- May 14, 2010
-
-
Jim Grosbach authored
llvm-svn: 103806
-
Jim Grosbach authored
while debugging what's mishandled about them in the post-RA pass. llvm-svn: 103805
-
- May 01, 2010
-
-
Dan Gohman authored
changes before doing phi lowering for switches. llvm-svn: 102809
-
- Apr 17, 2010
-
-
Bob Wilson authored
just remove them all. Radar 7873207 (working around the root problem of Radar 7759363). llvm-svn: 101604
-
- Apr 12, 2010
-
-
Dan Gohman authored
llvm-svn: 101043
-
- Mar 05, 2010
-
-
Dale Johannesen authored
llvm-svn: 97765
-
- Jan 05, 2010
-
-
David Greene authored
llvm-svn: 92594
-
- Dec 09, 2009
-
-
- Dec 03, 2009
-
-
Jakob Stoklund Olesen authored
The MO reference to a MachineOperand can be invalidated by MachineInstr::addOperand. Don't even use it for debugging. llvm-svn: 90381
-
- Nov 20, 2009
-
-
David Goodwin authored
Remove some old experimental code that is no longer needed. Remove additional, speculative scheduling pass as its cost did not translate into significant performance improvement. Minor tweaks. llvm-svn: 89471
-
- Nov 13, 2009
-
-
David Goodwin authored
llvm-svn: 88682
-
- Nov 12, 2009
-
-
David Goodwin authored
llvm-svn: 87015
-
- Nov 10, 2009
-
-
David Goodwin authored
llvm-svn: 86634
-
David Goodwin authored
Allow targets to specify register classes whose member registers should not be renamed to break anti-dependencies. llvm-svn: 86628
-
- Nov 05, 2009
-
-
David Goodwin authored
Break anti-dependencies using free registers in a round-robin manner to avoid introducing new anti-dependencies. llvm-svn: 86098
-
- Nov 03, 2009
-
-
David Goodwin authored
Do a scheduling pass ignoring anti-dependencies to identify candidate registers that should be renamed. llvm-svn: 85939
-
- Oct 31, 2009
-
-
Dan Gohman authored
- Be consistent when referring to MachineBasicBlocks: BB#0. - Be consistent when referring to virtual registers: %reg1024. - Be consistent when referring to unknown physical registers: %physreg10. - Be consistent when referring to known physical registers: %RAX - Be consistent when referring to register 0: %reg0 - Be consistent when printing alignments: align=16 - Print jump table contents. - Don't print host addresses, in general. - and various other cleanups. llvm-svn: 85682
-
- Oct 28, 2009
-
-
David Goodwin authored
llvm-svn: 85412
-
- Oct 26, 2009
-
-
David Goodwin authored
Allow the aggressive anti-dep breaker to process the same region multiple times. This is necessary because new anti-dependencies are exposed when "current" ones are broken. llvm-svn: 85166
-
David Goodwin authored
llvm-svn: 85146
-
David Goodwin authored
Add aggressive anti-dependence breaker. Currently it is not the default for any target. Enable with -break-anti-dependencies=all. llvm-svn: 85145
-
David Goodwin authored
llvm-svn: 85127
-
- Oct 25, 2009
-
-
Nick Lewycky authored
VISIBILITY_HIDDEN removal. llvm-svn: 85043
-
Nick Lewycky authored
Chris claims we should never have visibility_hidden inside any .cpp file but that's still not true even after this commit. llvm-svn: 85042
-
- Oct 23, 2009
-
-
David Goodwin authored
Allow the target to select the level of anti-dependence breaking that should be performed by the post-RA scheduler. The default is none. llvm-svn: 84911
-
- Oct 21, 2009
-
-
Dan Gohman authored
llvm-svn: 84727
-
David Goodwin authored
Respect src register allocation requirements when breaking anti-dependencies. Remove some dead code. llvm-svn: 84691
-
- Oct 20, 2009
-
-
David Goodwin authored
llvm-svn: 84658
-
- Oct 16, 2009
-
-
Evan Cheng authored
llvm-svn: 84273
-
Evan Cheng authored
llvm-svn: 84248
-
- Oct 13, 2009
-
-
David Goodwin authored
llvm-svn: 84011
-
- Oct 10, 2009
-
-
Dan Gohman authored
llvm-svn: 83695
-
Dan Gohman authored
is trivially rematerializable and integrate it into TargetInstrInfo::isTriviallyReMaterializable. This way, all places that need to know whether an instruction is rematerializable will get the same answer. This enables the useful parts of the aggressive-remat option by default -- using AliasAnalysis to determine whether a memory location is invariant, and removes the questionable parts -- rematting operations with virtual register inputs that may not be live everywhere. llvm-svn: 83687
-
- Oct 02, 2009
-
-
Benjamin Kramer authored
MI->addOperand invalidates references to it's operands, avoid touching the operand after a new one was added. llvm-svn: 83249
-
David Goodwin authored
llvm-svn: 83223
-
David Goodwin authored
Remove neonfp attribute and instead set default based on CPU string. Add -arm-use-neon-fp to override the default. llvm-svn: 83218
-
- Oct 01, 2009
-
-
David Goodwin authored
Restore the -post-RA-scheduler flag as an override for the target specification. Remove -mattr for setting PostRAScheduler enable and instead use CPU string. llvm-svn: 83215
-
David Goodwin authored
Use MachineFrameInfo.getPristineRegs() to determine which callee-saved registers are available for anti-dependency breaking. Some cleanup. llvm-svn: 83208
-
Evan Cheng authored
operands of instructions with these properties while breaking anti-dep. llvm-svn: 83198
-
- Sep 30, 2009
-
-
Reid Kleckner authored
basic blocks that are so long that their size overflows a short. Also assert that overflow does not happen in the future, as requested by Evan. This fixes PR4401. llvm-svn: 83159
-