a20a773654
Fix a x86-64 codegen deficiency. Allow gv + offset when using rip addressing mode.
...
Before:
_main:
subq $8, %rsp
leaq _X(%rip), %rax
movsd 8(%rax), %xmm1
movss _X(%rip), %xmm0
call _t
xorl %ecx, %ecx
movl %ecx, %eax
addq $8, %rsp
ret
Now:
_main:
subq $8, %rsp
movsd _X+8(%rip), %xmm1
movss _X(%rip), %xmm0
call _t
xorl %ecx, %ecx
movl %ecx, %eax
addq $8, %rsp
ret
Notice there is another idiotic codegen issue that needs to be fixed asap:
xorl %ecx, %ecx
movl %ecx, %eax
llvm-svn: 46850
2008-02-07 08:53:49 +00:00
1bc1cae318
In some cases, e.g. ADD32ri, no transformation is made. Guide against it.
...
llvm-svn: 46849
2008-02-07 08:29:53 +00:00
7c1d787977
Don't make up new directives. (".set_foobar")
...
llvm-svn: 46848
2008-02-07 06:36:26 +00:00
b3efe03672
Fix a typo in a comment.
...
llvm-svn: 46836
2008-02-07 02:30:40 +00:00
4f26eb7270
Add support to FoldingSet for hashing APInt objects.
...
llvm-svn: 46833
2008-02-06 23:09:15 +00:00
2d489b5081
Re-apply the memory operand changes, with a fix for the static
...
initializer problem, a minor tweak to the way the
DAGISelEmitter finds load/store nodes, and a renaming of the
new PseudoSourceValue objects.
llvm-svn: 46827
2008-02-06 22:27:42 +00:00
c676a0329c
Temporarily reverting:
...
http://lists.cs.uiuc.edu/pipermail/llvm-commits/Week-of-Mon-20080128/057882.html
This is causing a miscompilation on PPC G5 and just now seeing it on iMac x86-64.
llvm-svn: 46822
2008-02-06 20:03:07 +00:00
1ec748c784
Fix a number of local register allocator issues: PR1609.
...
llvm-svn: 46821
2008-02-06 19:16:53 +00:00
8291ab4449
RegAllocaLocal still *requires* LiveVariables since it runs PHIElimination, followed by TwoAddress which requires LiveVariables. We cannot run LiveVariables on non-SSA code.
...
llvm-svn: 46813
2008-02-06 08:00:32 +00:00
182a9fd39f
Throttle the non-local dependence analysis for basic blocks with more than 50 predecessors. Added command line option to play with this threshold.
...
llvm-svn: 46790
2008-02-06 00:54:55 +00:00
87fbd66f9f
Fix PR1975: dag isel emitter produces patterns that isel wrong flag result.
...
llvm-svn: 46776
2008-02-05 22:50:29 +00:00
0f32916111
Move to getCALLSEQ_END to ensure CALLSEQ_END node produces a flag. This is consistent with the definition in td file.
...
llvm-svn: 46775
2008-02-05 22:44:06 +00:00
a838141957
Make RenamePass faster by making the 'is this a new phi node'
...
check more intelligent. This speeds up mem2reg from 5.29s to
0.79s on a synthetic testcase with tons of predecessors and
phi nodes.
llvm-svn: 46767
2008-02-05 21:26:23 +00:00
d88f1d060e
Implement sseregparm.
...
llvm-svn: 46764
2008-02-05 20:46:33 +00:00
8d78b0597b
If a vr is already marked alive in a bb, then it has PHI uses that are visited earlier, then it is not killed in the def block (i.e. not dead).
...
llvm-svn: 46763
2008-02-05 20:04:18 +00:00
f3c89be368
Ident mnemonics appropriately
...
llvm-svn: 46746
2008-02-05 08:49:09 +00:00
682a7dc653
Fix a bug compiling PR1978 (perhaps not the only one though) which
...
was incorrectly simplifying "x == (gep x, 1, i)" into false, even
though i could be negative. As it turns out, all the code to
handle this already existed, we just need to disable the incorrect
optimization case and let the general case handle it.
llvm-svn: 46739
2008-02-05 04:45:32 +00:00
1de5997119
Fix an obscure read-after-free bug that Duncan found.
...
llvm-svn: 46738
2008-02-05 04:34:03 +00:00
ac3cd69add
Typo.
...
llvm-svn: 46725
2008-02-04 23:10:38 +00:00
2cb9068c78
Dwarf requires variable entries to be in the source order. Right now, since we are recording variable information at isel time this means parameters would appear in the reverse order. The short term fix is to issue recordVariable() at asm printing time instead.
...
llvm-svn: 46724
2008-02-04 23:06:48 +00:00
5420516b3f
This method should be virtual
...
llvm-svn: 46723
2008-02-04 23:04:24 +00:00
ef14d5f926
Eliminate some redundant code.
...
llvm-svn: 46720
2008-02-04 21:44:06 +00:00
e288786356
Added "bucket_iterators" to FoldingSet. Bucket iterators allow iteration
...
over all the nodes in a particular bucket.
llvm-svn: 46716
2008-02-04 21:11:17 +00:00
3d4f1b3695
Set error message.
...
Patch by Shantonu Sen.
llvm-svn: 46715
2008-02-04 20:57:54 +00:00
726933a589
Fixed 80 col. violation.
...
llvm-svn: 46709
2008-02-04 17:14:20 +00:00
354e353220
I don't see how NodeUpdated can be called with a
...
ReadyToProcess node - add an assertion to check
this. Add an assertion to NodeDeleted that checks
that processed/ready nodes are indeed not deleted.
It is because they are never deleted that none of
the maps can have a deleted node as the source of
a mapping. It does however seem to be possible in
theory to have a deleted value as the target of a
mapping, however this has not yet been spotted in
the wild. Still mulling on what to do about this.
[The theoretical situation is this: a node A is
expanded/promoted/whatever to a newly created node
B. Thus A->B is added to a map. When the subtree
rooted at B is legalized it is conceivable that B
is deleted due to RAUW on a node somewhere above
it].
llvm-svn: 46705
2008-02-04 09:29:17 +00:00
e146c0e3fd
The rest of the SSE4.1 intrinsic patterns that are obvious to me. Getting
...
Evan's help with the rest.
llvm-svn: 46697
2008-02-04 06:00:24 +00:00
ccdfd4aa17
Some more SSE 4.1 intrinsic patterns.
...
llvm-svn: 46696
2008-02-04 05:34:34 +00:00
a82c9931f4
Be more precise when eliminating pointers bue to memcpy's. This allows more
...
stores to be deleted in some cases.
llvm-svn: 46694
2008-02-04 04:53:00 +00:00
c4a7c41869
Allow GVN to hack on memcpy's, making them open to further optimization.
...
llvm-svn: 46693
2008-02-04 02:59:58 +00:00
3b59214320
There are some cases where icmp(add) can be folded into a new icmp. Handle them.
...
llvm-svn: 46687
2008-02-03 16:33:09 +00:00
c7a4ba044b
Hack on vectors too.
...
llvm-svn: 46684
2008-02-03 08:19:11 +00:00
e6e3a7f6ea
Fold away one multiply in instcombine. This would normally be caught in
...
reassociate anyways, but they could be generated during instcombine's run.
llvm-svn: 46683
2008-02-03 07:42:09 +00:00
c41e535df1
Fix typo
...
llvm-svn: 46682
2008-02-03 07:30:27 +00:00
e14fdfaecd
SSE 4.1 Intrinsics and detection
...
llvm-svn: 46681
2008-02-03 07:18:54 +00:00
62f67ea73a
handle the case where a node can become ready to process
...
multiple times due to a RAUW.
llvm-svn: 46680
2008-02-03 07:13:32 +00:00
4e9898825e
Use the new infrastructure for listening to node updates to
...
keep the LegalizeTypes node flags up to date when doing a RAUW.
This fixes a nasty bug that Duncan ran into and makes the
previous (nonbuggy case) more efficent.
llvm-svn: 46679
2008-02-03 07:08:51 +00:00
d2d166ea9f
the world doesn't need my debugging code.
...
llvm-svn: 46678
2008-02-03 07:01:05 +00:00
b2b9d6f0fb
Change the 'global modification' APIs in SelectionDAG to take a new
...
DAGUpdateListener object pointer instead of just returning a vector
of deleted nodes. This makes the interfaces more efficient (no more
allocating a vector [at least a malloc], filling it in, then walking
it) and more clean. This also allows the client to be notified of
nodes that are *changed* but not deleted.
llvm-svn: 46677
2008-02-03 06:49:24 +00:00
1770fb883b
explicitly include Compiler.h instead of getting it from tblgen in the middle of a class.
...
llvm-svn: 46676
2008-02-03 05:43:57 +00:00
7685891aa3
Generalize the SDOperand->SDOperand form of
...
SelectionDAG::ReplaceAllUsesWith to handle replacement of
an SDOperand with *any* sdoperand, not just one for a node with
a single result. Note that this has a horrible FIXME'd hack in it
to work around PR1975. This should be removed when PR1975 is fixed.
llvm-svn: 46674
2008-02-03 03:35:22 +00:00
e99faac423
don't do ReplaceUses on a result that doesn't exist.
...
llvm-svn: 46673
2008-02-03 03:20:59 +00:00
f34dfe4f28
add a -view-legalize-types-dags option, for viewing the dags going into legalize types.
...
llvm-svn: 46672
2008-02-03 02:05:04 +00:00
32e5347eb8
Get rid of the annoying blank lines before labels.
...
llvm-svn: 46667
2008-02-02 08:39:46 +00:00
f5b9938ef6
Don't use uninitialized values. Fixes vec_align.ll on X86 Linux.
...
llvm-svn: 46666
2008-02-02 08:29:58 +00:00
2aa360adf8
Unbreak ppc debug support.
...
llvm-svn: 46665
2008-02-02 05:06:29 +00:00
efd142a920
SDIsel processes llvm.dbg.declare by recording the variable debug information descriptor and its corresponding stack frame index in MachineModuleInfo. This only works if the local variable is "homed" in the stack frame. It does not work for byval parameter, etc.
...
Added ISD::DECLARE node type to represent llvm.dbg.declare intrinsic. Now the intrinsic calls are lowered into a SDNode and lives on through out the codegen passes.
For now, since all the debugging information recording is done at isel time, when a ISD::DECLARE node is selected, it has the side effect of also recording the variable. This is a short term solution that should be fixed in time.
llvm-svn: 46659
2008-02-02 04:07:54 +00:00
8df7cc1119
Add comment explaining what is lower level analysis pass.
...
llvm-svn: 46658
2008-02-02 01:43:30 +00:00
931e121ad1
Fixing a bug creating floating point constants of type other
...
than double through the C bindings. Thanks to Tomas Lindquist
Olsen for reporting it.
llvm-svn: 46656
2008-02-02 01:07:50 +00:00
4e7ff941f1
Frame index can be negative.
...
llvm-svn: 46655
2008-02-02 00:17:00 +00:00
192c07b727
CBackend: Implement unaligned load/store.
...
llvm-svn: 46646
2008-02-01 21:25:59 +00:00
9aa789fda3
Don't drop function/call return attributes like 'nounwind'.
...
llvm-svn: 46645
2008-02-01 20:37:16 +00:00
d6e44ab5ec
Remove the nasty LABEL hack with a much less evil one. Now llvm.dbg.func.start implies a stoppoint is set. SelectionDAGISel records a new source line but does not create a ISD::LABEL node for this special stoppoint. Asm printer will magically print this label. This ensures nothing is emitted before.
...
llvm-svn: 46635
2008-02-01 09:10:45 +00:00
263070ea2b
Rename RecordLabel to RecordSourceLine because that's what it is doing.
...
llvm-svn: 46628
2008-02-01 02:05:57 +00:00
27b32b87ed
Revert 46556 and 46585. Dan please fix the PseudoSourceValue problem and re-commit.
...
llvm-svn: 46623
2008-01-31 21:00:00 +00:00
8ef8f24c40
Chris' change to print an approximation to long doubles
...
exposed a bug in APFloat's long double->double conversion of
NaNs. Broke several things in the ieee part of gcc testsuite.
llvm-svn: 46617
2008-01-31 18:34:01 +00:00
f4f1d44779
Add a comment for a nasty short term hack.
...
llvm-svn: 46610
2008-01-31 10:05:13 +00:00
1c6c16ea11
Add an extra operand to LABEL nodes which distinguishes between debug, EH, or misc labels. This fixes the EH breakage. However I am not convinced this is *the* solution.
...
llvm-svn: 46609
2008-01-31 09:59:15 +00:00
0592cf7e74
Allow ComplexExpressions in InstrInfo.td files to be slightly more... complex! ComplexExpressions can now have attributes which affect how TableGen interprets
...
the pattern when generating matchin code.
The first (and currently, only) attribute causes the immediate parent node of the ComplexPattern operand to be passed into the matching code rather than the node at the root of the entire DAG containing the pattern.
llvm-svn: 46606
2008-01-31 07:27:46 +00:00
58ffa8c57a
Add more thorough error checking for NULL register classes.
...
llvm-svn: 46605
2008-01-31 07:09:08 +00:00
6332dbec69
Add x86 specific getFrameIndexOffset(). This fixes local variable debugging info.
...
llvm-svn: 46598
2008-01-31 04:06:00 +00:00
a41d3bcb12
MRegisterInfo::getLocation() is a really bad idea. Its function is to calculate the offset from frame pointer to a stack slot and then storing the delta in a MachineLocation object. The name is bad (it implies a getter), and MRegisterInfo doesn't need to know about MachineLocation.
...
Replace getLocation() with getFrameIndexOffset() which returns the delta from frame pointer to stack slot. Dwarf writer can then use the information for whatever it wants.
llvm-svn: 46597
2008-01-31 03:37:28 +00:00
3c0486fb38
Makes the same change in ppc backend: avoid inserting prologue before debug labels.
...
llvm-svn: 46596
2008-01-31 03:33:38 +00:00
a65951fef0
Avoid unnecessarily casting away const, fixing a FIXME.
...
llvm-svn: 46591
2008-01-31 01:05:10 +00:00
ed346f2ed5
Avoid unnecessarily casting away const.
...
llvm-svn: 46590
2008-01-31 01:01:48 +00:00
9ba4d76816
Rename ISD::FLT_ROUNDS to ISD::FLT_ROUNDS_ to avoid conflicting
...
with the real FLT_ROUNDS (defined in <float.h>).
llvm-svn: 46587
2008-01-31 00:41:03 +00:00
4863fcc3eb
Also avoid adding callee save code before debug labels.
...
llvm-svn: 46586
2008-01-31 00:27:49 +00:00
3646fdda67
Create a new class, MemOperand, for describing memory references
...
in the backend. Introduce a new SDNode type, MemOperandSDNode, for
holding a MemOperand in the SelectionDAG IR, and add a MemOperand
list to MachineInstr, and code to manage them. Remove the offset
field from SrcValueSDNode; uses of SrcValueSDNode that were using
it are all all using MemOperandSDNode now.
Also, begin updating some getLoad and getStore calls to use the
PseudoSourceValue objects.
Most of this was written by Florian Brander, some
reorganization and updating to TOT by me.
llvm-svn: 46585
2008-01-31 00:25:39 +00:00
b9b740119d
Fixed a bug in MergeValueInAsValue() pointed out by David Greene. Replace val# with previous liverange's.
...
llvm-svn: 46579
2008-01-30 22:44:55 +00:00
a3395a61cc
Treat the label for the first @llvm.dbg.stoppoint the same way as the dbg_func_start label. Make sure nothing else is inserted before them.
...
Note this solution might be somewhat fragile since ISD::LABEL may be used for other
purposes. If that ends up to be an issue, we may need to introduce a different node
for debug labels.
llvm-svn: 46571
2008-01-30 20:08:35 +00:00
19cf69ff9d
Adjust loop per review feedback.
...
llvm-svn: 46569
2008-01-30 19:44:39 +00:00
a3ff8e6110
A semi-gross fix for a debug info issue. When inserting the "function start" label (i.e. first label in the entry block) take care to insert it at the beginning of the block.
...
llvm-svn: 46568
2008-01-30 19:35:32 +00:00
56d4903db5
Accept getelementptr starting at GV with all 0 indices as a
...
legitimate way of representing global variable GV in debug info.
llvm-svn: 46565
2008-01-30 19:00:21 +00:00
29cfb67e28
Even though InsertAtEndOfBasicBlock is an ugly hack it still deserves a proper name. Rename it to EmitInstrWithCustomInserter since it does not necessarily insert
...
instruction at the end.
llvm-svn: 46562
2008-01-30 18:18:23 +00:00
02b6792dd4
Add a new PseudoSourceValue class, which will be used to help track
...
memory reference information in the backend. Most of this was written by
Florian Brander, cleanup and updating to TOT by me.
llvm-svn: 46556
2008-01-30 16:35:31 +00:00
6b016703a9
Remove a couple more cases of "getNumUses() == 0". No need to walk the linked
...
list just to see if whether the list is empty.
llvm-svn: 46555
2008-01-30 08:01:28 +00:00
625e89c8b0
Use empty() instead of comparing size() with zero.
...
llvm-svn: 46554
2008-01-30 07:54:16 +00:00
0e3a5cb14a
Don't DCE FreeInst's. We were using those! Patch from Owen Anderson.
...
llvm-svn: 46553
2008-01-30 07:45:37 +00:00
ed17ef7e18
Skip over the label which marks the beginning of the function before inserting prologue code.
...
llvm-svn: 46546
2008-01-30 03:57:33 +00:00
cd2bb20b5f
Back out mods to llvmAsmParser, incorrectly committed
...
llvm-svn: 46545
2008-01-30 03:10:00 +00:00
bb713ae0c7
More cleanups for CellSPU:
...
- Expand tabs... (poss 80-col violations, will get them later...)
- Consolidate logic for SelectDFormAddr and SelectDForm2Addr into a single
function, simplifying maintenance. Also reduced custom instruction
generation for SPUvecinsert/INSERT_MASK.
llvm-svn: 46544
2008-01-30 02:55:46 +00:00
4e4b116750
Make DSE much more aggressive by performing DCE earlier. Update a testcase to reflect this increased aggressiveness.
...
llvm-svn: 46542
2008-01-30 01:24:47 +00:00
b255ada55b
Fix an issue where, under very specific circumstances, memdep could end up dereferencing the end
...
of one of its internal maps.
llvm-svn: 46541
2008-01-30 01:24:05 +00:00
b9e5b8fb9e
Fix a bug where scalarrepl would discard offset if type would match.
...
In practice this can only happen on code with already undefined behavior,
but this is still a good thing to handle correctly.
llvm-svn: 46539
2008-01-30 00:39:15 +00:00
47a7d6fafe
Factor the addressing mode and the load/store VT out of LoadSDNode
...
and StoreSDNode into their common base class LSBaseSDNode. Member
functions getLoadedVT and getStoredVT are replaced with the common
getMemoryVT to simplify code that will handle both loads and stores.
llvm-svn: 46538
2008-01-30 00:15:11 +00:00
084a1cdcdd
Work in progress. This patch *fixes* x86-64 calls which are modelled as StructRet but really should be return in registers, e.g. _Complex long double, some 128-bit aggregates. This is a short term solution that is necessary only because llvm, for now, cannot model i128 nor call's with multiple results.
...
Status: This only works for direct calls, and only the caller side is done. Disabled for now.
llvm-svn: 46527
2008-01-29 19:34:22 +00:00
032a5d2690
When expanding an operand, it's not the result value
...
type that matters but the operand type. This fixes
2008-01-08-IllegalCMP.ll which crashed with the new
legalize infrastructure because SETCC with result
type i8 and operand type i64 was being custom expanded
by the X86 backend. With this fix, the gcc build gets
as far as the first libcall.
llvm-svn: 46525
2008-01-29 19:29:08 +00:00
ade0abb498
Don't let globalopt hack on volatile loads or stores.
...
llvm-svn: 46523
2008-01-29 19:01:37 +00:00
70de4cb1cd
Use empty() instead of comparing size() with zero.
...
llvm-svn: 46514
2008-01-29 13:02:09 +00:00
cf8827a282
Fix a typo in a comment.
...
llvm-svn: 46513
2008-01-29 12:43:50 +00:00
929391a19a
Fix 80-col violations.
...
llvm-svn: 46510
2008-01-29 12:09:55 +00:00
b456a15a5b
Remove top-level const qualifiers from casts, avoiding associated
...
compiler warnings.
llvm-svn: 46509
2008-01-29 12:08:20 +00:00
cd170a7017
Fix a typo in a comment.
...
llvm-svn: 46508
2008-01-29 12:07:11 +00:00
242223abd5
Add explicit keywords.
...
llvm-svn: 46506
2008-01-29 11:36:12 +00:00
17819d971e
eliminate additions of 0.0 when they are obviously dead. This has to be careful to
...
avoid turning -0.0 + 0.0 -> -0.0 which is incorrect.
llvm-svn: 46499
2008-01-29 06:52:45 +00:00
05837edae7
Use getPreferredAlignmentLog or getPreferredAlignment
...
to get the alignment of global variables, rather than
using hand-made versions.
llvm-svn: 46495
2008-01-29 06:23:44 +00:00
48d37806e2
Add support for eliminating memcpy's at the end of functions. Also fix some errors I noticed in
...
the handling of eliminating stores to byval arguments.
llvm-svn: 46494
2008-01-29 06:18:36 +00:00
5aa1615add
RegAllocBigBlock doesn't need LiveVariables either.
...
llvm-svn: 46488
2008-01-29 02:32:13 +00:00
ef33767efb
Properly expand extract-element for non-power-of-2 codegen
...
llvm-svn: 46486
2008-01-29 02:24:00 +00:00
2b3bc30420
Handle 'X' constraint in asm's better.
...
llvm-svn: 46485
2008-01-29 02:21:21 +00:00
Evan Cheng