Keep track of the last instruction to define each register individually
instead of per DomainValue.  This lets us track more accurately when a
register was last written.

Also track register ages across basic blocks.  When entering a new
basic block, use the least stale predecessor def as a worst case
estimate for register age.

The register age is used to arbitrate between conflicting domains. The
most recently defined register wins.

llvm-svn: 144601

During the initial RPO traversal of the basic blocks, remember the ones
that are incomplete because of back-edges from predecessors that haven't
been visited yet.

After the initial RPO, revisit all those loop headers so the incoming
DomainValues on the back-edges can be properly collapsed.

This will properly fix execution domains on software pipelined code,
like the included test case.

llvm-svn: 144151

When merging two uncollapsed DomainValues, place a link to the active
DomainValue from the passive DomainValue.  This allows old stale
references to the passive DomainValue to be updated to point to the
active DomainValue.

The new resolve() function finds the active DomainValue and updates the
pointer.

This change makes old live-out lists more useful since they may contain
uncollapsed DomainValues that have since been merged into other
DomainValues.

llvm-svn: 144149

This allows clear() to be called on a DomainValue with references.

llvm-svn: 144147

There is no need to involve the LiveRegs array and kill() any longer.

llvm-svn: 144133

No functional change.

llvm-svn: 144132

This new function will decrement the reference count, and collapse a
domain value when the last reference is gone.

This simplifies DomainValue reference counting, and decouples it from
the LiveRegs array.

llvm-svn: 144131

The old value may still be referenced by some live-out list, and we
don't wan't to collapse those instructions twice.

This fixes the "Can only swizzle VMOVD" assertion in some armv7 SPEC
builds.

<rdar://problem/10413292>

llvm-svn: 144117

DomainValues that are only used by "don't care" instructions are now
collapsed to the first possible execution domain after all basic blocks
have been processed.  This typically means the PS domain on x86.

For example, the vsel_i64 and vsel_double functions in sse2-blend.ll are
completely collapsed to the PS domain instead of containing a mix of
execution domains created by isel.

llvm-svn: 144037

The enterBasicBlock() function is combining live-out values from
predecessor blocks.  The RPO traversal means that more predecessors
have been visited when that happens, only back-edges are missing.

llvm-svn: 144025

llvm-svn: 144020

llvm-svn: 144015

llvm-svn: 144014

No functional change intended.

llvm-svn: 140664

I'll clean up the source in the next commit.

llvm-svn: 140663

This also enables domain swizzling for AVX code which required a few
trivial test changes.

The pass will be moved to lib/CodeGen shortly.

llvm-svn: 140659

I am going to unify the SSEDomainFix and NEONMoveFix passes into a
single target independent pass.  They are essentially doing the same
thing.

llvm-svn: 140652

llvm-svn: 110460

llvm-svn: 110410

ID member as the sole unique type identifier.  Clean up APIs related to this change.

llvm-svn: 110396

This means that our Registers are now ordered R7, R8, R9, R10, R12, ...
Not R1, R10, R11, R12, R2, R3, ...

llvm-svn: 104745

MachineBasicBlock::livein_iterator a const_iterator, because
clients shouldn't ever be using the iterator interface to
mutate the livein set.

llvm-svn: 101147

solution.  The only reason these don't fire with gcc-4.2 is that gcc turns off
part of -Wsign-compare in C++ on accident.

llvm-svn: 100581

This fixes the Bullet regression on i386/nocona.

llvm-svn: 100553

Restrict bit mask operations to the DomainValue class. Rename methods for
clarity.

llvm-svn: 100353

llvm-svn: 100332

llvm-svn: 100042

llvm-svn: 100037

llvm-svn: 100016

llvm-svn: 99974

llvm-svn: 99916

llvm-svn: 99855

Cross-block inference is primitive and wrong, but the pass is working otherwise.

llvm-svn: 99848

llvm-svn: 99542

On Nehalem and newer CPUs there is a 2 cycle latency penalty on using a register
in a different domain than where it was defined. Some instructions have
equvivalents for different domains, like por/orps/orpd.

The SSEDomainFix pass tries to minimize the number of domain crossings by
changing between equvivalent opcodes where possible.

This is a work in progress, in particular the pass doesn't do anything yet. SSE
instructions are tagged with their execution domain in TableGen using the last
two bits of TSFlags. Note that not all instructions are tagged correctly. Life
just isn't that simple.

The SSE execution domain issue is very similar to the ARM NEON/VFP pipeline
issue handled by NEONMoveFixPass. This pass may become target independent to
handle both.

llvm-svn: 99524

This reverts commit 99345. It was breaking buildbots.

llvm-svn: 99352

This is work in progress. So far, SSE execution domain tables are added to
X86InstrInfo, and a skeleton pass is enabled with -sse-domain-fix.

llvm-svn: 99345