maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
85,913 Commits 23 Branches 0 Tags 2.2 GiB
Commit Graph

14321 Commits

Author SHA1 Message Date
Chris Lattner 055097f024 If coercing something from int or pointer type to int or pointer type 
(potentially after unwrapping it from a struct) do it without going through
memory.  We now compile:

struct DeclGroup {
  unsigned NumDecls;
};

int foo(DeclGroup D) {
  return D.NumDecls;
}

into:

%struct.DeclGroup = type { i32 }

define i32 @_Z3foo9DeclGroup(i64) nounwind ssp noredzone {
entry:
  %D = alloca %struct.DeclGroup, align 4          ; <%struct.DeclGroup*> [#uses=2]
  %coerce.dive = getelementptr %struct.DeclGroup* %D, i32 0, i32 0 ; <i32*> [#uses=1]
  %coerce.val.ii = trunc i64 %0 to i32            ; <i32> [#uses=1]
  store i32 %coerce.val.ii, i32* %coerce.dive
  %tmp = getelementptr inbounds %struct.DeclGroup* %D, i32 0, i32 0 ; <i32*> [#uses=1]
  %tmp1 = load i32* %tmp                          ; <i32> [#uses=1]
  ret i32 %tmp1
}

instead of:

%struct.DeclGroup = type { i32 }

define i32 @_Z3foo9DeclGroup(i64) nounwind ssp noredzone {
entry:
  %D = alloca %struct.DeclGroup, align 4          ; <%struct.DeclGroup*> [#uses=2]
  %tmp = alloca i64                               ; <i64*> [#uses=2]
  %coerce.dive = getelementptr %struct.DeclGroup* %D, i32 0, i32 0 ; <i32*> [#uses=1]
  store i64 %0, i64* %tmp
  %1 = bitcast i64* %tmp to i32*                  ; <i32*> [#uses=1]
  %2 = load i32* %1, align 1                      ; <i32> [#uses=1]
  store i32 %2, i32* %coerce.dive
  %tmp1 = getelementptr inbounds %struct.DeclGroup* %D, i32 0, i32 0 ; <i32*> [#uses=1]
  %tmp2 = load i32* %tmp1                         ; <i32> [#uses=1]
  ret i32 %tmp2
}

... which is quite a bit less terrifying.

llvm-svn: 106975
 2010-06-27 06:26:04 +00:00
Chris Lattner 895c52ba8b Same patch as the previous on the store side. Before we compiled this: 
struct DeclGroup {
  unsigned NumDecls;
};

int foo(DeclGroup D) {
  return D.NumDecls;
}

to:

%struct.DeclGroup = type { i32 }

define i32 @_Z3foo9DeclGroup(i64) nounwind ssp noredzone {
entry:
  %D = alloca %struct.DeclGroup, align 4          ; <%struct.DeclGroup*> [#uses=2]
  %tmp = alloca i64                               ; <i64*> [#uses=2]
  store i64 %0, i64* %tmp
  %1 = bitcast i64* %tmp to %struct.DeclGroup*    ; <%struct.DeclGroup*> [#uses=1]
  %2 = load %struct.DeclGroup* %1, align 1        ; <%struct.DeclGroup> [#uses=1]
  store %struct.DeclGroup %2, %struct.DeclGroup* %D
  %tmp1 = getelementptr inbounds %struct.DeclGroup* %D, i32 0, i32 0 ; <i32*> [#uses=1]
  %tmp2 = load i32* %tmp1                         ; <i32> [#uses=1]
  ret i32 %tmp2
}

which caused fast isel bailouts due to the FCA load/store of %2.  Now
we generate this just blissful code:

%struct.DeclGroup = type { i32 }

define i32 @_Z3foo9DeclGroup(i64) nounwind ssp noredzone {
entry:
  %D = alloca %struct.DeclGroup, align 4          ; <%struct.DeclGroup*> [#uses=2]
  %tmp = alloca i64                               ; <i64*> [#uses=2]
  %coerce.dive = getelementptr %struct.DeclGroup* %D, i32 0, i32 0 ; <i32*> [#uses=1]
  store i64 %0, i64* %tmp
  %1 = bitcast i64* %tmp to i32*                  ; <i32*> [#uses=1]
  %2 = load i32* %1, align 1                      ; <i32> [#uses=1]
  store i32 %2, i32* %coerce.dive
  %tmp1 = getelementptr inbounds %struct.DeclGroup* %D, i32 0, i32 0 ; <i32*> [#uses=1]
  %tmp2 = load i32* %tmp1                         ; <i32> [#uses=1]
  ret i32 %tmp2
}

This avoids fastisel bailing out and is groundwork for future patch.
This reduces bailouts on CGStmt.ll to 911 from 935.

llvm-svn: 106974
 2010-06-27 06:04:18 +00:00
Chris Lattner 1cd6698a7c improve CreateCoercedLoad a bit to generate slightly less awful 
IR when handling X86-64 by-value struct stuff.  For example, we
use to compile this:

struct DeclGroup {
  unsigned NumDecls;
};

int foo(DeclGroup D);
void bar(DeclGroup *D) {
  foo(*D);
}

into:

define void @_Z3barP9DeclGroup(%struct.DeclGroup* %D) ssp nounwind {
entry:
  %D.addr = alloca %struct.DeclGroup*, align 8    ; <%struct.DeclGroup**> [#uses=2]
  %agg.tmp = alloca %struct.DeclGroup, align 4    ; <%struct.DeclGroup*> [#uses=2]
  %tmp3 = alloca i64                              ; <i64*> [#uses=2]
  store %struct.DeclGroup* %D, %struct.DeclGroup** %D.addr
  %tmp = load %struct.DeclGroup** %D.addr         ; <%struct.DeclGroup*> [#uses=1]
  %tmp1 = bitcast %struct.DeclGroup* %agg.tmp to i8* ; <i8*> [#uses=1]
  %tmp2 = bitcast %struct.DeclGroup* %tmp to i8*  ; <i8*> [#uses=1]
  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %tmp1, i8* %tmp2, i64 4, i32 4, i1 false)
  %0 = bitcast i64* %tmp3 to %struct.DeclGroup*   ; <%struct.DeclGroup*> [#uses=1]
  %1 = load %struct.DeclGroup* %agg.tmp           ; <%struct.DeclGroup> [#uses=1]
  store %struct.DeclGroup %1, %struct.DeclGroup* %0, align 1
  %2 = load i64* %tmp3                            ; <i64> [#uses=1]
  call void @_Z3foo9DeclGroup(i64 %2)
  ret void
}

which would cause fastisel to bail out due to the first class aggregate load %1.  With
this patch we now compile it into the (still awful):

define void @_Z3barP9DeclGroup(%struct.DeclGroup* %D) nounwind ssp noredzone {
entry:
  %D.addr = alloca %struct.DeclGroup*, align 8    ; <%struct.DeclGroup**> [#uses=2]
  %agg.tmp = alloca %struct.DeclGroup, align 4    ; <%struct.DeclGroup*> [#uses=2]
  %tmp3 = alloca i64                              ; <i64*> [#uses=2]
  store %struct.DeclGroup* %D, %struct.DeclGroup** %D.addr
  %tmp = load %struct.DeclGroup** %D.addr         ; <%struct.DeclGroup*> [#uses=1]
  %tmp1 = bitcast %struct.DeclGroup* %agg.tmp to i8* ; <i8*> [#uses=1]
  %tmp2 = bitcast %struct.DeclGroup* %tmp to i8*  ; <i8*> [#uses=1]
  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %tmp1, i8* %tmp2, i64 4, i32 4, i1 false)
  %coerce.dive = getelementptr %struct.DeclGroup* %agg.tmp, i32 0, i32 0 ; <i32*> [#uses=1]
  %0 = bitcast i64* %tmp3 to i32*                 ; <i32*> [#uses=1]
  %1 = load i32* %coerce.dive                     ; <i32> [#uses=1]
  store i32 %1, i32* %0, align 1
  %2 = load i64* %tmp3                            ; <i64> [#uses=1]
  %call = call i32 @_Z3foo9DeclGroup(i64 %2) noredzone ; <i32> [#uses=0]
  ret void
}

which doesn't bail out.  On CGStmt.ll, this reduces fastisel bail outs from 958 to 935,
and is the precursor of better things to come.

llvm-svn: 106973
 2010-06-27 05:56:15 +00:00
Jordy Rose 7f8ea4d677 Implicitly compare symbolic expressions to zero when they're being used as constraints. Part of PR7491. 
llvm-svn: 106972
 2010-06-27 01:20:56 +00:00
Chris Lattner 3fcc790cd8 Change IR generation for return (in the simple case) to avoid doing silly 
load/store nonsense in the epilog.  For example, for:

int foo(int X) {
  int A[100];
  return A[X];
}

we used to generate:

  %arrayidx = getelementptr inbounds [100 x i32]* %A, i32 0, i64 %idxprom ; <i32*> [#uses=1]
  %tmp1 = load i32* %arrayidx                     ; <i32> [#uses=1]
  store i32 %tmp1, i32* %retval
  %0 = load i32* %retval                          ; <i32> [#uses=1]
  ret i32 %0
}

which codegen'd to this code:

_foo:                                   ## @foo
## BB#0:                                ## %entry
	subq	$408, %rsp              ## imm = 0x198
	movl	%edi, 400(%rsp)
	movl	400(%rsp), %edi
	movslq	%edi, %rax
	movl	(%rsp,%rax,4), %edi
	movl	%edi, 404(%rsp)
	movl	404(%rsp), %eax
	addq	$408, %rsp              ## imm = 0x198
	ret

Now we generate:

  %arrayidx = getelementptr inbounds [100 x i32]* %A, i32 0, i64 %idxprom ; <i32*> [#uses=1]
  %tmp1 = load i32* %arrayidx                     ; <i32> [#uses=1]
  ret i32 %tmp1
}

and:

_foo:                                   ## @foo
## BB#0:                                ## %entry
	subq	$408, %rsp              ## imm = 0x198
	movl	%edi, 404(%rsp)
	movl	404(%rsp), %edi
	movslq	%edi, %rax
	movl	(%rsp,%rax,4), %eax
	addq	$408, %rsp              ## imm = 0x198
	ret

This actually does matter, cutting out 2000 lines of IR from CGStmt.ll 
for example.

Another interesting effect is that altivec.h functions which are dead
now get dce'd by the inliner.  Hence all the changes to 
builtins-ppc-altivec.c to ensure the calls aren't dead.

llvm-svn: 106970
 2010-06-27 01:06:27 +00:00
Chris Lattner 726b3d09cd reduce indentation 
llvm-svn: 106967
 2010-06-26 23:13:19 +00:00
Chris Lattner 6c5abe88bf Implement rdar://7530813 - collapse multiple GEP instructions in IRgen 
This avoids generating two gep's for common array operations.  Before
we would generate something like:

  %tmp = load i32* %X.addr                        ; <i32> [#uses=1]
  %arraydecay = getelementptr inbounds [100 x i32]* %A, i32 0, i32 0 ; <i32*> [#uses=1]
  %arrayidx = getelementptr inbounds i32* %arraydecay, i32 %tmp ; <i32*> [#uses=1]
  %tmp1 = load i32* %arrayidx                     ; <i32> [#uses=1]

Now we generate:

  %tmp = load i32* %X.addr                        ; <i32> [#uses=1]
  %arrayidx = getelementptr inbounds [100 x i32]* %A, i32 0, i32 %tmp ; <i32*> [#uses=1]
  %tmp1 = load i32* %arrayidx                     ; <i32> [#uses=1]

Less IR is better at -O0.

llvm-svn: 106966
 2010-06-26 23:03:20 +00:00
Ted Kremenek f00eac5cff Allow '__extension__' to be analyzed in a lvalue context. 
llvm-svn: 106964
 2010-06-26 22:40:52 +00:00
Chris Lattner 57ce97151f minor cleanup: don't emit the base of an array subscript until after 
we're done diddling around with the index stuff.  Use a cheaper type
comparison.

llvm-svn: 106963
 2010-06-26 22:40:46 +00:00
Chris Lattner 431bef4409 fix inc/dec to honor -fwrapv and -ftrapv, implementing PR7426. 
llvm-svn: 106962
 2010-06-26 22:18:28 +00:00
Chris Lattner 05dc78c096 move scalar inc/dec codegen into ScalarExprEmitter instead 
of being in CGF.  No functionality change.

llvm-svn: 106961
 2010-06-26 22:09:34 +00:00
Chris Lattner fa20e95043 use more efficient type comparison predicates. 
llvm-svn: 106958
 2010-06-26 21:52:32 +00:00
Chris Lattner 0bf27620f0 Fix unary minus to trap on overflow with -ftrapv, refactoring binop 
code so we can use it from VisitUnaryMinus.

llvm-svn: 106957
 2010-06-26 21:48:21 +00:00
Chris Lattner 51924e517b Implement support for -fwrapv, rdar://7221421 
As part of this, pull together trapv handling into the same enum.

This also add support for NSW multiplies.

This also makes PCH disagreement on overflow behavior silent, since it
really doesn't matter except for warnings and codegen (no macros get 
defined etc).

llvm-svn: 106956
 2010-06-26 21:25:03 +00:00
Chris Lattner 217e056e40 implement rdar://7432000 - signed negate should codegen as NSW. 
While I'm in there, adjust pointer to member adjustments as well.

llvm-svn: 106955
 2010-06-26 20:27:24 +00:00
Chris Lattner 30c924b3e8 Implement support for #pragma message, patch by Michael Spencer! 
llvm-svn: 106950
 2010-06-26 17:11:39 +00:00
Anders Carlsson 04775f8413 Change EmitReferenceBindingToExpr to take a decl instead of a boolean. 
llvm-svn: 106949
 2010-06-26 16:35:32 +00:00
Anders Carlsson 709ef8e46c Add function for mangling reference temporaries. 
llvm-svn: 106948
 2010-06-26 16:09:40 +00:00
Charles Davis f4db33cbdf Mangle pointer and (lvalue) reference types in the Microsoft C++ Mangler. 
Also, fix mangling of throw specs. Turns out MSVC totally ignores throw
specs when mangling names.

llvm-svn: 106937
 2010-06-26 03:50:05 +00:00
Bob Wilson f11a38dcce Add a missing dependency to try to fix a buildbot failure. 
It complained with:

llvm[5]: Building Clang arm_neon.h.inc with tblgen
cp: cannot create regular file `/build/buildbot-llvm/clang-x86_64-linux-selfhost-rel/llvm.obj.2/Release/lib/clang/2.0/include/arm_neon.h': No such file or directory

llvm-svn: 106922
 2010-06-26 00:03:23 +00:00
Ted Kremenek 58f61ec1de Relax assertion since non-pod C++ classes are not aggregates, but still can appear in this context. 
llvm-svn: 106919
 2010-06-25 23:51:38 +00:00
Jordy Rose c3bcc36a0b When a constant size array is casted to another type, its length should be scaled as well. 
llvm-svn: 106911
 2010-06-25 23:23:04 +00:00
Ted Kremenek abb1f91325 Use TypeSourceInfo to help determine the SourceRange of a CXXNewExpr. This fixes several 
cases where we generated an invalid SourceRange for this expression.  Thanks to John McCall
for helping me figure this out.

llvm-svn: 106903
 2010-06-25 22:48:49 +00:00
Ted Kremenek fe97a1ac65 Add "checker caching" to GRExprEngine::CheckerVisit to progressively build 
a winowed list of checkers that actually do something for a given StmtClass.
As the number of checkers grows, this may potentially significantly reduce
the number of checkers called at any one time.  My own measurements show that
for the ~20 registered Checker objects, only ~5 of them respond at any one time
to a give statement.  While this isn't a net performance win right now (there
is a minor slowdown on sqlite.3) this improvement does greatly improve debugging
when stepping through the checkers used to evaluate a given statement.

llvm-svn: 106884
 2010-06-25 20:59:31 +00:00
Ted Kremenek 76abf19ea6 Fix -analyze-display-progress (once again), this time with an additional regression test. 
llvm-svn: 106883
 2010-06-25 20:59:24 +00:00
Fariborz Jahanian b66b08ef01 Minor change to my last patch to fix PR7490. 
llvm-svn: 106875
 2010-06-25 20:01:13 +00:00
Eric Christopher 17c7b89054 Translate numbers properly. 
llvm-svn: 106873
 2010-06-25 19:04:52 +00:00
Fariborz Jahanian d5202e0926 IRGen for trivial initialization of dynamiccaly allocated 
array of other done c++ objects. Fixes PR7490.

llvm-svn: 106869
 2010-06-25 18:26:07 +00:00
Tom Care 375387d1f8 Change RegionStoreManager::Retrieve to infer the type of a symbolic region from the context when it is not already available. 
llvm-svn: 106868
 2010-06-25 18:22:31 +00:00
Daniel Dunbar 283fe3d07a build: Get CLANG_VERSION from Version.inc instead of depending on VER file directly. 
llvm-svn: 106864
 2010-06-25 17:33:49 +00:00
Argyrios Kyrtzidis b1d38e3f4a Support NonTypeTemplateParmDecl for PCH. 
llvm-svn: 106860
 2010-06-25 16:25:09 +00:00
Argyrios Kyrtzidis 03e5e0467c Make PCHWriter::FlushStmts() robust. If we added null Stmts, reading them back got messed up. 
llvm-svn: 106859
 2010-06-25 16:25:02 +00:00
Argyrios Kyrtzidis f0f7a792d7 Support DependentTemplateSpecializationType and ElaboratedType for PCH. 
llvm-svn: 106858
 2010-06-25 16:24:58 +00:00
Argyrios Kyrtzidis dc9ca0afa8 Add forgotten breaks in case statements. 
llvm-svn: 106857
 2010-06-25 16:24:51 +00:00
Argyrios Kyrtzidis 58e01ad26f Support UnresolvedLookupExpr for PCH. 
llvm-svn: 106832
 2010-06-25 09:03:34 +00:00
Argyrios Kyrtzidis b8d3c63820 Support UnresolvedMemberExpr for PCH. 
llvm-svn: 106831
 2010-06-25 09:03:26 +00:00
Argyrios Kyrtzidis 6ba1bb5dec Print source location when we encounter unhandled statement during PCH writing. 
llvm-svn: 106830
 2010-06-25 09:03:12 +00:00
Chandler Carruth f40c42f2cd Implement dependent alignment attribute support. This is a bit gross given the 
current attribute system, but it is enough to handle class templates which
specify parts of their alignment in terms of their template parameters.

This also replaces the attributes test in SemaTemplate with one that actually
tests working attributes instead of broken ones. I plan to add more tests here
for non-dependent attributes in a subsequent patch.

Thanks to John for walking me through some of this. =D

llvm-svn: 106818
 2010-06-25 03:22:07 +00:00
Fariborz Jahanian ad356a14f9 Add comment for my last patch. 
llvm-svn: 106813
 2010-06-25 00:05:45 +00:00
John Thompson ceebdf1fc6 Fixed another double-char in PPC-specific asm constraints. 
llvm-svn: 106812
 2010-06-25 00:02:05 +00:00
John Thompson 07a61a41c8 Added PPC-specific asm constraints, PS3 configuration changes. 
llvm-svn: 106806
 2010-06-24 22:44:13 +00:00
Eric Christopher ca10da8839 Remove HAS_TLS define. 
llvm-svn: 106786
 2010-06-24 20:41:41 +00:00
Fariborz Jahanian 4f9c9d6591 Fixes a regression when redeclaration of a global satic 
is an extern local to a function. Radar 8125274.

llvm-svn: 106773
 2010-06-24 18:50:41 +00:00
Ted Kremenek 87f475a329 Return null pointer instead of 'false' (fixes clang warning). 
llvm-svn: 106755
 2010-06-24 16:26:12 +00:00
Zhongxing Xu facf8a8e74 Add check for illegal whence argument of fseek. 
llvm-svn: 106742
 2010-06-24 13:36:41 +00:00
Zhongxing Xu a7e5dd6c3a Should return stateNotNull. 
llvm-svn: 106741
 2010-06-24 13:09:02 +00:00
Zhongxing Xu ae45144d81 Let StreamChecker::CheckNullStream() return a GRState after successful check. 
llvm-svn: 106738
 2010-06-24 12:52:28 +00:00
Argyrios Kyrtzidis bfcacee9b3 Support a couple more C++ Exprs for PCH. 
llvm-svn: 106727
 2010-06-24 08:57:31 +00:00
Argyrios Kyrtzidis 30d98f3d9e Fix broken de/serialization for a couple of C++ Exprs. 
llvm-svn: 106726
 2010-06-24 08:57:09 +00:00
Eric Christopher 03256c32ff More clang support for darwin tls. Add a __has_feature macro and 
target specific preprocessor define as well.

llvm-svn: 106715
 2010-06-24 02:02:00 +00:00