Chris Lattner 5d056952ba optimize single MBB loops better. In particular, produce: ... LBB1_57: #bb207.i movl 72(%esp), %ecx movb (%ecx,%eax), %cl movl 80(%esp), %edx movb %cl, 1(%edx,%eax) incl %eax cmpl $143, %eax jne LBB1_57 #bb207.i jmp LBB1_64 #cond_next255.i intead of: LBB1_57: #bb207.i movl 72(%esp), %ecx movb (%ecx,%eax), %cl movl 80(%esp), %edx movb %cl, 1(%edx,%eax) incl %eax cmpl $143, %eax je LBB1_64 #cond_next255.i jmp LBB1_57 #bb207.i This eliminates a branch per iteration of the loop. This hurted PPC particularly, because the extra branch meant another dispatch group for each iteration of the loop. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@31530 91177308-0d34-0410-b5e6-96231b3b80d8		2006-11-08 01:03:21 +00:00
..
SelectionDAG	Add post-indexed load / store transformations.	2006-11-07 09:03:05 +00:00
AsmPrinter.cpp	Add a printSetLabel that takes two id's.	2006-11-01 09:23:08 +00:00
BranchFolding.cpp	optimize single MBB loops better. In particular, produce:	2006-11-08 01:03:21 +00:00
DwarfWriter.cpp	1. Add a pass to fold debug label instructions so a debug info client can detect	2006-11-07 19:33:46 +00:00
ELFWriter.cpp	For PR786:	2006-11-02 20:25:50 +00:00
IntrinsicLowering.cpp	For PR950:	2006-10-20 07:07:24 +00:00
LiveInterval.cpp	For PR786:	2006-11-02 20:25:50 +00:00
LiveIntervalAnalysis.cpp	Enable improved spilling costs by default. This speeds up viterbi on x86	2006-11-07 18:04:58 +00:00
LiveVariables.cpp	For PR786:	2006-11-02 20:25:50 +00:00
LLVMTargetMachine.cpp	1. Add a pass to fold debug label instructions so a debug info client can detect	2006-11-07 19:33:46 +00:00
MachineBasicBlock.cpp	add moveBefore/moveAfter helper methods	2006-10-24 00:02:26 +00:00
MachineDebugInfo.cpp	Accidently reran commit.	2006-11-07 21:58:55 +00:00
MachineFunction.cpp	const'ify jump table stuff	2006-10-28 18:17:09 +00:00
MachineInstr.cpp	be more aggressive about matching identical instructions.	2006-10-25 18:08:14 +00:00
MachinePassRegistry.cpp
MachOWriter.cpp
Makefile	this will work better	2006-11-03 19:15:55 +00:00
Passes.cpp
PHIElimination.cpp
PhysRegTracker.h
PrologEpilogInserter.cpp	TargetRegisterClass specifies the desired spill alignment. However, it cannot be honored if stack alignment is smaller.	2006-09-28 18:52:32 +00:00
RegAllocLinearScan.cpp	Use correct value for float HUGH_VAL.	2006-11-07 12:25:45 +00:00
RegAllocLocal.cpp
RegAllocSimple.cpp	Rename	2006-11-01 23:18:32 +00:00
TwoAddressInstructionPass.cpp	Two-address instructions no longer have to be A := A op C. Now any pair of dest / src operands can be tied together.	2006-11-01 23:06:55 +00:00
UnreachableBlockElim.cpp
VirtRegMap.cpp	Fixed some spiller bugs exposed by the recent two-address code changes. Now	2006-11-04 00:21:55 +00:00
VirtRegMap.h