llvm-svn: 64859

llvm-svn: 64703

Fix pr3571: If stride is a value defined by an instruction, make sure it dominates the loop preheader. When IV users are strength reduced, the stride is inserted into the preheader. It could create a use before def situation.

llvm-svn: 64579

llvm-svn: 64575

about the code it describes, but at least now the comment
is right.

llvm-svn: 64465

addrec in a different loop to check the value being added to
the accumulated Start value, not the Start value before it has
the new value added to it. This prevents LSR from going crazy
on the included testcase. Dale, please review.

llvm-svn: 64440

after sorting by stride value. This prevents it from missing
IV reuse opportunities in a host-sensitive manner.

llvm-svn: 64415

llvm-svn: 64177

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

suggested by Chris.

llvm-svn: 62099

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: 61181

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.  (This patch does not handle 
all the cases where this can happen.)  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.

Everything above is exercised in
CodeGen/X86/lsr-negative-stride.ll (and ifcvt4 in ARM which is
the same IR).

llvm-svn: 61178

can be negative.  Keep track of whether all uses of
an IV are outside the loop.  Some cosmetics; no
functional change.

llvm-svn: 61109

on test/CodeGen/Generic/2007-06-06-CriticalEdgeLandingPad.

llvm-svn: 60739

loops when they can be subsumed into addressing modes.

Change X86 addressing mode check to realize that
some PIC references need an extra register.
(I believe this is correct for Linux, if not, I'm sure
someone will tell me.)

llvm-svn: 60608

llvm-svn: 60508

llvm-svn: 60506

llvm-svn: 60494

llvm-svn: 60442

llvm-svn: 60431

llvm-svn: 60395

figuring out the base of the IV.  This produces better
code in the example.  (Addresses use (IV) instead of 
(BASE,IV) - a significant improvement on low-register
machines like x86).

llvm-svn: 60374

instead of std::sort.  This shrinks the release-asserts LSR.o file
by 1100 bytes of code on my system.

We should start using array_pod_sort where possible.

llvm-svn: 60335

This is a lot cheaper and conceptually simpler.

llvm-svn: 60332

DeadInsts ivar, just use it directly.

llvm-svn: 60330

buggy rewrite, this notifies ScalarEvolution of a pending instruction
about to be removed and then erases it, instead of erasing it then 
notifying.

llvm-svn: 60329

llvm-svn: 60233

making it use RecursivelyDeleteTriviallyDeadInstructions to do
the heavy lifting.

llvm-svn: 60195

llvm-svn: 60192

LoopPass*.
 - Although less precise, this means they can be used in clients
   without RTTI (who would otherwise need to include LoopPass.h, which
   eventually includes things using dynamic_cast). This was the
   simplest solution that presented itself, but I am happy to use a
   better one if available.

llvm-svn: 58010

instruction, not after. This fixes some uses of free'd memory.

llvm-svn: 56908

cases.  See the comment above OptimizeSMax for the full story, and
the testcase for an example. This cancels out a pessimization
commonly attributed to indvars, and will allow us to lift some of
the artificial throttles in indvars, rather than add new ones.

llvm-svn: 56230

llvm-svn: 56011

llvm-svn: 55924

llvm-svn: 55913

llvm-svn: 55779

llvm-svn: 55682