llvm-svn: 13076

llvm-svn: 13073

llvm-svn: 13072

llvm-svn: 13071

the name of %fsr (as the comment in SparcV9RegClassInfo.h used to suggest)
you would walk off the end of the FloatCCRegName array.

llvm-svn: 13070

Remove the extra %fsr register from SparcV9FloatCCRegClass.

llvm-svn: 13069

but it's a start, and seems to do it's basic job.

llvm-svn: 13068

llvm-svn: 13067

llvm-svn: 13066

llvm-svn: 13065

llvm-svn: 13064

wrapper idea uniformly: we can use Value::replaceAllUsesWith() instead of
special-casing by class of user.

llvm-svn: 13063

* Fix usage of <p> tag and some grammar

llvm-svn: 13062

* Wrap a long line

llvm-svn: 13061

llvm-svn: 13060

* Remove #include
* Add some methods to update loop/loopinfo
* Stop explicitly holding the loop depth in the Loop class.  Instead, just
  dynamically calculate it.  This makes it easier to update LoopInfo as a
  result of transformations.

llvm-svn: 13059

llvm-svn: 13058

llvm-svn: 13057

llvm-svn: 13056

llvm-svn: 13055

by creating an internal wrapper function with same signature as the external
function, and use it instead of the "real" function.

The wrapper then calls the external function using the same JIT function
resolution API that has been used before for rewriting instructions, since the
wrapper has an explicit call instruction which we can rewrite.

llvm-svn: 13054

in a loop.

llvm-svn: 13052

llvm-svn: 13051

llvm-svn: 13050

llvm-svn: 13049

llvm-svn: 13048

llvm-svn: 13047

llvm-svn: 13046

structure to being dynamically computed on demand.  This makes updating
loop information MUCH easier.

llvm-svn: 13045

llvm-svn: 13041

llvm-svn: 13040

that the exit block of the loop becomes the new entry block of the function.

This was causing a verifier assertion on 252.eon.

llvm-svn: 13039

using instructions inside of the loop.  This should fix the MishaTest failure
from last night.

llvm-svn: 13038

llvm-svn: 13037

llvm-svn: 13036

llvm-svn: 13035

block.  The primary motivation for doing this is that we can now unroll nested loops.

This makes a pretty big difference in some cases.  For example, in 183.equake,
we are now beating the native compiler with the CBE, and we are a lot closer
with LLC.

I'm now going to play around a bit with the unroll factor and see what effect
it really has.

llvm-svn: 13034

While we're at it, add support for updating loop information correctly.

llvm-svn: 13033

have a canonical indvar

llvm-svn: 13032

llvm-svn: 13031