mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-21 03:53:04 +02:00
8f90c2a416
Summary: Multi-dword constant loads generated unnecessary moves from SGPRs into VGPRs, increasing the code size and VGPR pressure. These moves are now folded away. Note that this lack of operand folding was not a problem for VMEM loads, because COPY nodes from VReg_Nnn to VGPR32 are eliminated by the register coalescer. Some tests are updated, note that the fsub.ll test explicitly checks that the move is elided. With the IR generated by current Mesa, the changes are obviously relatively minor: 7063 shaders in 3531 tests Totals: SGPRS: 351872 -> 352560 (0.20 %) VGPRS: 199984 -> 200732 (0.37 %) Code Size: 9876968 -> 9881112 (0.04 %) bytes LDS: 91 -> 91 (0.00 %) blocks Scratch: 1779712 -> 1767424 (-0.69 %) bytes per wave Wait states: 295164 -> 295337 (0.06 %) Totals from affected shaders: SGPRS: 65784 -> 66472 (1.05 %) VGPRS: 38064 -> 38812 (1.97 %) Code Size: 1993828 -> 1997972 (0.21 %) bytes LDS: 42 -> 42 (0.00 %) blocks Scratch: 795648 -> 783360 (-1.54 %) bytes per wave Wait states: 54026 -> 54199 (0.32 %) Reviewers: tstellarAMD, arsenm, mareko Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D15875 llvm-svn: 257074 |
||
---|---|---|
.. | ||
AsmParser | ||
InstPrinter | ||
MCTargetDesc | ||
TargetInfo | ||
Utils | ||
AMDGPU.h | ||
AMDGPU.td | ||
AMDGPUAlwaysInlinePass.cpp | ||
AMDGPUAnnotateKernelFeatures.cpp | ||
AMDGPUAnnotateUniformValues.cpp | ||
AMDGPUAsmPrinter.cpp | ||
AMDGPUAsmPrinter.h | ||
AMDGPUCallingConv.td | ||
AMDGPUDiagnosticInfoUnsupported.cpp | ||
AMDGPUDiagnosticInfoUnsupported.h | ||
AMDGPUFrameLowering.cpp | ||
AMDGPUFrameLowering.h | ||
AMDGPUInstrInfo.cpp | ||
AMDGPUInstrInfo.h | ||
AMDGPUInstrInfo.td | ||
AMDGPUInstructions.td | ||
AMDGPUIntrinsicInfo.cpp | ||
AMDGPUIntrinsicInfo.h | ||
AMDGPUIntrinsics.td | ||
AMDGPUISelDAGToDAG.cpp | ||
AMDGPUISelLowering.cpp | ||
AMDGPUISelLowering.h | ||
AMDGPUMachineFunction.cpp | ||
AMDGPUMachineFunction.h | ||
AMDGPUMCInstLower.cpp | ||
AMDGPUMCInstLower.h | ||
AMDGPUOpenCLImageTypeLoweringPass.cpp | ||
AMDGPUPromoteAlloca.cpp | ||
AMDGPURegisterInfo.cpp | ||
AMDGPURegisterInfo.h | ||
AMDGPURegisterInfo.td | ||
AMDGPUSubtarget.cpp | ||
AMDGPUSubtarget.h | ||
AMDGPUTargetMachine.cpp | ||
AMDGPUTargetMachine.h | ||
AMDGPUTargetObjectFile.cpp | ||
AMDGPUTargetObjectFile.h | ||
AMDGPUTargetTransformInfo.cpp | ||
AMDGPUTargetTransformInfo.h | ||
AMDILCFGStructurizer.cpp | ||
AMDKernelCodeT.h | ||
CaymanInstructions.td | ||
CIInstructions.td | ||
CMakeLists.txt | ||
EvergreenInstructions.td | ||
LLVMBuild.txt | ||
Makefile | ||
Processors.td | ||
R600ClauseMergePass.cpp | ||
R600ControlFlowFinalizer.cpp | ||
R600Defines.h | ||
R600EmitClauseMarkers.cpp | ||
R600ExpandSpecialInstrs.cpp | ||
R600InstrFormats.td | ||
R600InstrInfo.cpp | ||
R600InstrInfo.h | ||
R600Instructions.td | ||
R600Intrinsics.td | ||
R600ISelLowering.cpp | ||
R600ISelLowering.h | ||
R600MachineFunctionInfo.cpp | ||
R600MachineFunctionInfo.h | ||
R600MachineScheduler.cpp | ||
R600MachineScheduler.h | ||
R600OptimizeVectorRegisters.cpp | ||
R600Packetizer.cpp | ||
R600RegisterInfo.cpp | ||
R600RegisterInfo.h | ||
R600RegisterInfo.td | ||
R600Schedule.td | ||
R600TextureIntrinsicsReplacer.cpp | ||
R700Instructions.td | ||
SIAnnotateControlFlow.cpp | ||
SIDefines.h | ||
SIFixControlFlowLiveIntervals.cpp | ||
SIFixSGPRCopies.cpp | ||
SIFixSGPRLiveRanges.cpp | ||
SIFoldOperands.cpp | ||
SIFrameLowering.cpp | ||
SIFrameLowering.h | ||
SIInsertWaits.cpp | ||
SIInstrFormats.td | ||
SIInstrInfo.cpp | ||
SIInstrInfo.h | ||
SIInstrInfo.td | ||
SIInstructions.td | ||
SIIntrinsics.td | ||
SIISelLowering.cpp | ||
SIISelLowering.h | ||
SILoadStoreOptimizer.cpp | ||
SILowerControlFlow.cpp | ||
SILowerI1Copies.cpp | ||
SIMachineFunctionInfo.cpp | ||
SIMachineFunctionInfo.h | ||
SIRegisterInfo.cpp | ||
SIRegisterInfo.h | ||
SIRegisterInfo.td | ||
SISchedule.td | ||
SIShrinkInstructions.cpp | ||
SITypeRewriter.cpp | ||
VIInstrFormats.td | ||
VIInstructions.td |