Nate Begeman af4ab1b103 Optimize FSEL a bit for fneg arguments. This fixes the recently added test
case so that we emit

_test_fneg_sel:
.LBB_test_fneg_sel_0:   ;
        fsel f1, f1, f3, f2
        blr

instead of:

_test_fneg_sel:
.LBB_test_fneg_sel_0:   ;
        fneg f0, f1
        fneg f0, f0
        fsel f1, f0, f3, f2
        blr


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@21177 91177308-0d34-0410-b5e6-96231b3b80d8
2005-04-09 09:33:07 +00:00
..
2004-11-21 00:00:54 +00:00
2004-12-16 17:26:44 +00:00
2004-12-16 16:31:57 +00:00
2004-12-16 16:31:57 +00:00
2005-04-06 22:42:08 +00:00
2004-11-23 05:57:57 +00:00
2004-12-16 16:31:57 +00:00
2004-11-23 18:47:55 +00:00

TODO:
* poor switch statement codegen
* load/store to alloca'd array or struct.
* implement not-R0 register GPR class
* implement scheduling info
* implement do-loop pass
* implement do-loop -> bdnz transform
* implement powerpc-64 for darwin
* implement powerpc-64 for aix
* use stfiwx in float->int
* should hint to the branch select pass that it doesn't need to print the
  second unconditional branch, so we don't end up with things like:
	b .LBBl42__2E_expand_function_8_674	; loopentry.24
	b .LBBl42__2E_expand_function_8_42	; NewDefault
	b .LBBl42__2E_expand_function_8_42	; NewDefault

Currently failing tests that should pass:
* MultiSource
  |- Applications
  |  `- hbd: miscompilation