248c41d108
Rename RegUseTracker's RegUses member to RegUsesMap to avoid
...
confusion with LSRInstance's RegUses member.
llvm-svn: 104076
2010-05-18 22:33:00 +00:00
6739a89117
Fixes for Microsoft Visual Studio 2010, from Steven Watanabe!
...
llvm-svn: 103457
2010-05-11 06:17:44 +00:00
d0800241d2
When pruning candidate formulae out of an LSRUse, update the
...
LSRUse's Regs set after all pruning is done, rather than trying
to do it on the fly, which can produce an incomplete result.
This fixes a case where heuristic pruning was stripping all
formulae from a use, which led the solver to enter an infinite
loop.
Also, add a few asserts to diagnose this kind of situation.
llvm-svn: 103328
2010-05-07 23:36:59 +00:00
1d2ded75e2
Use getConstant instead of getIntegerSCEV. The two are basically the
...
same, now that getConstant has overloads consistent with ConstantInt::get.
llvm-svn: 102965
2010-05-03 22:09:21 +00:00
534ba376f6
Generalize LSR's OptimizeMax to handle the new kinds of max expressions
...
that indvars may use, now that indvars is recognizing le and ge loops.
llvm-svn: 102235
2010-04-24 03:13:44 +00:00
997bbc54d6
Fix LSR to tolerate cases where ScalarEvolution initially
...
misses an opportunity to fold add operands, but folds them
after LSR has separated them out. This fixes rdar://7886751.
llvm-svn: 102157
2010-04-23 01:55:05 +00:00
e637ff5e9a
Remove the Expr member from IVUsers. Instead of remembering the expression,
...
just ask ScalarEvolution for it on demand. This helps IVUsers be more robust
in the case of expressions changing underneath it. This fixes PR6862.
llvm-svn: 101819
2010-04-19 21:48:58 +00:00
27c8e79839
Delete this code, which is no longer needed.
...
llvm-svn: 101033
2010-04-12 08:00:22 +00:00
607e02b33a
When determining a canonical insert position, don't climb deeper
...
into adjacent loops. Also, ensure that the insert position is
dominated by the loop latch of any loop in the post-inc set which
has a latch.
llvm-svn: 100906
2010-04-09 22:07:05 +00:00
42ec4eb351
When looking for loop-invariant users, look through no-op instructions,
...
so that an unfortunately placed bitcast doesn't pin a value in a
register.
llvm-svn: 100883
2010-04-09 19:12:34 +00:00
d2df643ddb
Refactor the code for computing the insertion point for an expression into
...
a separate function.
llvm-svn: 100845
2010-04-09 02:00:38 +00:00
9b5d0bb774
Avoid allocating a value of zero in a register if the initial formula
...
inputs happen to negate each other.
llvm-svn: 100828
2010-04-08 23:36:27 +00:00
4ce1fb1448
Add variants of ult, ule, etc. which take a uint64_t RHS, for convenience.
...
llvm-svn: 100824
2010-04-08 23:03:40 +00:00
4506539d84
When expanding expressions which are using post-inc mode for multiple loops,
...
ensure that the expansion is dominated by the increments of those loops.
llvm-svn: 100748
2010-04-08 05:57:57 +00:00
d006ab90dd
Generalize IVUsers to track arbitrary expressions rather than expressions
...
explicitly split into stride-and-offset pairs. Also, add the
ability to track multiple post-increment loops on the same expression.
This refines the concept of "normalizing" SCEV expressions used for
to post-increment uses, and introduces a dedicated utility routine for
normalizing and denormalizing expressions.
This fixes the expansion of expressions which are post-increment users
of more than one loop at a time. More broadly, this takes LSR another
step closer to being able to reason about more than one loop at a time.
llvm-svn: 100699
2010-04-07 22:27:08 +00:00
d42e09d91e
Ignore debug intrinsics in yet more places.
...
llvm-svn: 99580
2010-03-26 00:33:27 +00:00
c78d720f02
rename use_const_iterator to const_use_iterator for consistency's sake
...
llvm-svn: 99564
2010-03-25 23:06:16 +00:00
29707de4fe
Make SCEVExpander and LSR more aggressive about hoisting expressions out
...
of loops.
llvm-svn: 97642
2010-03-03 05:29:13 +00:00
52f5563973
Non-affine post-inc SCEV expansions have more code which must be
...
emitted after the increment. Make sure the insert position
reflects this. This fixes PR6453.
llvm-svn: 97537
2010-03-02 01:59:21 +00:00
8b0a419eb1
Spelling fixes.
...
llvm-svn: 97453
2010-03-01 17:49:51 +00:00
8c16b38262
Remove unused variables and parameters.
...
llvm-svn: 96780
2010-02-22 04:11:59 +00:00
4506fcb3c2
When emitting an instruction which depends on both a post-incremented
...
induction variable value and a loop-variant value, don't force the
insert position to be at the post-increment position, because it may
not be dominated by the loop-variant value. This fixes a
use-before-def problem noticed on PPC.
llvm-svn: 96774
2010-02-22 03:59:54 +00:00
4eebb94094
Rename getSDiv to getExactSDiv to reflect its behavior in cases where
...
the division would have a remainder.
llvm-svn: 96693
2010-02-19 19:35:48 +00:00
85af256779
Check for overflow when scaling up an add or an addrec for
...
scaled reuse.
llvm-svn: 96692
2010-02-19 19:32:49 +00:00
2446f57503
When determining the set of interesting reuse factors, consider
...
strides in foreign loops. This helps locate reuse opportunities
with existing induction variables in foreign loops and reduces
the need for inserting new ones. This fixes rdar://7657764.
llvm-svn: 96629
2010-02-19 00:05:23 +00:00
13ac3b2139
Delete some unneeded casts.
...
llvm-svn: 96429
2010-02-17 00:42:19 +00:00
5f10d6c52c
Don't attempt to divide INT_MIN by -1; consider such cases to
...
have overflowed.
llvm-svn: 96428
2010-02-17 00:41:53 +00:00
6deab96c81
Refactor rewriting for PHI nodes into a separate function.
...
llvm-svn: 96382
2010-02-16 20:25:07 +00:00
0849ed5e26
Fix whitespace.
...
llvm-svn: 96372
2010-02-16 19:42:34 +00:00
19d0b47b1f
There are two ways of checking for a given type, for example isa<PointerType>(T)
...
and T->isPointerTy(). Convert most instances of the first form to the second form.
Requested by Chris.
llvm-svn: 96344
2010-02-16 11:11:14 +00:00
521efe68ab
Split the main for-each-use loop again, this time for GenerateTruncates,
...
as it also peeks at which registers are being used by other uses. This
makes LSR less sensitive to use-list order.
llvm-svn: 96308
2010-02-16 01:42:53 +00:00
e4e51a63da
Fix whitespace.
...
llvm-svn: 96179
2010-02-14 18:51:39 +00:00
e7f74bb16c
Fix a comment.
...
llvm-svn: 96178
2010-02-14 18:51:20 +00:00
bb7d52213c
When complicated expressions are broken down into subexpressions
...
with multiplication by constants distributed through, occasionally
those subexpressions can include both x and -x. For now, if this
condition is discovered within LSR, just prune such cases away,
as they won't be profitable. This fixes a "zero allocated in a
base register" assertion failure.
llvm-svn: 96177
2010-02-14 18:50:49 +00:00
2d0f96d49a
Actually, this code doesn't have to be quite so conservative in
...
the no-TLI case. But it should still default to declining the
transformation.
llvm-svn: 96152
2010-02-14 03:21:49 +00:00
cb76a806f0
Don't attempt aggressive post-inc uses if TargetLowering is not available,
...
because profitability can't be sufficiently approximated.
llvm-svn: 96148
2010-02-14 02:45:21 +00:00
0daaf13b97
Make LSR not crash if invoked without target lowering info, e.g. if invoked
...
from opt.
llvm-svn: 96135
2010-02-13 23:40:16 +00:00
5b18f039eb
Fix a pruning heuristic which implicitly assumed that SmallPtrSet is
...
deterministically sorted.
llvm-svn: 96071
2010-02-13 02:06:02 +00:00
2b75de97c0
Reapply 95979, a compile-time speedup, now that the bug it exposed is fixed.
...
llvm-svn: 96005
2010-02-12 19:35:25 +00:00
363f847ec6
Fix this code to avoid dereferencing an end() iterator in
...
offset distributions it doesn't expect.
llvm-svn: 96002
2010-02-12 19:20:37 +00:00
e0b2c69d3c
Revert "Reverse the order for collecting the parts of an addrec. The order", it
...
is breaking llvm-gcc bootstrap.
llvm-svn: 95988
2010-02-12 17:27:08 +00:00
0194f58047
Reverse the order for collecting the parts of an addrec. The order
...
doesn't matter, except that ScalarEvolution tends to need less time
to fold the results this way.
llvm-svn: 95979
2010-02-12 11:08:26 +00:00
45774ce0ad
Reapply the new LoopStrengthReduction code, with compile time and
...
bug fixes, and with improved heuristics for analyzing foreign-loop
addrecs.
This change also flattens IVUsers, eliminating the stride-oriented
groupings, which makes it easier to work with.
llvm-svn: 95975
2010-02-12 10:34:29 +00:00
48816a0b3f
Generic reformatting and comment fixing. No functionality change.
...
llvm-svn: 94771
2010-01-29 00:52:43 +00:00
8277838cf8
Add newline to debugging output, and fix some grammar-os in comment.
...
llvm-svn: 94765
2010-01-29 00:27:39 +00:00
045f81981a
Revert LoopStrengthReduce.cpp to pre-r94061 for now.
...
llvm-svn: 94123
2010-01-22 00:46:49 +00:00
b1ee154b6b
When inserting expressions for post-increment users which contain
...
loop-variant components, adds must be inserted after the increment.
Keep track of the increment position for this case, and insert
these adds in the correct location.
llvm-svn: 94110
2010-01-21 23:01:22 +00:00
cb8d577eb2
Include IVUsers information in LSR's debug output.
...
llvm-svn: 94108
2010-01-21 22:46:32 +00:00
29916e023d
Prune the search for candidate formulae if the number of register
...
operands exceeds the number of registers used in the initial
solution, as that wouldn't lead to a profitable solution anyway.
llvm-svn: 94107
2010-01-21 22:42:49 +00:00
c903499ff8
Add a comment.
...
llvm-svn: 94104
2010-01-21 21:31:09 +00:00
51ad99d2c5
Re-implement the main strength-reduction portion of LoopStrengthReduction.
...
This new version is much more aggressive about doing "full" reduction in
cases where it reduces register pressure, and also more aggressive about
rewriting induction variables to count down (or up) to zero when doing so
reduces register pressure.
It currently uses fairly simplistic algorithms for finding reuse
opportunities, but it introduces a new framework allows it to combine
multiple strategies at once to form hybrid solutions, instead of doing
all full-reduction or all base+index.
llvm-svn: 94061
2010-01-21 02:09:26 +00:00
b5358003fb
Set Changed properly after calling DeleteDeadPHIs.
...
llvm-svn: 92735
2010-01-05 16:31:45 +00:00
2330f78075
Remove dump routine and the associated Debug.h from a header. Patch up
...
other files to compensate.
llvm-svn: 92075
2009-12-23 22:58:38 +00:00
18fa5686f6
Add Loop contains utility methods for testing whether a loop
...
contains another loop, or an instruction. The loop form is
substantially more efficient on large loops than the typical
code it replaces.
llvm-svn: 91654
2009-12-18 01:24:09 +00:00
fd7231f1fe
Minor code simplification.
...
llvm-svn: 91653
2009-12-18 01:20:44 +00:00
b1924e8a0f
Don't pass const pointers by reference.
...
llvm-svn: 91647
2009-12-18 00:38:08 +00:00
92c3696524
Reapply LoopStrengthReduce and IVUsers cleanups, excluding the part
...
of 91296 that caused trouble -- the Processed list needs to be
preserved for the livetime of the pass, as AddUsersIfInteresting
is called from other passes.
llvm-svn: 91641
2009-12-18 00:06:20 +00:00
090ac0865a
Revert 91280-91283, 91286-91289, 91291, 91293, 91295-91296. It apparently introduced a non-deterministic behavior in the optimizer somewhere.
...
llvm-svn: 91598
2009-12-17 09:39:49 +00:00
265ce318b8
Delete an unused function.
...
llvm-svn: 91432
2009-12-15 16:30:09 +00:00
fbeec7270c
Fix a thinko; isNotAlreadyContainedIn had a built-in negative, so the
...
condition was inverted when the code was converted to contains().
llvm-svn: 91295
2009-12-14 17:31:01 +00:00
416d5b7361
Remove unnecessary #includes.
...
llvm-svn: 91293
2009-12-14 17:19:06 +00:00
163fb26927
Instead of having a ScalarEvolution pointer member in BasedUser, just pass
...
the ScalarEvolution pointer into the functions which need it.
llvm-svn: 91289
2009-12-14 17:12:51 +00:00
8dbd4e3d16
Don't bother cleaning up if there's nothing to clean up.
...
llvm-svn: 91288
2009-12-14 17:10:44 +00:00
88c7e61c5b
Delete an unused variable.
...
llvm-svn: 91287
2009-12-14 17:08:09 +00:00
838f604543
LSR itself doesn't need LoopInfo.
...
llvm-svn: 91283
2009-12-14 17:02:34 +00:00
273e692952
LSR itself doesn't need DominatorTree.
...
llvm-svn: 91282
2009-12-14 16:57:08 +00:00
c3513095cf
Remove the code in LSR that manually hoists expansions out of loops;
...
SCEVExpander does this automatically.
llvm-svn: 91281
2009-12-14 16:52:55 +00:00
ec2a7c58e8
Minor code cleanups.
...
llvm-svn: 91280
2009-12-14 16:37:29 +00:00
6bf5305f5d
grammar
...
llvm-svn: 89145
2009-11-17 21:37:04 +00:00
e4e018ae67
80-column violations
...
llvm-svn: 89123
2009-11-17 19:05:35 +00:00
ba4e5da727
Generalize OptimizeLoopTermCond to optimize more loop terminating icmp to use postinc iv.
...
llvm-svn: 89116
2009-11-17 18:10:11 +00:00
60f4854c76
Remove trailing whitespace
...
llvm-svn: 89110
2009-11-17 17:53:56 +00:00
85a9f430e9
- Teach LSR to avoid changing cmp iv stride if it will create an immediate that
...
cannot be folded into target cmp instruction.
- Avoid a phase ordering issue where early cmp optimization would prevent the
later count-to-zero optimization.
- Add missing checks which could cause LSR to reuse stride that does not have
users.
- Fix a bug in count-to-zero optimization code which failed to find the pre-inc
iv's phi node.
- Remove, tighten, loosen some incorrect checks disable valid transformations.
- Quite a bit of code clean up.
llvm-svn: 86969
2009-11-12 07:35:05 +00:00
12f146d8f7
Block terminator may be a switch.
...
llvm-svn: 86761
2009-11-11 00:00:21 +00:00
87fe40b32d
Generalize lsr code that optimize loop to count down towards zero.
...
llvm-svn: 86715
2009-11-10 21:14:05 +00:00
a1bf0c0acc
Teach LSR to avoid calling SplitCriticalEdge on edges with indirectbr.
...
llvm-svn: 86193
2009-11-05 23:34:59 +00:00
a83ac2d9e7
Update various Loop optimization passes to cope with the possibility that
...
LoopSimplify form may not be available.
llvm-svn: 86175
2009-11-05 21:11:53 +00:00
d632f89596
Make LSR's OptimizeShadowIV ignore induction variables with negative
...
strides for now, because it doesn't handle them correctly. This fixes a
miscompile of SingleSource/Benchmarks/Misc-C++/ray.
This problem was usually hidden because indvars transforms such induction
variables into negations of canonical induction variables.
llvm-svn: 85118
2009-10-26 15:32:57 +00:00
54d7179a25
Remove ICmpInst::isSignedPredicate which was a reimplementation
...
CmpInst::isSigned.
llvm-svn: 85037
2009-10-25 05:20:17 +00:00
42fb7452df
Instruction::clone does not need to take an LLVMContext&. Remove that and
...
update all the callers.
llvm-svn: 82889
2009-09-27 07:38:41 +00:00
3ddbc242fb
Re-apply r80926, with fixes: keep the domtree informed of new blocks
...
that get created during loop unswitching, and fix SplitBlockPredecessors'
LCSSA updating code to create new PHIs instead of trying to just move
existing ones.
Also, optimize Loop::verifyLoop, since it gets called a lot. Use
searches on a sorted list of blocks instead of calling the "contains"
function, as is done in other places in the Loop class, since "contains"
does a linear search. Also, don't call verifyLoop from LoopSimplify or
LCSSA, as the PassManager is already calling verifyLoop as part of
LoopInfo's verifyAnalysis.
llvm-svn: 81221
2009-09-08 15:45:00 +00:00
904199547b
Revert r80926. It causes loop unswitch assertion and slow down some JIT tests significantly.
...
llvm-svn: 81101
2009-09-06 02:26:10 +00:00
4c1bdcf5d7
Add a verifyAnalysis to LoopInfo, LoopSimplify, and LCSSA form that verify
...
that these passes are properly preserved.
Fix several transformation passes that claimed to preserve LoopSimplify
form but weren't.
llvm-svn: 80926
2009-09-03 16:31:42 +00:00
2dd09dbdf7
eliminate VISIBILITY_HIDDEN from Transforms/Scalar. PR4861
...
llvm-svn: 80766
2009-09-02 06:11:42 +00:00
b25de3ff60
eliminate the "Value" printing methods that print to a std::ostream.
...
This required converting a bunch of stuff off DOUT and other cleanups.
llvm-svn: 79819
2009-08-23 04:37:46 +00:00
55f1c09e31
Push LLVMContexts through the IntegerType APIs.
...
llvm-svn: 78948
2009-08-13 21:58:54 +00:00
53aa7a960c
Rename MVT to EVT, in preparation for splitting SimpleValueType out into its own struct type.
...
llvm-svn: 78610
2009-08-10 22:56:29 +00:00
298bce2aa9
Check for !isa<Constant> instead of isa<Instruction>. This
...
matches what the comment says, and it avoids spurious BitCast
instructions for Argument values.
llvm-svn: 78121
2009-08-04 23:23:56 +00:00
5a1acd9912
Move a few more APIs back to 2.5 forms. The only remaining ones left to change back are
...
metadata related, which I'm waiting on to avoid conflicting with Devang.
llvm-svn: 77721
2009-07-31 20:28:14 +00:00
47d02732e0
Eliminate a few unused-variable warnings
...
llvm-svn: 77519
2009-07-29 22:41:10 +00:00
4056ca9568
Move types back to the 2.5 API.
...
llvm-svn: 77516
2009-07-29 22:17:13 +00:00
487375e9a2
Move ConstantExpr to 2.5 API.
...
llvm-svn: 77494
2009-07-29 18:55:55 +00:00
69c464dec4
Move ConstantFP construction back to the 2.5-ish API.
...
llvm-svn: 77247
2009-07-27 20:59:43 +00:00
6115b39ffd
Remove Value::getName{Start,End}, the last of the old Name APIs.
...
llvm-svn: 77152
2009-07-26 09:48:23 +00:00
edb4a70325
Revert the ConstantInt constructors back to their 2.5 forms where possible, thanks to contexts-on-types. More to come.
...
llvm-svn: 77011
2009-07-24 23:12:02 +00:00
47db941fd3
Get rid of the Pass+Context magic.
...
llvm-svn: 76702
2009-07-22 00:24:57 +00:00
cc85ae132c
Make Loop and MachineLoop be subclasses of LoopBase, rather than typedefs,
...
using the Curiously Recurring Template Pattern with LoopBase.
This will help further refactoring, and future functionality for
Loop. Also, Headers can now foward-declare Loop, instead of pulling
in LoopInfo.h or doing tricks.
llvm-svn: 75519
2009-07-13 21:51:15 +00:00
1e5f00e7a7
This started as a small change, I swear. Unfortunately, lots of things call the [I|F]CmpInst constructors. Who knew!?
...
llvm-svn: 75200
2009-07-09 23:48:35 +00:00
af75234955
Change all SCEV* to SCEV *.
...
llvm-svn: 74918
2009-07-07 17:06:11 +00:00
80baed63b4
Second batch of passes using LLVMContext.
...
llvm-svn: 74753
2009-07-03 00:54:20 +00:00
Dan Gohman