in both time and memory savings for GVN. For example, one testcase went from 10.5s to 6s with
this patch.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@49345 91177308-0d34-0410-b5e6-96231b3b80d8
needs to be fixed here - a previous commit made sure
that intrinsics always get the right attributes.
So remove no-longer needed code, and while there use
Intrinsic::getDeclaration rather than getOrInsertFunction.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@49337 91177308-0d34-0410-b5e6-96231b3b80d8
nounwind. When such calls are inlined into something
else that is invoked, they were getting changed to invokes,
which is badness.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@49299 91177308-0d34-0410-b5e6-96231b3b80d8
Specifically, introduction of XXX::Create methods
for Users that have a potentially variable number of
Uses.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@49277 91177308-0d34-0410-b5e6-96231b3b80d8
don't access cached iterators from after the erased element.
Re-apply 49056 with SmallVector support.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@49106 91177308-0d34-0410-b5e6-96231b3b80d8
2. Do not use # of basic blocks as part of the cost computation since it doesn't really figure into function size.
3. More aggressively inline function with vector code.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@49061 91177308-0d34-0410-b5e6-96231b3b80d8
not marked nounwind, or for all functions when -enable-eh
is set, provided the target supports Dwarf EH.
llvm-gcc generates nounwind in the right places; other FEs
will need to do so also. Given such a FE, -enable-eh should
no longer be needed.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@49006 91177308-0d34-0410-b5e6-96231b3b80d8
when something changes, instead of moving forward. This allows us to
simplify memset lowering, inserting the memset at the end of the range of
stuff we're touching instead of at the start.
This, in turn, allows us to make use of the addressing instructions already
used in the function instead of inserting our own. For example, we now
codegen:
%tmp41 = getelementptr [8 x i8]* %ref_idx, i32 0, i32 0 ; <i8*> [#uses=2]
call void @llvm.memset.i64( i8* %tmp41, i8 -1, i64 8, i32 1 )
instead of:
%tmp20 = getelementptr [8 x i8]* %ref_idx, i32 0, i32 7 ; <i8*> [#uses=1]
%ptroffset = getelementptr i8* %tmp20, i64 -7 ; <i8*> [#uses=1]
call void @llvm.memset.i64( i8* %ptroffset, i8 -1, i64 8, i32 1 )
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@48940 91177308-0d34-0410-b5e6-96231b3b80d8
memsets that initialize "structs of arrays" and other store sequences
that are not sequential. This is still only enabled if you pass
-form-memset-from-stores. The flag is not heavily tested and I haven't
analyzed the perf regressions when -form-memset-from-stores is passed
either, but this causes no make check regressions.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@48909 91177308-0d34-0410-b5e6-96231b3b80d8
Furthermore, double the limit when more than 10% of the callee instructions are vector instructions. Multimedia kernels tend to love inlining.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@48725 91177308-0d34-0410-b5e6-96231b3b80d8
This fires dozens of times across spec and multisource, but I don't know
if it actually speeds stuff up. Hopefully the testers will show something
nice :)
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@48680 91177308-0d34-0410-b5e6-96231b3b80d8
simplify things like (X & 4) >> 1 == 2 --> (X & 4) == 4.
since it is obvious that the shift doesn't remove any bits.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@48631 91177308-0d34-0410-b5e6-96231b3b80d8
