jhuber6 updated this revision to Diff 414371.
jhuber6 added a comment.
Herald added subscribers: abrachet, phosek.
Fix architecture parsing and still include the GPU binary so cuobjcopy can use
them.
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D120272/new/
https://reviews.llvm.org/D120272
Files:
clang/include/clang/Basic/Cuda.h
clang/include/clang/Basic/DiagnosticDriverKinds.td
clang/include/clang/Driver/Options.td
clang/lib/Driver/Driver.cpp
clang/lib/Driver/ToolChains/Clang.cpp
clang/test/Driver/cuda-openmp-driver.cu
Index: clang/test/Driver/cuda-openmp-driver.cu
===================================================================
--- /dev/null
+++ clang/test/Driver/cuda-openmp-driver.cu
@@ -0,0 +1,16 @@
+// REQUIRES: clang-driver
+// REQUIRES: x86-registered-target
+// REQUIRES: nvptx-registered-target
+
+// RUN: %clang -### -target x86_64-linux-gnu -nocudalib -ccc-print-bindings -fgpu-rdc \
+// RUN: -foffload-new-driver --offload-arch=sm_35 --offload-arch=sm_70 %s 2>&1 \
+// RUN: | FileCheck -check-prefix CHECK %s
+
+// CHECK: "nvptx64-nvidia-cuda" - "clang", inputs: ["[[INPUT:.+]]"], output: "[[PTX_SM_35:.+]]"
+// CHECK: "nvptx64-nvidia-cuda" - "NVPTX::Assembler", inputs: ["[[PTX_SM_35]]"], output: "[[CUBIN_SM_35:.+]]"
+// CHECK: "nvptx64-nvidia-cuda" - "NVPTX::Linker", inputs: ["[[CUBIN_SM_35]]", "[[PTX_SM_35]]"], output: "[[FATBIN_SM_35:.+]]"
+// CHECK: "nvptx64-nvidia-cuda" - "clang", inputs: ["[[INPUT]]"], output: "[[PTX_SM_70:.+]]"
+// CHECK: "nvptx64-nvidia-cuda" - "NVPTX::Assembler", inputs: ["[[PTX_SM_70:.+]]"], output: "[[CUBIN_SM_70:.+]]"
+// CHECK: "nvptx64-nvidia-cuda" - "NVPTX::Linker", inputs: ["[[CUBIN_SM_70]]", "[[PTX_SM_70:.+]]"], output: "[[FATBIN_SM_70:.+]]"
+// CHECK: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[INPUT]]", "[[FATBIN_SM_35]]", "[[FATBIN_SM_70]]"], output: "[[HOST_OBJ:.+]]"
+// CHECK: "x86_64-unknown-linux-gnu" - "Offload::Linker", inputs: ["[[HOST_OBJ]]"], output: "a.out"
Index: clang/lib/Driver/ToolChains/Clang.cpp
===================================================================
--- clang/lib/Driver/ToolChains/Clang.cpp
+++ clang/lib/Driver/ToolChains/Clang.cpp
@@ -71,8 +71,8 @@
if (Args.hasArg(options::OPT_static))
if (const Arg *A =
Args.getLastArg(options::OPT_dynamic, options::OPT_mdynamic_no_pic))
- D.Diag(diag::err_drv_argument_not_allowed_with) << A->getAsString(Args)
- << "-static";
+ D.Diag(diag::err_drv_argument_not_allowed_with)
+ << A->getAsString(Args) << "-static";
}
// Add backslashes to escape spaces and other backslashes.
@@ -157,8 +157,8 @@
/// parameter in reciprocal argument strings. Return false if there is an error
/// parsing the refinement step. Otherwise, return true and set the Position
/// of the refinement step in the input string.
-static bool getRefinementStep(StringRef In, const Driver &D,
- const Arg &A, size_t &Position) {
+static bool getRefinementStep(StringRef In, const Driver &D, const Arg &A,
+ size_t &Position) {
const char RefinementStepToken = ':';
Position = In.find(RefinementStepToken);
if (Position != StringRef::npos) {
@@ -510,7 +510,7 @@
}
static bool mustUseNonLeafFramePointerForTarget(const llvm::Triple &Triple) {
- switch (Triple.getArch()){
+ switch (Triple.getArch()) {
default:
return false;
case llvm::Triple::arm:
@@ -705,7 +705,7 @@
/// Add a CC1 and CC1AS option to specify the coverage file path prefix map.
static void addCoveragePrefixMapArg(const Driver &D, const ArgList &Args,
- ArgStringList &CmdArgs) {
+ ArgStringList &CmdArgs) {
for (const Arg *A : Args.filtered(options::OPT_ffile_prefix_map_EQ,
options::OPT_fcoverage_prefix_map_EQ)) {
StringRef Map = A->getValue();
@@ -801,13 +801,12 @@
CSPGOGenerateArg->getOption().matches(options::OPT_fno_profile_generate))
CSPGOGenerateArg = nullptr;
- auto *ProfileGenerateArg = Args.getLastArg(
- options::OPT_fprofile_instr_generate,
- options::OPT_fprofile_instr_generate_EQ,
- options::OPT_fno_profile_instr_generate);
- if (ProfileGenerateArg &&
- ProfileGenerateArg->getOption().matches(
- options::OPT_fno_profile_instr_generate))
+ auto *ProfileGenerateArg =
+ Args.getLastArg(options::OPT_fprofile_instr_generate,
+ options::OPT_fprofile_instr_generate_EQ,
+ options::OPT_fno_profile_instr_generate);
+ if (ProfileGenerateArg && ProfileGenerateArg->getOption().matches(
+ options::OPT_fno_profile_instr_generate))
ProfileGenerateArg = nullptr;
if (PGOGenerateArg && ProfileGenerateArg)
@@ -1334,8 +1333,8 @@
}
if (ThroughHeader.empty()) {
- CmdArgs.push_back(Args.MakeArgString(
- Twine("-pch-through-hdrstop-") + (YcArg ? "create" : "use")));
+ CmdArgs.push_back(Args.MakeArgString(Twine("-pch-through-hdrstop-") +
+ (YcArg ? "create" : "use")));
} else {
CmdArgs.push_back(
Args.MakeArgString(Twine("-pch-through-header=") + ThroughHeader));
@@ -1374,8 +1373,8 @@
continue;
} else {
// Ignore the PCH if not first on command line and emit warning.
- D.Diag(diag::warn_drv_pch_not_first_include) << P
- << A->getAsString(Args);
+ D.Diag(diag::warn_drv_pch_not_first_include)
+ << P << A->getAsString(Args);
}
}
} else if (A->getOption().matches(options::OPT_isystem_after)) {
@@ -1552,8 +1551,9 @@
if (Arg *FinalOutput = Args.getLastArg(options::OPT_o))
F = FinalOutput->getValue();
} else {
- if (Format != "yaml" && // For YAML, keep the original behavior.
- Triple.isOSDarwin() && // Enable this only on darwin, since it's the only platform supporting .dSYM bundles.
+ if (Format != "yaml" && // For YAML, keep the original behavior.
+ Triple.isOSDarwin() && // Enable this only on darwin, since it's the
+ // only platform supporting .dSYM bundles.
Output.isFilename())
F = Output.getFilename();
}
@@ -1647,7 +1647,7 @@
StringRef(*StrictAlignIter) == "+strict-align")
CmdArgs.push_back("-Wunaligned-access");
}
-}
+} // namespace
static void CollectARMPACBTIOptions(const ToolChain &TC, const ArgList &Args,
ArgStringList &CmdArgs, bool isAArch64) {
@@ -1842,7 +1842,7 @@
CmdArgs.push_back("-target-abi");
CmdArgs.push_back(ABIName);
}
-}
+} // namespace
void Clang::AddAArch64TargetArgs(const ArgList &Args,
ArgStringList &CmdArgs) const {
@@ -1884,17 +1884,19 @@
if (Val.endswith("+"))
Val = Val.substr(0, Val.size() - 1);
else {
- bool Invalid = Val.getAsInteger(10, Bits); (void)Invalid;
+ bool Invalid = Val.getAsInteger(10, Bits);
+ (void)Invalid;
assert(!Invalid && "Failed to parse value");
CmdArgs.push_back(
Args.MakeArgString("-mvscale-max=" + llvm::Twine(Bits / 128)));
}
- bool Invalid = Val.getAsInteger(10, Bits); (void)Invalid;
+ bool Invalid = Val.getAsInteger(10, Bits);
+ (void)Invalid;
assert(!Invalid && "Failed to parse value");
CmdArgs.push_back(
Args.MakeArgString("-mvscale-min=" + llvm::Twine(Bits / 128)));
- // Silently drop requests for vector-length agnostic code as it's implied.
+ // Silently drop requests for vector-length agnostic code as it's implied.
} else if (!Val.equals("scalable"))
// Handle the unsupported values passed to msve-vector-bits.
D.Diag(diag::err_drv_unsupported_option_argument)
@@ -2077,8 +2079,8 @@
if (T.isOSBinFormatELF()) {
switch (getToolChain().getArch()) {
case llvm::Triple::ppc64: {
- if ((T.isOSFreeBSD() && T.getOSMajorVersion() >= 13) ||
- T.isOSOpenBSD() || T.isMusl())
+ if ((T.isOSFreeBSD() && T.getOSMajorVersion() >= 13) || T.isOSOpenBSD() ||
+ T.isMusl())
ABIName = "elfv2";
else
ABIName = "elfv1";
@@ -2100,9 +2102,9 @@
else if (V == "ibmlongdouble")
IEEELongDouble = false;
else if (V != "altivec")
- // The ppc64 linux abis are all "altivec" abis by default. Accept and ignore
- // the option if given as we don't have backend support for any targets
- // that don't use the altivec abi.
+ // The ppc64 linux abis are all "altivec" abis by default. Accept and
+ // ignore the option if given as we don't have backend support for any
+ // targets that don't use the altivec abi.
ABIName = A->getValue();
}
if (IEEELongDouble)
@@ -2204,8 +2206,8 @@
void Clang::AddSystemZTargetArgs(const ArgList &Args,
ArgStringList &CmdArgs) const {
- bool HasBackchain = Args.hasFlag(options::OPT_mbackchain,
- options::OPT_mno_backchain, false);
+ bool HasBackchain =
+ Args.hasFlag(options::OPT_mbackchain, options::OPT_mno_backchain, false);
bool HasPackedStack = Args.hasFlag(options::OPT_mpacked_stack,
options::OPT_mno_packed_stack, false);
systemz::FloatABI FloatABI =
@@ -2214,7 +2216,7 @@
if (HasBackchain && HasPackedStack && !HasSoftFloat) {
const Driver &D = getToolChain().getDriver();
D.Diag(diag::err_drv_unsupported_opt)
- << "-mpacked-stack -mbackchain -mhard-float";
+ << "-mpacked-stack -mbackchain -mhard-float";
}
if (HasBackchain)
CmdArgs.push_back("-mbackchain");
@@ -2371,7 +2373,8 @@
void Clang::DumpCompilationDatabase(Compilation &C, StringRef Filename,
StringRef Target, const InputInfo &Output,
- const InputInfo &Input, const ArgList &Args) const {
+ const InputInfo &Input,
+ const ArgList &Args) const {
// If this is a dry run, do not create the compilation database file.
if (C.getArgs().hasArg(options::OPT__HASH_HASH_HASH))
return;
@@ -2384,8 +2387,8 @@
auto File = std::make_unique<llvm::raw_fd_ostream>(
Filename, EC, llvm::sys::fs::OF_TextWithCRLF);
if (EC) {
- D.Diag(clang::diag::err_drv_compilationdatabase) << Filename
- << EC.message();
+ D.Diag(clang::diag::err_drv_compilationdatabase)
+ << Filename << EC.message();
return;
}
CompilationDatabase = std::move(File);
@@ -2408,7 +2411,7 @@
CDB << ", \"" << escape(Buf) << "\"";
}
CDB << ", \"" << escape(Input.getFilename()) << "\"";
- for (auto &A: Args) {
+ for (auto &A : Args) {
auto &O = A->getOption();
// Skip language selection, which is positional.
if (O.getID() == options::OPT_x)
@@ -2424,7 +2427,7 @@
// All other arguments are quoted and appended.
ArgStringList ASL;
A->render(Args, ASL);
- for (auto &it: ASL)
+ for (auto &it : ASL)
CDB << ", \"" << escape(it) << "\"";
}
Buf = "--target=";
@@ -2646,26 +2649,26 @@
Value.startswith("-mhwdiv") || Value.startswith("-march")) {
// Do nothing, we'll validate it later.
} else if (Value == "-defsym") {
- if (A->getNumValues() != 2) {
- D.Diag(diag::err_drv_defsym_invalid_format) << Value;
- break;
- }
- const char *S = A->getValue(1);
- auto Pair = StringRef(S).split('=');
- auto Sym = Pair.first;
- auto SVal = Pair.second;
-
- if (Sym.empty() || SVal.empty()) {
- D.Diag(diag::err_drv_defsym_invalid_format) << S;
- break;
- }
- int64_t IVal;
- if (SVal.getAsInteger(0, IVal)) {
- D.Diag(diag::err_drv_defsym_invalid_symval) << SVal;
- break;
- }
- CmdArgs.push_back(Value.data());
- TakeNextArg = true;
+ if (A->getNumValues() != 2) {
+ D.Diag(diag::err_drv_defsym_invalid_format) << Value;
+ break;
+ }
+ const char *S = A->getValue(1);
+ auto Pair = StringRef(S).split('=');
+ auto Sym = Pair.first;
+ auto SVal = Pair.second;
+
+ if (Sym.empty() || SVal.empty()) {
+ D.Diag(diag::err_drv_defsym_invalid_format) << S;
+ break;
+ }
+ int64_t IVal;
+ if (SVal.getAsInteger(0, IVal)) {
+ D.Diag(diag::err_drv_defsym_invalid_symval) << SVal;
+ break;
+ }
+ CmdArgs.push_back(Value.data());
+ TakeNextArg = true;
} else if (Value == "-fdebug-compilation-dir") {
CmdArgs.push_back("-fdebug-compilation-dir");
TakeNextArg = true;
@@ -2717,7 +2720,7 @@
bool AssociativeMath = false;
bool ReciprocalMath = false;
bool SignedZeros = true;
- bool TrappingMath = false; // Implemented via -ffp-exception-behavior
+ bool TrappingMath = false; // Implemented via -ffp-exception-behavior
bool TrappingMathPresent = false; // Is trapping-math in args, and not
// overriden by ffp-exception-behavior?
bool RoundingFPMath = false;
@@ -2773,10 +2776,9 @@
StringRef Val = A->getValue();
if (OFastEnabled && !Val.equals("fast")) {
- // Only -ffp-model=fast is compatible with OFast, ignore.
+ // Only -ffp-model=fast is compatible with OFast, ignore.
D.Diag(clang::diag::warn_drv_overriding_flag_option)
- << Args.MakeArgString("-ffp-model=" + Val)
- << "-Ofast";
+ << Args.MakeArgString("-ffp-model=" + Val) << "-Ofast";
break;
}
StrictFPModel = false;
@@ -2808,35 +2810,65 @@
D.Diag(diag::err_drv_unsupported_option_argument)
<< A->getOption().getName() << Val;
break;
- }
+ }
}
switch (optID) {
// If this isn't an FP option skip the claim below
- default: continue;
+ default:
+ continue;
// Options controlling individual features
- case options::OPT_fhonor_infinities: HonorINFs = true; break;
- case options::OPT_fno_honor_infinities: HonorINFs = false; break;
- case options::OPT_fhonor_nans: HonorNaNs = true; break;
- case options::OPT_fno_honor_nans: HonorNaNs = false; break;
- case options::OPT_fapprox_func: ApproxFunc = true; break;
- case options::OPT_fno_approx_func: ApproxFunc = false; break;
- case options::OPT_fmath_errno: MathErrno = true; break;
- case options::OPT_fno_math_errno: MathErrno = false; break;
- case options::OPT_fassociative_math: AssociativeMath = true; break;
- case options::OPT_fno_associative_math: AssociativeMath = false; break;
- case options::OPT_freciprocal_math: ReciprocalMath = true; break;
- case options::OPT_fno_reciprocal_math: ReciprocalMath = false; break;
- case options::OPT_fsigned_zeros: SignedZeros = true; break;
- case options::OPT_fno_signed_zeros: SignedZeros = false; break;
+ case options::OPT_fhonor_infinities:
+ HonorINFs = true;
+ break;
+ case options::OPT_fno_honor_infinities:
+ HonorINFs = false;
+ break;
+ case options::OPT_fhonor_nans:
+ HonorNaNs = true;
+ break;
+ case options::OPT_fno_honor_nans:
+ HonorNaNs = false;
+ break;
+ case options::OPT_fapprox_func:
+ ApproxFunc = true;
+ break;
+ case options::OPT_fno_approx_func:
+ ApproxFunc = false;
+ break;
+ case options::OPT_fmath_errno:
+ MathErrno = true;
+ break;
+ case options::OPT_fno_math_errno:
+ MathErrno = false;
+ break;
+ case options::OPT_fassociative_math:
+ AssociativeMath = true;
+ break;
+ case options::OPT_fno_associative_math:
+ AssociativeMath = false;
+ break;
+ case options::OPT_freciprocal_math:
+ ReciprocalMath = true;
+ break;
+ case options::OPT_fno_reciprocal_math:
+ ReciprocalMath = false;
+ break;
+ case options::OPT_fsigned_zeros:
+ SignedZeros = true;
+ break;
+ case options::OPT_fno_signed_zeros:
+ SignedZeros = false;
+ break;
case options::OPT_ftrapping_math:
if (!TrappingMathPresent && !FPExceptionBehavior.empty() &&
!FPExceptionBehavior.equals("strict"))
// Warn that previous value of option is overridden.
D.Diag(clang::diag::warn_drv_overriding_flag_option)
- << Args.MakeArgString("-ffp-exception-behavior=" + FPExceptionBehavior)
- << "-ftrapping-math";
+ << Args.MakeArgString("-ffp-exception-behavior=" +
+ FPExceptionBehavior)
+ << "-ftrapping-math";
TrappingMath = true;
TrappingMathPresent = true;
FPExceptionBehavior = "strict";
@@ -2846,8 +2878,9 @@
!FPExceptionBehavior.equals("ignore"))
// Warn that previous value of option is overridden.
D.Diag(clang::diag::warn_drv_overriding_flag_option)
- << Args.MakeArgString("-ffp-exception-behavior=" + FPExceptionBehavior)
- << "-fno-trapping-math";
+ << Args.MakeArgString("-ffp-exception-behavior=" +
+ FPExceptionBehavior)
+ << "-fno-trapping-math";
TrappingMath = false;
TrappingMathPresent = true;
FPExceptionBehavior = "ignore";
@@ -2891,7 +2924,7 @@
FPContract = Val;
else
D.Diag(diag::err_drv_unsupported_option_argument)
- << A->getOption().getName() << Val;
+ << A->getOption().getName() << Val;
break;
}
@@ -2909,8 +2942,9 @@
!FPExceptionBehavior.equals(Val))
// Warn that previous value of option is overridden.
D.Diag(clang::diag::warn_drv_overriding_flag_option)
- << Args.MakeArgString("-ffp-exception-behavior=" + FPExceptionBehavior)
- << Args.MakeArgString("-ffp-exception-behavior=" + Val);
+ << Args.MakeArgString("-ffp-exception-behavior=" +
+ FPExceptionBehavior)
+ << Args.MakeArgString("-ffp-exception-behavior=" + Val);
TrappingMath = TrappingMathPresent = false;
if (Val.equals("ignore") || Val.equals("maytrap"))
FPExceptionBehavior = Val;
@@ -3021,9 +3055,10 @@
StrictFPModel = false;
FPModel = "";
D.Diag(clang::diag::warn_drv_overriding_flag_option)
- << "-ffp-model=strict" <<
- ((A->getNumValues() == 0) ? A->getSpelling()
- : Args.MakeArgString(A->getSpelling() + A->getValue()));
+ << "-ffp-model=strict"
+ << ((A->getNumValues() == 0)
+ ? A->getSpelling()
+ : Args.MakeArgString(A->getSpelling() + A->getValue()));
}
}
@@ -3087,8 +3122,8 @@
CmdArgs.push_back(Args.MakeArgString("-frounding-math"));
if (!FPExceptionBehavior.empty())
- CmdArgs.push_back(Args.MakeArgString("-ffp-exception-behavior=" +
- FPExceptionBehavior));
+ CmdArgs.push_back(
+ Args.MakeArgString("-ffp-exception-behavior=" + FPExceptionBehavior));
if (!FPEvalMethod.empty())
CmdArgs.push_back(Args.MakeArgString("-ffp-eval-method=" + FPEvalMethod));
@@ -3110,8 +3145,8 @@
CmdArgs.push_back(Args.MakeArgString("-ffp-contract=fast"));
else
D.Diag(clang::diag::warn_drv_overriding_flag_option)
- << "-ffp-model=fast"
- << Args.MakeArgString("-ffp-contract=" + FPContract);
+ << "-ffp-model=fast"
+ << Args.MakeArgString("-ffp-contract=" + FPContract);
}
}
@@ -3166,8 +3201,7 @@
CmdArgs.push_back("-analyzer-checker=osx");
CmdArgs.push_back(
"-analyzer-checker=security.insecureAPI.decodeValueOfObjCType");
- }
- else if (Triple.isOSFuchsia())
+ } else if (Triple.isOSFuchsia())
CmdArgs.push_back("-analyzer-checker=fuchsia");
CmdArgs.push_back("-analyzer-checker=deadcode");
@@ -3176,7 +3210,8 @@
CmdArgs.push_back("-analyzer-checker=cplusplus");
if (!Triple.isPS4()) {
- CmdArgs.push_back("-analyzer-checker=security.insecureAPI.UncheckedReturn");
+ CmdArgs.push_back(
+ "-analyzer-checker=security.insecureAPI.UncheckedReturn");
CmdArgs.push_back("-analyzer-checker=security.insecureAPI.getpw");
CmdArgs.push_back("-analyzer-checker=security.insecureAPI.gets");
CmdArgs.push_back("-analyzer-checker=security.insecureAPI.mktemp");
@@ -3391,7 +3426,8 @@
}
if (!TrivialAutoVarInit.empty()) {
- if (TrivialAutoVarInit == "zero" && !Args.hasArg(options::OPT_enable_trivial_var_init_zero))
+ if (TrivialAutoVarInit == "zero" &&
+ !Args.hasArg(options::OPT_enable_trivial_var_init_zero))
D.Diag(diag::err_drv_trivial_auto_var_init_zero_disabled);
CmdArgs.push_back(
Args.MakeArgString("-ftrivial-auto-var-init=" + TrivialAutoVarInit));
@@ -3428,8 +3464,7 @@
options::OPT_cl_mad_enable,
options::OPT_cl_no_signed_zeros,
options::OPT_cl_fp32_correctly_rounded_divide_sqrt,
- options::OPT_cl_uniform_work_group_size
- };
+ options::OPT_cl_uniform_work_group_size};
if (Arg *A = Args.getLastArg(options::OPT_cl_std_EQ)) {
std::string CLStdStr = std::string("-cl-std=") + A->getValue();
@@ -3458,7 +3493,8 @@
options::OPT_ccc_arcmt_migrate)) {
ARCMTEnabled = true;
switch (A->getOption().getID()) {
- default: llvm_unreachable("missed a case");
+ default:
+ llvm_unreachable("missed a case");
case options::OPT_ccc_arcmt_check:
CmdArgs.push_back("-arcmt-action=check");
break;
@@ -3744,10 +3780,9 @@
static void RenderCharacterOptions(const ArgList &Args, const llvm::Triple &T,
ArgStringList &CmdArgs) {
// -fsigned-char is default.
- if (const Arg *A = Args.getLastArg(options::OPT_fsigned_char,
- options::OPT_fno_signed_char,
- options::OPT_funsigned_char,
- options::OPT_fno_unsigned_char)) {
+ if (const Arg *A = Args.getLastArg(
+ options::OPT_fsigned_char, options::OPT_fno_signed_char,
+ options::OPT_funsigned_char, options::OPT_fno_unsigned_char)) {
if (A->getOption().matches(options::OPT_funsigned_char) ||
A->getOption().matches(options::OPT_fno_signed_char)) {
CmdArgs.push_back("-fno-signed-char");
@@ -3840,9 +3875,8 @@
auto *Arg = Args.getLastArg(
options::OPT_fobjc_convert_messages_to_runtime_calls,
options::OPT_fno_objc_convert_messages_to_runtime_calls);
- if (Arg &&
- Arg->getOption().matches(
- options::OPT_fno_objc_convert_messages_to_runtime_calls))
+ if (Arg && Arg->getOption().matches(
+ options::OPT_fno_objc_convert_messages_to_runtime_calls))
CmdArgs.push_back("-fno-objc-convert-messages-to-runtime-calls");
}
@@ -4290,7 +4324,8 @@
? "-gpubnames"
: "-ggnu-pubnames");
const auto *SimpleTemplateNamesArg =
- Args.getLastArg(options::OPT_gsimple_template_names, options::OPT_gno_simple_template_names,
+ Args.getLastArg(options::OPT_gsimple_template_names,
+ options::OPT_gno_simple_template_names,
options::OPT_gsimple_template_names_EQ);
bool ForwardTemplateParams = DebuggerTuning == llvm::DebuggerKind::SCE;
if (SimpleTemplateNamesArg &&
@@ -4391,6 +4426,7 @@
// one input.
bool IsCuda = JA.isOffloading(Action::OFK_Cuda);
bool IsCudaDevice = JA.isDeviceOffloading(Action::OFK_Cuda);
+ bool IsCudaHost = JA.isHostOffloading(Action::OFK_Cuda);
bool IsHIP = JA.isOffloading(Action::OFK_HIP);
bool IsHIPDevice = JA.isDeviceOffloading(Action::OFK_HIP);
bool IsOpenMPDevice = JA.isDeviceOffloading(Action::OFK_OpenMP);
@@ -4403,7 +4439,7 @@
// A header module compilation doesn't have a main input file, so invent a
// fake one as a placeholder.
- const char *ModuleName = [&]{
+ const char *ModuleName = [&] {
auto *ModuleNameArg = Args.getLastArg(options::OPT_fmodule_name_EQ);
return ModuleNameArg ? ModuleNameArg->getValue() : "";
}();
@@ -4414,6 +4450,7 @@
InputInfoList ModuleHeaderInputs;
InputInfoList OpenMPHostInputs;
+ InputInfoList CudaHostInputs;
const InputInfo *CudaDeviceInput = nullptr;
const InputInfo *OpenMPDeviceInput = nullptr;
for (const InputInfo &I : Inputs) {
@@ -4428,6 +4465,9 @@
<< types::getTypeName(Expected);
}
ModuleHeaderInputs.push_back(I);
+ } else if (IsCudaHost && Args.hasArg(options::OPT_fopenmp_new_driver)) {
+ CudaHostInputs.push_back(I);
+ CudaDeviceInput = &I;
} else if ((IsCuda || IsHIP) && !CudaDeviceInput) {
CudaDeviceInput = &I;
} else if (IsOpenMPDevice && !OpenMPDeviceInput) {
@@ -4533,8 +4573,8 @@
bool Failure =
Triple.getArchName().substr(Offset).consumeInteger(10, Version);
if (Failure || Version < 7)
- D.Diag(diag::err_target_unsupported_arch) << Triple.getArchName()
- << TripleStr;
+ D.Diag(diag::err_target_unsupported_arch)
+ << Triple.getArchName() << TripleStr;
}
// Push all default warning arguments that are specific to
@@ -4604,9 +4644,8 @@
if (JA.getType() == types::TY_Nothing)
CmdArgs.push_back("-fsyntax-only");
else if (JA.getType() == types::TY_ModuleFile)
- CmdArgs.push_back(IsHeaderModulePrecompile
- ? "-emit-header-module"
- : "-emit-module-interface");
+ CmdArgs.push_back(IsHeaderModulePrecompile ? "-emit-header-module"
+ : "-emit-module-interface");
else
CmdArgs.push_back("-emit-pch");
} else if (isa<VerifyPCHJobAction>(JA)) {
@@ -4769,7 +4808,8 @@
// Render ABI arguments
switch (TC.getArch()) {
- default: break;
+ default:
+ break;
case llvm::Triple::arm:
case llvm::Triple::armeb:
case llvm::Triple::thumbeb:
@@ -5105,7 +5145,7 @@
}
CodeGenOptions::FramePointerKind FPKeepKind =
- getFramePointerKind(Args, RawTriple);
+ getFramePointerKind(Args, RawTriple);
const char *FPKeepKindStr = nullptr;
switch (FPKeepKind) {
case CodeGenOptions::FramePointerKind::None:
@@ -5149,12 +5189,10 @@
options::OPT_fno_allow_editor_placeholders, false))
CmdArgs.push_back("-fallow-editor-placeholders");
if (Args.hasFlag(options::OPT_fstrict_vtable_pointers,
- options::OPT_fno_strict_vtable_pointers,
- false))
+ options::OPT_fno_strict_vtable_pointers, false))
CmdArgs.push_back("-fstrict-vtable-pointers");
if (Args.hasFlag(options::OPT_fforce_emit_vtables,
- options::OPT_fno_force_emit_vtables,
- false))
+ options::OPT_fno_force_emit_vtables, false))
CmdArgs.push_back("-fforce-emit-vtables");
if (!Args.hasFlag(options::OPT_foptimize_sibling_calls,
options::OPT_fno_optimize_sibling_calls))
@@ -5697,8 +5735,7 @@
/*Joined=*/true);
} else
ImplyVCPPCVer = true;
- }
- else if (IsWindowsMSVC)
+ } else if (IsWindowsMSVC)
ImplyVCPPCXXVer = true;
Args.AddLastArg(CmdArgs, options::OPT_ftrigraphs,
@@ -5806,7 +5843,7 @@
if (const Arg *A = Args.getLastArg(options::OPT_fcf_runtime_abi_EQ)) {
static const char *kCFABIs[] = {
- "standalone", "objc", "swift", "swift-5.0", "swift-4.2", "swift-4.1",
+ "standalone", "objc", "swift", "swift-5.0", "swift-4.2", "swift-4.1",
};
if (find(kCFABIs, StringRef(A->getValue())) == std::end(kCFABIs))
@@ -5927,13 +5964,13 @@
<< A->getAsString(Args) << TripleStr;
}
-
if (Args.hasFlag(options::OPT_fvisibility_inlines_hidden,
- options::OPT_fno_visibility_inlines_hidden, false))
+ options::OPT_fno_visibility_inlines_hidden, false))
CmdArgs.push_back("-fvisibility-inlines-hidden");
- Args.AddLastArg(CmdArgs, options::OPT_fvisibility_inlines_hidden_static_local_var,
- options::OPT_fno_visibility_inlines_hidden_static_local_var);
+ Args.AddLastArg(CmdArgs,
+ options::OPT_fvisibility_inlines_hidden_static_local_var,
+ options::OPT_fno_visibility_inlines_hidden_static_local_var);
Args.AddLastArg(CmdArgs, options::OPT_fvisibility_global_new_delete_hidden);
Args.AddLastArg(CmdArgs, options::OPT_ftlsmodel_EQ);
@@ -6319,8 +6356,8 @@
ToolChain::RTTIMode RTTIMode = TC.getRTTIMode();
- if (KernelOrKext || (types::isCXX(InputType) &&
- (RTTIMode == ToolChain::RM_Disabled)))
+ if (KernelOrKext ||
+ (types::isCXX(InputType) && (RTTIMode == ToolChain::RM_Disabled)))
CmdArgs.push_back("-fno-rtti");
// -fshort-enums=0 is default for all architectures except Hexagon and z/OS.
@@ -6654,16 +6691,16 @@
if (Arg *inputCharset = Args.getLastArg(options::OPT_finput_charset_EQ)) {
StringRef value = inputCharset->getValue();
if (!value.equals_insensitive("utf-8"))
- D.Diag(diag::err_drv_invalid_value) << inputCharset->getAsString(Args)
- << value;
+ D.Diag(diag::err_drv_invalid_value)
+ << inputCharset->getAsString(Args) << value;
}
// -fexec_charset=UTF-8 is default. Reject others
if (Arg *execCharset = Args.getLastArg(options::OPT_fexec_charset_EQ)) {
StringRef value = execCharset->getValue();
if (!value.equals_insensitive("utf-8"))
- D.Diag(diag::err_drv_invalid_value) << execCharset->getAsString(Args)
- << value;
+ D.Diag(diag::err_drv_invalid_value)
+ << execCharset->getAsString(Args) << value;
}
RenderDiagnosticsOptions(D, Args, CmdArgs);
@@ -6827,15 +6864,13 @@
// parser.
// -finclude-default-header flag is for preprocessor,
// do not pass it to other cc1 commands when save-temps is enabled
- if (C.getDriver().isSaveTempsEnabled() &&
- !isa<PreprocessJobAction>(JA)) {
+ if (C.getDriver().isSaveTempsEnabled() && !isa<PreprocessJobAction>(JA)) {
for (auto Arg : Args.filtered(options::OPT_Xclang)) {
Arg->claim();
if (StringRef(Arg->getValue()) != "-finclude-default-header")
CmdArgs.push_back(Arg->getValue());
}
- }
- else {
+ } else {
Args.AddAllArgValues(CmdArgs, options::OPT_Xclang);
}
for (const Arg *A : Args.filtered(options::OPT_mllvm)) {
@@ -6911,10 +6946,10 @@
// Host-side cuda compilation receives all device-side outputs in a single
// fatbin as Inputs[1]. Include the binary with -fcuda-include-gpubinary.
if ((IsCuda || IsHIP) && CudaDeviceInput) {
- CmdArgs.push_back("-fcuda-include-gpubinary");
- CmdArgs.push_back(CudaDeviceInput->getFilename());
- if (Args.hasFlag(options::OPT_fgpu_rdc, options::OPT_fno_gpu_rdc, false))
- CmdArgs.push_back("-fgpu-rdc");
+ CmdArgs.push_back("-fcuda-include-gpubinary");
+ CmdArgs.push_back(CudaDeviceInput->getFilename());
+ if (Args.hasFlag(options::OPT_fgpu_rdc, options::OPT_fno_gpu_rdc, false))
+ CmdArgs.push_back("-fgpu-rdc");
}
if (IsCuda) {
@@ -6970,6 +7005,7 @@
auto OpenMPTCs = C.getOffloadToolChains<Action::OFK_OpenMP>();
for (auto TI = OpenMPTCs.first, TE = OpenMPTCs.second; TI != TE;
++TI, ++InputFile) {
+ assert(InputFile->isFilename() && "Offloading requires a filename");
const ToolChain *TC = TI->second;
const ArgList &TCArgs = C.getArgsForToolChain(TC, "", Action::OFK_OpenMP);
StringRef File =
@@ -6982,6 +7018,20 @@
TC->getTripleString() + "." +
TCArgs.getLastArgValue(options::OPT_march_EQ) + "." + InputName));
}
+ } else if (IsCudaHost && !CudaHostInputs.empty()) {
+ const ToolChain *TC = C.getSingleOffloadToolChain<Action::OFK_Cuda>();
+ for (const auto &InputFile : CudaHostInputs) {
+ assert(InputFile.isFilename() && "Offloading requires a filename");
+ StringRef File =
+ C.getArgs().MakeArgString(TC->getInputFilename(InputFile));
+ StringRef InputName = Clang::getBaseInputStem(Args, Inputs);
+ // The CUDA toolchain should have a bound arch appended to the filename.
+ StringRef Arch = File.rsplit(".").first.rsplit('-').second;
+ CmdArgs.push_back(Args.MakeArgString(
+ "-fembed-offload-object=" + File + "," +
+ Action::GetOffloadKindName(Action::OFK_Cuda) + "." +
+ TC->getTripleString() + "." + Arch + "." + InputName));
+ }
}
if (Triple.isAMDGPU()) {
@@ -7093,14 +7143,14 @@
}
if (Args.hasArg(options::OPT_forder_file_instrumentation)) {
- CmdArgs.push_back("-forder-file-instrumentation");
- // Enable order file instrumentation when ThinLTO is not on. When ThinLTO is
- // on, we need to pass these flags as linker flags and that will be handled
- // outside of the compiler.
- if (!IsUsingLTO) {
- CmdArgs.push_back("-mllvm");
- CmdArgs.push_back("-enable-order-file-instrumentation");
- }
+ CmdArgs.push_back("-forder-file-instrumentation");
+ // Enable order file instrumentation when ThinLTO is not on. When ThinLTO is
+ // on, we need to pass these flags as linker flags and that will be handled
+ // outside of the compiler.
+ if (!IsUsingLTO) {
+ CmdArgs.push_back("-mllvm");
+ CmdArgs.push_back("-enable-order-file-instrumentation");
+ }
}
if (Arg *A = Args.getLastArg(options::OPT_fforce_enable_int128,
@@ -7226,8 +7276,8 @@
if (Arg *A = Args.getLastArg(options::OPT_pg))
if (FPKeepKind == CodeGenOptions::FramePointerKind::None &&
!Args.hasArg(options::OPT_mfentry))
- D.Diag(diag::err_drv_argument_not_allowed_with) << "-fomit-frame-pointer"
- << A->getAsString(Args);
+ D.Diag(diag::err_drv_argument_not_allowed_with)
+ << "-fomit-frame-pointer" << A->getAsString(Args);
// Claim some arguments which clang supports automatically.
@@ -7280,7 +7330,7 @@
!getToolChain().getTriple().isOSBinFormatCOFF()) {
getToolChain().getDriver().Diag(
diag::err_drv_gnustep_objc_runtime_incompatible_binary)
- << runtime.getVersion().getMajor();
+ << runtime.getVersion().getMajor();
}
runtimeArg->render(args, cmdArgs);
@@ -7579,11 +7629,10 @@
if (VolatileOptionID == options::OPT__SLASH_volatile_ms)
CmdArgs.push_back("-fms-volatile");
- if (Args.hasFlag(options::OPT__SLASH_Zc_dllexportInlines_,
- options::OPT__SLASH_Zc_dllexportInlines,
- false)) {
- CmdArgs.push_back("-fno-dllexport-inlines");
- }
+ if (Args.hasFlag(options::OPT__SLASH_Zc_dllexportInlines_,
+ options::OPT__SLASH_Zc_dllexportInlines, false)) {
+ CmdArgs.push_back("-fno-dllexport-inlines");
+ }
Arg *MostGeneralArg = Args.getLastArg(options::OPT__SLASH_vmg);
Arg *BestCaseArg = Args.getLastArg(options::OPT__SLASH_vmb);
@@ -7735,7 +7784,7 @@
}
void ClangAs::AddRISCVTargetArgs(const ArgList &Args,
- ArgStringList &CmdArgs) const {
+ ArgStringList &CmdArgs) const {
const llvm::Triple &Triple = getToolChain().getTriple();
StringRef ABIName = riscv::getRISCVABI(Args, Triple);
@@ -7854,7 +7903,6 @@
renderDwarfFormat(D, Triple, Args, CmdArgs, DwarfVersion);
RenderDebugInfoCompressionArgs(Args, CmdArgs, D, getToolChain());
-
// Handle -fPIC et al -- the relocation-model affects the assembler
// for some targets.
llvm::Reloc::Model RelocationModel;
@@ -7916,8 +7964,8 @@
// only, not C/C++.
if (Args.hasFlag(options::OPT_mdefault_build_attributes,
options::OPT_mno_default_build_attributes, true)) {
- CmdArgs.push_back("-mllvm");
- CmdArgs.push_back("-arm-add-build-attributes");
+ CmdArgs.push_back("-mllvm");
+ CmdArgs.push_back("-arm-add-build-attributes");
}
break;
@@ -8234,14 +8282,17 @@
ArgStringList CmdArgs;
// Pass the CUDA path to the linker wrapper tool.
- for (auto &I : llvm::make_range(OpenMPTCRange.first, OpenMPTCRange.second)) {
- const ToolChain *TC = I.second;
- if (TC->getTriple().isNVPTX()) {
- CudaInstallationDetector CudaInstallation(D, TheTriple, Args);
- if (CudaInstallation.isValid())
- CmdArgs.push_back(Args.MakeArgString(
- "--cuda-path=" + CudaInstallation.getInstallPath()));
- break;
+ for (Action::OffloadKind Kind : {Action::OFK_Cuda, Action::OFK_OpenMP}) {
+ auto TCRange = C.getOffloadToolChains(Kind);
+ for (auto &I : llvm::make_range(TCRange.first, TCRange.second)) {
+ const ToolChain *TC = I.second;
+ if (TC->getTriple().isNVPTX()) {
+ CudaInstallationDetector CudaInstallation(D, TheTriple, Args);
+ if (CudaInstallation.isValid())
+ CmdArgs.push_back(Args.MakeArgString(
+ "--cuda-path=" + CudaInstallation.getInstallPath()));
+ break;
+ }
}
}
Index: clang/lib/Driver/Driver.cpp
===================================================================
--- clang/lib/Driver/Driver.cpp
+++ clang/lib/Driver/Driver.cpp
@@ -456,6 +456,10 @@
}
}
+ // Using the new offloading driver implies redistributable device code.
+ if (A->getOption().matches(options::OPT_foffload_new_driver))
+ DAL->AddFlagArg(A, Opts.getOption(options::OPT_fgpu_rdc));
+
// Pick up inputs via the -- option.
if (A->getOption().matches(options::OPT__DASH_DASH)) {
A->claim();
@@ -4088,6 +4092,101 @@
Args.ClaimAllArgs(options::OPT_cuda_compile_host_device);
}
+/// Returns the canonical name for the offloading architecture when using HIP or
+/// CUDA.
+static StringRef getCanonicalArchString(Compilation &C,
+ llvm::opt::DerivedArgList &Args,
+ StringRef ArchStr,
+ Action::OffloadKind Kind) {
+ if (Kind == Action::OFK_Cuda) {
+ CudaArch Arch = StringToCudaArch(ArchStr);
+ if (Arch == CudaArch::UNKNOWN || !IsNVIDIAGpuArch(Arch)) {
+ C.getDriver().Diag(clang::diag::err_drv_cuda_bad_gpu_arch) << ArchStr;
+ return StringRef();
+ }
+ return Args.MakeArgStringRef(CudaArchToString(Arch));
+ } else if (Kind == Action::OFK_HIP) {
+ llvm::StringMap<bool> Features;
+ // getHIPOffloadTargetTriple() is known to return valid value as it has
+ // been called successfully in the CreateOffloadingDeviceToolChains().
+ auto Arch = parseTargetID(
+ *getHIPOffloadTargetTriple(C.getDriver(), C.getInputArgs()), ArchStr,
+ &Features);
+ if (!Arch) {
+ C.getDriver().Diag(clang::diag::err_drv_bad_target_id) << ArchStr;
+ C.setContainsError();
+ return StringRef();
+ }
+ return Args.MakeArgStringRef(
+ getCanonicalTargetID(Arch.getValue(), Features));
+ }
+ return StringRef();
+}
+
+/// Checks if the set offloading architectures does not conflict. Returns the
+/// incompatible pair if a conflict occurs.
+static llvm::Optional<std::pair<llvm::StringRef, llvm::StringRef>>
+getConflictOffloadArchCombination(const llvm::DenseSet<StringRef> &Archs,
+ Action::OffloadKind Kind) {
+ if (Kind != Action::OFK_HIP)
+ return None;
+
+ std::set<StringRef> ArchSet;
+ llvm::copy(Archs, std::inserter(ArchSet, ArchSet.begin()));
+ return getConflictTargetIDCombination(ArchSet);
+}
+
+/// Returns the set of bound architectures active for this compilation kind.
+/// This function returns a set of bound architectures, if there are no bound
+/// architctures we return a set containing only the empty string.
+static llvm::DenseSet<StringRef>
+getOffloadArchs(Compilation &C, llvm::opt::DerivedArgList &Args,
+ Action::OffloadKind Kind) {
+
+ // If this is OpenMP offloading we don't use a bound architecture.
+ if (Kind == Action::OFK_OpenMP)
+ return llvm::DenseSet<StringRef>{StringRef()};
+
+ // --offload and --offload-arch options are mutually exclusive.
+ if (Args.hasArgNoClaim(options::OPT_offload_EQ) &&
+ Args.hasArgNoClaim(options::OPT_offload_arch_EQ,
+ options::OPT_no_offload_arch_EQ)) {
+ C.getDriver().Diag(diag::err_opt_not_valid_with_opt)
+ << "--offload"
+ << (Args.hasArgNoClaim(options::OPT_offload_arch_EQ)
+ ? "--offload-arch"
+ : "--no-offload-arch");
+ }
+
+ llvm::DenseSet<StringRef> Archs;
+ for (auto &Arg : Args) {
+ if (Arg->getOption().matches(options::OPT_offload_arch_EQ)) {
+ Archs.insert(getCanonicalArchString(C, Args, Arg->getValue(), Kind));
+ } else if (Arg->getOption().matches(options::OPT_no_offload_arch_EQ)) {
+ if (Arg->getValue() == StringRef("all"))
+ Archs.clear();
+ else
+ Archs.erase(getCanonicalArchString(C, Args, Arg->getValue(), Kind));
+ }
+ }
+
+ if (auto ConflictingArchs = getConflictOffloadArchCombination(Archs, Kind)) {
+ C.getDriver().Diag(clang::diag::err_drv_bad_offload_arch_combo)
+ << ConflictingArchs.getValue().first
+ << ConflictingArchs.getValue().second;
+ C.setContainsError();
+ }
+
+ if (Archs.empty()) {
+ if (Kind == Action::OFK_Cuda)
+ Archs.insert(CudaArchToString(DefaultCudaArch));
+ else if (Kind == Action::OFK_HIP)
+ Archs.insert(CudaArchToString(DefaultHIPArch));
+ }
+
+ return Archs;
+}
+
Action *Driver::BuildOffloadingActions(Compilation &C,
llvm::opt::DerivedArgList &Args,
const InputTy &Input,
@@ -4100,12 +4199,18 @@
types::ID InputType = Input.first;
const Arg *InputArg = Input.second;
- const Action::OffloadKind OffloadKinds[] = {Action::OFK_OpenMP};
+ const Action::OffloadKind OffloadKinds[] = {
+ Action::OFK_OpenMP, Action::OFK_Cuda, Action::OFK_HIP};
for (Action::OffloadKind Kind : OffloadKinds) {
SmallVector<const ToolChain *, 2> ToolChains;
ActionList DeviceActions;
+ const bool Relocatable =
+ Kind == Action::OFK_OpenMP ||
+ Args.hasFlag(options::OPT_fgpu_rdc, options::OPT_fno_gpu_rdc,
+ /*Default=*/false);
+
auto TCRange = C.getOffloadToolChains(Kind);
for (auto TI = TCRange.first, TE = TCRange.second; TI != TE; ++TI)
ToolChains.push_back(TI->second);
@@ -4113,7 +4218,18 @@
if (ToolChains.empty())
continue;
- for (unsigned I = 0; I < ToolChains.size(); ++I)
+ if (!Relocatable) {
+ Diags.Report(diag::err_drv_non_relocatable);
+ return HostAction;
+ }
+
+ // Get the product of all bound architectures and toolchains.
+ SmallVector<std::pair<const ToolChain *, StringRef>> TCAndArchs;
+ for (const ToolChain *TC : ToolChains)
+ for (StringRef Arch : getOffloadArchs(C, Args, Kind))
+ TCAndArchs.push_back(std::make_pair(TC, Arch));
+
+ for (unsigned I = 0, E = TCAndArchs.size(); I != E; ++I)
DeviceActions.push_back(C.MakeAction<InputAction>(*InputArg, InputType));
if (DeviceActions.empty())
@@ -4127,7 +4243,7 @@
break;
}
- auto TC = ToolChains.begin();
+ auto TCAndArch = TCAndArchs.begin();
for (Action *&A : DeviceActions) {
A = ConstructPhaseAction(C, Args, Phase, A, Kind);
@@ -4135,19 +4251,28 @@
HostAction->setCannotBeCollapsedWithNextDependentAction();
OffloadAction::HostDependence HDep(
*HostAction, *C.getSingleOffloadToolChain<Action::OFK_Host>(),
- /*BourdArch=*/nullptr, Action::OFK_OpenMP);
+ /*BoundArch=*/nullptr, Kind);
OffloadAction::DeviceDependences DDep;
- DDep.add(*A, **TC, /*BoundArch=*/nullptr, Kind);
+ DDep.add(*A, *TCAndArch->first, /*BoundArch=*/nullptr, Kind);
A = C.MakeAction<OffloadAction>(HDep, DDep);
+ ++TCAndArch;
+ } else if (isa<AssembleJobAction>(A) && Kind == Action::OFK_Cuda) {
+ ActionList FatbinActions;
+ for (Action *A : {A, A->getInputs()[0]}) {
+ OffloadAction::DeviceDependences DDep;
+ DDep.add(*A, *TCAndArch->first, TCAndArch->second.data(), Kind);
+ FatbinActions.emplace_back(
+ C.MakeAction<OffloadAction>(DDep, A->getType()));
+ }
+ A = C.MakeAction<LinkJobAction>(FatbinActions, types::TY_CUDA_FATBIN);
}
- ++TC;
}
}
- auto TC = ToolChains.begin();
+ auto TCAndArch = TCAndArchs.begin();
for (Action *A : DeviceActions) {
- DDeps.add(*A, **TC, /*BoundArch=*/nullptr, Kind);
- TC++;
+ DDeps.add(*A, *TCAndArch->first, TCAndArch->second.data(), Kind);
+ ++TCAndArch;
}
}
@@ -4249,7 +4374,7 @@
return C.MakeAction<BackendJobAction>(Input, Output);
}
if (isUsingLTO(/* IsOffload */ true) &&
- TargetDeviceOffloadKind == Action::OFK_OpenMP) {
+ TargetDeviceOffloadKind != Action::OFK_None) {
types::ID Output =
Args.hasArg(options::OPT_S) ? types::TY_LTO_IR : types::TY_LTO_BC;
return C.MakeAction<BackendJobAction>(Input, Output);
Index: clang/include/clang/Driver/Options.td
===================================================================
--- clang/include/clang/Driver/Options.td
+++ clang/include/clang/Driver/Options.td
@@ -2512,6 +2512,8 @@
HelpText<"Use the static host OpenMP runtime while linking.">;
def fopenmp_new_driver : Flag<["-"], "fopenmp-new-driver">, Flags<[CC1Option]>, Group<Action_Group>,
HelpText<"Use the new driver for OpenMP offloading.">;
+def foffload_new_driver : Flag<["-"], "foffload-new-driver">, Flags<[CC1Option]>, Group<Action_Group>,
+ HelpText<"Use the new driver for offloading.">;
def fno_optimize_sibling_calls : Flag<["-"], "fno-optimize-sibling-calls">, Group<f_Group>;
def foptimize_sibling_calls : Flag<["-"], "foptimize-sibling-calls">, Group<f_Group>;
defm escaping_block_tail_calls : BoolFOption<"escaping-block-tail-calls",
Index: clang/include/clang/Basic/DiagnosticDriverKinds.td
===================================================================
--- clang/include/clang/Basic/DiagnosticDriverKinds.td
+++ clang/include/clang/Basic/DiagnosticDriverKinds.td
@@ -327,6 +327,8 @@
"invalid value '%1' in '%0', value must be 'none' or a positive integer">;
def err_drv_small_columns : Error<
"invalid value '%1' in '%0', value must be '%2' or greater">;
+def err_drv_non_relocatable : Error<
+ "the new driver requires relocatable code, compile with '-fgpu-rdc' enabled">;
def err_drv_invalid_malign_branch_EQ : Error<
"invalid argument '%0' to -malign-branch=; each element must be one of: %1">;
Index: clang/include/clang/Basic/Cuda.h
===================================================================
--- clang/include/clang/Basic/Cuda.h
+++ clang/include/clang/Basic/Cuda.h
@@ -102,6 +102,9 @@
LAST,
};
+constexpr CudaArch DefaultCudaArch = CudaArch::SM_35;
+constexpr CudaArch DefaultHIPArch = CudaArch::GFX803;
+
static inline bool IsNVIDIAGpuArch(CudaArch A) {
return A >= CudaArch::SM_20 && A < CudaArch::GFX600;
}
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
