Commit Graph

52182 Commits

Author SHA1 Message Date
Victor Hernandez 46cd467310 Auto-upgrade malloc instructions to malloc calls.
Reviewed by Devang Patel.

llvm-svn: 82694
2009-09-24 17:47:49 +00:00
Bob Wilson 5fe313d6e0 Fix a hypothetical problem for targets with StackGrowsUp and a non-zero
LocalAreaOffset.  (We don't have any of those right now.)
PEI::calculateFrameObjectOffsets includes the absolute value of the
LocalAreaOffset in the cumulative offset value used to calculate the
stack frame size.  It then adds the raw value of the LocalAreaOffset
to the stack size.  For a StackGrowsDown target, that raw value is negative
and has the effect of cancelling out the absolute value that was added
earlier, but that obviously won't work for a StackGrowsUp target.  Change
to subtract the absolute value of the LocalAreaOffset.

llvm-svn: 82693
2009-09-24 16:42:27 +00:00
Devang Patel 4e6f2e46e8 Move parent assertion check before metadata deletion.
llvm-svn: 82692
2009-09-24 16:19:11 +00:00
Torok Edwin f95a450ef9 Don't constant propagate byval pointers, since they are not really pointers, but
rather structs passed by value.
This fixes PR5038.

llvm-svn: 82689
2009-09-24 09:47:18 +00:00
Daniel Dunbar 00dd448cff Add count/not tools as executables.
- Apparently, I'm willing to do incredibly stupid things in the name of portability.

llvm-svn: 82685
2009-09-24 06:23:57 +00:00
Chris Lattner 87d8f2b9d5 unconditionally compute MMI even if the target doesn't support EH or Debug info, because the target may use it for other things, this fixes PR5036
llvm-svn: 82684
2009-09-24 05:44:53 +00:00
Chris Lattner 4e37f877b5 reapply r82348 with a fix, thanks Jeffrey.
llvm-svn: 82683
2009-09-24 05:38:36 +00:00
Evan Cheng 26ea28eb5f Fix PR5024 with a big hammer: disable the double-def assertion in the scavenger.
LiveVariables add implicit kills to correctly track partial register kills. This works well enough and is fairly accurate. But coalescer can make it impossible to maintain these markers. e.g.

        BL <ga:sss1>, %R0<kill,undef>, %S0<kill>, %R0<imp-def>, %R1<imp-def,dead>, %R2<imp-def,dead>, %R3<imp-def,dead>, %R12<imp-def,dead>, %LR<imp-def,dead>, %D0<imp-def>, ...
...
	%reg1031<def> = FLDS <cp#1>, 0, 14, %reg0, Mem:LD4[ConstantPool]
...
   	%S0<def> = FCPYS %reg1031<kill>, 14, %reg0, %D0<imp-use,kill>

When reg1031 and S0 are coalesced, the copy (FCPYS) will be eliminated the the implicit-kill of D0 is lost. In this case it's possible to move the marker to the FLDS. But in many cases, this is not possible. Suppose

	%reg1031<def> = FOO <cp#1>, %D0<imp-def>
...
   	%S0<def> = FCPYS %reg1031<kill>, 14, %reg0, %D0<imp-use,kill>

When FCPYS goes away, the definition of S0 is the "FOO" instruction. However, transferring the D0 implicit-kill to FOO doesn't work since it is the def of D0 itself. We need to fix this in another time by introducing a "kill" pseudo instruction to track liveness.

Disabling the assertion is not ideal, but machine verifier is doing that job now. It's important to know double-def is not a miscomputation since it means a register should be free but it's not tracked as free. It's a performance issue instead.

llvm-svn: 82677
2009-09-24 02:27:09 +00:00
Evan Cheng a21aac3811 Clean up LiveVariables and change how it deals with partial updates and kills. This also eliminate the horrible check which scan forward to the end of the basic block. It should be faster and more accurate.
llvm-svn: 82676
2009-09-24 02:15:22 +00:00
Jeffrey Yasskin a75d6bf3a8 Roll back r82348, which introduced an infinite loop in ParseCStringVector() that
a trivial unittest would have caught.  This revision also adds the trivial
unittest.

llvm-svn: 82675
2009-09-24 01:14:07 +00:00
Dale Johannesen fb1b55bc9c A minor improvment in accuracy to inline cost
computation, and some cosmetics.

llvm-svn: 82660
2009-09-23 22:05:24 +00:00
Dale Johannesen ea406ed0a6 Disable test; what it's testing for is wrong.
llvm-svn: 82658
2009-09-23 21:46:36 +00:00
David Goodwin afcaf79603 Checkpoint NEON scheduling itineraries.
llvm-svn: 82657
2009-09-23 21:38:08 +00:00
Dan Gohman 203d53ed79 Use getStoreSize() instead of getStoreSizeInBits()/8.
llvm-svn: 82656
2009-09-23 21:07:02 +00:00
Dan Gohman 99bdae2992 Spruce up some comments.
llvm-svn: 82655
2009-09-23 21:06:36 +00:00
Dan Gohman 08c0a95ac6 Rename several variables from EVT to more descriptive names, now that EVT
is also the name of their type, as declarations like "EVT EVT" look
really odd.

llvm-svn: 82654
2009-09-23 21:02:20 +00:00
Dan Gohman 2366ffd2cb Add an EVT::getStoreSize function, like getStoreSizeInBits but in bytes.
llvm-svn: 82653
2009-09-23 20:59:10 +00:00
Jakob Stoklund Olesen 75b9c2741d Fix verification of explicit operands.
The machine code verifier did not check for explicit operands correctly. It
used MachineInstr::getNumExplicitOperands, but that method may cheat and use
the declared count in the TargetInstrDesc.

Now we check the explicit operands one at a time in visitMachineOperand.

llvm-svn: 82652
2009-09-23 20:57:55 +00:00
Bob Wilson abfdbbfd1a Remove BlackfinRegisterInfo::getFrameIndexOffset since it is the same as the
default implementation.  Update comment on the default version, which made it
sound like most targets override it.  Currently only X86 and SystemZ override
this method.

llvm-svn: 82651
2009-09-23 20:57:02 +00:00
Dan Gohman 49f271afb3 Correct a comment.
llvm-svn: 82648
2009-09-23 20:40:16 +00:00
Devang Patel 52e819c7cf Delete attached metadata when an instruction is deleted.
llvm-svn: 82647
2009-09-23 20:33:51 +00:00
Anton Korobeynikov 29a44df5f8 ARM does not support offset folding (yet). Disable it for now.
This fixes PR5031. Unfortunately, there is no small testcase :(

llvm-svn: 82643
2009-09-23 19:04:09 +00:00
Bob Wilson c2c86cede6 Edit a comment.
llvm-svn: 82641
2009-09-23 18:53:19 +00:00
Devang Patel add586526e Do not leave behind metadata while cloning an instruction.
llvm-svn: 82638
2009-09-23 18:32:25 +00:00
Evan Cheng 3cf0ddf094 Add nounwind.
llvm-svn: 82637
2009-09-23 18:20:27 +00:00
Devang Patel e4e8181111 s/*Location/*DebugLocation/g
llvm-svn: 82635
2009-09-23 17:20:43 +00:00
Jeffrey Yasskin 42a49dfb02 PR4047: Permit configure --enable-targets=host,cpp for example. "host" has the
same effect that "host-only" used to have, but can be combined with other
targets.  host-only is still available as a synonym but no longer documented.

llvm-svn: 82634
2009-09-23 17:05:42 +00:00
David Goodwin a4c98a3e34 Fix bug in kill flag updating for post-register-allocation scheduling. When the kill flag of a superreg needs to be cleared because there are one or more subregs live, we instead add implicit-defs of those subregs and leave the kill flag on the superreg. This allows us to end the live-range of the superreg without ending the live-ranges of the subregs.
llvm-svn: 82629
2009-09-23 16:35:25 +00:00
Benjamin Kramer 43355aec61 Fix a struct/class mismatch.
llvm-svn: 82622
2009-09-23 11:48:57 +00:00
John McCall 0110327ae3 Make the type traits for a const pointer defer to those for a unqualified
pointer, instead of providing independent values modelled on the default
implementation.

llvm-svn: 82620
2009-09-23 06:53:51 +00:00
Evan Cheng 262f86ed90 Fix PR5024. LiveVariables physical register defs should *commit* only after all
of the defs are processed.
Also fix a implicit_def propagation bug: a implicit_def of a physical register
should be applied to uses of the sub-registers.

llvm-svn: 82616
2009-09-23 06:28:31 +00:00
Evan Cheng b2abe07457 Fix a obvious logic error.
llvm-svn: 82610
2009-09-23 05:23:19 +00:00
Gabor Greif 98dd936bc9 pretty mechanical changes to match coding guidelines (blessed by sabre on IRC)
llvm-svn: 82603
2009-09-23 02:46:12 +00:00
Chris Lattner 8bcc6445c7 errorstr can be null, don't unconditionally set it. Only report that
"the jit has not been linked in" if the interpreter failed.

This fixes a unit test failure.

llvm-svn: 82601
2009-09-23 02:03:49 +00:00
Chris Lattner 41fa2bd112 Make EngineBuilder return more error codes, by KS Sreeram.
llvm-svn: 82600
2009-09-23 01:46:04 +00:00
Dan Gohman c0353bfff5 Give MachineMemOperand an operator<<, factoring out code from
two different places for printing MachineMemOperands.

Drop the virtual from Value::dump and instead give Value a
protected virtual hook that can be overridden by subclasses
to implement custom printing. This lets printing be more
consistent, and simplifies printing of PseudoSourceValue
values.

llvm-svn: 82599
2009-09-23 01:33:16 +00:00
Dan Gohman 1439957928 Fix X86's unfoldMemoryOperand to properly handle MachineMemOperands.
llvm-svn: 82597
2009-09-23 01:29:41 +00:00
Mike Stump 8808063181 This is overly constraining with respect to clang.
llvm-svn: 82591
2009-09-23 00:13:30 +00:00
Erick Tryzelaar 21e83eab3f Add examples for Kaleidoscope chapters 2 through 6.
Conflicts:

	examples/Makefile

llvm-svn: 82574
2009-09-22 21:15:19 +00:00
Erick Tryzelaar 2d8813cfb0 Rename Kaleidoscope to show that it's for Chapter 7 of the tutorial.
llvm-svn: 82573
2009-09-22 21:15:00 +00:00
Erick Tryzelaar 6e2b34bc14 Sync c++ kaleidoscope tutorial with test.
llvm-svn: 82572
2009-09-22 21:14:49 +00:00
Devang Patel 320a1c4083 Add SetLocation() to allow IRBuilder user to set location info for an instruction already created.
llvm-svn: 82570
2009-09-22 20:56:31 +00:00
Devang Patel 276b02b325 Check exisiting dbg MDKind first.
llvm-svn: 82568
2009-09-22 20:54:13 +00:00
Victor Hernandez ddc2ce4fe2 No need to verify that malloc's return type is i8*.
llvm-svn: 82561
2009-09-22 18:50:03 +00:00
David Goodwin 74b79566f6 Use early returns.
llvm-svn: 82554
2009-09-22 16:47:52 +00:00
Daniel Dunbar 7e3aa3f68c Revert "Don't allow formatted_ostream to be unbuffered, even if its underlying
buffer", while we work out a solution.

Dan convinced me that making debugging annoying for him is worse than 10x being
slower for me. :)

llvm-svn: 82553
2009-09-22 16:33:42 +00:00
Daniel Dunbar b2942cb5cb ... missed hiding a variable for MSVC only.
llvm-svn: 82552
2009-09-22 16:10:35 +00:00
Daniel Dunbar 1bdedd3876 Hide MSVC specific CRT interaction behind _MSC_VER.
llvm-svn: 82551
2009-09-22 15:58:35 +00:00
Mikhail Glushenkov 88e98fec70 Remove the GetProcessId() call from Win32/Program.inc, take 2.
GetProcessId() was introduced only in Windows XP, and we want to support earlier
versions.

llvm-svn: 82548
2009-09-22 15:40:32 +00:00
Daniel Dunbar 86707c9913 Fix commento.
llvm-svn: 82544
2009-09-22 10:30:34 +00:00