my earlier patch to this file.

The issue there was that all uses of an IV inside a loop
are actually references to Base[IV*2], and there was one
use outside that was the same but LSR didn't see the base
or the scaling because it didn't recurse into uses outside
the loop; thus, it used base+IV*scale mode inside the loop
instead of pulling base out of the loop.  This was extra bad
because register pressure later forced both base and IV into
memory.  Doing that recursion, at least enough
to figure out addressing modes, is a good idea in general;
the change in AddUsersIfInteresting does this.  However,
there were side effects....

It is also possible for recursing outside the loop to
introduce another IV where there was only 1 before (if
the refs inside are not scaled and the ref outside is).
I don't think this is a common case, but it's in the testsuite.
It is right to be very aggressive about getting rid of
such introduced IVs (CheckForIVReuse and the handling of
nonzero RewriteFactor in StrengthReduceStridedIVUsers).
In the testcase in question the new IV produced this way
has both a nonconstant stride and a nonzero base, neither
of which was handled before.  And when inserting 
new code that feeds into a PHI, it's right to put such 
code at the original location rather than in the PHI's 
immediate predecessor(s) when the original location is outside 
the loop (a case that couldn't happen before)
(RewriteInstructionToUseNewBase); better to avoid making
multiple copies of it in this case.

Also, the mechanism for keeping SCEV's corresponding to GEP's
no longer works, as the GEP might change after its SCEV
is remembered, invalidating the SCEV, and we might get a bad
SCEV value when looking up the GEP again for a later loop.  
This also couldn't happen before, as we weren't recursing
into GEP's outside the loop.

Also, when we build an expression that involves a (possibly
non-affine) IV from a different loop as well as an IV from
the one we're interested in (containsAddRecFromDifferentLoop),
don't recurse into that.  We can't do much with it and will
get in trouble if we try to create new non-affine IVs or something.

More testcases are coming.

llvm-svn: 62212

vector and extraneous loop over it, 2) not delete globals used by
phis/selects etc which could actually be useful.  This fixes PR3321.
Many thanks to Duncan for narrowing this down.

llvm-svn: 62201

llvm-svn: 62189

least their preferred alignment.

llvm-svn: 62176

llvm-svn: 62165

back to 200; 400 seems to be too high, loses more than
it gains.

llvm-svn: 62107

suggested by Chris.

llvm-svn: 62099

compensation for turning off gcc's inliner.  This gets
us closer to the amount of inlining we were getting before.
It is not a win on everything, of course, but seems to
gain overall.

llvm-svn: 62058

not thrilled about 64-bit % in general, so rewrite to use * instead.

llvm-svn: 62047

We should treat vectors as atomic types, not like arrays.

llvm-svn: 62046

canonicalization transform based on duncan's comments:

1) improve the comment about %.
2) within our index loop make sure the offset stays 
   within the *type size*, instead of within the *abi size*.
   This allows us to reason explicitly about landing in tail
   padding and means that issues like non-zero offsets into
   [0 x foo] types don't occur anymore.

llvm-svn: 62045

llvm-svn: 61997

llvm-svn: 61995

llvm-svn: 61991

I noticed this in the code compiled for a routine using std::map, which produced
this code:
	%25 = tail call i32 @memcmp(i8* %24, i8* %23, i32 6) nounwind readonly
	%.lobit.i = lshr i32 %25, 31		; <i32> [#uses=1]
	%tmp.i = trunc i32 %.lobit.i to i8		; <i8> [#uses=1]
	%toBool = icmp eq i8 %tmp.i, 0		; <i1> [#uses=1]
	br i1 %toBool, label %bb3, label %bb4
which compiled to:

	call	L_memcmp$stub
	shrl	$31, %eax
	testb	%al, %al
	jne	LBB1_11	## 

with this change, we compile it to:

	call	L_memcmp$stub
	testl	%eax, %eax
	js	LBB1_11

This triggers all the time in common code, with patters like this:

	%169 = and i32 %ply, 1		; <i32> [#uses=1]
	%170 = trunc i32 %169 to i8		; <i8> [#uses=1]
	%toBool = icmp ne i8 %170, 0		; <i1> [#uses=1]

 	%7 = lshr i32 %6, 24		; <i32> [#uses=1]
	%9 = trunc i32 %7 to i8		; <i8> [#uses=1]
	%10 = icmp ne i8 %9, 0		; <i1> [#uses=1]

etc

llvm-svn: 61985

llvm-svn: 61984

jump threading can have bugs, who knew? ;-)

llvm-svn: 61983

llvm-svn: 61980

(which is constant time and cheap) before checking hasAllZeroIndices.

llvm-svn: 61976

llvm-svn: 61969

functions that don't already have a (dynamic) alloca.
Dynamic allocas cause inefficient codegen and we shouldn't
propagate this (behavior follows gcc).  Two existing tests
assumed such inlining would be done; they are hacked by
adding an alloca in the caller, preserving the point of
the tests.

llvm-svn: 61946

loads from allocas that cover the entire aggregate.  This handles
some memcpy/byval cases that are produced by llvm-gcc.  This triggers
a few times in kc++ (with std::pair<std::_Rb_tree_const_iterator
<kc::impl_abstract_phylum*>,bool>) and once in 176.gcc (with %struct..0anon).

llvm-svn: 61915

llvm-svn: 61879

was it not very helpful, it was also wrong!  The problem
is shown in the testcase: the alloca might be passed to
a nocapture callee which dereferences it and returns the
original pointer.  But because it was a nocapture call we
think we don't need to track its uses, but we do.

llvm-svn: 61876

llvm-svn: 61873

llvm-svn: 61872

llvm-svn: 61870

integer to a (transitive) bitcast the alloca and if that integer
has the full size of the alloca, then it clobbers the whole thing.
Handle this by extracting pieces out of the stored integer and 
filing them away in the SROA'd elements.

This triggers fairly frequently because the CFE uses integers to
pass small structs by value and the inliner exposes these.  For 
example, in kimwitu++, I see a bunch of these with i64 stores to
"%struct.std::pair<std::_Rb_tree_const_iterator<kc::impl_abstract_phylum*>,bool>"

In 176.gcc I see a few i32 stores to "%struct..0anon".

In the testcase, this is a difference between compiling test1 to:

_test1:
	subl	$12, %esp
	movl	20(%esp), %eax
	movl	%eax, 4(%esp)
	movl	16(%esp), %eax
	movl	%eax, (%esp)
	movl	(%esp), %eax
	addl	4(%esp), %eax
	addl	$12, %esp
	ret

vs:

_test1:
	movl	8(%esp), %eax
	addl	4(%esp), %eax
	ret

The second half of this will be to handle loads of the same form.

llvm-svn: 61853

llvm-svn: 61852

change.

llvm-svn: 61851

requerying it all over the place.

llvm-svn: 61850

code, no functionality change.

llvm-svn: 61849

as template arguments instead of as instance variables, exposing more
optimization opportunities to the compiler earlier.

llvm-svn: 61776

global aliases.

llvm-svn: 61754

llvm-svn: 61752

llvm-svn: 61745

llvm-svn: 61744

llvm-svn: 61743

In fact this also deletes those with linkonce linkage,
however this is currently dead because for the moment
aliases aren't allowed to have this linkage type.

llvm-svn: 61742

llvm-svn: 61715