Commit Graph

62 Commits

Author SHA1 Message Date
Evan Cheng
48575f6ea7 Making use of VFP / NEON floating point multiply-accumulate / subtraction is
difficult on current ARM implementations for a few reasons.
1. Even though a single vmla has latency that is one cycle shorter than a pair
   of vmul + vadd, a RAW hazard during the first (4? on Cortex-a8) can cause
   additional pipeline stall. So it's frequently better to single codegen
   vmul + vadd.
2. A vmla folowed by a vmul, vmadd, or vsub causes the second fp instruction to
   stall for 4 cycles. We need to schedule them apart.
3. A vmla followed vmla is a special case. Obvious issuing back to back RAW
   vmla + vmla is very bad. But this isn't ideal either:
     vmul
     vadd
     vmla
   Instead, we want to expand the second vmla:
     vmla
     vmul
     vadd
   Even with the 4 cycle vmul stall, the second sequence is still 2 cycles
   faster.

Up to now, isel simply avoid codegen'ing fp vmla / vmls. This works well enough
but it isn't the optimial solution. This patch attempts to make it possible to
use vmla / vmls in cases where it is profitable.

A. Add missing isel predicates which cause vmla to be codegen'ed.
B. Make sure the fmul in (fadd (fmul)) has a single use. We don't want to
   compute a fmul and a fmla.
C. Add additional isel checks for vmla, avoid cases where vmla is feeding into
   fp instructions (except for the #3 exceptional case).
D. Add ARM hazard recognizer to model the vmla / vmls hazards.
E. Add a special pre-regalloc case to expand vmla / vmls when it's likely the
   vmla / vmls will trigger one of the special hazards.

Work in progress, only A+B are enabled.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@120960 91177308-0d34-0410-b5e6-96231b3b80d8
2010-12-05 22:04:16 +00:00
Jim Grosbach
baf120fbe8 Move the ARMAsmPrinter class defintiion into a header file.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@120551 91177308-0d34-0410-b5e6-96231b3b80d8
2010-12-01 03:45:07 +00:00
Chris Lattner
30e2cc254b rename LowerToMCInst -> LowerARMMachineInstrToMCInst.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@119071 91177308-0d34-0410-b5e6-96231b3b80d8
2010-11-14 21:00:02 +00:00
Chris Lattner
1612a619f1 even more simplifications. ARM MCInstLowering is now just
a single function instead of a class.  It doesn't need the
complexity that X86 does.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@119070 91177308-0d34-0410-b5e6-96231b3b80d8
2010-11-14 20:58:38 +00:00
Jason W Kim
d4d4f4f488 I added a new file ARMAsmBackend which stubs out in similar ways to
the eqv X86 class.
For now, I split the ELFARMAsmBackend from the DarwinARMAsmBackend
(also mimicking X86)

Tested against -r115126



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@115129 91177308-0d34-0410-b5e6-96231b3b80d8
2010-09-30 02:17:26 +00:00
Jim Grosbach
568eeedea7 Add skeleton infrastructure for the ARMMCCodeEmitter class. Patch by Jason Kim!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@114195 91177308-0d34-0410-b5e6-96231b3b80d8
2010-09-17 18:46:17 +00:00
Jim Grosbach
754578b565 Factor out basic enums and hleper functions from ARM.h for cleaner sharing
between the compiler back end and the MC libraries.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@114007 91177308-0d34-0410-b5e6-96231b3b80d8
2010-09-15 19:26:06 +00:00
Bob Wilson
bd916c54b7 Convert some VTBL and VTBX instructions to use pseudo instructions prior to
register allocation.  Remove the NEONPreAllocPass, which is no longer needed.
Yeah!!


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@113818 91177308-0d34-0410-b5e6-96231b3b80d8
2010-09-13 23:55:10 +00:00
Bill Wendling
5e7044bd0e Add comments for what the condition code symbols mean.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@111889 91177308-0d34-0410-b5e6-96231b3b80d8
2010-08-24 01:11:30 +00:00
Johnny Chen
1adc40cac3 Cleaned up the for-disassembly-only entries in the arm instruction table so that
the memory barrier variants (other than 'SY' full system domain read and write)
are treated as one instruction with option operand.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@110951 91177308-0d34-0410-b5e6-96231b3b80d8
2010-08-12 20:46:17 +00:00
Anton Korobeynikov
cec36f4c11 Hook in GlobalMerge pass
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109359 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-24 21:52:08 +00:00
Evan Cheng
dca653951c Remove early IT block formation. It's not used.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@107513 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-02 21:07:09 +00:00
Bob Wilson
07f6e805b1 Remove the hidden "neon-reg-sequence" option. The reg sequences are working
now, so there's no need to disable them.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@106155 91177308-0d34-0410-b5e6-96231b3b80d8
2010-06-16 21:34:01 +00:00
Evan Cheng
d847124211 Thumb2 IT blocks are fairly expensive. When there are multiple selects using
the same condition, it's important to make sure they are scheduled together
to avoid forming multiple IT blocks. I'm adding a pre-regalloc pass that forms
IT blocks early (by re-scheduling instructions and split basic blocks) to
attempt to fix this. This is not turned on by default since I am not sure this
is the right fix.

Another issue is llvm selects are modeled as two-address conditional moves.
This can be very bad when the copies before the conditional moves are not
coalesced away. Teach IT formation pass to move the copies above the IT block
(when legal) to avoid breaking the IT block.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@105669 91177308-0d34-0410-b5e6-96231b3b80d8
2010-06-09 01:46:50 +00:00
Evan Cheng
de8aa4ed9c Model CONCAT_VECTORS of two 64-bit values as a REG_SEQUENCE.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@103104 91177308-0d34-0410-b5e6-96231b3b80d8
2010-05-05 18:28:36 +00:00
Anton Korobeynikov
4b38debf59 Remove late ARM codegen optimization pass committed by accident.
It is not ready for public yet.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@100673 91177308-0d34-0410-b5e6-96231b3b80d8
2010-04-07 18:23:27 +00:00
Anton Korobeynikov
1e7b324fe5 Some initial version of global merger
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@100641 91177308-0d34-0410-b5e6-96231b3b80d8
2010-04-07 18:19:07 +00:00
Chris Lattner
55fed86353 tidy some targets.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@95146 91177308-0d34-0410-b5e6-96231b3b80d8
2010-02-02 22:13:21 +00:00
Chris Lattner
e0faa54705 remove dead code.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@95134 91177308-0d34-0410-b5e6-96231b3b80d8
2010-02-02 21:38:59 +00:00
Jim Grosbach
e27d205d5d Factor the stack alignment calculations out into a target independent pass.
No functionality change.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@90336 91177308-0d34-0410-b5e6-96231b3b80d8
2009-12-02 19:30:24 +00:00
Jim Grosbach
a44321776e Detect need for autoalignment of the stack earlier to catch spills more
conservatively. eliminateFrameIndex() machinery adjust to handle addr mode
6 (vld1/vst1) used for spills. Fix tests to expect aligned Q-reg spilling

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@88874 91177308-0d34-0410-b5e6-96231b3b80d8
2009-11-15 21:45:34 +00:00
Evan Cheng
b9803a8fa6 - Add pseudo instructions tLDRpci_pic and t2LDRpci_pic which does a pc-relative
load of a GV from constantpool and then add pc. It allows the code sequence to
  be rematerializable so it would be hoisted by machine licm.
- Add a late pass to break these pseudo instructions into a number of real
  instructions. Also move the code in Thumb2 IT pass that breaks up t2MOVi32imm
  to this pass. This is done before post regalloc scheduling to allow the
  scheduler to proper schedule these instructions. It also allow them to be
  if-converted and shrunk by later passes.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@86304 91177308-0d34-0410-b5e6-96231b3b80d8
2009-11-06 23:52:48 +00:00
Anton Korobeynikov
7aaf94bb0d Turn neon reg-reg moves fixup code into separate pass. This should reduce the compile time.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@85850 91177308-0d34-0410-b5e6-96231b3b80d8
2009-11-03 01:04:26 +00:00
Bob Wilson
522ce97532 Pass the optimization level when constructing the ARM instruction selector.
Otherwise, it is always set to "default", which prevents debug info from
even being generated during isel.  Radar 7250345.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@82988 91177308-0d34-0410-b5e6-96231b3b80d8
2009-09-28 14:30:20 +00:00
Jim Grosbach
764ab52dd8 Whitespace cleanup. Remove trailing whitespace.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@78666 91177308-0d34-0410-b5e6-96231b3b80d8
2009-08-11 15:33:49 +00:00
Evan Cheng
8fb903604e Code refactoring. No functionality change.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@78455 91177308-0d34-0410-b5e6-96231b3b80d8
2009-08-08 03:20:32 +00:00
Bob Wilson
70cd88fb7b Add a new pre-allocation pass to assign adjacent registers for Neon instructions
that have that constraint.  This is currently just assigning a fixed set of
registers, and it only handles VLDn for n=2,3,4 with DPR registers.
I'm going to expand it to handle more operations next; we can make it smarter
once everything is working correctly.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@78256 91177308-0d34-0410-b5e6-96231b3b80d8
2009-08-05 23:12:45 +00:00
Bob Wilson
7f0f2515a0 Remove a redundant declaration.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@78216 91177308-0d34-0410-b5e6-96231b3b80d8
2009-08-05 17:39:44 +00:00
Daniel Dunbar
0c795d6187 Add new helpers for registering targets.
- Less boilerplate == good.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@77052 91177308-0d34-0410-b5e6-96231b3b80d8
2009-07-25 06:49:55 +00:00
Daniel Dunbar
4cb1e13769 Put Target definitions inside Target specific header, and llvm namespace.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@76344 91177308-0d34-0410-b5e6-96231b3b80d8
2009-07-18 23:03:22 +00:00
Daniel Dunbar
51b198af83 Reapply TargetRegistry refactoring commits.
--- Reverse-merging r75799 into '.':
 U   test/Analysis/PointerTracking
U    include/llvm/Target/TargetMachineRegistry.h
U    include/llvm/Target/TargetMachine.h
U    include/llvm/Target/TargetRegistry.h
U    include/llvm/Target/TargetSelect.h
U    tools/lto/LTOCodeGenerator.cpp
U    tools/lto/LTOModule.cpp
U    tools/llc/llc.cpp
U    lib/Target/PowerPC/PPCTargetMachine.h
U    lib/Target/PowerPC/AsmPrinter/PPCAsmPrinter.cpp
U    lib/Target/PowerPC/PPCTargetMachine.cpp
U    lib/Target/PowerPC/PPC.h
U    lib/Target/ARM/ARMTargetMachine.cpp
U    lib/Target/ARM/AsmPrinter/ARMAsmPrinter.cpp
U    lib/Target/ARM/ARMTargetMachine.h
U    lib/Target/ARM/ARM.h
U    lib/Target/XCore/XCoreTargetMachine.cpp
U    lib/Target/XCore/XCoreTargetMachine.h
U    lib/Target/PIC16/PIC16TargetMachine.cpp
U    lib/Target/PIC16/PIC16TargetMachine.h
U    lib/Target/Alpha/AsmPrinter/AlphaAsmPrinter.cpp
U    lib/Target/Alpha/AlphaTargetMachine.cpp
U    lib/Target/Alpha/AlphaTargetMachine.h
U    lib/Target/X86/X86TargetMachine.h
U    lib/Target/X86/X86.h
U    lib/Target/X86/AsmPrinter/X86ATTAsmPrinter.h
U    lib/Target/X86/AsmPrinter/X86AsmPrinter.cpp
U    lib/Target/X86/AsmPrinter/X86IntelAsmPrinter.h
U    lib/Target/X86/X86TargetMachine.cpp
U    lib/Target/MSP430/MSP430TargetMachine.cpp
U    lib/Target/MSP430/MSP430TargetMachine.h
U    lib/Target/CppBackend/CPPTargetMachine.h
U    lib/Target/CppBackend/CPPBackend.cpp
U    lib/Target/CBackend/CTargetMachine.h
U    lib/Target/CBackend/CBackend.cpp
U    lib/Target/TargetMachine.cpp
U    lib/Target/IA64/IA64TargetMachine.cpp
U    lib/Target/IA64/AsmPrinter/IA64AsmPrinter.cpp
U    lib/Target/IA64/IA64TargetMachine.h
U    lib/Target/IA64/IA64.h
U    lib/Target/MSIL/MSILWriter.cpp
U    lib/Target/CellSPU/SPUTargetMachine.h
U    lib/Target/CellSPU/SPU.h
U    lib/Target/CellSPU/AsmPrinter/SPUAsmPrinter.cpp
U    lib/Target/CellSPU/SPUTargetMachine.cpp
U    lib/Target/Mips/AsmPrinter/MipsAsmPrinter.cpp
U    lib/Target/Mips/MipsTargetMachine.cpp
U    lib/Target/Mips/MipsTargetMachine.h
U    lib/Target/Mips/Mips.h
U    lib/Target/Sparc/AsmPrinter/SparcAsmPrinter.cpp
U    lib/Target/Sparc/SparcTargetMachine.cpp
U    lib/Target/Sparc/SparcTargetMachine.h
U    lib/ExecutionEngine/JIT/TargetSelect.cpp
U    lib/Support/TargetRegistry.cpp


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@75820 91177308-0d34-0410-b5e6-96231b3b80d8
2009-07-15 20:24:03 +00:00
Stuart Hastings
2286f8dc4c Revert 75762, 75763, 75766..75769, 75772..75775, 75778, 75780, 75782 to repair broken LLVM-GCC build.
Will revert 75770 in the llvm-gcc trunk.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@75799 91177308-0d34-0410-b5e6-96231b3b80d8
2009-07-15 17:27:11 +00:00
Daniel Dunbar
4246790aa8 Register Target's TargetMachine and AsmPrinter in the new registry.
- This abuses TargetMachineRegistry's constructor for now, this will get
   cleaned up in time.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@75762 91177308-0d34-0410-b5e6-96231b3b80d8
2009-07-15 09:22:31 +00:00
David Greene
71847813bc Have asm printers use formatted_raw_ostream directly to avoid a
dynamic_cast<>.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@75670 91177308-0d34-0410-b5e6-96231b3b80d8
2009-07-14 20:18:05 +00:00
Torok Edwin
c23197a26f llvm_unreachable->llvm_unreachable(0), LLVM_UNREACHABLE->llvm_unreachable.
This adds location info for all llvm_unreachable calls (which is a macro now) in
!NDEBUG builds.
In NDEBUG builds location info and the message is off (it only prints
"UREACHABLE executed").


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@75640 91177308-0d34-0410-b5e6-96231b3b80d8
2009-07-14 16:55:14 +00:00
Torok Edwin
c25e7581b9 assert(0) -> LLVM_UNREACHABLE.
Make llvm_unreachable take an optional string, thus moving the cerr<< out of
line.
LLVM_UNREACHABLE is now a simple wrapper that makes the message go away for
NDEBUG builds.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@75379 91177308-0d34-0410-b5e6-96231b3b80d8
2009-07-11 20:10:48 +00:00
Evan Cheng
06e16587eb Add a thumb2 pass to insert IT blocks.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@75218 91177308-0d34-0410-b5e6-96231b3b80d8
2009-07-10 01:54:42 +00:00
Bruno Cardoso Lopes
ac57e6e498 Add the Object Code Emitter class. Original patch by Aaron Gray, I did some
cleanup, removed some #includes and moved Object Code Emitter out-of-line.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@74813 91177308-0d34-0410-b5e6-96231b3b80d8
2009-07-06 05:09:34 +00:00
Daniel Dunbar
5bcc8bd0c6 Remove unused AsmPrinter OptLevel argument, and propogate.
- This more or less amounts to a revert of r65379. I'm curious to know what
   happened that caused this variable to become unused.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@74579 91177308-0d34-0410-b5e6-96231b3b80d8
2009-07-01 01:48:54 +00:00
Anton Korobeynikov
d49ea77cbc Split thumb-related stuff into separate classes.
Step 1: ARMInstructionInfo => {ARM,Thumb}InstructionInfo

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@74329 91177308-0d34-0410-b5e6-96231b3b80d8
2009-06-26 21:28:53 +00:00
Evan Cheng
e7d6df7353 Add a ARM specific pre-allocation pass that re-schedule loads / stores from
consecutive addresses togther. This makes it easier for the post-allocation pass
to form ldm / stm.

This is step 1. We are still missing a lot of ldm / stm opportunities because
of register allocation are not done in the desired order. More enhancements
coming.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@73291 91177308-0d34-0410-b5e6-96231b3b80d8
2009-06-13 09:12:55 +00:00
Bruno Cardoso Lopes
434dd4fd94 Fix new CodeEmitter stuff to follow LLVM codying style. Patch by Aaron Gray
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@72697 91177308-0d34-0410-b5e6-96231b3b80d8
2009-06-01 19:57:37 +00:00
Bruno Cardoso Lopes
a3f99f9033 First patch in the direction of splitting MachineCodeEmitter in two subclasses:
JITCodeEmitter and ObjectCodeEmitter. No functional changes yet. Patch by Aaron Gray



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@72631 91177308-0d34-0410-b5e6-96231b3b80d8
2009-05-30 20:51:52 +00:00
Bill Wendling
98a366d547 Instead of passing in an unsigned value for the optimization level, use an enum,
which better identifies what the optimization is doing. And is more flexible for
future uses.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@70440 91177308-0d34-0410-b5e6-96231b3b80d8
2009-04-29 23:29:43 +00:00
Bill Wendling
be8cc2a3de Second attempt:
Massive check in. This changes the "-fast" flag to "-O#" in llc. If you want to
use the old behavior, the flag is -O0. This change allows for finer-grained
control over which optimizations are run at different -O levels.

Most of this work was pretty mechanical. The majority of the fixes came from
verifying that a "fast" variable wasn't used anymore. The JIT still uses a
"Fast" flag. I'll change the JIT with a follow-up patch.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@70343 91177308-0d34-0410-b5e6-96231b3b80d8
2009-04-29 00:15:41 +00:00
Bill Wendling
c69d56f115 r70270 isn't ready yet. Back this out. Sorry for the noise.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@70275 91177308-0d34-0410-b5e6-96231b3b80d8
2009-04-28 01:04:53 +00:00
Bill Wendling
2e9d5f912a Massive check in. This changes the "-fast" flag to "-O#" in llc. If you want to
use the old behavior, the flag is -O0. This change allows for finer-grained
control over which optimizations are run at different -O levels.

Most of this work was pretty mechanical. The majority of the fixes came from
verifying that a "fast" variable wasn't used anymore. The JIT still uses a
"Fast" flag. I'm not 100% sure if it's necessary to change it there...


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@70270 91177308-0d34-0410-b5e6-96231b3b80d8
2009-04-28 00:21:31 +00:00
Evan Cheng
42bf74be14 CodeGen still defaults to non-verbose asm, but llc now overrides it and default to verbose.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@67668 91177308-0d34-0410-b5e6-96231b3b80d8
2009-03-25 01:47:28 +00:00
Bill Wendling
57f0db833d Overhaul my earlier submission due to feedback. It's a large patch, but most of
them are generic changes.

- Use the "fast" flag that's already being passed into the asm printers instead
  of shoving it into the DwarfWriter.

- Instead of calling "MI->getParent()->getParent()" for every MI, set the
  machine function when calling "runOnMachineFunction" in the asm printers.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@65379 91177308-0d34-0410-b5e6-96231b3b80d8
2009-02-24 08:30:20 +00:00
Dan Gohman
d68a07650c Tidy up #includes, deleting a bunch of unnecessary #includes.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@61715 91177308-0d34-0410-b5e6-96231b3b80d8
2009-01-05 17:59:02 +00:00