suggested by Chris.

llvm-svn: 62099

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

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

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

llvm-svn: 61752

Finalization occurs after all the FunctionPasses in the group have run, which
is clearly not what we want.

This also means that we have to make sure that we apply the right param 
attributes when creating a new function.

Also, add a missed optimization: strdup and strndup. NoCapture and 
NoAlias return!

llvm-svn: 61658

llvm-svn: 61632

llvm-svn: 61623

llvm-svn: 61538

 xor (or (icmp, icmp), true) -> and(icmp, icmp)

This is possible because of De Morgan's law.

llvm-svn: 61537

llvm-svn: 61403

other SPEC breakage.  I'll be reverting all recent
changes shortly, this checking is mostly so this
change doesn't get lost.

llvm-svn: 61402

my last 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.

I owe some testcases for this, want to get it in for nightly runs.

llvm-svn: 61362

llvm-svn: 61358

llvm-svn: 61354

llvm-svn: 61353

llvm-svn: 61352

llvm-svn: 61350

llvm-svn: 61349

truely deleted. These will be expanded with further checks of all of the data
structures.

llvm-svn: 61347

llvm-svn: 61297

our optz'n will apply to it, then build the replacement vector only if needed.

llvm-svn: 61279

- CodeGenPrepare does not split loop back edges but it only knows about back edges of single block loops. It now does a DFS walk to find loop back edges.
- Use SplitBlockPredecessors to factor out common predecessors of the critical edge destination. This is disabled for now due to some regressions.

llvm-svn: 61248

llvm-svn: 61222

llvm-svn: 61219