c16b0c387f
now that tblgen is smarter, use integers directly. This should help Andrew too
...
llvm-svn: 23818
2005-10-19 04:32:04 +00:00
5f37623218
teach ppc backend these are copies
...
llvm-svn: 23813
2005-10-19 01:50:36 +00:00
5b6f4dc623
Convert these cases to patterns
...
llvm-svn: 23811
2005-10-19 01:38:02 +00:00
9eaa6bac06
Woo, it kinda works. We now generate this atrociously bad, but correct,
...
code for long long foo(long long a, long long b) { return a + b; }
_foo:
or r2, r3, r3
or r3, r4, r4
or r4, r5, r5
or r5, r6, r6
rldicr r2, r2, 32, 31
rldicl r3, r3, 0, 32
rldicr r4, r4, 32, 31
rldicl r5, r5, 0, 32
or r2, r3, r2
or r3, r5, r4
add r4, r3, r2
rldicl r2, r4, 32, 32
or r4, r4, r4
or r3, r2, r2
blr
llvm-svn: 23809
2005-10-19 01:12:32 +00:00
ecdf842311
apply some tblgen majik to simplify the X register definitions
...
llvm-svn: 23805
2005-10-19 00:17:55 +00:00
5172ce641e
Teach Legalize how to do something with EXTRACT_ELEMENT when the type of
...
the pair of elements is a legal type.
llvm-svn: 23804
2005-10-19 00:06:56 +00:00
92e77502f3
Make a new reg class for 64 bit regs that aliases the 32 bit regs. This
...
will have to tide us over until we get real subreg support, but it prevents
the PrologEpilogInserter from spilling 8 byte GPRs on a G4 processor.
Add some initial support for TRUNCATE and ANY_EXTEND, but they don't
currently work due to issues with ScheduleDAG. Something wll have to be
figured out.
llvm-svn: 23803
2005-10-19 00:05:37 +00:00
78afac2ddd
Add the ability to lower return instructions to TargetLowering. This
...
allows us to lower legal return types to something else, to meet ABI
requirements (such as that i64 be returned in two i32 regs on Darwin/ppc).
llvm-svn: 23802
2005-10-18 23:23:37 +00:00
0a71a9ac86
Fix Generic/2005-10-18-ZeroSizeStackObject.ll by not requesting a zero
...
sized stack object if either the array size or the type size is zero.
llvm-svn: 23801
2005-10-18 22:14:06 +00:00
8396a308a7
remove hack
...
llvm-svn: 23797
2005-10-18 22:11:42 +00:00
d812a2e449
Simple edits; remove unimplimented cases and clarify long haul SLU cases.
...
llvm-svn: 23788
2005-10-18 16:59:23 +00:00
5a2fb9787b
Fix the JIT encoding of LWA, LD, STD, and STDU.
...
llvm-svn: 23787
2005-10-18 16:51:22 +00:00
c6533006c8
Checking in first round of scheduling tablegen files. Not tied in as yet.
...
llvm-svn: 23786
2005-10-18 16:23:40 +00:00
53b9c3ad4c
add a case
...
llvm-svn: 23785
2005-10-18 06:30:51 +00:00
45517baf9f
Add an option to this pass. If it is set, we are allowed to internalize
...
all but main. If it's not set, we can still internalize, but only if an
explicit symbol list is provided.
llvm-svn: 23783
2005-10-18 06:29:22 +00:00
6c14c35bd7
Fold (select C, load A, load B) -> load (select C, A, B). This happens quite
...
a lot throughout many programs. In particular, specfp triggers it a bunch for
constant FP nodes when you have code like cond ? 1.0 : -1.0.
If the PPC ISel exposed the loads implicit in pic references to external globals,
we would be able to eliminate a load in cases like this as well:
%X = external global int
%Y = external global int
int* %test4(bool %C) {
%G = select bool %C, int* %X, int* %Y
ret int* %G
}
Note that this breaks things that use SrcValue's (see the fixme), but since nothing
uses them yet, this is ok.
Also, simplify some code to use hasOneUse() on an SDOperand instead of hasNUsesOfValue directly.
llvm-svn: 23781
2005-10-18 06:04:22 +00:00
e74dfbb9ce
Do the right thing and enable 64 bit regs under the control of a subtarget
...
option. Currently the only way to enable this is to specify the
64bitregs mattr flag. It is never enabled by default on any config yet.
llvm-svn: 23779
2005-10-18 00:56:42 +00:00
0b71e007ef
First bits of 64 bit PowerPC stuff, currently disabled. A lot of this is
...
purely mechanical.
llvm-svn: 23778
2005-10-18 00:28:58 +00:00
418c6e4045
Implement some feedback from Chris re: constant canonicalization
...
llvm-svn: 23777
2005-10-18 00:28:13 +00:00
bd5f41a6a6
Legalize BUILD_PAIR appropriately for upcoming 64 bit PowerPC work.
...
llvm-svn: 23776
2005-10-18 00:27:41 +00:00
ec48a1bfbd
fold fmul X, +2.0 -> fadd X, X;
...
llvm-svn: 23774
2005-10-17 20:40:11 +00:00
da1b152c43
Make this work for FP constantexprs
...
llvm-svn: 23773
2005-10-17 20:18:38 +00:00
7fde91e365
Oops, X+0.0 isn't foldable, but X+-0.0 is.
...
llvm-svn: 23772
2005-10-17 17:56:38 +00:00
32979336a7
relax this a bit, as we only support the default rounding mode
...
llvm-svn: 23771
2005-10-17 17:49:32 +00:00
eeb2bda2fa
add a trivial fold
...
llvm-svn: 23764
2005-10-17 01:07:11 +00:00
6cca84e43c
More PPC32 -> PPC changes, as well as merging some classes that were
...
redundant after the change.
llvm-svn: 23759
2005-10-16 05:39:50 +00:00
e540800d5a
Fix this logic.
...
llvm-svn: 23756
2005-10-15 22:35:40 +00:00
17cc9edd33
Add a case we were missing that was causing us to fail CodeGen/PowerPC/rlwinm.ll:test3
...
llvm-svn: 23755
2005-10-15 22:18:08 +00:00
c0896117d3
Remove some dead code now that the dag combiner exists.
...
llvm-svn: 23754
2005-10-15 22:08:02 +00:00
d869bec4fe
Remove some dead code: the ORI/ORIS cases are autogen'd. This makes
...
SelectIntImmediateExpr dead.
llvm-svn: 23753
2005-10-15 22:06:18 +00:00
03354280eb
prune #includes
...
llvm-svn: 23752
2005-10-15 21:58:54 +00:00
a52969c8d6
These instructions are now autogenerated
...
llvm-svn: 23751
2005-10-15 21:44:56 +00:00
286c1d7cfa
Add a pattern for FSQRTS
...
llvm-svn: 23750
2005-10-15 21:44:15 +00:00
efa382616b
remove dead code
...
llvm-svn: 23749
2005-10-15 21:40:12 +00:00
b986f471be
Use getExtLoad here instead of getNode, as extloads produce two values. This
...
fixes a legalize failure on SPASS for itanium.
llvm-svn: 23747
2005-10-15 20:24:07 +00:00
e33870d154
remove broken SRA/rlwimi case
...
llvm-svn: 23746
2005-10-15 19:04:48 +00:00
6f3b954662
Rename PPC32*.h to PPC*.h
...
This completes the grand PPC file renaming
llvm-svn: 23745
2005-10-14 23:59:06 +00:00
0aa794ba5b
Merge PPCJITInfo.h and PPC32JITInfo.h. Note that the PowerPCJITInfo
...
and PPC32JITInfo classes should be merged.
llvm-svn: 23744
2005-10-14 23:53:41 +00:00
bfca1ab79d
Rename PowerPC*.h to PPC*.h
...
llvm-svn: 23743
2005-10-14 23:51:18 +00:00
e80bf1b33a
Rename PowerPCInstrBuilder.h -> PPC*
...
llvm-svn: 23742
2005-10-14 23:45:43 +00:00
2ed745a905
Nuke the PowerPCTargetMachine.h header. Note that the PowerPCTargetMachine
...
still should be merged into the PPC32TargetMachine class
llvm-svn: 23741
2005-10-14 23:44:05 +00:00
7503d46feb
Rename PowerPC*.td -> PPC*.td
...
llvm-svn: 23740
2005-10-14 23:40:39 +00:00
f3b97f53b9
These are dead
...
llvm-svn: 23739
2005-10-14 23:38:51 +00:00
0921e3bfc1
Eliminate PowerPC.td and PPC32.td, consolidating them into PPC.td
...
llvm-svn: 23738
2005-10-14 23:37:35 +00:00
09cd9e7661
Like the comment says...
...
llvm-svn: 23737
2005-10-14 22:48:24 +00:00
2121f3ca50
Nuke PowerPCInstrFormats.h, its contents are dead. Remove the definitions
...
from the .td file that correspond to it
llvm-svn: 23736
2005-10-14 22:44:13 +00:00
9d7008b08d
Properly split f32 and f64 into separate register classes for scalar sse fp
...
fixing a bunch of nasty hackery
llvm-svn: 23735
2005-10-14 22:06:00 +00:00
c41e1be2e8
Remove an unnecsesary file. PPC32 and PPC64 share architected registers.
...
We will decide with subtarget support whether we ever use an i64 register
class.
llvm-svn: 23734
2005-10-14 18:58:46 +00:00
56f31f5408
add the integer truncate/extension operations
...
llvm-svn: 23733
2005-10-14 06:40:20 +00:00
7d9f719d42
These are now autogenerated
...
llvm-svn: 23731
2005-10-14 06:26:29 +00:00
9c0d3c5932
Add patterns for FP round/extend
...
llvm-svn: 23727
2005-10-14 04:55:50 +00:00
6e83cbf7f3
add a new SDTCisOpSmallerThanOp type constraint, and implement fround/fextend in terms of it
...
llvm-svn: 23726
2005-10-14 04:55:10 +00:00
6e673b24d3
fold sext_in_reg, sext_in_reg where both have the same VT. This was
...
popping up in Fourinarow.
llvm-svn: 23722
2005-10-14 01:29:07 +00:00
e3870fbe4a
Allow $
...
llvm-svn: 23721
2005-10-14 01:28:34 +00:00
d59e5a7abb
Relax the checking on zextload generation a bit, since as sabre pointed out
...
you could be AND'ing with the result of a shift that shifts out all the
bits you care about, in addition to a constant.
Also, move over an add/sub_parts fold from legalize to the dag combiner,
where it works for things other than constants. Woot!
llvm-svn: 23720
2005-10-14 01:12:21 +00:00
b8282987f4
Fix the trunc(load) case, finally allowing crafty and povray to pass
...
llvm-svn: 23718
2005-10-13 22:10:05 +00:00
dbc5ae3109
Fix some bugs in (sext (load x))
...
llvm-svn: 23717
2005-10-13 21:52:31 +00:00
258521d7ea
When ExpandOp'ing a [SZ]EXTLOAD, make sure to remember that the chain
...
is also legal. Add support for ExpandOp'ing raw EXTLOADs too.
llvm-svn: 23716
2005-10-13 21:44:47 +00:00
d23f4b7411
Implement PromoteOp for *EXTLOAD, allowing MallocBench/gs to Legalize
...
llvm-svn: 23715
2005-10-13 20:07:41 +00:00
8e022b3d89
Fix the remaining DAGCombiner issues pointed out by sabre. This should fix
...
the remainder of the failures introduced by my patch last night.
llvm-svn: 23714
2005-10-13 18:34:58 +00:00
a80f1f6e72
Fix a minor bug in the dag combiner that broke pcompress2 and some other
...
tests.
llvm-svn: 23713
2005-10-13 18:16:34 +00:00
c3a89c5259
Add support to Legalize for expanding i64 sextload/zextload into hi and lo
...
parts. This should fix the crafty and signed long long unit test failure
on x86 last night.
llvm-svn: 23711
2005-10-13 17:15:37 +00:00
5d7a50ac44
Inhibit instructions from being pushed before function calls. This will
...
minimize unnecessary spilling.
llvm-svn: 23710
2005-10-13 16:44:00 +00:00
02b23c6065
Move some Legalize functionality over to the DAGCombiner where it belongs.
...
Kill some dead code.
llvm-svn: 23706
2005-10-13 03:11:28 +00:00
70d28c5e32
Fix a potential bug with two combine-to's back to back that chris pointed
...
out, where after the first CombineTo() call, the node the second CombineTo
wishes to replace may no longer exist.
Fix a very real bug with the truncated load optimization on little endian
targets, which do not need a byte offset added to the load.
llvm-svn: 23704
2005-10-12 23:18:53 +00:00
8caf81d617
More cool stuff for the dag combiner. We can now finally handle things
...
like turning:
_foo:
fctiwz f0, f1
stfd f0, -8(r1)
lwz r2, -4(r1)
rlwinm r3, r2, 0, 16, 31
blr
into
_foo:
fctiwz f0,f1
stfd f0,-8(r1)
lhz r3,-2(r1)
blr
Also removed an unncessary constraint from sra -> srl conversion, which
should take care of hte only reason we would ever need to handle sra in
MaskedValueIsZero, AFAIK.
llvm-svn: 23703
2005-10-12 20:40:40 +00:00
63b1419b74
Finally committing to the new scheduler. Still -sched=none by default.
...
llvm-svn: 23702
2005-10-12 18:29:35 +00:00
d00db257c7
Added graphviz/gv support for MF.
...
llvm-svn: 23700
2005-10-12 12:09:05 +00:00
192cd18f53
Fix (hopefully the last) issue where LSR is nondeterminstic. When pulling
...
out CSE's of base expressions it could build a result whose order was
nondet.
llvm-svn: 23698
2005-10-11 18:41:04 +00:00
5c9d63da31
Fix another problem where LSR was being nondeterminstic. Also remove elements
...
from the end of a vector instead of the beginning
llvm-svn: 23697
2005-10-11 18:30:57 +00:00
b7a3894e7c
Fix another lsr-is-nondeterministic case
...
llvm-svn: 23695
2005-10-11 18:17:57 +00:00
514f058be1
Fix a powerpc crash on CodeGen/Generic/llvm-ct-intrinsics.ll
...
llvm-svn: 23694
2005-10-11 17:56:34 +00:00
c38fb8e2a1
Add a canonicalization that got lost, fixing PowerPC/fold-li.ll:SUB
...
llvm-svn: 23693
2005-10-11 06:07:15 +00:00
cc6e53e6ee
clean up some corner cases
...
llvm-svn: 23692
2005-10-10 23:00:08 +00:00
04c737091f
Implement trivial DSE. If two stores are neighbors and store to the same
...
location, replace them with a new store of the last value. This occurs
in the same neighborhood in 197.parser, speeding it up about 1.5%
llvm-svn: 23691
2005-10-10 22:31:19 +00:00
e260ed8628
Add support for CombineTo, allowing the dag combiner to replace nodes with
...
multiple results.
Use this support to implement trivial store->load forwarding, implementing
CodeGen/PowerPC/store-load-fwd.ll. Though this is the most simple case and
can be extended in the future, it is still useful. For example, it speeds
up 197.parser by 6.2% by avoiding an LSU reject in xalloc:
stw r6, lo16(l5_end_of_array)(r2)
addi r2, r5, -4
stwx r5, r4, r2
- lwzx r5, r4, r2
- rlwinm r5, r5, 0, 0, 30
stwx r5, r4, r2
lwz r2, -4(r4)
ori r2, r2, 1
llvm-svn: 23690
2005-10-10 22:04:48 +00:00
6828ed9bfd
Teach the DAGCombiner several new tricks, teaching it how to turn
...
sext_inreg into zext_inreg based on the signbit (fires a lot), srem into
urem, etc.
llvm-svn: 23688
2005-10-10 21:26:48 +00:00
7730924067
Fix comment
...
llvm-svn: 23686
2005-10-10 16:52:03 +00:00
3d1d4a3d12
Add ISD::ADD to MaskedValueIsZero
...
llvm-svn: 23685
2005-10-10 16:51:40 +00:00
56e44a6da5
This function is now dead
...
llvm-svn: 23684
2005-10-10 16:49:22 +00:00
bcfebebf22
Enable Nate's excellent DAG combiner work by default. This allows the
...
removal of a bunch of ad-hoc and crufty code from SelectionDAG.cpp.
llvm-svn: 23682
2005-10-10 16:47:10 +00:00
d59a57a8d5
These definitions have been moved to common code.
...
llvm-svn: 23681
2005-10-10 06:01:00 +00:00
d83571bbf2
Pull DAG ISel generation nodes out of the PowerPC backend to where they
...
can be used by other targets. For those targets that want to use it,
have at. :)
llvm-svn: 23680
2005-10-10 06:00:30 +00:00
6a49b7cabb
add a todo for something I noticed
...
llvm-svn: 23679
2005-10-09 22:59:08 +00:00
1d3dc00674
(X & Y) & C == 0 if either X&C or Y&C are zero
...
llvm-svn: 23678
2005-10-09 22:12:36 +00:00
03b9eb506c
Make MaskedValueIsZero a bit more aggressive
...
llvm-svn: 23677
2005-10-09 22:08:50 +00:00
1dfb85c7af
This seems useful from the original patch that added the function. If there is a reason it is not useful on a RISC type target, let me know and I will pull it out
...
llvm-svn: 23676
2005-10-09 20:11:35 +00:00
62010c450f
Fix funky xcode indentation
...
llvm-svn: 23674
2005-10-09 06:36:35 +00:00
eb4be8b942
Hrm, you didn't see this.
...
llvm-svn: 23673
2005-10-09 06:24:02 +00:00
4ea0a3eaac
Fix a source of non-determinism in the backend: the order of processing
...
IV strides dependend on the pointer order of the strides in memory.
Non-determinism is bad.
llvm-svn: 23672
2005-10-09 06:20:55 +00:00
0832f2635a
When emiting a CopyFromReg and the source is already a vreg, do not bother
...
creating a new vreg and inserting a copy: just use the input vreg directly.
This speeds up the compile (e.g. about 5% on mesa with a debug build of llc)
by not adding a bunch of copies and vregs to be coallesced away. On mesa,
for example, this reduces the number of intervals from 168601 to 129040
going into the coallescer.
llvm-svn: 23671
2005-10-09 05:58:56 +00:00
89c7fa22b1
Disable formation of rlwinm instructions from SRA bases. This fixes
...
the 177.mesa failure from last night, and fixes the
CodeGen/PowerPC/2005-10-08-ArithmeticRotate.ll regression test I added.
If this code cannot be fixed, it should be removed for good, but I'll leave
it to Nate to decide its fate.
llvm-svn: 23670
2005-10-09 05:36:17 +00:00
967ce74980
Remove another unused file. Preparing for the great "enable i64 on ppc32"
...
merge, and using subtarget info for ptr size.
llvm-svn: 23668
2005-10-08 01:32:34 +00:00
af72457fc4
Remove a file that is no longer used
...
llvm-svn: 23666
2005-10-08 01:21:27 +00:00
2042aa5b92
Lo and behold, the last bits of SelectionDAG.cpp have been moved over.
...
llvm-svn: 23665
2005-10-08 00:29:44 +00:00
dae96f8881
When preselecting, favor things that have low depth to select first. This
...
is faster and uses less stack space. This reduces our stack requirement
enough to compile sixtrack, and though it's a hack, should be enough until
we switch to iterative isel
llvm-svn: 23664
2005-10-07 22:10:27 +00:00
be4bbca0ba
remove debugging code
...
llvm-svn: 23663
2005-10-07 15:31:26 +00:00
fb12624a3f
implement CodeGen/PowerPC/div-2.ll:test2-4 by propagating zero bits through
...
C-X's
llvm-svn: 23662
2005-10-07 15:30:32 +00:00
b27a4147d3
fix indentation
...
llvm-svn: 23660
2005-10-07 06:37:02 +00:00
5bcd0dd811
Turn sdivs into udivs when we can prove the sign bits are clear. This
...
implements CodeGen/PowerPC/div-2.ll
llvm-svn: 23659
2005-10-07 06:10:46 +00:00
572910c9a2
Remove useless variable.
...
llvm-svn: 23656
2005-10-07 05:28:29 +00:00
20a244577d
add a hack to work around broken VC++ scoping rules. Thx to JeffC for pointing
...
this out to me
llvm-svn: 23655
2005-10-07 05:23:36 +00:00
e373592258
Fix a CQ regression from my patch to split F32/F64 into seperate register
...
classes on PPC. We were emitting fmr instructions to do fp extensions, which
weren't getting coallesced. This fixes Regression/CodeGen/PowerPC/fpcopy.ll
llvm-svn: 23654
2005-10-07 05:00:52 +00:00
cd8b421799
Fix CodeGen/Generic/bool-to-double.ll
...
llvm-svn: 23652
2005-10-07 04:50:48 +00:00
318622fb9f
Pull out Call, reducing stack frame size from 6032 bytes to 5184 bytes.
...
llvm-svn: 23650
2005-10-06 19:07:45 +00:00
491b8294f4
Pull out setcc, this reduces stack frame size from 7520 to 6032 bytes
...
llvm-svn: 23649
2005-10-06 19:03:35 +00:00
502a36935e
Pull two more methods out, reducing stack frame size from 8224 -> 7520 bytes
...
llvm-svn: 23648
2005-10-06 18:56:10 +00:00
259e6c76f2
Add a recursive-iterative hybrid stage to attempt to reduce stack space, this
...
helps but not enough.
Start pulling cases out of PPC32DAGToDAGISel::Select. With GCC 4, this function
required 8512 bytes of stack space for each invocation (GCC 3 required less
than 700 bytes). Pulling this first function out gets us down to 8224. More
to come :(
llvm-svn: 23647
2005-10-06 18:45:51 +00:00
7bf8d06f02
silence a bogus GCC warning
...
llvm-svn: 23646
2005-10-06 17:39:10 +00:00
fabe55f155
Fix the LLC regressions on X86 last night. In particular, when undoing
...
previous copy elisions and we discover we need to reload a register, make
sure to use the regclass of the original register for the reload, not the
class of the current register. This avoid using 16-bit loads to reload 32-bit
values.
llvm-svn: 23645
2005-10-06 17:19:06 +00:00
e4c91fc9e8
This is suppose to work now
...
llvm-svn: 23644
2005-10-06 16:54:29 +00:00
332df13b9e
remove VAX compatibility instruction, we will never use this
...
llvm-svn: 23643
2005-10-06 16:53:32 +00:00
4bbbb9eed7
Make the legalizer completely non-recursive
...
llvm-svn: 23642
2005-10-06 01:20:27 +00:00
558beb3729
Let the combiner handle more cases
...
llvm-svn: 23641
2005-10-05 21:44:43 +00:00
f8221c5e2c
Remove some bad code from Legalize
...
llvm-svn: 23640
2005-10-05 21:44:10 +00:00
bd7df030d2
Check in some more DAGCombiner pieces
...
llvm-svn: 23639
2005-10-05 21:43:42 +00:00
55149d7835
Fix a bug in the local spiller, where we could take code like this:
...
store r12 -> [ss#2]
R3 = load [ss#1]
use R3
R3 = load [ss#2]
R4 = load [ss#1]
and turn it into this code:
store R12 -> [ss#2]
R3 = load [ss#1]
use R3
R3 = R12
R4 = R3 <- oops!
The problem was that promoting R3 = load[ss#2] to a copy missed the fact that
the instruction invalidated R3 at that point.
llvm-svn: 23638
2005-10-05 18:30:19 +00:00
05da0d966e
silence some warnings
...
llvm-svn: 23637
2005-10-05 17:15:09 +00:00
a49e16fefa
implement visitBR_CC so that PowerPC/inverted-bool-compares.ll passes
...
with the dag combiner. This speeds up espresso by 8%, reaching performance
parity with the dag-combiner-disabled llc.
llvm-svn: 23636
2005-10-05 06:47:48 +00:00
b11d15637a
fix some pastos
...
llvm-svn: 23635
2005-10-05 06:37:22 +00:00
06f1d0f73a
Add a new HandleNode class, which is used to handle (haha) cases in the
...
dead node elim and dag combiner passes where the root is potentially updated.
This fixes a fixme in the dag combiner.
llvm-svn: 23634
2005-10-05 06:35:28 +00:00
a6895d180e
Implement the code for PowerPC/inverted-bool-compares.ll, even though it
...
that testcase still does not pass with the dag combiner. This is because
not all forms of br* are folded yet.
Also, when we combine a node into another one, delete the node immediately
instead of waiting for the node to potentially come up in the future.
llvm-svn: 23632
2005-10-05 06:11:08 +00:00
6bd8fd09b6
make sure that -view-isel-dags is the input to the isel, not the input to
...
the second phase of dag combining
llvm-svn: 23631
2005-10-05 06:09:10 +00:00
746d50a01a
Fix a crash compiling Olden/tsp
...
llvm-svn: 23630
2005-10-05 04:45:43 +00:00
3b793c6521
refactor a bit of code.
...
When moving constant entries in 'Map' if the entry is the representative
constant for the abstractypemap, make sure to update it as well. This
fixes the bcreader failures from last night on several C++ apps.
llvm-svn: 23628
2005-10-04 21:35:50 +00:00
dff59118c6
Minor speedup to avoid array searches given a Use*. This speeds up bc reading
...
of the python test from 1:00 to 54s.
llvm-svn: 23627
2005-10-04 18:47:09 +00:00
7a1450dbc6
Change the signature of replaceUsesOfWithOnConstant. The bool was always
...
true dynamically. Finally, pass the Use* that replaceAllUsesWith has into
the method for future use.
llvm-svn: 23626
2005-10-04 18:13:04 +00:00
935aa922e3
For large constants (e.g. arrays and structs with many elements) just
...
creating the keys and doing comparisons to index into 'Map' takes a lot
of time. For these large constants, keep an inverse map so that 'remove'
and move operations are much faster.
This speeds up a release build of the bc reader on Eric's nasty python
bytecode file from 1:39 to 1:00s.
llvm-svn: 23624
2005-10-04 17:48:46 +00:00
5bbf60a5b6
minor cleanup/fastpath for the bcreader. This speeds up the bcreader
...
from 1:41 -> 1:39 on the large python .bc file in a release build.
llvm-svn: 23623
2005-10-04 16:52:46 +00:00
327d4298e1
Reverting to version - until problem isolated.
...
llvm-svn: 23622
2005-10-04 16:41:51 +00:00
d1a5bc8dbd
Add a forward def
...
llvm-svn: 23621
2005-10-04 05:09:20 +00:00
5da6908d65
Fix some faulty logic in the libcall inserter.
...
Since calls return more than one value, don't bail if one of their uses
happens to be a node that's not an MVT::Other when following the chain
from CALLSEQ_START to CALLSEQ_END.
Once we've found a CALLSEQ_START, we can just return; there's no need to
tail-recurse further up the graph.
Most importantly, just because something only has one use doesn't mean we
should use it's one use to follow from start to end. This faulty logic
caused us to follow a chain of one-use FP operations back to a much earlier
call, putting a cycle in the graph from a later start to an earlier end.
This is a better fix that reverting to the workaround committed earlier
today.
llvm-svn: 23620
2005-10-04 02:10:55 +00:00
8760ec73d8
implement the struct version of the array speedup, speeding up the
...
testcase a bit more from 1:48 -> 1.40.
llvm-svn: 23619
2005-10-04 01:17:50 +00:00
20b0754c41
Fix DemoteRegToStack on an invoke. This fixes PR634.
...
llvm-svn: 23618
2005-10-04 00:44:01 +00:00
54fb5002e5
Add back a workaround that fixes some breakages from chris's last change.
...
Neither of us have yet figured out why this code is necessary, but stuff
breaks if its not there. Still tracking this down...
llvm-svn: 23617
2005-10-04 00:37:37 +00:00
4c3b2b536c
Clean up the code a bit. Use isInstructionTriviallyDead to be more aggressive
...
and more correct than use_empty(). This fixes PR635 and
SimplifyCFG/2005-10-02-InvokeSimplify.ll
llvm-svn: 23616
2005-10-03 23:43:43 +00:00
b64419ac40
Change ConstantArray::replaceUsesOfWithOnConstant to attempt to update
...
constant arrays in place instead of reallocating them and replaceAllUsesOf'ing
the result. This speeds up a release build of the bcreader from:
136.987u 120.866s 4:24.38
to
49.790u 49.890s 1:40.14
... a 2.6x speedup parsing a large python bc file.
llvm-svn: 23614
2005-10-03 22:51:37 +00:00
c4062ba65f
move some methods, no other changes
...
llvm-svn: 23613
2005-10-03 21:58:36 +00:00
0144fadc17
minor microoptimizations
...
llvm-svn: 23612
2005-10-03 21:56:24 +00:00
bad09e71d0
Use a map to cache the ModuleType information, so we can do logarithmic
...
lookups instead of linear time lookups. This speeds up bc parsing of a
large file from
137.834u 118.256s 4:27.96
to
132.611u 114.436s 4:08.53
with a release build.
llvm-svn: 23611
2005-10-03 21:26:53 +00:00
409a6b204e
Refactor gathering node info and emission.
...
llvm-svn: 23610
2005-10-03 12:30:32 +00:00
57b21f9f10
clean up this code a bit, no functionality change
...
llvm-svn: 23609
2005-10-03 07:22:07 +00:00
afef68baff
Speed up the asm printer a lot by not printing formatted LLVM asm output
...
for globals
llvm-svn: 23608
2005-10-03 07:08:36 +00:00
5f096e2847
Break the body of the loop out into a new method
...
llvm-svn: 23606
2005-10-03 04:47:08 +00:00
f07a587c79
Make IVUseShouldUsePostIncValue more aggressive when the use is a PHI. In
...
particular, it should realize that phi's use their values in the pred block
not the phi block itself. This change turns our em3d loop from this:
_test:
cmpwi cr0, r4, 0
bgt cr0, LBB_test_2 ; entry.no_exit_crit_edge
LBB_test_1: ; entry.loopexit_crit_edge
li r2, 0
b LBB_test_6 ; loopexit
LBB_test_2: ; entry.no_exit_crit_edge
li r6, 0
LBB_test_3: ; no_exit
or r2, r6, r6
lwz r6, 0(r3)
cmpw cr0, r6, r5
beq cr0, LBB_test_6 ; loopexit
LBB_test_4: ; endif
addi r3, r3, 4
addi r6, r2, 1
cmpw cr0, r6, r4
blt cr0, LBB_test_3 ; no_exit
LBB_test_5: ; endif.loopexit.loopexit_crit_edge
addi r3, r2, 1
blr
LBB_test_6: ; loopexit
or r3, r2, r2
blr
into:
_test:
cmpwi cr0, r4, 0
bgt cr0, LBB_test_2 ; entry.no_exit_crit_edge
LBB_test_1: ; entry.loopexit_crit_edge
li r2, 0
b LBB_test_5 ; loopexit
LBB_test_2: ; entry.no_exit_crit_edge
li r6, 0
LBB_test_3: ; no_exit
lwz r2, 0(r3)
cmpw cr0, r2, r5
or r2, r6, r6
beq cr0, LBB_test_5 ; loopexit
LBB_test_4: ; endif
addi r3, r3, 4
addi r6, r6, 1
cmpw cr0, r6, r4
or r2, r6, r6
blt cr0, LBB_test_3 ; no_exit
LBB_test_5: ; loopexit
or r3, r2, r2
blr
Unfortunately, this is actually worse code, because the register coallescer
is getting confused somehow. If it were doing its job right, it could turn the
code into this:
_test:
cmpwi cr0, r4, 0
bgt cr0, LBB_test_2 ; entry.no_exit_crit_edge
LBB_test_1: ; entry.loopexit_crit_edge
li r6, 0
b LBB_test_5 ; loopexit
LBB_test_2: ; entry.no_exit_crit_edge
li r6, 0
LBB_test_3: ; no_exit
lwz r2, 0(r3)
cmpw cr0, r2, r5
beq cr0, LBB_test_5 ; loopexit
LBB_test_4: ; endif
addi r3, r3, 4
addi r6, r6, 1
cmpw cr0, r6, r4
blt cr0, LBB_test_3 ; no_exit
LBB_test_5: ; loopexit
or r3, r6, r6
blr
... which I'll work on next. :)
llvm-svn: 23604
2005-10-03 02:50:05 +00:00
e4ed42a426
Refactor some code into a function
...
llvm-svn: 23603
2005-10-03 01:04:44 +00:00
360928dbed
This break is bogus and I have no idea why it was there. Basically it prevents
...
memoizing code when IV's are used by phinodes outside of loops. In a simple
example, we were getting this code before (note that r6 and r7 are isomorphic
IV's):
li r6, 0
or r7, r6, r6
LBB_test_3: ; no_exit
lwz r2, 0(r3)
cmpw cr0, r2, r5
or r2, r7, r7
beq cr0, LBB_test_5 ; loopexit
LBB_test_4: ; endif
addi r2, r7, 1
addi r7, r7, 1
addi r3, r3, 4
addi r6, r6, 1
cmpw cr0, r6, r4
blt cr0, LBB_test_3 ; no_exit
Now we get:
li r6, 0
LBB_test_3: ; no_exit
or r2, r6, r6
lwz r6, 0(r3)
cmpw cr0, r6, r5
beq cr0, LBB_test_6 ; loopexit
LBB_test_4: ; endif
addi r3, r3, 4
addi r6, r2, 1
cmpw cr0, r6, r4
blt cr0, LBB_test_3 ; no_exit
this was noticed in em3d.
llvm-svn: 23602
2005-10-03 00:37:33 +00:00
8fcce170cf
when checking if we should move a split edge block outside of a loop,
...
check the presplit pred, not the post-split pred. This was causing us
to make the wrong decision in some cases, leaving the critical edge block
in the loop.
llvm-svn: 23601
2005-10-03 00:31:52 +00:00
9cfccfb517
Fix a problem where the legalizer would run out of stack space on extremely
...
large basic blocks because it was purely recursive. This switches it to an
iterative/recursive hybrid.
llvm-svn: 23596
2005-10-02 17:49:46 +00:00
7f718e61e8
silence a bogus warning
...
llvm-svn: 23595
2005-10-02 16:30:51 +00:00
Chris Lattner