| Commit message (Collapse) | Author | Age | Files | Lines |
| |
|
|
|
|
|
|
|
|
| |
int test1() {
return;
}
default to an error.
llvm-svn: 108108
|
| |
|
|
| |
llvm-svn: 107845
|
| |
|
|
|
|
|
|
|
|
|
| |
was not producing a memcpy with the right address
spaces because of two places in it doing casts of
the arguments to i8, one of which that didn't
preserve the address space.
There is also an optimizer bug here.
llvm-svn: 107842
|
| |
|
|
| |
llvm-svn: 107841
|
| |
|
|
|
|
| |
Fixes rdar://problem/8154689
llvm-svn: 107755
|
| |
|
|
|
|
|
|
|
| |
alloca for an argument. Make sure the argument gets the proper
decl alignment, which may be different than the type alignment.
This fixes PR7567
llvm-svn: 107627
|
| |
|
|
|
|
| |
wasn't handling array padding elements right.
llvm-svn: 107621
|
| |
|
|
| |
llvm-svn: 107387
|
| |
|
|
| |
llvm-svn: 107367
|
| |
|
|
|
|
|
|
|
|
| |
r107173, "fix PR7519: after thrashing around and remembering how all this stuff"
r107216, "fix PR7523, which was caused by the ABI code calling ConvertType instead"
This includes a fix to make ConvertTypeForMem handle the "recursive" case, and call
it as such when lowering function types which have an indirect result.
llvm-svn: 107310
|
| |
|
|
|
|
| |
this stuff", it broke bootstrap.
llvm-svn: 107232
|
| |
|
|
|
|
|
|
| |
would trigger an extra method call).
- While in the area, I also changed Clang to not emit an unnecessary load from
'x' in cases like 'y = (x = 1)'.
llvm-svn: 107210
|
| |
|
|
| |
llvm-svn: 107186
|
| |
|
|
|
|
|
| |
works, the fix is quite simple: just make sure to call ConvertTypeRecursive
when the function type being lowered is in the midst of ConvertType.
llvm-svn: 107173
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
avoid passing ASTContext down through all the methods it has.
When classifying an argument, or argument piece, as INTEGER, check
to see if we have a pointer at exactly the same offset in the
preferred type. If so, use that pointer type instead of i64. This
allows us to compile A function taking a stringref into something
like this:
define i8* @foo(i64 %D.coerce0, i8* %D.coerce1) nounwind ssp {
entry:
%D = alloca %struct.DeclGroup, align 8 ; <%struct.DeclGroup*> [#uses=4]
%0 = getelementptr %struct.DeclGroup* %D, i32 0, i32 0 ; <i64*> [#uses=1]
store i64 %D.coerce0, i64* %0
%1 = getelementptr %struct.DeclGroup* %D, i32 0, i32 1 ; <i8**> [#uses=1]
store i8* %D.coerce1, i8** %1
%tmp = getelementptr inbounds %struct.DeclGroup* %D, i32 0, i32 0 ; <i64*> [#uses=1]
%tmp1 = load i64* %tmp ; <i64> [#uses=1]
%tmp2 = getelementptr inbounds %struct.DeclGroup* %D, i32 0, i32 1 ; <i8**> [#uses=1]
%tmp3 = load i8** %tmp2 ; <i8*> [#uses=1]
%add.ptr = getelementptr inbounds i8* %tmp3, i64 %tmp1 ; <i8*> [#uses=1]
ret i8* %add.ptr
}
instead of this:
define i8* @foo(i64 %D.coerce0, i64 %D.coerce1) nounwind ssp {
entry:
%D = alloca %struct.DeclGroup, align 8 ; <%struct.DeclGroup*> [#uses=3]
%0 = insertvalue %0 undef, i64 %D.coerce0, 0 ; <%0> [#uses=1]
%1 = insertvalue %0 %0, i64 %D.coerce1, 1 ; <%0> [#uses=1]
%2 = bitcast %struct.DeclGroup* %D to %0* ; <%0*> [#uses=1]
store %0 %1, %0* %2, align 1
%tmp = getelementptr inbounds %struct.DeclGroup* %D, i32 0, i32 0 ; <i64*> [#uses=1]
%tmp1 = load i64* %tmp ; <i64> [#uses=1]
%tmp2 = getelementptr inbounds %struct.DeclGroup* %D, i32 0, i32 1 ; <i8**> [#uses=1]
%tmp3 = load i8** %tmp2 ; <i8*> [#uses=1]
%add.ptr = getelementptr inbounds i8* %tmp3, i64 %tmp1 ; <i8*> [#uses=1]
ret i8* %add.ptr
}
This implements rdar://7375902 - [codegen quality] clang x86-64 ABI lowering code punishing StringRef
llvm-svn: 107123
|
| |
|
|
| |
llvm-svn: 107105
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
is a FCA to pass each of the elements as individual scalars. This
produces code fast isel is less likely to reject and is easier on
the optimizers.
For example, before we would compile:
struct DeclGroup { long NumDecls; char * Y; };
char * foo(DeclGroup D) {
return D.NumDecls+D.Y;
}
to:
%struct.DeclGroup = type { i64, i64 }
define i64 @_Z3foo9DeclGroup(%struct.DeclGroup) nounwind {
entry:
%D = alloca %struct.DeclGroup, align 8 ; <%struct.DeclGroup*> [#uses=3]
store %struct.DeclGroup %0, %struct.DeclGroup* %D, align 1
%tmp = getelementptr inbounds %struct.DeclGroup* %D, i32 0, i32 0 ; <i64*> [#uses=1]
%tmp1 = load i64* %tmp ; <i64> [#uses=1]
%tmp2 = getelementptr inbounds %struct.DeclGroup* %D, i32 0, i32 1 ; <i64*> [#uses=1]
%tmp3 = load i64* %tmp2 ; <i64> [#uses=1]
%add = add nsw i64 %tmp1, %tmp3 ; <i64> [#uses=1]
ret i64 %add
}
Now we get:
%0 = type { i64, i64 }
%struct.DeclGroup = type { i64, i8* }
define i8* @_Z3foo9DeclGroup(i64, i64) nounwind {
entry:
%D = alloca %struct.DeclGroup, align 8 ; <%struct.DeclGroup*> [#uses=3]
%2 = insertvalue %0 undef, i64 %0, 0 ; <%0> [#uses=1]
%3 = insertvalue %0 %2, i64 %1, 1 ; <%0> [#uses=1]
%4 = bitcast %struct.DeclGroup* %D to %0* ; <%0*> [#uses=1]
store %0 %3, %0* %4, align 1
%tmp = getelementptr inbounds %struct.DeclGroup* %D, i32 0, i32 0 ; <i64*> [#uses=1]
%tmp1 = load i64* %tmp ; <i64> [#uses=1]
%tmp2 = getelementptr inbounds %struct.DeclGroup* %D, i32 0, i32 1 ; <i8**> [#uses=1]
%tmp3 = load i8** %tmp2 ; <i8*> [#uses=1]
%add.ptr = getelementptr inbounds i8* %tmp3, i64 %tmp1 ; <i8*> [#uses=1]
ret i8* %add.ptr
}
Elimination of the FCA inside the function is still-to-come.
llvm-svn: 107099
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
pass/return structs of float/int as float/i32 instead of double/i64
to make the code generated for ABI cleaner. Passing in the low part
of a double is the same as passing in a float.
For example, we now compile:
struct DeclGroup { float NumDecls; };
float foo(DeclGroup D);
void bar(DeclGroup *D) {
foo(*D);
}
into:
%struct.DeclGroup = type { float }
define void @_Z3barP9DeclGroup(%struct.DeclGroup* %D) nounwind {
entry:
%D.addr = alloca %struct.DeclGroup*, align 8 ; <%struct.DeclGroup**> [#uses=2]
%agg.tmp = alloca %struct.DeclGroup, align 4 ; <%struct.DeclGroup*> [#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 ; <float*> [#uses=1]
%0 = load float* %coerce.dive, align 1 ; <float> [#uses=1]
%call = call float @_Z3foo9DeclGroup(float %0) ; <float> [#uses=0]
ret void
}
instead of:
%struct.DeclGroup = type { float }
define void @_Z3barP9DeclGroup(%struct.DeclGroup* %D) 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 double ; <double*> [#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 ; <float*> [#uses=1]
%0 = bitcast double* %tmp3 to float* ; <float*> [#uses=1]
%1 = load float* %coerce.dive ; <float> [#uses=1]
store float %1, float* %0, align 1
%2 = load double* %tmp3 ; <double> [#uses=1]
%call = call float @_Z3foo9DeclGroup(double %2) ; <float> [#uses=0]
ret void
}
which is this machine code (at -O0):
__Z3barP9DeclGroup:
subq $24, %rsp
movq %rdi, 16(%rsp)
movq 16(%rsp), %rdi
leaq 8(%rsp), %rax
movl (%rdi), %ecx
movl %ecx, (%rax)
movss 8(%rsp), %xmm0
callq __Z3foo9DeclGroup
addq $24, %rsp
ret
vs this:
__Z3barP9DeclGroup:
subq $24, %rsp
movq %rdi, 16(%rsp)
movq 16(%rsp), %rdi
leaq 8(%rsp), %rax
movl (%rdi), %ecx
movl %ecx, (%rax)
movss 8(%rsp), %xmm0
movss %xmm0, (%rsp)
movsd (%rsp), %xmm0
callq __Z3foo9DeclGroup
addq $24, %rsp
ret
At -O3, it is the difference between this now:
__Z3barP9DeclGroup:
movss (%rdi), %xmm0
jmp __Z3foo9DeclGroup # TAILCALL
vs this before:
__Z3barP9DeclGroup:
movl (%rdi), %eax
movd %rax, %xmm0
jmp __Z3foo9DeclGroup # TAILCALL
llvm-svn: 107048
|
| |
|
|
|
|
| |
name. Fixes radar 7860965.
llvm-svn: 107044
|
| |
|
|
| |
llvm-svn: 107040
|
| |
|
|
|
|
| |
I broke negate of FP values.
llvm-svn: 107019
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
(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
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
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
|
| |
|
|
| |
llvm-svn: 106971
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
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
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
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
|
| |
|
|
| |
llvm-svn: 106962
|
| |
|
|
|
|
| |
code so we can use it from VisitUnaryMinus.
llvm-svn: 106957
|
| |
|
|
|
|
|
|
|
|
|
|
| |
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
|
| |
|
|
|
|
| |
While I'm in there, adjust pointer to member adjustments as well.
llvm-svn: 106955
|
| |
|
|
|
|
| |
Lexer/hexfloat.cpp is now XFAIL'd, I'd appreciate if someone could look into it.
llvm-svn: 106840
|
| |
|
|
|
|
| |
Elhage!
llvm-svn: 106507
|
| |
|
|
|
|
| |
Patch by Anton Yartsev!
llvm-svn: 106387
|
| |
|
|
|
|
| |
function to redeclarations of that function. Fixes PR7025.
llvm-svn: 106317
|
| |
|
|
|
|
| |
(the last argument of the triple).
llvm-svn: 106131
|
| |
|
|
| |
llvm-svn: 106120
|
| |
|
|
| |
llvm-svn: 106118
|
| |
|
|
| |
llvm-svn: 105937
|
| |
|
|
|
|
|
| |
vector is filled with the given constant; we were just initializing the
first element.
llvm-svn: 105824
|
| |
|
|
| |
llvm-svn: 105596
|
| |
|
|
| |
llvm-svn: 105500
|
| |
|
|
|
|
|
| |
was given. Remove some unnecessary accounting from BlockScopeInfo. Handle
typedef'ed function types until such time as we decide not.
llvm-svn: 105478
|
| |
|
|
|
|
| |
(radar 8040068).
llvm-svn: 105011
|
| |
|
|
|
|
| |
(radar 8020384)
llvm-svn: 104996
|
| |
|
|
|
|
| |
LLVM backends support these yet.
llvm-svn: 104867
|
| |
|
|
| |
llvm-svn: 104618
|
| |
|
|
| |
llvm-svn: 104118
|
| |
|
|
| |
llvm-svn: 104037
|
| |
|
|
| |
llvm-svn: 104026
|
| |
|
|
|
|
|
| |
definitions.
llvm-svn: 103932
|