| Commit message (Collapse) | Author | Age | Files | Lines |
... | |
|
|
|
| |
llvm-svn: 110165
|
|
|
|
|
|
|
| |
mark it nounwind based on whether it contains any non-nounwind calls.
<rdar://problem/8087431>
llvm-svn: 110163
|
|
|
|
|
|
|
|
|
|
| |
them, but
as soon as we properly codegen the simple vector operations, remove the
unnecessary built-ins/intrinsics from clang and llvm. Also add tests for the new
built-ins
llvm-svn: 110096
|
|
|
|
|
|
|
|
|
|
| |
a switch or goto somewhere in the function. Indirect gotos trigger the
jump-checker regardless, because the conditions there are slightly more
elaborate and it's too marginal a case to be worth optimizing.
Turns off the jump-checker in a lot of cases in C++. rdar://problem/7702918
llvm-svn: 109962
|
|
|
|
| |
llvm-svn: 109847
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
end of a struct. This improves the case when the struct being passed
contains 3 floats, either due to a struct or array of 3 things. Before
we'd generate this IR for the testcase:
define float @bar(double %X.coerce0, double %X.coerce1) nounwind {
entry:
%X = alloca %struct.foof, align 8 ; <%struct.foof*> [#uses=2]
%0 = bitcast %struct.foof* %X to %1* ; <%1*> [#uses=2]
%1 = getelementptr %1* %0, i32 0, i32 0 ; <double*> [#uses=1]
store double %X.coerce0, double* %1
%2 = getelementptr %1* %0, i32 0, i32 1 ; <double*> [#uses=1]
store double %X.coerce1, double* %2
%tmp = getelementptr inbounds %struct.foof* %X, i32 0, i32 2 ; <float*> [#uses=1]
%tmp1 = load float* %tmp ; <float> [#uses=1]
ret float %tmp1
}
which compiled (with optimization) to:
_bar: ## @bar
## BB#0: ## %entry
movd %xmm1, %rax
movd %eax, %xmm0
ret
Now we produce:
define float @bar(double %X.coerce0, float %X.coerce1) nounwind {
entry:
%X = alloca %struct.foof, align 8 ; <%struct.foof*> [#uses=2]
%0 = bitcast %struct.foof* %X to %0* ; <%0*> [#uses=2]
%1 = getelementptr %0* %0, i32 0, i32 0 ; <double*> [#uses=1]
store double %X.coerce0, double* %1
%2 = getelementptr %0* %0, i32 0, i32 1 ; <float*> [#uses=1]
store float %X.coerce1, float* %2
%tmp = getelementptr inbounds %struct.foof* %X, i32 0, i32 2 ; <float*> [#uses=1]
%tmp1 = load float* %tmp ; <float> [#uses=1]
ret float %tmp1
}
and:
_bar: ## @bar
## BB#0: ## %entry
movaps %xmm1, %xmm0
ret
llvm-svn: 109776
|
|
|
|
|
|
| |
that Eli pointed out, rdar://8249586
llvm-svn: 109762
|
|
|
|
|
|
| |
this will hopefully fix the osuosl clang-i686-darwin10 builder.
llvm-svn: 109760
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
struct a {
struct c {
double x;
int y;
} x[1];
};
void foo(struct a A) {
}
into:
define void @foo(double %A.coerce0, i32 %A.coerce1) nounwind {
entry:
%A = alloca %struct.a, align 8 ; <%struct.a*> [#uses=1]
%0 = bitcast %struct.a* %A to %struct.c* ; <%struct.c*> [#uses=2]
%1 = getelementptr %struct.c* %0, i32 0, i32 0 ; <double*> [#uses=1]
store double %A.coerce0, double* %1
%2 = getelementptr %struct.c* %0, i32 0, i32 1 ; <i32*> [#uses=1]
store i32 %A.coerce1, i32* %2
instead of:
define void @foo(double %A.coerce0, i64 %A.coerce1) nounwind {
entry:
%A = alloca %struct.a, align 8 ; <%struct.a*> [#uses=1]
%0 = bitcast %struct.a* %A to %0* ; <%0*> [#uses=2]
%1 = getelementptr %0* %0, i32 0, i32 0 ; <double*> [#uses=1]
store double %A.coerce0, double* %1
%2 = getelementptr %0* %0, i32 0, i32 1 ; <i64*> [#uses=1]
store i64 %A.coerce1, i64* %2
I only do this now because I never want to look at this code again :)
llvm-svn: 109738
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
small integer + padding as that small integer. On code
like:
struct c { double x; int y; };
void bar(struct c C) { }
This means that we compile to:
define void @bar(double %C.coerce0, i32 %C.coerce1) nounwind {
entry:
%C = alloca %struct.c, align 8 ; <%struct.c*> [#uses=2]
%0 = getelementptr %struct.c* %C, i32 0, i32 0 ; <double*> [#uses=1]
store double %C.coerce0, double* %0
%1 = getelementptr %struct.c* %C, i32 0, i32 1 ; <i32*> [#uses=1]
store i32 %C.coerce1, i32* %1
instead of:
define void @bar(double %C.coerce0, i64 %C.coerce1) nounwind {
entry:
%C = alloca %struct.c, align 8 ; <%struct.c*> [#uses=3]
%0 = bitcast %struct.c* %C to %0* ; <%0*> [#uses=2]
%1 = getelementptr %0* %0, i32 0, i32 0 ; <double*> [#uses=1]
store double %C.coerce0, double* %1
%2 = getelementptr %0* %0, i32 0, i32 1 ; <i64*> [#uses=1]
store i64 %C.coerce1, i64* %2
which gives SRoA heartburn.
This implements rdar://5711709, a nice low number :)
llvm-svn: 109737
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
have a "coerce to" type which often matches the default lowering of Clang
type to LLVM IR type, but the coerce case can be handled by making them
not be the same.
This simplifies things and fixes issues where X86-64 abi lowering would
return coerce after making preferred types exactly match up. This caused
us to compile:
typedef float v4f32 __attribute__((__vector_size__(16)));
v4f32 foo(v4f32 X) {
return X+X;
}
into this code at -O0:
define <4 x float> @foo(<4 x float> %X.coerce) nounwind {
entry:
%retval = alloca <4 x float>, align 16 ; <<4 x float>*> [#uses=2]
%coerce = alloca <4 x float>, align 16 ; <<4 x float>*> [#uses=2]
%X.addr = alloca <4 x float>, align 16 ; <<4 x float>*> [#uses=3]
store <4 x float> %X.coerce, <4 x float>* %coerce
%X = load <4 x float>* %coerce ; <<4 x float>> [#uses=1]
store <4 x float> %X, <4 x float>* %X.addr
%tmp = load <4 x float>* %X.addr ; <<4 x float>> [#uses=1]
%tmp1 = load <4 x float>* %X.addr ; <<4 x float>> [#uses=1]
%add = fadd <4 x float> %tmp, %tmp1 ; <<4 x float>> [#uses=1]
store <4 x float> %add, <4 x float>* %retval
%0 = load <4 x float>* %retval ; <<4 x float>> [#uses=1]
ret <4 x float> %0
}
Now we get:
define <4 x float> @foo(<4 x float> %X) nounwind {
entry:
%X.addr = alloca <4 x float>, align 16 ; <<4 x float>*> [#uses=3]
store <4 x float> %X, <4 x float>* %X.addr
%tmp = load <4 x float>* %X.addr ; <<4 x float>> [#uses=1]
%tmp1 = load <4 x float>* %X.addr ; <<4 x float>> [#uses=1]
%add = fadd <4 x float> %tmp, %tmp1 ; <<4 x float>> [#uses=1]
ret <4 x float> %add
}
This implements rdar://8248065
llvm-svn: 109733
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Before we'd compile the example into something like:
%coerce.dive2 = getelementptr %struct.v4f32wrapper* %retval, i32 0, i32 0 ; <<4 x float>*> [#uses=1]
%1 = bitcast <4 x float>* %coerce.dive2 to <2 x double>* ; <<2 x double>*> [#uses=1]
%2 = load <2 x double>* %1, align 1 ; <<2 x double>> [#uses=1]
ret <2 x double> %2
Now we produce:
%coerce.dive2 = getelementptr %struct.v4f32wrapper* %retval, i32 0, i32 0 ; <<4 x float>*> [#uses=1]
%0 = load <4 x float>* %coerce.dive2, align 1 ; <<4 x float>> [#uses=1]
ret <4 x float> %0
llvm-svn: 109732
|
|
|
|
|
|
| |
with return values, improving stuff that returns __m128 etc.
llvm-svn: 109731
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
for return values too. Instead of compiling something like:
struct foo {
int *X;
float *Y;
};
struct foo test(struct foo *P) { return *P; }
to:
%1 = type { i64, i64 }
define %1 @test(%struct.foo* %P) nounwind {
entry:
%retval = alloca %struct.foo, align 8 ; <%struct.foo*> [#uses=2]
%P.addr = alloca %struct.foo*, align 8 ; <%struct.foo**> [#uses=2]
store %struct.foo* %P, %struct.foo** %P.addr
%tmp = load %struct.foo** %P.addr ; <%struct.foo*> [#uses=1]
%tmp1 = bitcast %struct.foo* %retval to i8* ; <i8*> [#uses=1]
%tmp2 = bitcast %struct.foo* %tmp to i8* ; <i8*> [#uses=1]
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %tmp1, i8* %tmp2, i64 16, i32 8, i1 false)
%0 = bitcast %struct.foo* %retval to %1* ; <%1*> [#uses=1]
%1 = load %1* %0, align 1 ; <%1> [#uses=1]
ret %1 %1
}
We now get the result more type safe, with:
define %struct.foo @test(%struct.foo* %P) nounwind {
entry:
%retval = alloca %struct.foo, align 8 ; <%struct.foo*> [#uses=2]
%P.addr = alloca %struct.foo*, align 8 ; <%struct.foo**> [#uses=2]
store %struct.foo* %P, %struct.foo** %P.addr
%tmp = load %struct.foo** %P.addr ; <%struct.foo*> [#uses=1]
%tmp1 = bitcast %struct.foo* %retval to i8* ; <i8*> [#uses=1]
%tmp2 = bitcast %struct.foo* %tmp to i8* ; <i8*> [#uses=1]
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %tmp1, i8* %tmp2, i64 16, i32 8, i1 false)
%0 = load %struct.foo* %retval ; <%struct.foo> [#uses=1]
ret %struct.foo %0
}
That memcpy is completely terrible, but I don't know how to fix it.
llvm-svn: 109729
|
|
|
|
|
|
|
|
| |
possible. This improves the example to pass <4 x float> instead of
<2 x double> but we still get awful code, and still don't get the
return value right.
llvm-svn: 109700
|
|
|
|
|
|
| |
don't get errors similar to PR7714 on the return path.
llvm-svn: 109689
|
|
|
|
|
|
|
| |
x86-64 abi. This also improves codegen as well. Some refactoring is needed of
this code.
llvm-svn: 109681
|
|
|
|
|
|
|
| |
block returns structs. Fies radar 8241648.
Executable test added to llvm test suite.
llvm-svn: 109620
|
|
|
|
|
|
|
| |
if it hs side-effect to matchgcc's behaviour.
Addresses radar 8172109.
llvm-svn: 109467
|
|
|
|
|
|
|
| |
the block-release unwind cleanup: we're never going to test it if we don't turn
it on.
llvm-svn: 108992
|
|
|
|
|
|
| |
fixed return types.
llvm-svn: 108657
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
their call expressions synthetically have the "deduced" types based on their
first argument. We only insert conversions in the AST for arguments whose
values require conversion to match the value type expected. This keeps PR7600
closed by maintaining the return type, but avoids assertions due to unexpected
implicit casts making the type unsigned (test case added from Daniel).
The magic is moved into the codegen for the atomic builtin which inserts the
casts as needed at the IR level to raise the type to an integer suitable for
the LLVM intrinsic. This shouldn't cause any real change in functionality, but
now we can make the builtin be more truly polymorphic.
llvm-svn: 108638
|
|
|
|
|
|
| |
asm operand twice.
llvm-svn: 108489
|
|
|
|
|
|
|
| |
the builtin as void __clear_cache(...) to workaround this, which appears to
match what GCC does.
llvm-svn: 108487
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
- This issue here is that /usr/include/Blocks.h wants to define some of the
block runtime globals as weak, depending on the target. This doesn't work in
Clang because we aren't using the AST decl for these globals.
- The fix is a pretty gross hack which just watches all the decls for the
specific blocks globals we need to know about; if we see one we use it,
otherwise we use the hand coded type.
In time, I would like to clean this up by changing IRgen to ask Sema/AST for
the decl, which would then be lazily loaded from the builtin table if
necessary. This could be used in a whole host of places in IRgen and would
get rid of a lot of grotty hand coding of LLVM IR; however, we need some
extra Sema support for this as well as support for builtin global variables.
llvm-svn: 108482
|
|
|
|
| |
llvm-svn: 108470
|
|
|
|
|
|
| |
with always_inline attribute. Thanks to Howard for the tip.
llvm-svn: 108469
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
strip cv-qualifiers from the expression's type when the language calls
for it: in C, that's all the time, while C++ only does it for
non-class types.
Centralized the computation of the call expression type in
QualType::getCallResultType() and some helper functions in other nodes
(FunctionDecl, ObjCMethodDecl, FunctionType), and updated all relevant
callers of getResultType() to getCallResultType().
Fixes PR7598 and PR7463, along with a bunch of getResultType() call
sites that weren't stripping references off the result type (nothing
stripped cv-qualifiers properly before this change).
llvm-svn: 108234
|
|
|
|
|
|
|
|
| |
at -O0. The only change from the previous patch is that we don't try
to generate virtual method thunks for an available_externally
function.
llvm-svn: 108230
|
|
|
|
| |
llvm-svn: 108194
|
|
|
|
|
|
|
|
|
|
| |
-O0, since we won't be using the definitions for anything anyway. For
lib/System/Path.o when built in Debug+Asserts mode, this leads to a 4%
improvement in compile time (and suppresses 440 function bodies).
<rdar://problem/7987644>
llvm-svn: 108156
|
|
|
|
|
|
|
|
|
|
| |
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
|