- Get rid of "HasStackProtector" in MachineFrameInfo.
- Modify intrinsics to tell which are doing what with memory.

llvm-svn: 58799

llvm-svn: 58796

llvm-svn: 58793

"alloca".

llvm-svn: 58792

- stackprotector_prologue creates a stack object and stores the guard there.

- stackprotector_epilogue reads the stack guard from the stack position created
  by stackprotector_prologue.

- The PrologEpilogInserter was changed to make sure that the stack guard is
  first on the stack frame.

llvm-svn: 58791

llvm-svn: 58790

llvm-svn: 58789

llvm-svn: 58788

llvm-svn: 58787

llvm-svn: 58786

llvm-svn: 58782

llvm-svn: 58781

llvm-svn: 58780

llvm-svn: 58778

Restructure ARM code emitter to use instruction formats instead of addressing modes to determine how to encode instructions.

llvm-svn: 58764

changes.

llvm-svn: 58760

llvm-svn: 58755

llvm-svn: 58753

llvm-svn: 58752

llvm-svn: 58751

llvm-svn: 58750

priority function. Instead, just iterate over the AllNodes list, which is
already in topological order. This eliminates a fair amount of bookkeeping,
and speeds up the isel phase by about 15% on many testcases.

The impact on most targets is that AddToISelQueue calls can be simply removed.

In the x86 target, there are two additional notable changes.

The rule-bending AND+SHIFT optimization in MatchAddress that creates new
pre-isel nodes during isel is now a little more verbose, but more robust.
Instead of either creating an invalid DAG or creating an invalid topological
sort, as it has historically done, it can now just insert the new nodes into
the node list at a position where they will be consistent with the topological
ordering.

Also, the address-matching code has logic that checked to see if a node was
"already selected". However, when a node is selected, it has all its uses
taken away via ReplaceAllUsesWith or equivalent, so it won't recieve any
further visits from MatchAddress. This code is now removed.

llvm-svn: 58748

by isel and potentially forced into registers.

llvm-svn: 58747

indirect gv reference. Please don't call it lazy.

llvm-svn: 58746

llvm-svn: 58744

llvm-svn: 58743

llvm-svn: 58742

llvm-svn: 58741

llvm-svn: 58740

llvm-svn: 58739

llvm-svn: 58738

llvm-svn: 58737

llvm-svn: 58736

isn't going to be generated.

llvm-svn: 58734

a specialized pass that it not likely to be generally useful.

llvm-svn: 58732

fix memory leak in pass manager when adding an analysis pass that already existed. as pass manager takes ownership of the added passes, it has to delete the pass if it isnt added to the pass list
tweak the opt tool so that it doesnt access a Pass after the ownership was taken by the pass manager

llvm-svn: 58730

llvm-svn: 58728

  "getOrInsertFunction" in that it either adds a new declaration of the global
  and returns it, or returns the current one -- optionally casting it to the
  correct type.
- Use the new getOrInsertGlobal in the stack protector code.
- Use "splitBasicBlock" in the stack protector code.

llvm-svn: 58727

First pass at checking for the creation of a new join point when doing pre-alloc splitting.  This is not turned on yet.

llvm-svn: 58726

llvm-svn: 58725