| Commit message (Collapse) | Author | Age | Files | Lines |
| |
|
|
| |
llvm-svn: 106980
|
| |
|
|
|
|
|
|
| |
large integers, the first inserted value would always create
an 'or X, 0'. Even though this is trivially zapped by
instcombine, don't bother creating this pointless instruction.
llvm-svn: 106979
|
| |
|
|
| |
llvm-svn: 106978
|
| |
|
|
|
|
|
|
| |
have CGF create and make accessible standard int32,int64 and
intptr types. This fixes a ton of 80 column violations
introduced by LLVMContextification and cleans up stuff a lot.
llvm-svn: 106977
|
| |
|
|
| |
llvm-svn: 106976
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
(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
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
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
|
| |
|
|
|
|
| |
constraints. Part of PR7491.
llvm-svn: 106972
|
| |
|
|
| |
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
|
| |
|
|
| |
llvm-svn: 106969
|
| |
|
|
| |
llvm-svn: 106968
|
| |
|
|
| |
llvm-svn: 106967
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
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: 106964
|
| |
|
|
|
|
|
| |
we're done diddling around with the index stuff. Use a cheaper type
comparison.
llvm-svn: 106963
|
| |
|
|
| |
llvm-svn: 106962
|
| |
|
|
|
|
| |
of being in CGF. No functionality change.
llvm-svn: 106961
|
| |
|
|
|
|
| |
it for now.
llvm-svn: 106960
|
| |
|
|
| |
llvm-svn: 106959
|
| |
|
|
| |
llvm-svn: 106958
|
| |
|
|
|
|
| |
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
|
| |
|
|
| |
llvm-svn: 106954
|
| |
|
|
|
|
| |
operations or the names assigned to the specialized functions
llvm-svn: 106953
|
| |
|
|
|
|
| |
This produces terrible but correct code.
llvm-svn: 106952
|
| |
|
|
|
|
|
|
|
|
| |
regressions.
--- Reverse-merging r106939 into '.':
U test/CodeGen/Thumb2/thumb2-ifcvt3.ll
U lib/CodeGen/IfConversion.cpp
llvm-svn: 106951
|
| |
|
|
| |
llvm-svn: 106950
|
| |
|
|
| |
llvm-svn: 106949
|
| |
|
|
| |
llvm-svn: 106948
|
| |
|
|
|
|
|
|
| |
the returned value after the tail call if it differs from other return
values. The optimal thing to do would be to introduce a phi node for
the return value, but for the moment just fix the miscompile.
llvm-svn: 106947
|
| |
|
|
| |
llvm-svn: 106946
|
| |
|
|
| |
llvm-svn: 106945
|
| |
|
|
| |
llvm-svn: 106944
|
| |
|
|
| |
llvm-svn: 106943
|
| |
|
|
| |
llvm-svn: 106942
|
| |
|
|
| |
llvm-svn: 106941
|
| |
|
|
| |
llvm-svn: 106940
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
if-conversion. The RemoveExtraEdges function doesn't work for blocks that
end with unanalyzable branches, so in those cases, the "extra" edges must
be explicitly removed. The CopyAndPredicateBlock and MergeBlocks methods
can also avoid copying successor edges due to branches that have already
been removed. The latter case is especially helpful when MergeBlocks is
called for handling "diamond" if-conversions, where otherwise you can end
up with some weird intermediate states in the CFG. Unfortunately I've
been unable to find cases where this cleanup actually makes a significant
difference in the code. There is one test where we manage to remove an
empty block at the end of a function. Radar 6911268.
llvm-svn: 106939
|
| |
|
|
| |
llvm-svn: 106938
|
| |
|
|
|
|
|
| |
Also, fix mangling of throw specs. Turns out MSVC totally ignores throw
specs when mangling names.
llvm-svn: 106937
|
| |
|
|
| |
llvm-svn: 106935
|
| |
|
|
|
|
|
|
|
|
|
| |
CopyFromReg nodes for aliasing registers (AX and AL). This confuses the fast
register allocator.
Instead of CopyFromReg(AL), use ExtractSubReg(CopyFromReg(AX), sub_8bit).
This fixes PR7312.
llvm-svn: 106934
|
| |
|
|
| |
llvm-svn: 106932
|
| |
|
|
| |
llvm-svn: 106929
|
| |
|
|
| |
llvm-svn: 106927
|
| |
|
|
|
|
|
|
|
| |
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
|
| |
|
|
|
|
| |
"N..." instead of "NEON..." for consistency with the other NEON format names.
llvm-svn: 106921
|