:.*.out]]"
+// NEW-SAME:
"--image=file=[[OBJ_DEV_B_803]],triple=amdgcn-amd-amdhsa,arch=gfx803,kind=hip"
+// NEW-SAME:
"--image=file=[[OBJ_DEV_B_900]],triple=amdgcn-amd-amdhsa,arch=gfx900,kind=hip"
// CHECK: [[CLANG]] "-cc1" "-triple" "x86_64-unknown-linux-gnu"
// CHECK-SAME: "-aux-triple" "amdgcn-amd-amdhsa"
// CHECK-SAME: "-emit-obj"
// CHECK-SAME: {{.*}} "-main-file-name" "b.hip"
-// CHECK-SAME: {{.*}} "-fcuda-include-gpubinary" "[[BUNDLE_A]]"
-// CHECK-SAME: {{.*}} "-o" [[B_OBJ_HOST:".*o"]] "-x" "hip"
+// OLD-SAME: {{.*}} "-fcuda-include-gpubinary" "[[BUNDLE_B]]"
+// NEW-SAME: {{.*}} "-fembed-offload-object=[[PACKAGE_B]]"
+// OLD-SAME: {{.*}} "-o" [[B_OBJ_HOST:".*o"]] "-x" "hip"
+// NEW-SAME: {{.*}} "-o" [[B_OBJ_HOST_TMP:".*o"]] "-x" "hip"
// CHECK-SAME: {{.*}} [[B_SRC]]
+// NEW: [[WRAPPER:".*clang-linker-wrapper]]"
{{.*}}"--host-triple=x86_64-unknown-linux-gnu"
+// NEW: "--linker-path={{.*}}" "-o" [[B_OBJ_HOST:".*o"]] [[B_OBJ_HOST_TMP]]
"-r"
+
//
// Link host objects.
//
>From 501b77e186ee9518b0ee6bddbda3ff5fd6318945 Mon Sep 17 00:00:00 2001
From: "Yaxun (Sam) Liu" <yaxun....@amd.com>
Date: Wed, 11 Jun 2025 17:37:29 -0400
Subject: [PATCH 2/3] Fix assertion with -flto
Missing offload linker wrapper job action to wrap device
binary for -flto.
---
clang/lib/Driver/Driver.cpp | 5 ++++-
clang/test/Driver/hip-phases.hip | 11 +++++++++--
2 files changed, 13 insertions(+), 3 deletions(-)
diff --git a/clang/lib/Driver/Driver.cpp b/clang/lib/Driver/Driver.cpp
index 98bc4b91a0bcd..060f76fb653c9 100644
--- a/clang/lib/Driver/Driver.cpp
+++ b/clang/lib/Driver/Driver.cpp
@@ -4882,7 +4882,10 @@ Action *Driver::BuildOffloadingActions(Compilation &C,
// For HIP non-rdc non-device-only compilation, create a linker wrapper
// action for each host object to link, bundle and wrap device files in
// it.
- if (isa<AssembleJobAction>(HostAction) && HIPNoRDC && !offloadDeviceOnly()) {
+ if ((isa<AssembleJobAction>(HostAction) ||
+ (isa<BackendJobAction>(HostAction) &&
+ HostAction->getType() == types::TY_LTO_BC)) &&
+ HIPNoRDC && !offloadDeviceOnly()) {
ActionList AL{HostAction};
HostAction = C.MakeAction<LinkerWrapperJobAction>(AL, types::TY_Object);
HostAction->propagateHostOffloadInfo(C.getActiveOffloadKinds(),
diff --git a/clang/test/Driver/hip-phases.hip b/clang/test/Driver/hip-phases.hip
index 996d72e58755a..d8a58b78d6d5c 100644
--- a/clang/test/Driver/hip-phases.hip
+++ b/clang/test/Driver/hip-phases.hip
@@ -12,6 +12,9 @@
// RUN: %clang -x hip --target=x86_64-unknown-linux-gnu -ccc-print-phases \
// RUN: --offload-new-driver --cuda-gpu-arch=gfx803 %s 2>&1 \
// RUN: | FileCheck -check-prefixes=BIN,NEW,NEWN %s
+// RUN: %clang -x hip --target=x86_64-unknown-linux-gnu -ccc-print-phases \
+// RUN: --offload-new-driver --cuda-gpu-arch=gfx803 -flto -c %s 2>&1 \
+// RUN: | FileCheck -check-prefixes=BIN,NEW,NEWLTO %s
//
// RUN: %clang -x hip --target=x86_64-unknown-linux-gnu -ccc-print-phases \
// RUN: --no-offload-new-driver --cuda-gpu-arch=gfx803 -fgpu-rdc %s 2>&1 \
@@ -45,10 +48,14 @@
// OLDR-DAG: [[P11:[0-9]+]]: offload, "device-[[T]] (amdgcn-amd-amdhsa)"
{[[P10]]}, object
// OLDN-DAG: [[P12:[0-9]+]]: backend, {[[P11]]}, assembler, (host-[[T]])
// OLDN-DAG: [[P13:[0-9]+]]: assembler, {[[P12]]}, object, (host-[[T]])
-// NEW-DAG: [[P12:[0-9]+]]: backend, {[[P11]]}, assembler, (host-[[T]])
-// NEW-DAG: [[P13:[0-9]+]]: assembler, {[[P12]]}, object, (host-[[T]])
+// NEWN-DAG: [[P12:[0-9]+]]: backend, {[[P11]]}, assembler, (host-[[T]])
+// NEWN-DAG: [[P13:[0-9]+]]: assembler, {[[P12]]}, object, (host-[[T]])
+// NEWLTO-DAG: [[P13:[0-9]+]]: backend, {[[P11]]}, lto-bc, (host-hip)
+// NEWR-DAG: [[P12:[0-9]+]]: backend, {[[P11]]}, assembler, (host-[[T]])
+// NEWR-DAG: [[P13:[0-9]+]]: assembler, {[[P12]]}, object, (host-[[T]])
// OLDN-DAG: [[P14:[0-9]+]]: linker, {[[P13]]}, image, (host-[[T]])
// NEWN-DAG: [[P14:[0-9]+]]: clang-linker-wrapper, {[[P13]]}, object,
(host-[[T]])
+// NEWLTO-DAG: [[P14:[0-9]+]]: clang-linker-wrapper, {[[P13]]}, object,
(host-[[T]])
// OLDR-DAG: [[P14:[0-9]+]]: linker, {[[P13]], [[P11]]}, image, (host-[[T]])
// NEWR-DAG: [[P14:[0-9]+]]: clang-linker-wrapper, {[[P13]]}, image,
(host-[[T]])
// NEWN-DAG: [[P15:[0-9]+]]: linker, {[[P14]]}, image
>From 7b488bb9e44bc8541ea32fc2f8aa12962fb3babf Mon Sep 17 00:00:00 2001
From: "Yaxun (Sam) Liu" <yaxun....@amd.com>
Date: Thu, 12 Jun 2025 15:53:34 -0400
Subject: [PATCH 3/3] Fix issue about mutiple source files
HIP now uses llvm_offload_entries as section name.
---
clang/test/Driver/linker-wrapper.c | 1 +
.../ClangLinkerWrapper.cpp | 31 +++++++++----------
2 files changed, 16 insertions(+), 16 deletions(-)
diff --git a/clang/test/Driver/linker-wrapper.c
b/clang/test/Driver/linker-wrapper.c
index a7e98e7351d98..80b1a5745a123 100644
--- a/clang/test/Driver/linker-wrapper.c
+++ b/clang/test/Driver/linker-wrapper.c
@@ -223,6 +223,7 @@ __attribute__((visibility("protected"), used)) int x;
// RELOCATABLE-LINK-HIP: clang-offload-bundler{{.*}} -type=o
-bundle-align=4096
-targets=host-x86_64-unknown-linux-gnu,hip-amdgcn-amd-amdhsa--gfx90a
-input={{/dev/null|NUL}} -input={{.*}} -output={{.*}}
// RELOCATABLE-LINK-HIP: /usr/bin/ld.lld{{.*}}-r
// RELOCATABLE-LINK-HIP: llvm-objcopy{{.*}}a.out --remove-section
.llvm.offloading
+// RELOCATABLE-LINK-HIP: --rename-section llvm_offload_entries
// RUN: clang-offload-packager -o %t.out \
// RUN:
--image=file=%t.elf.o,kind=cuda,triple=nvptx64-nvidia-cuda,arch=sm_89 \
diff --git a/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp
b/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp
index 95b6f74af1f13..b8019fac4c2ec 100644
--- a/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp
+++ b/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp
@@ -310,22 +310,21 @@ Error relocateOffloadSection(const ArgList &Args,
StringRef Output) {
// Remove the old .llvm.offloading section to prevent further linking.
ObjcopyArgs.emplace_back("--remove-section");
ObjcopyArgs.emplace_back(".llvm.offloading");
- for (StringRef Prefix : {"omp", "cuda", "hip"}) {
- auto Section = (Prefix + "_offloading_entries").str();
- // Rename the offloading entires to make them private to this link unit.
- ObjcopyArgs.emplace_back("--rename-section");
- ObjcopyArgs.emplace_back(
- Args.MakeArgString(Section + "=" + Section + Suffix));
-
- // Rename the __start_ / __stop_ symbols appropriately to iterate over the
- // newly renamed section containing the offloading entries.
- ObjcopyArgs.emplace_back("--redefine-sym");
- ObjcopyArgs.emplace_back(Args.MakeArgString("__start_" + Section + "=" +
- "__start_" + Section +
Suffix));
- ObjcopyArgs.emplace_back("--redefine-sym");
- ObjcopyArgs.emplace_back(Args.MakeArgString("__stop_" + Section + "=" +
- "__stop_" + Section + Suffix));
- }
+ StringRef Prefix = "llvm";
+ auto Section = (Prefix + "llvm_offload_entries").str();
+ // Rename the offloading entires to make them private to this link unit.
+ ObjcopyArgs.emplace_back("--rename-section");
+ ObjcopyArgs.emplace_back(
+ Args.MakeArgString(Section + "=" + Section + Suffix));
+
+ // Rename the __start_ / __stop_ symbols appropriately to iterate over the
+ // newly renamed section containing the offloading entries.
+ ObjcopyArgs.emplace_back("--redefine-sym");
+ ObjcopyArgs.emplace_back(Args.MakeArgString("__start_" + Section + "=" +
+ "__start_" + Section + Suffix));
+ ObjcopyArgs.emplace_back("--redefine-sym");
+ ObjcopyArgs.emplace_back(Args.MakeArgString("__stop_" + Section + "=" +
+ "__stop_" + Section + Suffix));
if (Error Err = executeCommands(*ObjcopyPath, ObjcopyArgs))
return Err;
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
