Chris Lattner 903236468c More aggressively sink GEP offsets into loops. For example, before we ...

generated:

        movl 8(%esp), %eax
        movl %eax, %edx
        addl $4316, %edx
        cmpb $1, %cl
        ja LBB1_2       #cond_false
LBB1_1: #cond_true
        movl L_QuantizationTables720$non_lazy_ptr, %ecx
        movl %ecx, (%edx)
        movl L_QNOtoQuantTableShift720$non_lazy_ptr, %edx
        movl %edx, 4460(%eax)
        ret
...

Now we generate:

        movl 8(%esp), %eax
        cmpb $1, %cl
        ja LBB1_2       #cond_false
LBB1_1: #cond_true
        movl L_QuantizationTables720$non_lazy_ptr, %ecx
        movl %ecx, 4316(%eax)
        movl L_QNOtoQuantTableShift720$non_lazy_ptr, %ecx
        movl %ecx, 4460(%eax)
        ret

... which uses one fewer register.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28129 91177308-0d34-0410-b5e6-96231b3b80d8

2006-05-05 21:17:49 +00:00

..

SelectionDAG

More aggressively sink GEP offsets into loops. For example, before we

2006-05-05 21:17:49 +00:00

AsmPrinter.cpp

Refactor TargetMachine, pushing handling of TargetData into the target-specific subclasses. This has one caller-visible change: getTargetData() now returns a pointer instead of a reference.

2006-05-03 01:29:57 +00:00

BranchFolding.cpp

Remove trailing whitespace

2005-04-21 22:36:52 +00:00

DwarfWriter.cpp

Refactor TargetMachine, pushing handling of TargetData into the target-specific subclasses. This has one caller-visible change: getTargetData() now returns a pointer instead of a reference.

2006-05-03 01:29:57 +00:00

ELFWriter.cpp

Suck block address tracking out of targets into the JIT Emitter. This

2006-05-03 17:10:41 +00:00

IntrinsicLowering.cpp

Handle new forms of llvm.dbg intrinsics.

2006-03-23 18:06:46 +00:00

LiveInterval.cpp

Fix LiveInterval::getOverlapingRanges to take things in the right order

2005-10-21 06:41:30 +00:00

LiveIntervalAnalysis.cpp

Move some methods out of MachineInstr into MachineOperand

2006-05-04 17:52:23 +00:00

LiveVariables.cpp

Remove a bunch more dead V9 specific stuff

2006-05-04 01:26:39 +00:00

MachineBasicBlock.cpp

Remove and simplify some more machineinstr/machineoperand stuff.

2006-05-04 18:16:01 +00:00

MachineDebugInfo.cpp

Expand some code with temporary variables to rid ourselves of the warning

2006-04-13 18:29:58 +00:00

MachineFunction.cpp

Refactor TargetMachine, pushing handling of TargetData into the target-specific subclasses. This has one caller-visible change: getTargetData() now returns a pointer instead of a reference.

2006-05-03 01:29:57 +00:00

MachineInstr.cpp

Final pass of minor cleanups for MachineInstr

2006-05-04 19:36:09 +00:00

Makefile

Change Library Names Not To Conflict With Others When Installed

2004-10-27 23:18:45 +00:00

Passes.cpp

Alkis agrees that that iterative scan allocator isn't going to be worked on

2005-10-24 04:14:30 +00:00

PHIElimination.cpp

Add support for targets (like Alpha) that have terminator instructions which

2006-01-04 07:12:21 +00:00

PhysRegTracker.h

Improved PhysRegTracker interface. RegAlloc lazily allocates the register tracker using a std::auto_ptr

2004-02-23 06:10:13 +00:00

PrologEpilogInserter.cpp

Foundation for call frame information.

2006-04-07 16:34:46 +00:00

RegAllocLinearScan.cpp

Add some comments.

2006-03-25 23:00:56 +00:00

RegAllocLocal.cpp

Move some methods out of MachineInstr into MachineOperand

2006-05-04 17:52:23 +00:00

RegAllocSimple.cpp

Move some methods out of MachineInstr into MachineOperand

2006-05-04 17:52:23 +00:00

TwoAddressInstructionPass.cpp

Move some methods out of MachineInstr into MachineOperand

2006-05-04 17:52:23 +00:00

UnreachableBlockElim.cpp

Remove trailing whitespace

2005-04-21 22:36:52 +00:00

VirtRegMap.cpp

Move some methods out of MachineInstr into MachineOperand

2006-05-04 17:52:23 +00:00

VirtRegMap.h

Fix a latent bug that my spiller patch last week exposed: we were leaving

2006-05-01 22:03:24 +00:00