mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-19 11:02:59 +02:00
94ebbdf753
Summary: Whole quad mode is already enabled for pixel shaders that compute derivatives, but it must be suspended for instructions that cause a shader to have side effects (i.e. stores and atomics). This pass addresses the issue by storing the real (initial) live mask in a register, masking EXEC before instructions that require exact execution and (re-)enabling WQM where required. This pass is run before register coalescing so that we can use machine SSA for analysis. The changes in this patch expose a problem with the second machine scheduling pass: target independent instructions like COPY implicitly use EXEC when they operate on VGPRs, but this fact is not encoded in the MIR. This can lead to miscompilation because instructions are moved past changes to EXEC. This patch fixes the problem by adding use-implicit operands to target independent instructions. Some general codegen passes are relaxed to work with such implicit use operands. Reviewers: arsenm, tstellarAMD, mareko Subscribers: MatzeB, arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D18162 llvm-svn: 263982
75 lines
2.2 KiB
CMake
75 lines
2.2 KiB
CMake
set(LLVM_TARGET_DEFINITIONS AMDGPU.td)
|
|
|
|
tablegen(LLVM AMDGPUGenRegisterInfo.inc -gen-register-info)
|
|
tablegen(LLVM AMDGPUGenInstrInfo.inc -gen-instr-info)
|
|
tablegen(LLVM AMDGPUGenDAGISel.inc -gen-dag-isel)
|
|
tablegen(LLVM AMDGPUGenCallingConv.inc -gen-callingconv)
|
|
tablegen(LLVM AMDGPUGenSubtargetInfo.inc -gen-subtarget)
|
|
tablegen(LLVM AMDGPUGenIntrinsics.inc -gen-tgt-intrinsic)
|
|
tablegen(LLVM AMDGPUGenMCCodeEmitter.inc -gen-emitter)
|
|
tablegen(LLVM AMDGPUGenDFAPacketizer.inc -gen-dfa-packetizer)
|
|
tablegen(LLVM AMDGPUGenAsmWriter.inc -gen-asm-writer)
|
|
tablegen(LLVM AMDGPUGenAsmMatcher.inc -gen-asm-matcher)
|
|
tablegen(LLVM AMDGPUGenDisassemblerTables.inc -gen-disassembler)
|
|
add_public_tablegen_target(AMDGPUCommonTableGen)
|
|
|
|
add_llvm_target(AMDGPUCodeGen
|
|
AMDILCFGStructurizer.cpp
|
|
AMDGPUAlwaysInlinePass.cpp
|
|
AMDGPUAnnotateKernelFeatures.cpp
|
|
AMDGPUAnnotateUniformValues.cpp
|
|
AMDGPUAsmPrinter.cpp
|
|
AMDGPUFrameLowering.cpp
|
|
AMDGPUTargetObjectFile.cpp
|
|
AMDGPUIntrinsicInfo.cpp
|
|
AMDGPUISelDAGToDAG.cpp
|
|
AMDGPUMCInstLower.cpp
|
|
AMDGPUMachineFunction.cpp
|
|
AMDGPUOpenCLImageTypeLoweringPass.cpp
|
|
AMDGPUSubtarget.cpp
|
|
AMDGPUTargetMachine.cpp
|
|
AMDGPUTargetTransformInfo.cpp
|
|
AMDGPUISelLowering.cpp
|
|
AMDGPUInstrInfo.cpp
|
|
AMDGPUPromoteAlloca.cpp
|
|
AMDGPURegisterInfo.cpp
|
|
R600ClauseMergePass.cpp
|
|
R600ControlFlowFinalizer.cpp
|
|
R600EmitClauseMarkers.cpp
|
|
R600ExpandSpecialInstrs.cpp
|
|
R600InstrInfo.cpp
|
|
R600ISelLowering.cpp
|
|
R600MachineFunctionInfo.cpp
|
|
R600MachineScheduler.cpp
|
|
R600OptimizeVectorRegisters.cpp
|
|
R600Packetizer.cpp
|
|
R600RegisterInfo.cpp
|
|
R600TextureIntrinsicsReplacer.cpp
|
|
SIAnnotateControlFlow.cpp
|
|
SIFixControlFlowLiveIntervals.cpp
|
|
SIFixSGPRCopies.cpp
|
|
SIFixSGPRLiveRanges.cpp
|
|
SIFoldOperands.cpp
|
|
SIFrameLowering.cpp
|
|
SIInsertNopsPass.cpp
|
|
SIInsertWaits.cpp
|
|
SIInstrInfo.cpp
|
|
SIISelLowering.cpp
|
|
SILoadStoreOptimizer.cpp
|
|
SILowerControlFlow.cpp
|
|
SILowerI1Copies.cpp
|
|
SIMachineFunctionInfo.cpp
|
|
SIMachineScheduler.cpp
|
|
SIRegisterInfo.cpp
|
|
SIShrinkInstructions.cpp
|
|
SITypeRewriter.cpp
|
|
SIWholeQuadMode.cpp
|
|
)
|
|
|
|
add_subdirectory(AsmParser)
|
|
add_subdirectory(InstPrinter)
|
|
add_subdirectory(Disassembler)
|
|
add_subdirectory(TargetInfo)
|
|
add_subdirectory(MCTargetDesc)
|
|
add_subdirectory(Utils)
|