llvm-svn: 109045

TII::isMoveInstr is going tobe completely removed.

llvm-svn: 108507

EXTRACT_SUBREG no longer appears as a machine instruction. Use COPY instead.

Add isCopy() checks in many places using isMoveInstr() and isExtractSubreg().
The isMoveInstr hook will be removed later.

llvm-svn: 107879

This code is transitional, it will soon be possible to eliminate
isExtractSubreg, isInsertSubreg, and isMoveInstr in most places.

llvm-svn: 107547

llvm-svn: 105502

llvm-svn: 105399

llvm-svn: 105308

Evan please verify!

llvm-svn: 104408

Allow machine cse to cse instructions which define physical registers. Controlled by option -machine-cse-phys-defs.

llvm-svn: 104385

use of it in MachineCSE.

llvm-svn: 103726

llvm-svn: 101964

llvm-svn: 101914

After trivial coalescing, the MI being visited may have become a copy. Avoid adding it to CSE hash table since copies aren't being considered for CSE and they may be deleted.
rdar://7819990

llvm-svn: 100170

llvm-svn: 99378

llvm-svn: 99319

llvm-svn: 98224

1. Be careful with cse "cheap" expressions. e.g. constant materialization. Only cse them when the common expression is local or in a direct predecessor. We don't want cse of cheap instruction causing other expressions to be spilled.
2. Watch out for the case where the expression doesn't itself uses a virtual register. e.g. lea of frame object. If the common expression itself is used by copies (common for passing addresses to function calls), don't perform the cse. Since these expressions do not use a register, it creates a live range but doesn't close any, we want to be very careful with increasing register pressure.

Note these are heuristics so machine cse doesn't make register allocator unhappy. Once we have proper live range splitting and re-materialization support in place, these should be evaluated again.

Now machine cse is almost always a win on llvm nightly tests on x86 and x86_64.

llvm-svn: 98121

llvm-svn: 98048

llvm-svn: 98044

  coalescer) handle sub-register classes.
- Add heuristics to avoid non-profitable cse. Given the current lack of live
  range splitting, avoid cse when an expression has PHI use and the would be
  new use is in a BB where the expression wasn't already being used.

llvm-svn: 98043

Don't waste time trying to CSE labels, phis, inline asm. Definitely avoid cse implicit-def for obvious performance reason.

llvm-svn: 98009

llvm-svn: 98007

llvm-svn: 97861

llvm-svn: 97747

Look ahead a bit to determine if a physical register def that is not marked dead is really alive. This is necessary to catch a lot of common cse opportunities for targets like x86.

llvm-svn: 97706

Fix a logic error. An instruction that has a live physical register def cannot be CSE'ed, but it *can* be used to replace a common subexpression.

llvm-svn: 97688

Re-apply r97667 but with a little bit of thought put into the patch. This implements a special DenseMapInfo trait for DenseMap<MachineInstr*> that compare the value of the MachineInstr rather than the pointer value. Since the hashing and equality test functions ignore defs it's useful for doing CSE kind optimization.

llvm-svn: 97678

llvm-svn: 97673

llvm-svn: 97667

Machine CSE work in progress. It's doing some CSE now. But implicit def of physical registers are getting in the way.

llvm-svn: 97664

llvm-svn: 97635

llvm-svn: 97577

llvm-svn: 97543