Commit Graph

96 Commits

Author SHA1 Message Date
Evan Cheng
bee78fe5fc Clean up ARM fused multiply + add/sub support some more: rename some isel
predicates.
Also remove NEON2 since it's not really useful and it is confusing. If
NEON + VFP4 implies NEON2 but NEON2 doesn't imply NEON + VFP4, what does it
really mean?

rdar://10139676


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154480 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-11 05:33:07 +00:00
Evan Cheng
82509e5c62 Fix a number of problems with ARM fused multiply add/subtract instructions.
1. The new instruction itinerary entries are not properly described.
2. The asm parser can't handle vfms and vfnms.
3. There were no assembler, disassembler test cases.
4. HasNEON2 has the wrong assembler predicate.
rdar://10139676


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154456 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-11 00:13:00 +00:00
Sebastian Pop
74bebde7c4 updated patch for the ARM fused multiply add/sub
In this update:
- I assumed neon2 does not imply vfpv4, but neon and vfpv4 imply neon2.
- I kept setting .fpu=neon-vfpv4 code attribute because that is what the
assembler understands.

Patch by Ana Pazos <apazos@codeaurora.org>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@152036 91177308-0d34-0410-b5e6-96231b3b80d8
2012-03-05 17:39:52 +00:00
Evan Cheng
4bfcd4acbc Re-commit r151623 with fix. Only issue special no-return calls if it's a direct call.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@151645 91177308-0d34-0410-b5e6-96231b3b80d8
2012-02-28 18:51:51 +00:00
Daniel Dunbar
20bd5296ce Revert r151623 "Some ARM implementaions, e.g. A-series, does return stack prediction. ...", it is breaking the Clang build during the Compiler-RT part.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@151630 91177308-0d34-0410-b5e6-96231b3b80d8
2012-02-28 15:36:07 +00:00
Evan Cheng
ec52aaa12f Some ARM implementaions, e.g. A-series, does return stack prediction. That is,
the processor keeps a return addresses stack (RAS) which stores the address
and the instruction execution state of the instruction after a function-call
type branch instruction.

Calling a "noreturn" function with normal call instructions (e.g. bl) can
corrupt RAS and causes 100% return misprediction so LLVM should use a
unconditional branch instead. i.e.
mov lr, pc
b _foo
The "mov lr, pc" is issued in order to get proper backtrace.

rdar://8979299


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@151623 91177308-0d34-0410-b5e6-96231b3b80d8
2012-02-28 06:42:03 +00:00
Jia Liu
31d157ae1a Emacs-tag and some comment fix for all ARM, CellSPU, Hexagon, MBlaze, MSP430, PPC, PTX, Sparc, X86, XCore.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@150878 91177308-0d34-0410-b5e6-96231b3b80d8
2012-02-18 12:03:15 +00:00
Anton Korobeynikov
4b4e62219b Add fused multiple+add instructions from VFPv4.
Patch by Ana Pazos!


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@148658 91177308-0d34-0410-b5e6-96231b3b80d8
2012-01-22 12:07:33 +00:00
Evan Cheng
afff941211 ARM target code clean up. Check for iOS, not Darwin where it makes sense.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146981 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-20 18:26:50 +00:00
Evan Cheng
44ee4714a8 Hide cpu name checking in ARMSubtarget.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@144154 91177308-0d34-0410-b5e6-96231b3b80d8
2011-11-09 01:57:03 +00:00
David Meyer
928698b14e Remove NaClMode
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@142338 91177308-0d34-0410-b5e6-96231b3b80d8
2011-10-18 05:29:23 +00:00
Bob Wilson
6d2f9cec71 Reenable tail calls for iOS 5.0 and later.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@141370 91177308-0d34-0410-b5e6-96231b3b80d8
2011-10-07 17:17:49 +00:00
James Molloy
acad68da50 Check in a patch that has already been code reviewed by Owen that I'd forgotten to commit.
Build on previous patches to successfully distinguish between an M-series and A/R-series MSR and MRS instruction. These take different mask names and have a *slightly* different opcode format.

Add decoder and disassembler tests.

Improvement on the previous patch - successfully distinguish between valid v6m and v7m masks (one is a subset of the other). The patch had to be edited slightly to apply to ToT.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@140696 91177308-0d34-0410-b5e6-96231b3b80d8
2011-09-28 14:21:38 +00:00
Nick Lewycky
1fac6b50ea Add a new MC bit for NaCl (Native Client) mode. NaCl requires that certain
instructions are more aligned than the CPU requires, and adds some additional
directives, to follow in future patches. Patch by David Meyer!


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@139125 91177308-0d34-0410-b5e6-96231b3b80d8
2011-09-05 21:51:43 +00:00
Evan Cheng
4761a8d654 Rewrite comment in English.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@134627 91177308-0d34-0410-b5e6-96231b3b80d8
2011-07-07 19:09:06 +00:00
Evan Cheng
963b03c1a9 Rename attribute 'thumb' to a more descriptive 'thumb-mode'.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@134626 91177308-0d34-0410-b5e6-96231b3b80d8
2011-07-07 19:05:12 +00:00
Evan Cheng
0ddff1b535 Compute feature bits at time of MCSubtargetInfo initialization.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@134606 91177308-0d34-0410-b5e6-96231b3b80d8
2011-07-07 07:07:08 +00:00
Evan Cheng
39dfb0ff84 Change some ARM subtarget features to be single bit yes/no in order to sink them down to MC layer. Also fix tests.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@134590 91177308-0d34-0410-b5e6-96231b3b80d8
2011-07-07 03:55:05 +00:00
Evan Cheng
94ca42ff04 Factor ARM triple parsing out of ARMSubtarget. Another step towards making ARM subtarget info available to MC.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@134569 91177308-0d34-0410-b5e6-96231b3b80d8
2011-07-07 00:08:19 +00:00
Evan Cheng
385e930d55 Rename XXXGenSubtarget.inc to XXXGenSubtargetInfo.inc for consistency.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@134281 91177308-0d34-0410-b5e6-96231b3b80d8
2011-07-01 22:36:09 +00:00
Jim Grosbach
a7603982db ARMv7M vs. ARMv7E-M support.
The DSP instructions in the Thumb2 instruction set are an optional extension
in the Cortex-M* archtitecture. When present, the implementation is considered
an "ARMv7E-M implementation," and when not, an "ARMv7-M implementation."

Add a subtarget feature hook for the v7e-m instructions and hook it up. The
cortex-m3 cpu is an example of a v7m implementation, while the cortex-m4 is
a v7e-m implementation.

rdar://9572992



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@134261 91177308-0d34-0410-b5e6-96231b3b80d8
2011-07-01 21:12:19 +00:00
Evan Cheng
5b1b4489cf Rename TargetSubtarget to TargetSubtargetInfo for consistency.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@134259 91177308-0d34-0410-b5e6-96231b3b80d8
2011-07-01 21:01:15 +00:00
Evan Cheng
94214703d9 - Added MCSubtargetInfo to capture subtarget features and scheduling
itineraries.
- Refactor TargetSubtarget to be based on MCSubtargetInfo.
- Change tablegen generated subtarget info to initialize MCSubtargetInfo
  and hide more details from targets.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@134257 91177308-0d34-0410-b5e6-96231b3b80d8
2011-07-01 20:45:01 +00:00
Evan Cheng
276365dd4b Fix the ridiculous SubtargetFeatures API where it implicitly expects CPU name to
be the first encoded as the first feature. It then uses the CPU name to look up
features / scheduling itineray even though clients know full well the CPU name
being used to query these properties.

The fix is to just have the clients explictly pass the CPU name!


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@134127 91177308-0d34-0410-b5e6-96231b3b80d8
2011-06-30 01:53:36 +00:00
Evan Cheng
ab8be96fd3 Sink SubtargetFeature and TargetInstrItineraries (renamed MCInstrItineraries) into MC.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@134049 91177308-0d34-0410-b5e6-96231b3b80d8
2011-06-29 01:14:12 +00:00
Evan Cheng
0b65599015 Revert accidental commit.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@131739 91177308-0d34-0410-b5e6-96231b3b80d8
2011-05-20 17:38:48 +00:00
Evan Cheng
2e6496026f Revert r131664 and fix it in instcombine instead. rdar://9467055
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@131708 91177308-0d34-0410-b5e6-96231b3b80d8
2011-05-20 00:54:37 +00:00
Evan Cheng
c8578948c9 Remove -use-divmod-libcall. Let targets opt in when they are available.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@129884 91177308-0d34-0410-b5e6-96231b3b80d8
2011-04-20 22:20:12 +00:00
Daniel Dunbar
912225e185 ADT/Triple: Move a variety of clients to using isOSDarwin() and isOSWindows()
predicates.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@129816 91177308-0d34-0410-b5e6-96231b3b80d8
2011-04-19 21:14:45 +00:00
Bob Wilson
5dde893c2b Avoid some 's' 16-bit instruction which partially update CPSR
(and add false dependency) when it isn't dependent on last CPSR defining
instruction. rdar://8928208

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@129773 91177308-0d34-0410-b5e6-96231b3b80d8
2011-04-19 18:11:49 +00:00
Evan Cheng
463d358f1d Distribute (A + B) * C to (A * C) + (B * C) to make use of NEON multiplier
accumulator forwarding:
vadd d3, d0, d1
vmul d3, d3, d2
=>
vmul d3, d0, d2
vmla d3, d1, d2


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@128665 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-31 19:38:48 +00:00
Evan Cheng
b72d2a92b7 Clean up ARM subtarget code by using Triple ADT.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@123276 91177308-0d34-0410-b5e6-96231b3b80d8
2011-01-11 21:46:47 +00:00
Andrew Trick
2da8bc8a5f Various bits of framework needed for precise machine-level selection
DAG scheduling during isel. Most new functionality is currently
guarded by -enable-sched-cycles and -enable-sched-hazard.

Added InstrItineraryData::IssueWidth field, currently derived from
ARM itineraries, but could be initialized differently on other targets.

Added ScheduleHazardRecognizer::MaxLookAhead to indicate whether it is
active, and if so how many cycles of state it holds.

Added SchedulingPriorityQueue::HasReadyFilter to allowing gating entry
into the scheduler's available queue.

ScoreboardHazardRecognizer now accesses the ScheduleDAG in order to
get information about it's SUnits, provides RecedeCycle for bottom-up
scheduling, correctly computes scoreboard depth, tracks IssueCount, and
considers potential stall cycles when checking for hazards.

ScheduleDAGRRList now models machine cycles and hazards (under
flags). It tracks MinAvailableCycle, drives the hazard recognizer and
priority queue's ready filter, manages a new PendingQueue, properly
accounts for stall cycles, etc.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@122541 91177308-0d34-0410-b5e6-96231b3b80d8
2010-12-24 05:03:26 +00:00
Andrew Trick
6e8f4c4048 whitespace
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@122539 91177308-0d34-0410-b5e6-96231b3b80d8
2010-12-24 04:28:06 +00:00
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
Evan Cheng
dfed19fe2c Fix preload instruction isel. Only v7 supports pli, and only v7 with mp extension supports pldw. Add subtarget attribute to denote mp extension support and legalize illegal ones to nothing.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@118160 91177308-0d34-0410-b5e6-96231b3b80d8
2010-11-03 06:34:55 +00:00
Bob Wilson
77f42b5278 PR8359: The ARM backend may end up allocating registers D16 to D31 when
"-mattr=+vfp3" is specified. However, this will not work for hardware that
only supports 16 registers.  Add a new flag to support -"mattr=+vfp3,+d16".
Patch by Jan Voung!


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@116310 91177308-0d34-0410-b5e6-96231b3b80d8
2010-10-12 16:22:47 +00:00
Rafael Espindola
0febc4657b Jim Asked us to move DataLayout on ARM back to the most specialized classes. Do
so and also change X86 for consistency.

Investigating if this can be improved a bit.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@115469 91177308-0d34-0410-b5e6-96231b3b80d8
2010-10-03 18:59:45 +00:00
Bob Wilson
7122ba7efb Increase ARM APCS preferred alignment for i64 and f64 from 32 bits to 64 bits.
LDM/STM instructions can run one cycle faster on some ARM processors if the
memory address is 64-bit aligned.  Radar 8489376.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@115047 91177308-0d34-0410-b5e6-96231b3b80d8
2010-09-29 17:54:10 +00:00
Owen Anderson
654d5440a4 Add a subtarget hook for reporting the misprediction penalty. Use this to provide more precise
cost modeling for if-conversion.  Now if only we had a way to estimate the misprediction probability.

Adjsut CodeGen/ARM/ifcvt10.ll.  The pipeline on Cortex-A8 is long enough that it is still profitable
to predicate an ldm, but the shorter pipeline on Cortex-A9 makes it unprofitable.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@114995 91177308-0d34-0410-b5e6-96231b3b80d8
2010-09-28 21:57:50 +00:00
Bob Wilson
02aba73a9e Add a command line option "-arm-strict-align" to disallow unaligned memory
accesses for ARM targets that would otherwise allow it.  Radar 8465431.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@114941 91177308-0d34-0410-b5e6-96231b3b80d8
2010-09-28 04:09:35 +00:00
Daniel Dunbar
3b9569e70d Hard to imagine there are still people using inferior compilers.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@114862 91177308-0d34-0410-b5e6-96231b3b80d8
2010-09-27 20:12:58 +00:00
Rafael Espindola
fd9493d74e Odd additional stub framework for the ARM MC ELF emission.
llc now recognizes the "intent" to support MC/obj emission for ARM, but
given that they are all stubs, it asserts on --filetype=obj --march=arm

Patch by Jason Kim.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@114856 91177308-0d34-0410-b5e6-96231b3b80d8
2010-09-27 18:31:37 +00:00
Evan Cheng
3ef1c8759a Teach if-converter to be more careful with predicating instructions that would
take multiple cycles to decode.
For the current if-converter clients (actually only ARM), the instructions that
are predicated on false are not nops. They would still take machine cycles to
decode. Micro-coded instructions such as LDM / STM can potentially take multiple
cycles to decode. If-converter should take treat them as non-micro-coded
simple instructions.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@113570 91177308-0d34-0410-b5e6-96231b3b80d8
2010-09-10 01:29:16 +00:00
Jim Grosbach
fcba5e6b64 cortex m4 has floating point support, but only single precision.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@110810 91177308-0d34-0410-b5e6-96231b3b80d8
2010-08-11 15:44:15 +00:00
Evan Cheng
7b4d31176e Report error if codegen tries to instantiate a ARM target when the cpu does support it. e.g. cortex-m* processors.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@110798 91177308-0d34-0410-b5e6-96231b3b80d8
2010-08-11 07:17:46 +00:00
Evan Cheng
d6b4632256 Add ARM Archv6M and let it implies FeatureDB (having dmb, etc.)
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@110795 91177308-0d34-0410-b5e6-96231b3b80d8
2010-08-11 06:51:54 +00:00
Evan Cheng
11db068721 - Add subtarget feature -mattr=+db which determine whether an ARM cpu has the
memory and synchronization barrier dmb and dsb instructions.
- Change instruction names to something more sensible (matching name of actual
  instructions).
- Added tests for memory barrier codegen.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@110785 91177308-0d34-0410-b5e6-96231b3b80d8
2010-08-11 06:22:01 +00:00
Evan Cheng
e44be63816 Change -prefer-32bit-thumb to attribute -mattr=+32bit instead to disable more 32-bit to 16-bit optimizations.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@110584 91177308-0d34-0410-b5e6-96231b3b80d8
2010-08-09 18:35:19 +00:00
Evan Cheng
7a41599962 Add an ARM "feature". Cortex-a8 fp comparison is very slow (> 20 cycles).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@108256 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-13 19:21:50 +00:00