mirror of
https://github.com/llvm/llvm-project.git
synced 2025-04-17 18:16:42 +00:00
[Offload] Unify offloading entries into a single section (#125731)
Summary: This patch unifies the existing offloading entires into a single section called `llvm_offload_entires`. This lets us use a more unified offloading infrastructure so that all targets share the same handling. The effect is that people in the runtimes now need to check if the kind is what they expect, but the expectation is that you can combine multiple potential providers into a compile job. Doesn't fully work yet because of other runtime issues, but some day. Mostly this helps the future of liboffload where we want to handle different languages than OpenMP.
This commit is contained in:
Joseph Huber
GitHub
parent
e833e5276c
commit
f1e917d07b
@ -40,8 +40,6 @@ class CGNVCUDARuntime : public CGCUDARuntime {
|
||||
|
||||
/// The prefix used for function calls and section names (CUDA, HIP, LLVM)
|
||||
StringRef Prefix;
|
||||
/// TODO: We should transition the OpenMP section to LLVM/Offload
|
||||
StringRef SectionPrefix;
|
||||
|
||||
private:
|
||||
llvm::IntegerType *IntTy, *SizeTy;
|
||||
@ -234,13 +232,12 @@ CGNVCUDARuntime::CGNVCUDARuntime(CodeGenModule &CGM)
|
||||
VoidTy = CGM.VoidTy;
|
||||
PtrTy = CGM.UnqualPtrTy;
|
||||
|
||||
if (CGM.getLangOpts().OffloadViaLLVM) {
|
||||
if (CGM.getLangOpts().OffloadViaLLVM)
|
||||
Prefix = "llvm";
|
||||
SectionPrefix = "omp";
|
||||
} else if (CGM.getLangOpts().HIP)
|
||||
SectionPrefix = Prefix = "hip";
|
||||
else if (CGM.getLangOpts().HIP)
|
||||
Prefix = "hip";
|
||||
else
|
||||
SectionPrefix = Prefix = "cuda";
|
||||
Prefix = "cuda";
|
||||
}
|
||||
|
||||
llvm::FunctionCallee CGNVCUDARuntime::getSetupArgumentFn() const {
|
||||
@ -1198,17 +1195,19 @@ void CGNVCUDARuntime::transformManagedVars() {
|
||||
// register the symbols with the linked device image.
|
||||
void CGNVCUDARuntime::createOffloadingEntries() {
|
||||
SmallVector<char, 32> Out;
|
||||
StringRef Section = (SectionPrefix + "_offloading_entries").toStringRef(Out);
|
||||
llvm::object::OffloadKind Kind = CGM.getLangOpts().HIP
|
||||
? llvm::object::OffloadKind::OFK_HIP
|
||||
: llvm::object::OffloadKind::OFK_Cuda;
|
||||
// For now, just spoof this as OpenMP because that's the runtime it uses.
|
||||
if (CGM.getLangOpts().OffloadViaLLVM)
|
||||
Kind = llvm::object::OffloadKind::OFK_OpenMP;
|
||||
|
||||
llvm::Module &M = CGM.getModule();
|
||||
for (KernelInfo &I : EmittedKernels)
|
||||
llvm::offloading::emitOffloadingEntry(
|
||||
M, Kind, KernelHandles[I.Kernel->getName()],
|
||||
getDeviceSideName(cast<NamedDecl>(I.D)), /*Flags=*/0, /*Data=*/0,
|
||||
llvm::offloading::OffloadGlobalEntry, Section);
|
||||
llvm::offloading::OffloadGlobalEntry);
|
||||
|
||||
for (VarInfo &I : DeviceVars) {
|
||||
uint64_t VarSize =
|
||||
@ -1233,23 +1232,23 @@ void CGNVCUDARuntime::createOffloadingEntries() {
|
||||
llvm::offloading::emitOffloadingEntry(
|
||||
M, Kind, I.Var, getDeviceSideName(I.D), VarSize,
|
||||
llvm::offloading::OffloadGlobalManagedEntry | Flags,
|
||||
/*Data=*/I.Var->getAlignment(), Section, ManagedVar);
|
||||
/*Data=*/I.Var->getAlignment(), ManagedVar);
|
||||
} else {
|
||||
llvm::offloading::emitOffloadingEntry(
|
||||
M, Kind, I.Var, getDeviceSideName(I.D), VarSize,
|
||||
llvm::offloading::OffloadGlobalEntry | Flags,
|
||||
/*Data=*/0, Section);
|
||||
/*Data=*/0);
|
||||
}
|
||||
} else if (I.Flags.getKind() == DeviceVarFlags::Surface) {
|
||||
llvm::offloading::emitOffloadingEntry(
|
||||
M, Kind, I.Var, getDeviceSideName(I.D), VarSize,
|
||||
llvm::offloading::OffloadGlobalSurfaceEntry | Flags,
|
||||
I.Flags.getSurfTexType(), Section);
|
||||
I.Flags.getSurfTexType());
|
||||
} else if (I.Flags.getKind() == DeviceVarFlags::Texture) {
|
||||
llvm::offloading::emitOffloadingEntry(
|
||||
M, Kind, I.Var, getDeviceSideName(I.D), VarSize,
|
||||
llvm::offloading::OffloadGlobalTextureEntry | Flags,
|
||||
I.Flags.getSurfTexType(), Section);
|
||||
I.Flags.getSurfTexType());
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@ -18,62 +18,62 @@
|
||||
|
||||
//.
|
||||
// CUDA: @managed = global i32 undef, align 4
|
||||
// CUDA: @.offloading.entry_name = internal unnamed_addr constant [8 x i8] c"_Z3foov\00", section ".llvm.rodata.offloading", align 1
|
||||
// CUDA: @.offloading.entry._Z3foov = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 0, ptr @_Z18__device_stub__foov, ptr @.offloading.entry_name, i64 0, i64 0, ptr null }, section "cuda_offloading_entries", align 1
|
||||
// CUDA: @.offloading.entry_name.1 = internal unnamed_addr constant [11 x i8] c"_Z6kernelv\00", section ".llvm.rodata.offloading", align 1
|
||||
// CUDA: @.offloading.entry._Z6kernelv = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 0, ptr @_Z21__device_stub__kernelv, ptr @.offloading.entry_name.1, i64 0, i64 0, ptr null }, section "cuda_offloading_entries", align 1
|
||||
// CUDA: @.offloading.entry_name.2 = internal unnamed_addr constant [4 x i8] c"var\00", section ".llvm.rodata.offloading", align 1
|
||||
// CUDA: @.offloading.entry.var = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 0, ptr @var, ptr @.offloading.entry_name.2, i64 4, i64 0, ptr null }, section "cuda_offloading_entries", align 1
|
||||
// CUDA: @.offloading.entry_name.3 = internal unnamed_addr constant [8 x i8] c"managed\00", section ".llvm.rodata.offloading", align 1
|
||||
// CUDA: @.offloading.entry.managed = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 0, ptr @managed, ptr @.offloading.entry_name.3, i64 4, i64 0, ptr null }, section "cuda_offloading_entries", align 1
|
||||
// CUDA: @.offloading.entry_name.4 = internal unnamed_addr constant [5 x i8] c"surf\00", section ".llvm.rodata.offloading", align 1
|
||||
// CUDA: @.offloading.entry.surf = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 2, ptr @surf, ptr @.offloading.entry_name.4, i64 4, i64 1, ptr null }, section "cuda_offloading_entries", align 1
|
||||
// CUDA: @.offloading.entry_name.5 = internal unnamed_addr constant [4 x i8] c"tex\00", section ".llvm.rodata.offloading", align 1
|
||||
// CUDA: @.offloading.entry.tex = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 3, ptr @tex, ptr @.offloading.entry_name.5, i64 4, i64 1, ptr null }, section "cuda_offloading_entries", align 1
|
||||
// CUDA: @.offloading.entry_name = internal unnamed_addr constant [8 x i8] c"_Z3foov\00", section ".llvm.rodata.offloading"
|
||||
// CUDA: @.offloading.entry._Z3foov = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 0, ptr @_Z18__device_stub__foov, ptr @.offloading.entry_name, i64 0, i64 0, ptr null }, section "llvm_offload_entries"
|
||||
// CUDA: @.offloading.entry_name.1 = internal unnamed_addr constant [11 x i8] c"_Z6kernelv\00", section ".llvm.rodata.offloading"
|
||||
// CUDA: @.offloading.entry._Z6kernelv = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 0, ptr @_Z21__device_stub__kernelv, ptr @.offloading.entry_name.1, i64 0, i64 0, ptr null }, section "llvm_offload_entries"
|
||||
// CUDA: @.offloading.entry_name.2 = internal unnamed_addr constant [4 x i8] c"var\00", section ".llvm.rodata.offloading"
|
||||
// CUDA: @.offloading.entry.var = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 0, ptr @var, ptr @.offloading.entry_name.2, i64 4, i64 0, ptr null }, section "llvm_offload_entries"
|
||||
// CUDA: @.offloading.entry_name.3 = internal unnamed_addr constant [8 x i8] c"managed\00", section ".llvm.rodata.offloading"
|
||||
// CUDA: @.offloading.entry.managed = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 0, ptr @managed, ptr @.offloading.entry_name.3, i64 4, i64 0, ptr null }, section "llvm_offload_entries"
|
||||
// CUDA: @.offloading.entry_name.4 = internal unnamed_addr constant [5 x i8] c"surf\00", section ".llvm.rodata.offloading"
|
||||
// CUDA: @.offloading.entry.surf = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 2, ptr @surf, ptr @.offloading.entry_name.4, i64 4, i64 1, ptr null }, section "llvm_offload_entries"
|
||||
// CUDA: @.offloading.entry_name.5 = internal unnamed_addr constant [4 x i8] c"tex\00", section ".llvm.rodata.offloading"
|
||||
// CUDA: @.offloading.entry.tex = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 3, ptr @tex, ptr @.offloading.entry_name.5, i64 4, i64 1, ptr null }, section "llvm_offload_entries"
|
||||
//.
|
||||
// HIP: @managed.managed = global i32 0, align 4
|
||||
// HIP: @managed = externally_initialized global ptr null
|
||||
// HIP: @.offloading.entry_name = internal unnamed_addr constant [8 x i8] c"_Z3foov\00", section ".llvm.rodata.offloading", align 1
|
||||
// HIP: @.offloading.entry._Z3foov = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 0, ptr @_Z3foov, ptr @.offloading.entry_name, i64 0, i64 0, ptr null }, section "hip_offloading_entries", align 1
|
||||
// HIP: @.offloading.entry_name.1 = internal unnamed_addr constant [11 x i8] c"_Z6kernelv\00", section ".llvm.rodata.offloading", align 1
|
||||
// HIP: @.offloading.entry._Z6kernelv = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 0, ptr @_Z6kernelv, ptr @.offloading.entry_name.1, i64 0, i64 0, ptr null }, section "hip_offloading_entries", align 1
|
||||
// HIP: @.offloading.entry_name.2 = internal unnamed_addr constant [4 x i8] c"var\00", section ".llvm.rodata.offloading", align 1
|
||||
// HIP: @.offloading.entry.var = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 0, ptr @var, ptr @.offloading.entry_name.2, i64 4, i64 0, ptr null }, section "hip_offloading_entries", align 1
|
||||
// HIP: @.offloading.entry_name.3 = internal unnamed_addr constant [8 x i8] c"managed\00", section ".llvm.rodata.offloading", align 1
|
||||
// HIP: @.offloading.entry.managed = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 1, ptr @managed.managed, ptr @.offloading.entry_name.3, i64 4, i64 4, ptr @managed }, section "hip_offloading_entries", align 1
|
||||
// HIP: @.offloading.entry_name.4 = internal unnamed_addr constant [5 x i8] c"surf\00", section ".llvm.rodata.offloading", align 1
|
||||
// HIP: @.offloading.entry.surf = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 2, ptr @surf, ptr @.offloading.entry_name.4, i64 4, i64 1, ptr null }, section "hip_offloading_entries", align 1
|
||||
// HIP: @.offloading.entry_name.5 = internal unnamed_addr constant [4 x i8] c"tex\00", section ".llvm.rodata.offloading", align 1
|
||||
// HIP: @.offloading.entry.tex = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 3, ptr @tex, ptr @.offloading.entry_name.5, i64 4, i64 1, ptr null }, section "hip_offloading_entries", align 1
|
||||
// HIP: @.offloading.entry_name = internal unnamed_addr constant [8 x i8] c"_Z3foov\00", section ".llvm.rodata.offloading"
|
||||
// HIP: @.offloading.entry._Z3foov = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 0, ptr @_Z3foov, ptr @.offloading.entry_name, i64 0, i64 0, ptr null }, section "llvm_offload_entries"
|
||||
// HIP: @.offloading.entry_name.1 = internal unnamed_addr constant [11 x i8] c"_Z6kernelv\00", section ".llvm.rodata.offloading"
|
||||
// HIP: @.offloading.entry._Z6kernelv = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 0, ptr @_Z6kernelv, ptr @.offloading.entry_name.1, i64 0, i64 0, ptr null }, section "llvm_offload_entries"
|
||||
// HIP: @.offloading.entry_name.2 = internal unnamed_addr constant [4 x i8] c"var\00", section ".llvm.rodata.offloading"
|
||||
// HIP: @.offloading.entry.var = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 0, ptr @var, ptr @.offloading.entry_name.2, i64 4, i64 0, ptr null }, section "llvm_offload_entries"
|
||||
// HIP: @.offloading.entry_name.3 = internal unnamed_addr constant [8 x i8] c"managed\00", section ".llvm.rodata.offloading"
|
||||
// HIP: @.offloading.entry.managed = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 1, ptr @managed.managed, ptr @.offloading.entry_name.3, i64 4, i64 4, ptr @managed }, section "llvm_offload_entries"
|
||||
// HIP: @.offloading.entry_name.4 = internal unnamed_addr constant [5 x i8] c"surf\00", section ".llvm.rodata.offloading"
|
||||
// HIP: @.offloading.entry.surf = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 2, ptr @surf, ptr @.offloading.entry_name.4, i64 4, i64 1, ptr null }, section "llvm_offload_entries"
|
||||
// HIP: @.offloading.entry_name.5 = internal unnamed_addr constant [4 x i8] c"tex\00", section ".llvm.rodata.offloading"
|
||||
// HIP: @.offloading.entry.tex = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 3, ptr @tex, ptr @.offloading.entry_name.5, i64 4, i64 1, ptr null }, section "llvm_offload_entries"
|
||||
//.
|
||||
// CUDA-COFF: @managed = dso_local global i32 undef, align 4
|
||||
// CUDA-COFF: @.offloading.entry_name = internal unnamed_addr constant [8 x i8] c"_Z3foov\00", section ".llvm.rodata.offloading", align 1
|
||||
// CUDA-COFF: @.offloading.entry._Z3foov = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 0, ptr @_Z18__device_stub__foov, ptr @.offloading.entry_name, i64 0, i64 0, ptr null }, section "cuda_offloading_entries$OE", align 1
|
||||
// CUDA-COFF: @.offloading.entry_name.1 = internal unnamed_addr constant [11 x i8] c"_Z6kernelv\00", section ".llvm.rodata.offloading", align 1
|
||||
// CUDA-COFF: @.offloading.entry._Z6kernelv = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 0, ptr @_Z21__device_stub__kernelv, ptr @.offloading.entry_name.1, i64 0, i64 0, ptr null }, section "cuda_offloading_entries$OE", align 1
|
||||
// CUDA-COFF: @.offloading.entry_name.2 = internal unnamed_addr constant [4 x i8] c"var\00", section ".llvm.rodata.offloading", align 1
|
||||
// CUDA-COFF: @.offloading.entry.var = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 0, ptr @var, ptr @.offloading.entry_name.2, i64 4, i64 0, ptr null }, section "cuda_offloading_entries$OE", align 1
|
||||
// CUDA-COFF: @.offloading.entry_name.3 = internal unnamed_addr constant [8 x i8] c"managed\00", section ".llvm.rodata.offloading", align 1
|
||||
// CUDA-COFF: @.offloading.entry.managed = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 0, ptr @managed, ptr @.offloading.entry_name.3, i64 4, i64 0, ptr null }, section "cuda_offloading_entries$OE", align 1
|
||||
// CUDA-COFF: @.offloading.entry_name.4 = internal unnamed_addr constant [5 x i8] c"surf\00", section ".llvm.rodata.offloading", align 1
|
||||
// CUDA-COFF: @.offloading.entry.surf = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 2, ptr @surf, ptr @.offloading.entry_name.4, i64 4, i64 1, ptr null }, section "cuda_offloading_entries$OE", align 1
|
||||
// CUDA-COFF: @.offloading.entry_name.5 = internal unnamed_addr constant [4 x i8] c"tex\00", section ".llvm.rodata.offloading", align 1
|
||||
// CUDA-COFF: @.offloading.entry.tex = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 3, ptr @tex, ptr @.offloading.entry_name.5, i64 4, i64 1, ptr null }, section "cuda_offloading_entries$OE", align 1
|
||||
// CUDA-COFF: @.offloading.entry_name = internal unnamed_addr constant [8 x i8] c"_Z3foov\00", section ".llvm.rodata.offloading"
|
||||
// CUDA-COFF: @.offloading.entry._Z3foov = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 0, ptr @_Z18__device_stub__foov, ptr @.offloading.entry_name, i64 0, i64 0, ptr null }, section "llvm_offload_entries$OE"
|
||||
// CUDA-COFF: @.offloading.entry_name.1 = internal unnamed_addr constant [11 x i8] c"_Z6kernelv\00", section ".llvm.rodata.offloading"
|
||||
// CUDA-COFF: @.offloading.entry._Z6kernelv = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 0, ptr @_Z21__device_stub__kernelv, ptr @.offloading.entry_name.1, i64 0, i64 0, ptr null }, section "llvm_offload_entries$OE"
|
||||
// CUDA-COFF: @.offloading.entry_name.2 = internal unnamed_addr constant [4 x i8] c"var\00", section ".llvm.rodata.offloading"
|
||||
// CUDA-COFF: @.offloading.entry.var = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 0, ptr @var, ptr @.offloading.entry_name.2, i64 4, i64 0, ptr null }, section "llvm_offload_entries$OE"
|
||||
// CUDA-COFF: @.offloading.entry_name.3 = internal unnamed_addr constant [8 x i8] c"managed\00", section ".llvm.rodata.offloading"
|
||||
// CUDA-COFF: @.offloading.entry.managed = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 0, ptr @managed, ptr @.offloading.entry_name.3, i64 4, i64 0, ptr null }, section "llvm_offload_entries$OE"
|
||||
// CUDA-COFF: @.offloading.entry_name.4 = internal unnamed_addr constant [5 x i8] c"surf\00", section ".llvm.rodata.offloading"
|
||||
// CUDA-COFF: @.offloading.entry.surf = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 2, ptr @surf, ptr @.offloading.entry_name.4, i64 4, i64 1, ptr null }, section "llvm_offload_entries$OE"
|
||||
// CUDA-COFF: @.offloading.entry_name.5 = internal unnamed_addr constant [4 x i8] c"tex\00", section ".llvm.rodata.offloading"
|
||||
// CUDA-COFF: @.offloading.entry.tex = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 3, ptr @tex, ptr @.offloading.entry_name.5, i64 4, i64 1, ptr null }, section "llvm_offload_entries$OE"
|
||||
//.
|
||||
// HIP-COFF: @managed.managed = dso_local global i32 0, align 4
|
||||
// HIP-COFF: @managed = dso_local externally_initialized global ptr null
|
||||
// HIP-COFF: @.offloading.entry_name = internal unnamed_addr constant [8 x i8] c"_Z3foov\00", section ".llvm.rodata.offloading", align 1
|
||||
// HIP-COFF: @.offloading.entry._Z3foov = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 0, ptr @_Z3foov, ptr @.offloading.entry_name, i64 0, i64 0, ptr null }, section "hip_offloading_entries$OE", align 1
|
||||
// HIP-COFF: @.offloading.entry_name.1 = internal unnamed_addr constant [11 x i8] c"_Z6kernelv\00", section ".llvm.rodata.offloading", align 1
|
||||
// HIP-COFF: @.offloading.entry._Z6kernelv = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 0, ptr @_Z6kernelv, ptr @.offloading.entry_name.1, i64 0, i64 0, ptr null }, section "hip_offloading_entries$OE", align 1
|
||||
// HIP-COFF: @.offloading.entry_name.2 = internal unnamed_addr constant [4 x i8] c"var\00", section ".llvm.rodata.offloading", align 1
|
||||
// HIP-COFF: @.offloading.entry.var = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 0, ptr @var, ptr @.offloading.entry_name.2, i64 4, i64 0, ptr null }, section "hip_offloading_entries$OE", align 1
|
||||
// HIP-COFF: @.offloading.entry_name.3 = internal unnamed_addr constant [8 x i8] c"managed\00", section ".llvm.rodata.offloading", align 1
|
||||
// HIP-COFF: @.offloading.entry.managed = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 1, ptr @managed.managed, ptr @.offloading.entry_name.3, i64 4, i64 4, ptr @managed }, section "hip_offloading_entries$OE", align 1
|
||||
// HIP-COFF: @.offloading.entry_name.4 = internal unnamed_addr constant [5 x i8] c"surf\00", section ".llvm.rodata.offloading", align 1
|
||||
// HIP-COFF: @.offloading.entry.surf = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 2, ptr @surf, ptr @.offloading.entry_name.4, i64 4, i64 1, ptr null }, section "hip_offloading_entries$OE", align 1
|
||||
// HIP-COFF: @.offloading.entry_name.5 = internal unnamed_addr constant [4 x i8] c"tex\00", section ".llvm.rodata.offloading", align 1
|
||||
// HIP-COFF: @.offloading.entry.tex = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 3, ptr @tex, ptr @.offloading.entry_name.5, i64 4, i64 1, ptr null }, section "hip_offloading_entries$OE", align 1
|
||||
// HIP-COFF: @.offloading.entry_name = internal unnamed_addr constant [8 x i8] c"_Z3foov\00", section ".llvm.rodata.offloading"
|
||||
// HIP-COFF: @.offloading.entry._Z3foov = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 0, ptr @_Z3foov, ptr @.offloading.entry_name, i64 0, i64 0, ptr null }, section "llvm_offload_entries$OE"
|
||||
// HIP-COFF: @.offloading.entry_name.1 = internal unnamed_addr constant [11 x i8] c"_Z6kernelv\00", section ".llvm.rodata.offloading"
|
||||
// HIP-COFF: @.offloading.entry._Z6kernelv = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 0, ptr @_Z6kernelv, ptr @.offloading.entry_name.1, i64 0, i64 0, ptr null }, section "llvm_offload_entries$OE"
|
||||
// HIP-COFF: @.offloading.entry_name.2 = internal unnamed_addr constant [4 x i8] c"var\00", section ".llvm.rodata.offloading"
|
||||
// HIP-COFF: @.offloading.entry.var = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 0, ptr @var, ptr @.offloading.entry_name.2, i64 4, i64 0, ptr null }, section "llvm_offload_entries$OE"
|
||||
// HIP-COFF: @.offloading.entry_name.3 = internal unnamed_addr constant [8 x i8] c"managed\00", section ".llvm.rodata.offloading"
|
||||
// HIP-COFF: @.offloading.entry.managed = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 1, ptr @managed.managed, ptr @.offloading.entry_name.3, i64 4, i64 4, ptr @managed }, section "llvm_offload_entries$OE"
|
||||
// HIP-COFF: @.offloading.entry_name.4 = internal unnamed_addr constant [5 x i8] c"surf\00", section ".llvm.rodata.offloading"
|
||||
// HIP-COFF: @.offloading.entry.surf = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 2, ptr @surf, ptr @.offloading.entry_name.4, i64 4, i64 1, ptr null }, section "llvm_offload_entries$OE"
|
||||
// HIP-COFF: @.offloading.entry_name.5 = internal unnamed_addr constant [4 x i8] c"tex\00", section ".llvm.rodata.offloading"
|
||||
// HIP-COFF: @.offloading.entry.tex = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 3, ptr @tex, ptr @.offloading.entry_name.5, i64 4, i64 1, ptr null }, section "llvm_offload_entries$OE"
|
||||
//.
|
||||
// CUDA-LABEL: @_Z18__device_stub__foov(
|
||||
// CUDA-NEXT: entry:
|
||||
|
||||
@ -14,18 +14,18 @@
|
||||
// RUN: clang-linker-wrapper --print-wrapped-module --dry-run --host-triple=x86_64-unknown-windows-gnu \
|
||||
// RUN: --linker-path=/usr/bin/ld %t.o -o a.out 2>&1 | FileCheck %s --check-prefixes=OPENMP,OPENMP-COFF
|
||||
|
||||
// OPENMP-ELF: @__start_omp_offloading_entries = external hidden constant [0 x %struct.__tgt_offload_entry]
|
||||
// OPENMP-ELF-NEXT: @__stop_omp_offloading_entries = external hidden constant [0 x %struct.__tgt_offload_entry]
|
||||
// OPENMP-ELF-NEXT: @__dummy.omp_offloading_entries = internal constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "omp_offloading_entries"
|
||||
// OPENMP-ELF: @__start_llvm_offload_entries = external hidden constant [0 x %struct.__tgt_offload_entry]
|
||||
// OPENMP-ELF-NEXT: @__stop_llvm_offload_entries = external hidden constant [0 x %struct.__tgt_offload_entry]
|
||||
// OPENMP-ELF-NEXT: @__dummy.llvm_offload_entries = internal constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "llvm_offload_entries"
|
||||
|
||||
// OPENMP-COFF: @__start_omp_offloading_entries = weak_odr hidden constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "omp_offloading_entries$OA"
|
||||
// OPENMP-COFF-NEXT: @__stop_omp_offloading_entries = weak_odr hidden constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "omp_offloading_entries$OZ"
|
||||
// OPENMP-COFF: @__start_llvm_offload_entries = weak_odr hidden constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "llvm_offload_entries$OA"
|
||||
// OPENMP-COFF-NEXT: @__stop_llvm_offload_entries = weak_odr hidden constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "llvm_offload_entries$OZ"
|
||||
|
||||
// OPENMP-REL: @.omp_offloading.device_image = internal unnamed_addr constant [[[SIZE:[0-9]+]] x i8] c"\10\FF\10\AD{{.*}}", section ".llvm.offloading.relocatable", align 8
|
||||
|
||||
// OPENMP: @.omp_offloading.device_image = internal unnamed_addr constant [[[SIZE:[0-9]+]] x i8] c"\10\FF\10\AD{{.*}}", section ".llvm.offloading", align 8
|
||||
// OPENMP-NEXT: @.omp_offloading.device_images = internal unnamed_addr constant [1 x %__tgt_device_image] [%__tgt_device_image { ptr getelementptr ([[[BEGIN:[0-9]+]] x i8], ptr @.omp_offloading.device_image, i64 0, i64 144), ptr getelementptr ([[[END:[0-9]+]] x i8], ptr @.omp_offloading.device_image, i64 0, i64 144), ptr @__start_omp_offloading_entries, ptr @__stop_omp_offloading_entries }]
|
||||
// OPENMP-NEXT: @.omp_offloading.descriptor = internal constant %__tgt_bin_desc { i32 1, ptr @.omp_offloading.device_images, ptr @__start_omp_offloading_entries, ptr @__stop_omp_offloading_entries }
|
||||
// OPENMP-NEXT: @.omp_offloading.device_images = internal unnamed_addr constant [1 x %__tgt_device_image] [%__tgt_device_image { ptr getelementptr ([[[BEGIN:[0-9]+]] x i8], ptr @.omp_offloading.device_image, i64 0, i64 144), ptr getelementptr ([[[END:[0-9]+]] x i8], ptr @.omp_offloading.device_image, i64 0, i64 144), ptr @__start_llvm_offload_entries, ptr @__stop_llvm_offload_entries }]
|
||||
// OPENMP-NEXT: @.omp_offloading.descriptor = internal constant %__tgt_bin_desc { i32 1, ptr @.omp_offloading.device_images, ptr @__start_llvm_offload_entries, ptr @__stop_llvm_offload_entries }
|
||||
// OPENMP-NEXT: @llvm.global_ctors = appending global [1 x { i32, ptr, ptr }] [{ i32, ptr, ptr } { i32 101, ptr @.omp_offloading.descriptor_reg, ptr null }]
|
||||
|
||||
// OPENMP: define internal void @.omp_offloading.descriptor_reg() section ".text.startup" {
|
||||
@ -51,12 +51,12 @@
|
||||
// RUN: clang-linker-wrapper --print-wrapped-module --dry-run --host-triple=x86_64-unknown-windows-gnu \
|
||||
// RUN: --linker-path=/usr/bin/ld %t.o -o a.out 2>&1 | FileCheck %s --check-prefixes=CUDA,CUDA-COFF
|
||||
|
||||
// CUDA-ELF: @__start_cuda_offloading_entries = external hidden constant [0 x %struct.__tgt_offload_entry]
|
||||
// CUDA-ELF-NEXT: @__stop_cuda_offloading_entries = external hidden constant [0 x %struct.__tgt_offload_entry]
|
||||
// CUDA-ELF-NEXT: @__dummy.cuda_offloading_entries = internal constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "cuda_offloading_entries"
|
||||
// CUDA-ELF: @__start_llvm_offload_entries = external hidden constant [0 x %struct.__tgt_offload_entry]
|
||||
// CUDA-ELF-NEXT: @__stop_llvm_offload_entries = external hidden constant [0 x %struct.__tgt_offload_entry]
|
||||
// CUDA-ELF-NEXT: @__dummy.llvm_offload_entries = internal constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "llvm_offload_entries"
|
||||
|
||||
// CUDA-COFF: @__start_cuda_offloading_entries = weak_odr hidden constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "cuda_offloading_entries$OA"
|
||||
// CUDA-COFF-NEXT: @__stop_cuda_offloading_entries = weak_odr hidden constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "cuda_offloading_entries$OZ"
|
||||
// CUDA-COFF: @__start_llvm_offload_entries = weak_odr hidden constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "llvm_offload_entries$OA"
|
||||
// CUDA-COFF-NEXT: @__stop_llvm_offload_entries = weak_odr hidden constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "llvm_offload_entries$OZ"
|
||||
|
||||
// CUDA: @.fatbin_image = internal constant [0 x i8] zeroinitializer, section ".nv_fatbin"
|
||||
// CUDA-NEXT: @.fatbin_wrapper = internal constant %fatbin_wrapper { i32 1180844977, i32 1, ptr @.fatbin_image, ptr null }, section ".nvFatBinSegment", align 8
|
||||
@ -83,11 +83,11 @@
|
||||
//
|
||||
// CUDA: define internal void @.cuda.globals_reg(ptr %0) section ".text.startup" {
|
||||
// CUDA-NEXT: entry:
|
||||
// CUDA-NEXT: %1 = icmp ne ptr @__start_cuda_offloading_entries, @__stop_cuda_offloading_entries
|
||||
// CUDA-NEXT: %1 = icmp ne ptr @__start_llvm_offload_entries, @__stop_llvm_offload_entries
|
||||
// CUDA-NEXT: br i1 %1, label %while.entry, label %while.end
|
||||
//
|
||||
// CUDA: while.entry:
|
||||
// CUDA-NEXT: %entry1 = phi ptr [ @__start_cuda_offloading_entries, %entry ], [ %16, %if.end ]
|
||||
// CUDA-NEXT: %entry1 = phi ptr [ @__start_llvm_offload_entries, %entry ], [ %16, %if.end ]
|
||||
// CUDA-NEXT: %2 = getelementptr inbounds %struct.__tgt_offload_entry, ptr %entry1, i32 0, i32 4
|
||||
// CUDA-NEXT: %addr = load ptr, ptr %2, align 8
|
||||
// CUDA-NEXT: %3 = getelementptr inbounds %struct.__tgt_offload_entry, ptr %entry1, i32 0, i32 8
|
||||
@ -145,7 +145,7 @@
|
||||
//
|
||||
// CUDA: if.end:
|
||||
// CUDA-NEXT: %16 = getelementptr inbounds %struct.__tgt_offload_entry, ptr %entry1, i64 1
|
||||
// CUDA-NEXT: %17 = icmp eq ptr %16, @__stop_cuda_offloading_entries
|
||||
// CUDA-NEXT: %17 = icmp eq ptr %16, @__stop_llvm_offload_entries
|
||||
// CUDA-NEXT: br i1 %17, label %while.end, label %while.entry
|
||||
//
|
||||
// CUDA: while.end:
|
||||
@ -162,12 +162,12 @@
|
||||
// RUN: clang-linker-wrapper --print-wrapped-module --dry-run --host-triple=x86_64-unknown-windows-gnu \
|
||||
// RUN: --linker-path=/usr/bin/ld %t.o -o a.out 2>&1 | FileCheck %s --check-prefixes=HIP,HIP-COFF
|
||||
|
||||
// HIP-ELF: @__start_hip_offloading_entries = external hidden constant [0 x %struct.__tgt_offload_entry]
|
||||
// HIP-ELF-NEXT: @__stop_hip_offloading_entries = external hidden constant [0 x %struct.__tgt_offload_entry]
|
||||
// HIP-ELF-NEXT: @__dummy.hip_offloading_entries = internal constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "hip_offloading_entries"
|
||||
// HIP-ELF: @__start_llvm_offload_entries = external hidden constant [0 x %struct.__tgt_offload_entry]
|
||||
// HIP-ELF-NEXT: @__stop_llvm_offload_entries = external hidden constant [0 x %struct.__tgt_offload_entry]
|
||||
// HIP-ELF-NEXT: @__dummy.llvm_offload_entries = internal constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "llvm_offload_entries"
|
||||
|
||||
// HIP-COFF: @__start_hip_offloading_entries = weak_odr hidden constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "hip_offloading_entries$OA"
|
||||
// HIP-COFF-NEXT: @__stop_hip_offloading_entries = weak_odr hidden constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "hip_offloading_entries$OZ"
|
||||
// HIP-COFF: @__start_llvm_offload_entries = weak_odr hidden constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "llvm_offload_entries$OA"
|
||||
// HIP-COFF-NEXT: @__stop_llvm_offload_entries = weak_odr hidden constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "llvm_offload_entries$OZ"
|
||||
|
||||
// HIP: @.fatbin_image = internal constant [0 x i8] zeroinitializer, section ".hip_fatbin"
|
||||
// HIP-NEXT: @.fatbin_wrapper = internal constant %fatbin_wrapper { i32 1212764230, i32 1, ptr @.fatbin_image, ptr null }, section ".hipFatBinSegment", align 8
|
||||
@ -193,11 +193,11 @@
|
||||
//
|
||||
// HIP: define internal void @.hip.globals_reg(ptr %0) section ".text.startup" {
|
||||
// HIP-NEXT: entry:
|
||||
// HIP-NEXT: %1 = icmp ne ptr @__start_hip_offloading_entries, @__stop_hip_offloading_entries
|
||||
// HIP-NEXT: %1 = icmp ne ptr @__start_llvm_offload_entries, @__stop_llvm_offload_entries
|
||||
// HIP-NEXT: br i1 %1, label %while.entry, label %while.end
|
||||
//
|
||||
// HIP: while.entry:
|
||||
// HIP-NEXT: %entry1 = phi ptr [ @__start_hip_offloading_entries, %entry ], [ %16, %if.end ]
|
||||
// HIP-NEXT: %entry1 = phi ptr [ @__start_llvm_offload_entries, %entry ], [ %16, %if.end ]
|
||||
// HIP-NEXT: %2 = getelementptr inbounds %struct.__tgt_offload_entry, ptr %entry1, i32 0, i32 4
|
||||
// HIP-NEXT: %addr = load ptr, ptr %2, align 8
|
||||
// HIP-NEXT: %3 = getelementptr inbounds %struct.__tgt_offload_entry, ptr %entry1, i32 0, i32 8
|
||||
@ -257,7 +257,7 @@
|
||||
//
|
||||
// HIP: if.end:
|
||||
// HIP-NEXT: %16 = getelementptr inbounds %struct.__tgt_offload_entry, ptr %entry1, i64 1
|
||||
// HIP-NEXT: %17 = icmp eq ptr %16, @__stop_hip_offloading_entries
|
||||
// HIP-NEXT: %17 = icmp eq ptr %16, @__stop_llvm_offload_entries
|
||||
// HIP-NEXT: br i1 %17, label %while.end, label %while.entry
|
||||
//
|
||||
// HIP: while.end:
|
||||
|
||||
@ -27,11 +27,11 @@
|
||||
// HOST: [[SIZES:@.+]] = private unnamed_addr constant [3 x i64] [i64 4, i64 4, i64 4]
|
||||
// HOST: [[MAPTYPES:@.+]] = private unnamed_addr constant [3 x i64] [i64 35, i64 531, i64 531]
|
||||
// HOST: @.offloading.entry_name{{.*}} = internal unnamed_addr constant [{{[0-9]+}} x i8] c"c_decl_tgt_ref_ptr\00"
|
||||
// HOST: @.offloading.entry.c_decl_tgt_ref_ptr = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 1, ptr @c_decl_tgt_ref_ptr, ptr @.offloading.entry_name, i64 8, i64 0, ptr null }, section "omp_offloading_entries", align 1
|
||||
// HOST-COFF: @.offloading.entry.{{.*}} = weak constant %struct.__tgt_offload_entry { {{.*}} }, section "omp_offloading_entries$OE", align 1
|
||||
// HOST: @.offloading.entry.c_decl_tgt_ref_ptr = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 1, ptr @c_decl_tgt_ref_ptr, ptr @.offloading.entry_name, i64 8, i64 0, ptr null }, section "llvm_offload_entries"
|
||||
// HOST-COFF: @.offloading.entry.{{.*}} = weak constant %struct.__tgt_offload_entry { {{.*}} }, section "llvm_offload_entries$OE"
|
||||
// DEVICE-NOT: internal unnamed_addr constant [{{[0-9]+}} x i8] c"c_{{.*}}_decl_tgt_ref_ptr\00"
|
||||
// HOST: @.offloading.entry_name{{.*}} = internal unnamed_addr constant [{{[0-9]+}} x i8] c"_{{.*}}d_{{.*}}_decl_tgt_ref_ptr\00"
|
||||
// HOST: @.offloading.entry.[[D_PTR]] = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 1, ptr @[[D_PTR]], ptr @.offloading.entry_name.3, i64 8, i64 0, ptr null }, section "omp_offloading_entries", align 1
|
||||
// HOST: @.offloading.entry.[[D_PTR]] = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 1, ptr @[[D_PTR]], ptr @.offloading.entry_name.3, i64 8, i64 0, ptr null }, section "llvm_offload_entries"
|
||||
|
||||
extern int c;
|
||||
#pragma omp declare target link(c)
|
||||
|
||||
@ -47,10 +47,10 @@ int bar(int n){
|
||||
// CHECK-HOST: [[OFFLOAD_MAPTYPES:@.+]] = private unnamed_addr constant [2 x i64] [i64 800, i64 800]
|
||||
|
||||
// CHECK-HOST: [[OMP_OFFLOAD_ENTRY_LINK_VAR_PTR_NAME:@.+]] = internal unnamed_addr constant [21 x i8]
|
||||
// CHECK-HOST: [[OMP_OFFLOAD_ENTRY_LINK_VAR_PTR:@.+]] = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 1, ptr [[VAR_DECL_TGT_LINK_PTR]], ptr [[OMP_OFFLOAD_ENTRY_LINK_VAR_PTR_NAME]], i64 8, i64 0, ptr null }, section "omp_offl
|
||||
// CHECK-HOST: [[OMP_OFFLOAD_ENTRY_LINK_VAR_PTR:@.+]] = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 1, ptr [[VAR_DECL_TGT_LINK_PTR]], ptr [[OMP_OFFLOAD_ENTRY_LINK_VAR_PTR_NAME]], i64 8, i64 0, ptr null }, section "llvm_offload_entries"
|
||||
|
||||
// CHECK-HOST: [[OMP_OFFLOAD_ENTRY_TO_VAR_PTR_NAME:@.+]] = internal unnamed_addr constant [24 x i8]
|
||||
// CHECK-HOST: [[OMP_OFFLOAD_ENTRY_TO_VAR_PTR:@.+]] = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 0, ptr [[VAR_DECL_TGT_TO_PTR]], ptr [[OMP_OFFLOAD_ENTRY_TO_VAR_PTR_NAME]], i64 8, i64 0, ptr null }, section "omp_offloading_entries", align 1
|
||||
// CHECK-HOST: [[OMP_OFFLOAD_ENTRY_TO_VAR_PTR:@.+]] = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 0, ptr [[VAR_DECL_TGT_TO_PTR]], ptr @.offloading.entry_name.1, i64 8, i64 0, ptr null }, section "llvm_offload_entries"
|
||||
|
||||
// CHECK-HOST: [[N_CASTED:%.+]] = alloca i64
|
||||
// CHECK-HOST: [[SUM_CASTED:%.+]] = alloca i64
|
||||
|
||||
@ -691,22 +691,19 @@ wrapDeviceImages(ArrayRef<std::unique_ptr<MemoryBuffer>> Buffers,
|
||||
switch (Kind) {
|
||||
case OFK_OpenMP:
|
||||
if (Error Err = offloading::wrapOpenMPBinaries(
|
||||
M, BuffersToWrap,
|
||||
offloading::getOffloadEntryArray(M, "omp_offloading_entries"),
|
||||
M, BuffersToWrap, offloading::getOffloadEntryArray(M),
|
||||
/*Suffix=*/"", /*Relocatable=*/Args.hasArg(OPT_relocatable)))
|
||||
return std::move(Err);
|
||||
break;
|
||||
case OFK_Cuda:
|
||||
if (Error Err = offloading::wrapCudaBinary(
|
||||
M, BuffersToWrap.front(),
|
||||
offloading::getOffloadEntryArray(M, "cuda_offloading_entries"),
|
||||
M, BuffersToWrap.front(), offloading::getOffloadEntryArray(M),
|
||||
/*Suffix=*/"", /*EmitSurfacesAndTextures=*/false))
|
||||
return std::move(Err);
|
||||
break;
|
||||
case OFK_HIP:
|
||||
if (Error Err = offloading::wrapHIPBinary(
|
||||
M, BuffersToWrap.front(),
|
||||
offloading::getOffloadEntryArray(M, "hip_offloading_entries")))
|
||||
M, BuffersToWrap.front(), offloading::getOffloadEntryArray(M)))
|
||||
return std::move(Err);
|
||||
break;
|
||||
default:
|
||||
|
||||
@ -82,8 +82,8 @@ StructType *getEntryTy(Module &M);
|
||||
/// \param AuxAddr An extra pointer if needed.
|
||||
void emitOffloadingEntry(Module &M, object::OffloadKind Kind, Constant *Addr,
|
||||
StringRef Name, uint64_t Size, uint32_t Flags,
|
||||
uint64_t Data, StringRef SectionName,
|
||||
Constant *AuxAddr = nullptr);
|
||||
uint64_t Data, Constant *AuxAddr = nullptr,
|
||||
StringRef SectionName = "llvm_offload_entries");
|
||||
|
||||
/// Create a constant struct initializer used to register this global at
|
||||
/// runtime.
|
||||
@ -96,7 +96,7 @@ getOffloadingEntryInitializer(Module &M, object::OffloadKind Kind,
|
||||
/// Creates a pair of globals used to iterate the array of offloading entries by
|
||||
/// accessing the section variables provided by the linker.
|
||||
std::pair<GlobalVariable *, GlobalVariable *>
|
||||
getOffloadEntryArray(Module &M, StringRef SectionName);
|
||||
getOffloadEntryArray(Module &M, StringRef SectionName = "llvm_offload_entries");
|
||||
|
||||
namespace amdgpu {
|
||||
/// Check if an image is compatible with current system's environment. The
|
||||
|
||||
@ -83,8 +83,8 @@ offloading::getOffloadingEntryInitializer(Module &M, object::OffloadKind Kind,
|
||||
void offloading::emitOffloadingEntry(Module &M, object::OffloadKind Kind,
|
||||
Constant *Addr, StringRef Name,
|
||||
uint64_t Size, uint32_t Flags,
|
||||
uint64_t Data, StringRef SectionName,
|
||||
Constant *AuxAddr) {
|
||||
uint64_t Data, Constant *AuxAddr,
|
||||
StringRef SectionName) {
|
||||
llvm::Triple Triple(M.getTargetTriple());
|
||||
|
||||
auto [EntryInitializer, NameGV] = getOffloadingEntryInitializer(
|
||||
@ -103,7 +103,7 @@ void offloading::emitOffloadingEntry(Module &M, object::OffloadKind Kind,
|
||||
Entry->setSection((SectionName + "$OE").str());
|
||||
else
|
||||
Entry->setSection(SectionName);
|
||||
Entry->setAlignment(Align(1));
|
||||
Entry->setAlignment(Align(object::OffloadBinary::getAlignment()));
|
||||
}
|
||||
|
||||
std::pair<GlobalVariable *, GlobalVariable *>
|
||||
@ -135,6 +135,7 @@ offloading::getOffloadEntryArray(Module &M, StringRef SectionName) {
|
||||
M, ZeroInitilaizer->getType(), true, GlobalVariable::InternalLinkage,
|
||||
ZeroInitilaizer, "__dummy." + SectionName);
|
||||
DummyEntry->setSection(SectionName);
|
||||
DummyEntry->setAlignment(Align(object::OffloadBinary::getAlignment()));
|
||||
appendToCompilerUsed(M, DummyEntry);
|
||||
} else {
|
||||
// The COFF linker will merge sections containing a '$' together into a
|
||||
|
||||
@ -9227,8 +9227,7 @@ void OpenMPIRBuilder::createOffloadEntry(Constant *ID, Constant *Addr,
|
||||
if (!Config.isGPU()) {
|
||||
llvm::offloading::emitOffloadingEntry(
|
||||
M, object::OffloadKind::OFK_OpenMP, ID,
|
||||
Name.empty() ? Addr->getName() : Name, Size, Flags, /*Data=*/0,
|
||||
"omp_offloading_entries");
|
||||
Name.empty() ? Addr->getName() : Name, Size, Flags, /*Data=*/0);
|
||||
return;
|
||||
}
|
||||
// TODO: Add support for global variables on the device after declare target
|
||||
@ -9404,9 +9403,9 @@ void OpenMPIRBuilder::createOffloadEntriesAndInfoMetadata(
|
||||
offloading::emitOffloadingEntry(
|
||||
M, object::OffloadKind::OFK_OpenMP,
|
||||
Constant::getNullValue(PointerType::getUnqual(M.getContext())),
|
||||
/*Name=*/"",
|
||||
/*Size=*/0, OffloadEntriesInfoManager::OMPTargetGlobalRegisterRequires,
|
||||
Config.getRequiresFlags(), "omp_offloading_entries");
|
||||
".requires", /*Size=*/0,
|
||||
OffloadEntriesInfoManager::OMPTargetGlobalRegisterRequires,
|
||||
Config.getRequiresFlags());
|
||||
}
|
||||
|
||||
void TargetRegionEntryInfo::getTargetRegionEntryFnName(
|
||||
|
||||
@ -7,14 +7,14 @@ module attributes {llvm.target_triple = "x86_64-unknown-linux-gnu", omp.is_targe
|
||||
// CHECK-DAG: @_QMtest_0Earray_1d = global [3 x i32] [i32 1, i32 2, i32 3]
|
||||
// CHECK-DAG: @_QMtest_0Earray_1d_decl_tgt_ref_ptr = weak global ptr @_QMtest_0Earray_1d
|
||||
// CHECK-DAG: @.offloading.entry_name{{.*}} = internal unnamed_addr constant [36 x i8] c"_QMtest_0Earray_1d_decl_tgt_ref_ptr\00"
|
||||
// CHECK-DAG: @.offloading.entry._QMtest_0Earray_1d_decl_tgt_ref_ptr = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 1, ptr @_QMtest_0Earray_1d_decl_tgt_ref_ptr, ptr @.offloading.entry_name{{.*}}, i64 8, i64 0, ptr null }, section "omp_offloading_entries", align 1
|
||||
// CHECK-DAG: @.offloading.entry._QMtest_0Earray_1d_decl_tgt_ref_ptr = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 1, ptr @_QMtest_0Earray_1d_decl_tgt_ref_ptr, ptr @.offloading.entry_name{{.*}}, i64 8, i64 0, ptr null }, section "llvm_offload_entries"
|
||||
// CHECK-DAG: !{{.*}} = !{i32 {{.*}}, !"_QMtest_0Earray_1d_decl_tgt_ref_ptr", i32 {{.*}}, i32 {{.*}}}
|
||||
llvm.mlir.global external @_QMtest_0Earray_1d(dense<[1, 2, 3]> : tensor<3xi32>) {addr_space = 0 : i32, omp.declare_target = #omp.declaretarget<device_type = (any), capture_clause = (link)>} : !llvm.array<3 x i32>
|
||||
|
||||
// CHECK-DAG: @_QMtest_0Earray_2d = global [2 x [2 x i32]] {{.*}}
|
||||
// CHECK-DAG: @_QMtest_0Earray_2d_decl_tgt_ref_ptr = weak global ptr @_QMtest_0Earray_2d
|
||||
// CHECK-DAG: @.offloading.entry_name{{.*}} = internal unnamed_addr constant [36 x i8] c"_QMtest_0Earray_2d_decl_tgt_ref_ptr\00"
|
||||
// CHECK-DAG: @.offloading.entry._QMtest_0Earray_2d_decl_tgt_ref_ptr = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 1, ptr @_QMtest_0Earray_2d_decl_tgt_ref_ptr, ptr @.offloading.entry_name{{.*}}, i64 8, i64 0, ptr null }, section "omp_offloading_entries", align 1
|
||||
// CHECK-DAG: @.offloading.entry._QMtest_0Earray_2d_decl_tgt_ref_ptr = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 1, ptr @_QMtest_0Earray_2d_decl_tgt_ref_ptr, ptr @.offloading.entry_name{{.*}}, i64 8, i64 0, ptr null }, section "llvm_offload_entries"
|
||||
// CHECK-DAG: !{{.*}} = !{i32 {{.*}}, !"_QMtest_0Earray_2d_decl_tgt_ref_ptr", i32 {{.*}}, i32 {{.*}}}
|
||||
llvm.mlir.global external @_QMtest_0Earray_2d() {addr_space = 0 : i32, omp.declare_target = #omp.declaretarget<device_type = (any), capture_clause = (link)>} : !llvm.array<2 x array<2 x i32>> {
|
||||
%0 = llvm.mlir.undef : !llvm.array<2 x array<2 x i32>>
|
||||
@ -34,7 +34,7 @@ module attributes {llvm.target_triple = "x86_64-unknown-linux-gnu", omp.is_targe
|
||||
// CHECK-DAG: @_QMtest_0Edata_extended_link_1 = global float 2.000000e+00
|
||||
// CHECK-DAG: @_QMtest_0Edata_extended_link_1_decl_tgt_ref_ptr = weak global ptr @_QMtest_0Edata_extended_link_1
|
||||
// CHECK-DAG: @.offloading.entry_name{{.*}} = internal unnamed_addr constant [48 x i8] c"_QMtest_0Edata_extended_link_1_decl_tgt_ref_ptr\00"
|
||||
// CHECK-DAG: @.offloading.entry._QMtest_0Edata_extended_link_1_decl_tgt_ref_ptr = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 1, ptr @_QMtest_0Edata_extended_link_1_decl_tgt_ref_ptr, ptr @.offloading.entry_name{{.*}}, i64 8, i64 0, ptr null }, section "omp_offloading_entries", align 1
|
||||
// CHECK-DAG: @.offloading.entry._QMtest_0Edata_extended_link_1_decl_tgt_ref_ptr = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 1, ptr @_QMtest_0Edata_extended_link_1_decl_tgt_ref_ptr, ptr @.offloading.entry_name{{.*}}, i64 8, i64 0, ptr null }, section "llvm_offload_entries"
|
||||
// CHECK-DAG: !{{.*}} = !{i32 {{.*}}, !"_QMtest_0Edata_extended_link_1_decl_tgt_ref_ptr", i32 {{.*}}, i32 {{.*}}}
|
||||
llvm.mlir.global external @_QMtest_0Edata_extended_link_1() {addr_space = 0 : i32, omp.declare_target = #omp.declaretarget<device_type = (any), capture_clause = (link)>} : f32 {
|
||||
%0 = llvm.mlir.constant(2.000000e+00 : f32) : f32
|
||||
@ -44,7 +44,7 @@ module attributes {llvm.target_triple = "x86_64-unknown-linux-gnu", omp.is_targe
|
||||
// CHECK-DAG: @_QMtest_0Edata_extended_link_2 = global float 3.000000e+00
|
||||
// CHECK-DAG: @_QMtest_0Edata_extended_link_2_decl_tgt_ref_ptr = weak global ptr @_QMtest_0Edata_extended_link_2
|
||||
// CHECK-DAG: @.offloading.entry_name{{.*}} = internal unnamed_addr constant [48 x i8] c"_QMtest_0Edata_extended_link_2_decl_tgt_ref_ptr\00"
|
||||
// CHECK-DAG: @.offloading.entry._QMtest_0Edata_extended_link_2_decl_tgt_ref_ptr = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 1, ptr @_QMtest_0Edata_extended_link_2_decl_tgt_ref_ptr, ptr @.offloading.entry_name{{.*}}, i64 8, i64 0, ptr null }, section "omp_offloading_entries", align 1
|
||||
// CHECK-DAG: @.offloading.entry._QMtest_0Edata_extended_link_2_decl_tgt_ref_ptr = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 1, ptr @_QMtest_0Edata_extended_link_2_decl_tgt_ref_ptr, ptr @.offloading.entry_name{{.*}}, i64 8, i64 0, ptr null }, section "llvm_offload_entries"
|
||||
// CHECK-DAG: !{{.*}} = !{i32 {{.*}}, !"_QMtest_0Edata_extended_link_2_decl_tgt_ref_ptr", i32 {{.*}}, i32 {{.*}}}
|
||||
llvm.mlir.global external @_QMtest_0Edata_extended_link_2() {addr_space = 0 : i32, omp.declare_target = #omp.declaretarget<device_type = (any), capture_clause = (link)>} : f32 {
|
||||
%0 = llvm.mlir.constant(3.000000e+00 : f32) : f32
|
||||
@ -53,7 +53,7 @@ module attributes {llvm.target_triple = "x86_64-unknown-linux-gnu", omp.is_targe
|
||||
|
||||
// CHECK-DAG: @_QMtest_0Edata_extended_to_1 = global float 2.000000e+00
|
||||
// CHECK-DAG: @.offloading.entry_name{{.*}} = internal unnamed_addr constant [29 x i8] c"_QMtest_0Edata_extended_to_1\00"
|
||||
// CHECK-DAG: @.offloading.entry._QMtest_0Edata_extended_to_1 = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 0, ptr @_QMtest_0Edata_extended_to_1, ptr @.offloading.entry_name{{.*}}, i64 4, i64 0, ptr null }, section "omp_offloading_entries", align 1
|
||||
// CHECK-DAG: @.offloading.entry._QMtest_0Edata_extended_to_1 = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 0, ptr @_QMtest_0Edata_extended_to_1, ptr @.offloading.entry_name{{.*}}, i64 4, i64 0, ptr null }, section "llvm_offload_entries"
|
||||
// CHECK-DAG: !{{.*}} = !{i32 {{.*}}, !"_QMtest_0Edata_extended_to_1", i32 {{.*}}, i32 {{.*}}}
|
||||
llvm.mlir.global external @_QMtest_0Edata_extended_to_1() {addr_space = 0 : i32, omp.declare_target = #omp.declaretarget<device_type = (any), capture_clause = (to)>} : f32 {
|
||||
%0 = llvm.mlir.constant(2.000000e+00 : f32) : f32
|
||||
@ -62,7 +62,7 @@ module attributes {llvm.target_triple = "x86_64-unknown-linux-gnu", omp.is_targe
|
||||
|
||||
// CHECK-DAG: @_QMtest_0Edata_extended_enter_1 = global float 2.000000e+00
|
||||
// CHECK-DAG: @.offloading.entry_name{{.*}} = internal unnamed_addr constant [32 x i8] c"_QMtest_0Edata_extended_enter_1\00"
|
||||
// CHECK-DAG: @.offloading.entry._QMtest_0Edata_extended_enter_1 = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 0, ptr @_QMtest_0Edata_extended_enter_1, ptr @.offloading.entry_name{{.*}}, i64 4, i64 0, ptr null }, section "omp_offloading_entries", align 1
|
||||
// CHECK-DAG: @.offloading.entry._QMtest_0Edata_extended_enter_1 = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 0, ptr @_QMtest_0Edata_extended_enter_1, ptr @.offloading.entry_name{{.*}}, i64 4, i64 0, ptr null }, section "llvm_offload_entries"
|
||||
// CHECK-DAG: !{{.*}} = !{i32 {{.*}}, !"_QMtest_0Edata_extended_enter_1", i32 {{.*}}, i32 {{.*}}}
|
||||
llvm.mlir.global external @_QMtest_0Edata_extended_enter_1() {addr_space = 0 : i32, omp.declare_target = #omp.declaretarget<device_type = (any), capture_clause = (enter)>} : f32 {
|
||||
%0 = llvm.mlir.constant(2.000000e+00 : f32) : f32
|
||||
@ -71,7 +71,7 @@ module attributes {llvm.target_triple = "x86_64-unknown-linux-gnu", omp.is_targe
|
||||
|
||||
// CHECK-DAG: @_QMtest_0Edata_extended_to_2 = global float 3.000000e+00
|
||||
// CHECK-DAG: @.offloading.entry_name{{.*}} = internal unnamed_addr constant [29 x i8] c"_QMtest_0Edata_extended_to_2\00"
|
||||
// CHECK-DAG: @.offloading.entry._QMtest_0Edata_extended_to_2 = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 0, ptr @_QMtest_0Edata_extended_to_2, ptr @.offloading.entry_name{{.*}}, i64 4, i64 0, ptr null }, section "omp_offloading_entries", align 1
|
||||
// CHECK-DAG: @.offloading.entry._QMtest_0Edata_extended_to_2 = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 0, ptr @_QMtest_0Edata_extended_to_2, ptr @.offloading.entry_name{{.*}}, i64 4, i64 0, ptr null }, section "llvm_offload_entries"
|
||||
// CHECK-DAG: !{{.*}} = !{i32 {{.*}}, !"_QMtest_0Edata_extended_to_2", i32 {{.*}}, i32 {{.*}}}
|
||||
llvm.mlir.global external @_QMtest_0Edata_extended_to_2() {addr_space = 0 : i32, omp.declare_target = #omp.declaretarget<device_type = (any), capture_clause = (to)>} : f32 {
|
||||
%0 = llvm.mlir.constant(3.000000e+00 : f32) : f32
|
||||
@ -80,7 +80,7 @@ module attributes {llvm.target_triple = "x86_64-unknown-linux-gnu", omp.is_targe
|
||||
|
||||
// CHECK-DAG: @_QMtest_0Edata_extended_enter_2 = global float 3.000000e+00
|
||||
// CHECK-DAG: @.offloading.entry_name{{.*}} = internal unnamed_addr constant [32 x i8] c"_QMtest_0Edata_extended_enter_2\00"
|
||||
// CHECK-DAG: @.offloading.entry._QMtest_0Edata_extended_enter_2 = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 0, ptr @_QMtest_0Edata_extended_enter_2, ptr @.offloading.entry_name{{.*}}, i64 4, i64 0, ptr null }, section "omp_offloading_entries", align 1
|
||||
// CHECK-DAG: @.offloading.entry._QMtest_0Edata_extended_enter_2 = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 0, ptr @_QMtest_0Edata_extended_enter_2, ptr @.offloading.entry_name{{.*}}, i64 4, i64 0, ptr null }, section "llvm_offload_entries"
|
||||
// CHECK-DAG: !{{.*}} = !{i32 {{.*}}, !"_QMtest_0Edata_extended_enter_2", i32 {{.*}}, i32 {{.*}}}
|
||||
llvm.mlir.global external @_QMtest_0Edata_extended_enter_2() {addr_space = 0 : i32, omp.declare_target = #omp.declaretarget<device_type = (any), capture_clause = (enter)>} : f32 {
|
||||
%0 = llvm.mlir.constant(3.000000e+00 : f32) : f32
|
||||
@ -90,7 +90,7 @@ module attributes {llvm.target_triple = "x86_64-unknown-linux-gnu", omp.is_targe
|
||||
// CHECK-DAG: @_QMtest_0Edata_int = global i32 1
|
||||
// CHECK-DAG: @_QMtest_0Edata_int_decl_tgt_ref_ptr = weak global ptr @_QMtest_0Edata_int
|
||||
// CHECK-DAG: @.offloading.entry_name{{.*}} = internal unnamed_addr constant [36 x i8] c"_QMtest_0Edata_int_decl_tgt_ref_ptr\00"
|
||||
// CHECK-DAG: @.offloading.entry._QMtest_0Edata_int_decl_tgt_ref_ptr = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 1, ptr @_QMtest_0Edata_int_decl_tgt_ref_ptr, ptr @.offloading.entry_name{{.*}}, i64 8, i64 0, ptr null }, section "omp_offloading_entries", align 1
|
||||
// CHECK-DAG: @.offloading.entry._QMtest_0Edata_int_decl_tgt_ref_ptr = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 1, ptr @_QMtest_0Edata_int_decl_tgt_ref_ptr, ptr @.offloading.entry_name{{.*}}, i64 8, i64 0, ptr null }, section "llvm_offload_entries"
|
||||
// CHECK-DAG: !{{.*}} = !{i32 {{.*}}, !"_QMtest_0Edata_int_decl_tgt_ref_ptr", i32 {{.*}}, i32 {{.*}}}
|
||||
llvm.mlir.global external @_QMtest_0Edata_int() {addr_space = 0 : i32, omp.declare_target = #omp.declaretarget<device_type = (any), capture_clause = (link)>} : i32 {
|
||||
%0 = llvm.mlir.constant(10 : i32) : i32
|
||||
@ -99,7 +99,7 @@ module attributes {llvm.target_triple = "x86_64-unknown-linux-gnu", omp.is_targe
|
||||
|
||||
// CHECK-DAG: @_QMtest_0Edata_int_clauseless_to = global i32 1
|
||||
// CHECK-DAG: @.offloading.entry_name{{.*}} = internal unnamed_addr constant [33 x i8] c"_QMtest_0Edata_int_clauseless_to\00"
|
||||
// CHECK-DAG: @.offloading.entry._QMtest_0Edata_int_clauseless_to = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 0, ptr @_QMtest_0Edata_int_clauseless_to, ptr @.offloading.entry_name{{.*}}, i64 4, i64 0, ptr null }, section "omp_offloading_entries", align 1
|
||||
// CHECK-DAG: @.offloading.entry._QMtest_0Edata_int_clauseless_to = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 0, ptr @_QMtest_0Edata_int_clauseless_to, ptr @.offloading.entry_name{{.*}}, i64 4, i64 0, ptr null }, section "llvm_offload_entries"
|
||||
// CHECK-DAG: !{{.*}} = !{i32 {{.*}}, !"_QMtest_0Edata_int_clauseless_to", i32 {{.*}}, i32 {{.*}}}
|
||||
llvm.mlir.global external @_QMtest_0Edata_int_clauseless_to() {addr_space = 0 : i32, omp.declare_target = #omp.declaretarget<device_type = (any), capture_clause = (to)>} : i32 {
|
||||
%0 = llvm.mlir.constant(1 : i32) : i32
|
||||
@ -108,7 +108,7 @@ module attributes {llvm.target_triple = "x86_64-unknown-linux-gnu", omp.is_targe
|
||||
|
||||
// CHECK-DAG: @_QMtest_0Edata_int_clauseless_enter = global i32 1
|
||||
// CHECK-DAG: @.offloading.entry_name{{.*}} = internal unnamed_addr constant [36 x i8] c"_QMtest_0Edata_int_clauseless_enter\00"
|
||||
// CHECK-DAG: @.offloading.entry._QMtest_0Edata_int_clauseless_enter = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 0, ptr @_QMtest_0Edata_int_clauseless_enter, ptr @.offloading.entry_name{{.*}}, i64 4, i64 0, ptr null }, section "omp_offloading_entries", align 1
|
||||
// CHECK-DAG: @.offloading.entry._QMtest_0Edata_int_clauseless_enter = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 0, ptr @_QMtest_0Edata_int_clauseless_enter, ptr @.offloading.entry_name{{.*}}, i64 4, i64 0, ptr null }, section "llvm_offload_entries"
|
||||
// CHECK-DAG: !{{.*}} = !{i32 {{.*}}, !"_QMtest_0Edata_int_clauseless_enter", i32 {{.*}}, i32 {{.*}}}
|
||||
llvm.mlir.global external @_QMtest_0Edata_int_clauseless_enter() {addr_space = 0 : i32, omp.declare_target = #omp.declaretarget<device_type = (any), capture_clause = (enter)>} : i32 {
|
||||
%0 = llvm.mlir.constant(1 : i32) : i32
|
||||
@ -117,7 +117,7 @@ module attributes {llvm.target_triple = "x86_64-unknown-linux-gnu", omp.is_targe
|
||||
|
||||
// CHECK-DAG: @_QMtest_0Edata_int_to = global i32 5
|
||||
// CHECK-DAG: @.offloading.entry_name{{.*}} = internal unnamed_addr constant [22 x i8] c"_QMtest_0Edata_int_to\00"
|
||||
// CHECK-DAG: @.offloading.entry._QMtest_0Edata_int_to = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 0, ptr @_QMtest_0Edata_int_to, ptr @.offloading.entry_name{{.*}}, i64 4, i64 0, ptr null }, section "omp_offloading_entries", align 1
|
||||
// CHECK-DAG: @.offloading.entry._QMtest_0Edata_int_to = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 0, ptr @_QMtest_0Edata_int_to, ptr @.offloading.entry_name{{.*}}, i64 4, i64 0, ptr null }, section "llvm_offload_entries"
|
||||
// CHECK-DAG: !{{.*}} = !{i32 {{.*}}, !"_QMtest_0Edata_int_to", i32 {{.*}}, i32 {{.*}}}
|
||||
llvm.mlir.global external @_QMtest_0Edata_int_to() {addr_space = 0 : i32, omp.declare_target = #omp.declaretarget<device_type = (any), capture_clause = (to)>} : i32 {
|
||||
%0 = llvm.mlir.constant(5 : i32) : i32
|
||||
@ -126,7 +126,7 @@ module attributes {llvm.target_triple = "x86_64-unknown-linux-gnu", omp.is_targe
|
||||
|
||||
// CHECK-DAG: @_QMtest_0Edata_int_enter = global i32 5
|
||||
// CHECK-DAG: @.offloading.entry_name{{.*}} = internal unnamed_addr constant [25 x i8] c"_QMtest_0Edata_int_enter\00"
|
||||
// CHECK-DAG: @.offloading.entry._QMtest_0Edata_int_enter = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 0, ptr @_QMtest_0Edata_int_enter, ptr @.offloading.entry_name{{.*}}, i64 4, i64 0, ptr null }, section "omp_offloading_entries", align 1
|
||||
// CHECK-DAG: @.offloading.entry._QMtest_0Edata_int_enter = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 0, ptr @_QMtest_0Edata_int_enter, ptr @.offloading.entry_name{{.*}}, i64 4, i64 0, ptr null }, section "llvm_offload_entries"
|
||||
// CHECK-DAG: !{{.*}} = !{i32 {{.*}}, !"_QMtest_0Edata_int_enter", i32 {{.*}}, i32 {{.*}}}
|
||||
llvm.mlir.global external @_QMtest_0Edata_int_enter() {addr_space = 0 : i32, omp.declare_target = #omp.declaretarget<device_type = (any), capture_clause = (enter)>} : i32 {
|
||||
%0 = llvm.mlir.constant(5 : i32) : i32
|
||||
@ -136,7 +136,7 @@ module attributes {llvm.target_triple = "x86_64-unknown-linux-gnu", omp.is_targe
|
||||
// CHECK-DAG: @_QMtest_0Ept1 = global { ptr, i64, i32, i8, i8, i8, i8 } { ptr null, i64 ptrtoint (ptr getelementptr (i32, ptr null, i32 1) to i64), i32 20180515, i8 0, i8 9, i8 1, i8 0 }
|
||||
// CHECK-DAG: @_QMtest_0Ept1_decl_tgt_ref_ptr = weak global ptr @_QMtest_0Ept1
|
||||
// CHECK-DAG: @.offloading.entry_name{{.*}} = internal unnamed_addr constant [31 x i8] c"_QMtest_0Ept1_decl_tgt_ref_ptr\00"
|
||||
// CHECK-DAG: @.offloading.entry._QMtest_0Ept1_decl_tgt_ref_ptr = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 1, ptr @_QMtest_0Ept1_decl_tgt_ref_ptr, ptr @.offloading.entry_name{{.*}}, i64 8, i64 0, ptr null }, section "omp_offloading_entries", align 1
|
||||
// CHECK-DAG: @.offloading.entry._QMtest_0Ept1_decl_tgt_ref_ptr = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 1, ptr @_QMtest_0Ept1_decl_tgt_ref_ptr, ptr @.offloading.entry_name{{.*}}, i64 8, i64 0, ptr null }, section "llvm_offload_entries"
|
||||
// CHECK-DAG: !{{.*}} = !{i32 {{.*}}, !"_QMtest_0Ept1_decl_tgt_ref_ptr", i32 {{.*}}, i32 {{.*}}}
|
||||
llvm.mlir.global external @_QMtest_0Ept1() {addr_space = 0 : i32, omp.declare_target = #omp.declaretarget<device_type = (any), capture_clause = (link)>} : !llvm.struct<(ptr, i64, i32, i8, i8, i8, i8)> {
|
||||
%0 = llvm.mlir.zero : !llvm.ptr
|
||||
@ -167,7 +167,7 @@ module attributes {llvm.target_triple = "x86_64-unknown-linux-gnu", omp.is_targe
|
||||
// CHECK-DAG: @_QMtest_0Ept2_tar = global i32 5
|
||||
// CHECK-DAG: @_QMtest_0Ept2_tar_decl_tgt_ref_ptr = weak global ptr @_QMtest_0Ept2_tar
|
||||
// CHECK-DAG: @.offloading.entry_name{{.*}} = internal unnamed_addr constant [35 x i8] c"_QMtest_0Ept2_tar_decl_tgt_ref_ptr\00"
|
||||
// CHECK-DAG: @.offloading.entry._QMtest_0Ept2_tar_decl_tgt_ref_ptr = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 1, ptr @_QMtest_0Ept2_tar_decl_tgt_ref_ptr, ptr @.offloading.entry_name{{.*}}, i64 8, i64 0, ptr null }, section "omp_offloading_entries", align 1
|
||||
// CHECK-DAG: @.offloading.entry._QMtest_0Ept2_tar_decl_tgt_ref_ptr = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 1, i32 1, ptr @_QMtest_0Ept2_tar_decl_tgt_ref_ptr, ptr @.offloading.entry_name{{.*}}, i64 8, i64 0, ptr null }, section "llvm_offload_entries"
|
||||
// CHECK-DAG: !{{.*}} = !{i32 {{.*}}, !"_QMtest_0Ept2_tar_decl_tgt_ref_ptr", i32 {{.*}}, i32 {{.*}}}
|
||||
llvm.mlir.global external @_QMtest_0Ept2_tar() {addr_space = 0 : i32, omp.declare_target = #omp.declaretarget<device_type = (any), capture_clause = (link)>} : i32 {
|
||||
%0 = llvm.mlir.constant(5 : i32) : i32
|
||||
|
||||
@ -330,7 +330,8 @@ void PluginManager::unregisterLib(__tgt_bin_desc *Desc) {
|
||||
PM->TblMapMtx.lock();
|
||||
for (llvm::offloading::EntryTy *Cur = Desc->HostEntriesBegin;
|
||||
Cur < Desc->HostEntriesEnd; ++Cur) {
|
||||
PM->HostPtrToTableMap.erase(Cur->Address);
|
||||
if (Cur->Kind == object::OffloadKind::OFK_OpenMP)
|
||||
PM->HostPtrToTableMap.erase(Cur->Address);
|
||||
}
|
||||
|
||||
// Remove translation table for this descriptor.
|
||||
@ -400,6 +401,9 @@ static int loadImagesOntoDevice(DeviceTy &Device) {
|
||||
TransTable->TargetsEntries[DeviceId];
|
||||
for (llvm::offloading::EntryTy &Entry :
|
||||
llvm::make_range(Img->EntriesBegin, Img->EntriesEnd)) {
|
||||
if (Entry.Kind != object::OffloadKind::OFK_OpenMP)
|
||||
continue;
|
||||
|
||||
__tgt_device_binary &Binary = *BinaryOrErr;
|
||||
|
||||
llvm::offloading::EntryTy DeviceEntry = Entry;
|
||||
@ -437,22 +441,6 @@ static int loadImagesOntoDevice(DeviceTy &Device) {
|
||||
__tgt_target_table *TargetTable = TransTable->TargetsTable[DeviceId] =
|
||||
&TransTable->DeviceTables[DeviceId];
|
||||
|
||||
// 4) Verify whether the two table sizes match.
|
||||
size_t Hsize =
|
||||
TransTable->HostTable.EntriesEnd - TransTable->HostTable.EntriesBegin;
|
||||
size_t Tsize = TargetTable->EntriesEnd - TargetTable->EntriesBegin;
|
||||
|
||||
// Invalid image for these host entries!
|
||||
if (Hsize != Tsize) {
|
||||
REPORT(
|
||||
"Host and Target tables mismatch for device id %d [%zx != %zx].\n",
|
||||
DeviceId, Hsize, Tsize);
|
||||
TransTable->TargetsImages[DeviceId] = 0;
|
||||
TransTable->TargetsTable[DeviceId] = 0;
|
||||
Rc = OFFLOAD_FAIL;
|
||||
break;
|
||||
}
|
||||
|
||||
MappingInfoTy::HDTTMapAccessorTy HDTTMap =
|
||||
Device.getMappingInfo().HostDataToTargetMap.getExclusiveAccessor();
|
||||
|
||||
@ -463,7 +451,8 @@ static int loadImagesOntoDevice(DeviceTy &Device) {
|
||||
*EntryDeviceEnd = TargetTable->EntriesEnd;
|
||||
CurrDeviceEntry != EntryDeviceEnd;
|
||||
CurrDeviceEntry++, CurrHostEntry++) {
|
||||
if (CurrDeviceEntry->Size == 0)
|
||||
if (CurrDeviceEntry->Size == 0 ||
|
||||
CurrDeviceEntry->Kind != object::OffloadKind::OFK_OpenMP)
|
||||
continue;
|
||||
|
||||
assert(CurrDeviceEntry->Size == CurrHostEntry->Size &&
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user