Stanislav Mekhanoshin 57d341c27a [AMDGPU] Fix handling of void types in isLegalAddressingMode ...

It is legal for the type passed to isLegalAddressingMode to be
unsized or, more specifically, VoidTy. In this case, we must
check the legality of load / stores for all legal types. Directly
trying to call getTypeStoreSize is incorrect, and leads to breakage
in e.g. Loop Strength Reduction. This change guards against that
behaviour.

Differential Revision: https://reviews.llvm.org/D40405

llvm-svn: 332409

2018-05-15 22:07:51 +00:00

..

AsmParser

[AMDGPU] Added checks for dpp_ctrl value

2018-05-08 16:53:02 +00:00

Disassembler

AMDGPU: Add disasm tests for deep learning instructions + fix v_fmac_f32 disasm

2018-05-15 17:39:13 +00:00

InstPrinter

[AMDGPU] Added checks for dpp_ctrl value

2018-05-08 16:53:02 +00:00

MCTargetDesc

[AMDGPU] Provide machine -> name mapping

2018-05-08 18:53:04 +00:00

TargetInfo

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

Utils

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

AMDGPU.h

AMDGPU: Rename OpenCL lowering pass to be R600 specific.

2018-05-13 10:04:48 +00:00

AMDGPU.td

AMDGPU/NFC: Update D16PreservesUnusedBits description based Tony Tye's comments

2018-05-04 22:53:55 +00:00

AMDGPUAliasAnalysis.cpp

[AMDGPU] Change constant addr space to 4

2018-02-13 18:00:25 +00:00

AMDGPUAliasAnalysis.h

[AMDGPU] Fix some Clang-tidy modernize-use-using and Include What You Use warnings; other minor fixes (NFC).

2017-08-08 23:53:55 +00:00

AMDGPUAlwaysInlinePass.cpp

AMDGPU: Add option to stress calls

2017-09-21 07:00:48 +00:00

AMDGPUAnnotateKernelFeatures.cpp

[Analysis] Fix some Clang-tidy modernize-use-using and Include What You Use warnings; other minor fixes. Also affected in files (NFC).

2017-08-31 21:56:16 +00:00

AMDGPUAnnotateUniformValues.cpp

AMDGPU: Fix converting unanalyzable global loads to SMRD

2017-07-12 23:06:18 +00:00

AMDGPUArgumentUsageInfo.cpp

[CodeGen] Rename functions PrintReg* to printReg*

2017-11-28 12:42:37 +00:00

AMDGPUArgumentUsageInfo.h

[AMDGPU] Fixed MSVC build break

2017-08-04 10:53:07 +00:00

AMDGPUAsmPrinter.cpp

[AMDGPU] Fix compilation failure when IR contains comdat

2018-05-11 20:40:14 +00:00

AMDGPUAsmPrinter.h

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

AMDGPUCallingConv.td

AMDGPU: Initial implementation of calls

2017-08-01 19:54:18 +00:00

AMDGPUCallLowering.cpp

AMDGPU/GlobalISel: Don't try to lower hull shaders

2018-05-07 22:17:54 +00:00

AMDGPUCallLowering.h

AMDGPU: Start defining a calling convention

2017-05-17 21:56:25 +00:00

AMDGPUCodeGenPrepare.cpp

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

AMDGPUFrameLowering.cpp

[AMDGPU] Split R600/SI getFrameIndexReference and emit stack object offsets for SI

2017-03-10 19:39:07 +00:00

AMDGPUFrameLowering.h

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

AMDGPUGenRegisterBankInfo.def

AMDGPU/GlobalISel: Use a more correct getValueMapping

2018-03-01 21:08:51 +00:00

AMDGPUGISel.td

AMDGPU/GlobalISel: Implement select() for 32-bit G_FPTOUI

2018-05-11 05:44:16 +00:00

AMDGPUInline.cpp

Rename DEBUG macro to LLVM_DEBUG.

2018-05-14 12:53:11 +00:00

AMDGPUInstrInfo.cpp

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

AMDGPUInstrInfo.h

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

AMDGPUInstrInfo.td

AMDGPU: Add intrinsics llvm.amdgcn.cvt.{pknorm.i16, pknorm.u16, pk.i16, pk.u16}

2018-01-31 20:18:04 +00:00

AMDGPUInstructions.td

[AMDGPU] Supported ds_write_b128 generation.

2018-03-16 18:12:00 +00:00

AMDGPUInstructionSelector.cpp

AMDGPU/GlobalISel: Implement select() for G_FCONSTANT

2018-05-15 17:57:09 +00:00

AMDGPUInstructionSelector.h

AMDGPU/GlobalISel: Implement select() for 32-bit G_FPTOUI

2018-05-11 05:44:16 +00:00

AMDGPUIntrinsicInfo.cpp

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

AMDGPUIntrinsicInfo.h

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

AMDGPUIntrinsics.td

AMDGPU: Remove deprecated llvm.AMDGPU.kilp intrinsic

2018-04-24 21:37:57 +00:00

AMDGPUISelDAGToDAG.cpp

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

AMDGPUISelLowering.cpp

AMDGPU: Ignore any_extend in mul24 combine

2018-05-09 21:11:35 +00:00

AMDGPUISelLowering.h

AMDGPU: Add combine for trunc of bitcast from build_vector

2018-05-09 18:37:39 +00:00

AMDGPULegalizerInfo.cpp

[IR][CodeGen] Remove dependency on EVT from IR/Function.cpp. Move EVT to CodeGen layer.

2018-03-29 17:21:10 +00:00

AMDGPULegalizerInfo.h

AMDGPU/GlobalISel: Pass subtarget + TM to LegalizerInfo

2018-03-08 16:24:16 +00:00

AMDGPULibCalls.cpp

Rename DEBUG macro to LLVM_DEBUG.

2018-05-14 12:53:11 +00:00

AMDGPULibFunc.cpp

[AMDGPU] Remove hardcoded address space value from AMDGPULibFunc

2017-11-04 17:37:43 +00:00

AMDGPULibFunc.h

[AMDGPU] Remove hardcoded address space value from AMDGPULibFunc

2017-11-04 17:37:43 +00:00

AMDGPULowerIntrinsics.cpp

Extend memcpy expansion in Transform/Utils to handle wider operand types.

2017-07-07 02:00:06 +00:00

AMDGPUMachineCFGStructurizer.cpp

Rename DEBUG macro to LLVM_DEBUG.

2018-05-14 12:53:11 +00:00

AMDGPUMachineFunction.cpp

MachineFunction: Return reference from getFunction(); NFC

2017-12-15 22:22:58 +00:00

AMDGPUMachineFunction.h

[NFC] fix trivial typos in document and comments

2018-04-14 08:59:00 +00:00

AMDGPUMachineModuleInfo.cpp

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

AMDGPUMachineModuleInfo.h

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

AMDGPUMacroFusion.cpp

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

AMDGPUMacroFusion.h

…

AMDGPUMCInstLower.cpp

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

AMDGPUMCInstLower.h

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

AMDGPUOpenCLEnqueuedBlockLowering.cpp

Rename DEBUG macro to LLVM_DEBUG.

2018-05-14 12:53:11 +00:00

AMDGPUPromoteAlloca.cpp

Rename DEBUG macro to LLVM_DEBUG.

2018-05-14 12:53:11 +00:00

AMDGPUPTNote.h

AMDGPU/NFC: Move AMDGPU specific note types to ELF.h

2017-10-12 18:59:54 +00:00

AMDGPURegAsmNames.inc.cpp

AMDGPU: Work around build special casing .inc files

2017-06-08 19:25:21 +00:00

AMDGPURegisterBankInfo.cpp

AMDGPU/GlobalISel: RegBankSelect for basic int ops

2018-03-19 14:07:23 +00:00

AMDGPURegisterBankInfo.h

AMDGPU/GlobalISel: Define instruction mapping for G_OR

2018-03-01 21:25:25 +00:00

AMDGPURegisterBanks.td

AMDGPU/GlobalISel: Define InstrMappings for G_ICMP

2018-03-01 19:27:10 +00:00

AMDGPURegisterInfo.cpp

AMDGPU: Make getSubRegFromChannel a static member of AMDGPURegisterInfo

2018-05-03 22:38:06 +00:00

AMDGPURegisterInfo.h

AMDGPU: Make getSubRegFromChannel a static member of AMDGPURegisterInfo

2018-05-03 22:38:06 +00:00

AMDGPURegisterInfo.td

AMDGPU: Move INDIRECT_BASE_ADDR definition out of common files

2017-07-29 03:44:07 +00:00

AMDGPURewriteOutArguments.cpp

Rename DEBUG macro to LLVM_DEBUG.

2018-05-14 12:53:11 +00:00

AMDGPUSearchableTables.td

AMDGPU: Dimension-aware image intrinsics

2018-04-04 10:58:54 +00:00

AMDGPUSubtarget.cpp

AMDGPU/GlobalISel: Enable TableGen'd instruction selector

2018-05-10 20:53:06 +00:00

AMDGPUSubtarget.h

AMDGPU: Add D16 instructions preserve unused bits feature

2018-05-04 20:06:57 +00:00

AMDGPUTargetMachine.cpp

AMDGPU: Rename OpenCL lowering pass to be R600 specific.

2018-05-13 10:04:48 +00:00

AMDGPUTargetMachine.h

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

AMDGPUTargetObjectFile.cpp

AMDGPU: Fix set but not used warnings related to AMDGPUAS

2017-11-01 19:12:38 +00:00

AMDGPUTargetObjectFile.h

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

AMDGPUTargetTransformInfo.cpp

Rename DEBUG macro to LLVM_DEBUG.

2018-05-14 12:53:11 +00:00

AMDGPUTargetTransformInfo.h

[AMDGPU] Support horizontal vectorization of min/max.

2018-05-09 21:18:34 +00:00

AMDGPUUnifyDivergentExitNodes.cpp

AMDGPU: Use eraseFromParent to delete am instruction when it is no longer needed.

2018-05-08 18:32:35 +00:00

AMDGPUUnifyMetadata.cpp

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

AMDILCFGStructurizer.cpp

Rename DEBUG macro to LLVM_DEBUG.

2018-05-14 12:53:11 +00:00

AMDKernelCodeT.h

Remove @brief commands from doxygen comments, too.

2018-05-01 16:10:38 +00:00

BUFInstructions.td

AMDGPU: Add D16 instructions preserve unused bits feature

2018-05-04 20:06:57 +00:00

CaymanInstructions.td

[CodeGen] Use MachineOperand::print in the MIRPrinter for MO_Register.

2017-12-07 10:40:31 +00:00

CMakeLists.txt

AMDGPU: Rename OpenCL lowering pass to be R600 specific.

2018-05-13 10:04:48 +00:00

DSInstructions.td

AMDGPU: Add D16 instructions preserve unused bits feature

2018-05-04 20:06:57 +00:00

EvergreenInstructions.td

AMDGPU: Select BFI patterns with 64-bit ints

2018-02-07 00:21:34 +00:00

FLATInstructions.td

AMDGPU: Add D16 instructions preserve unused bits feature

2018-05-04 20:06:57 +00:00

GCNHazardRecognizer.cpp

[DebugInfo] Examine all uses of isDebugValue() for debug instructions.

2018-05-09 02:42:00 +00:00

GCNHazardRecognizer.h

[AMDGPU] Add GCNHazardRecognizer::checkInlineAsmHazards() and GCNHazardRecognizer::checkVALUHazardsHelper(). checkInlineAsmHazards() checks INLINEASM for hazards that we particularly care about (so not exhaustive); this patch adds a check for INLINEASM that defs vregs that hold data-to-be stored by immediately preceding store of more than 8 bytes. If the instr were not within an INLINEASM, this scenario would be handled by checkVALUHazard(). Add checkVALUHazardsHelper(), which will be called by both checkVALUHazards() and checkInlineAsmHazards().

2017-12-07 20:34:25 +00:00

GCNILPSched.cpp

Rename DEBUG macro to LLVM_DEBUG.

2018-05-14 12:53:11 +00:00

GCNIterativeScheduler.cpp

Rename DEBUG macro to LLVM_DEBUG.

2018-05-14 12:53:11 +00:00

GCNIterativeScheduler.h

AMDGPU: Partial ILP scheduler port from SelectionDAG to SchedulingDAG (experimental)

2017-11-20 14:35:53 +00:00

GCNMinRegStrategy.cpp

Rename DEBUG macro to LLVM_DEBUG.

2018-05-14 12:53:11 +00:00

GCNProcessors.td

AMDGPU: Add Vega12 and Vega20

2018-04-30 19:08:16 +00:00

GCNRegPressure.cpp

[DebugInfo] Examine all uses of isDebugValue() for debug instructions.

2018-05-09 02:42:00 +00:00

GCNRegPressure.h

Rename LiveIntervalAnalysis.h to LiveIntervals.h

2017-12-13 02:51:04 +00:00

GCNSchedStrategy.cpp

Rename DEBUG macro to LLVM_DEBUG.

2018-05-14 12:53:11 +00:00

GCNSchedStrategy.h

…

LLVMBuild.txt

…

MIMGInstructions.td

[AMDGPU][MC] Added support of 3-element addresses for MIMG instructions

2018-04-04 13:01:17 +00:00

R600ClauseMergePass.cpp

Rename DEBUG macro to LLVM_DEBUG.

2018-05-14 12:53:11 +00:00

R600ControlFlowFinalizer.cpp

Rename DEBUG macro to LLVM_DEBUG.

2018-05-14 12:53:11 +00:00

R600Defines.h

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

R600EmitClauseMarkers.cpp

Sort the remaining #include lines in include/... and lib/....

2017-06-06 11:49:48 +00:00

R600ExpandSpecialInstrs.cpp

AMDGPU: Make getSubRegFromChannel a static member of AMDGPURegisterInfo

2018-05-03 22:38:06 +00:00

R600FrameLowering.cpp

Sort the remaining #include lines in include/... and lib/....

2017-06-06 11:49:48 +00:00

R600FrameLowering.h

AMDGPU: Initial implementation of calls

2017-08-01 19:54:18 +00:00

R600InstrFormats.td

AMDGPU: Remove global isGCN predicates

2017-10-03 00:06:41 +00:00

R600InstrInfo.cpp

AMDGPU: Make getSubRegFromChannel a static member of AMDGPURegisterInfo

2018-05-03 22:38:06 +00:00

R600InstrInfo.h

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

R600Instructions.td

AMDGPU: Remove deprecated llvm.AMDGPU.kilp intrinsic

2018-04-24 21:37:57 +00:00

R600Intrinsics.td

AMDGPU/R600: Move int_r600_store_stream_output to the public intrinsic file

2018-04-25 20:02:53 +00:00

R600ISelLowering.cpp

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

R600ISelLowering.h

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

R600MachineFunctionInfo.cpp

AMDGPU: Delete more dead code

2016-07-22 17:01:25 +00:00

R600MachineFunctionInfo.h

AMDGPU: Delete more dead code

2016-07-22 17:01:25 +00:00

R600MachineScheduler.cpp

Rename DEBUG macro to LLVM_DEBUG.

2018-05-14 12:53:11 +00:00

R600MachineScheduler.h

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

R600OpenCLImageTypeLoweringPass.cpp

AMDGPU: Rename OpenCL lowering pass to be R600 specific.

2018-05-13 10:04:48 +00:00

R600OptimizeVectorRegisters.cpp

Rename DEBUG macro to LLVM_DEBUG.

2018-05-14 12:53:11 +00:00

R600Packetizer.cpp

Rename DEBUG macro to LLVM_DEBUG.

2018-05-14 12:53:11 +00:00

R600Processors.td

AMDGPU/EG: Add a new FeatureFMA and use it to selectively enable FMA instruction

2017-12-04 23:07:28 +00:00

R600RegisterInfo.cpp

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

R600RegisterInfo.h

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

R600RegisterInfo.td

AMDGPU: Move INDIRECT_BASE_ADDR definition out of common files

2017-07-29 03:44:07 +00:00

R600Schedule.td

…

R700Instructions.td

…

SIAnnotateControlFlow.cpp

Rename DEBUG macro to LLVM_DEBUG.

2018-05-14 12:53:11 +00:00

SIDebuggerInsertNops.cpp

[DebugInfo] Examine all uses of isDebugValue() for debug instructions.

2018-05-09 02:42:00 +00:00

SIDefines.h

[AMDGPU] Added checks for dpp_ctrl value

2018-05-08 16:53:02 +00:00

SIFixSGPRCopies.cpp

Rename DEBUG macro to LLVM_DEBUG.

2018-05-14 12:53:11 +00:00

SIFixVGPRCopies.cpp

Rename DEBUG macro to LLVM_DEBUG.

2018-05-14 12:53:11 +00:00

SIFixWWMLiveness.cpp

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

SIFoldOperands.cpp

Rename DEBUG macro to LLVM_DEBUG.

2018-05-14 12:53:11 +00:00

SIFrameLowering.cpp

AMDGPU: Assign enum name to stack ID

2018-04-23 15:51:26 +00:00

SIFrameLowering.h

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

SIInsertSkips.cpp

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

SIInsertWaitcnts.cpp

Rename DEBUG macro to LLVM_DEBUG.

2018-05-14 12:53:11 +00:00

SIInstrFormats.td

[MachineOperand][Target] MachineOperand::isRenamable semantics changes

2018-02-23 18:25:08 +00:00

SIInstrInfo.cpp

[AMDGPU] Added checks for dpp_ctrl value

2018-05-08 16:53:02 +00:00

SIInstrInfo.h

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

SIInstrInfo.td

AMDGPU: Add Vega12 and Vega20

2018-04-30 19:08:16 +00:00

SIInstructions.td

AMDGPU: Add Vega12 and Vega20

2018-04-30 19:08:16 +00:00

SIIntrinsics.td

…

SIISelLowering.cpp

[AMDGPU] Fix handling of void types in isLegalAddressingMode

2018-05-15 22:07:51 +00:00

SIISelLowering.h

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

SILoadStoreOptimizer.cpp

Rename DEBUG macro to LLVM_DEBUG.

2018-05-14 12:53:11 +00:00

SILowerControlFlow.cpp

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

SILowerI1Copies.cpp

AMDGPU: Fix copying i1 value out of loop with non-uniform exit

2018-04-04 10:57:58 +00:00

SIMachineFunctionInfo.cpp

AMDGPU: Fix not preserving CSR VGPR if used for SGPR spills

2018-03-27 19:42:55 +00:00

SIMachineFunctionInfo.h

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

SIMachineScheduler.cpp

Rename DEBUG macro to LLVM_DEBUG.

2018-05-14 12:53:11 +00:00

SIMachineScheduler.h

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

SIMemoryLegalizer.cpp

Remove \brief commands from doxygen comments.

2018-05-01 15:54:18 +00:00

SIOptimizeExecMasking.cpp

Rename DEBUG macro to LLVM_DEBUG.

2018-05-14 12:53:11 +00:00

SIOptimizeExecMaskingPreRA.cpp

Rename DEBUG macro to LLVM_DEBUG.

2018-05-14 12:53:11 +00:00

SIPeepholeSDWA.cpp

Rename DEBUG macro to LLVM_DEBUG.

2018-05-14 12:53:11 +00:00

SIRegisterInfo.cpp

AMDGPU/GlobalISel: Implement select() for >32-bit G_STORE

2018-05-11 23:12:49 +00:00

SIRegisterInfo.h

AMDGPU/GlobalISel: Enable TableGen'd instruction selector

2018-05-10 20:53:06 +00:00

SIRegisterInfo.td

[AMDGPU][MC][GFX8][GFX9] Added XNACK_MASK support

2018-01-10 14:22:19 +00:00

SISchedule.td

[SchedModel] Complete models shouldn't match against itineraries when they don't use them (PR35639)

2018-04-05 13:11:36 +00:00

SIShrinkInstructions.cpp

Rename DEBUG macro to LLVM_DEBUG.

2018-05-14 12:53:11 +00:00

SIWholeQuadMode.cpp

Rename DEBUG macro to LLVM_DEBUG.

2018-05-14 12:53:11 +00:00

SMInstructions.td

[AMDGPU][MC][VI][GFX9] Added s_atc_probe* instructions

2018-04-06 15:48:39 +00:00

SOPInstructions.td

[AMDGPU][MC][GFX9] Added instructions s_mul_hi_*32, s_lshl*_add_u32

2018-04-09 13:10:33 +00:00

VIInstrFormats.td

…

VIInstructions.td

…

VOP1Instructions.td

[AMDGPU][MC][GFX9] Added v_screen_partition_4se_b32

2018-04-11 13:13:30 +00:00

VOP2Instructions.td

AMDGPU: Add Vega12 and Vega20

2018-04-30 19:08:16 +00:00

VOP3Instructions.td

AMDGPU: Fix v_dot{4, 8}* instruction encoding

2018-05-15 19:32:47 +00:00

VOP3PInstructions.td

AMDGPU: Fix v_dot{4, 8}* instruction encoding

2018-05-15 19:32:47 +00:00

VOPCInstructions.td

[AMDGPU][MC] Corrected default values for unused SDWA operands

2018-03-16 15:40:27 +00:00

VOPInstructions.td

AMDGPU: Introduce common SOP_Pseudo and VOP_Pseudo TableGen base classes

2018-03-26 13:56:53 +00:00