Cold-Air-Networks/mirror-llvm-project
2
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 7
mirror-llvm-project/llvm/lib/Target/AMDGPU
History
K.Roy c27bee245f
[AMDGPU] Generalize MFMA VGPR->AGPR opcode mapping (NFC) (#213274) 
Move the VGPR/AGPR pairing out of MFMATable into a generalized
AGPRFormTable class and rename getMFMASrcCVDstAGPROp to getAGPRFormOp.
MFMATable inherits AGPRFormTable, so the instantiation sites and the
generated table are unchanged.

Other instruction families with paired VGPR/AGPR pseudos, such as DS,
can now be tagged with AGPRFormTable.

Related to #168983
2026-08-01 06:15:50 +00:00
..
AsmParser [AMDGPU] Duplicate packed fp32 instructions (#212857) 2026-07-30 16:29:41 -07:00
Disassembler AMDGPU: Introduce amdgpu triple arch (#206480) 2026-07-09 13:43:41 +02:00
MCA AMDGPU: Introduce amdgpu triple arch (#206480) 2026-07-09 13:43:41 +02:00
MCTargetDesc AMDGPU: Handle more TargetParser queries in tablegen (#212357) 2026-07-30 06:58:20 +02:00
TargetInfo AMDGPU: Introduce amdgpu triple arch (#206480) 2026-07-09 13:43:41 +02:00
Utils [AMDGPU] Duplicate packed fp32 instructions (#212857) 2026-07-30 16:29:41 -07:00
AMDGPU.h [NPM] Make few more passes required (#203511) 2026-07-14 14:39:20 +05:30
AMDGPU.td AMDGPU: Separate image_msaa_load from bvh-ray-tracing-insts (#213270) 2026-07-31 19:35:56 +00:00
AMDGPUAliasAnalysis.cpp
AMDGPUAliasAnalysis.h
AMDGPUAlwaysInlinePass.cpp [AMDGPU] Make use of getFunction and getMF. NFC. (#167872) 2025-11-14 11:00:57 +00:00
AMDGPUAnnotateUniformValues.cpp [Uniformity] Introduce isUniform/DivergentTerminator naming. NFC. (#204343) 2026-06-17 19:45:21 +01:00
AMDGPUArgumentUsageInfo.cpp [AMDGPU] Remove AMDGPUArgumentUsageInfo pass (#182490) 2026-02-23 18:47:01 +05:30
AMDGPUArgumentUsageInfo.h [CodeGen] Merge TargetRegClass into MCRegClass (#207168) 2026-07-03 07:52:57 +02:00
AMDGPUAsanInstrumentation.cpp [AMDGPU] Add ptr.s.buffer.load intrinsic, use it from Clang (#209243) 2026-07-30 09:27:28 -07:00
AMDGPUAsanInstrumentation.h
AMDGPUAsmPrinter.cpp AMDGPU: Add supports-wgp subtarget feature (#212704) 2026-07-30 05:53:00 +02:00
AMDGPUAsmPrinter.h [AMDGPU][NPM] Complete AsmPrinter support (#203509) 2026-07-06 10:33:10 +05:30
AMDGPUAtomicOptimizer.cpp [AMDGPU] Add threshold for DPP atomic optimizer on LDS atomics (#186762) 2026-07-14 17:41:27 +09:00
AMDGPUAttributes.def [AMDGPU] Change isSingleLaneExecution to account for WWM enabling lanes even if there's only one workitem (#188316) 2026-04-06 12:51:46 -04:00
AMDGPUAttributor.cpp [AMDGPU] Relocated getMaxNumWorkGroups function out of AMDGPUSubtarget (NFC) (#205636) 2026-06-30 09:49:27 +02:00
AMDGPUBarrierLatency.cpp AMDGPU: Replace tgsplit subtarget feature with attribute (#204216) 2026-07-07 13:38:05 +02:00
AMDGPUBarrierLatency.h [AMDGPU] Ignore wavefront barrier latency during scheduling DAG mutation (#168500) 2025-11-19 17:49:14 +09:00
AMDGPUCallingConv.td AMDGPU: Change ABI of 16-bit scalar values for gfx6/gfx7 (#175795) 2026-01-22 18:34:06 +00:00
AMDGPUCallLowering.cpp AMDGPU/GlobalISel: Fix cs_chain use of constrainOperandRegClass (#212248) 2026-07-27 16:40:03 +02:00
AMDGPUCallLowering.h [AMDGPU] Remove AMDGPUCallLowering dependency on AMDGPUTargetLowering. NFC. (#187008) 2026-03-17 12:38:25 +00:00
AMDGPUCodeGenPrepare.cpp AMDGPU: Fix creating temporary TTI in AMDGPUCodeGenPrepare (#209976) 2026-07-16 10:01:24 +02:00
AMDGPUCoExecSchedStrategy.cpp [AMDGPU] Classify VMEM as VMEM for CoExecSched (#203396) 2026-06-18 10:53:38 -07:00
AMDGPUCoExecSchedStrategy.h [AMDGPU] NFC: Drop constexpr from getFlavor*Name functions (#203603) 2026-06-12 20:08:15 +00:00
AMDGPUCombine.td [AMDGPU] SDAG and GISel support for folding fabs into fp_round source modifiers (#204861) 2026-07-08 08:54:29 -07:00
AMDGPUCombinerHelper.cpp AMDGPU/GlobalISel: Use extended LLTs in AMDGPUCombinerHelper (#210102) 2026-07-20 15:06:40 +02:00
AMDGPUCombinerHelper.h [AMDGPU] SDAG and GISel support for folding fabs into fp_round source modifiers (#204861) 2026-07-08 08:54:29 -07:00
AMDGPUCtorDtorLowering.cpp [AMDGPUCtorDtorLowering] Remove unnecessary pointer arithmetic (#182869) 2026-02-23 17:04:49 +01:00
AMDGPUCtorDtorLowering.h [PassManager] Make passes inherit from RequiredPassInfoMixin/OptionalPassInfoMixin (#192120) 2026-05-06 10:00:07 -07:00
AMDGPUExportClustering.cpp
AMDGPUExportClustering.h
AMDGPUExportKernelRuntimeHandles.cpp
AMDGPUExportKernelRuntimeHandles.h [PassManager] Make passes inherit from RequiredPassInfoMixin/OptionalPassInfoMixin (#192120) 2026-05-06 10:00:07 -07:00
AMDGPUFeatures.td AMDGPU: Add dedicated features for wavesize support (#212581) 2026-07-28 19:23:18 +00:00
AMDGPUFrameLowering.cpp
AMDGPUFrameLowering.h
AMDGPUGenRegisterBankInfo.def
AMDGPUGISel.td [SelectionDAG][GlobalISel] Move to_tframeindex & renderFrameIndex from targets into common code. (#210896) 2026-07-21 11:30:12 -07:00
AMDGPUGlobalISelDivergenceLowering.cpp [CycleInfo] Represent cycles by an opaque handle. NFC (#210117) 2026-07-17 00:34:28 -07:00
AMDGPUGlobalISelUtils.cpp AMDGPU/GlobalISel: Use integers for read-any-lane split type (#210098) 2026-07-20 14:47:46 +02:00
AMDGPUGlobalISelUtils.h
AMDGPUHazardLatency.cpp [AMDGPU] NFC: Obviously show isVALU includes LDSDMA instructions (#203548) 2026-06-16 13:14:08 -07:00
AMDGPUHazardLatency.h [AMDGPU] Add scheduling DAG mutation for hazard latencies (#170075) 2026-02-03 11:10:28 +09:00
AMDGPUHSAMetadataStreamer.cpp AMDGPU: Add supports-wgp subtarget feature (#212704) 2026-07-30 05:53:00 +02:00
AMDGPUHSAMetadataStreamer.h AMDGPU: Rename AMDGPUTargetID to TargetID (#205269) 2026-06-23 11:13:33 +00:00
AMDGPUHWEvents.cpp [AMDGPU] Handle expert scheduling VA_VDST WAR hazards (#201619) 2026-07-17 08:37:26 +00:00
AMDGPUHWEvents.def [AMDGPU] Handle expert scheduling VA_VDST WAR hazards (#201619) 2026-07-17 08:37:26 +00:00
AMDGPUHWEvents.h [AMDGPU] Handle expert scheduling VA_VDST WAR hazards (#201619) 2026-07-17 08:37:26 +00:00
AMDGPUIGroupLP.cpp [AMDGPU] [NFC] Init pointers, widen mask complements (#208469) 2026-07-10 00:45:59 +00:00
AMDGPUIGroupLP.h [NFC][AMDGPU]: expose IGLPStrategyID in AMDGPUIGroupLP.h (#191340) 2026-04-09 23:02:28 -07:00
AMDGPUImageIntrinsicOptimizer.cpp [AMDGPU] Fix ImageIntrinsicOptimizer DMask check starting at wrong arg index (#213264) 2026-07-31 21:42:30 +02:00
AMDGPUInsertDelayAlu.cpp [NFC][AMDGPU] Use SIInstrFlags predicates in CodeGen passes (#204829) 2026-06-30 15:27:25 +02:00
AMDGPUInstCombineIntrinsic.cpp [AMDGPU] Add ptr.s.buffer.load intrinsic, use it from Clang (#209243) 2026-07-30 09:27:28 -07:00
AMDGPUInstrInfo.cpp AMDGPU: Fix treating unknown mem operands as uniform (#170309) 2025-12-02 16:19:46 +00:00
AMDGPUInstrInfo.h [AMDGPU] Remove unused forward declaration 2026-03-19 13:15:18 +00:00
AMDGPUInstrInfo.td AMDGPU: Remove AMDGPUbfm (#203148) 2026-06-11 01:59:29 +00:00
AMDGPUInstructions.td [AMDGPU] Fix instruction size of LDS-DMA buffer loads (#211302) 2026-07-24 21:32:51 +02:00
AMDGPUInstructionSelector.cpp Revert "[AMDGPU] Fix llvm.amdgcn.ballot with return width != wavefront size" (#212628) 2026-07-28 15:30:31 -07:00
AMDGPUInstructionSelector.h [SelectionDAG][GlobalISel] Move to_tframeindex & renderFrameIndex from targets into common code. (#210896) 2026-07-21 11:30:12 -07:00
AMDGPUISelDAGToDAG.cpp DAG: Stop legalizing poison to undef (#211890) 2026-07-25 20:39:49 +02:00
AMDGPUISelDAGToDAG.h [AMDGPU] Remove stale declarations. NFC. (#205047) 2026-06-22 08:25:33 +00:00
AMDGPUISelLowering.cpp [AMDGPU] Flush denormal results when constant folding amdgcn.rcp (#203566) 2026-07-22 16:32:59 +02:00
AMDGPUISelLowering.h [AMDGPU] Avoid errors with 24-bit div/rem (#209711) 2026-07-15 10:12:47 -05:00
AMDGPULaneMaskUtils.h [AMDGPU] Waterfall loop codegen improvement in SIInstrInfo (#192415) 2026-06-22 15:00:01 +01:00
AMDGPULateCodeGenPrepare.cpp [AMDGPU] Fix bit-packing condition in LiveRegOptimizer (#201520) 2026-06-29 13:47:20 +02:00
AMDGPULegalizerInfo.cpp AMDGPU/GlobalISel: Switch more FP opcodes to extended LLTs (part 4) (#213353) 2026-07-31 17:18:03 -07:00
AMDGPULegalizerInfo.h [AMDGPU] Remove stale declarations. NFC. (#205047) 2026-06-22 08:25:33 +00:00
AMDGPULibCalls.cpp [AMDGPU] [NFC] Init pointers, widen mask complements (#208469) 2026-07-10 00:45:59 +00:00
AMDGPULibFunc.cpp AMDGPU: Try to fix leak in AMDGPULibFunc (#182583) 2026-02-20 15:07:19 -08:00
AMDGPULibFunc.h AMDGPU: Perform libcall recognition to replace fast OpenCL pow (#182135) 2026-02-19 11:49:32 +01:00
AMDGPULowerBufferFatPointers.cpp [LowerBufferFatPointers] Correctly handle alignment modes (#134329) 2026-07-06 11:38:46 -07:00
AMDGPULowerExecSync.cpp [NFC][AMDGPU] Generalize some LDS MemoryUtils (#195611) 2026-06-15 13:33:43 +02:00
AMDGPULowerIntrinsics.cpp [AMDGPU] Add ptr.s.buffer.load intrinsic, use it from Clang (#209243) 2026-07-30 09:27:28 -07:00
AMDGPULowerKernelArguments.cpp [AMDGPU] Do not copy noundef onto a widened kernarg load (#211181) 2026-07-22 09:54:11 +02:00
AMDGPULowerKernelAttributes.cpp [AMDGPU] Fix incorrect grid_dims constant folding for reqd_work_group_size (#211285) 2026-07-24 16:50:05 +02:00
AMDGPULowerModuleLDSPass.cpp [NFC][AMDGPU] Generalize some LDS MemoryUtils (#195611) 2026-06-15 13:33:43 +02:00
AMDGPULowerVGPREncoding.cpp [AMDGPU][CodeGen] Place S_NOP after S_SETREG_IMM32_B32 in predecessor MBB (#209620) 2026-07-15 17:25:28 +02:00
AMDGPULowerVGPREncoding.h [PassManager] Make passes inherit from RequiredPassInfoMixin/OptionalPassInfoMixin (#192120) 2026-05-06 10:00:07 -07:00
AMDGPUMachineFunctionInfo.cpp [AMDGPU] Rename AMDGPUMachineFunction to AMDGPUMachineFunctionInfo. NFC. (#187276) 2026-03-18 20:29:47 +00:00
AMDGPUMachineFunctionInfo.h [AMDGPU] Rename AMDGPUMachineFunction to AMDGPUMachineFunctionInfo. NFC. (#187276) 2026-03-18 20:29:47 +00:00
AMDGPUMachineModuleInfo.cpp
AMDGPUMachineModuleInfo.h [AMDGPU] Fix SSID merge in SIMemoryLegalizer to use smallest inclusiv… (#208300) 2026-07-13 08:23:26 -05:00
AMDGPUMacroFusion.cpp [MacroFusion] Add SDep param to predicates(NFC) (#212255) 2026-07-30 02:29:48 +03:00
AMDGPUMacroFusion.h
AMDGPUMarkLastScratchLoad.cpp Revert "[NFC][LiveStacks] Use vectors instead of map and unordred_map" (#180421) 2026-02-08 16:54:51 +00:00
AMDGPUMCInstLower.cpp [AMDGPU] Apply target flag specifier when lowering MO_ExternalSymbol operands (#202389) 2026-07-01 05:02:35 +02:00
AMDGPUMCInstLower.h [AMDGPU] Standardize on using AMDGPU::getNullPointerValue. NFC. (#187037) 2026-03-17 17:08:16 +00:00
AMDGPUMCResourceInfo.cpp Revert "[AMDGPU] Capping max number of registers to function's occupancy budget for indirect calls" (#204605) 2026-06-18 16:14:06 +02:00
AMDGPUMCResourceInfo.h [AMDGPU] Report only local per-function resource usage when object linking is enabled (#192594) 2026-04-20 16:49:59 +00:00
AMDGPUMemoryUtils.cpp [AMDGPU] Improve MemorySSA walking in isClobberedInFunction (#211817) 2026-07-29 15:14:49 +01:00
AMDGPUMemoryUtils.h [NFC][AMDGPU] Generalize some LDS MemoryUtils (#195611) 2026-06-15 13:33:43 +02:00
AMDGPUMIRFormatter.cpp [AMDGPU][MIRFormatter] S_WAIT_LOADCNT_DSCNT human-readable mask (#200059) 2026-05-29 09:13:03 -07:00
AMDGPUMIRFormatter.h [AMDGPU][MIRFormatter] S_WAIT_LOADCNT_DSCNT human-readable mask (#200059) 2026-05-29 09:13:03 -07:00
AMDGPUNextUseAnalysis.cpp [LoopInfo] Replace raw loop-container accessors with semantic operations (#210653) 2026-07-21 07:01:19 +00:00
AMDGPUNextUseAnalysis.h [PassManager] Make passes inherit from RequiredPassInfoMixin/OptionalPassInfoMixin (#192120) 2026-05-06 10:00:07 -07:00
AMDGPUPassRegistry.def AMDGPU: Prefer getting the triple from the module over the TargetMachine (#206055) 2026-06-26 15:04:22 +00:00
AMDGPUPerfHintAnalysis.cpp
AMDGPUPerfHintAnalysis.h [PassManager] Make passes inherit from RequiredPassInfoMixin/OptionalPassInfoMixin (#192120) 2026-05-06 10:00:07 -07:00
AMDGPUPostLegalizerCombiner.cpp Remove analysis preservations subsumed by CFG preservation. NFC (#212672) 2026-07-28 21:47:19 -07:00
AMDGPUPredicateControl.td
AMDGPUPreLegalizerCombiner.cpp Remove analysis preservations subsumed by CFG preservation. NFC (#212672) 2026-07-28 21:47:19 -07:00
AMDGPUPreloadKernArgProlog.cpp [AMDGPU] Fix backward compatibility kernarg preload prolog base offset (#201355) 2026-06-03 18:21:14 +02:00
AMDGPUPreloadKernArgProlog.h [PassManager] Make passes inherit from RequiredPassInfoMixin/OptionalPassInfoMixin (#192120) 2026-05-06 10:00:07 -07:00
AMDGPUPreloadKernelArguments.cpp [AMDGPU] Make use of getFunction and getMF. NFC. (#167872) 2025-11-14 11:00:57 +00:00
AMDGPUPrepareAGPRAlloc.cpp [NFC][AMDGPU] Remove pass initialization from pass constructors (#180149) 2026-02-06 09:05:14 -08:00
AMDGPUPrepareAGPRAlloc.h [PassManager] Make passes inherit from RequiredPassInfoMixin/OptionalPassInfoMixin (#192120) 2026-05-06 10:00:07 -07:00
AMDGPUPrintfRuntimeBinding.cpp [AMDGPU] Fix printf %s buffer slot oversized when strlen % 4 == 0 (#207772) 2026-07-06 19:28:24 +02:00
AMDGPUPromoteAlloca.cpp AMDGPU: Initialize Module fields in AMDGPUPromoteAllocaImpl (#206052) 2026-06-26 16:19:04 +02:00
AMDGPUPromoteKernelArguments.cpp [AMDGPU][NFC] Document flat-to-global promotion assumption in AMDGPUP… (#212590) 2026-07-28 15:33:12 -05:00
AMDGPUPTNote.h
AMDGPURegBankCombiner.cpp Remove analysis preservations subsumed by CFG preservation. NFC (#212672) 2026-07-28 21:47:19 -07:00
AMDGPURegBankLegalize.cpp AMDGPU/GlobalISel: Implement G_GET/SET_ROUNDING (#205265) 2026-06-24 08:34:40 -07:00
AMDGPURegBankLegalizeHelper.cpp [AMDGPU] Add ptr.s.buffer.load intrinsic, use it from Clang (#209243) 2026-07-30 09:27:28 -07:00
AMDGPURegBankLegalizeHelper.h AMDGPU/GlobalISel: Switch RegBankLegalize lowering to extended LLTs (#208270) 2026-07-10 17:54:18 +02:00
AMDGPURegBankLegalizeRules.cpp AMDGPU/GlobalISel: RegBankLegalize G_ANYEXT s16 to s64 (#205470) 2026-07-23 08:28:16 -07:00
AMDGPURegBankLegalizeRules.h AMDGPU/GlobalISel: Implement G_GET/SET_ROUNDING (#205265) 2026-06-24 08:34:40 -07:00
AMDGPURegBankSelect.cpp [UniformityAnalysis] Rename public api's in UA (NFC) (#196251) 2026-05-12 18:38:05 +05:30
AMDGPURegisterBankInfo.cpp [AMDGPU] Rename packed 64-bit features to include SingleSGPR. NFCI. (#212891) 2026-07-30 19:10:47 -07:00
AMDGPURegisterBankInfo.h
AMDGPURegisterBanks.td AMDGPU: Start using RegClassByHwMode for wavesize operands 2025-11-11 15:07:59 -08:00
AMDGPURemoveIncompatibleFunctions.cpp AMDGPU: Add dedicated features for wavesize support (#212581) 2026-07-28 19:23:18 +00:00
AMDGPURemoveIncompatibleFunctions.h [PassManager] Make passes inherit from RequiredPassInfoMixin/OptionalPassInfoMixin (#192120) 2026-05-06 10:00:07 -07:00
AMDGPUReserveWWMRegs.cpp
AMDGPUReserveWWMRegs.h [PassManager] Make passes inherit from RequiredPassInfoMixin/OptionalPassInfoMixin (#192120) 2026-05-06 10:00:07 -07:00
AMDGPUResourceUsageAnalysis.cpp [AMDGPU] Do not propagate vgpr count in dVGPR mode (#187078) 2026-06-02 15:38:57 +02:00
AMDGPUResourceUsageAnalysis.h [AMDGPU] Do not propagate vgpr count in dVGPR mode (#187078) 2026-06-02 15:38:57 +02:00
AMDGPURewriteAGPRCopyMFMA.cpp [AMDGPU] Generalize MFMA VGPR->AGPR opcode mapping (NFC) (#213274) 2026-08-01 06:15:50 +00:00
AMDGPURewriteOutArguments.cpp [AMDGPU] Employ MemorySSA when rewriting out arguments (NFCI) (#207922) 2026-07-10 09:55:33 +02:00
AMDGPURewriteUndefForPHI.cpp Remove analysis preservations subsumed by CFG preservation. NFC (#212672) 2026-07-28 21:47:19 -07:00
AMDGPUSearchableTables.td [AMDGPU] Fix GISel lowering for amdgcn_s_quadmask, amdgcn_s_wqm (#202704) 2026-06-09 13:44:28 -07:00
AMDGPUSelectionDAGInfo.cpp [AMDGPU] Fix type of SIlds / AMDGPUISD::LDS node (#210340) 2026-07-17 14:29:10 +00:00
AMDGPUSelectionDAGInfo.h [AMDGPU] Disable generic DAG combines at -O0 to preserve debuggability. (#176304) 2026-04-01 11:55:17 +02:00
AMDGPUSetWavePriority.cpp [AMDGPU] NFC: Obviously show isVALU includes LDSDMA instructions (#203548) 2026-06-16 13:14:08 -07:00
AMDGPUSplitModule.cpp [NFC] Move TimePasses globals from Pass.h to PassTimingInfo.h (#192352) 2026-04-15 22:58:20 +00:00
AMDGPUSplitModule.h [PassManager] Make passes inherit from RequiredPassInfoMixin/OptionalPassInfoMixin (#192120) 2026-05-06 10:00:07 -07:00
AMDGPUSubtarget.cpp Revert "[AMDGPU] Use wavefront scope for single-wave workgroup synchronization (#187673)" (#208280) 2026-07-08 20:42:04 +00:00
AMDGPUSubtarget.h Revert "[AMDGPU] Use wavefront scope for single-wave workgroup synchronization (#187673)" (#208280) 2026-07-08 20:42:04 +00:00
AMDGPUSwLowerLDS.cpp [IR][NFC] Add LoadStoreProperties to copy load/store attrs (#206470) 2026-07-08 19:06:50 +08:00
AMDGPUTargetMachine.cpp [AMDGPU][NewPM] Run UniformityInfoAnalysis inside AMDGPUISelDAGToDAGPass (#211174) 2026-07-22 15:09:02 +08:00
AMDGPUTargetMachine.h AMDGPU: Use module flags to control xnack and sramecc (#204595) 2026-07-21 14:38:39 +02:00
AMDGPUTargetObjectFile.cpp
AMDGPUTargetObjectFile.h
AMDGPUTargetParser.td AMDGPU: TableGen subarch to major subarch table (#212605) 2026-07-30 05:42:12 +00:00
AMDGPUTargetTransformInfo.cpp [AMDGPU] Rename packed 64-bit features to include SingleSGPR. NFCI. (#212891) 2026-07-30 19:10:47 -07:00
AMDGPUTargetTransformInfo.h [AMDGPU] Using feature to define vmem cacheline size (#207884) 2026-07-23 14:54:09 +08:00
AMDGPUUniformIntrinsicCombine.cpp [UniformityAnalysis] Rename public api's in UA (NFC) (#196251) 2026-05-12 18:38:05 +05:30
AMDGPUUnifyDivergentExitNodes.cpp [Uniformity] Introduce isUniform/DivergentTerminator naming. NFC. (#204343) 2026-06-17 19:45:21 +01:00
AMDGPUUnifyDivergentExitNodes.h [NPM] Make few more passes required (#203511) 2026-07-14 14:39:20 +05:30
AMDGPUWaitcntUtils.cpp [AMDGPU] Handle expert scheduling VA_VDST WAR hazards (#201619) 2026-07-17 08:37:26 +00:00
AMDGPUWaitcntUtils.h [AMDGPU] Handle expert scheduling VA_VDST WAR hazards (#201619) 2026-07-17 08:37:26 +00:00
AMDGPUWaitSGPRHazards.cpp [AMDGPU] Refactor GFX11 VALU Mask Hazard Waitcnt Merging (#169213) 2026-07-17 14:23:03 +09:00
AMDGPUWaitSGPRHazards.h [NPM] Make few more passes required (#203511) 2026-07-14 14:39:20 +05:30
AMDKernelCodeT.h
BUFInstructions.td [AMDGPU] Support i16 element types for tbuffer D16 load/store (#201420) 2026-07-22 19:11:16 +02:00
CaymanInstructions.td
CMakeLists.txt AMDGPU/GlobalISel: Switch to extended LLTs (#207419) 2026-07-10 14:40:51 +02:00
DSDIRInstructions.td [AMDGPU] Add VDSDIR encoding to gfx13 (#181620) 2026-02-17 09:25:14 +01:00
DSInstructions.td [AMDGPU] Support atomic load and store for vector float types (v2f16, v2i16, v4i16, v4f16, v2f32) (#192904) 2026-05-09 11:18:13 +08:00
EvergreenInstructions.td AMDGPU: Remove AMDGPUbfm (#203148) 2026-06-11 01:59:29 +00:00
EXPInstructions.td [AMDGPU] Add VEXPORT encoding for gfx13 (#181788) 2026-02-19 08:46:50 +01:00
FLATInstructions.td [AMDGPU] Add gfx13 support for global_load_async_to_lds (#211248) 2026-07-23 08:49:39 +02:00
GCNCreateVOPD.cpp [AMDGPU] Rework VOPD constraints for gfx12+ with data deps (#191264) 2026-05-06 19:25:58 +00:00
GCNDPPCombine.cpp Remove analysis preservations subsumed by CFG preservation. NFC (#212672) 2026-07-28 21:47:19 -07:00
GCNDPPCombine.h [PassManager] Make passes inherit from RequiredPassInfoMixin/OptionalPassInfoMixin (#192120) 2026-05-06 10:00:07 -07:00
GCNHazardRecognizer.cpp [AMDGPU] Fix gfx1250 WMMA latencies (#202522) 2026-07-23 22:02:06 -07:00
GCNHazardRecognizer.h [AMDGPU] Fix checkVALUHazardsHelper distance accounting on branchy CFG (#203770) 2026-06-17 10:27:30 -04:00
GCNILPSched.cpp
GCNIterativeScheduler.cpp [AMDGPU] Preserve liveness flags in ILP scheduler (#211190) 2026-07-23 09:56:00 +02:00
GCNIterativeScheduler.h [AMDGPU] Preserve liveness flags in ILP scheduler (#211190) 2026-07-23 09:56:00 +02:00
GCNMinRegStrategy.cpp
GCNNSAReassign.cpp [NFC][AMDGPU] Remove pass initialization from pass constructors (#180149) 2026-02-06 09:05:14 -08:00
GCNNSAReassign.h [NPM] Make few more passes required (#203511) 2026-07-14 14:39:20 +05:30
GCNPreRALongBranchReg.cpp [NFC][AMDGPU] Remove pass initialization from pass constructors (#180149) 2026-02-06 09:05:14 -08:00
GCNPreRALongBranchReg.h [NPM] Make few more passes required (#203511) 2026-07-14 14:39:20 +05:30
GCNPreRAOptimizations.cpp [CodeGen] Merge TargetRegClass into MCRegClass (#207168) 2026-07-03 07:52:57 +02:00
GCNPreRAOptimizations.h [PassManager] Make passes inherit from RequiredPassInfoMixin/OptionalPassInfoMixin (#192120) 2026-05-06 10:00:07 -07:00
GCNProcessors.td AMDGPU: TableGen subarch to major subarch table (#212605) 2026-07-30 05:42:12 +00:00
GCNRegPressure.cpp [AMDGPU] Fix register pressure estimates for use-and-redefs (#211139) 2026-07-24 12:42:48 +02:00
GCNRegPressure.h [AMDGPU] Coverity fixes - check ret val and init class members (#198570) 2026-05-21 12:20:41 +01:00
GCNRewritePartialRegUses.cpp [NFC][CodeGen] Add helper function to check SubReg validity (#181489) 2026-02-19 12:39:11 -08:00
GCNRewritePartialRegUses.h [NPM] Make few more passes required (#203511) 2026-07-14 14:39:20 +05:30
GCNSchedStrategy.cpp [AMDGPU] Generalize MFMA VGPR->AGPR opcode mapping (NFC) (#213274) 2026-08-01 06:15:50 +00:00
GCNSchedStrategy.h [AMDGPU] Fix illegal AGPR reclassification in RewriteMFMAFormStage (#200972) 2026-06-12 16:14:52 +02:00
GCNSubtarget.cpp AMDGPU: Use module flags to control xnack and sramecc (#204595) 2026-07-21 14:38:39 +02:00
GCNSubtarget.h [AMDGPU] Rename packed 64-bit features to include SingleSGPR. NFCI. (#212891) 2026-07-30 19:10:47 -07:00
GCNVOPDUtils.cpp [MacroFusion] Add SDep param to predicates(NFC) (#212255) 2026-07-30 02:29:48 +03:00
GCNVOPDUtils.h [AMDGPU] Rework VOPD constraints for gfx12+ with data deps (#191264) 2026-05-06 19:25:58 +00:00
MIMGInstructions.td AMDGPU: Separate image_msaa_load from bvh-ray-tracing-insts (#213270) 2026-07-31 19:35:56 +00:00
R600.h
R600.td CodeGen: Make all targets override pseudos with pointers (#159881) 2025-11-26 14:57:14 +00:00
R600AsmPrinter.cpp
R600AsmPrinter.h
R600ClauseMergePass.cpp
R600ControlFlowFinalizer.cpp [NFCI][AMDGPU] Use GET_SUBTARGETINFO_MACRO in GCNSubtarget.h and R600Subtarget.h (#177402) 2026-01-25 09:38:42 -05:00
R600Defines.h
R600EmitClauseMarkers.cpp
R600ExpandSpecialInstrs.cpp
R600FrameLowering.cpp
R600FrameLowering.h
R600InstrFormats.td
R600InstrInfo.cpp [AMDGPU] Make use of getFunction and getMF. NFC. (#167872) 2025-11-14 11:00:57 +00:00
R600InstrInfo.h [TableGen] Return int32_t from InstrMapping table lookup functions. NFC. (#182079) 2026-02-18 18:49:58 +00:00
R600InstrInfo.td
R600Instructions.td [AMDGPU] Use FPImmLeaf for float constants, fix build_vector patterns (#178018) 2026-01-28 10:51:42 +01:00
R600ISelDAGToDAG.cpp
R600ISelLowering.cpp DAG: Use poison in getLoad/getStore for offsets (#212066) 2026-07-31 06:33:58 +02:00
R600ISelLowering.h [AMDGPU] Remove stale declarations. NFC. (#205047) 2026-06-22 08:25:33 +00:00
R600MachineCFGStructurizer.cpp [AMDGPU] Use empty() instead of size() comparisons. NFC. (#187424) 2026-03-19 16:08:56 +00:00
R600MachineFunctionInfo.cpp [AMDGPU] Rename AMDGPUMachineFunction to AMDGPUMachineFunctionInfo. NFC. (#187276) 2026-03-18 20:29:47 +00:00
R600MachineFunctionInfo.h [AMDGPU] Rename AMDGPUMachineFunction to AMDGPUMachineFunctionInfo. NFC. (#187276) 2026-03-18 20:29:47 +00:00
R600MachineScheduler.cpp
R600MachineScheduler.h
R600MCInstLower.cpp [AMDGPU] Standardize on using AMDGPU::getNullPointerValue. NFC. (#187037) 2026-03-17 17:08:16 +00:00
R600OpenCLImageTypeLoweringPass.cpp
R600OptimizeVectorRegisters.cpp [CodeGen] Stop requiring analyses that no pass reads (#212430) 2026-07-28 18:04:48 +00:00
R600Packetizer.cpp [CodeGen] Stop requiring analyses that no pass reads (#212430) 2026-07-28 18:04:48 +00:00
R600Processors.td AMDGPU: Split R600 feature bitmask into separate enum from amdgcn (#212484) 2026-07-28 19:52:26 +02:00
R600RegisterInfo.cpp
R600RegisterInfo.h
R600RegisterInfo.td
R600Schedule.td
R600Subtarget.cpp [AMDGPU] Remove FeaturePromoteAlloca (#177636) 2026-02-23 15:24:57 -05:00
R600Subtarget.h [AMDGPU][NFCI] Change MCSubtargetInfo references in AMDGPUBaseInfo.h/.cpp to be const ref instead of pointers (#197038) 2026-05-19 09:48:59 -05:00
R600TargetMachine.cpp [Target] Remove Target::resetTargetOptions (#201825) 2026-06-06 14:40:42 +08:00
R600TargetMachine.h [AsmPrinter] Use AsmPrinterAnalysis to hold AsmPrinter 2026-04-11 10:35:07 -07:00
R600TargetTransformInfo.cpp [AArch64] Increase the max interleave factor to 4 for loops with reductions (#205612) 2026-06-26 14:54:41 +00:00
R600TargetTransformInfo.h [AArch64] Increase the max interleave factor to 4 for loops with reductions (#205612) 2026-06-26 14:54:41 +00:00
R700Instructions.td
SIAnnotateControlFlow.cpp [Uniformity] Introduce isUniform/DivergentTerminator naming. NFC. (#204343) 2026-06-17 19:45:21 +01:00
SIDefines.h [NFC][AMDGPU] Use SIInstrFlags predicates in SIMemoryLegalizer and AMDGPUBaseInfo. (#209821) 2026-07-20 12:02:03 +02:00
SIFixSGPRCopies.cpp Remove analysis preservations subsumed by CFG preservation. NFC (#212672) 2026-07-28 21:47:19 -07:00
SIFixSGPRCopies.h [NPM] Make few more passes required (#203511) 2026-07-14 14:39:20 +05:30
SIFixVGPRCopies.cpp [NFC][AMDGPU] Remove pass initialization from pass constructors (#180149) 2026-02-06 09:05:14 -08:00
SIFixVGPRCopies.h [NPM] Make few more passes required (#203511) 2026-07-14 14:39:20 +05:30
SIFoldOperands.cpp Remove analysis preservations subsumed by CFG preservation. NFC (#212672) 2026-07-28 21:47:19 -07:00
SIFoldOperands.h [PassManager] Make passes inherit from RequiredPassInfoMixin/OptionalPassInfoMixin (#192120) 2026-05-06 10:00:07 -07:00
SIFormMemoryClauses.cpp [AMDGPU] Fix inconsistencies in RP tracking advance/reset behavior (#196595) 2026-05-11 19:29:40 +02:00
SIFormMemoryClauses.h [PassManager] Make passes inherit from RequiredPassInfoMixin/OptionalPassInfoMixin (#192120) 2026-05-06 10:00:07 -07:00
SIFrameLowering.cpp [AMDGPU] Fix CFI emission when scratch instructions are used to spill (#209534) 2026-07-14 16:24:30 -04:00
SIFrameLowering.h [AMDGPU] Implement CFI for CSR spills (#183150) 2026-05-27 15:15:24 -04:00
SIInsertHardClauses.cpp [AMDGPU] Don't allow nesting hard clauses. (#188460) 2026-03-26 11:47:35 +01:00
SIInsertWaitcnts.cpp [AMDGPU] SIInsertWaitcnts: rebase async marks into the merged frame at CFG joins (#211688) 2026-07-30 09:01:16 -07:00
SIInstrFormats.td
SIInstrInfo.cpp [AMDGPU] Duplicate packed fp32 instructions (#212857) 2026-07-30 16:29:41 -07:00
SIInstrInfo.h [AMDGPU] Generalize MFMA VGPR->AGPR opcode mapping (NFC) (#213274) 2026-08-01 06:15:50 +00:00
SIInstrInfo.td [AMDGPU] Generalize MFMA VGPR->AGPR opcode mapping (NFC) (#213274) 2026-08-01 06:15:50 +00:00
SIInstructions.td [AMDGPU] Rename packed 64-bit features to include SingleSGPR. NFCI. (#212891) 2026-07-30 19:10:47 -07:00
SIISelLowering.cpp [AMDGPU] Fix canonicalization of undef in v2f16 (#213373) 2026-07-31 19:34:21 -05:00
SIISelLowering.h [AMDGPU] Do not treat bitcast across FP types as canonicality-preserving (#203560) 2026-07-31 21:44:24 +02:00
SILateBranchLowering.cpp [AMDGPU] Teach SILateBranchLowering pass to preserve MachineLoopInfo (#178276) 2026-01-29 22:23:00 +05:30
SILoadStoreOptimizer.cpp Remove analysis preservations subsumed by CFG preservation. NFC (#212672) 2026-07-28 21:47:19 -07:00
SILoadStoreOptimizer.h [PassManager] Make passes inherit from RequiredPassInfoMixin/OptionalPassInfoMixin (#192120) 2026-05-06 10:00:07 -07:00
SILowerControlFlow.cpp [CodeGen] Add MachineRegisterClassInfo analysis pass (#210826) 2026-07-22 21:34:54 +02:00
SILowerControlFlow.h [NPM] Make few more passes required (#203511) 2026-07-14 14:39:20 +05:30
SILowerI1Copies.cpp [MachineSSAUpdater][AMDGPU] Add faster version of MachineSSAUpdater class. (#145722) 2026-04-24 13:25:51 +02:00
SILowerI1Copies.h [NFC][AMDGPU] Move PhiLoweringHelper and related types into AMDGPU namespace (#192586) 2026-04-20 14:06:42 +01:00
SILowerSGPRSpills.cpp [CycleInfo] Represent cycles by an opaque handle. NFC (#210117) 2026-07-17 00:34:28 -07:00
SILowerSGPRSpills.h [NPM] Make few more passes required (#203511) 2026-07-14 14:39:20 +05:30
SILowerWWMCopies.cpp [NFC][AMDGPU] Remove pass initialization from pass constructors (#180149) 2026-02-06 09:05:14 -08:00
SILowerWWMCopies.h [NPM] Make few more passes required (#203511) 2026-07-14 14:39:20 +05:30
SIMachineFunctionInfo.cpp [AMDGPU] Relocated getMaxNumWorkGroups function out of AMDGPUSubtarget (NFC) (#205636) 2026-06-30 09:49:27 +02:00
SIMachineFunctionInfo.h [CodeGen] Merge TargetRegClass into MCRegClass (#207168) 2026-07-03 07:52:57 +02:00
SIMachineScheduler.cpp [AMDGPU] Use empty() instead of size() comparisons. NFC. (#187424) 2026-03-19 16:08:56 +00:00
SIMachineScheduler.h [AMDGPU] Remove stale declarations. NFC. (#205047) 2026-06-22 08:25:33 +00:00
SIMemoryLegalizer.cpp [NFC][AMDGPU] Use SIInstrFlags predicates in SIMemoryLegalizer and AMDGPUBaseInfo. (#209821) 2026-07-20 12:02:03 +02:00
SIModeRegister.cpp AMDGPU: Add SALU support for llvm.fptrunc.round f32 to f16 (#203406) 2026-06-15 11:55:15 -07:00
SIModeRegisterDefaults.cpp [AMDGPU] Remove DX10_CLAMP and IEEE bits from gfx1170 (#182107) 2026-03-04 12:16:41 +01:00
SIModeRegisterDefaults.h
SIOptimizeExecMasking.cpp [AMDGPU] Waterfall loop codegen improvement in SIInstrInfo (#192415) 2026-06-22 15:00:01 +01:00
SIOptimizeExecMasking.h [PassManager] Make passes inherit from RequiredPassInfoMixin/OptionalPassInfoMixin (#192120) 2026-05-06 10:00:07 -07:00
SIOptimizeExecMaskingPreRA.cpp [NFC][AMDGPU] Remove pass initialization from pass constructors (#180149) 2026-02-06 09:05:14 -08:00
SIOptimizeExecMaskingPreRA.h [PassManager] Make passes inherit from RequiredPassInfoMixin/OptionalPassInfoMixin (#192120) 2026-05-06 10:00:07 -07:00
SIOptimizeVGPRLiveRange.cpp Remove analysis preservations subsumed by CFG preservation. NFC (#212672) 2026-07-28 21:47:19 -07:00
SIOptimizeVGPRLiveRange.h [PassManager] Make passes inherit from RequiredPassInfoMixin/OptionalPassInfoMixin (#192120) 2026-05-06 10:00:07 -07:00
SIPeepholeSDWA.cpp [AMDGPU] Re-fold masked hi16 pack into v_or_b32_sdwa (#210735) 2026-07-30 12:14:37 +02:00
SIPeepholeSDWA.h [PassManager] Make passes inherit from RequiredPassInfoMixin/OptionalPassInfoMixin (#192120) 2026-05-06 10:00:07 -07:00
SIPostRABundler.cpp [NFC][AMDGPU] Use SIInstrFlags predicates in CodeGen passes (#204829) 2026-06-30 15:27:25 +02:00
SIPostRABundler.h [PassManager] Make passes inherit from RequiredPassInfoMixin/OptionalPassInfoMixin (#192120) 2026-05-06 10:00:07 -07:00
SIPreAllocateWWMRegs.cpp [AMDGPU] Fix SIPreAllocateWWMRegs to reserve AV-class WWM defs (#211560) 2026-07-23 17:41:28 +02:00
SIPreAllocateWWMRegs.h [NPM] Make few more passes required (#203511) 2026-07-14 14:39:20 +05:30
SIPreEmitPeephole.cpp [AMDGPU] Duplicate packed fp32 instructions (#212857) 2026-07-30 16:29:41 -07:00
SIProgramInfo.cpp [AMDGPU] Fix typos SGRP and VGRP. NFC. (#212732) 2026-07-29 11:10:32 +00:00
SIProgramInfo.h Reland "[AMDGPU] Account for inline asm size in inst_pref_size calculation" (#197227) 2026-05-20 08:02:24 -05:00
SIRegisterInfo.cpp [AMDGPU] Fix S_ADD_I32 frame index folding emitting COPY with immediate (#212440) 2026-07-30 09:17:27 +05:30
SIRegisterInfo.h [CodeGen] Merge TargetRegClass into MCRegClass (#207168) 2026-07-03 07:52:57 +02:00
SIRegisterInfo.td [AMDGPU] Add gfx1251 V_PK_ADD/SUB_NC_U64 (#203607) 2026-06-12 13:06:19 -07:00
SISchedule.td [AMDGPU] Fix gfx1250 WMMA latencies (#202522) 2026-07-23 22:02:06 -07:00
SIShrinkInstructions.cpp Remove analysis preservations subsumed by CFG preservation. NFC (#212672) 2026-07-28 21:47:19 -07:00
SIShrinkInstructions.h [PassManager] Make passes inherit from RequiredPassInfoMixin/OptionalPassInfoMixin (#192120) 2026-05-06 10:00:07 -07:00
SISpillUtils.cpp [AMDGPU] Fix crash with dead frame indices in debug values (#183297) 2026-04-01 13:41:53 +01:00
SISpillUtils.h [AMDGPU] Fix crash with dead frame indices in debug values (#183297) 2026-04-01 13:41:53 +01:00
SIWholeQuadMode.cpp [AMDGPU] Change static NOP last terminator SI_DEMOTE_I1 to be replaced by S_BRANCH instead of assert (#204649) 2026-06-23 15:48:06 -04:00
SIWholeQuadMode.h [NPM] Make few more passes required (#203511) 2026-07-14 14:39:20 +05:30
SMInstructions.td [AMDGPU][GFX1250] Add cpol support for some prefetch instructions (#208368) 2026-07-09 09:19:37 -04:00
SOPInstructions.td [AMDGPU] Rename packed 64-bit features to include SingleSGPR. NFCI. (#212891) 2026-07-30 19:10:47 -07:00
VIInstrFormats.td
VINTERPInstructions.td [AMDGPU] Add VINTERP encoding to gfx13 (#182481) 2026-03-02 10:50:08 +01:00
VOP1Instructions.td [AMDGPU] Add custom lowering of llvm.convert.from.arbitrary.fp for FP8 (#194144) 2026-07-31 15:16:30 +02:00
VOP2Instructions.td [AMDGPU] Remove support for ADDC/ADDE/SUBC/SUBE DAG nodes (#205082) 2026-06-22 14:58:10 +01:00
VOP3Instructions.td AMDGPU: Give v_cvt_sr_pk_bf16_f32 its own subtarget feature (#213150) 2026-07-31 09:55:40 +00:00
VOP3PInstructions.td [AMDGPU] Generalize MFMA VGPR->AGPR opcode mapping (NFC) (#213274) 2026-08-01 06:15:50 +00:00
VOPCInstructions.td [AMDGPU] Mark VOPC_e64 instructions rematerializable (#186195) 2026-03-13 21:16:18 +00:00
VOPDInstructions.td [AMDGPU] Use sparse direct lookup table for VOPD eligibility (#206534) 2026-06-30 09:23:40 +01:00
VOPInstructions.td AMDGPU: Reland: Codegen for v_dual_dot2acc_f32_f16/bf16 from VOP3 (#196516) 2026-07-22 14:10:52 +02:00