summaryrefslogtreecommitdiffstats
path: root/clang/lib
diff options
context:
space:
mode:
authorArtem Belevich <tra@google.com>2016-09-28 17:47:35 +0000
committerArtem Belevich <tra@google.com>2016-09-28 17:47:35 +0000
commitfda990506296ed7bead5761da987f464c34709d4 (patch)
tree3b51df8505096f2a18a5d59ff260e12852df31bf /clang/lib
parent16b2ace0abb8e15e0b7aa10b01893441d9bdbc7f (diff)
downloadbcm5719-llvm-fda990506296ed7bead5761da987f464c34709d4.tar.gz
bcm5719-llvm-fda990506296ed7bead5761da987f464c34709d4.zip
[CUDA] added __nvvm_atom_{sys|cta}_* builtins.
These builtins are available on sm_60+ GPU only. Differential Revision: https://reviews.llvm.org/D24944 llvm-svn: 282609
Diffstat (limited to 'clang/lib')
-rw-r--r--clang/lib/Basic/Targets.cpp15
-rw-r--r--clang/lib/CodeGen/CGBuiltin.cpp111
2 files changed, 124 insertions, 2 deletions
diff --git a/clang/lib/Basic/Targets.cpp b/clang/lib/Basic/Targets.cpp
index 96c10bcdd70..8e30ba1713b 100644
--- a/clang/lib/Basic/Targets.cpp
+++ b/clang/lib/Basic/Targets.cpp
@@ -1850,8 +1850,19 @@ public:
return llvm::makeArrayRef(BuiltinInfo,
clang::NVPTX::LastTSBuiltin - Builtin::FirstTSBuiltin);
}
+ bool
+ initFeatureMap(llvm::StringMap<bool> &Features, DiagnosticsEngine &Diags,
+ StringRef CPU,
+ const std::vector<std::string> &FeaturesVec) const override {
+ Features["satom"] = GPU >= CudaArch::SM_60;
+ return TargetInfo::initFeatureMap(Features, Diags, CPU, FeaturesVec);
+ }
+
bool hasFeature(StringRef Feature) const override {
- return Feature == "ptx" || Feature == "nvptx";
+ return llvm::StringSwitch<bool>(Feature)
+ .Cases("ptx", "nvptx", true)
+ .Case("satom", GPU >= CudaArch::SM_60) // Atomics w/ scope.
+ .Default(false);
}
ArrayRef<const char *> getGCCRegNames() const override;
@@ -1906,6 +1917,8 @@ const Builtin::Info NVPTXTargetInfo::BuiltinInfo[] = {
{ #ID, TYPE, ATTRS, nullptr, ALL_LANGUAGES, nullptr },
#define LIBBUILTIN(ID, TYPE, ATTRS, HEADER) \
{ #ID, TYPE, ATTRS, HEADER, ALL_LANGUAGES, nullptr },
+#define TARGET_BUILTIN(ID, TYPE, ATTRS, FEATURE) \
+ { #ID, TYPE, ATTRS, nullptr, ALL_LANGUAGES, FEATURE },
#include "clang/Basic/BuiltinsNVPTX.def"
};
diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index 8cf29420c21..2f4fbcff253 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -8124,7 +8124,13 @@ Value *CodeGenFunction::EmitNVPTXBuiltinExpr(unsigned BuiltinID,
Ptr->getType()}),
{Ptr, ConstantInt::get(Builder.getInt32Ty(), Align.getQuantity())});
};
-
+ auto MakeScopedAtomic = [&](unsigned IntrinsicID) {
+ Value *Ptr = EmitScalarExpr(E->getArg(0));
+ return Builder.CreateCall(
+ CGM.getIntrinsic(IntrinsicID, {Ptr->getType()->getPointerElementType(),
+ Ptr->getType()}),
+ {Ptr, EmitScalarExpr(E->getArg(1))});
+ };
switch (BuiltinID) {
case NVPTX::BI__nvvm_atom_add_gen_i:
case NVPTX::BI__nvvm_atom_add_gen_l:
@@ -8243,6 +8249,109 @@ Value *CodeGenFunction::EmitNVPTXBuiltinExpr(unsigned BuiltinID,
case NVPTX::BI__nvvm_ldg_d:
case NVPTX::BI__nvvm_ldg_d2:
return MakeLdg(Intrinsic::nvvm_ldg_global_f);
+
+ case NVPTX::BI__nvvm_atom_cta_add_gen_i:
+ case NVPTX::BI__nvvm_atom_cta_add_gen_l:
+ case NVPTX::BI__nvvm_atom_cta_add_gen_ll:
+ return MakeScopedAtomic(Intrinsic::nvvm_atomic_add_gen_i_cta);
+ case NVPTX::BI__nvvm_atom_sys_add_gen_i:
+ case NVPTX::BI__nvvm_atom_sys_add_gen_l:
+ case NVPTX::BI__nvvm_atom_sys_add_gen_ll:
+ return MakeScopedAtomic(Intrinsic::nvvm_atomic_add_gen_i_sys);
+ case NVPTX::BI__nvvm_atom_cta_add_gen_f:
+ case NVPTX::BI__nvvm_atom_cta_add_gen_d:
+ return MakeScopedAtomic(Intrinsic::nvvm_atomic_add_gen_f_cta);
+ case NVPTX::BI__nvvm_atom_sys_add_gen_f:
+ case NVPTX::BI__nvvm_atom_sys_add_gen_d:
+ return MakeScopedAtomic(Intrinsic::nvvm_atomic_add_gen_f_sys);
+ case NVPTX::BI__nvvm_atom_cta_xchg_gen_i:
+ case NVPTX::BI__nvvm_atom_cta_xchg_gen_l:
+ case NVPTX::BI__nvvm_atom_cta_xchg_gen_ll:
+ return MakeScopedAtomic(Intrinsic::nvvm_atomic_exch_gen_i_cta);
+ case NVPTX::BI__nvvm_atom_sys_xchg_gen_i:
+ case NVPTX::BI__nvvm_atom_sys_xchg_gen_l:
+ case NVPTX::BI__nvvm_atom_sys_xchg_gen_ll:
+ return MakeScopedAtomic(Intrinsic::nvvm_atomic_exch_gen_i_sys);
+ case NVPTX::BI__nvvm_atom_cta_max_gen_i:
+ case NVPTX::BI__nvvm_atom_cta_max_gen_ui:
+ case NVPTX::BI__nvvm_atom_cta_max_gen_l:
+ case NVPTX::BI__nvvm_atom_cta_max_gen_ul:
+ case NVPTX::BI__nvvm_atom_cta_max_gen_ll:
+ case NVPTX::BI__nvvm_atom_cta_max_gen_ull:
+ return MakeScopedAtomic(Intrinsic::nvvm_atomic_max_gen_i_cta);
+ case NVPTX::BI__nvvm_atom_sys_max_gen_i:
+ case NVPTX::BI__nvvm_atom_sys_max_gen_ui:
+ case NVPTX::BI__nvvm_atom_sys_max_gen_l:
+ case NVPTX::BI__nvvm_atom_sys_max_gen_ul:
+ case NVPTX::BI__nvvm_atom_sys_max_gen_ll:
+ case NVPTX::BI__nvvm_atom_sys_max_gen_ull:
+ return MakeScopedAtomic(Intrinsic::nvvm_atomic_max_gen_i_sys);
+ case NVPTX::BI__nvvm_atom_cta_min_gen_i:
+ case NVPTX::BI__nvvm_atom_cta_min_gen_ui:
+ case NVPTX::BI__nvvm_atom_cta_min_gen_l:
+ case NVPTX::BI__nvvm_atom_cta_min_gen_ul:
+ case NVPTX::BI__nvvm_atom_cta_min_gen_ll:
+ case NVPTX::BI__nvvm_atom_cta_min_gen_ull:
+ return MakeScopedAtomic(Intrinsic::nvvm_atomic_min_gen_i_cta);
+ case NVPTX::BI__nvvm_atom_sys_min_gen_i:
+ case NVPTX::BI__nvvm_atom_sys_min_gen_ui:
+ case NVPTX::BI__nvvm_atom_sys_min_gen_l:
+ case NVPTX::BI__nvvm_atom_sys_min_gen_ul:
+ case NVPTX::BI__nvvm_atom_sys_min_gen_ll:
+ case NVPTX::BI__nvvm_atom_sys_min_gen_ull:
+ return MakeScopedAtomic(Intrinsic::nvvm_atomic_min_gen_i_sys);
+ case NVPTX::BI__nvvm_atom_cta_inc_gen_ui:
+ return MakeScopedAtomic(Intrinsic::nvvm_atomic_inc_gen_i_cta);
+ case NVPTX::BI__nvvm_atom_cta_dec_gen_ui:
+ return MakeScopedAtomic(Intrinsic::nvvm_atomic_dec_gen_i_cta);
+ case NVPTX::BI__nvvm_atom_sys_inc_gen_ui:
+ return MakeScopedAtomic(Intrinsic::nvvm_atomic_inc_gen_i_sys);
+ case NVPTX::BI__nvvm_atom_sys_dec_gen_ui:
+ return MakeScopedAtomic(Intrinsic::nvvm_atomic_dec_gen_i_sys);
+ case NVPTX::BI__nvvm_atom_cta_and_gen_i:
+ case NVPTX::BI__nvvm_atom_cta_and_gen_l:
+ case NVPTX::BI__nvvm_atom_cta_and_gen_ll:
+ return MakeScopedAtomic(Intrinsic::nvvm_atomic_and_gen_i_cta);
+ case NVPTX::BI__nvvm_atom_sys_and_gen_i:
+ case NVPTX::BI__nvvm_atom_sys_and_gen_l:
+ case NVPTX::BI__nvvm_atom_sys_and_gen_ll:
+ return MakeScopedAtomic(Intrinsic::nvvm_atomic_and_gen_i_sys);
+ case NVPTX::BI__nvvm_atom_cta_or_gen_i:
+ case NVPTX::BI__nvvm_atom_cta_or_gen_l:
+ case NVPTX::BI__nvvm_atom_cta_or_gen_ll:
+ return MakeScopedAtomic(Intrinsic::nvvm_atomic_or_gen_i_cta);
+ case NVPTX::BI__nvvm_atom_sys_or_gen_i:
+ case NVPTX::BI__nvvm_atom_sys_or_gen_l:
+ case NVPTX::BI__nvvm_atom_sys_or_gen_ll:
+ return MakeScopedAtomic(Intrinsic::nvvm_atomic_or_gen_i_sys);
+ case NVPTX::BI__nvvm_atom_cta_xor_gen_i:
+ case NVPTX::BI__nvvm_atom_cta_xor_gen_l:
+ case NVPTX::BI__nvvm_atom_cta_xor_gen_ll:
+ return MakeScopedAtomic(Intrinsic::nvvm_atomic_xor_gen_i_cta);
+ case NVPTX::BI__nvvm_atom_sys_xor_gen_i:
+ case NVPTX::BI__nvvm_atom_sys_xor_gen_l:
+ case NVPTX::BI__nvvm_atom_sys_xor_gen_ll:
+ return MakeScopedAtomic(Intrinsic::nvvm_atomic_xor_gen_i_sys);
+ case NVPTX::BI__nvvm_atom_cta_cas_gen_i:
+ case NVPTX::BI__nvvm_atom_cta_cas_gen_l:
+ case NVPTX::BI__nvvm_atom_cta_cas_gen_ll: {
+ Value *Ptr = EmitScalarExpr(E->getArg(0));
+ return Builder.CreateCall(
+ CGM.getIntrinsic(
+ Intrinsic::nvvm_atomic_cas_gen_i_cta,
+ {Ptr->getType()->getPointerElementType(), Ptr->getType()}),
+ {Ptr, EmitScalarExpr(E->getArg(1)), EmitScalarExpr(E->getArg(2))});
+ }
+ case NVPTX::BI__nvvm_atom_sys_cas_gen_i:
+ case NVPTX::BI__nvvm_atom_sys_cas_gen_l:
+ case NVPTX::BI__nvvm_atom_sys_cas_gen_ll: {
+ Value *Ptr = EmitScalarExpr(E->getArg(0));
+ return Builder.CreateCall(
+ CGM.getIntrinsic(
+ Intrinsic::nvvm_atomic_cas_gen_i_sys,
+ {Ptr->getType()->getPointerElementType(), Ptr->getType()}),
+ {Ptr, EmitScalarExpr(E->getArg(1)), EmitScalarExpr(E->getArg(2))});
+ }
default:
return nullptr;
}
OpenPOWER on IntegriCloud