Owen Anderson
fe44aedf8a
Add my most recent work.
...
llvm-svn: 28604
2006-05-31 22:15:45 +00:00
Evan Cheng
cf70c7f42d
Sign extender
...
llvm-svn: 28603
2006-05-31 22:05:11 +00:00
Reid Spencer
d8df61a4d0
Squelch this warning:
...
/bzlib.c:126: warning: string length `1056' is greater than the length `509' ISO
C89 compilers are required to support
llvm-svn: 28602
2006-05-31 21:53:42 +00:00
Chris Lattner
9b32cf59e0
Fix utostr once and for all, by making there only be one function named
...
utostr. To keep the efficiency in the 32-bit case, make it check to see if
the value is 32-bits and if so switch over to the faster 32-bit case.
llvm-svn: 28601
2006-05-31 21:25:50 +00:00
Chris Lattner
1df0e98ac2
Swap the order of operands created here. For +&|^, the order doesn't matter,
...
but for sub, it really does! Fix fixes a miscompilation of fibheap_cut in
llvmgcc4.
llvm-svn: 28600
2006-05-31 21:14:00 +00:00
Owen Anderson
dad8c57340
Extract a huge loop into a helper method. Fix a few iterator-invalidation bugs.
...
llvm-svn: 28599
2006-05-31 20:55:06 +00:00
Andrew Lenharth
440dcd03fa
4 billion names is enough for anyone. And really fix the build on alpha this time
...
llvm-svn: 28598
2006-05-31 20:40:36 +00:00
Andrew Lenharth
53250e7fcb
fix utostr
...
llvm-svn: 28597
2006-05-31 20:18:56 +00:00
Andrew Lenharth
0d4c10eae6
Fix build breakage on alpha, without causing it on x86. as a bonus, all platforms can invent the same number of unique names now
...
llvm-svn: 28596
2006-05-31 20:18:28 +00:00
Andrew Lenharth
40d4af63f2
revert for now
...
llvm-svn: 28595
2006-05-31 19:16:26 +00:00
Evan Cheng
25e44e008d
Rename instructions for consistency sake.
...
llvm-svn: 28594
2006-05-31 19:00:07 +00:00
Andrew Lenharth
26baab1593
make 64-bit safe and fix the build on alpha
...
llvm-svn: 28593
2006-05-31 18:56:42 +00:00
Evan Cheng
0c0996a97b
commuteInstruction() does not always create a new MI!
...
llvm-svn: 28592
2006-05-31 18:03:39 +00:00
Reid Spencer
5dd0111188
Add a brief description for the tblgen program. More detail is needed but
...
the current author is not the person to provide it. Now that the file
exists, perhaps others will chime in and embellish.
llvm-svn: 28591
2006-05-31 17:54:39 +00:00
Reid Spencer
a9355fa5d8
Update the documentation for llvm2cpp after the -gen-* options were added.
...
llvm-svn: 28590
2006-05-31 17:32:21 +00:00
Reid Spencer
de2daad0ac
Major reorganization and extension of the code. The diff on this will be a
...
mess as functions were moved around into a better ordering. The code was
extended to provide various -gen-* options to better control what the
generated output should be. Currently it is possible to generate entire
modules (three different ways), functions, global variables, and types.
llvm-svn: 28589
2006-05-31 17:31:38 +00:00
Reid Spencer
9fef163d19
Make the getNamedFunction and getNamedGlobal methods be const. They don't
...
change the module in any way and we should enforce that.
llvm-svn: 28588
2006-05-31 16:40:28 +00:00
Vladimir Prus
735e3f76a8
Clarify type naming.
...
llvm-svn: 28587
2006-05-31 16:03:20 +00:00
Vladimir Prus
c1eae29b91
Improve InstVisitor docs.
...
llvm-svn: 28586
2006-05-31 15:30:18 +00:00
Evan Cheng
9d91caa053
Eliminate a memory leak.
...
llvm-svn: 28585
2006-05-31 07:13:03 +00:00
Evan Cheng
64d2846017
visitVBinOp: Can't fold divide by zero!
...
llvm-svn: 28584
2006-05-31 06:08:35 +00:00
Reid Spencer
03977ec9b1
Don't generate module definitions when the -fragment option is given.
...
llvm-svn: 28583
2006-05-31 04:43:19 +00:00
Evan Cheng
8abf45e22d
Select vector_shuffle v1, undef <2, 3, ?, ?> to MOVHLPS.
...
llvm-svn: 28582
2006-05-31 00:51:37 +00:00
Evan Cheng
550cb663e8
Remove dead code.
...
llvm-svn: 28581
2006-05-31 00:50:42 +00:00
Evan Cheng
6821bbb1ea
Update vector extract test cases.
...
llvm-svn: 28580
2006-05-31 00:48:09 +00:00
Evan Cheng
ddced95d8f
A new entry
...
llvm-svn: 28579
2006-05-30 23:56:31 +00:00
Evan Cheng
57399704b3
MAXP{D|S} and MINP{D|S} are commutable.
...
llvm-svn: 28578
2006-05-30 23:47:30 +00:00
Evan Cheng
c0f90bef47
Commute shufps / shufpd.
...
llvm-svn: 28577
2006-05-30 23:34:30 +00:00
Reid Spencer
b5ddb66ce0
1. No need to thwart this test with an environment variable. Turning it off
...
is the default and handled by the makefile system and runtest
2. Redirect stderr of llvm-as and llvm2cpp so that warning messages about
instrinsics don't cause Tcl to report the run as failed.
llvm-svn: 28576
2006-05-30 23:07:17 +00:00
Evan Cheng
f21045a5cd
Somehow I lost a condition when I was shuffling some code around. Anyway,
...
only transform a shufps to pshufd when the first two operands are the same.
llvm-svn: 28575
2006-05-30 22:13:36 +00:00
Evan Cheng
c8c172eaae
Fix a build breaker.
...
llvm-svn: 28574
2006-05-30 21:45:53 +00:00
Evan Cheng
a4fc5b8699
Oops. PSHUFD is only available with SSE2.
...
llvm-svn: 28573
2006-05-30 21:30:59 +00:00
Chris Lattner
a5d4587296
Add a note
...
llvm-svn: 28572
2006-05-30 21:29:15 +00:00
Chris Lattner
b9342afa56
Always reserve space for 8 spilled GPRs. GCC apparently assumes that this
...
space will be available, even if the callee isn't varargs.
llvm-svn: 28571
2006-05-30 21:21:04 +00:00
Reid Spencer
c3b9370754
llvm2cpp is ready to be compiled so add it to the makefile, but make it
...
optional.
llvm-svn: 28570
2006-05-30 21:20:55 +00:00
Reid Spencer
ad7da68343
Add the new command line arguments.
...
llvm-svn: 28569
2006-05-30 21:19:29 +00:00
Reid Spencer
30945ca559
Fix more bugs. This version now passes all of the Feature test except for
...
a floating point conversion problem with NAN in intrinsics.ll. llvm2cpp
makes an attempt to provide the correct conversion, based on the
implementation in the CBackend writer, but it doesn't get NAN correct.
llvm-svn: 28568
2006-05-30 21:18:23 +00:00
Evan Cheng
baace007a3
Added a test case for parameter passing of vector values.
...
llvm-svn: 28567
2006-05-30 20:37:00 +00:00
Evan Cheng
1ec0e4233e
Fix the test failure on non-Darwin targets.
...
llvm-svn: 28566
2006-05-30 20:35:46 +00:00
Evan Cheng
66f849bd7b
Allow shufps x, x, mask to be converted to pshufd x, mask to save a move.
...
llvm-svn: 28565
2006-05-30 20:26:50 +00:00
Evan Cheng
b33e54ead7
Remove bogus comment.
...
llvm-svn: 28564
2006-05-30 20:24:48 +00:00
Reid Spencer
f9aa688f5b
Add llvm2cpp program.
...
llvm-svn: 28563
2006-05-30 19:56:31 +00:00
Reid Spencer
82ebabafde
Provide a simpler interface for getting a ConstantArray from a character
...
string. Instead of specifying the length, just specify whether the user
wants a terminating null or not. The default is "true" to retain the same
behavior as previously provided by this function.
llvm-svn: 28562
2006-05-30 18:15:07 +00:00
Evan Cheng
d12c97d23a
Make sure the register pressure reduction schedulers work for non-uniform
...
latency targets, e.g. PPC32.
llvm-svn: 28561
2006-05-30 18:05:39 +00:00
Evan Cheng
61e9f0d680
When a priority_queue is empty, the behavior of top() operator is
...
non-deterministic. Returns NULL when it's empty!
llvm-svn: 28560
2006-05-30 18:04:34 +00:00
Rafael Espindola
5bc60da112
Expand ret into "CopyToReg;BRIND"
...
llvm-svn: 28559
2006-05-30 17:33:19 +00:00
Chris Lattner
11c25cfa13
Enable -fno-use-cxa-atexit on darwin/ppc also.
...
llvm-svn: 28558
2006-05-30 16:38:06 +00:00
Reid Spencer
b0cffafb59
Undo a patch that breaks llvm-as because the warning message is written to
...
stdout when the output of llvm-as is also written to stdout. We'll have to
fix tcl some other way.
llvm-svn: 28557
2006-05-30 16:34:59 +00:00
Reid Spencer
b5c64fc3b6
Write the WARNING message to cout instead of cerr. Writing to cerr causes
...
Tcl to claim that the program had an error and thus produces errors in
the dejagnu testing when its really just a warning.
llvm-svn: 28556
2006-05-30 16:05:59 +00:00
Vladimir Prus
413441b9c9
Make doc comment visible in doxygen output. Clarify Type construction.
...
llvm-svn: 28555
2006-05-30 15:49:30 +00:00
Reid Spencer
37cf1765ed
Fix many small bugs in llvm2cpp. This patch gets llvm2cpp working with
...
everything except PHI nodes and one odd recurse/opaque type situation.
PHI nodes forward reference INSTRUCTIONS (aaaaaaaahhhhhhh!) :)
llvm-svn: 28554
2006-05-30 10:21:41 +00:00
Reid Spencer
84504f215b
Properly document the second form of ConstArray::get()
...
llvm-svn: 28553
2006-05-30 08:26:13 +00:00
Reid Spencer
6f61453ff8
Adjust the interface to ConstantArray::get. The previous
...
implementation always added a null byte to the end of the string. It turns
out that this is not always wanted. By adding a length parameter we preserve
this behavior when length==0 (default value) but also allow other lengths
(not null terminated) to be created.
llvm-svn: 28552
2006-05-30 08:23:18 +00:00
Evan Cheng
02420144ab
Add a note about integer multiplication by constants.
...
llvm-svn: 28551
2006-05-30 07:37:37 +00:00
Evan Cheng
734e1e241b
A addressing mode folding enhancement:
...
Fold c2 in (x << c1) | c2 where (c2 < c1)
e.g.
int test(int x) {
return (x << 3) + 7;
}
This can be codegen'd as:
leal 7(,%eax,8), %eax
llvm-svn: 28550
2006-05-30 06:59:36 +00:00
Evan Cheng
905e88caaa
Add a lea instruction selection test case.
...
llvm-svn: 28549
2006-05-30 06:53:55 +00:00
Evan Cheng
749138582e
Some new entries about truncate / anyext
...
llvm-svn: 28548
2006-05-30 06:23:50 +00:00
Reid Spencer
c267698f23
First complete version of llvm2cpp that doesn't crash on any of the Feature
...
tests. The output in a few cases still doesn't compile, however.
llvm-svn: 28547
2006-05-30 03:43:49 +00:00
Andrew Lenharth
c3cff44880
move calltarget to dsa
...
llvm-svn: 28546
2006-05-29 23:39:48 +00:00
Andrew Lenharth
e465381401
Since there was interest on the mailing list, this is a utility pass that
...
uses DSA to make find targets of calls. It provides a very convinient
interface to DSA results to do things with indirect calls, such as
write a devirtualizer (which I have and may commit one of these days).
llvm-svn: 28545
2006-05-29 22:58:38 +00:00
Chris Lattner
d65928994a
Silly cleanup
...
llvm-svn: 28544
2006-05-29 18:52:52 +00:00
Chris Lattner
dc0b3afcdd
silly cleanup
...
llvm-svn: 28543
2006-05-29 18:52:05 +00:00
Reid Spencer
131ca2869c
Fix a bug with diffing the wrong files. Make output more readable.
...
llvm-svn: 28542
2006-05-29 18:09:38 +00:00
Reid Spencer
c194e7e843
Next batch of implementation:
...
1. Get rid of old AsmWriter cruft that's not needed.
2. Implement several instructions. Enough to get by globalvars.ll and
alignment.ll in the Feature test suite.
3. Handle constants properly (don't repeat definitions).
4. Make the output compatible with llvm-dis for diff purposes.
llvm-svn: 28541
2006-05-29 18:08:06 +00:00
Reid Spencer
4967fa722d
Fix file header comment.
...
llvm-svn: 28540
2006-05-29 18:06:28 +00:00
Reid Spencer
fe361813aa
Remove temporary testing rules.
...
llvm-svn: 28539
2006-05-29 18:05:59 +00:00
Vladimir Prus
5150b763ce
Reset DEBUG_SYMBOL_TABLE back to 0.
...
llvm-svn: 28538
2006-05-29 12:54:52 +00:00
Vladimir Prus
f10bbd052d
Fix compile error when DEBUG_SYMBOL_TABLE is defined.
...
llvm-svn: 28537
2006-05-29 12:45:15 +00:00
Reid Spencer
84f1a3e639
Fix two bugs in the CppWriter.cpp:
...
1. Return the module from the MakeModule function so it can be verified.
2. Make sure types get generated with their names
llvm-svn: 28536
2006-05-29 02:58:15 +00:00
Reid Spencer
7af13d73f7
Fix the file's comment block.
...
llvm-svn: 28535
2006-05-29 02:35:29 +00:00
Reid Spencer
edcf47ea45
Fix grammar in a comment.
...
llvm-svn: 28534
2006-05-29 02:34:34 +00:00
Reid Spencer
5531640f4b
Replace an old C-style cast with a C++ cast (squelch warning)
...
llvm-svn: 28533
2006-05-29 02:32:43 +00:00
Reid Spencer
d078a1fd4c
Correct some grammar and describe current reality.
...
llvm-svn: 28532
2006-05-29 02:31:47 +00:00
Owen Anderson
a03aa6f37f
Require both tests to pass.
...
llvm-svn: 28531
2006-05-29 01:28:16 +00:00
Owen Anderson
c01e7bde40
Update the testcase to check the full extent of LCSSA.
...
llvm-svn: 28530
2006-05-29 01:07:04 +00:00
Owen Anderson
8a8f278f15
Add Use replacement. Assuming there is nothing horribly wrong with this, LCSSA
...
is now theoretically feature-complete. It has not, however, been thoroughly
test, and is still considered experimental.
llvm-svn: 28529
2006-05-29 01:00:00 +00:00
Reid Spencer
58d5dce11d
Initial Commit of llvm2cpp
...
This is a safekeeping commit. The program is not finished. It currently
handles modules, types, global variables and function declarations. Blocks
and instructions remain to be done.
llvm-svn: 28528
2006-05-29 00:57:22 +00:00
Owen Anderson
152d063ccb
Major think-o. Iterate over all live out-of-loop values, and perform the
...
other calculations on each individually, rather than trying to delay it and do
them all at the end.
llvm-svn: 28527
2006-05-28 19:33:28 +00:00
Reid Spencer
497120ef63
Fix a problem where dejagnu won't accept the value of global tcl variable
...
"libdir" for some reason. Changing to llvmlibsdir instead fixes it.
llvm-svn: 28526
2006-05-28 07:22:42 +00:00
Reid Spencer
633301acea
Provide an infrastructure for testing the llvm2cpp program (yet to be
...
committed). This infrastructure is only activated when RUNLLVM2CPP=1 is
specified on the make command line. Currently it is only supported in the
Feature test suite.
llvm-svn: 28525
2006-05-28 04:21:40 +00:00
Owen Anderson
1310e42803
Make LCSSA insert proper Phi nodes throughout the rest of the CFG by computing
...
the iterated Dominance Frontier of the loop-closure Phi's. This is the
second phase of the LCSSA pass. The third phase (coming soon) will be to
update all uses of loop variables to use the loop-closure Phi's instead.
llvm-svn: 28524
2006-05-27 18:47:11 +00:00
Chris Lattner
67c424e010
Fix some regression from the inliner patch I committed last night. This fixes
...
ldecod, lencod, and SPASS.
llvm-svn: 28523
2006-05-27 17:28:13 +00:00
Chris Lattner
6b852931a0
Fix pastos in comments
...
llvm-svn: 28522
2006-05-27 06:57:55 +00:00
Chris Lattner
be853d77e9
Switch the inliner over to using CloneAndPruneFunctionInto. This effectively
...
makes it so that it constant folds instructions on the fly. This is good
for several reasons:
0. Many instructions are constant foldable after inlining, particularly if
inlining a call with constant arguments.
1. Without this, the inliner has to allocate memory for all of the instructions
that can be constant folded, then a subsequent pass has to delete them. This
gets the job done without this extra work.
2. This makes the inliner *pass* a bit more aggressive: in particular, it
partially solves a phase order issue where the inliner would inline lots
of code that folds away to nothing, but think that the resultant function
is big because of this code that will be gone. Now the code never exists.
This is the first part of a 2-step process. The second part will be smart
enough to see when this implicit constant folding propagates a constant into
a branch or switch instruction, making CFG edges dead.
This implements Transforms/Inline/inline_constprop.ll
llvm-svn: 28521
2006-05-27 01:28:04 +00:00
Chris Lattner
64d8692dee
Ignore generated files
...
llvm-svn: 28520
2006-05-27 01:23:30 +00:00
Chris Lattner
3df13f4f22
Implement a new method, CloneAndPruneFunctionInto, as documented.
...
llvm-svn: 28519
2006-05-27 01:22:24 +00:00
Chris Lattner
53e97ebd2c
Implement a new method: CloneAndPruneFunctionInto, as documented.
...
llvm-svn: 28518
2006-05-27 01:21:50 +00:00
Chris Lattner
bc3c879fcf
Refactor some code to expose an interface to constant fold and instruction given it's opcode, typeand operands.
...
llvm-svn: 28517
2006-05-27 01:18:04 +00:00
Chris Lattner
00bb5f8248
Add an interface to constant fold and instruction given it's opcode, type
...
and operands.
llvm-svn: 28516
2006-05-27 01:17:40 +00:00
Chris Lattner
1a2a101359
New testcase: check that the inliner constant folds instructions on the
...
fly if it can.
llvm-svn: 28515
2006-05-27 01:16:22 +00:00
Chris Lattner
8f872d2091
Fix a nasty dag combiner bug that caused nondeterminstic crashes (MY FAVORITE!):
...
SimplifySelectOps would eliminate a Select, delete it, then return true.
The clients would see that it did something and return null.
The top level would see a null return, and decide that nothing happened,
proceeding to process the node in other ways: boom.
The fix is simple: clients of SimplifySelectOps should return the select
node itself.
In order to catch really obnoxious boogs like this in the future, add an
assert that nodes are not deleted. We do this by checking for a sentry node
type that the SDNode dtor sets when a node is destroyed.
llvm-svn: 28514
2006-05-27 00:43:02 +00:00
Chris Lattner
608290c299
Add a new sentry node type, allowing assertions to catch trivial
...
use-after-deleted errors.
llvm-svn: 28513
2006-05-27 00:40:15 +00:00
Owen Anderson
b4e16996f1
A few small clean-ups, and the addition of an LCSSA statistic.
...
llvm-svn: 28512
2006-05-27 00:31:37 +00:00
Evan Cheng
21dee4e0b2
Make CALL node consistent with RET node. Signness of value has type MVT::i32
...
instead of MVT::i1. Either is fine except MVT::i32 is probably a legal type
for most (if not all) platforms while MVT::i1 is not.
llvm-svn: 28511
2006-05-26 23:13:20 +00:00
Evan Cheng
a3add0fea8
Change RET node to include signness information of the return values. i.e.
...
RET chain, value1, sign1, value2, sign2, ...
llvm-svn: 28510
2006-05-26 23:10:12 +00:00
Evan Cheng
a2e9953c54
Change RET node to include signness information of the return values. e.g.
...
RET chain, value1, sign1, value2, sign2
llvm-svn: 28509
2006-05-26 23:09:09 +00:00
Owen Anderson
f980a7478f
Trivial testcase that LCSSA can already handle.
...
llvm-svn: 28508
2006-05-26 21:59:20 +00:00
Owen Anderson
6e047ab8fc
Fix a copy-and-paste-o that would break some compilers.
...
llvm-svn: 28507
2006-05-26 21:19:17 +00:00
Owen Anderson
f3dd3e2bfd
Clean up and refactor LCSSA a bunch. It should also run faster now, though
...
there's still a lot of work to be done on it.
llvm-svn: 28506
2006-05-26 21:11:53 +00:00
Evan Cheng
b92f418408
Vector argument must be passed in memory location aligned on 16-byte boundary.
...
llvm-svn: 28505
2006-05-26 20:37:47 +00:00