shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions 6 Packages Projects Releases Wiki Activity
llvm-project/llvm/lib/Target/AMDGPU
History
Nikita Popov 0f46e31cfb
[IR] Change representation of getelementptr inrange (#84341) 
As part of the migration to ptradd
(https://discourse.llvm.org/t/rfc-replacing-getelementptr-with-ptradd/68699),
we need to change the representation of the `inrange` attribute, which
is used for vtable splitting.

Currently, inrange is specified as follows:

```
getelementptr inbounds ({ [4 x ptr], [4 x ptr] }, ptr @vt, i64 0, inrange i32 1, i64 2)
```

The `inrange` is placed on a GEP index, and all accesses must be "in
range" of that index. The new representation is as follows:

```
getelementptr inbounds inrange(-16, 16) ({ [4 x ptr], [4 x ptr] }, ptr @vt, i64 0, i32 1, i64 2)
```

This specifies which offsets are "in range" of the GEP result. The new
representation will continue working when canonicalizing to ptradd
representation:

```
getelementptr inbounds inrange(-16, 16) (i8, ptr @vt, i64 48)
```

The inrange offsets are relative to the return value of the GEP. An
alternative design could make them relative to the source pointer
instead. The result-relative format was chosen on the off-chance that we
want to extend support to non-constant GEPs in the future, in which case
this variant is more expressive.

This implementation "upgrades" the old inrange representation in bitcode
by simply dropping it. This is a very niche feature, and I don't think
trying to upgrade it is worthwhile. Let me know if you disagree.
2024-03-20 10:59:45 +01:00
..
AsmParser
Reland [AMDGPU] Add AMDGPU specific variadic operation MCExprs (#84562)
2024-03-14 14:31:00 +00:00
Disassembler
[AMDGPU] Only try DecoderTables for the current subtarget. NFCI. (#82992)
2024-02-26 13:02:08 +00:00
MCA
[AMDGPU][SIInsertWaitcnts] Do not add s_waitcnt when the counters are known to be 0 already (#72830)
2023-12-15 12:33:32 +01:00
MCTargetDesc
Reland [AMDGPU] Add AMDGPU specific variadic operation MCExprs (#84562)
2024-03-14 14:31:00 +00:00
TargetInfo
[AMDGPU] Eliminate SIMCCodeEmitter and de-virtualise encoding methods.
2023-07-05 10:13:33 +01:00
Utils
[AMDGPU] Fix GFX11 sendmsg codes (#85299)
2024-03-15 09:46:58 -07:00
AMDGPU.h
[AMDGPU] Add IR-level pass to rewrite away address space 7 (#77952)
2024-03-06 09:49:58 -06:00
AMDGPU.td
[AMDGPU][True16] Make NotHasTrue16BitInsts a True16Predicate (#84771)
2024-03-11 13:58:45 -04:00
AMDGPUAliasAnalysis.cpp
[AA] Skip the layer of indirection in returning conservative results.
2023-07-28 12:13:35 -07:00
AMDGPUAliasAnalysis.h
[AA] Allow for flow-sensitive analyses.
2022-12-15 21:04:38 -08:00
AMDGPUAlwaysInlinePass.cpp
[amdgpu] Implement dynamic LDS accesses from non-kernel functions
2023-04-04 20:06:34 +01:00
AMDGPUAnnotateKernelFeatures.cpp
…
AMDGPUAnnotateUniformValues.cpp
[AMDGPU] Replace LegacyDA with Uniformity Analysis in AnnotateUniformValues
2023-02-28 13:05:38 -07:00
AMDGPUArgumentUsageInfo.cpp
[AMDGPU] Add DAG ISel support for preloaded kernel arguments
2023-09-25 09:32:59 -07:00
AMDGPUArgumentUsageInfo.h
[AMDGPU] Miscellaneous clang-format changes (#75186)
2023-12-12 14:26:04 +00:00
AMDGPUAsmPrinter.cpp
Reapply "[AMDGPU] Add pal metadata 3.0 support to callable pal funcs (#67104)"
2024-03-14 10:56:43 +09:00
AMDGPUAsmPrinter.h
[AMDGPU] Remove AMDGPUAsmPrinter::isBlockOnlyReachableByFallthrough (#71407)
2023-11-06 16:29:52 +00:00
AMDGPUAtomicOptimizer.cpp
[AMDGPU] Fix scan of atomicFSub in AtomicOptimizer. (#66082)
2023-09-13 09:57:10 +05:30
AMDGPUAttributes.def
Partially reapply "AMDGPU: Invert handling of enqueued block detection"
2023-01-12 15:02:16 -05:00
AMDGPUAttributor.cpp
[AMDGPU] Add an asm directive to track code_object_version (#76267)
2024-01-21 11:54:47 -05:00
AMDGPUCallingConv.td
[AMDGPU] promote i1 arg type for amdgpu_cs (#82971)
2024-03-01 14:25:46 +05:30
AMDGPUCallLowering.cpp
[GlobalISel] convergence control tokens and intrinsics (#67006)
2024-03-18 10:34:11 +05:30
AMDGPUCallLowering.h
[AMDGPU] ISel for @llvm.amdgcn.cs.chain intrinsic (#68186)
2023-11-06 12:30:07 +01:00
AMDGPUCodeGenPrepare.cpp
[AMDGCN] Use ZExt when handling indices in insertment element (#85718)
2024-03-19 21:44:08 -07:00
AMDGPUCombine.td
[AMDGPU][GlobalISel] Add fdiv / sqrt to rsq combine (#78673)
2024-02-22 09:47:36 +01:00
AMDGPUCombinerHelper.cpp
[AMDGPU] Min/max changes for GFX12 (#75214)
2023-12-13 14:18:10 +01:00
AMDGPUCombinerHelper.h
[llvm] Fix include guards
2023-06-13 10:47:18 +01:00
AMDGPUCtorDtorLowering.cpp
[llvm] Replace calls to Type::getPointerTo (NFC)
2023-11-30 13:18:51 -06:00
AMDGPUCtorDtorLowering.h
AMDGPU: Port AMDGPUCtorDtorLowering to new PM
2022-12-09 13:43:38 -05:00
AMDGPUExportClustering.cpp
…
AMDGPUExportClustering.h
…
AMDGPUFeatures.td
…
AMDGPUFrameLowering.cpp
[NFC][AMDGPU] Fix typo.
2022-08-20 08:30:42 +02:00
AMDGPUFrameLowering.h
…
AMDGPUGenRegisterBankInfo.def
Silence illegal address computation warning (#83244)
2024-03-01 21:41:12 +05:30
AMDGPUGISel.td
[AMDGPU] Add GFX12 WMMA and SWMMAC instructions (#77795)
2024-01-24 13:43:07 +01:00
AMDGPUGlobalISelDivergenceLowering.cpp
AMDGPU/GlobalISel: lane masks merging (#73337)
2024-02-29 13:57:59 +01:00
AMDGPUGlobalISelUtils.cpp
[AMDGPU] Remove hasAtomicFaddRtnForTy as it is not used anywhere (#82841)
2024-02-23 21:14:38 -05:00
AMDGPUGlobalISelUtils.h
[AMDGPU] Remove hasAtomicFaddRtnForTy as it is not used anywhere (#82841)
2024-02-23 21:14:38 -05:00
AMDGPUHSAMetadataStreamer.cpp
[AMDGPU] Adding the amdgpu_num_work_groups function attribute (#79035)
2024-03-12 10:30:39 -07:00
AMDGPUHSAMetadataStreamer.h
[AMDGPU] Introduce Code Object V6 (#76954)
2024-02-05 08:19:53 +01:00
AMDGPUIGroupLP.cpp
[AMDGPU] Do not attempt to fallback to default mutations (#83208)
2024-02-27 18:04:59 -08:00
AMDGPUIGroupLP.h
[AMDGPU] Do not attempt to fallback to default mutations (#83208)
2024-02-27 18:04:59 -08:00
AMDGPUImageIntrinsicOptimizer.cpp
[AMDGPU] Use llvm::none_of (NFC)
2024-01-24 00:27:37 -08:00
AMDGPUInsertDelayAlu.cpp
[AMDGPU] Add functions for composing and decomposing S_WAIT_DEPCTR operands
2023-07-04 11:02:12 +01:00
AMDGPUInsertSingleUseVDST.cpp
[AMDGPU] New AMDGPUInsertSingleUseVDST pass (#72388)
2023-11-24 10:23:06 +00:00
AMDGPUInstCombineIntrinsic.cpp
[IRBuilder] Fold binary intrinsics (#80743)
2024-03-15 09:58:25 +01:00
AMDGPUInstrInfo.cpp
Restore "[GlobalISel] GIntrinsic subclass to represent intrinsics in Generic Machine IR"
2023-07-27 14:49:17 +05:30
AMDGPUInstrInfo.h
Restore "[GlobalISel] GIntrinsic subclass to represent intrinsics in Generic Machine IR"
2023-07-27 14:49:17 +05:30
AMDGPUInstrInfo.td
[AMDGPU] Min/max changes for GFX12 (#75214)
2023-12-13 14:18:10 +01:00
AMDGPUInstructions.td
[AMDGPU] Fix canonicalization of truncated values. (#83054)
2024-03-13 12:08:39 +00:00
AMDGPUInstructionSelector.cpp
[KnownBits] Add API for nuw flag in computeForAddSub; NFC
2024-03-05 12:59:58 -06:00
AMDGPUInstructionSelector.h
[AMDGPU] Clean up functions for checking inline literals (#81282)
2024-02-15 12:11:51 -05:00
AMDGPUISelDAGToDAG.cpp
[CodeGen] Use LocationSize for MMO getSize (#84751)
2024-03-17 18:15:56 +00:00
AMDGPUISelDAGToDAG.h
[AMDGPU] Clean up functions for checking inline literals (#81282)
2024-02-15 12:11:51 -05:00
AMDGPUISelLowering.cpp
AMDGPU: Enable ExpandLargeFpConvert for > 64-bit types
2024-03-15 16:08:39 +05:30
AMDGPUISelLowering.h
[AMDGPU] Remove unnecessary add instructions in ctlz.i8 (#77615)
2024-01-19 10:16:46 +00:00
AMDGPULateCodeGenPrepare.cpp
[AMDGPU] Do not widen scalar loads on GFX12 (#78724)
2024-01-19 15:30:07 +00:00
AMDGPULegalizerInfo.cpp
[CodeGen] Use LocationSize for MMO getSize (#84751)
2024-03-17 18:15:56 +00:00
AMDGPULegalizerInfo.h
[AMDGPU] Implement 'llvm.get.fpenv' and 'llvm.set.fpenv' (#83906)
2024-03-06 08:11:54 -06:00
AMDGPULibCalls.cpp
[NFC][RemoveDIs] Use iterators for insertion at various call-sites (#84736)
2024-03-19 16:36:29 +00:00
AMDGPULibFunc.cpp
[llvm] Use StringRef::{starts,ends}_with (NFC) (#74956)
2023-12-11 21:01:36 -08:00
AMDGPULibFunc.h
AMDGPU: Use pown instead of pow if known integral
2023-09-01 08:22:16 -04:00
AMDGPULowerBufferFatPointers.cpp
[IR] Change representation of getelementptr inrange (#84341)
2024-03-20 10:59:45 +01:00
AMDGPULowerKernelArguments.cpp
[AMDGPU] Enable kernel arg preloading with gfx90a (#81180)
2024-02-12 22:33:29 -08:00
AMDGPULowerKernelAttributes.cpp
[AMDGPU] Add an asm directive to track code_object_version (#76267)
2024-01-21 11:54:47 -05:00
AMDGPULowerModuleLDSPass.cpp
[AMDGPU] Let LowerModuleLDS run twice on the same module (#81729)
2024-03-11 09:20:01 +01:00
AMDGPUMachineCFGStructurizer.cpp
Use object directly instead of accessing ArrayRef (#83263)
2024-03-01 19:15:42 +05:30
AMDGPUMachineFunction.cpp
[AMDGPU] Add dynamic LDS size implicit kernel argument to CO-v5 (#65273)
2024-01-04 19:05:12 +05:30
AMDGPUMachineFunction.h
[AMDGPU] Add dynamic LDS size implicit kernel argument to CO-v5 (#65273)
2024-01-04 19:05:12 +05:30
AMDGPUMachineModuleInfo.cpp
…
AMDGPUMachineModuleInfo.h
std::optional::value => operator*/operator->
2022-12-17 00:42:05 +00:00
AMDGPUMacroFusion.cpp
[DAG] clang-format createBranchMacroFusionDAGMutation calls. NFC.
2023-11-20 12:13:09 +00:00
AMDGPUMacroFusion.h
…
AMDGPUMarkLastScratchLoad.cpp
[AMDGPU] Add mark last scratch load pass (#75512)
2024-01-18 09:36:44 +01:00
AMDGPUMCInstLower.cpp
[AMDGPU] Fix expensive-checks build.
2023-07-05 10:26:21 +01:00
AMDGPUMCInstLower.h
AMDGPU: Fix missing c++ mode comment
2022-06-01 21:14:48 -04:00
AMDGPUMIRFormatter.cpp
AMDGPU: Remove ImagePSV and move images to addrspace 7
2022-11-30 11:32:34 +01:00
AMDGPUMIRFormatter.h
[llvm] Remove redundaunt virtual specifiers (NFC)
2022-07-24 21:50:35 -07:00
AMDGPUOpenCLEnqueuedBlockLowering.cpp
[NFC] Remove Type::getInt8PtrTy (#71029)
2023-11-07 17:26:26 +01:00
AMDGPUPerfHintAnalysis.cpp
[AMDGPU] Set amdgpu-memory-bound if a basic block has dense global memory access
2022-07-19 15:16:28 +05:30
AMDGPUPerfHintAnalysis.h
[AMDGPU] Set amdgpu-memory-bound if a basic block has dense global memory access
2022-07-19 15:16:28 +05:30
AMDGPUPostLegalizerCombiner.cpp
[AMDGPU][GlobalISel] Add fdiv / sqrt to rsq combine (#78673)
2024-02-22 09:47:36 +01:00
AMDGPUPredicateControl.td
[AMDGPU][TableGen][NFC] Combine predicates without using classes. (#82346)
2024-02-21 11:45:36 +00:00
AMDGPUPreLegalizerCombiner.cpp
[AArch64][GlobalISel] Refactor Combine G_CONCAT_VECTOR (#80866)
2024-02-15 10:09:20 +00:00
AMDGPUPrintfRuntimeBinding.cpp
[NFC][RemoveDIs] Use iterators for insertion at various call-sites (#84736)
2024-03-19 16:36:29 +00:00
AMDGPUPromoteAlloca.cpp
[AMDGPU][PromoteAlloca] Whole-function alloca promotion to vector (#84735)
2024-03-19 11:49:22 +01:00
AMDGPUPromoteKernelArguments.cpp
[llvm] Remove uses of getWithSamePointeeType() (NFC)
2023-07-18 12:07:09 +02:00
AMDGPUPTNote.h
…
AMDGPURegBankCombiner.cpp
[NFC][CodeGen] Change CodeGenOpt::Level/CodeGenFileType into enum classes (#66295)
2023-09-14 14:10:14 -07:00
AMDGPURegBankSelect.cpp
AMDGPU: Special case uniformity info for single lane workgroups
2023-06-28 07:25:48 -04:00
AMDGPURegBankSelect.h
AMDGPU/GlobalISel: Add stub custom regbankselect pass
2023-01-30 16:18:20 -04:00
AMDGPURegisterBankInfo.cpp
[CodeGen] Use LocationSize for MMO getSize (#84751)
2024-03-17 18:15:56 +00:00
AMDGPURegisterBankInfo.h
[AMDGPU] Make isScalarLoadLegal a member of AMDGPURegisterBankInfo. NFC.
2024-01-09 11:53:12 +00:00
AMDGPURegisterBanks.td
[AMDGPU][True16] Don't use the VGPR_LO/HI16 register classes. (#76440)
2023-12-28 11:48:25 +00:00
AMDGPURemoveIncompatibleFunctions.cpp
[AMDGPU] Introduce GFX9/10.1/10.3/11 Generic Targets (#76955)
2024-02-12 10:18:20 +01:00
AMDGPUResourceUsageAnalysis.cpp
[Target][AMDGPU] Fix TSan error on AMDGPU Target. (#79529)
2024-01-25 21:32:37 -08:00
AMDGPUResourceUsageAnalysis.h
[Target][AMDGPU] Fix TSan error on AMDGPU Target. (#79529)
2024-01-25 21:32:37 -08:00
AMDGPURewriteOutArguments.cpp
[llvm] Stop including llvm/ADT/SmallSet.h (NFC)
2023-11-11 12:32:15 -08:00
AMDGPURewriteUndefForPHI.cpp
[AMDGPU] Do not preserve UniformityInfo (#76696)
2024-01-02 13:42:56 +05:30
AMDGPUSearchableTables.td
[AMDGPU] Add GFX12 WMMA and SWMMAC instructions (#77795)
2024-01-24 13:43:07 +01:00
AMDGPUSetWavePriority.cpp
[AMDGPU][SetWavePriority] Fix dealing with MBBInfo records.
2022-09-30 14:27:50 +01:00
AMDGPUSubtarget.cpp
[AMDGPU] Adding the amdgpu_num_work_groups function attribute (#79035)
2024-03-12 10:30:39 -07:00
AMDGPUSubtarget.h
[AMDGPU] Adding the amdgpu_num_work_groups function attribute (#79035)
2024-03-12 10:30:39 -07:00
AMDGPUTargetMachine.cpp
Revert "[AMDGPU] Run LowerLDS at the end of the fullLTO pipeline (#75333)"
2024-03-18 11:18:57 +01:00
AMDGPUTargetMachine.h
Restore "Implement convergence control in MIR using SelectionDAG (#71785)"
2024-03-06 12:19:32 +05:30
AMDGPUTargetObjectFile.cpp
[llvm] Use StringRef::{starts,ends}_with (NFC) (#74956)
2023-12-11 21:01:36 -08:00
AMDGPUTargetObjectFile.h
…
AMDGPUTargetTransformInfo.cpp
[TTI]Fallback to SingleSrcPermute shuffle kind, if no direct estimation for
2024-02-12 07:09:49 -05:00
AMDGPUTargetTransformInfo.h
GFX12: Add LoopDataPrefetchPass (#75625)
2023-12-19 08:32:16 +01:00
AMDGPUUnifyDivergentExitNodes.cpp
[AMDGPU] Do not preserve UniformityInfo (#76696)
2024-01-02 13:42:56 +05:30
AMDGPUUnifyDivergentExitNodes.h
[llvm] Fix include guards
2023-06-13 10:47:18 +01:00
AMDGPUUnifyMetadata.cpp
[Target] Qualify auto in range-based for loops (NFC)
2022-08-28 10:41:50 -07:00
AMDKernelCodeT.h
…
BUFInstructions.td
[AMDGPU] Remove unneeded MnemonicAlias. NFC.
2024-03-13 12:03:41 +00:00
CaymanInstructions.td
…
CMakeLists.txt
[AMDGPU] Add IR-level pass to rewrite away address space 7 (#77952)
2024-03-06 09:49:58 -06:00
DSDIRInstructions.td
AMDGPU: Copy SubtargetPredicate from pseudo for DSDIR_Real (#84057)
2024-03-05 13:49:34 -08:00
DSInstructions.td
AMDGPU: Remove incorrect uses of SubtaretPredicate around DS_Reals (#85001)
2024-03-13 09:49:30 -07:00
EvergreenInstructions.td
Use llvm::popcount instead of llvm::countPopulation(NFC)
2023-01-22 12:48:51 -08:00
EXPInstructions.td
[AMDGPU] Simplify EXP Real instruction definitions. NFC.
2024-03-07 11:04:43 +00:00
FLATInstructions.td
[AMDGPU] Remove unneeded addr mode predicates on FLAT Real instructions (#85641)
2024-03-18 14:29:53 +00:00
GCNCreateVOPD.cpp
[AMDGPU] Update VOP instructions for GFX12 (#74853)
2023-12-12 11:38:24 +01:00
GCNDPPCombine.cpp
[AMDGPU] Fix warnings about unused variables [NFC]
2024-01-25 09:35:10 +01:00
GCNHazardRecognizer.cpp
AMDGPU: Refactor mfma hazard handling [NFC] (#84276)
2024-03-07 14:39:59 +05:30
GCNHazardRecognizer.h
[AMDGPU][GFX11] Mitigate VALU mask write hazard
2022-10-01 16:21:24 +09:00
GCNILPSched.cpp
Add llvm::min/max_element and use it in llvm/ and mlir/ directories. (#84678)
2024-03-10 20:00:13 -07:00
GCNIterativeScheduler.cpp
[AMDGPU] Prefer lower total register usage in regions with spilling
2024-02-26 12:19:52 -08:00
GCNIterativeScheduler.h
…
GCNMinRegStrategy.cpp
[llvm] Qualify auto in range-based for loops (NFC)
2022-08-13 12:55:42 -07:00
GCNNSAReassign.cpp
[AMDGPU] Do not run GCNNSAReassign pass for GFX12 (#78185)
2024-01-17 15:22:48 +00:00
GCNPreRALongBranchReg.cpp
[AMDGPU] Reserve SGPR pair when long branches are present
2023-06-29 16:50:46 -05:00
GCNPreRAOptimizations.cpp
…
GCNProcessors.td
[AMDGPU] Replace '.' with '-' in generic target names (#81718)
2024-02-14 15:19:04 +01:00
GCNRegPressure.cpp
[AMDGPU] Prefer lower total register usage in regions with spilling
2024-02-26 12:19:52 -08:00
GCNRegPressure.h
[AMDGPU] Prefer lower total register usage in regions with spilling
2024-02-26 12:19:52 -08:00
GCNRewritePartialRegUses.cpp
[AMDGPU] Fix GCNRewritePartialRegUses pass: vector regclass is selected instead of scalar. (#69957)
2023-11-16 16:56:46 +01:00
GCNSchedStrategy.cpp
[AMDGPU] Do not attempt to fallback to default mutations (#83208)
2024-02-27 18:04:59 -08:00
GCNSchedStrategy.h
[AMDGPU] Fix typos. NFC
2024-01-26 12:04:58 +01:00
GCNSubtarget.h
AMDGPU: Rename HasVinterInsts to HasVINTERPEncoding, NFC (#84535)
2024-03-08 10:53:28 -08:00
GCNVOPDUtils.cpp
[AMDGPU] Update VOP instructions for GFX12 (#74853)
2023-12-12 11:38:24 +01:00
GCNVOPDUtils.h
[AMDGPU] gfx11 Generate VOPD Instructions
2022-07-05 09:18:19 -04:00
InstCombineTables.td
…
MIMGInstructions.td
AMDGPU: Proper use of HasImageInsts in vimage inst definitions, NFC (#83884)
2024-03-04 12:06:49 -08:00
R600.h
[NFC][CodeGen] Change CodeGenOpt::Level/CodeGenFileType into enum classes (#66295)
2023-09-14 14:10:14 -07:00
R600.td
[AMDGPU][NFC] Extend PredicateControl to support True16 predicates. (#82245)
2024-02-20 11:37:44 +00:00
R600AsmPrinter.cpp
[llvm] LLVM_FALLTHROUGH => [[fallthrough]]. NFC
2022-08-08 11:24:15 -07:00
R600AsmPrinter.h
…
R600ClauseMergePass.cpp
…
R600ControlFlowFinalizer.cpp
[llvm] LLVM_FALLTHROUGH => [[fallthrough]]. NFC
2022-08-08 11:24:15 -07:00
R600Defines.h
…
R600EmitClauseMarkers.cpp
…
R600ExpandSpecialInstrs.cpp
…
R600FrameLowering.cpp
…
R600FrameLowering.h
…
R600InstrFormats.td
…
R600InstrInfo.cpp
[Target] Use *{Set,Map}::contains (NFC)
2023-03-14 18:06:55 -07:00
R600InstrInfo.h
CodeGen: Move getAddressSpaceForPseudoSourceKind into TargetMachine
2022-06-01 09:45:40 -04:00
R600InstrInfo.td
…
R600Instructions.td
[AMDGPU] Generic lowering for rint and nearbyint (#69596)
2023-11-14 18:49:21 +01:00
R600ISelDAGToDAG.cpp
[NFC][CodeGen] Change CodeGenOpt::Level/CodeGenFileType into enum classes (#66295)
2023-09-14 14:10:14 -07:00
R600ISelLowering.cpp
[Target] Use getConstantOperandVal (NFC)
2024-01-14 00:53:29 -08:00
R600ISelLowering.h
AMDGPU: Support atomicrmw uinc_wrap/udec_wrap
2023-01-27 22:17:16 -04:00
R600MachineCFGStructurizer.cpp
[AMDGPU] Fix -Wunused-variable in -DLLVM_ENABLE_ASSERTIONS=off builds
2022-04-19 22:36:58 -07:00
R600MachineFunctionInfo.cpp
CodeGen: Don't lazily construct MachineFunctionInfo
2022-12-21 10:49:32 -05:00
R600MachineFunctionInfo.h
CodeGen: Don't lazily construct MachineFunctionInfo
2022-12-21 10:49:32 -05:00
R600MachineScheduler.cpp
…
R600MachineScheduler.h
…
R600MCInstLower.cpp
[NFC] Hide implementation details in anonymous namespaces
2023-01-08 17:37:02 +01:00
R600OpenCLImageTypeLoweringPass.cpp
[llvm] Use StringRef::{starts,ends}_with (NFC) (#74956)
2023-12-11 21:01:36 -08:00
R600OptimizeVectorRegisters.cpp
[AMDGPU] Use llvm::all_of (NFC)
2024-01-30 22:12:07 -08:00
R600Packetizer.cpp
…
R600Processors.td
…
R600RegisterInfo.cpp
PEI should be able to use backward walk in replaceFrameIndicesBackward.
2022-11-18 15:57:34 +01:00
R600RegisterInfo.h
PEI should be able to use backward walk in replaceFrameIndicesBackward.
2022-11-18 15:57:34 +01:00
R600RegisterInfo.td
…
R600Schedule.td
…
R600Subtarget.cpp
AMDGPU: Clean up LDS-related occupancy calculations
2023-01-23 21:43:06 +01:00
R600Subtarget.h
…
R600TargetMachine.cpp
Fix Passing TargetOptions by Value in TargetMachines for AMDGPU (#79866)
2024-02-01 09:50:44 -08:00
R600TargetMachine.h
Fix Passing TargetOptions by Value in TargetMachines for AMDGPU (#79866)
2024-02-01 09:50:44 -08:00
R600TargetTransformInfo.cpp
[llvm][TypeSize] Fix addition/subtraction in TypeSize. (#72979)
2023-11-22 08:52:53 +00:00
R600TargetTransformInfo.h
[LV][NFC] Use ElementCount for getMaxInterleaveFactor
2023-02-22 10:15:05 +00:00
R700Instructions.td
…
SIAnnotateControlFlow.cpp
[llvm] Use Instruction::hasMetadata (NFC)
2024-01-27 22:20:22 -08:00
SIDefines.h
[AMDGPU] Fix GFX11 sendmsg codes (#85299)
2024-03-15 09:46:58 -07:00
SIFixSGPRCopies.cpp
Add llvm::min/max_element and use it in llvm/ and mlir/ directories. (#84678)
2024-03-10 20:00:13 -07:00
SIFixVGPRCopies.cpp
AMDGPU: Make SIFixVGPRCopies preserve everything
2023-07-06 10:26:21 -04:00
SIFoldOperands.cpp
Add non-null check before accessing pointer (#83459)
2024-03-07 10:31:34 +05:30
SIFormMemoryClauses.cpp
[AMDGPU] Make use of MachineInstr::all_defs and all_uses. NFCI.
2023-06-05 10:32:33 +01:00
SIFrameLowering.cpp
[AMDGPU][NFC] Have helpers to deal with encoding fields. (#82772)
2024-02-23 17:34:55 +00:00
SIFrameLowering.h
Revert "[AMDGPU] Compiler should synthesize private buffer resource descriptor from flat_scratch_init" (#81234)
2024-02-09 09:57:38 +01:00
SIInsertHardClauses.cpp
[Codegen] Make Width in getMemOperandsWithOffsetWidth a LocationSize. (#83875)
2024-03-06 17:40:13 +00:00
SIInsertWaitcnts.cpp
[AMDGPU] Add eventMask function in WaitcntGenerator class (NFC) (#85210)
2024-03-15 10:22:58 +05:30
SIInstrFormats.td
[AMDGPU] Consolidate SGPRSpill and VGPRSpill into single Spill bit (#81901)
2024-02-16 13:32:59 -05:00
SIInstrInfo.cpp
[CodeGen] Use LocationSize for MMO getSize (#84751)
2024-03-17 18:15:56 +00:00
SIInstrInfo.h
AMDGPU: Treat SWMMAC the same as MFMA and other WMMA for sched_barrier (#85721)
2024-03-19 09:58:09 -07:00
SIInstrInfo.td
AMDGPU: Partially clean up canonicalized predicates in tablegen (#85404)
2024-03-15 21:09:18 +05:30
SIInstructions.td
AMDGPU: Partially clean up canonicalized predicates in tablegen (#85404)
2024-03-15 21:09:18 +05:30
SIISelLowering.cpp
[AMDGPU] Fix canonicalization of truncated values. (#83054)
2024-03-13 12:08:39 +00:00
SIISelLowering.h
[AMDGPU] Fix canonicalization of truncated values. (#83054)
2024-03-13 12:08:39 +00:00
SILateBranchLowering.cpp
[AMDGPU] ISel for @llvm.amdgcn.cs.chain intrinsic (#68186)
2023-11-06 12:30:07 +01:00
SILoadStoreOptimizer.cpp
[CodeGen] Use LocationSize for MMO getSize (#84751)
2024-03-17 18:15:56 +00:00
SILowerControlFlow.cpp
[NFC][CodeGen] Change CodeGenOpt::Level/CodeGenFileType into enum classes (#66295)
2023-09-14 14:10:14 -07:00
SILowerI1Copies.cpp
AMDGPU/GlobalISelDivergenceLowering: select divergent i1 phis (#80003)
2024-02-05 14:07:01 +01:00
SILowerI1Copies.h
AMDGPU/GlobalISelDivergenceLowering: select divergent i1 phis (#80003)
2024-02-05 14:07:01 +01:00
SILowerSGPRSpills.cpp
[AMDGPU] Pick available high VGPR for CSR SGPR spilling (#78669)
2024-01-24 07:08:43 +05:30
SILowerWWMCopies.cpp
Reapply "[CodeGen]Allow targets to use target specific COPY instructions for live range splitting"
2023-07-31 20:15:45 -04:00
SIMachineFunctionInfo.cpp
[AMDGPU] Adding the amdgpu_num_work_groups function attribute (#79035)
2024-03-12 10:30:39 -07:00
SIMachineFunctionInfo.h
[AMDGPU] Adding the amdgpu_num_work_groups function attribute (#79035)
2024-03-12 10:30:39 -07:00
SIMachineScheduler.cpp
Add llvm::min/max_element and use it in llvm/ and mlir/ directories. (#84678)
2024-03-10 20:00:13 -07:00
SIMachineScheduler.h
…
SIMemoryLegalizer.cpp
[AMDGPU] Handle amdgpu.last.use metadata (#83816)
2024-03-06 16:33:52 +01:00
SIModeRegister.cpp
[AMDGPU][NFC] Have helpers to deal with encoding fields. (#82772)
2024-02-23 17:34:55 +00:00
SIModeRegisterDefaults.cpp
[AMDGPU] Update IEEE and DX10_CLAMP for GFX12 (#75030)
2023-12-13 13:52:40 +01:00
SIModeRegisterDefaults.h
[AMDGPU] Update IEEE and DX10_CLAMP for GFX12 (#75030)
2023-12-13 13:52:40 +01:00
SIOptimizeExecMasking.cpp
Reapply "Convert many LivePhysRegs uses to LiveRegUnits" (#84338)
2024-03-08 19:05:00 +05:30
SIOptimizeExecMaskingPreRA.cpp
[MC] Add MCRegisterInfo::regunits for iteration over register units
2023-06-16 05:39:50 +03:00
SIOptimizeVGPRLiveRange.cpp
[AMDGPU] Skip debug instruction uses while optimizing live range of a reg in SIOptimizeVGPRLiveRange
2023-08-07 11:35:39 +05:30
SIPeepholeSDWA.cpp
[AMDGPU] Don't form sext/abs/neg fp8 cvt (#83843)
2024-03-06 10:38:20 +01:00
SIPostRABundler.cpp
[MC] Add MCRegisterInfo::regunits for iteration over register units
2023-06-16 05:39:50 +03:00
SIPreAllocateWWMRegs.cpp
[CodeGen] Do not pass MF into MachineRegisterInfo methods. NFC. (#84770)
2024-03-11 15:35:05 +00:00
SIPreEmitPeephole.cpp
[AMDGPU] Use MachineBasicBlock::instrs (NFC)
2024-01-28 10:47:07 -08:00
SIProgramInfo.cpp
[AMDGPU] Update IEEE and DX10_CLAMP for GFX12 (#75030)
2023-12-13 13:52:40 +01:00
SIProgramInfo.h
[AMDGPU] Update IEEE and DX10_CLAMP for GFX12 (#75030)
2023-12-13 13:52:40 +01:00
SIRegisterInfo.cpp
Silence potential overflow warning (#83272)
2024-03-18 14:38:27 +00:00
SIRegisterInfo.h
[CodeGen] Make some includes explicit (NFC)
2023-11-24 14:43:18 +01:00
SIRegisterInfo.td
[AMDGPU] Fix decoder for BF16 inline constants (#82276)
2024-02-19 13:45:23 -08:00
SISchedule.td
AMDGPU: Correct cycle counts for f64 mfma on gfx940 (#83782)
2024-03-06 09:36:01 +05:30
SIShrinkInstructions.cpp
AMDGPU/NFC: Remove some bits from TSFlags (#81525)
2024-02-12 16:43:48 -05:00
SIWholeQuadMode.cpp
[AMDGPU] Add VDSDIR instructions for GFX12 (#75197)
2024-01-03 16:32:00 +01:00
SMInstructions.td
[AMDGPU] Remove AtomicNoRet class and getAtomicNoRetOp table (#83593)
2024-03-01 17:18:55 +00:00
SOPInstructions.td
[AMDGPU] Simplify some uniform patterns. NFC. (#85407)
2024-03-15 15:40:23 +00:00
VIInstrFormats.td
[AMDGPU] gfx11 export instructions
2022-05-25 14:44:09 -04:00
VINTERPInstructions.td
AMDGPU: Rename HasVinterInsts to HasVINTERPEncoding, NFC (#84535)
2024-03-08 10:53:28 -08:00
VOP1Instructions.td
AMDGPU: Copy SubtargetPredicate from pseudo to real for dpp16 and dpp8 (#84517)
2024-03-08 10:30:01 -08:00
VOP2Instructions.td
[AMDGPU][True16] Make NotHasTrue16BitInsts a True16Predicate (#84771)
2024-03-11 13:58:45 -04:00
VOP3Instructions.td
[GlobalISel][AMDGPU] Import patterns with multiple defs (#84171)
2024-03-08 09:39:10 +01:00
VOP3PInstructions.td
[AMDGPU] Replace isInlinableLiteral16 with specific version (#84402)
2024-03-08 14:49:52 -05:00
VOPCInstructions.td
[AMDGPU][True16] Make NotHasTrue16BitInsts a True16Predicate (#84771)
2024-03-11 13:58:45 -04:00
VOPDInstructions.td
[AMDGPU] Update VOP instructions for GFX12 (#74853)
2023-12-12 11:38:24 +01:00
VOPInstructions.td
AMDGPU: Copy SubtargetPredicate from pseudo to real for dpp16 and dpp8 (#84517)
2024-03-08 10:30:01 -08:00