Commit Graph

79 Commits

Author SHA1 Message Date
Evan Cheng
020f4106f8 Model ARM predicated write as read-mod-write. e.g.
r0 = mov #0
r0 = moveq #1

Then the second instruction has an implicit data dependency on the first
instruction. Sadly I have yet to come up with a small test case that
demonstrate the post-ra scheduler taking advantage of this.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146583 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-14 20:00:08 +00:00
Evan Cheng
12dfdb424d Allow target to specify register output dependency. Still default to one.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146547 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-14 02:28:53 +00:00
Evan Cheng
ddfd1377d2 - Add MachineInstrBundle.h and MachineInstrBundle.cpp. This includes a function
to finalize MI bundles (i.e. add BUNDLE instruction and computing register def
  and use lists of the BUNDLE instruction) and a pass to unpack bundles.
- Teach more of MachineBasic and MachineInstr methods to be bundle aware.
- Switch Thumb2 IT block to MI bundles and delete the hazard recognizer hack to
  prevent IT blocks from being broken apart.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146542 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-14 02:11:42 +00:00
Evan Cheng
5a96b3dad2 Add bundle aware API for querying instruction properties and switch the code
generator to it. For non-bundle instructions, these behave exactly the same
as the MC layer API.

For properties like mayLoad / mayStore, look into the bundle and if any of the
bundled instructions has the property it would return true.
For properties like isPredicable, only return true if *all* of the bundled
instructions have the property.
For properties like canFoldAsLoad, isCompare, conservatively return false for
bundles.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146026 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-07 07:15:52 +00:00
Evan Cheng
7c2a4a30e0 First chunk of MachineInstr bundle support.
1. Added opcode BUNDLE
2. Taught MachineInstr class to deal with bundled MIs
3. Changed MachineBasicBlock iterator to skip over bundled MIs; added an iterator to walk all the MIs
4. Taught MachineBasicBlock methods about bundled MIs


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@145975 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-06 22:12:01 +00:00
Hal Finkel
db809e0eb7 make sure ScheduleDAGInstrs::EmitSchedule does not crash when the first instruction in Sequence is a Noop
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@145677 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-02 04:58:07 +00:00
Andrew Trick
e8deca83c1 PostRA scheduler fix. Clear stale loop dependencies.
Fixes <rdar://problem/10235725>


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@141357 91177308-0d34-0410-b5e6-96231b3b80d8
2011-10-07 06:33:09 +00:00
Andrew Trick
4563bbaba7 whitespace
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@141356 91177308-0d34-0410-b5e6-96231b3b80d8
2011-10-07 06:27:02 +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
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
e837dead3c - Rename TargetInstrDesc, TargetOperandInfo to MCInstrDesc and MCOperandInfo and
sink them into MC layer.
- Added MCInstrInfo, which captures the tablegen generated static data. Chang
TargetInstrInfo so it's based off MCInstrInfo.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@134021 91177308-0d34-0410-b5e6-96231b3b80d8
2011-06-28 19:10:37 +00:00
Devang Patel
ee1f87881b Remove dead code.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@132488 91177308-0d34-0410-b5e6-96231b3b80d8
2011-06-02 21:31:00 +00:00
Devang Patel
e29e8e100e Update DBG_VALUEs while breaking anti dependencies.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@132487 91177308-0d34-0410-b5e6-96231b3b80d8
2011-06-02 21:26:52 +00:00
Devang Patel
cf4cc84738 During post RA scheduling, do not try to chase reg defs. to preserve DBG_VALUEs. This approach has several downsides, for example, it does not work when dbg value is a constant integer, it does not work if reg is defined more than once, it places end of debug value range markers in the wrong place. It even causes misleading incorrect debug info when duplicate DBG_VALUE instructions point to same reg def.
Instead, use simpler approach and let DBG_VALUE follow its predecessor instruction. After live debug value analysis pass, all DBG_VALUE instruction are placed at the right place. Thanks Jakob for the hint!


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@132483 91177308-0d34-0410-b5e6-96231b3b80d8
2011-06-02 20:07:12 +00:00
Andrew Trick
9b668535a8 Added an assertion, and updated a comment.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@131022 91177308-0d34-0410-b5e6-96231b3b80d8
2011-05-06 21:52:52 +00:00
Andrew Trick
ee10915892 ARM post RA scheduler compile time fix.
BuildSchedGraph was quadratic in the number of calls in the basic
block. After this fix, it keeps only a single call at the top of the
DefList so compile time doesn't blow up on large blocks. This reduces
postRA sched time on an external test case from 81s to 0.3s.  Although
r130800 (reduced ARM register alias defs) also partially fixes the
issue by reducing the constant overhead of checking call interference
by an order of magnitude.

Fixes <rdar://problem/7662664> very poor compile time with post RA scheduling.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@130943 91177308-0d34-0410-b5e6-96231b3b80d8
2011-05-05 19:32:21 +00:00
Andrew Trick
f405b1ad19 whitespace
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@130942 91177308-0d34-0410-b5e6-96231b3b80d8
2011-05-05 19:24:06 +00:00
Chris Lattner
7a2bdde0a0 Fix a ton of comment typos found by codespell. Patch by
Luis Felipe Strano Moraes!



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@129558 91177308-0d34-0410-b5e6-96231b3b80d8
2011-04-15 05:18:47 +00:00
Evan Cheng
c36b7069b4 Do not model all INLINEASM instructions as having unmodelled side effects.
Instead encode llvm IR level property "HasSideEffects" in an operand (shared
with IsAlignStack). Added MachineInstrs::hasUnmodeledSideEffects() to check
the operand when the instruction is an INLINEASM.

This allows memory instructions to be moved around INLINEASM instructions.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@123044 91177308-0d34-0410-b5e6-96231b3b80d8
2011-01-07 23:50:32 +00:00
Dan Gohman
5034dd318a Move Value::getUnderlyingObject to be a standalone
function so that it can live in Analysis instead of
VMCore.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@121885 91177308-0d34-0410-b5e6-96231b3b80d8
2010-12-15 20:02:24 +00:00
Evan Cheng
8239daf7c8 Two sets of changes. Sorry they are intermingled.
1. Fix pre-ra scheduler so it doesn't try to push instructions above calls to
   "optimize for latency". Call instructions don't have the right latency and
   this is more likely to use introduce spills.
2. Fix if-converter cost function. For ARM, it should use instruction latencies,
   not # of micro-ops since multi-latency instructions is completely executed
   even when the predicate is false. Also, some instruction will be "slower"
   when they are predicated due to the register def becoming implicit input.
   rdar://8598427


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@118135 91177308-0d34-0410-b5e6-96231b3b80d8
2010-11-03 00:45:17 +00:00
Evan Cheng
de5fa932b9 Putting r117193 back except for the compile time cost. Rather than assuming fallthroughs uses all registers, just gather the union of all successor liveins.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@117506 91177308-0d34-0410-b5e6-96231b3b80d8
2010-10-27 23:17:17 +00:00
Evan Cheng
38fd9f2a2d Neuter r117193 as it causes significant post-ra scheduler compile time regression.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@117329 91177308-0d34-0410-b5e6-96231b3b80d8
2010-10-25 23:56:21 +00:00
Evan Cheng
ec6906ba47 Properly model the latency of register defs which are 1) function returns or
2) live-outs.

Previously the post-RA schedulers completely ignore these dependencies since
returns, branches, etc. are all scheduling barriers. This patch model the
latencies between instructions being scheduled and the barriers. It also
handle calls by marking their register uses.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@117193 91177308-0d34-0410-b5e6-96231b3b80d8
2010-10-23 02:10:46 +00:00
Evan Cheng
d82de8341c Avoid compiler warning: comparison between signed and unsigned integer.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@116119 91177308-0d34-0410-b5e6-96231b3b80d8
2010-10-08 23:01:57 +00:00
Evan Cheng
1aca5bc135 Fix operand latency computation in cases where the definition operand is
implicit. e.g.
%D6<def>, %D7<def> = VLD1q16 %R2<kill>, 0, ..., %Q3<imp-def>                                                                                                                                                                              
%Q1<def> = VMULv8i16 %Q1<kill>, %Q3<kill>, ...

The real definition indices are 0,1.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@116080 91177308-0d34-0410-b5e6-96231b3b80d8
2010-10-08 18:42:25 +00:00
Nick Lewycky
9c220fc165 Remove unused variables.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@115802 91177308-0d34-0410-b5e6-96231b3b80d8
2010-10-06 18:11:50 +00:00
Evan Cheng
a0792de66c - Add TargetInstrInfo::getOperandLatency() to compute operand latencies. This
allow target to correctly compute latency for cases where static scheduling
  itineraries isn't sufficient. e.g. variable_ops instructions such as
  ARM::ldm.
  This also allows target without scheduling itineraries to compute operand
  latencies. e.g. X86 can return (approximated) latencies for high latency
  instructions such as division.
- Compute operand latencies for those defined by load multiple instructions,
  e.g. ldm and those used by store multiple instructions, e.g. stm.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@115755 91177308-0d34-0410-b5e6-96231b3b80d8
2010-10-06 06:27:31 +00:00
Evan Cheng
3881cb7a5d Model Cortex-a9 load to SUB, RSB, ADD, ADC, SBC, RSC, CMN, MVN, or CMP
pipeline forwarding path.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@115098 91177308-0d34-0410-b5e6-96231b3b80d8
2010-09-29 22:42:35 +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
Bob Wilson
f28dd88611 Change ScheduleDAGInstrs::Defs and ::Uses to be variable-size vectors
instead of fixed size arrays, so that increasing FirstVirtualRegister to 16K
won't cause a compile time performance regression.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@109330 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-24 06:01:53 +00:00
Bill Wendling
87ea294b0d Use std::vector instead of TargetRegisterInfo::FirstVirtualRegister.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@108452 91177308-0d34-0410-b5e6-96231b3b80d8
2010-07-15 20:04:36 +00:00
Jim Grosbach
309d20c89c Fix the post-RA instruction scheduler to handle instructions referenced by
more than one dbg_value instruction. rdar://7759363


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@104174 91177308-0d34-0410-b5e6-96231b3b80d8
2010-05-19 22:57:06 +00:00
Dan Gohman
af1d8ca44a Get rid of the EdgeMapping map. Instead, just check for BasicBlock
changes before doing phi lowering for switches.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@102809 91177308-0d34-0410-b5e6-96231b3b80d8
2010-05-01 00:01:06 +00:00
Dan Gohman
3fb150a902 Fix -Wcast-qual warnings.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@101655 91177308-0d34-0410-b5e6-96231b3b80d8
2010-04-17 17:42:52 +00:00
Evan Cheng
a69ec09364 Reduce indentation.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@99214 91177308-0d34-0410-b5e6-96231b3b80d8
2010-03-22 21:24:33 +00:00
Evan Cheng
fc91114a2e 80 col violation.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@99195 91177308-0d34-0410-b5e6-96231b3b80d8
2010-03-22 18:40:50 +00:00
Dale Johannesen
bfdf7f3852 Progress towards shepherding debug info through SelectionDAG.
No functional effect yet.  This is still evolving and should
not be viewed as final.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@98195 91177308-0d34-0410-b5e6-96231b3b80d8
2010-03-10 22:13:47 +00:00
Duncan Sands
1df9859c40 There are two ways of checking for a given type, for example isa<PointerType>(T)
and T->isPointerTy().  Convert most instances of the first form to the second form.
Requested by Chris.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@96344 91177308-0d34-0410-b5e6-96231b3b80d8
2010-02-16 11:11:14 +00:00
David Goodwin
980d494ab6 Fix dependencies added to model memory aliasing for post-RA scheduling. The dependencies were overly conservative for memory access that are known not to alias.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@86580 91177308-0d34-0410-b5e6-96231b3b80d8
2009-11-09 19:22:17 +00:00
David Goodwin
5be870add9 Correctly add chain dependencies around calls and unknown-side-effect instructions.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@86080 91177308-0d34-0410-b5e6-96231b3b80d8
2009-11-05 00:16:44 +00:00
David Goodwin
a9e610768b <rdar://problem/7352605>. When building schedule graph use mayAlias information to avoid chaining loads/stores of spill slots with non-aliased memory ops.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@85934 91177308-0d34-0410-b5e6-96231b3b80d8
2009-11-03 20:15:00 +00:00
David Goodwin
7c9b1ac507 Chain dependencies used to enforce memory order should have latency of 0 (except for true dependency of Store followed by aliased Load... we estimate that case with a single cycle of latency assuming the hardware will bypass)
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@85807 91177308-0d34-0410-b5e6-96231b3b80d8
2009-11-02 17:06:28 +00:00
Dan Gohman
91203cf87b When checking whether a def of an aliased register is dead, ask the
machineinstr whether the aliased register is dead, rather than the original
register is dead. This allows it to get the correct answer when examining
an instruction like this:
  CALLpcrel32 <ga:foo>, %AL<imp-def>, %EAX<imp-def,dead>
where EAX is dead but a subregister of it is still live. This fixes PR5294.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@85135 91177308-0d34-0410-b5e6-96231b3b80d8
2009-10-26 18:26:18 +00:00
Evan Cheng
38bdfc69cb Spill slots cannot alias.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@84432 91177308-0d34-0410-b5e6-96231b3b80d8
2009-10-18 19:58:47 +00:00
Evan Cheng
ff89dcb06f -Revert parts of 84326 and 84411. Distinquishing between fixed and non-fixed
stack slots and giving them different PseudoSourceValue's did not fix the
problem of post-alloc scheduling miscompiling llvm itself.
- Apply Dan's conservative workaround by assuming any non fixed stack slots can
alias other memory locations. This means a load from spill slot #1 cannot 
move above a store of spill slot #2. 
- Enable post-alloc scheduling for x86 at optimization leverl Default and above.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@84424 91177308-0d34-0410-b5e6-96231b3b80d8
2009-10-18 18:16:27 +00:00
Dan Gohman
a70dca156f Factor out LiveIntervalAnalysis' code to determine whether an instruction
is trivially rematerializable and integrate it into
TargetInstrInfo::isTriviallyReMaterializable. This way, all places that
need to know whether an instruction is rematerializable will get the
same answer.

This enables the useful parts of the aggressive-remat option by
default -- using AliasAnalysis to determine whether a memory location
is invariant, and removes the questionable parts -- rematting operations
with virtual register inputs that may not be live everywhere.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@83687 91177308-0d34-0410-b5e6-96231b3b80d8
2009-10-09 23:27:56 +00:00
Dan Gohman
e33f44cfc5 Replace TargetInstrInfo::isInvariantLoad and its target-specific
implementations with a new MachineInstr::isInvariantLoad, which uses
MachineMemOperands and is target-independent. This brings MachineLICM
and other functionality to targets which previously lacked an
isInvariantLoad implementation.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@83475 91177308-0d34-0410-b5e6-96231b3b80d8
2009-10-07 17:38:06 +00:00
Dan Gohman
c76909abfe Improve MachineMemOperand handling.
- Allocate MachineMemOperands and MachineMemOperand lists in MachineFunctions.
   This eliminates MachineInstr's std::list member and allows the data to be
   created by isel and live for the remainder of codegen, avoiding a lot of
   copying and unnecessary translation. This also shrinks MemSDNode.
 - Delete MemOperandSDNode. Introduce MachineSDNode which has dedicated
   fields for MachineMemOperands.
 - Change MemSDNode to have a MachineMemOperand member instead of its own
   fields with the same information. This introduces some redundancy, but
   it's more consistent with what MachineInstr will eventually want.
 - Ignore alignment when searching for redundant loads for CSE, but remember
   the greatest alignment.

Target-specific code which previously used MemOperandSDNodes with generic
SDNodes now use MemIntrinsicSDNodes, with opcodes in a designated range
so that the SelectionDAG framework knows that MachineMemOperand information
is available.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@82794 91177308-0d34-0410-b5e6-96231b3b80d8
2009-09-25 20:36:54 +00:00
Evan Cheng
fb2e752e41 Enhance EmitInstrWithCustomInserter() so target can specify CFG changes that sdisel will use to properly complete phi nodes.
Not functionality change yet.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@82273 91177308-0d34-0410-b5e6-96231b3b80d8
2009-09-18 21:02:19 +00:00