weiwang created this revision.
Herald added subscribers: hoy, dexonsmith, wenlei, dang, guansong, yaxunl.
weiwang requested review of this revision.
Herald added a reviewer: jdoerfert.
Herald added subscribers: cfe-commits, sstefan1.
Herald added a project: clang.
There are cases where no target compilation/offloading would ever happen, but
we are still paying the price for handling deferred diags. The new cc1 option
allows user to explictly skip deferred diags handling in FE.
This results in considerable build time improvement from our internal
workloads.
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D109175
Files:
clang/include/clang/Basic/LangOptions.def
clang/include/clang/Driver/Options.td
clang/lib/Frontend/CompilerInvocation.cpp
clang/lib/Sema/SemaDecl.cpp
clang/test/OpenMP/declare_target_messages.cpp
Index: clang/test/OpenMP/declare_target_messages.cpp
===================================================================
--- clang/test/OpenMP/declare_target_messages.cpp
+++ clang/test/OpenMP/declare_target_messages.cpp
@@ -6,6 +6,9 @@
// RUN: %clang_cc1 -triple x86_64-apple-macos10.7.0
-verify=expected,omp5,host5 -fopenmp-simd -fopenmp-is-device -fnoopenmp-use-tls
-ferror-limit 100 -o - %s
// RUN: %clang_cc1 -triple x86_64-apple-macos10.7.0 -verify=expected,omp45
-fopenmp-version=45 -fopenmp-simd -fnoopenmp-use-tls -ferror-limit 100 -o - %s
+// RUN: %clang_cc1 -triple x86_64-apple-macos10.7.0 -verify=expected,omp5,dev5
-fopenmp -fopenmp-is-device -fopenmp-targets=x86_64-apple-macos10.7.0
-aux-triple x86_64-apple-macos10.7.0 -fnoopenmp-use-tls
-fopenmp-skip-deferred-diags -ferror-limit 100 -o - %s
+// RUN: %clang_cc1 -triple x86_64-apple-macos10.7.0
-verify=expected,omp5,host5 -fopenmp-simd -fopenmp-is-device -fnoopenmp-use-tls
-fopenmp-skip-deferred-diags -ferror-limit 100 -o - %s
+// RUN: %clang_cc1 -triple x86_64-apple-macos10.7.0 -verify=expected,omp5
-fopenmp -fnoopenmp-use-tls -fopenmp-skip-deferred-diags -ferror-limit 100 -o -
%s
#pragma omp end declare target // expected-error {{unexpected OpenMP directive
'#pragma omp end declare target'}}
int a, b, z; // omp5-error {{variable captured in declare target region must
appear in a to clause}}
Index: clang/lib/Sema/SemaDecl.cpp
===================================================================
--- clang/lib/Sema/SemaDecl.cpp
+++ clang/lib/Sema/SemaDecl.cpp
@@ -12609,7 +12609,8 @@
VDecl->setInitStyle(VarDecl::ListInit);
}
- if (LangOpts.OpenMP && VDecl->isFileVarDecl())
+ if (LangOpts.OpenMP && !LangOpts.OpenMPSkipDeferredDiags &&
+ VDecl->isFileVarDecl())
DeclsToCheckForDeferredDiags.insert(VDecl);
CheckCompleteVariableDeclaration(VDecl);
}
@@ -14839,7 +14840,8 @@
DiscardCleanupsInEvaluationContext();
}
- if (FD && (LangOpts.OpenMP || LangOpts.CUDA || LangOpts.SYCLIsDevice)) {
+ if (FD && ((LangOpts.OpenMP && !LangOpts.OpenMPSkipDeferredDiags) ||
+ LangOpts.CUDA || LangOpts.SYCLIsDevice)) {
auto ES = getEmissionStatus(FD);
if (ES == Sema::FunctionEmissionStatus::Emitted ||
ES == Sema::FunctionEmissionStatus::Unknown)
Index: clang/lib/Frontend/CompilerInvocation.cpp
===================================================================
--- clang/lib/Frontend/CompilerInvocation.cpp
+++ clang/lib/Frontend/CompilerInvocation.cpp
@@ -3489,6 +3489,9 @@
if (Opts.OpenMPCUDAForceFullRuntime)
GenerateArg(Args, OPT_fopenmp_cuda_force_full_runtime, SA);
+ if (Opts.OpenMPSkipDeferredDiags)
+ GenerateArg(Args, OPT_fopenmp_skip_deferred_diags, SA);
+
// The arguments used to set Optimize, OptimizeSize and NoInlineDefine are
// generated from CodeGenOptions.
@@ -3928,6 +3931,10 @@
Opts.OpenMPIsDevice && (T.isNVPTX() || T.isAMDGCN()) &&
Args.hasArg(options::OPT_fopenmp_cuda_force_full_runtime);
+ Opts.OpenMPSkipDeferredDiags =
+ Opts.OpenMP && !Opts.OpenMPSimd && !IsTargetSpecified &&
+ Args.hasArg(options::OPT_fopenmp_skip_deferred_diags);
+
// FIXME: Eliminate this dependency.
unsigned Opt = getOptimizationLevel(Args, IK, Diags),
OptSize = getOptimizationLevelSize(Args);
Index: clang/include/clang/Driver/Options.td
===================================================================
--- clang/include/clang/Driver/Options.td
+++ clang/include/clang/Driver/Options.td
@@ -5799,6 +5799,8 @@
HelpText<"Generate code only for an OpenMP target device.">;
def fopenmp_host_ir_file_path : Separate<["-"], "fopenmp-host-ir-file-path">,
HelpText<"Path to the IR file produced by the frontend for the host.">;
+def fopenmp_skip_deferred_diags : Flag<["-"], "fopenmp-skip-deferred-diags">,
+ HelpText<"Do not generate deferred diagnostics for function host/device
availability. Use this flag only when no offloading or omp target directive is
used.">;
//===----------------------------------------------------------------------===//
// SYCL Options
Index: clang/include/clang/Basic/LangOptions.def
===================================================================
--- clang/include/clang/Basic/LangOptions.def
+++ clang/include/clang/Basic/LangOptions.def
@@ -243,6 +243,7 @@
LANGOPT(OpenMPCUDAReductionBufNum , 32, 1024, "Number of the reduction records
in the intermediate reduction buffer used for the teams reductions.")
LANGOPT(OpenMPTargetNewRuntime , 1, 0, "Use the new bitcode library for OpenMP
offloading")
LANGOPT(OpenMPOptimisticCollapse , 1, 0, "Use at most 32 bits to represent
the collapsed loop nest counter.")
+LANGOPT(OpenMPSkipDeferredDiags, 1, 0, "Do not generate deferred diagnostics
for function host/device availability.")
LANGOPT(RenderScript , 1, 0, "RenderScript")
LANGOPT(CUDAIsDevice , 1, 0, "compiling for CUDA device")
Index: clang/test/OpenMP/declare_target_messages.cpp
===================================================================
--- clang/test/OpenMP/declare_target_messages.cpp
+++ clang/test/OpenMP/declare_target_messages.cpp
@@ -6,6 +6,9 @@
// RUN: %clang_cc1 -triple x86_64-apple-macos10.7.0 -verify=expected,omp5,host5 -fopenmp-simd -fopenmp-is-device -fnoopenmp-use-tls -ferror-limit 100 -o - %s
// RUN: %clang_cc1 -triple x86_64-apple-macos10.7.0 -verify=expected,omp45 -fopenmp-version=45 -fopenmp-simd -fnoopenmp-use-tls -ferror-limit 100 -o - %s
+// RUN: %clang_cc1 -triple x86_64-apple-macos10.7.0 -verify=expected,omp5,dev5 -fopenmp -fopenmp-is-device -fopenmp-targets=x86_64-apple-macos10.7.0 -aux-triple x86_64-apple-macos10.7.0 -fnoopenmp-use-tls -fopenmp-skip-deferred-diags -ferror-limit 100 -o - %s
+// RUN: %clang_cc1 -triple x86_64-apple-macos10.7.0 -verify=expected,omp5,host5 -fopenmp-simd -fopenmp-is-device -fnoopenmp-use-tls -fopenmp-skip-deferred-diags -ferror-limit 100 -o - %s
+// RUN: %clang_cc1 -triple x86_64-apple-macos10.7.0 -verify=expected,omp5 -fopenmp -fnoopenmp-use-tls -fopenmp-skip-deferred-diags -ferror-limit 100 -o - %s
#pragma omp end declare target // expected-error {{unexpected OpenMP directive '#pragma omp end declare target'}}
int a, b, z; // omp5-error {{variable captured in declare target region must appear in a to clause}}
Index: clang/lib/Sema/SemaDecl.cpp
===================================================================
--- clang/lib/Sema/SemaDecl.cpp
+++ clang/lib/Sema/SemaDecl.cpp
@@ -12609,7 +12609,8 @@
VDecl->setInitStyle(VarDecl::ListInit);
}
- if (LangOpts.OpenMP && VDecl->isFileVarDecl())
+ if (LangOpts.OpenMP && !LangOpts.OpenMPSkipDeferredDiags &&
+ VDecl->isFileVarDecl())
DeclsToCheckForDeferredDiags.insert(VDecl);
CheckCompleteVariableDeclaration(VDecl);
}
@@ -14839,7 +14840,8 @@
DiscardCleanupsInEvaluationContext();
}
- if (FD && (LangOpts.OpenMP || LangOpts.CUDA || LangOpts.SYCLIsDevice)) {
+ if (FD && ((LangOpts.OpenMP && !LangOpts.OpenMPSkipDeferredDiags) ||
+ LangOpts.CUDA || LangOpts.SYCLIsDevice)) {
auto ES = getEmissionStatus(FD);
if (ES == Sema::FunctionEmissionStatus::Emitted ||
ES == Sema::FunctionEmissionStatus::Unknown)
Index: clang/lib/Frontend/CompilerInvocation.cpp
===================================================================
--- clang/lib/Frontend/CompilerInvocation.cpp
+++ clang/lib/Frontend/CompilerInvocation.cpp
@@ -3489,6 +3489,9 @@
if (Opts.OpenMPCUDAForceFullRuntime)
GenerateArg(Args, OPT_fopenmp_cuda_force_full_runtime, SA);
+ if (Opts.OpenMPSkipDeferredDiags)
+ GenerateArg(Args, OPT_fopenmp_skip_deferred_diags, SA);
+
// The arguments used to set Optimize, OptimizeSize and NoInlineDefine are
// generated from CodeGenOptions.
@@ -3928,6 +3931,10 @@
Opts.OpenMPIsDevice && (T.isNVPTX() || T.isAMDGCN()) &&
Args.hasArg(options::OPT_fopenmp_cuda_force_full_runtime);
+ Opts.OpenMPSkipDeferredDiags =
+ Opts.OpenMP && !Opts.OpenMPSimd && !IsTargetSpecified &&
+ Args.hasArg(options::OPT_fopenmp_skip_deferred_diags);
+
// FIXME: Eliminate this dependency.
unsigned Opt = getOptimizationLevel(Args, IK, Diags),
OptSize = getOptimizationLevelSize(Args);
Index: clang/include/clang/Driver/Options.td
===================================================================
--- clang/include/clang/Driver/Options.td
+++ clang/include/clang/Driver/Options.td
@@ -5799,6 +5799,8 @@
HelpText<"Generate code only for an OpenMP target device.">;
def fopenmp_host_ir_file_path : Separate<["-"], "fopenmp-host-ir-file-path">,
HelpText<"Path to the IR file produced by the frontend for the host.">;
+def fopenmp_skip_deferred_diags : Flag<["-"], "fopenmp-skip-deferred-diags">,
+ HelpText<"Do not generate deferred diagnostics for function host/device availability. Use this flag only when no offloading or omp target directive is used.">;
//===----------------------------------------------------------------------===//
// SYCL Options
Index: clang/include/clang/Basic/LangOptions.def
===================================================================
--- clang/include/clang/Basic/LangOptions.def
+++ clang/include/clang/Basic/LangOptions.def
@@ -243,6 +243,7 @@
LANGOPT(OpenMPCUDAReductionBufNum , 32, 1024, "Number of the reduction records in the intermediate reduction buffer used for the teams reductions.")
LANGOPT(OpenMPTargetNewRuntime , 1, 0, "Use the new bitcode library for OpenMP offloading")
LANGOPT(OpenMPOptimisticCollapse , 1, 0, "Use at most 32 bits to represent the collapsed loop nest counter.")
+LANGOPT(OpenMPSkipDeferredDiags, 1, 0, "Do not generate deferred diagnostics for function host/device availability.")
LANGOPT(RenderScript , 1, 0, "RenderScript")
LANGOPT(CUDAIsDevice , 1, 0, "compiling for CUDA device")
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
