Tom Stellard eb3aa070c9 R600: Expand v2i32 load/store instead of custom lowering ...

The custom lowering causes llc to crash with a segfault.

Ideally, the custom lowering can be fixed, but this allows
programs which load/store v2i32 to work without crashing.

Patch by: Aaron Watry

Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
Signed-off-by: Aaron Watry<awatry@gmail.com>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@184480 91177308-0d34-0410-b5e6-96231b3b80d8

2013-06-20 21:55:23 +00:00

..

InstPrinter

Move passes from namespace llvm into anonymous namespaces. Sort includes while there.

2013-05-23 17:10:37 +00:00

MCTargetDesc

R600: Use correct encoding for Vertex Fetch instructions on Cayman

2013-06-14 22:12:30 +00:00

TargetInfo

R600: Remove unnecessary include

2013-06-07 20:28:43 +00:00

AMDGPU.h

R600: Rework subtarget info and remove AMDILDevice classes

2013-06-07 20:37:48 +00:00

AMDGPU.td

R600: Rework subtarget info and remove AMDILDevice classes

2013-06-07 20:37:48 +00:00

AMDGPUAsmPrinter.cpp

R600: Rework subtarget info and remove AMDILDevice classes

2013-06-07 20:37:48 +00:00

AMDGPUAsmPrinter.h

R600: Emit used GPRs count

2013-04-17 15:17:25 +00:00

AMDGPUCallingConv.td

R600: Rework subtarget info and remove AMDILDevice classes

2013-06-07 20:37:48 +00:00

AMDGPUConvertToISA.cpp

…

AMDGPUFrameLowering.cpp

R600: Fix calculation of stack offset in AMDGPUFrameLowering

2013-06-07 20:52:05 +00:00

AMDGPUFrameLowering.h

R600: Support for indirect addressing v4

2013-02-06 17:32:29 +00:00

AMDGPUIndirectAddressing.cpp

Don't cache the instruction and register info from the TargetMachine, because

2013-06-07 20:28:55 +00:00

AMDGPUInstrInfo.cpp

R600: Rework subtarget info and remove AMDILDevice classes

2013-06-07 20:37:48 +00:00

AMDGPUInstrInfo.h

R600: Support for indirect addressing v4

2013-02-06 17:32:29 +00:00

AMDGPUInstrInfo.td

Create an FPOW SDNode opcode def in the target independent .td file rather than in a specific backend.

2013-05-22 06:36:09 +00:00

AMDGPUInstructions.td

R600/SI: Add support for global loads

2013-06-03 17:39:43 +00:00

AMDGPUIntrinsics.td

R600/SI: remove shader type intrinsic

2013-03-07 09:03:46 +00:00

AMDGPUISelLowering.cpp

R600/SI: Add a calling convention for compute shaders

2013-06-03 17:40:11 +00:00

AMDGPUISelLowering.h

R600/SI: Add support for work item and work group intrinsics

2013-06-03 17:40:18 +00:00

AMDGPUMachineFunction.cpp

R600: Initialize AMDGPUMachineFunction::ShaderType to ShaderType::COMPUTE

2013-04-26 18:32:24 +00:00

AMDGPUMachineFunction.h

R600/SI: Share code recording ShaderTypeAttribute between generations

2013-04-01 21:47:53 +00:00

AMDGPUMCInstLower.cpp

Move all of the header files which are involved in modelling the LLVM IR

2013-01-02 11:36:10 +00:00

AMDGPUMCInstLower.h

R600: BB operand support for SI

2012-12-17 15:14:54 +00:00

AMDGPURegisterInfo.cpp

Don't cache the instruction and register info from the TargetMachine, because

2013-06-07 20:28:55 +00:00

AMDGPURegisterInfo.h

Don't cache the instruction and register info from the TargetMachine, because

2013-06-07 20:28:55 +00:00

AMDGPURegisterInfo.td

Make SubRegIndex size mandatory, following r183020.

2013-05-31 23:45:26 +00:00

AMDGPUSubtarget.cpp

R600: Rework subtarget info and remove AMDILDevice classes

2013-06-07 20:37:48 +00:00

AMDGPUSubtarget.h

R600: Rework subtarget info and remove AMDILDevice classes

2013-06-07 20:37:48 +00:00

AMDGPUTargetMachine.cpp

Move StructurizeCFG out of R600 to generic Transforms.

2013-06-19 20:18:24 +00:00

AMDGPUTargetMachine.h

Remove dead prototype.

2013-06-18 06:24:14 +00:00

AMDILBase.td

R600: Move Subtarget feature definitions into AMDGPU.td

2013-06-07 20:28:49 +00:00

AMDILCFGStructurizer.cpp

R600: Rework subtarget info and remove AMDILDevice classes

2013-06-07 20:37:48 +00:00

AMDILInstrInfo.td

R600: Rework subtarget info and remove AMDILDevice classes

2013-06-07 20:37:48 +00:00

AMDILIntrinsicInfo.cpp

R600: Rework subtarget info and remove AMDILDevice classes

2013-06-07 20:37:48 +00:00

AMDILIntrinsicInfo.h

Move all of the header files which are involved in modelling the LLVM IR

2013-01-02 11:36:10 +00:00

AMDILIntrinsics.td

R600/SI: Use MULADD_IEEE/V_MAD_F32 instruction for mad pattern

2013-02-18 14:11:28 +00:00

AMDILISelDAGToDAG.cpp

Access the TargetLoweringInfo from the TargetMachine object instead of caching it. The TLI may change between functions. No functionality change.

2013-06-19 21:36:55 +00:00

AMDILISelLowering.cpp

R600: Rework subtarget info and remove AMDILDevice classes

2013-06-07 20:37:48 +00:00

AMDILRegisterInfo.td

…

CMakeLists.txt

Move StructurizeCFG out of R600 to generic Transforms.

2013-06-19 20:18:24 +00:00

LLVMBuild.txt

…

Makefile

…

Processors.td

R600: Rework subtarget info and remove AMDILDevice classes

2013-06-07 20:37:48 +00:00

R600ControlFlowFinalizer.cpp

R600: Use EXPORT_RAT_INST_STORE_DWORD for stores on Cayman

2013-06-14 22:12:24 +00:00

R600Defines.h

R600: Relax some vector constraints on Dot4.

2013-05-17 16:50:32 +00:00

R600EmitClauseMarkers.cpp

Don't cache the instruction and register info from the TargetMachine, because

2013-06-07 20:28:55 +00:00

R600ExpandSpecialInstrs.cpp

Don't cache the instruction and register info from the TargetMachine, because

2013-06-07 20:28:55 +00:00

R600InstrFormats.td

R600: Use correct encoding for Vertex Fetch instructions on Cayman

2013-06-14 22:12:30 +00:00

R600InstrInfo.cpp

R600: PV stores Reg id, not index

2013-06-17 20:16:40 +00:00

R600InstrInfo.h

R600: Rework subtarget info and remove AMDILDevice classes

2013-06-07 20:37:48 +00:00

R600Instructions.td

R600: Properly set COUNT_3 bit in TEX clause initiating inst for pre EG gen.

2013-06-17 20:16:26 +00:00

R600Intrinsics.td

R600: Improve texture handling

2013-05-17 16:50:20 +00:00

R600ISelLowering.cpp

R600: Expand v2i32 load/store instead of custom lowering

2013-06-20 21:55:23 +00:00

R600ISelLowering.h

Don't cache the instruction and register info from the TargetMachine, because

2013-06-07 20:28:55 +00:00

R600MachineFunctionInfo.cpp

R600/SI: Share code recording ShaderTypeAttribute between generations

2013-04-01 21:47:53 +00:00

R600MachineFunctionInfo.h

Move passes from namespace llvm into anonymous namespaces. Sort includes while there.

2013-05-23 17:10:37 +00:00

R600MachineScheduler.cpp

R600: Use a refined heuristic to choose when switching clause

2013-06-07 23:30:34 +00:00

R600MachineScheduler.h

R600: Use a refined heuristic to choose when switching clause

2013-06-07 23:30:34 +00:00

R600OptimizeVectorRegisters.cpp

Don't cache the instruction and register info from the TargetMachine, because

2013-06-07 20:28:55 +00:00

R600Packetizer.cpp

R600: 3 op instructions have no write bit but the result are store in PV

2013-06-03 15:56:12 +00:00

R600RegisterInfo.cpp

Don't cache the instruction and register info from the TargetMachine, because

2013-06-07 20:28:55 +00:00

R600RegisterInfo.h

Don't cache the instruction and register info from the TargetMachine, because

2013-06-07 20:28:55 +00:00

R600RegisterInfo.td

R600: use capital letter for PV channel

2013-06-03 15:44:35 +00:00

R600Schedule.td

R600: Rework Scheduling to handle difference between VLIW4 and VLIW5 chips

2013-04-30 00:14:17 +00:00

R600TextureIntrinsicsReplacer.cpp

Move passes from namespace llvm into anonymous namespaces. Sort includes while there.

2013-05-23 17:10:37 +00:00

SIAnnotateControlFlow.cpp

R600: Remove unnecessary include

2013-06-07 20:28:43 +00:00

SIDefines.h

R600/SI: Emit config values in register value pairs.

2013-04-15 17:51:35 +00:00

SIInsertWaits.cpp

Don't cache the instruction and register info from the TargetMachine, because

2013-06-07 20:28:55 +00:00

SIInstrFormats.td

R600/SI: Use the same names for VOP3 operands and encoding fields

2013-05-20 15:02:08 +00:00

SIInstrInfo.cpp

Don't cache the instruction and register info from the TargetMachine, because

2013-06-07 20:28:55 +00:00

SIInstrInfo.h

R600/SI: adjust writemask to only the used components

2013-04-10 08:39:08 +00:00

SIInstrInfo.td

Access the TargetLoweringInfo from the TargetMachine object instead of caching it. The TLI may change between functions. No functionality change.

2013-06-19 21:36:55 +00:00

SIInstructions.td

R600: Add SI load support for v[24]i32 and store for v2i32

2013-06-15 00:09:31 +00:00

SIIntrinsics.td

R600/SI: Add intrinsic for MIMG IMAGE_GET_RESINFO opcode

2013-05-06 23:02:19 +00:00

SIISelLowering.cpp

R600: Rework subtarget info and remove AMDILDevice classes

2013-06-07 20:37:48 +00:00

SIISelLowering.h

Don't cache the instruction and register info from the TargetMachine, because

2013-06-07 20:28:55 +00:00

SILowerControlFlow.cpp

Don't cache the instruction and register info from the TargetMachine, because

2013-06-07 20:28:55 +00:00

SIMachineFunctionInfo.cpp

R600/SI: Share code recording ShaderTypeAttribute between generations

2013-04-01 21:47:53 +00:00

SIMachineFunctionInfo.h

R600/SI: Share code recording ShaderTypeAttribute between generations

2013-04-01 21:47:53 +00:00

SIRegisterInfo.cpp

Don't cache the instruction and register info from the TargetMachine, because

2013-06-07 20:28:55 +00:00

SIRegisterInfo.h

Don't cache the instruction and register info from the TargetMachine, because

2013-06-07 20:28:55 +00:00

SIRegisterInfo.td

R600/SI: dynamical figure out the reg class of MIMG

2013-04-10 08:39:16 +00:00

SISchedule.td

…