llvm-svn: 55074

llvm-svn: 55072

llvm-svn: 55071

llvm-svn: 55070

llvm-svn: 55069

llvm-svn: 55067

and the slow-path cases out of line.  This speeds up instcombine
a bit in real world cases.  Patch contributed by m-s.

llvm-svn: 55063

llvm-svn: 55059

alignment and volatility information, such as loads and
stores, to reduce the number of integer values added to
the FoldingSetNodeID.

llvm-svn: 55058

llvm-svn: 55057

necessary to use dyn_cast in these predicates.

llvm-svn: 55055

llvm-svn: 55054

llvm-svn: 55053

llvm-svn: 55052

llvm-svn: 55050

llvm-svn: 55049

llvm-svn: 55047

llvm-svn: 55035

not have a fall-through successor.

llvm-svn: 55033

llvm-svn: 55031

llvm-svn: 55029

a command-line option, so that the default behavior is an abort, which
is useful for exposing code that isn't supported yet.

llvm-svn: 55028

that aren't available as virtual registers (for now).

llvm-svn: 55026

Just expand it like the other X-bit sub_and_fetches.

llvm-svn: 55023

llvm-svn: 55022

llvm-svn: 55021

llvm-svn: 55020

was already present, but not hooked up to anything.

llvm-svn: 55018

llvm-svn: 55015

llvm-svn: 55014

llvm-svn: 55012

llvm-svn: 55011

llvm-svn: 55010

instead of the one that doesn't and then adding it manually.

llvm-svn: 55006

a desired opcode.

llvm-svn: 55005

With this patch, all of MultiSource/Applications and all of SPEC2000/2006 pass with
the SimpleSpiller and this fast-path enabled.

llvm-svn: 55000

builtins on X86.

Change "lock" instructions to be on a separate line.
This is needed to work around a bug in the Darwin
assembler.

llvm-svn: 54999

llvm-svn: 54995

llvm-svn: 54994

Also skip indirect encoding for platforms that ask for one: we direclty
write an address, not a pointer to the address.

llvm-svn: 54987