llvm-6502/lib/Target/Sparc
Jakob Stoklund Olesen 89f530ebbf Also expand 64-bit bitcasts.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@182229 91177308-0d34-0410-b5e6-96231b3b80d8
2013-05-20 01:01:43 +00:00
..
MCTargetDesc Remove unused argument. 2013-05-10 18:16:59 +00:00
TargetInfo
CMakeLists.txt
DelaySlotFiller.cpp [Sparc] Prevent instructions that defines or uses %o7 to be in call's delay slot. 2013-05-16 23:53:29 +00:00
FPMover.cpp
LLVMBuild.txt
Makefile
README.txt Don't use %g0 to materialize 0 directly. 2013-05-19 21:47:13 +00:00
Sparc.h
Sparc.td
SparcAsmPrinter.cpp
SparcCallingConv.td
SparcFrameLowering.cpp [Sparc] Implements hasReservedCallFrame and hasFP. 2013-05-17 15:14:34 +00:00
SparcFrameLowering.h [Sparc] Implements hasReservedCallFrame and hasFP. 2013-05-17 15:14:34 +00:00
SparcInstr64Bit.td Don't use %g0 to materialize 0 directly. 2013-05-19 21:47:13 +00:00
SparcInstrFormats.td
SparcInstrInfo.cpp Implement spill and fill of I64Regs. 2013-05-20 00:53:25 +00:00
SparcInstrInfo.h
SparcInstrInfo.td Implement SPselectfcc for i64 operands. 2013-05-19 20:20:54 +00:00
SparcISelDAGToDAG.cpp
SparcISelLowering.cpp Also expand 64-bit bitcasts. 2013-05-20 01:01:43 +00:00
SparcISelLowering.h
SparcMachineFunctionInfo.cpp
SparcMachineFunctionInfo.h
SparcRegisterInfo.cpp [Sparc] Rearrange integer registers' allocation order so that register allocator will use I and G registers before using L and O registers. 2013-05-19 20:07:20 +00:00
SparcRegisterInfo.h
SparcRegisterInfo.td [Sparc] Rearrange integer registers' allocation order so that register allocator will use I and G registers before using L and O registers. 2013-05-19 20:07:20 +00:00
SparcSelectionDAGInfo.cpp
SparcSelectionDAGInfo.h
SparcSubtarget.cpp
SparcSubtarget.h
SparcTargetMachine.cpp Remove the MachineMove class. 2013-05-13 01:16:13 +00:00
SparcTargetMachine.h

To-do
-----

* Keep the address of the constant pool in a register instead of forming its
  address all of the time.
* We can fold small constant offsets into the %hi/%lo references to constant
  pool addresses as well.
* When in V9 mode, register allocate %icc[0-3].
* Add support for isel'ing UMUL_LOHI instead of marking it as Expand.
* Emit the 'Branch on Integer Register with Prediction' instructions.  It's
  not clear how to write a pattern for this though:

float %t1(int %a, int* %p) {
        %C = seteq int %a, 0
        br bool %C, label %T, label %F
T:
        store int 123, int* %p
        br label %F
F:
        ret float undef
}

codegens to this:

t1:
        save -96, %o6, %o6
1)      subcc %i0, 0, %l0
1)      bne .LBBt1_2    ! F
        nop
.LBBt1_1:       ! T
        or %g0, 123, %l0
        st %l0, [%i1]
.LBBt1_2:       ! F
        restore %g0, %g0, %g0
        retl
        nop

1) should be replaced with a brz in V9 mode.

* Same as above, but emit conditional move on register zero (p192) in V9 
  mode.  Testcase:

int %t1(int %a, int %b) {
        %C = seteq int %a, 0
        %D = select bool %C, int %a, int %b
        ret int %D
}

* Emit MULX/[SU]DIVX instructions in V9 mode instead of fiddling 
  with the Y register, if they are faster.

* Codegen bswap(load)/store(bswap) -> load/store ASI

* Implement frame pointer elimination, e.g. eliminate save/restore for 
  leaf fns.
* Fill delay slots

* Implement JIT support

* Use %g0 directly to materialize 0. No instruction is required.