Brian Gaeke
e383a14960
Use C++ math header instead of C version.
...
llvm-svn: 8648
2003-09-21 03:57:37 +00:00
Brian Gaeke
32cd554853
Erase now-unused prototypes.
...
llvm-svn: 8647
2003-09-21 02:51:00 +00:00
Brian Gaeke
20c888fa9f
Rearrange #includes ... since there are fewer now I guess it's a win.
...
(I also zapped printMachineCode() and printLabel() at the previous checkin,
but forgot to mention it.)
llvm-svn: 8646
2003-09-21 02:50:21 +00:00
Brian Gaeke
3a0a5fc1b3
Standardize the names of include guards.
...
llvm-svn: 8645
2003-09-21 02:31:37 +00:00
Brian Gaeke
58dabb4406
Standardize the names of include guards.
...
Remove more excess whitespace.
llvm-svn: 8644
2003-09-21 02:31:25 +00:00
Brian Gaeke
73d10dc47b
Standardize the names of include guards.
...
Fix typos in file header comment.
llvm-svn: 8643
2003-09-21 02:31:15 +00:00
Brian Gaeke
43593b8cd0
I tried to standardize the formatting and tidy up the huge amount of
...
excess whitespace a little. Also improved some comments.
llvm-svn: 8642
2003-09-21 02:24:09 +00:00
Brian Gaeke
e1061018bf
Convert PhyRegAlloc into a proper pass.
...
PhyRegAlloc.cpp:
Don't include TargetMachine.h or TargetRegInfo.h, because these are provided
by PhyRegAlloc.h.
Merge class RegisterAllocator into class PhyRegAlloc.
Simplify & move ctor, dtor to PhyRegAlloc.h.
Make some of PhyRegAlloc's reference members into pointer members,
so they can be more easily messed with.
MarkAllocatedRegs() becomes a member method, with fewer args.
PhyRegAlloc.h:
Include Pass.h, TargetMachine.h and TargetRegInfo.h. Don't declare
TargetRegInfo forward.
Give AddedInstrns the obvious clear() method.
Make some of PhyRegAlloc's reference members into pointer members,
so they can be more easily messed with.
Add prototype for markAllocatedRegs().
Remove unused inline void constructLiveRanges().
llvm-svn: 8641
2003-09-21 01:23:46 +00:00
Misha Brukman
02fe6b7683
Fixed spelling.
...
llvm-svn: 8588
2003-09-17 21:34:23 +00:00
Brian Gaeke
666b18f1a6
Fix typo in comment. Take out some random whitespace.
...
(Partial merge from my working file)
llvm-svn: 8564
2003-09-16 15:38:05 +00:00
Brian Gaeke
c8a9ec01b6
Edit comment for accuracy
...
llvm-svn: 8562
2003-09-16 15:36:50 +00:00
Vikram S. Adve
8579a9a38c
Add flag to control whether or not delay slots are filled during
...
instruction scheduling (this is off by default).
llvm-svn: 8553
2003-09-16 05:55:15 +00:00
Brian Gaeke
75ed4b8831
Fix typos in comments.
...
llvm-svn: 8523
2003-09-15 05:28:42 +00:00
Misha Brukman
acda7df68b
Fixed spelling and grammar.
...
llvm-svn: 8489
2003-09-11 22:34:13 +00:00
Chris Lattner
5718a6bf99
Don't build dead directories
...
llvm-svn: 8308
2003-09-01 20:34:15 +00:00
Chris Lattner
c87312a858
Remove dead library makefile
...
llvm-svn: 8304
2003-09-01 20:29:43 +00:00
Chris Lattner
a5b78c68d9
Remove makefile for dead library
...
llvm-svn: 8303
2003-09-01 20:26:52 +00:00
Chris Lattner
eefb565449
LiveRange.h is now in lib/CodeGen/RegAlloc
...
llvm-svn: 8299
2003-09-01 20:17:13 +00:00
Chris Lattner
e80612a28e
LiveRangeInfo got moved into the lib/CodeGen/RegAlloc directory
...
llvm-svn: 8297
2003-09-01 20:12:17 +00:00
Chris Lattner
f1ab45bdf5
PhyRegAlloc.h got moved to lib/CodeGen/RegAlloc
...
llvm-svn: 8296
2003-09-01 20:09:04 +00:00
Chris Lattner
7127065f24
Move IGNode from public include directory to here. Minor cleanups like adding std:: namespace qualifiers
...
llvm-svn: 8295
2003-09-01 20:05:47 +00:00
John Criswell
a4b09fe071
Fixed two double free bugs that caused llc to segfault or run forever.
...
llvm-svn: 8191
2003-08-28 21:43:17 +00:00
Tanya Lattner
190b7a86ba
Removing README
...
llvm-svn: 8180
2003-08-28 17:17:59 +00:00
Tanya Lattner
7efb18f49c
Putting my revised version of ModuloScheduling in cvs. This is not complete...
...
llvm-svn: 8179
2003-08-28 17:12:14 +00:00
Tanya Lattner
89860151b9
Moved index into BB to common graph class because its needed by ModuloSchedGraph.
...
llvm-svn: 8174
2003-08-28 15:30:40 +00:00
Tanya Lattner
cf8851eb20
Added/removed header file
...
llvm-svn: 8160
2003-08-27 15:12:24 +00:00
Tanya Lattner
9af699b885
*** empty log message ***
...
llvm-svn: 8153
2003-08-27 02:42:58 +00:00
Tanya Lattner
cc85d4544f
First version of SchedGraph common class and refactoring of SchedGraph.
...
llvm-svn: 8148
2003-08-25 22:42:20 +00:00
Chris Lattner
e6235443a5
Fix bug: Jello/2003-08-23-RegisterAllocatePhysReg.ll
...
llvm-svn: 8095
2003-08-23 23:49:42 +00:00
Misha Brukman
be372b91e1
The word `dependent' has no `a'.
...
llvm-svn: 8030
2003-08-21 22:14:26 +00:00
Chris Lattner
a73b95821a
Fix spello
...
llvm-svn: 8029
2003-08-21 22:05:57 +00:00
Misha Brukman
7eb05a170a
Spell `necessary' correctly.
...
llvm-svn: 7944
2003-08-18 14:43:39 +00:00
Chris Lattner
931947db18
Fix bug: Jello/2003-08-15-AllocaAssertion.ll
...
llvm-svn: 7916
2003-08-17 18:01:15 +00:00
Brian Gaeke
91e16e750b
Fix typo in comment
...
llvm-svn: 7906
2003-08-15 21:19:25 +00:00
Chris Lattner
3b5b633c77
Remove uses of the NonCopyable class, to make the doxygen output look better
...
llvm-svn: 7880
2003-08-15 05:20:06 +00:00
Chris Lattner
0605c232b7
rename selection directory and library to SelectionDAG
...
llvm-svn: 7877
2003-08-15 04:55:22 +00:00
Chris Lattner
e81de41edf
Add a bunch of new node types, etc
...
llvm-svn: 7875
2003-08-15 04:53:16 +00:00
Brian Gaeke
8c14ba96ca
Factory methods for function passes now return type FunctionPass *.
...
llvm-svn: 7839
2003-08-14 06:09:32 +00:00
Brian Gaeke
cbd3a40626
Factory methods for function passes now return type FunctionPass *.
...
Get rid of RegisterLLC, which can't handle FunctionPasses anyway.
llvm-svn: 7836
2003-08-14 06:04:49 +00:00
Brian Gaeke
89207943a1
Factory methods for FunctionPasses now return type FunctionPass *.
...
llvm-svn: 7823
2003-08-13 18:18:15 +00:00
Chris Lattner
bb9be9ddbc
Mapping directory no longer exists
...
llvm-svn: 7801
2003-08-13 02:37:24 +00:00
Chris Lattner
e9643bb118
Obsolete file
...
llvm-svn: 7799
2003-08-13 02:27:13 +00:00
Vikram S. Adve
7dc5b6707c
For instructions in a delay slot of another instruction,
...
we no longer need to find the live-before set of the delayed
branch since that set is now included the live-before/after
set of the instructions in each delay slot. Just assert that instead.
llvm-svn: 7796
2003-08-12 22:22:24 +00:00
Chris Lattner
2c2062cdba
Build the SelectionDAG library
...
llvm-svn: 7718
2003-08-11 14:57:48 +00:00
Chris Lattner
600d308853
Initial checkin of SelectionDAG implementation. This is still rough and
...
unfinished
llvm-svn: 7717
2003-08-11 14:57:33 +00:00
Vikram S. Adve
da92f366c7
Fix assertion in MachineInstr::substituteValue().
...
llvm-svn: 7675
2003-08-07 15:01:48 +00:00
Chris Lattner
30e987470f
Use a new local data structure instead of the MachineInstr::regsUsed set
...
llvm-svn: 7621
2003-08-05 22:11:13 +00:00
Chris Lattner
92f5fb598c
Add a map
...
llvm-svn: 7620
2003-08-05 22:09:31 +00:00
Chris Lattner
e62a2a76e5
Minor cleanups
...
llvm-svn: 7619
2003-08-05 22:03:27 +00:00
Chris Lattner
b05d3508d6
Physical registers no longer live in the regsUsed set for each machine instr
...
llvm-svn: 7618
2003-08-05 21:55:58 +00:00
Chris Lattner
020b544cbc
Do not insert physical regsiters into the regsUsed set
...
llvm-svn: 7617
2003-08-05 21:55:20 +00:00
Chris Lattner
cd4f4320b0
All callers of these methods actually wanted them to preserve the flags,
...
so get rid of the def/use parameters that were getting passed in.
**** This now changes the semantics of these methods to preserve the flags,
not clobber them!
llvm-svn: 7602
2003-08-05 16:58:46 +00:00
Chris Lattner
92a199dca7
Fix bugs handling ESP in alloca references
...
llvm-svn: 7591
2003-08-05 04:13:58 +00:00
Chris Lattner
506fa6843e
Revert previous change, and be really anal about what physical registers can do.
...
llvm-svn: 7588
2003-08-05 00:49:09 +00:00
Chris Lattner
4b637cc666
Don't bother calculating info unless its needed. May reduce number of stack slots created.
...
llvm-svn: 7584
2003-08-04 23:42:37 +00:00
Chris Lattner
815b85e3ba
* Fix spelling of 'necessary'
...
* Add a lot more DEBUG output, which is better structured than before
* Fix bug: Jello/2003-08-04-PhysRegLiveFailure.llx
llvm-svn: 7583
2003-08-04 23:36:39 +00:00
Chris Lattner
41a894de77
Simplify code, eliminating the need for the X86 isVoid target instr flag
...
llvm-svn: 7534
2003-08-03 21:51:45 +00:00
Chris Lattner
74e4e9b44f
Set debug types
...
llvm-svn: 7533
2003-08-03 21:47:31 +00:00
Chris Lattner
1789d23990
Remove using decl
...
llvm-svn: 7531
2003-08-03 20:24:29 +00:00
Chris Lattner
6cce665888
Wrap at 80 columns
...
llvm-svn: 7503
2003-08-03 13:49:03 +00:00
Chris Lattner
1007f033d4
Move DEBUG to Debug.h
...
llvm-svn: 7497
2003-08-01 22:21:34 +00:00
Vikram S. Adve
9143f1962e
All constant-evaluation code now unified into
...
TargetInstrInfo::ConvertConstantToIntType().
llvm-svn: 7390
2003-07-29 19:50:12 +00:00
Vikram S. Adve
c9cb319bcb
1. Bug fix: Don't use branch operand reg. as temp. reg. when
...
spilling values used by an instruction in the delay slot of the branch
(which will eventually be moved before the branch).
2. Bug fix: Delete the delay slot instr, not the branch instr, when
moving delay slot instr. out!!!!
3. Move code to insert caller-saves moved here from SparcRegInfo:
it is now machine-independent.
llvm-svn: 7389
2003-07-29 19:49:21 +00:00
Vikram S. Adve
e2ef34a818
Add const version of getLiveRangeForValue().
...
llvm-svn: 7386
2003-07-29 19:38:22 +00:00
Vikram S. Adve
91e75d87d2
Code to insert caller-saves moved here from SparcRegInfo: it is now
...
machine-independent.
Fix problem with using branch operand reg. as temp. reg. when
spilling values used by an instruction in the delay slot of the branch
(which will eventually be moved before the branch).
llvm-svn: 7385
2003-07-29 19:37:41 +00:00
Chris Lattner
0c8de4bfca
Making this code const-correct would be a pain, so I'll hack it.
...
llvm-svn: 7350
2003-07-26 23:29:51 +00:00
Chris Lattner
414832fea6
Const correctness fixes
...
llvm-svn: 7349
2003-07-26 23:24:56 +00:00
Chris Lattner
0ed86aca71
Be const correct
...
llvm-svn: 7348
2003-07-26 23:23:41 +00:00
Chris Lattner
1316383267
Hrm, another necesary one :(
...
llvm-svn: 7347
2003-07-26 23:22:19 +00:00
Chris Lattner
824398ec6d
Remove #include
...
llvm-svn: 7342
2003-07-26 23:01:04 +00:00
Chris Lattner
981e585021
Remove extraneous #includes
...
llvm-svn: 7341
2003-07-26 23:00:29 +00:00
Vikram S. Adve
45766ab682
(1) Change the way unused regs. are marked and found to consider regType
...
info (since multiple reg types may share the same reg class).
(2) Remove machine-specific regalloc. methods that are no longer needed.
In particular, arguments and return value from a call do not need
machine-specific code for allocation.
(3) Rename TargetRegInfo::getRegType variants to avoid unintentional
overloading when an include file is omitted.
llvm-svn: 7329
2003-07-25 21:06:09 +00:00
Vikram S. Adve
abcd8d75ff
Remove unused field. Change the way unused regs. are marked and
...
found to consider regType info (since multiple reg types may share
the same reg class, e.g., single and double on Sparc).
llvm-svn: 7327
2003-07-25 21:00:13 +00:00
Chris Lattner
79f22fe02f
Remove unnecessary casts
...
llvm-svn: 7250
2003-07-23 15:17:51 +00:00
Chris Lattner
b976da9ecf
Random cleanups
...
llvm-svn: 7247
2003-07-23 14:59:40 +00:00
Chris Lattner
0470412961
Remove using decl
...
llvm-svn: 7246
2003-07-23 14:55:59 +00:00
Vikram S. Adve
e2e50f2880
Values stored in CallArgsDescriptor cannot be const.
...
llvm-svn: 7156
2003-07-10 19:46:15 +00:00
Vikram S. Adve
abf331db03
isMarkedForSpill() should be const.
...
llvm-svn: 7155
2003-07-10 19:45:28 +00:00
Vikram S. Adve
689adb19b0
Change interface to MachineInstr::substituteValue to specify more precisely
...
which args can be substituted: defsOnly, defsAndUses or usesOnly.
llvm-svn: 7154
2003-07-10 19:45:07 +00:00
Vikram S. Adve
39587d6264
Print out all neighbors in interference graph, not just higher-numbered ones.
...
llvm-svn: 7153
2003-07-10 19:43:33 +00:00
Vikram S. Adve
5224b19deb
Several fixes to handling of int CC register:
...
(1) An int CC live range must be spilled if there are any interferences,
even if no other "neighbour" in the interf. graph has been allocated
that reg. yet. This is actually true of any class with only one reg!
(2) SparcIntCCRegClass::colorIGNode sets the color even if the LR must
be spilled so that the machine-independent spill code doesn't have to
make the machine-dependent decision of which CC name to use based on
operand type: %xcc or %icc. (These are two halves of the same
register.)
(3) LR->isMarkedForSpill() is no longer the same as LR->hasColor().
These should never have been the same, and this is necessary now for #2 .
(4) All RDCCR and WRCCR instructions are directly generated with the
phony number for %ccr so that EmitAssembly/EmitBinary doesn't have to
deal with this.
llvm-svn: 7152
2003-07-10 19:42:55 +00:00
Vikram S. Adve
3bb921e8df
Choose register instead of immediate for ConstantExpr in ChooseRegOrImmed.
...
llvm-svn: 7112
2003-07-06 20:33:21 +00:00
Vikram S. Adve
1fce4cfa95
Minor beautification: fold a couple of lines of code.
...
llvm-svn: 7054
2003-07-02 01:24:00 +00:00
Vikram S. Adve
fa1dde06aa
A def. operand of a machine instruction may be an ordinary Value*,
...
not just an Instruction*, at least in one unfortunate case:
the first operand to the va_arg instruction.
Modify ValueToDefVecMap to map from Value*, not Instruction*.
llvm-svn: 7052
2003-07-02 01:16:01 +00:00
John Criswell
3ef61afb76
Merged in autoconf branch. This provides configuration via the autoconf
...
system.
llvm-svn: 7014
2003-06-30 21:59:07 +00:00
Chris Lattner
52de05c6b3
Remove a ton of extraneous #includes
...
llvm-svn: 6842
2003-06-22 03:08:05 +00:00
Chris Lattner
55491774bb
Actually, change it to use explicit new/delete, which is more likely to be
...
optimized INTO an alloca
llvm-svn: 6727
2003-06-16 22:29:09 +00:00
Chris Lattner
5b7e3cae42
Remove two using decls
...
Remove usage of alloca
llvm-svn: 6725
2003-06-16 22:18:28 +00:00
Brian Gaeke
7a719ed20c
Isolate machine-dependent use of <alloca.h> in "Support/Alloca.h",
...
so that we can easily change its use to be conditional on the result of
an autoconf test later.
llvm-svn: 6723
2003-06-16 21:54:01 +00:00
John Criswell
cfac736363
Included assert.h so that the code compiles under newer versions of GCC.
...
llvm-svn: 6682
2003-06-11 14:01:36 +00:00
Guochun Shi
c40f66c928
add some comments
...
add a function ModuloScheduling::dumpFinalSchedule() to print out final schedule
llvm-svn: 6677
2003-06-10 20:04:30 +00:00
Guochun Shi
f6b88e55ed
add an brief instruction what this pass is
...
llvm-svn: 6676
2003-06-10 20:03:39 +00:00
Guochun Shi
d2656536f5
a simple introduction to this pass
...
llvm-svn: 6675
2003-06-10 20:02:16 +00:00
Guochun Shi
9766f8c3a2
cleaned code
...
add some comments
llvm-svn: 6674
2003-06-10 19:09:00 +00:00
Guochun Shi
2ee8c115d8
delete useless functions
...
add comment
llvm-svn: 6673
2003-06-08 23:16:07 +00:00
Guochun Shi
1ecd0e0228
change DEBUG to DEBUG_PRINT
...
llvm-svn: 6672
2003-06-08 20:40:47 +00:00
Misha Brukman
366494ab0d
Do not hastily change the Opcode from 'r' to 'i' type if we're not actually
...
SETTING the operand to be an immediate or have verified that one of the operands
is really a SignExtended or Unextended immediate value already, which warrants
an 'i' opcode.
llvm-svn: 6662
2003-06-07 02:34:43 +00:00
Chris Lattner
a7c5e0fba3
Fix bug: Jello/2003-06-04-bzip2-bug.ll
...
llvm-svn: 6624
2003-06-05 17:15:04 +00:00
Misha Brukman
4e7bad01ff
I have finally seen the light. The code to change the opcode must live higher in
...
the loop, and in both cases. In the first case, it is a VReg that is a constant
so it may be actually converted to a constant. In the second case, it is already
a constant, but then if it doesn't change its type (e.g. to become a register
and have the value loaded from memory if it is too large to live in its
instruction field), we must change the opcode BEFORE the 'continue', otherwise
we miss the opportunity.
llvm-svn: 6602
2003-06-04 04:54:06 +00:00
Misha Brukman
a6c3f896da
Pass through the emitConstantPool() call to the real emitter.
...
llvm-svn: 6590
2003-06-03 20:00:49 +00:00