llvm-project/clang/lib/CodeGen
Douglas Gregor d94105a1c2 Don't generate any code for an explicit call to a trivial destructor.
Now that parsing, semantic analysis, and (I think) code generation of
pseudo-destructor expressions and explicit destructor calls works,
update the example-dynarray.cpp test to destroy the objects it
allocates and update the test to actually compile + link.
The code seems correct, but the Clang-compiled version dies with a
malloc error. Time to debug!

llvm-svn: 81025
2009-09-04 19:04:08 +00:00
..
ABIInfo.h LLVMContext is a class now. 2009-08-11 17:46:57 +00:00
CGBlocks.cpp Fix build of clang with gcc-4.4: #include <cstdio> was missing. 2009-08-24 13:25:12 +00:00
CGBlocks.h Update for LLVM API change. 2009-08-13 21:57:51 +00:00
CGBuilder.h Disable generation of basic block names in NDEBUG mode. 2008-11-12 00:01:12 +00:00
CGBuiltin.cpp PR4836, part 2: CodeGen for __builtin_isnan. 2009-09-01 04:19:44 +00:00
CGCXX.cpp Don't generate any code for an explicit call to a trivial destructor. 2009-09-04 19:04:08 +00:00
CGCXX.h Add CGCXX.h with ctor/dtor type enumerations. No functionality change. 2009-04-15 04:36:55 +00:00
CGCXXTemp.cpp Add an IsInitializer flag to EmitAnyExpr. This is used to prevent temporaries from being destroyed when they're bound to a reference variable. 2009-08-16 07:36:22 +00:00
CGCall.cpp Update for LLVM API change. 2009-08-13 21:57:51 +00:00
CGCall.h Unbreak CGFunctionInfo::Profile method and reenable caching of ABI 2009-02-05 00:00:23 +00:00
CGDebugInfo.cpp Rename DIBlock as DILexicalBlock. 2009-08-31 22:00:32 +00:00
CGDebugInfo.h Revert 75648 for now. It is causing test failures. 2009-07-14 21:31:22 +00:00
CGDecl.cpp Remove an ErrorUnsupported call. 2009-08-17 18:24:57 +00:00
CGExpr.cpp Implement AST, semantics, and CodeGen for C++ pseudo-destructor 2009-09-04 17:36:40 +00:00
CGExprAgg.cpp Re-implemented generation of objc_memmove_collectable 2009-08-31 19:33:16 +00:00
CGExprComplex.cpp Using "ObjCImplicitSetterGetterRefExpr" instead of "ObjCImplctSetterGetterRefExpr". 2009-08-20 17:02:02 +00:00
CGExprConstant.cpp Make address-space qualification work correctly for compound literals. 2009-08-26 20:01:39 +00:00
CGExprScalar.cpp Implement AST, semantics, and CodeGen for C++ pseudo-destructor 2009-09-04 17:36:40 +00:00
CGObjC.cpp Fixed a property getter ir-gen crash. 2009-09-01 17:02:21 +00:00
CGObjCGNU.cpp Re-implemented generation of objc_memmove_collectable 2009-08-31 19:33:16 +00:00
CGObjCMac.cpp Re-implemented generation of objc_memmove_collectable 2009-08-31 19:33:16 +00:00
CGObjCRuntime.h Re-implemented generation of objc_memmove_collectable 2009-08-31 19:33:16 +00:00
CGRecordLayoutBuilder.cpp If the alignment of the chosen field in a union is greater than the alignment of the union, we need to use a packed LLVM struct. Fixes <rdar://problem/7184250>. 2009-09-03 22:56:02 +00:00
CGRecordLayoutBuilder.h More work towards zero-initializing structs that contain member pointers in constant expressions. 2009-08-23 01:25:01 +00:00
CGStmt.cpp Update for LLVM API change. 2009-08-13 21:57:51 +00:00
CGValue.h Using "ObjCImplicitSetterGetterRefExpr" instead of "ObjCImplctSetterGetterRefExpr". 2009-08-20 17:02:02 +00:00
CMakeLists.txt Unbreak the CMake build 2009-07-23 15:15:06 +00:00
CodeGenFunction.cpp Patch to ir-gen user-defined conversions used in expressions 2009-08-29 20:33:32 +00:00
CodeGenFunction.h Add overidding for methods for vtable building for the secondary 2009-09-04 18:27:16 +00:00
CodeGenModule.cpp Don't generate any code for an explicit call to a trivial destructor. 2009-09-04 19:04:08 +00:00
CodeGenModule.h Add overidding for methods for vtable building for the secondary 2009-09-04 18:27:16 +00:00
CodeGenTypes.cpp More member pointer work. 2009-08-24 17:16:23 +00:00
CodeGenTypes.h More member pointer work. 2009-08-24 17:16:23 +00:00
Makefile Don't install Clang libraries. 2009-08-23 05:02:18 +00:00
Mangle.cpp Add mangling for covariant thunks. 2009-09-02 00:56:18 +00:00
Mangle.h Add mangling for covariant thunks. 2009-09-02 00:56:18 +00:00
ModuleBuilder.cpp Switch TargetInfo to store an llvm::Triple. 2009-08-24 09:10:05 +00:00
README.txt These IRgen improvements have been done. 2009-07-23 03:03:07 +00:00
TargetABIInfo.cpp Fixed bug introduced in r79900 where FreeBSD was turned into NetBSD, transposing the ABIs and breaking both platforms. 2009-09-03 01:48:05 +00:00

README.txt

IRgen optimization opportunities.

//===---------------------------------------------------------------------===//

The common pattern of
--
short x; // or char, etc
(x == 10)
--
generates an zext/sext of x which can easily be avoided.

//===---------------------------------------------------------------------===//

Bitfields accesses can be shifted to simplify masking and sign
extension. For example, if the bitfield width is 8 and it is
appropriately aligned then is is a lot shorter to just load the char
directly.

//===---------------------------------------------------------------------===//

It may be worth avoiding creation of alloca's for formal arguments
for the common situation where the argument is never written to or has
its address taken. The idea would be to begin generating code by using
the argument directly and if its address is taken or it is stored to
then generate the alloca and patch up the existing code.

In theory, the same optimization could be a win for block local
variables as long as the declaration dominates all statements in the
block.

NOTE: The main case we care about this for is for -O0 -g compile time
performance, and in that scenario we will need to emit the alloca
anyway currently to emit proper debug info. So this is blocked by
being able to emit debug information which refers to an LLVM
temporary, not an alloca.

//===---------------------------------------------------------------------===//

We should try and avoid generating basic blocks which only contain
jumps. At -O0, this penalizes us all the way from IRgen (malloc &
instruction overhead), all the way down through code generation and
assembly time.

On 176.gcc:expr.ll, it looks like over 12% of basic blocks are just
direct branches!

//===---------------------------------------------------------------------===//