llvm-svn: 157060

It is no longer necessary to separate VirtCopies, PhysCopies, and
ImpDefCopies. Implicitly defined copies are extremely rare after we
added the ProcessImplicitDefs pass, and physical register copies are not
joined any longer.

llvm-svn: 157059

This has been disabled for a while, and it is not a feature we want to
support. Copies between physical and virtual registers are eliminated by
good hinting support in the register allocator. Joining virtual and
physical registers is really a form of register allocation, and the
coalescer is not properly equipped to do that. In particular, it cannot
backtrack coalescing decisions, and sometimes that would cause it to
create programs that were impossible to register allocate, by exhausting
a small register class.

It was also very difficult to keep track of the live ranges of aliasing
registers when extending the live range of a physreg. By disabling
physreg joining, we can let fixed physreg live ranges remain constant
throughout the register allocator super-pass.

One type of physreg joining remains: A virtual register that has a
single value which is a copy of a reserved register can be merged into
the reserved physreg. This always lowers register pressure, and since we
don't compute live ranges for reserved registers, there are no problems
with aliases.

llvm-svn: 157055

SelectionDAGBuilder::Clusterify : main functinality was replaced with CRSBuilder::optimize, so big part of Clusterify's code was reduced.

llvm-svn: 157046

non-profitable commute using outdated info. The test case would still fail
because of poor pre-RA schedule. That will be fixed by MI scheduler.

rdar://11472010

llvm-svn: 157038

llvm-svn: 157020

llvm-svn: 157007

Introduce the basic strategy for register pressure scheduling.

1) Respect target limits at all times.

2) Indentify critical register classes (pressure sets).
   Track pressure within the scheduled region.
   Avoid increasing scheduled pressure for critical registers.

3) Avoid exceeding the max pressure of the region prior to scheduling.

Added logic for picking between the top and bottom ready Q's based on
regpressure heuristics.

Status: functional but needs to be asjusted to achieve good results.
llvm-svn: 157006

llvm-svn: 157005

llvm-svn: 157004

llvm-svn: 157003

llvm-svn: 157002

RegisterCoalescer set <undef> flags on all operands of copy instructions
that are scheduled to be removed. This is so they won't affect
shrinkToUses() by introducing false register reads.

Make sure those <undef> flags are never cleared, or shrinkToUses() could
cause live intervals to end at instructions about to be deleted.

This would be a lot simpler if RegisterCoalescer could just erase joined
copies immediately instead of keeping all the to-be-deleted instructions
around.

This fixes PR12862. Unfortunately, bugpoint can't create a sane test
case for this. Like many other coalescer problems, this failure depends
of a very fragile series of events.

<rdar://problem/11474428>

llvm-svn: 157001

Make sure useless (def-only) intervals also get verified.

llvm-svn: 157000

bugpoint-ing, it may turn into something else.

llvm-svn: 156998

SelectionDAGBuilder: CaseBlock, CaseRanges and CaseCmp changed representation of Low and High from signed to unsigned. Since unsigned ints usually simpler, faster and allows to reduce some extra signed bit checks needed before <,>,<=,>= comparisons.

llvm-svn: 156985

When widening an existing <def,reads-undef> operand to a super-register,
it may be necessary to clear the <undef> flag because the wider register
is now read-modify-write through the instruction.

Conversely, it may be necessary to add an <undef> flag when the
coalescer turns a full-register def into a sub-register def, but the
larger register wasn't live before the instruction.

This happens in test/CodeGen/ARM/coalesce-subregs.ll, but the test
is too small for the <undef> flags to affect the generated code.

llvm-svn: 156951

llvm-svn: 156909

It is now possible to coalesce weird skewed sub-register copies by
picking a super-register class larger than both original registers. The
included test case produces code like this:

  vld2.32 {d16, d17, d18, d19}, [r0]!
  vst2.32 {d18, d19, d20, d21}, [r0]

We still perform interference checking as if it were a normal full copy
join, so this is still quite conservative. In particular, the f1 and f2
functions in the included test case still have remaining copies because
of false interference.

llvm-svn: 156878

It is possible to coalesce two overlapping registers to a common
super-register that it larger than both of the original registers.

The important difference is that it may be necessary to rewrite DstReg
operands as well as SrcReg operands because the sub-register index has
changed.

This behavior is still disabled by CoalescerPair.

llvm-svn: 156869

This can happen when widening a virtual register to a super-register
class.

llvm-svn: 156867

There is no need to look at an always null SrcIdx.

llvm-svn: 156866

Now both SrcReg and DstReg can be sub-registers of the final coalesced
register.

CoalescerPair::setRegisters still rejects such copies because
RegisterCoalescer doesn't yet handle them.

llvm-svn: 156848

This feature avoids creating edges in the scheduler's dependence graph
for non-aliasing memory operations according to whichever alias
analysis is available. It has been fully tested in Hexagon. Before
making this default, it needs to be extended to handle multiple
MachineMemOperands, compile time needs more evaluation, and
benchmarking on X86 and ARM is needed.

Patch by Sergei Larin!

llvm-svn: 156842

Add the MCRegisterInfo to the factories and constructors.

Patch by Tom Stellard <Tom.Stellard@amd.com>.

llvm-svn: 156828

llvm-svn: 156808

SelectionDAGBuilder::Clusterify : main functinality was replaced with CRSBuilder::optimize, so big part of Clusterify's code was reduced.

llvm-svn: 156804

This should unbreak llvm-x86_64-linux.

llvm-svn: 156778

RAFast must add an <imp-def> operand when it is rewriting a sub-register
def that isn't a read-modify-write.

llvm-svn: 156777

llvm-svn: 156774

Empty live ranges represent undef and still get allocated, but they
won't appear in LiveIntervalUnions.

Patch by Patrik Hägglund!

llvm-svn: 156685

llvm-svn: 156662

llvm-svn: 156658

This patch will optimize the following cases:
  sub r1, r3 | sub r1, imm
  cmp r3, r1 or cmp r1, r3 | cmp r1, imm
  bge L1

TO
  subs r1, r3
  bge  L1 or ble L1

If the branch instruction can use flag from "sub", then we can replace
"sub" with "subs" and eliminate the "cmp" instruction.

rdar: 10734411
llvm-svn: 156599

but it generates int3 on x86 instead of ud2.

llvm-svn: 156593

llvm-svn: 156576

llvm-svn: 156575

Prioritize the instruction that comes closest to keeping pressure
under the target's limit. Then prioritize instructions that avoid
increasing the max pressure in the scheduled region. The max pressure
heuristic is a tad aggressive. Later I'll fix it to consider the
unscheduled pressure as well.

WIP: This is mostly functional but untested and not likely to do much good yet.
llvm-svn: 156574

llvm-svn: 156573

llvm-svn: 156572