[llvm-(min-)tblgen] Avoid redundant source compilation (#114494)

All the sources of `llvm-min-tblgen` are also used for `llvm-tblgen`,
with identical compilation flags. Reuse the object files of
`llvm-min-tblgen` for `llvm-tblgen` by applying the usual source
structure of an executable: One file per executable which named after
the executable name containing the (in this case trivial) main function,
which just calls the tblgen_main in TableGen.cpp. This should also clear
up any confusion (including mine) of where each executable's main
function is.

While this slightly reduces build time, the main motivation is ccache.
Using the hard_link
option, building the object files for `llvm-tblgen` will result in a
hard link to the same object file already used for `llvm-min-tblgen`. To
signal the build system that the file is new, ccache will update the
file's time stamp. Unfortunately, time stamps are shared between all
hard-linked files s.t. this will indirectly also update the time stamps
for the object files used for `llvm-tblgen`. At the next run, Ninja will
recognize this time stamp discrepancy to the expected stamp recorded in
`.ninja_log` and rebuild those object files for `llvm-min-tblgen`, which
again will also update the stamp for the `llvm-tblgen`... . This is
especially annoying for tablegen because it means Ninja will re-run all
tablegenning in every build.

I am using the hard_link option because it reduces the cost of having
multiple build-trees of the LLVM sources and reduces the wear to the SSD
they are stored on.

llvm/utils/TableGen/Basic/CMakeLists.txt

@@ -9,8 +9,15 @@ set(LLVM_LINK_COMPONENTS
   )
 
 add_llvm_library(LLVMTableGenBasic OBJECT EXCLUDE_FROM_ALL DISABLE_LLVM_LINK_LLVM_DYLIB
+  ARMTargetDefEmitter.cpp
+  Attributes.cpp
   CodeGenIntrinsics.cpp
+  DirectiveEmitter.cpp
+  IntrinsicEmitter.cpp
+  RISCVTargetDefEmitter.cpp
   SDNodeProperties.cpp
+  TableGen.cpp
+  VTEmitter.cpp
 )
 
 # Users may include its headers as "Basic/*.h"

llvm/utils/TableGen/Basic/IntrinsicEmitter.cpp

@@ -10,8 +10,8 @@
 //
 //===----------------------------------------------------------------------===//
 
-#include "Basic/CodeGenIntrinsics.h"
+#include "CodeGenIntrinsics.h"
-#include "Basic/SequenceToOffsetTable.h"
+#include "SequenceToOffsetTable.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/StringRef.h"

llvm/utils/TableGen/Basic/TableGen.cpp

@@ -6,10 +6,12 @@
 //
 //===----------------------------------------------------------------------===//
 //
-// This file contains the main function for LLVM's TableGen.
+// This file contains the global defintions (mostly command line parameters)
+// shared between llvm-tblgen and llvm-min-tblgen.
 //
 //===----------------------------------------------------------------------===//
 
+#include "TableGen.h"
 #include "llvm/ADT/StringRef.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/InitLLVM.h"
@@ -74,7 +76,7 @@ static TableGen::Emitter::Opt X[] = {
     {"print-sets", printSets, "Print expanded sets for testing DAG exprs"},
 };
 
-int main(int argc, char **argv) {
+int tblgen_main(int argc, char **argv) {
   InitLLVM X(argc, argv);
   cl::ParseCommandLineOptions(argc, argv);
 

llvm/utils/TableGen/Basic/TableGen.h

@@ -0,0 +1,13 @@
+//===- TableGen.h ---------------------------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// Shared entry point for llvm-tblgen and llvm-min-tblgen.
+//
+//===----------------------------------------------------------------------===//
+
+int tblgen_main(int argc, char **argv);

llvm/utils/TableGen/CMakeLists.txt

@@ -11,14 +11,13 @@ set(LLVM_LINK_COMPONENTS Support)
 # build llvm/include. It must not depend on TableGenCommon, as
 # TableGenCommon depends on this already to generate things such as
 # ValueType definitions.
+# Sources included in both, llvm-min-tblgen and llvm-tblgen, must be included
+# into LLVMTableGenBasic to avoid redundant compilation and problems with build
+# caches.
+# At least one source file must be included directly to avoid CMake problems.
+# E.g. CMake derives which linker to use from the types of sources added.
 add_tablegen(llvm-min-tblgen LLVM_HEADERS
-  TableGen.cpp
+  llvm-min-tblgen.cpp
-  ARMTargetDefEmitter.cpp
-  Attributes.cpp
-  DirectiveEmitter.cpp
-  IntrinsicEmitter.cpp
-  RISCVTargetDefEmitter.cpp
-  VTEmitter.cpp
   $<TARGET_OBJECTS:obj.LLVMTableGenBasic>
 
   PARTIAL_SOURCES_INTENDED
@@ -32,10 +31,8 @@ set(LLVM_LINK_COMPONENTS
 add_tablegen(llvm-tblgen LLVM
   DESTINATION "${LLVM_TOOLS_INSTALL_DIR}"
   EXPORT LLVM
-  ARMTargetDefEmitter.cpp
   AsmMatcherEmitter.cpp
   AsmWriterEmitter.cpp
-  Attributes.cpp
   CallingConvEmitter.cpp
   CodeEmitterGen.cpp
   CodeGenMapTable.cpp
@@ -48,7 +45,6 @@ add_tablegen(llvm-tblgen LLVM
   DecoderEmitter.cpp
   DFAEmitter.cpp
   DFAPacketizerEmitter.cpp
-  DirectiveEmitter.cpp
   DisassemblerEmitter.cpp
   DXILEmitter.cpp
   ExegesisEmitter.cpp
@@ -57,18 +53,15 @@ add_tablegen(llvm-tblgen LLVM
   GlobalISelEmitter.cpp
   InstrDocsEmitter.cpp
   InstrInfoEmitter.cpp
-  IntrinsicEmitter.cpp
+  llvm-tblgen.cpp
   MacroFusionPredicatorEmitter.cpp
   OptionParserEmitter.cpp
   OptionRSTEmitter.cpp
   PseudoLoweringEmitter.cpp
   RegisterBankEmitter.cpp
   RegisterInfoEmitter.cpp
-  RISCVTargetDefEmitter.cpp
   SearchableTableEmitter.cpp
   SubtargetEmitter.cpp
-  TableGen.cpp
-  VTEmitter.cpp
   WebAssemblyDisassemblerEmitter.cpp
   X86InstrMappingEmitter.cpp
   X86DisassemblerTables.cpp
@@ -79,6 +72,8 @@ add_tablegen(llvm-tblgen LLVM
   $<TARGET_OBJECTS:obj.LLVMTableGenBasic>
   $<TARGET_OBJECTS:obj.LLVMTableGenCommon>
 
+  PARTIAL_SOURCES_INTENDED
+
   DEPENDS
   intrinsics_gen # via llvm-min-tablegen
   )

llvm/utils/TableGen/llvm-min-tblgen.cpp

@@ -0,0 +1,18 @@
+//===- llvm-min-tblgen.cpp ------------------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This file contains the main function for LLVM's TableGen.
+//
+//===----------------------------------------------------------------------===//
+
+#include "Basic/TableGen.h"
+
+/// Command line parameters are shared between llvm-tblgen and llvm-min-tblgen.
+/// The indirection to tblgen_main exists to ensure that the static variables
+/// for the llvm::cl:: mechanism are linked into both executables.
+int main(int argc, char **argv) { return tblgen_main(argc, argv); }

llvm/utils/TableGen/llvm-tblgen.cpp

@@ -0,0 +1,18 @@
+//===- llvm-tblgen.cpp ----------------------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This file contains the main function for LLVM's TableGen.
+//
+//===----------------------------------------------------------------------===//
+
+#include "Basic/TableGen.h"
+
+/// Command line parameters are shared between llvm-tblgen and llvm-min-tblgen.
+/// The indirection to tblgen_main exists to ensure that the static variables
+/// for the llvm::cl:: mechanism are linked into both executables.
+int main(int argc, char **argv) { return tblgen_main(argc, argv); }